CN118796603A - A machine nest cloud edge intelligent inspection and equipment status monitoring system and method - Google Patents

Abstract

The invention belongs to the technical field of intelligent inspection, and discloses a system and a method for intelligent inspection of a cloud edge of a machine nest and monitoring of equipment states, wherein a data acquisition module is used for transmitting data to an edge computing node through an Internet of things technology by installing various sensors on equipment; the edge processing module performs preliminary processing on the acquired data, and performs preliminary state judgment by using a lightweight machine learning model; the cloud analysis module is used for uploading the key data subjected to edge processing to a cloud server, and the cloud server is used for carrying out deep analysis on the data by utilizing a more complex artificial intelligent algorithm; the intelligent inspection module automatically generates an inspection task and a plan according to the equipment state analysis result; the state monitoring and alarming module monitors the state of the equipment in real time, and once abnormality is found, alarming information is immediately sent to related personnel through various communication means, so that the problem of the equipment is timely handled. The invention can effectively improve the efficiency and accuracy of equipment inspection and state monitoring.

Description

A machine nest cloud edge intelligent inspection and equipment status monitoring system and method

Technical Field

The present invention belongs to the field of intelligent inspection technology, and in particular relates to a machine nest cloud edge intelligent inspection and equipment status monitoring system and method.

Background Art

In traditional industrial environments, equipment inspection and status monitoring mainly rely on manual operation, which is not only inefficient but also easily affected by human factors, resulting in inaccuracy and timeliness of inspection results. In addition, with the development of industrial Internet of Things (IoT) technology, more and more equipment needs to be monitored in real time, and traditional manual inspection methods are difficult to meet the needs of large-scale and efficient monitoring. Therefore, how to use modern information technology to improve the automation level, accuracy and real-time performance of equipment inspection and status monitoring has become a technical problem that needs to be solved urgently.

Among existing technologies, the closest technology to the Machine Nest Cloud Edge Intelligent Inspection and Equipment Status Monitoring System is the traditional cloud computing-based equipment monitoring system. Such systems usually rely on sensors installed on the equipment to collect data, such as temperature, vibration and other information, and send this data to the cloud server through the network for processing and analysis. The cloud server is responsible for executing complex data analysis algorithms, such as fault detection, predictive maintenance, etc., and then feeding back the results to users or maintenance teams.

The technical problems existing in the prior art include:

1. Latency issue: Since all data needs to be transmitted to the cloud for processing, this will cause delays in data transmission and processing, especially when the network connection is poor or the data volume is large. For application scenarios that require real-time response, such as automated production lines or monitoring of critical infrastructure, this delay leads to an inability to respond to failures or abnormal situations in a timely manner, thereby increasing risks.

2. Data security and privacy: All device data needs to be uploaded to the cloud, which involves the transmission of sensitive information and increases the risk of data being intercepted or abused. In addition, this system is not ideal for some application scenarios that have strict requirements on data privacy, such as medical device monitoring.

3. Bandwidth and cost: Transmitting large amounts of data to the cloud requires high network bandwidth, especially when using sensors that collect data at high frequencies. This not only takes up a lot of network resources, but also leads to higher data transmission costs.

4. Dependence on network connection: Traditional cloud computing monitoring systems are highly dependent on stable network connections. In the case of unstable or disconnected network, the equipment monitoring and analysis functions will be completely ineffective, affecting the reliability and efficiency of the entire monitoring system.

In comparison, the Machine Nest Cloud Edge Intelligent Inspection and Equipment Status Monitoring System overcomes the above problems to a certain extent by introducing edge computing nodes to delegate data preprocessing and preliminary analysis tasks closer to the data source. Edge computing can reduce reliance on cloud processing, reduce latency, reduce data transmission volume and costs, and also improve the robustness of the system in unstable network conditions. However, how to balance the task allocation between edge computing and cloud computing, ensure the secure processing of data at edge nodes, and effectively manage edge computing resources are still key technical issues that need to be solved.

Summary of the invention

In response to the problems existing in the prior art, the present invention provides a machine nest cloud edge intelligent inspection and equipment status monitoring system and method.

The present invention is implemented as follows: a device status monitoring system based on sensor data acquisition and artificial intelligence analysis, including a data acquisition module, an edge processing module, a cloud analysis module, an intelligent inspection module, and a status monitoring and alarm module, wherein:

A data acquisition module, configured to collect operating status data of the device in real time through sensors;

An edge processing module is configured to receive data transmitted by the data acquisition module, perform data cleaning and feature extraction, and use a lightweight machine learning model to make a preliminary state judgment on the feature set;

The cloud analysis module is configured to receive key data transmitted by the edge processing module and use complex artificial intelligence algorithms to perform in-depth analysis to determine the final status of the device;

An intelligent inspection module is configured to automatically generate inspection tasks and plans based on the final status of the equipment and guide the inspection;

The status monitoring and alarm module is configured to monitor the status of the equipment in real time. Once an abnormal status is found, an alarm message is immediately sent to relevant personnel through communication means.

The present invention also provides a method for equipment status monitoring and alarming using artificial intelligence, comprising the following steps:

Collect equipment operation status data in real time through sensors;

In the edge processing module, the collected data is cleaned and features are extracted, and a lightweight machine learning model is used to make preliminary status judgments;

The extracted key feature data is transmitted to the cloud analysis module, and a complex artificial intelligence algorithm is used for in-depth analysis to obtain the final status of the device;

Automatically generate inspection tasks and plans based on the final status of the equipment, and guide the inspection;

At the same time, the equipment status is monitored in real time. Once an abnormality is found, an alarm message is immediately sent to relevant personnel through the preset communication means;

In addition, the system can continuously optimize and iterate based on actual operating conditions and user feedback to improve system performance.

Furthermore, the specific algorithm implementation of the edge processing module and the cloud analysis module is as follows:

1. The edge processing module uses a data cleaning function (f_{clean}(D)＝D'＝{d'_1,d'_2,...,d'_n}), where (d'_i＝d_i) if (d_i) is within a predetermined normal range, otherwise (d'_i) is corrected by interpolation or other methods;

2. Feature extraction function (f_{feature}(D')＝F＝{f_1,f_2,...,f_m}), where (f_j) is the (j)th feature extracted from the data (D'), which can be obtained by spectrum analysis, time domain analysis, etc.

3. The lightweight machine learning model (M_{edge}) on the edge computing node can be a decision tree, support vector machine or shallow neural network, and its training process (T_{edge}) is based on the labeled feature set (F_{label}) and the corresponding state label (S_{label}), that is, (M_{edge}＝T_{edge}(F_{label},S_{label}));

4. The complex artificial intelligence algorithm (M_{cloud}) of the cloud analysis module can be a deep neural network, an ensemble learning model, or other advanced machine learning models. Its training process (T_{cloud}) uses

A large-scale dataset (F_{large}) and state labels (S_{large}) of devices and time periods, i.e. (M_{cloud}＝T_{cloud}(F_{large},S_{large}));

5. The status monitoring and alarm module defines the abnormal status judgment logic (S_{abnormal}＝{s|s in S_{final},snotin S_{normal}}), where (S_{normal}) is determined by the equipment operation history data and expert knowledge.

The present invention also provides a machine nest cloud edge intelligent inspection and equipment status monitoring system, the system comprising:

The data acquisition module collects real-time data on the equipment's operating status, such as temperature, vibration, and sound, by installing various sensors on the equipment, and transmits the data to the edge computing node through the Internet of Things technology;

The edge processing module is connected to the data acquisition module. The edge computing node performs preliminary processing on the collected data, such as data cleaning and feature extraction, and uses a lightweight machine learning model to make preliminary status judgments to reduce data transmission volume and improve response speed.

The cloud analysis module is connected to the edge processing module to upload the key data processed by the edge to the cloud server. The cloud server uses more complex artificial intelligence algorithms to conduct in-depth analysis of the data to achieve accurate judgment and prediction of the device status;

The intelligent inspection module is connected to the cloud analysis module. The system automatically generates inspection tasks and plans based on the equipment status analysis results, and guides inspection personnel or automated robots to conduct targeted inspections;

The status monitoring and alarm module is connected to the intelligent inspection module. The system monitors the equipment status in real time. Once an abnormality is found, it immediately sends an alarm message to relevant personnel through various communication methods (such as SMS, email, APP push, etc.) to ensure that equipment problems are handled in a timely manner.

Furthermore, the data acquisition module includes:

Sensor deployment unit: deploys various types of sensors on key equipment, such as temperature sensors, vibration sensors, sound sensors, etc., to monitor various operating parameters of the equipment in real time;

Data acquisition unit: The sensor collects the operating status data of the equipment in real time, and pre-processes the data through the data acquisition module on the equipment, such as formatting and standardization;

Data transmission unit: The collected data is securely transmitted to the nearest edge computing node through IoT technologies (such as WiFi, cellular network, LoRa, etc.).

Furthermore, the edge processing module specifically includes:

Data preprocessing unit: After receiving the data, the edge computing node performs further preprocessing, including data cleaning (noise removal, outlier processing), feature extraction (converting to a format recognizable by the machine learning model), etc.

The preliminary analysis unit uses a lightweight machine learning model deployed on the edge node to perform preliminary analysis on the preprocessed data and quickly identify signs of equipment anomalies or failures;

Response and feedback unit, based on the preliminary analysis results, the edge node can make some immediate responses, such as adjusting device parameters, issuing local alarms, etc., and uploading key data or abnormal reports to the cloud server.

Furthermore, the cloud analysis module specifically includes:

Data aggregation and storage unit: The cloud server receives data from multiple edge nodes, aggregates and stores them for a long time, and builds a device history database;

Deep analysis unit: Uses complex artificial intelligence algorithms (such as deep learning, time series analysis, etc.) to conduct in-depth analysis of aggregated data, accurately determine the status of equipment, and predict future problems;

Inspection plan generation unit: Based on the in-depth analysis results, the system automatically generates inspection tasks and plans, including inspection time, key inspection items, etc.

Furthermore, the intelligent inspection module specifically includes:

Task allocation unit: The system allocates inspection tasks and plans to inspection personnel or automated robots, guiding them to conduct targeted inspections;

Inspection execution unit: Inspection personnel or robots perform inspection tasks according to the plan provided by the system and use mobile devices or special tools to collect equipment status data;

Result feedback unit: Inspection results are fed back to the central monitoring system through mobile devices or automation systems to update equipment status and optimize subsequent inspection plans.

Furthermore, the status monitoring and alarm module specifically includes:

Real-time monitoring unit: The system monitors the status of all devices in real time and uses dashboards and visualization tools to display the operation of the devices;

Anomaly detection unit: The system analyzes equipment data in real time and immediately triggers an alarm mechanism once anomalies or signs of failure are detected;

Alarm notification unit: The system sends alarm information to maintenance personnel, management personnel and relevant responsible persons through various communication methods such as SMS, email, APP push, etc. to ensure that equipment problems are responded to and handled in a timely manner.

Another object of the present invention is to provide a method for implementing the machine nest cloud edge intelligent inspection and equipment status monitoring system, the method comprising:

S1: Using the data acquisition module, various sensors are installed on the equipment to collect real-time equipment operation status data, such as temperature, vibration, sound, etc., and transmit the data to the edge computing node through the Internet of Things technology; using the edge processing module, the edge computing node performs preliminary processing on the collected data, such as data cleaning and feature extraction, and uses a lightweight machine learning model to make preliminary status judgments to reduce the amount of data transmission and improve the response speed;

S2: Using the cloud analysis module, the key data processed by the edge is uploaded to the cloud server. The cloud server uses more complex artificial intelligence algorithms to conduct in-depth analysis of the data to accurately judge and predict the status of the equipment. Using the intelligent inspection module, according to the equipment status analysis results, it automatically generates inspection tasks and plans to guide inspection personnel or automated robots to conduct targeted inspections.

S3: Use the status monitoring and alarm module to monitor the equipment status in real time. Once an abnormality is found, immediately send an alarm message to relevant personnel through various communication methods (such as SMS, email, APP push, etc.) to ensure that the equipment problem is handled in a timely manner.

Another object of the present invention is to provide a computer device, which includes a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the machine nest cloud edge intelligent inspection and equipment status monitoring method.

Another object of the present invention is to provide a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, the processor executes the steps of the machine-nest cloud-edge intelligent inspection and equipment status monitoring method.

Another object of the present invention is to provide an information data processing terminal, which is used to implement the machine nest cloud edge intelligent inspection and equipment status monitoring system.

Another object of the present invention is to provide an intelligent inspection and equipment status monitoring system for drone nests, the system comprising:

The present invention relates to an intelligent inspection and equipment status monitoring system applied to a drone nest, which is composed of a plurality of key modules to realize efficient status monitoring, intelligent inspection and timely alarm of the drone.

1) Data acquisition module:

Function: Collect the operating status data of the drone in the drone nest in real time.

Configuration: Contains multiple sensors that can capture various information related to the operating status of the drone.

Data: The collected dataset (D) includes data items (d_1, d_2, ..., d_n) collected from various sensors, and each (d_i) represents the UAV operation status data collected from the (i)th sensor in the nest.

2) Edge processing module:

Connection: Connect to the data acquisition module to receive real-time collected data.

Function: Perform preliminary data processing, including data cleaning and feature extraction.

Data cleaning (f_{clean}(D)): Clean the original data to remove noise, errors or invalid data to obtain the cleaned data set (D').

Feature extraction (f_{feature}(D')): Extract key features from the cleaned data (D') to form a feature set (F).

Preliminary state judgment: Use a lightweight machine learning model (M_{edge}) to make a preliminary state judgment of the drone based on the feature set (F) and output the preliminary state (S_{prelim}).

3) Cloud analysis module:

Function: Receive key data transmitted by the edge processing module (F).

In-depth analysis: Use complex artificial intelligence algorithms (M_{cloud}) to conduct in-depth analysis of data (F) and output a more accurate and detailed final status judgment (S_{final}).

4) Intelligent inspection module:

Function: Automatically generate inspection tasks and plans based on the final status judgment (S_{final}) of the cloud analysis module.

Inspection guidance: guide inspection personnel or automated robots to carry out targeted inspection work.

5) Status monitoring and alarm module:

Function: Real-time monitoring of the device status (S_{final}) output by the cloud analysis module.

Alarm mechanism: Once an abnormal state (S_{abnormal}) is detected (i.e., the device state does not belong to the normal state set (S_{normal})), an alarm message is immediately sent to relevant personnel through communication means (C).

Through the collaborative work of real-time data collection, edge processing and cloud analysis, the entire system can achieve efficient status monitoring, intelligent inspections and timely alarms of drones in the drone nest, thereby improving the operation and maintenance efficiency and safety of the drone nest.

In combination with the above technical solutions and the technical problems solved, the advantages and positive effects of the technical solutions to be protected by the present invention are as follows:

First, the machine nest cloud edge intelligent inspection and equipment status monitoring system can effectively improve the efficiency and accuracy of equipment inspection and status monitoring. The specific technical effects include:

1. Improve efficiency: Through automated data collection and intelligent analysis, the workload of manual inspections is greatly reduced, and the efficiency and frequency of inspections are improved.

2. Improved accuracy: The use of advanced artificial intelligence algorithms improves the accuracy of equipment status judgment and prediction, and reduces equipment failures caused by human judgment errors.

3. Enhanced real-time performance: The cloud-edge collaborative architecture ensures the real-time performance of data processing, can quickly respond to changes in device status, and promptly detect and handle device problems.

4. Preventive maintenance: The system can predict potential equipment failures, realize the transition from passive repair to active prevention, and reduce equipment failure rate and maintenance costs.

5. Data-driven decision support: The system provides rich data analysis and visualization tools, providing data-driven decision support for equipment management and maintenance, and improving management efficiency and level.

Second, the significant technical advances of the present invention include the following aspects:

1. Improve efficiency and performance

Automation and optimization algorithms: By using efficient mathematical algorithms, the system is able to automate complex calculations and decision-making processes, significantly improving processing speed and performance.

Resource optimization: In scenarios such as inventory management, by accurately calculating the optimal inventory level and ordering time, resource waste is significantly reduced and resource utilization efficiency is improved.

2. Reduce costs

Reduced manual operations: Automated decisions and operations reduce the need for human intervention, thereby reducing labor costs.

Optimize operating costs: By optimizing inventory levels, production plans or logistics routes, the system helps companies reduce excess inventory, production delays or logistics costs.

3. Enhanced availability and reliability

User-friendly interface: The system makes complex mathematical models and algorithms more transparent and easy to operate for users through an intuitive user interface and visualization tools.

Stable algorithm implementation: High-quality algorithm implementation and software engineering practices ensure the stability and reliability of the system and reduce the probability of system failure.

4. Improve user experience

Instant feedback and interaction: The system can provide instant calculation results and feedback, support real-time interaction between users and the system, and greatly improve the user experience.

Customization and flexibility: The system provides customization options to meet the specific needs of different users, increasing the flexibility and applicability of the system.

5. Facilitate decision-making and strategic planning

Data-driven decision-making: The in-depth analysis and prediction tools provided by the system help decision makers make decisions based on big data and precise mathematical models, supporting more efficient and scientific strategic planning.

6. Promote innovation and industry development

Application of new technologies: Applying the latest mathematical theories, algorithms and technologies to practical problems not only solves specific problems, but also promotes technological innovation and industry development.

Interdisciplinary integration: Combining knowledge and technologies from multiple fields such as mathematics, computer science, and engineering promotes interdisciplinary integration and innovation.

Third, the machine nest cloud edge intelligent inspection and equipment status monitoring system provided by the present invention embodies significant technological progress, which is mainly reflected in the following aspects:

1. Combination of edge computing and cloud computing: By performing preliminary data processing and analysis at edge computing nodes, the system can achieve rapid response and reduce the demand for data transmission to the cloud. This not only reduces network bandwidth occupancy and transmission costs, but also improves the real-time and reliability of the system. The introduction of edge computing provides technical support for real-time monitoring and instant decision-making, especially when the network connection is unstable or the amount of data is extremely large.

2. Application of lightweight machine learning models: Deploy lightweight machine learning models on edge nodes for preliminary state judgment, which means that effective data analysis can be performed even in an environment with limited computing resources. This design allows the system to be widely deployed on various devices, including those with weak computing power, greatly expanding the scope of application of the system.

3. In-depth data analysis: The cloud server uses complex artificial intelligence algorithms to conduct in-depth analysis of data, providing more accurate judgment and prediction of equipment status. This in-depth analysis can reveal complex patterns and potential problems in equipment operation, providing strong data support for predictive maintenance and long-term equipment health management.

4. Intelligent inspection and automation: The system automatically generates inspection tasks and plans based on the equipment status analysis results, which can effectively guide inspection personnel or automated robots to conduct targeted inspections. This intelligent inspection plan greatly improves the efficiency and accuracy of maintenance work and reduces equipment failures caused by human omissions.

5. Real-time status monitoring and alarm: The system can monitor the status of equipment in real time and immediately send alarm information to relevant personnel through various communication methods when an abnormality is detected. This real-time alarm mechanism greatly improves the response speed to potential equipment problems and helps to take timely measures to avoid greater losses.

In summary, the system has achieved automation and intelligence in equipment monitoring and maintenance through technological innovation, which not only improves the accuracy and real-time performance of monitoring, but also provides strong technical support for the long-term health management and predictive maintenance of equipment, reflecting significant technological progress.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG1 is a structural diagram of a machine nest cloud edge intelligent inspection and equipment status monitoring system provided by an embodiment of the present invention;

FIG2 is a structural diagram of a data acquisition module provided in an embodiment of the present invention;

FIG3 is a structural diagram of an edge processing module provided by an embodiment of the present invention;

FIG4 is a structural diagram of a cloud analysis module provided by an embodiment of the present invention;

5 is a structural diagram of an intelligent inspection module provided in an embodiment of the present invention;

6 is a diagram of a state monitoring and alarm structure provided by an embodiment of the present invention;

7 is a flow chart of a method for intelligent inspection and equipment status monitoring of a machine nest cloud edge provided by an embodiment of the present invention;

In the figure: 1. Data acquisition module; 2. Edge processing module; 3. Cloud analysis module; 4. Intelligent inspection module; 5. Status monitoring and alarm module; 6. Sensor deployment unit; 7. Data acquisition unit; 8. Data transmission unit; 9. Data preprocessing unit; 10. Preliminary analysis unit; 11. Response and feedback unit; 12. Data aggregation and storage unit; 13. In-depth analysis unit; 14. Inspection plan generation unit; 15. Task allocation unit; 16. Inspection execution unit; 17. Result feedback unit; 18. Real-time monitoring unit; 19. Anomaly detection unit; 20. Alarm notification unit.

DETAILED DESCRIPTION

In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

The following are two specific implementation examples of equipment status monitoring systems based on sensor data collection and artificial intelligence analysis:

Example 1: Motor operation status monitoring system

1. System composition:

Data acquisition module: collects key operating data such as motor temperature, vibration, current, voltage, etc. through wireless sensor network nodes.

Edge processing module: pre-processes the collected data, including data cleaning and feature extraction, and then uses a lightweight machine learning model to perform preliminary status analysis.

Cloud analysis module: Receives data from the edge processing module and uses more complex artificial intelligence algorithms, such as deep learning, to make accurate status judgments and fault predictions.

Status monitoring and alarm module: monitors the motor status in real time. Once an abnormality is detected, such as overtemperature or excessive vibration, an alarm message is immediately sent to the management personnel via SMS or email.

2. Application effect:

The reliability and safety of motor operation are improved, and potential problems can be discovered and handled in a timely manner through real-time monitoring and early warning systems.

Reduce maintenance costs. Accurate condition monitoring and fault prediction can reduce unnecessary downtime and repair costs.

Example 2: Coal mining machine status monitoring system

1. System features:

Data acquisition module: It uses specially designed sensors to collect key operating parameters such as temperature, acceleration, vibration, etc. in real time according to the special working environment of the coal mining machine.

Combining edge processing with cloud analysis: An edge processing unit is set up near the coal mining machine to perform preliminary processing and analysis of the data, while uploading the data to the cloud for more in-depth analysis and storage.

Intelligent inspection module: Automatically generates inspection plans based on the operating status and historical data of the coal mining machine, and notifies inspection personnel through mobile devices.

Status monitoring and alarm module: not only monitors the real-time status of the coal mining machine, but also predicts possible failures and issues early warnings.

2. Implementation results:

It significantly improves the operating efficiency and safety of coal mining machines and reduces the occurrence of sudden failures.

Through intelligent inspection and early warning systems, the cost of manual inspection and safety risks are greatly reduced.

It provides coal mining enterprises with a more scientific and efficient equipment management solution.

These two embodiments demonstrate the specific application of the equipment status monitoring system based on sensor data acquisition and artificial intelligence analysis in different industrial fields, reflecting the significant advantages of the system in improving equipment operation efficiency, safety and reducing maintenance costs.

The signal and data processing process of the machine nest cloud edge intelligent inspection and equipment status monitoring system provided by the embodiment of the present invention is specifically as follows:

First, data acquisition module

1. Choose the right sensor to accurately capture the key operating parameters of the equipment.

2. Set the frequency of sensor data collection to ensure the real-time and accuracy of the data.

3. Configure the communication protocol between the sensor and the data acquisition module to ensure that data can be transmitted stably and efficiently.

4. Conduct a preliminary quality check on the collected raw data and eliminate obviously abnormal or invalid data points.

Second, edge processing module

1. Receive the data stream from the data acquisition module and perform data cleaning, including noise removal, missing value filling, smoothing, etc., to obtain the cleaned data set D'.

2. Perform feature extraction on D'. According to the device characteristics and analysis requirements, select the appropriate feature extraction method (such as time domain, frequency domain analysis, etc.) to obtain the feature set F.

3. Load and run the lightweight machine learning model M_{edge}, perform preliminary classification on F, and obtain the preliminary state S_{prelim} of the device.

4. Transmit the key features F and preliminary status S_{prelim} to the cloud analysis module.

Third, cloud analysis module

1. Receive feature data F transmitted by the edge processing module.

2. Use a complex artificial intelligence algorithm M_{cloud} (such as a deep learning model) to perform in-depth analysis on F and obtain the final state S_{final} of the device.

3. Transmit S_{final} to the intelligent inspection module and the status monitoring and alarm module.

Fourth, intelligent inspection module

1. Based on the received final status of the equipment S_{final}, combined with historical data and equipment maintenance standards, inspection tasks and plans are automatically generated.

2. According to the inspection plan, automatically dispatch inspection personnel or automated robots to conduct targeted inspections.

3. After the inspection is completed, collect and organize the inspection data to provide data support for subsequent equipment status analysis and prediction.

Fifth, status monitoring and alarm module

1. Monitor the received device final status S_{final} in real time.

2. Define the normal state set S_{normal} of the device, and continuously update and optimize the set to adapt to changes in the device state.

3. Once it is found that S_{final} does not belong to S_{normal}, that is, the device is in an abnormal state S_{abnormal}, the alarm mechanism is immediately triggered.

4. Send alarm information to relevant personnel through the configured communication means C (such as SMS, email, APP push, etc.) to ensure timely response and handling of equipment abnormalities.

Sixth, continuous optimization and iteration

1. Regularly evaluate and optimize the performance of data collection, edge processing, and cloud analysis modules to improve the accuracy and efficiency of data processing and analysis.

2. Based on actual operating conditions and user feedback, continuously optimize the functions and performance of the intelligent inspection and status monitoring and alarm modules to improve the practicality and reliability of the system.

3. Continue to pay attention to the development of new technologies and new methods, introduce advanced technologies into the system in a timely manner, and improve the overall performance and intelligence level of the system. In the application scenario of drone nests, an intelligent inspection and equipment status monitoring system can improve the operation and maintenance efficiency and safety of drone nests. The following is an implementation case of the system in drone nests:

1. Data acquisition module: This module collects the operating status data (D) of the drone in the nest in real time through various sensors installed in the drone nest, including the drone’s battery power, temperature, humidity and other information. These sensor data can provide real-time monitoring of the drone’s health status.

2. Edge processing module: After receiving the data (D) from the data acquisition module, this module performs preliminary processing on the data, including data cleaning and feature extraction, such as extracting key features that affect the performance of the drone from temperature and humidity data. Through a lightweight machine learning model (M_{edge}), this module can quickly judge the initial status of the drone and determine whether more in-depth analysis is needed.

3. Cloud analysis module: For those drones that are initially judged to have problems, key feature data (F) will be sent to the cloud for in-depth analysis. The cloud uses a more complex artificial intelligence algorithm (M_{cloud}) to make a final judgment on the status of the drone, thereby more accurately identifying potential problems and risks.

4. Intelligent inspection module: Based on the final status judgment of the cloud analysis module, the intelligent inspection module will automatically generate inspection tasks and plans. These tasks and plans will guide inspection personnel or automated robots to conduct targeted inspections and maintenance on specific drones to ensure the safe and reliable operation of all drones in the nest.

5. Status monitoring and alarm module: monitors the status of the drone in real time. Once an abnormal state (S_{abnormal}) is identified, the system will immediately send an alarm message to the operation and maintenance personnel through communication means such as email, SMS or application notification (C), prompting them to take necessary maintenance measures.

Through the above implementation cases, the intelligent inspection and equipment status monitoring system in the drone nest can not only realize the real-time status monitoring and health assessment of the drone, but also generate inspection tasks and alarms in time when potential problems are found, greatly improving the operation and maintenance efficiency and safety of the drone nest.

As shown in FIG1 , an embodiment of the present invention provides a machine nest cloud edge intelligent inspection and equipment status monitoring system, the system comprising:

Data acquisition module 1, by installing various sensors on the equipment, collects equipment operation status data in real time, such as temperature, vibration, sound, etc., and transmits the data to the edge computing node through the Internet of Things technology;

Edge processing module 2 is connected to the data acquisition module. The edge computing node performs preliminary processing on the collected data, such as data cleaning and feature extraction, and uses a lightweight machine learning model to make preliminary state judgments to reduce data transmission volume and improve response speed.

The cloud analysis module 3 is connected to the edge processing module to upload the key data processed by the edge to the cloud server. The cloud server uses more complex artificial intelligence algorithms to conduct in-depth analysis of the data to achieve accurate judgment and prediction of the device status;

The intelligent inspection module 4 is connected to the cloud analysis module. The system automatically generates inspection tasks and plans based on the equipment status analysis results, and guides the inspection personnel or automated robots to conduct targeted inspections;

The status monitoring and alarm module 5 is connected to the intelligent inspection module. The system monitors the equipment status in real time. Once an abnormality is found, an alarm message is immediately sent to relevant personnel through various communication means (such as SMS, email, APP push, etc.) to ensure that the equipment problem is handled in time.

The Jichao Cloud Edge Intelligent Inspection and Equipment Status Monitoring System is a highly integrated intelligent system that aims to achieve real-time monitoring, analysis and prediction of the status of various types of equipment through advanced information technology and Internet of Things (IoT) technology to improve equipment maintenance efficiency and reduce downtime. The following is the detailed signal and data processing process of the system:

1) Data acquisition module:

Various sensors are installed on the equipment, such as temperature sensors, vibration sensors, sound sensors, etc., to monitor the operating status of the equipment in real time.

The data collected by the sensors include but are not limited to temperature changes, vibration frequency, sound levels, etc., which can reflect the immediate status of the equipment and any problems that exist.

Through IoT technologies such as wireless networks, Bluetooth, ZigBee, etc., these data are transmitted to edge computing nodes in real time to prepare for subsequent processing and analysis.

2) Edge processing module:

The edge computing node receives the raw data from the data acquisition module and performs preliminary processing.

Data cleaning: remove noise, correct erroneous values, fill in missing values, etc. to ensure data quality.

Feature extraction: Extract key features from raw data based on the characteristics of equipment operation and failure modes, such as peak frequency in spectrum analysis, maximum amplitude in waveform analysis, etc.

Preliminary status judgment: Use lightweight machine learning models (such as decision trees, lightweight neural networks, etc.) to analyze the extracted features and conduct preliminary equipment status assessment, such as normal, abnormal, or warning status.

3) Cloud analysis module:

Upload the key data processed by the edge processing module to the cloud server.

Cloud servers use more complex artificial intelligence algorithms, such as deep learning and complex event processing (CEP), to conduct in-depth analysis of data.

Achieve accurate judgment and prediction of equipment status, including fault diagnosis, life prediction, maintenance needs analysis, etc.

4) Intelligent inspection module:

Based on the analysis results of the cloud analysis module, the system automatically generates inspection tasks and plans.

Tasks and plans guide inspectors or automated robots to perform targeted inspections, focusing on equipment components that have problems or are about to fail.

5) Status monitoring and alarm module:

The system monitors the equipment status in real time, including normal operation status and various warning and abnormal status.

Once the system detects an equipment anomaly or fault warning, it immediately sends an alarm message to maintenance personnel, equipment managers or other relevant personnel through various communication methods (such as SMS, email, APP push, etc.).

Ensure that equipment problems are discovered and handled promptly, minimizing equipment downtime and repair costs.

The design of the system fully utilizes the low latency advantage of edge computing and the powerful processing capabilities of cloud computing, achieving high efficiency and intelligent data processing, and greatly improving the efficiency and accuracy of equipment monitoring and maintenance.

As shown in FIG2 , the data acquisition module 1 includes:

Sensor deployment unit 6: deploy various types of sensors on key equipment, such as temperature sensors, vibration sensors, sound sensors, etc., to monitor various operating parameters of the equipment in real time;

Data acquisition unit 7: The sensor collects the operating status data of the equipment in real time, and pre-processes the data through the data acquisition module on the equipment, such as formatting and standardization;

Data transmission unit 8: The collected data is securely transmitted to the nearest edge computing node via IoT technology (such as WiFi, cellular network, LoRa, etc.).

As shown in FIG3 , the edge processing module 2 specifically includes:

Data preprocessing unit 9, after receiving the data, the edge computing node performs further preprocessing, including data cleaning (noise removal, outlier processing), feature extraction (converting to a format recognizable by the machine learning model), etc.;

A preliminary analysis unit 10 performs preliminary analysis on the preprocessed data using a lightweight machine learning model deployed on the edge node to quickly identify signs of equipment anomalies or failures;

Response and feedback unit 11, based on the preliminary analysis results, the edge node can make some immediate responses, such as adjusting device parameters, issuing local alarms, etc., and uploading key data or abnormality reports to the cloud server.

As shown in FIG4 , the cloud analysis module 3 specifically includes:

Data aggregation and storage unit 12: The cloud server receives data from multiple edge nodes, aggregates and stores them for a long time, and builds a device history database;

Deep Analysis Unit 13: Uses complex AI algorithms (such as deep learning, time series analysis, etc.) to conduct in-depth analysis of aggregated data, accurately determine the status of equipment, and predict future problems;

Inspection plan generation unit 14: Based on the in-depth analysis results, the system automatically generates inspection tasks and plans, including inspection time, key inspection items, etc.

As shown in FIG5 , the intelligent inspection module 4 specifically includes:

Task allocation unit 15: The system allocates inspection tasks and plans to inspection personnel or automated robots, and guides them to conduct targeted inspections;

Inspection execution unit 16: Inspection personnel or robots perform inspection tasks according to the plan provided by the system and collect equipment status data using mobile devices or special tools;

Result feedback unit 17: The inspection results are fed back to the central monitoring system through mobile devices or automation systems to update the equipment status and optimize subsequent inspection plans.

As shown in FIG6 , the status monitoring and alarm module 5 specifically includes:

Real-time monitoring unit 18: The system monitors the status of all devices in real time and uses dashboards and visualization tools to display the operation of the devices;

Anomaly detection unit 19: The system analyzes equipment data in real time and immediately triggers an alarm mechanism once anomalies or signs of failure are detected;

Alarm notification unit 20: The system sends alarm information to maintenance personnel, management personnel and relevant responsible persons through various communication means such as SMS, email, APP push, etc., to ensure that equipment problems are responded to and handled in a timely manner.

As shown in FIG. 7 , an embodiment of the present invention provides a method for implementing the machine nest cloud edge intelligent inspection and device status monitoring system, the method comprising:

S1: Using the data acquisition module, various sensors are installed on the equipment to collect real-time equipment operation status data, such as temperature, vibration, sound, etc., and transmit the data to the edge computing node through the Internet of Things technology; using the edge processing module, the edge computing node performs preliminary processing on the collected data, such as data cleaning and feature extraction, and uses a lightweight machine learning model to make preliminary status judgments to reduce the amount of data transmission and improve the response speed;

S2: Using the cloud analysis module, the key data processed by the edge is uploaded to the cloud server. The cloud server uses more complex artificial intelligence algorithms to conduct in-depth analysis of the data to accurately judge and predict the status of the equipment. Using the intelligent inspection module, according to the equipment status analysis results, it automatically generates inspection tasks and plans to guide inspection personnel or automated robots to conduct targeted inspections.

S3: Use the status monitoring and alarm module to monitor the equipment status in real time. Once an abnormality is found, an alarm message is immediately sent to relevant personnel through various communication methods (such as SMS, email, APP push, etc.) to ensure that equipment problems are handled in a timely manner.

An embodiment of the present invention provides a computer device, which includes a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the machine nest cloud edge intelligent inspection and equipment status monitoring method.

An embodiment of the present invention provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, the processor executes the steps of the machine-nest cloud-edge intelligent inspection and equipment status monitoring method.

An embodiment of the present invention provides an information data processing terminal, which is used to implement the machine nest cloud edge intelligent inspection and equipment status monitoring system.

Here is an example flow that shows how to combine mathematical formulas and algorithms to build a system to optimize inventory management:

1. Problem Definition

First, we need to identify the problems that the system needs to solve. In the inventory management scenario, the main problems include:

How to minimize inventory costs, including holding costs, stockout costs, and ordering costs.

How to ensure that inventory levels meet changes in demand to avoid stockouts or overstocks.

2. Establishment of mathematical model

Based on the problem definition, a mathematical model is established. For inventory management, a basic model is the economic order quantity (EOQ) model, whose formula is:

[EOQ = sqrt{frac{2DS}{H}}]

in:

(D) is the annual demand

(S) is the fixed cost per order

(H) is the annual holding cost per unit of goods

3. Algorithm Design

Design an algorithm based on a mathematical model. For example, using the EOQ model, design an algorithm to automatically calculate the optimal order quantity and trigger the order:

1. Data collection: Collect data on demand (D), ordering costs (S), and holding costs (H).

2. Calculate EOQ: Calculate the optimal order quantity based on the EOQ formula.

3. Trigger ordering: When the inventory drops to the reorder point, new ordering is triggered based on EOQ.

4. System Implementation

Integrate the algorithm into the system software:

Front-end: Develop user interface to display inventory levels, demand forecasts, EOQ calculation results, etc.

Backend: Implement EOQ algorithm and manage database storage demand, ordering cost, holding cost and other data.

Database: Design database to store inventory data, order data, cost data, etc.

5. Optimization and expansion

Optimize models and algorithms based on actual application feedback. For example, introduce more complex demand forecasting models, such as time series analysis or machine learning models, to more accurately predict future demand.

6. Deployment and testing

Deploy the system to the production environment and conduct comprehensive testing, including unit testing, integration testing, and performance testing, to ensure that the system is stable and reliable.

7. User Training and Documentation

Provide training to users to ensure they understand how to use the system. Also, write detailed user manuals and online help documentation.

Through the above steps, a system combining mathematical formulas and algorithms can be built to optimize the inventory management process. The same method can also be applied to other fields, such as financial modeling, logistics optimization, production scheduling, etc., just need to adjust the mathematical model and algorithm according to the specific problem.

The Machine Nest Cloud Edge Intelligent Inspection and Equipment Status Monitoring System combines a variety of cutting-edge technologies, such as the Internet of Things (IoT), edge computing, artificial intelligence (AI), and machine learning, to achieve efficient and accurate monitoring of industrial equipment. The following are two specific examples:

In the application example of the wind turbine monitoring system, vibration sensors, sound sensors, and temperature sensors are installed on key components such as blades, gearboxes, and generators to collect key data about the equipment's operating status in real time. This data is initially processed by the data acquisition unit on the wind turbine and then transmitted to the edge computing device for further preprocessing and preliminary analysis. At this stage, the edge computing device extracts key features, such as vibration spectrum analysis results, and uses lightweight machine learning models for fault analysis to quickly identify problems such as abnormal vibration patterns or temperature rise.

In the implementation of the intelligent manufacturing workshop monitoring system, current sensors, temperature sensors, and vibration sensors are deployed on key production equipment to continuously monitor the operating parameters of the equipment. After receiving the data, the edge processing node is responsible for denoising and standardization, and then uses the machine learning model to perform real-time data analysis to quickly detect equipment performance degradation or potential failures. This instant fault detection mechanism makes the monitoring of the production process more efficient and helps to identify and solve potential problems in a timely manner.

In both systems, the cloud-based analytics module performs in-depth analysis of the data received from the edge processing module. In the wind turbine system, the cloud system compares data across multiple wind turbines and time periods to identify long-term trends and potential failures. In the smart manufacturing workshop system, the cloud server uses complex algorithms to analyze historical data to predict equipment life and maintenance needs. This in-depth data analysis helps to more accurately determine the status of equipment, thereby more effectively planning maintenance work and resource allocation.

Finally, the intelligent inspection and status monitoring and alarm modules play a vital role in these two embodiments. The wind power generation system guides the inspectors or drones to conduct regular inspections of the blades and structural integrity through the inspection tasks and plans generated by the system. The intelligent manufacturing workshop system arranges inspectors to inspect and point out the problem areas of specific equipment based on the cloud analysis results. In addition, when any of the two systems detects an abnormality, the maintenance team will be quickly notified through the alarm system to ensure production safety and stable operation of the equipment. These two embodiments fully demonstrate the great potential of the machine nest cloud edge intelligent inspection and equipment status monitoring system in improving production efficiency and equipment reliability. It should be noted that the embodiments of the present invention can be implemented by hardware, software, or a combination of software and hardware. The hardware part can be implemented using dedicated logic; the software part can be stored in a memory and executed by an appropriate instruction execution system, such as a microprocessor or a dedicated design hardware. It can be understood by ordinary technicians in the field that the above-mentioned devices and methods can be implemented using computer executable instructions and/or contained in a processor control code, for example, such codes are provided on a carrier medium such as a disk, CD or DVDROM, a programmable memory such as a read-only memory (firmware), or a data carrier such as an optical or electronic signal carrier. The device and its modules of the present invention can be implemented by hardware circuits such as very large-scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, etc., or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc., and can also be implemented by software executed by various types of processors, or by a combination of the above hardware circuits and software, such as firmware.

The above description is only a specific implementation mode of the present invention, but the protection scope of the present invention is not limited thereto. Any modifications, equivalent substitutions and improvements made by any technician familiar with the technical field within the technical scope disclosed by the present invention and within the spirit and principle of the present invention should be covered by the protection scope of the present invention.

Claims (10)

1. A machine nest cloud edge intelligent inspection and equipment status monitoring system, characterized in that it includes a data acquisition module, an edge processing module, a cloud analysis module, an intelligent inspection module and a status monitoring and alarm module, wherein: A data acquisition module, configured to collect operating status data of the device in real time through sensors; An edge processing module is configured to receive data transmitted by the data acquisition module, perform data cleaning and feature extraction, and use a lightweight machine learning model to make a preliminary state judgment on the feature set; The cloud analysis module is configured to receive key data transmitted by the edge processing module and use complex artificial intelligence algorithms to perform in-depth analysis to determine the final status of the device; An intelligent inspection module is configured to automatically generate inspection tasks and plans based on the final status of the equipment and guide the inspection; The status monitoring and alarm module is configured to monitor the status of the equipment in real time. Once an abnormal status is found, an alarm message is immediately sent to relevant personnel through communication means. 2. A method for equipment status monitoring and alarm using artificial intelligence, characterized in that it includes the following steps: Collect equipment operation status data in real time through sensors; In the edge processing module, the collected data is cleaned and features are extracted, and a lightweight machine learning model is used to make preliminary status judgments; The extracted key feature data is transmitted to the cloud analysis module, and a complex artificial intelligence algorithm is used to perform in-depth analysis to obtain the final status of the device; Automatically generate inspection tasks and plans based on the final status of the equipment, and guide the inspection; At the same time, the equipment status is monitored in real time. Once an abnormality is found, an alarm message is immediately sent to relevant personnel through the preset communication means; In addition, the system can continuously optimize and iterate based on actual operating conditions and user feedback to improve system performance. 3. The device status monitoring system according to claim 1, characterized in that the specific algorithm implementation of the edge processing module and the cloud analysis module is: The edge processing module uses a data cleaning function (f_{clean}(D)=D'={d'_1,d'_2,...,d'_n}), where (d'_i=d_i) if (d_i) is within a predetermined normal range, otherwise (d'_i) is corrected by interpolation or other methods; Feature extraction function (f_{feature}(D')＝F＝{f_1,f_2,...,f_m}), where (f_j) is the (j)th feature extracted from the data (D'), which can be obtained by spectrum analysis, time domain analysis, etc. The lightweight machine learning model (M_{edge}) on the edge computing node can be a decision tree, support vector machine or shallow neural network, and its training process (T_{edge}) is based on the labeled feature set (F_{label}) and the corresponding state label (S_{label}), that is, (M_{edge}＝T_{edge}(F_{label},S_{label})); The complex artificial intelligence algorithm (M_{cloud}) of the cloud analysis module can be a deep neural network, an integrated learning model, or other advanced machine learning models, and its training process (T_{cloud}) utilizes large-scale data sets (F_{large}) and state labels (S_{large}) from multiple devices and time periods, that is, (M_{cloud}＝T_{cloud}(F_{large},S_{large})); The status monitoring and alarm module defines the abnormal status judgment logic (S_{abnormal}＝{s|s in S_{final},snotin S_{normal}}), where (S_{normal}) is determined by the equipment operation history data and expert knowledge. 4. The machine nest cloud edge intelligent inspection and equipment status monitoring system according to claim 1, characterized in that the data acquisition module includes: Sensor deployment unit: deploy various types of sensors on key equipment to monitor various operating parameters of the equipment in real time; Data acquisition unit: The sensor collects the operating status data of the equipment in real time and pre-processes the data through the data acquisition module on the equipment; Data transmission unit: The collected data is securely transmitted to the nearest edge computing node through IoT technology. 5. The machine nest cloud edge intelligent inspection and equipment status monitoring system according to claim 1, characterized in that the edge processing module specifically includes: Data preprocessing unit, after receiving the data, the edge computing node performs further preprocessing, including data cleaning and feature extraction; The preliminary analysis unit uses a lightweight machine learning model deployed on the edge node to perform preliminary analysis on the preprocessed data and quickly identify signs of equipment anomalies or failures; Response and feedback unit,Based on the preliminary analysis results, the edge node can make some immediate responses and upload key data or abnormal reports to the cloud server. 6. The machine nest cloud edge intelligent inspection and equipment status monitoring system according to claim 1, characterized in that the cloud analysis module specifically includes: Data aggregation and storage unit: The cloud server receives data from multiple edge nodes, aggregates and stores them for a long time, and builds a device history database; Deep Analysis Unit: Uses complex artificial intelligence algorithms to conduct in-depth analysis of aggregated data, accurately determine equipment status, and predict future problems; Inspection plan generation unit: Based on the in-depth analysis results, the system automatically generates inspection tasks and plans, including inspection time and key inspection items. 7. The machine nest cloud edge intelligent inspection and equipment status monitoring system according to claim 1, characterized in that the intelligent inspection module specifically includes: Task allocation unit: The system allocates inspection tasks and plans to inspection personnel or automated robots, guiding them to conduct targeted inspections; Inspection execution unit: Inspection personnel or robots perform inspection tasks according to the plan provided by the system and use mobile devices or special tools to collect equipment status data; Result feedback unit: Inspection results are fed back to the central monitoring system through mobile devices or automation systems to update equipment status and optimize subsequent inspection plans. 8. The machine nest cloud edge intelligent inspection and equipment status monitoring system according to claim 1, characterized in that the status monitoring and alarm module specifically includes: Real-time monitoring unit: The system monitors the status of all devices in real time and uses dashboards and visualization tools to display the operation of the devices; Anomaly detection unit: The system analyzes equipment data in real time and immediately triggers an alarm mechanism once anomalies or signs of failure are detected; Alarm notification unit: The system sends alarm information to maintenance personnel, management personnel and relevant responsible persons through SMS, email, APP push and other communication methods to ensure that equipment problems are responded to and handled in a timely manner. 9. A method for implementing the machine nest cloud edge intelligent inspection and equipment status monitoring system according to any one of claims 17, characterized in that the method comprises: S1: Using the data acquisition module, various sensors are installed on the equipment to collect the equipment operation status data in real time, and the data is transmitted to the edge computing node through the Internet of Things technology; using the edge processing module, the edge computing node performs preliminary processing on the collected data and uses a lightweight machine learning model to make preliminary status judgments to reduce the amount of data transmission and improve the response speed; S2: Using the cloud analysis module, the key data processed by the edge is uploaded to the cloud server. The cloud server uses more complex artificial intelligence algorithms to conduct in-depth analysis of the data to accurately judge and predict the status of the equipment. Using the intelligent inspection module, according to the equipment status analysis results, it automatically generates inspection tasks and plans to guide inspection personnel or automated robots to conduct targeted inspections. S3: Use the status monitoring and alarm module to monitor the equipment status in real time. Once an abnormality is found, an alarm message is immediately sent to relevant personnel through various communication methods to ensure that equipment problems are handled in a timely manner. 10. An intelligent inspection and equipment status monitoring system applied to drone nests, characterized in that the system includes: A data acquisition module (1) is configured with a plurality of sensors for real-time acquisition of operating status data (D = {d_1, d_2, ..., d_n}) of a drone in a drone nest, wherein each (d_i) represents the operating status data of the drone collected from the (i)th sensor in the nest; an edge processing module (2), connected to the data acquisition module (1), for receiving data (D) and performing preliminary processing on the data, including data cleaning (f_{clean}(D)) and feature extraction (F=f_{feature}(D')), wherein (D') is the cleaned data and (F) is a feature set extracted from (D'); A lightweight machine learning model (M_{edge}) is located in the edge processing module (2), which is used to make a preliminary state judgment of the drone based on the feature set (F) and output a preliminary state (S_{prelim}＝M_{edge}(F)); A cloud analysis module receives the key data (F) transmitted by the edge processing module (2), uses a complex artificial intelligence algorithm (M_{cloud}) to perform in-depth analysis on (F), and outputs a final state judgment (S_{final}＝M_{cloud}(F)); An intelligent inspection module that automatically generates inspection tasks and plans based on the final state judgment (S_{final}) of the cloud analysis module, and guides inspection personnel or automated robots to conduct targeted inspections; A status monitoring and alarm module monitors the device status (S_{final}) output by the cloud analysis module in real time. Once an abnormal status (S_{abnormal}) is found (i.e., the set (S_{final}notin S_{normal})), an alarm message is immediately sent to relevant personnel through communication means (C), where (S_{normal}) represents the normal status set of the device.