CN115826516A - An intelligent stainless steel chain production management method and system - Google Patents

Abstract

The invention provides an intelligent stainless steel chain production management method and system, and relates to the technical field of production management, wherein the method comprises the following steps: the method comprises the steps of obtaining distribution information of a production workshop to determine an information acquisition point, then arranging a plurality of sensors, obtaining real-time production information by taking the plurality of sensors as an information interaction medium, carrying out dynamic simulation based on a digital twin technology to generate a production twin model according to the real-time production information, determining production expected planning based on production order information, carrying out production fault probability prediction based on the production twin model, and carrying out production operation and maintenance optimization based on a fault probability prediction result to realize production optimization management.

Description

An intelligent stainless steel chain production management method and system

technical field

The invention relates to the technical field of production management, in particular to an intelligent stainless steel chain production management method and system.

Background technique

Because the technology of the factory is relatively backward, the management level is not high, the products are unstable, and the cost is very high. The development of the machinery industry is related to the development of our living standards, and the conveying machinery is an indispensable equipment for industrial production. As a part of the conveying machinery Important components, the production process and product quality of stainless steel chains are constantly improving. China's logistics equipment industry is constantly innovating under the market economy. The materials of stainless steel chains for conveying machinery are cheap, which brings more benefits to various industrial enterprises.

However, in recent years, due to the increase in the production demand of industrial enterprises, the demand for conveying machinery accessories has also greatly increased. In order to meet the needs of the market, manufacturers use inferior stainless steel chains for conveying machinery, which will wear off in a short time before use or when they are used. Rust and noise start to appear, these conveyor machinery stainless steel chains are of poor quality, but are usually beautifully packaged and inexpensive, so it's hard to tell the difference.

The stainless steel chain production method in the prior art has a low pass rate of the final stainless steel chain production due to insufficient control of the chain material, quality inspection and production process in the production process.

Contents of the invention

This application provides an intelligent stainless steel chain production management method and system, which is used to solve the stainless steel chain production method in the prior art due to insufficient control of the chain material, quality inspection and production process in the production process, which makes the final The technical problem of low pass rate in the production of stainless steel chains.

In view of the above problems, the present application provides an intelligent production management method and system for stainless steel chains.

In the first aspect, the present application provides an intelligent production management method for stainless steel chains. The method includes: acquiring production workshop distribution information, determining information collection points based on the production workshop distribution information; Each sensor is arranged, and the multiple sensors are used as an information interaction intermediary to obtain real-time production information; according to the real-time production information, a dynamic simulation is performed based on digital twin technology to generate a production twin model, wherein the production twin model is the same as the actual production State synchronization; determine the production forecast plan based on the production order information; based on the production forecast plan, perform production failure probability prediction according to the production twin model, and generate a failure probability prediction result; optimize production operation and maintenance based on the failure probability prediction result , to achieve production optimization management.

In the second aspect, the application provides an intelligent stainless steel chain production management system, the system includes: an information collection point module, the information collection point module is used to obtain the distribution information of the production workshop, based on the distribution information of the production workshop Determine the information collection point; real-time production information module, the real-time production information module is used to deploy multiple sensors based on the information collection point, and use the multiple sensors as an information interaction intermediary to obtain real-time production information; production twin model module , the production twin model module is used to perform dynamic simulation based on digital twin technology to generate a production twin model according to the real-time production information, wherein the production twin model is synchronized with the actual production state; the production forecast planning module, the The production forecast planning module is used to determine the production forecast plan based on the production order information; the failure probability prediction result module is used to perform production failure probability prediction based on the production forecast plan and according to the production twin model , generating a failure probability prediction result; a production optimization management module, the production optimization management module is used to optimize production operation and maintenance based on the failure probability prediction result, and realize production optimization management.

One or more technical solutions provided in this application have at least the following technical effects or advantages:

The application provides an intelligent production management method for stainless steel chains, which relates to the field of production management technology and solves the problems in the production process of stainless steel chains in the prior art due to the control of chain materials, quality inspection and production processes in the production process. Insufficient, the technical problem that makes the final stainless steel chain production pass rate low, realizes the rationalization and precise control of the stainless steel chain production process, and then improves the pass rate of stainless steel chain production.

Description of drawings

Fig. 1 provides a kind of intelligent stainless steel chain production management method flow diagram for the application;

Fig. 2 provides a schematic flow diagram of determining adaptive information collection points in an intelligent stainless steel chain production management method for the present application;

Fig. 3 provides a schematic diagram of the failure prediction result output process in an intelligent stainless steel chain production management method for the present application;

Fig. 4 is a structural schematic diagram of an intelligent stainless steel chain production management system provided by the present application.

Description of reference signs: information collection point module 1, real-time production information module 2, production twin model module 3, production forecast planning module 4, failure probability prediction result module 5, production optimization management module 6.

Detailed ways

This application provides an intelligent stainless steel chain production management method, which is used to solve the stainless steel chain production method in the prior art. Due to insufficient control of chain materials, quality inspection and production process in the production process, the final stainless steel chain production is qualified. Low rate technical issues.

Embodiment one

As shown in Figure 1, the embodiment of the present application provides an intelligent stainless steel chain production management method, which is applied to the production management system, LED device production system and image acquisition device, temperature sensor, humidity sensor, electrostatic potential measurement equipment A communication connection, the method comprising:

Step S100: Obtaining distribution information of production workshops, and determining information collection points based on the distribution information of production workshops;

Specifically, an intelligent stainless steel chain production management method provided in the embodiment of the present application is applied to a production management system, and the production management system communicates with multiple sensors, and the multiple sensor devices are used for real-time production information parameter collection .

On the basis of the actual production workshop distribution, obtain the production workshop distribution information, and further determine the information collection points according to the obtained production workshop distribution information. The production workshop distribution includes but not limited to static data, dynamic data and intermediate data. Static data refers to Data that generally does not change, such as material codes, internal numbers of processors, processing equipment numbers, warehouse numbers, etc. Dynamic data refers to data that changes with changes in the status of parts during the manufacturing process, including The processing procedure, size, logistics information, and completion time of parts, etc. These information directly reflect the quality and status of parts, enabling enterprises to understand the dynamics of parts and the current progress of tasks in real time, and provide information for upper-level data processing, quality monitoring, Task scheduling and supply chain management provide basic data. Intermediate data refers to the collection, analysis and processing of static and dynamic data due to the needs of enterprise management. For example, the management system sometimes needs to process data in batches. Format the data to meet the needs of processing or communication between modules, or generate reports for production information, etc., and then determine the information collection points that need to collect information based on static data, dynamic data, and intermediate data. Realize production optimization management as an important reference.

Step S200: deploy multiple sensors based on the information collection points, and use the multiple sensors as an information interaction intermediary to obtain real-time production information;

Specifically, multiple sensors are arranged according to the above-mentioned information collection points, among which multiple sensors include wireless temperature and humidity sensors, wireless temperature sensors, wireless mixed gas sensors, etc., and multiple sensors are used as information exchange media, that is, multiple The information collected by each sensor is summarized, integrated and interacted, and real-time production information is obtained from it, thereby guaranteeing the realization of production optimization management.

Step S300: According to the real-time production information, perform dynamic simulation based on digital twin technology to generate a production twin model, wherein the production twin model is synchronized with the actual production state;

Specifically, on the basis of the obtained real-time production information, use digital twin technology to perform dynamic simulation and then generate a production twin model. It is necessary to make full use of data such as physical models, sensor updates, and operation history to integrate multi-disciplinary, multi-physical quantities, The multi-scale, multi-probability simulation process completes the mapping in the virtual space, thereby reflecting the whole life cycle process of the corresponding actual production state, and finally generates the production twin model, in which the production twin model is synchronized with the actual production state, which is for the follow-up Realize production optimization management and lay a solid foundation.

Step S400: Determine the production forecast plan based on the production order information;

Specifically, on the basis of the generated production order information, reasonably plan production expectations, where the production order information includes delivery quantity, delivery price, delivery deadline, delivery date, delivery quality, etc., and according to the production order information The required delivery quantity, delivery date and delivery quality are reasonably expected, and the final production forecast plan is determined, which has a restrictive effect on the realization of production optimization management.

Step S500: Based on the production forecast plan, perform production failure probability prediction according to the production twin model, and generate a failure probability prediction result;

Specifically, on the basis of the production forecast plan generated above, the failure probability prediction during the production period is carried out on the obtained production twin model, and the failure probability prediction result is further generated. Under the circumstances, it matches with the production twin model, that is, in the case of obtaining the actual production state, corresponding prediction is made, so as to obtain the prediction result of failure probability, which has a profound impact on the realization of production optimization management in the later stage.

Step S600: Optimizing production operation and maintenance based on the prediction result of failure probability to realize production optimization management.

Specifically, the production operation and maintenance optimization of the obtained failure probability prediction results is to analyze and sort out the obtained failure probability results, and then detect the predicted failure points, and timely correct production abnormalities to improve production quality and Production efficiency, and then better realize the optimization of production operation and maintenance, and better realize production optimization management according to the optimization of production operation and maintenance.

Further, obtain the distribution information of the production workshop to determine the information collection points, then deploy multiple sensors, use multiple sensors as an information interaction intermediary to obtain real-time production information, and perform dynamic simulation based on digital twin technology to generate a production twin model based on real-time production information , the production order information is used to determine the expected production plan, the production failure probability is predicted based on the production twin model, and the production operation and maintenance optimization is performed based on the failure probability prediction results to realize production optimization management. Insufficient control of chain materials, quality inspection and production process in the production process leads to the technical problem of low pass rate of final stainless steel chain production, which realizes the rationalization and precise control of stainless steel chain production process, thereby improving the pass rate of stainless steel chain production.

Further, as shown in FIG. 2, step S100 of this application also includes:

Step S110: Obtain the product production process;

Step S120: Divide the production workshop based on the product production process to obtain multiple process areas;

Step S130: Determine the location of the process equipment for the multiple process areas, and determine the adaptive information collection point based on the location of the process equipment.

Specifically, the production workshop is divided on the basis of the existing production process of stainless steel chain products, so as to obtain multiple process areas, in which the production of stainless steel chain products includes three parts: blanking and knitting, welding and "shaping" and heat treatment. A very critical step, according to different product production processes, divide the production workshop into multiple process areas, and further, determine the positions of different process equipment for the multiple divided process areas, so as to obtain adaptive information collection points , that is, the determined product is obtained from the determined process equipment with the determined production process means, and the adaptive information collection point corresponds to one of them, achieving the technical effect of providing an important basis for the later realization of production optimization management.

Further, as shown in FIG. 3, step S500 of this application also includes:

Step S510: constructing a production failure probability prediction model based on machine learning algorithms;

Step S520: collecting multiple types of production failures based on big data;

Step S530: According to the various types of production failures, perform pseudo-fault experiments based on the production twin model to obtain multiple sets of failure parameters, wherein one type of production failure may correspond to multiple sets of failure parameters;

Step S540: Training the failure probability prediction model according to the multiple sets of failure parameters;

Step S550: Carry out failure prediction on the real-time production information based on the failure probability prediction model, and output a failure prediction result, wherein the failure prediction result includes a failure type, a failure node and a failure probability, and the two are in one-to-one correspondence.

Specifically, on the basis of using machine learning algorithms, a production failure probability prediction model is constructed, and then various types of production failures collected from big data are input into the production twin model for quasi-fault experiments. The plate is damaged, the transmission chain comes out of the chain plate machine groove, the transmission chain falls off on the power sprocket, the connecting link is broken, the connecting link is damaged, etc., and then input it into the production twin model to simulate the fault in the actual production state In the experiment, one of the production failure types corresponds to one or more sets of failure parameters, and then multiple sets of failure parameters are obtained.

Wherein the production failure probability prediction model is a neural network model in machine learning that can continuously perform self-iterative optimization. The production failure probability prediction model is obtained by training the training data set supervision data set, wherein each group in the training data set The training data all include multiple sets of fault parameters; the supervised data set is the fault probability prediction supervised data corresponding to the training data set one-to-one.

Further, the construction process of the production failure probability prediction model is as follows: each set of training data in the training data set is input into the production failure probability prediction model, and the output supervision and adjustment of the production failure probability prediction model is performed through the supervision data corresponding to this set of training data, When the output result of the production failure probability prediction model is consistent with the supervisory data, the current group training ends, and all the training data in the training data set are trained, and the production failure probability prediction model training is completed.

In order to ensure the accuracy of the production failure probability prediction model, the test processing of the production failure probability prediction model can be carried out through the test data set. For example, the test accuracy rate can be set to 85%. When the test accuracy rate of the test data set meets 85% %, the construction of the production failure probability prediction model is completed.

Input the real-time production information into the production failure probability prediction model, and output the failure prediction results.

The failure prediction result includes failure type, failure node and failure probability, so as to ensure high efficiency in production optimization management.

Further, step S540 of this application includes:

Step S531: Set a plurality of preset probability thresholds based on the various types of production failures, and obtain a set of preset probability thresholds;

Step S532: Based on the preset probability threshold set, determine whether the failure probability corresponding to the fault node satisfies a preset probability threshold;

Step S533: When satisfied, generate an operation adjustment instruction.

Specifically, multiple preset probability thresholds are set for various types of production failures obtained, in which the preset probability thresholds correspond to the types of production failures one by one, and all the preset probability thresholds are summarized and integrated to obtain the preset probability Threshold set, at the same time judge the failure probability of the faulty node trivially and the preset probability threshold, if the failure probability corresponding to the faulty node meets the preset probability threshold, an operation adjustment instruction is generated. Exemplarily, multiple fault types include chain boards damage, the transmission chain falls out of the chain plate machine groove, the transmission chain falls off the power sprocket, the connecting link is broken, the connecting link is damaged, etc., if the preset probability threshold of the conveying chain falling out of the chain plate machine groove is set to 40% to 50%, when the failure probability of the conveyor chain falling out of the chain conveyor groove in the actual production state is 47%, then the failure probability of the conveyor chain falling out of the chain conveyor groove meets the preset fault type The probability threshold is used to further generate operation adjustment instructions, so as to adjust the actual production status to reduce the probability of failure, and finally achieve the technical effect of providing reference for production optimization management.

Further, step S533 of this application also includes:

Step S5331: According to the operation adjustment instruction, conduct a production trial run based on the production twin model, and determine the production operation information of the faulty node;

Step S5332: Extract abnormal information from the production operation information of the faulty node, and obtain abnormal process information by performing process matching;

Step S5333: Obtain the time zone for running adjustment;

Step S5334: Based on the operation adjustment time zone, correct the production operation according to the abnormal process information, and perform production optimization management.

Specifically, according to the operation adjustment instructions obtained above, the production trial run is carried out on the basis of the production twin model, and then the production operation information of the faulty node is determined. In the actual production state, the production operation information of the faulty node can be Normal operation in the event of a fault, suspension of operation in the event of a fault, normal operation in the event of a fault, prediction and resolution of faults, and other normal states. Further, the abnormal information is extracted from the production and operation information of the fault node, that is, through the production process of the process and the production and operation information of the fault node. Matching, so as to find abnormal process information, where the abnormal process information includes suspension of operation without failure, suspension of operation due to failure, normal operation of predicted but unresolved failure, etc., and then the obtained operation adjustment time zone is corrected according to the abnormal process information. The obtained operation adjustment time zone refers to that in order to ensure the continuity of the actual production process, when adjusting the production process, such as equipment parameter adjustment, switching, etc., adjustments need to be made in advance, that is, the time spent on each part should be arranged in advance , which adjusts the specific interval size of the time zone to be set according to the actual situation, and finally achieves the technical effect of production optimization management.

Further, step S600 of this application also includes:

Step S610: Determine multiple production indicators based on the production order information;

Step S620: Obtain multiple production samples, perform quality inspection on the multiple production samples based on the multiple production indicators, and acquire multiple sets of indicator data;

Step S630: Set an index threshold based on the multiple production indexes, and construct an index threshold set;

Step S640: traversing the multiple sets of index data, judging whether the multiple sets of index data meet the set of index thresholds, and generating a batch product pass rate;

Step S650: When the qualified rate of the batch of products does not meet the standard, perform production process inspection based on the production twin model, and correct production abnormalities.

Specifically, multiple production indicators are determined based on the obtained production order information, including delivery quantity indicators, delivery price indicators, delivery period indicators, delivery date indicators, delivery quality indicators, etc., and then take 10% of the produced products as Multiple production samples, further quality inspection of multiple production samples based on multiple production indicators set, and then multiple sets of indicator data, in addition, multiple indicator thresholds will be set on the basis of multiple production indicators , where multiple production indicators correspond to the set indicator thresholds one by one, and then use the set multiple indicator thresholds to construct an indicator threshold set. For example, when the production sample meets the production indicator, that is, 85% and above, when the production sample does not When the production index is met, that is, below 85%, if the index threshold is set according to the production index to be 85% to 95%, when traversing multiple sets of index data, it is judged whether the obtained multiple sets of index data meet the set index threshold set, thereby generating The pass rate of batch products, where the pass rate is divided by the number of production samples that meet the production indicators divided by the total production number, assuming that the pass rate of batch products is 80%, when the pass rate of batch products is lower than 80%, it will On the basis of the twin model, the production process is inspected, that is, the abnormal correction of the birth process is performed on the production samples that do not meet the production indicators, so that the probability of the production samples meeting the production indicators is increased, and then the production optimization management is realized.

Embodiment two

Based on the same inventive concept as that of an intelligent stainless steel chain production management method in the foregoing embodiments, as shown in Figure 4, the present application provides an intelligent stainless steel chain production management system, which includes:

An information collection point module 1, the information collection point module 1 is used to obtain the distribution information of the production workshop, and determine the information collection point based on the distribution information of the production workshop;

A real-time production information module 2, the real-time production information module 2 is used to deploy multiple sensors based on the information collection points, and use the multiple sensors as an information interaction intermediary to obtain real-time production information;

A model building module 3, the model building module 3 is used to perform dynamic simulation based on digital twin technology to generate a production twin model according to the real-time production information, wherein the production twin model is synchronized with the actual production state;

A production forecast planning module 4, the production forecast planning module 4 is used to determine the production forecast plan based on the production order information;

A failure probability prediction result module 5, the failure probability prediction result module 5 is used to perform production failure probability prediction according to the production twin model based on the production expectation planning, and generate a failure probability prediction result;

A production optimization management module 6, which is used to perform production operation and maintenance optimization based on the failure probability prediction results, so as to realize production optimization management.

Furthermore, the system also includes:

Production process module, the production process module is used to obtain the product production process;

Multiple process area modules, the multiple process area modules are used to divide the production workshop based on the product production process to obtain multiple process areas;

Adaptive information collection point module, the adaptive information collection point module is used to respectively determine the location of process equipment for the plurality of process areas, and determine the adaptive information collection point based on the location of the process equipment.

Furthermore, the system also includes:

Production failure probability prediction model module, the production failure probability prediction model module is used to build a production failure probability prediction model based on machine learning algorithms;

Production failure type module, the production failure type module is used to collect various production failure types based on big data;

A fault parameter module, the fault parameter module is used to perform quasi-fault experiments based on the production twin model based on the multiple types of production faults, and obtain multiple sets of fault parameters, wherein one type of production fault may correspond to multiple sets of fault parameters;

A fault parameter training module, the fault parameter training module is used to train the fault probability prediction model according to the multiple sets of fault parameters;

A failure prediction result output module, the failure prediction result output module is used to perform failure prediction on the real-time production information based on the failure probability prediction model, and output the failure prediction result, wherein the failure prediction result includes failure type, failure node and failure Probability, one-to-one correspondence between the two.

Furthermore, the system also includes:

A preset probability threshold set module, the preset probability threshold set module is used to set multiple preset probability thresholds based on the various types of production failures, and obtain a preset probability threshold set;

A judging module, configured to judge whether the failure probability corresponding to the faulty node satisfies a preset probability threshold based on the preset probability threshold set;

The adjustment instruction generation module is used to generate the operation adjustment instruction when the adjustment instruction generation module is satisfied.

Furthermore, the system also includes:

A production operation information determination module, the production operation information determination module is used to perform production trial operation based on the production twin model according to the operation adjustment instruction, and determine the production operation information of the faulty node;

An abnormal process information acquisition module, the abnormal process information acquisition module is used to extract abnormal information from the production operation information of the faulty node, and obtain abnormal process information by performing process matching;

Adjust the time zone module, the time zone adjustment module is used to obtain the running adjustment time zone;

The production optimization module is used to adjust the time zone based on the operation, correct the production operation according to the abnormal process information, and perform production optimization management.

Furthermore, the system also includes:

Production indicator module, the production indicator module is used to determine multiple production indicators based on production order information;

Multiple sets of indicator data acquisition module, the multiple sets of indicator data acquisition module is used to acquire multiple production samples, perform quality inspection on the multiple production samples based on the multiple production indicators, and acquire multiple sets of indicator data;

An indicator threshold set building module, the indicator threshold set building module is used to set indicator thresholds based on the multiple production indicators, and construct an indicator threshold set;

A product pass rate generation module, the product pass rate generation module is used to traverse the multiple sets of index data, determine whether the multiple sets of index data meet the set of index thresholds, and generate batch product pass rates;

A production anomaly correction module. The production anomaly correction module is used to perform production process inspection based on the production twin model and correct production anomalies when the qualified rate of the batch of products does not meet the standard.

Through the foregoing detailed description of an intelligent stainless steel chain production management method in this manual, those skilled in the art can clearly know an intelligent stainless steel chain production management method and system in this embodiment. For the device disclosed in the embodiment As far as it is concerned, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and for the relevant part, please refer to the description of the method part.

The above description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the application. Therefore, the present application will not be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims (7)

1. an intelligent stainless steel chain production management method, is characterized in that, described method is applied to production management system, and described system is connected with a plurality of sensor communication, and described method comprises: Obtaining distribution information of production workshops, and determining information collection points based on the distribution information of production workshops; A plurality of sensors are laid out based on the information collection point, and the plurality of sensors are used as an information interaction intermediary to obtain real-time production information; According to the real-time production information, dynamic simulation is performed based on digital twin technology to generate a production twin model, wherein the production twin model is synchronized with the actual production state; Determine production forecast planning based on production order information; Based on the production forecast planning, the production failure probability prediction is performed according to the production twin model, and a failure probability prediction result is generated; Production operation and maintenance optimization is performed based on the failure probability prediction results to realize production optimization management. 2. The method according to claim 1, wherein said determining information collection points based on said production workshop distribution information comprises: Obtain product production process; Divide the production workshop based on the product production process to obtain multiple process areas; The location of the process equipment is determined respectively for the plurality of process areas, and an adaptive information collection point is determined based on the location of the process equipment. 3. The method according to claim 1, wherein said generating a failure probability prediction result comprises: Build a production failure probability prediction model based on machine learning algorithms; Collect various types of production failures based on big data; According to the multiple types of production failures, a quasi-fault experiment is performed based on the production twin model to obtain multiple sets of failure parameters, wherein one type of production failure may correspond to multiple sets of failure parameters; training the failure probability prediction model according to the multiple sets of failure parameters; The fault prediction is performed on the real-time production information based on the fault probability prediction model, and a fault prediction result is output, wherein the fault prediction result includes a fault type, a fault node, and a fault probability, and the two are in one-to-one correspondence. 4. The method of claim 3, comprising: setting a plurality of preset probability thresholds based on the various types of production failures, and obtaining a set of preset probability thresholds; Based on the set of preset probability thresholds, judging whether the failure probability corresponding to the faulty node satisfies a preset probability threshold; When satisfied, a run adjustment instruction is generated. 5. The method of claim 4, comprising: According to the operation adjustment instruction, a production trial run is performed based on the production twin model, and the production operation information of the faulty node is determined; Extract abnormal information from the production operation information of the faulty node, and obtain abnormal process information by performing process matching; Get the running adjustment time zone; Based on the operation adjustment time zone, the production operation correction is performed according to the abnormal process information, and the production optimization management is performed. 6. The method of claim 1, comprising: Determine multiple production indicators based on production order information; Acquiring multiple production samples, performing quality inspection on the multiple production samples based on the multiple production indicators, and acquiring multiple sets of indicator data; Setting an index threshold based on the plurality of production indexes, and constructing an index threshold set; Traversing the multiple sets of index data, judging whether the multiple sets of index data meet the set of index thresholds, and generating a qualified rate of batch products; When the pass rate of the batch of products does not meet the standard, the inspection of the production process is carried out based on the production twin model, and the abnormal production is corrected. 7. An intelligent stainless steel chain production management system is characterized in that the system is connected with a plurality of sensors in communication, and the system includes: An information collection point module, the information collection point module is used to obtain the distribution information of the production workshop, and determine the information collection point based on the distribution information of the production workshop; A real-time production information module, the real-time production information module is used to deploy multiple sensors based on the information collection points, and use the multiple sensors as an information interaction intermediary to obtain real-time production information; A model building module, the model building module is used to perform dynamic simulation based on digital twin technology to generate a production twin model according to the real-time production information, wherein the production twin model is synchronized with the actual production state; A production forecast planning module, the production forecast planning module is used to determine the production forecast plan based on the production order information; A failure probability prediction result module, the failure probability prediction result module is used to perform production failure probability prediction according to the production twin model based on the production expectation planning, and generate a failure probability prediction result; A production optimization management module, the production optimization management module is used to perform production operation and maintenance optimization based on the failure probability prediction results, so as to realize production optimization management.

Images