WO2025229411A1

WO2025229411A1 - Methods and systems for identifying patterns in process data of industrial system

Info

Publication number: WO2025229411A1
Application number: PCT/IB2025/051823
Authority: WO
Inventors: Chandrika K R; Divya Sheel; Jaivik Haresh DAVE; Dinesh PATIL
Original assignee: ABB Schweiz AG
Current assignee: ABB Schweiz AG
Priority date: 2024-04-30
Filing date: 2025-02-20
Publication date: 2025-11-06
Anticipated expiration: 2026-10-30

Abstract

The present disclosure relates to methods and systems for identifying patterns in process data of industrial systems. The method comprises receiving real-time process data (102) comprising plurality of data points. Further, the method comprises determining similarity value of the plurality of data points by comparing plurality of data points with each of plurality of patterns. Furthermore, the method comprises determining that similarity value is above a threshold value for at least one pattern of the plurality of patterns (104). Thereafter, the method comprises notifying at least one pattern and determined similarity value. The plurality of patterns (104) is generated by receiving reference pattern and generating plurality of augmented patterns corresponding to reference pattern based on historical data. The plurality of patterns (104) is filtered from the plurality of augmented patterns, based on one or more exclusion conditions, using an Artificial Intelligence (AI) model trained on the historical data.

Description

TITLE: “METHODS AND SYSTEMS FOR IDENTIFYING PATTERNS IN PROCESS DATA OF INDUSTRIAL SYSTEM”

TECHNICAL FIELD

[001] The present disclosure generally relates to data analytics in industrial systems. More particularly, the present disclosure relates to methods and systems for identifying patterns in process data of industrial systems.

BACKGROUND

[002] Process monitoring plays an important role in ensuring reliable operation of any industrial system. Generally, the industrial plants implement control systems to monitor the processes. Such control systems for example, include, Supervisory Control and Data Acquisition (SCADA), Distributed Control System (DCS), and the like. The control systems gather process data from sensors located in the industrial plants and monitors the process data to provide insights to users. The control system continuously monitors the processes for identifying any abnormality in the processes.

[003] The information disclosed in this background of the disclosure section is only for enhancement of understanding of the general background of the invention and should not be taken as an acknowledgement or any form of suggestion that this information forms the prior art already known to a person skilled in the art.

SUMMARY

[004] In an embodiment, the present disclosure discloses a method for identifying patterns in process data of industrial systems. The method comprises receiving real-time process data comprising a plurality of data points. Further, the method comprises determining a similarity value of the plurality of data points by comparing the plurality of data points with each of a plurality of patterns. Furthermore, the method comprises determining, that the similarity value of the plurality of data points is above a threshold value for at least one pattern of the plurality of patterns. Thereafter, the method comprises notifying the at least one pattern and the determined similarity value on a device. The plurality of patterns is generated by receiving a reference pattern from one or more sources and generating a plurality of augmented patterns corresponding to the reference pattern based on historical data associated with the process. Further, the plurality of patterns is filtered from the plurality of augmented patterns, based on one or more exclusion conditions, using an Artificial Intelligence (Al) model trained on the historical data.

[005] In an embodiment, the present disclosure discloses a method for identifying patterns in process data of industrial systems. The method comprises receiving a reference pattern from one or more sources. Further, the method comprises generating a plurality of augmented patterns corresponding to the reference pattern based on historical data associated with a process in an industrial system. Furthermore, the method comprises filtering a plurality of patterns from the plurality of augmented patterns, based on one or more exclusion conditions, using an Al model. The Al model is trained using context data associated with the reference pattern and corresponding process knowledge.

[006] In an embodiment, the present disclosure discloses a system for identifying patterns in process data of industrial systems. The system comprises a processor and a memory. The processor is configured to receive real-time process data comprising a plurality of data points. Further, the processor is configured to determine a similarity value of the plurality of data points by comparing the plurality of data points with each of a plurality of patterns. Furthermore, the processor is configured to determine that the similarity value of the plurality of data points is above a threshold value for at least one pattern of the plurality of patterns. Thereafter, the processor is configured to notify the at least one pattern and the determined similarity value on a device. The plurality of patterns is generated by receiving a reference pattern from one or more sources and generating a plurality of augmented patterns corresponding to the reference pattern based on historical data associated with the process. Further, the plurality of patterns is filtered from the plurality of augmented patterns, based on one or more exclusion conditions, using an Artificial Intelligence (Al) model trained on the historical data.

[007] In an embodiment, the present disclosure discloses a system for identifying patterns in process data of industrial systems. The system comprises a processor and a memory. The processor is configured to receive a reference pattern from one or more sources. Further, the processor is configured to generate a plurality of augmented patterns corresponding to the reference pattern based on historical data associated with a process in an industrial system. Furthermore, the processor is configured to filter a plurality of patterns from the plurality of augmented patterns, based on one or more exclusion conditions, using an Al model. The Al model is trained using context data associated with the reference pattern and corresponding process knowledge.

[008] The foregoing summary is illustrative only and is not intended to be in any way limiting. In addition to the illustrative aspects, embodiments, and features described above, further aspects, embodiments, and features will become apparent by reference to the drawings and the following detailed description.

BRIEF DESCRIPTION OF THE ACCOMPANYING DRAWINGS

[009] The novel features and characteristics of the disclosure are set forth in the appended claims. The disclosure itself, however, as well as a preferred mode of use, further objectives, and advantages thereof, will best be understood by reference to the following detailed description of an illustrative embodiment when read in conjunction with the accompanying figures. One or more embodiments are now described, by way of example only, with reference to the accompanying figures wherein like reference numerals represent like elements and in which:

[0010] Figure 1 illustrates an exemplary environment for identifying patterns in process data of industrial systems, in accordance with some embodiments of the present disclosure;

[0011] Figure 2 illustrates a detailed diagram of a system for identifying patterns in the process data of the industrial systems, in accordance with some embodiments of the present disclosure;

[0012] Figures 3A-3C show exemplary illustrations for identifying patterns in the process data of the industrial systems, in accordance with some embodiments of the present disclosure;

[0013] Figure 4 shows an exemplary flow chart illustrating method steps for generating a plurality of patterns, in accordance with some embodiments of the present disclosure;

[0014] Figure 5 shows an exemplary flow chart illustrating method steps for identifying patterns in the process data of the industrial systems, in accordance with some embodiments of the present disclosure;

[0015] Figure 6 shows a block diagram of a general-purpose computing system for identifying patterns in the process data of the industrial systems, in accordance with embodiments of the present disclosure. [0016] It should be appreciated by those skilled in the art that any block diagram herein represents conceptual views of illustrative systems embodying the principles of the present subject matter. Similarly, it will be appreciated that any flow charts, flow diagrams, state transition diagrams, pseudo code, and the like represent various processes which may be substantially represented in computer readable medium and executed by a computer or processor, whether or not such computer or processor is explicitly shown.

DETAILED DESCRIPTION

[0017] In the present document, the word "exemplary" is used herein to mean "serving as an example, instance, or illustration." Any embodiment or implementation of the present subject matter described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments.

[0018] While the disclosure is susceptible to various modifications and alternative forms, specific embodiment thereof has been shown by way of example in the drawings and will be described in detail below. It should be understood, however that it is not intended to limit the disclosure to the particular forms disclosed, but on the contrary, the disclosure is to cover all modifications, equivalents, and alternatives falling within the scope of the disclosure.

[0019] The terms “comprises”, “comprising”, or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a setup, device or method that comprises a list of components or steps does not include only those components or steps but may include other components or steps not expressly listed or inherent to such setup or device or method. In other words, one or more elements in a system or apparatus proceeded by “comprises. . . a” does not, without more constraints, preclude the existence of other elements or additional elements in the system or apparatus.

[0020] Industrial plants implement control systems to monitor the processes. The control systems gather process data from sensors located in the industrial plants and monitors the process data to provide insights to users. The users associated with the industrial systems such as an operator or a process engineer may desire to monitor patterns of interest in the process data. For instance, the user may observe certain pattern in the process data at a point of time. The user may desire to monitor such pattern in a future point of time. The users may desire to monitor such patterns of interest to identify abnormal events in an industrial plant, generating new patterns for use in data analytics of the industrial plant, and the like. The existing methods for online monitoring of the process data do not provide a methodology that allows the users to monitor patterns of interest in the process data.

[0021] The present disclosure provides methods and systems for identifying patterns in process data of industrial systems. Users or operators of the industrial systems may desire to monitor pattern of interest in the process data. The present disclosure allows to generate multiple patterns similar to the pattern of interest/reference pattern input by the user. These patterns are compared to real-time process data to determine a similarity value and notify the user when a pattern similar to the pattern of interest is observed in the real-time process data. Hence, the present disclosure enables monitoring of pattern of interest defined by users. The monitoring of pattern of interests allows the users to identify abnormal events in an industrial plant, correlate between different events occurring in the industrial plant, perform early detection of certain events, generating new patterns for use in data analytics of the industrial plant, and the like.

[0022] The present disclosure generates augmented patterns by considering noise and time variations with respect to the reference pattern in the process data. In this way, the present disclosure not only monitors the exact pattern defined by the user in the process data, but also considers the pattern subjected to noise and time variations in real-time. Also, the present disclosure allows to filter the augmented patterns to exclude patterns corresponding to certain pre-defined events which may not be desired by the user.

[0023] Figure 1 illustrates an exemplary environment 100 for identifying patterns in process data of industrial systems, in accordance with embodiments of the present disclosure. The environment 100 comprises a system 106 and a device 108. The system 106 is configured to identify a plurality of patterns 104 in process data 102. The process data 102 refers to data received from a process of an industrial system. The process of the industrial system may include, for example, oil production process, cement manufacturing process, and the like. The process data 102 may be collected from various sensors equipped in the process. The process data 102 is monitored and analyzed to improve operational efficiency, enhance process quality, reduce downtime, and ensure safety and compliance of the process. Generally, the process data 102 is analysed by identifying patterns in the process data 102 and analysing the patterns to perform predictions or gain insights. [0024] In the present disclosure, the system 106 is configured to identify patterns in the process data 102 of the industrial system. Herein, the system 106 receives a reference pattern from one or more sources. For instance, the system 106 receives the reference pattern from an operator associated with an industrial plant. The reference pattern may be a pattern of interest to the operator. The system 106 generates multiple augmented patterns corresponding to the reference pattern based on historical data of the process. The augmented patterns may include patterns similar to the reference pattern including time variations/noise with respect to the reference pattern. Then, the system 106 filters a plurality of patterns 104 from the augmented patterns based on one or more exclusion conditions using an Al model trained on the historical data. For instance, a user may define certain pre-defined event which is not desired for monitoring in the one or more exclusion conditions. Such patterns corresponding to the pre-defined event is filtered. As shown in Figure 1, the plurality of patterns 104 may be generated corresponding to the reference pattern. A first pattern in the plurality of patterns 104 illustrated in Figure 1 may be the reference pattern. The other three patterns may be similar patterns generated from the reference pattern.

[0025] The system 106 monitors the process data 102 in real-time basis the plurality of patterns 104. Herein, the system 106 receives the real-time process data 102 including data points. Each data point represents measurement data from the industrial plant received from sensors. The system 106 compares the data points with each of the plurality of patterns 104 and determines a similarity value of the data points. A pattern from the plurality of patterns 104 is identified when the similarity value of the data points is above a threshold value. The identified pattern is notified to the user on a device 108. For instance, the device 108 may be a user device such as a laptop, a handheld device, a fixed monitoring device, and the like. The identified pattern may be used, for instance, to perform early detection of certain events in the industrial plant. In an embodiment, the system 106 may be implemented in a variety of computing systems, such as a laptop computer, a desktop computer, a Personal Computer (PC), a notebook, a smartphone, a tablet, e-book readers, a server, a network server, a cloud-based server, and the like. In an embodiment, the system 106 may be implemented in the industrial system, an edge device, and/or a cloud server.

[0026] Figure 2 illustrates a detailed diagram 200 of the system 106 for identifying patterns in the process data 102 of the industrial system, in accordance with some embodiments of the present disclosure. The system 106 may include Central Processing Units 206 (also referred as “CPUs” or “one or more processors 206”), Input/ Output (I/O) interface 202, and a memory 204. In some embodiments, the memory 204 may be communicatively coupled to the one or more processors 206. The memory 204 stores instructions executable by the one or more processors 206. The one or more processors 206 may comprise at least one data processor for executing program components for executing user or system-generated requests. The memory 204 may be communicatively coupled to the one or more processors 206. The memory 204 stores instructions, executable by the one or more processors 206, which, on execution, may cause the one or more processors 206 to identify the patterns in the process data 102 of the industrial system. In an embodiment, the memory 204 may include one or more modules 210 and computation data 208. The one or more modules 210 may be configured to perform the steps of the present disclosure using the computation data 208, to identify the patterns in the process data 102 of the industrial system. In an embodiment, each of the one or more modules 210 may be a hardware unit which may be outside the memory 204 and coupled with the system 106. As used herein, the term modules 210 refers to an Application Specific Integrated Circuit (ASIC), an electronic circuit, a Field-Programmable Gate Arrays (FPGA), Programmable System-on-Chip (PSoC), a combinational logic circuit, and/or other suitable components that provide described functionality. The one or more modules 210 when configured with the described functionality defined in the present disclosure will result in a novel hardware. Further, the I/O interface 202 is coupled with the one or more processors 206 through which an input signal or/and an output signal is communicated. For example, the system 106 may receive the reference pattern from the one or more sources using the I/O interface 202.

[0027] In one implementation, the modules 210 may include, for example, a communication module 222, a pattern generation module 224, a filtering module 226, a determination module 228, a pattern identification module 230, and auxiliary modules 232. It will be appreciated that such aforementioned modules 205 may be represented as a single module or a combination of different modules. In one implementation, the computation data 208 may include, for example, communication data 212, pattern data 214, determination data 216, pattern identification data 218, and auxiliary data 220.

[0028] In an embodiment, the communication module 222 may be configured to receive a reference pattern from one or more sources. The reference pattern may include a pattern of interest to be monitored in the process data 102. For example, the reference pattern may be a pattern indicating a sudden dip in the flow rate of a fluid in a pipeline. In an embodiment, the reference pattern may be provided by a user associated with the process. For example, the communication module 222 may receive the reference pattern from an operator or a process engineer of an industrial plant. In another embodiment, the communication module 222 may receive the reference pattern from different units/systems associated with the industrial plant. For example, consider an Al model implemented in the industrial plant to predict energy consumption of various components in the industrial plant. The Al model may be trained to notify the communication module 222 of the system 106 in case any unexpected pattern other than patterns used during training the Al model. The Al model may provide the unexpected pattern to the communication module 222 to identify whether such pattern is observed again in future point of time. This helps to analyze unexpected events or generate new patterns in training of the Al model.

[0029] The communication module 222 may receive the reference pattern in various forms. In an example, a user may snip the pattern from an output of a system and transmit the pattern as an image to the communication module 222. In another example, the communication module 222 may receive the reference pattern as a set of data points from the other units/systems associated with the industrial plant. A person skilled in the art will appreciate that the communication module 222 may receive the pattern in any form other than the above- mentioned forms. Referring to Figure 3A, a reference pattern 302 is illustrated. The reference pattern 302 may be received from a user. Referring back to Figure 2, the reference pattern received from the one or more sources may be stored as the communication data 212 in the memory 204.

[0030] In an embodiment, the pattern generation module 224 may be configured to receive the reference pattern from the communication module 222. Further, the pattern generation module 224 may be configured to generate a plurality of augmented patterns corresponding to the reference pattern based on historical data associated with the process. The pattern generation module 224 receives the historical data of the process. The historical data of the process may comprise data logs of the process collected over time. The pattern generation module 224 performs a similarity search over the historical data to identify patterns similar to the reference pattern. The similarity search is explained in detail in subsequent paragraphs of the present description. The pattern generation module 224 identifies patterns in the historical data similar to the reference pattern that are subject to noise signals. Further, the pattern generation module 224 may generate the plurality of augmented patterns by adding noise to the reference pattern and performing the similarity search over the historical data. The pattern generation module 224 may add the noise using any noise addition techniques. The present disclosure considers similar patterns that are subject to noise signals/ adds noise to the reference pattern, as patterns are generally subject to noise in real-time process data. Hence, the present disclosure considers similar patterns to the reference pattern that are subject to noise signals. This helps to identify the reference pattern even when it is subject to noise in real-time process data.

[0031] Further, the pattern generation module 224 may identify the patterns in the historical data similar to the reference pattern, including time variations with respect to the reference pattern. Herein, the pattern generation module 224 may identify the patterns that are similar to the reference pattern but include variations with respect to time. For example, the pattern generation module 224 may identify patterns that are squished, stretched, etc. with respect to the reference pattern. In an embodiment, the pattern generation module 224 may generate the plurality of augmented patterns in a recursive manner. For instance, the pattern generation module 224 may generate the augmented patterns by identifying the patterns that are subject to noise signals. Then, the pattern generation module 224 may generate the augmented patterns by identifying similar patterns with the time variations. Further, the pattern generation module 224 may add noise to the identified patterns with the time variations to generate further patterns. Then, the pattern generation module 224 may again perform the similarity search on such patterns to identify additional patterns. The pattern generation module 224 may generate the plurality of augmented patterns in a recursive manner, until a required set of patterns are generated. Referring again to Figure 3A, 304 illustrates the plurality of augmented patterns that include both the patterns with time variations and that are subject to noise signals.

[0032] Referring back to Figure 2, in an embodiment, the pattern generation module 224 may perform the similarity search by sampling each of a plurality of historical data points in the historical data using a sliding window of defined length. The pattern generation module 224 may compare each sampled historical data point with the reference pattern based on a predefined value. The pre-defined value may indicate a value of similarity between the reference pattern and historical data points in the historical data. The pattern generation module 224 may identify patterns similar to the reference pattern based on the comparison. The pattern generation module 224 may identify similar patterns based on the pre-defined value.

[0033] In an embodiment, the pattern generation module 224 may exclude samples of historical data points based on the pre-defined value. Referring to Figure 3B, 308 illustrates sampling the plurality of historical data points using a sliding window ‘w’. In an example, consider the reference pattern includes 1000 data points. The size of the sliding window ‘w’ may be 100 data points. The pre-defined value may be 60%. The pattern generation module 224 may identify that the pre-defined value is reached when the sliding window ‘w’ slides over the plurality of historical data points six times. As shown in Figure 3B, the plurality of historical data points is similar to the reference pattern for the first 600 historical data points (match is indicated as ‘m’ in Figure 3B). In such a case, the samples of the remaining 400 historical data points may be excluded (exclusion is indicated as ‘e’ in Figure 3B). In another example, the pattern generation module 224 may identify that the plurality of data points starts to match after 400 historical data points. The pre-defined value is reached when the sliding window ‘w’ slides over the next 600 historical data points. In such a case, the samples of the initial 400 historical data points may be excluded. The exclusion of samples of the historical data points based on the pre-defined value ensures that there is no duplicate identification of similar patterns and increases accuracy in identification of similar patterns.

[0034] Referring back to Figure 2, the filtering module 226 is configured to filter a plurality of patterns 104 from the plurality of augmented patterns, using an Al model. The plurality of patterns 104 are filtered from the plurality of augmented patterns based on one or more exclusion conditions. The one or more exclusion conditions indicate patterns corresponding to pre-defined events to be excluded from the plurality of augmented patterns. Herein, the Al model is trained using context data associated with the reference pattern and corresponding process knowledge. The context data refers to metadata associated with each of the plurality of augmented data. For instance, consider that the plurality of augmented patterns includes a pattern that is identified from the historical data of a first process in a first plant. In such case, the context data includes the metadata regarding the first process. The Al model uses the context data along with the corresponding process knowledge/domain knowledge and filters the plurality of patterns 104 using the one or more exclusion conditions. The Al model identifies data specific to the process from the process knowledge using the context data. In an embodiment, the Al model may be a Large Language Model (LLM). A person skilled in the art will appreciate that any other Al models may be used.

[0035] The Al model may be trained using the one or more exclusion conditions to exclude patterns corresponding to the pre-defined events. The pre-defined events may be set a user/operator associated with the industrial system. The pre-defined events may be events that are not of interest or include known patterns. For example, the pre-defined events may include transient responses from a system, known maintenance trends, set point changes, start point and shut down points, and the like. The Al model is trained to identify these pre-defined events. For instance, the Al model is trained to understand a transient response from a system. The Al model excludes the patterns or contextual windows based on the one or more exclusion conditions. Referring again to Figure 3B, the Al model identifies that a fourth pattern among the plurality of augmented patterns 304 corresponds to a transient response. Hence, the fourth pattern is filtered from the plurality of augmented patterns 304 to generate the plurality of patterns 306. Referring back to Figure 2, the plurality of patterns 104 is stored as pattern data 214 in the memory 204.

[0036] In an embodiment, the communication module 222 is configured to receive real-time process data 102 comprising a plurality of data points. The communication module 222 may receive the plurality of patterns 104 generated from the reference pattern and the real-time process data 102 to monitor the plurality of patterns 104 in real-time. In an embodiment, the communication module 222 may receive each of the plurality of data points one at a time in real-time during the progress of the process. In another embodiment, the real-time process data 102 may be stored at a device in the industrial system for a particular time period which is then received at an edge device/cloud server for analysis. In such case, the communication module 222 may receive the plurality of data points as a log file/dataset. The real-time process data 102 may be stored as the communication data 212 in the memory 204.

[0037] In an embodiment, the determination module 228 may be configured to receive the realtime process data 102 from the communication module 222. Further, the determination module 228 may be configured to determine a similarity value of the plurality of data points by comparing the plurality of data points with each of a plurality of patterns 104. The comparison of the plurality of data points with each of the plurality of patterns 104 may include sliding a window of size ‘w’. For each data point among the plurality of data points, the window slides by one data point and each data point are compared with each of the plurality of patterns. The determination module 228 determines the similarity value of the plurality of data points based on the comparison. For example, consider the first pattern among the plurality of patterns 306 illustrated in Figure 3A. The first pattern may include 1000 data points. Each of the plurality of data points in the real-time process data 102 may be compared with each data point of the first pattern. The determination module 228 determines the similarity value of the plurality of data points based on the comparison. For example, consider that 700 data points in the real-time process data matches with the first pattern. The determination module 228 may determine the similarity value as 70%. Referring back to Figure 2, the similarity value may be stored as the determination data 216 in the memory 204.

[0038] In an embodiment, the pattern identification module 230 may be configured to receive the determination data 216 from the determination module 228. Further, the pattern identification module 230 may be configured to determine that the similarity value of the plurality of data points is above a threshold value for at least one pattern of the plurality of patterns 104. The determination of the threshold value is explained in the subsequent paragraph of the present description. The pattern identification module 230 may identify the at least one pattern when the similarity value of the plurality of data points is above the threshold value. Referring to the above-stated example, the similarity value of the first pattern is 70%. The threshold value be set as 60%. Hence, the first pattern may be identified as a pattern of interest in the real-time process data 102. In an embodiment, the pattern identification module 230 is configured to exclude subsequent samples of data points when the similarity value between the plurality of data points and at least one of the plurality of patterns 104 is above the threshold value. For example, referring to Figure 3C, the window of size ‘w’ slides over the real-time process data 102 as illustrated in 310. The pattern identification module 230 determines the similarity value exceeding the threshold value when the window moves by 600 points. The samples of the remaining 400 data points may be excluded to avoid any duplication in notifying the identified pattern. The at least one pattern and the similarity value may be stored as the pattern identification data 218 in the memory 204.

[0039] In an embodiment, the threshold value is determined by mapping each of the plurality of patterns 104 with the historical data. The plurality of patterns 104 are mapped with the historical data so as to determine similarities in the generated plurality of patterns 104 and the patterns that exist in processes from the historical data. A plurality of similarity values may be determined between each of the plurality of patterns 104 and the historical data. The threshold value is determined based on the plurality of similarity values. In an embodiment, a similarity search technique such as cosine similarity may be used to generate a set of distance vectors consisting of the similarity distance. The plurality of patterns 104 with a high similarity score (say 75%, which the operator/user can set) are selected for determining the threshold value. In an embodiment, the threshold value is adjusted by selecting a Doth value of sorted distance vectors as the similarity threshold value. In another embodiment, an adaptive quantile technique may be used to select the upper quantile of the similarity value with corresponding patterns. A person skilled in the art will appreciate that any other techniques may be used to determine the plurality of similarity values and adjust the similarity threshold value.

[0040] In an embodiment, the communication module 222 may be configured to receive the pattern identification data 218 from the pattern identification module 230. Further, the communication module 222 may be configured to notify the at least one pattern and the determined similarity value on a device 108. The at least one pattern and the determined similarity value may be notified to a user or another unit/system in the industrial plant. In an example, the device 108 may include a user device such as a laptop, a desktop, a smartphone, and the like. In another example, the device 108 may include the device/the system 106 that identifies the at least one pattern. The notification may be used by the users to identify abnormal events in an industrial plant, correlate between different events occurring in the industrial plant, perform early detection of certain events, generating new patterns for use in data analytics of the industrial plant, and the like. In an example, consider a sudden dip in pump flow rate observed by an operator. Also, the operator may observe that there is a pump trip. The operator may desire to monitor such a pattern in future point of time and analyze whether the pump trip and the sudden dip in flow rate are correlated to each other. In such a case, the claimed invention allows the operator to monitor patterns of interest in the process data.

[0041] The auxiliary data 220 may store data, including temporary data and temporary files, generated by the one or more modules 210 for performing the various functions of the system 106. The one or more modules 210 may also include the auxiliary modules 232 to perform various miscellaneous functionalities of the system 106. The auxiliary data 220 may be stored in the memory 204. It will be appreciated that the one or more modules 210 may be represented as a single module or a combination of different modules.

[0042] Figure 4 shows an exemplary flow chart illustrating method steps for identifying patterns in the process data of the industrial system, in accordance with some embodiments of the present disclosure. As illustrated in Figure 4, the method 400 may comprise one or more steps. The method 400 may be described in the general context of computer executable instructions. Generally, computer executable instructions can include routines, programs, objects, components, data structures, procedures, modules, and functions, which perform particular functions or implement particular abstract data types. [0043] The order in which the method 400 is described is not intended to be construed as a limitation, and any number of the described method blocks can be combined in any order to implement the method. Additionally, individual blocks may be deleted from the methods without departing from the scope of the subject matter described herein. Furthermore, the method can be implemented in any suitable hardware, software, firmware, or combination thereof.

[0044] At step 402, the reference pattern is received from the one or more sources. The reference pattern may include a pattern of interest to be monitored in the process data 102. In an embodiment, the reference pattern may be provided by a user associated with the process. In another embodiment, the system 106 may receive the reference pattern from different units/systems associated with the industrial plant.

[0045] At step 404, a plurality of augmented patterns is generated corresponding to the reference pattern based on historical data associated with the process. The system 106 performs a similarity search over the historical data to identify patterns similar to the reference pattern. The system 106 identifies patterns in the historical data similar to the reference pattern that are subject to noise signals. Further, the system 106 may identify the patterns in the historical data similar to the reference pattern, including time variations with respect to the reference pattern. In an embodiment, the system 106 may generate the plurality of augmented patterns in a recursive manner. In an embodiment, the system 106 may perform the similarity search by sampling each of a plurality of historical data points in the historical data using a sliding window of defined length. The system 106 may compare each sampled historical data point with the reference pattern based on a pre-defined value. The pre-defined value may indicate a value of similarity between the reference pattern and historical data points in the historical data. The system 106 may identify patterns similar to the reference pattern based on the comparison. The system 106 may identify similar patterns based on the pre-defined value. In an embodiment, the system 106 may exclude samples of historical data points based on the pre-defined value.

[0046] At step 406, a plurality of patterns 104 may be filtered from the plurality of augmented patterns, using an Al model. The plurality of patterns 104 are filtered from the plurality of augmented patterns based on one or more exclusion conditions. The one or more exclusion conditions indicate patterns corresponding to pre-defined events to be excluded from the plurality of augmented patterns. Herein, the Al model is trained using context data associated with the reference pattern and corresponding process knowledge. The Al model may be trained using the one or more exclusion conditions to exclude patterns corresponding to the pre-defined events. The pre-defined events may be set a user/operator associated with the industrial system. The pre-defined events may be events that are not of interest or are not required to be monitored or known patterns.

[0047] Figure 5 shows an exemplary flow chart illustrating method steps for identifying patterns in the process data of the industrial system, in accordance with some embodiments of the present disclosure. As illustrated in Figure 5, the method 500 may comprise one or more steps. The method 500 may be described in the general context of computer executable instructions. Generally, computer executable instructions can include routines, programs, objects, components, data structures, procedures, modules, and functions, which perform particular functions or implement particular abstract data types.

[0048] The order in which the method 500 is described is not intended to be construed as a limitation, and any number of the described method blocks can be combined in any order to implement the method. Additionally, individual blocks may be deleted from the methods without departing from the scope of the subject matter described herein. Furthermore, the method can be implemented in any suitable hardware, software, firmware, or combination thereof.

[0049] At step 502, real-time process data 102 comprising a plurality of data points is received. The system 106 may receive the plurality of patterns 104 generated from the reference pattern and the real-time process data 102 to monitor the plurality of patterns 104 in real-time.

[0050] At step 504, a similarity value of the plurality of data points is determined by comparing the plurality of data points with each of a plurality of patterns 104. The comparison of the plurality of data points with each of the plurality of patterns 104 may include sliding a window of size ‘w’. For each data point among the plurality of data points, the window slides by one data point and each data point are compared with each of the plurality of patterns. The system 106 determines the similarity value of the plurality of data points based on the comparison.

[0051] At step 506, the similarity value of the plurality of data points may be determined to be above a threshold value for at least one pattern of the plurality of patterns 104. In an embodiment, the system 106 is configured to exclude subsequent samples of data points when the similarity value between the plurality of data points and at least one of the plurality of patterns 104 is above the threshold value. In an embodiment, the threshold value is determined by mapping each of the plurality of patterns 104 with the historical data. A plurality of similarity values may be determined between each of the plurality of patterns 104 and the historical data. The threshold value is determined based on the plurality of similarity values.

[0052] At step 508, the at least one pattern and the determined similarity value is notified on a device 108. The at least one pattern and the determined similarity value may be notified to a user or another unit/system in the industrial plant. In an example, the device 108 may include a user device such as a laptop, a desktop, a smartphone, and the like. In another example, the device 108 may include the device/the system 106 that identifies the at least one pattern. The notification may be used by the users to identify abnormal events in an industrial plant, correlate between different events occurring in the industrial plant, perform early detection of certain events, generating new patterns for use in data analytics of the industrial plant, and the like.

COMPUTER SYSTEM

[0053] Figure 6 illustrates a block diagram of an exemplary computer system 600 for implementing embodiments consistent with the present disclosure. In an embodiment, the computer system 600 may be the system 106. Thus, the computer system 600 may be used to identify patterns in the process data in the industrial system. The computer system 600 may comprise a Central Processing Unit 604 (also referred as “CPU” or “processor”). The processor 604 may comprise at least one data processor. The processor 604 may include specialized processing units such as integrated system (bus) controllers, memory management control units, floating point units, graphics processing units, digital signal processing units, etc.

[0054] The processor 604 may be disposed in communication with one or more input/output (I/O) devices (not shown) via I/O interface 602. The I/O interface 602 may employ communication protocols/methods such as, without limitation, audio, analog, digital, monoaural, RCA, stereo, IEEE (Institute of Electrical and Electronics Engineers) -1394, serial bus, universal serial bus (USB), infrared, PS/2, BNC, coaxial, component, composite, digital visual interface (DVI), high-definition multimedia interface (HDMI), Radio Frequency (RF) antennas, S-Video, VGA, IEEE 802.n /b/g/n/x, Bluetooth, cellular (e.g., code-division multiple access (CDMA), high-speed packet access (HSPA+), global system for mobile communications (GSM), long-term evolution (LTE), WiMax, or the like), etc. [0055] Using the I/O interface 602, the computer system 600 may communicate with one or more I/O devices. For example, the input device 620 may be an antenna, keyboard, mouse, joystick, (infrared) remote control, camera, card reader, fax machine, dongle, biometric reader, microphone, touch screen, touchpad, trackball, stylus, scanner, storage device, transceiver, video device/source, etc. The output device 622 may be a printer, fax machine, video display (e.g., cathode ray tube (CRT), liquid crystal display (LCD), light-emitting diode (LED), plasma, Plasma display panel (PDP), Organic light-emitting diode display (OLED) or the like), audio speaker, etc.

[0056] The processor 604 may be disposed in communication with the communication network 618 via a network interface 606. The network interface 606 may communicate with the communication network 618. The network interface 606 may employ connection protocols including, without limitation, direct connect, Ethernet (e.g., twisted pair 10/100/1000 Base T), transmission control protocol/internet protocol (TCP/IP), token ring, IEEE 802.11a/b/g/n/x, etc. The communication network 618 may include, without limitation, a direct interconnection, local area network (LAN), wide area network (WAN), wireless network (e.g., using Wireless Application Protocol), the Internet, etc. The network interface 606 may employ connection protocols include, but not limited to, direct connect, Ethernet (e.g., twisted pair 10/100/1000 Base T), transmission control protocol/internet protocol (TCP/IP), token ring, IEEE 802.11a/b/g/n/x, etc.

[0057] The communication network 618 includes, but is not limited to, a direct interconnection, an e-commerce network, a peer to peer (P2P) network, local area network (LAN), wide area network (WAN), wireless network (e.g., using Wireless Application Protocol), the Internet, WiFi, and such. The first network and the second network may either be a dedicated network or a shared network, which represents an association of the different types of networks that use a variety of protocols, for example, Hypertext Transfer Protocol (HTTP), Transmission Control Protocol/internet Protocol (TCP/IP), Wireless Application Protocol (WAP), etc., to communicate with each other. Further, the first network and the second network may include a variety of network devices, including routers, bridges, servers, computing devices, storage devices, etc.

[0058] In some embodiments, the processor 604 may be disposed in communication with a memory 610 (e.g., RAM, ROM, etc. not shown in Figure 5) via a storage interface 608. The storage interface 608 may connect to memory 610 including, without limitation, memory drives, removable disc drives, etc., employing connection protocols such as serial advanced technology attachment (SATA), Integrated Drive Electronics (IDE), IEEE- 1394, Universal Serial Bus (USB), fiber channel, Small Computer Systems Interface (SCSI), etc. The memory drives may further include a drum, magnetic disc drive, magneto-optical drive, optical drive, Redundant Array of Independent Discs (RAID), solid-state memory devices, solid-state drives, etc.

[0059] The memory 610 may store a collection of program or database components, including, without limitation, user interface 612, an operating system 614, web browser 616 etc. In some embodiments, computer system 600 may store user/application data, such as, the data, variables, records, etc., as described in this disclosure. Such databases may be implemented as fault-tolerant, relational, scalable, secure databases such as Oracle ® or Sybase®.

[0060] The operating system 614 may facilitate resource management and operation of the computer system 600. Examples of operating systems include, without limitation, APPLE MACINTOSH¹* OS X, UNIX^R, UNIX-like system distributions (E.G., BERKELEY SOFTWARE DISTRIBUTION™ (BSD), FREEBSD™, NETBSD™, OPENBSD™, etc.), LINUX DISTRIBUTIONS™ (E.G., RED HAT™, UBUNTU™, KUBUNTU™, etc.), IBM™ OS/2, MICROSOFT™ WINDOWS™ (XP™, VISTA™/7/8, 10 etc.), APPLE^R IOS™, GOOGLE^R ANDROID™, BLACKBERRY¹* OS, or the like.

[0061] In some embodiments, the computer system 600 may implement the web browser 616 stored program component. The web browser 616 may be a hypertext viewing application, for example MICROSOFT¹* INTERNET EXPLORER™, GOOGLE¹* CHROME™⁰, MOZILLA¹* FIREFOX™, APPLE¹* SAFARI™, etc. Secure web browsing may be provided using Secure Hypertext Transport Protocol (HTTPS), Secure Sockets Layer (SSL), Transport Layer Security (TLS), etc. Web browsers 616 may utilize facilities such as AJAX™, DHTML™, ADOBE¹* FLASH™, JAVASCRIPT™, JAVA™, Application Programming Interfaces (APIs), etc. In some embodiments, the computer system 600 may implement a mail server (not shown in Figure) stored program component. The mail server may be an Internet mail server such as Microsoft Exchange, or the like. The mail server may utilize facilities such as ASP™, ACTIVEX™, ANSI™ C++/C#, MICROSOFT¹*, .NET™, CGI SCRIPTS™, JAVA™, JAVASCRIPT™, PERL™, PHP™, PYTHON™, WEBOBJECTS™, etc. The mail server may utilize communication protocols such as Internet Message Access Protocol (IMAP), Messaging Application Programming Interface (MAPI), MICROSOFT¹ exchange, Post Office Protocol (POP), Simple Mail Transfer Protocol (SMTP), or the like. In some embodiments, the computer system 600 may implement a mail client stored program component. The mail client (not shown in Figure) may be a mail viewing application, such as APPLE^R MAIL™, MICROSOFT¹* ENTOURAGE™, MICROSOFT¹* OUTLOOK™, MOZILLA¹* THUNDERBIRD™, etc.

[0062] Furthermore, one or more computer-readable storage media may be utilized in implementing embodiments consistent with the present disclosure. A computer-readable storage medium refers to any type of physical memory on which information or data readable by a processor may be stored. Thus, a computer-readable storage medium may store instructions for execution by one or more processors, including instructions for causing the processor(s) to perform steps or stages consistent with the embodiments described herein. The term “computer-readable medium” should be understood to include tangible items and exclude carrier waves and transient signals, i.e., be non-transitory. Examples include Random Access Memory (RAM), Read-Only Memory (ROM), volatile memory, non-volatile memory, hard drives, Compact Disc Read-Only Memory (CD ROMs), Digital Video Disc (DVDs), flash drives, disks, and any other known physical storage media.

[0063] The present disclosure provides methods and systems for identifying patterns in process data of industrial systems. The present disclosure allows to generate multiple patterns similar to the pattern of interest/reference pattern input by the user. The present disclosure enables monitoring of pattern of interest defined by users. The monitoring of pattern of interests allows the users to identify abnormal events in an industrial plant, correlate between different events occurring in the industrial plant, perform early detection of certain events, generating new patterns for use in data analytics of the industrial plant, and the like.

[0064] The present disclosure generates augmented patterns by considering noise and time variations with respect to the reference pattern in the process data. In this way, the present disclosure not only monitors the exact pattern defined by the user in the process data, but also considers the pattern subjected to noise and time variations in real-time. Also, the present disclosure allows to filter the augmented patterns to exclude patterns corresponding to certain pre-defined events which may not be desired by the user. [0065] The terms "an embodiment", "embodiment", "embodiments", "the embodiment", "the embodiments", "one or more embodiments", "some embodiments", and "one embodiment" mean "one or more (but not all) embodiments of the invention(s)" unless expressly specified otherwise.

[0066] The terms "including", "comprising", “having” and variations thereof mean "including but not limited to", unless expressly specified otherwise.

[0067] The enumerated listing of items does not imply that any or all of the items are mutually exclusive, unless expressly specified otherwise. The terms "a", "an" and "the" mean "one or more", unless expressly specified otherwise.

[0068] A description of an embodiment with several components in communication with each other does not imply that all such components are required. On the contrary a variety of optional components are described to illustrate the wide variety of possible embodiments of the invention.

[0069] When a single device or article is described herein, it will be readily apparent that more than one device/article (whether or not they cooperate) may be used in place of a single device/article. Similarly, where more than one device or article is described herein (whether or not they cooperate), it will be readily apparent that a single device/article may be used in place of the more than one device or article, or a different number of devices/articles may be used instead of the shown number of devices or programs. The functionality and/or the features of a device may be alternatively embodied by one or more other devices which are not explicitly described as having such functionality /features. Thus, other embodiments of the invention need not include the device itself.

[0070] The illustrated operations of Figures 4 and 5 show certain events occurring in a certain order. In alternative embodiments, certain operations may be performed in a different order, modified, or removed. Moreover, steps may be added to the above-described logic and still conform to the described embodiments. Further, operations described herein may occur sequentially or certain operations may be processed in parallel. Yet further, operations may be performed by a single processing unit or by distributed processing units.

[0071] Finally, the language used in the specification has been principally selected for readability and instructional purposes, and it may not have been selected to delineate or circumscribe the inventive subject matter. It is therefore intended that the scope of the invention be limited not by this detailed description, but rather by any claims that issue on an application based here on. Accordingly, the disclosure of the embodiments of the invention is intended to be illustrative, but not limiting, of the scope of the invention, which is set forth in the following claims.

[0072] While various aspects and embodiments have been disclosed herein, other aspects and embodiments will be apparent to those skilled in the art. The various aspects and embodiments disclosed herein are for purposes of illustration and are not intended to be limiting, with the true scope being indicated by the following claims.

Referral Numerals:

Claims

We claim:

1. A method for identifying patterns in process data of industrial systems, the method comprising: receiving, by a processor, real-time process data comprising a plurality of data points; determining, by the processor, a similarity value of the plurality of data points by comparing the plurality of data points with each of a plurality of patterns; determining, by the processor, that the similarity value of the plurality of data points is above a threshold value for at least one pattern of the plurality of patterns; and notifying on a device, by the processor, the at least one pattern and the determined similarity value, wherein the plurality of patterns is generated by: receiving a reference pattern from one or more sources; generating a plurality of augmented patterns corresponding to the reference pattern based on historical data associated with the process; and filtering the plurality of patterns from the plurality of augmented patterns, based on one or more exclusion conditions, using an Artificial Intelligence (Al) model trained on the historical data.

2 The method as claimed in claim 1, wherein generating the plurality of augmented patterns further comprising: identifying patterns in the historical data similar to the reference pattern, including time variations with respect to the reference pattern; identifying patterns in the historical data similar to the reference pattern that are subject to noise signals; and generating the plurality of augmented patterns based on the identification.

3 The method as claimed in claim 1, wherein generating the plurality of augmented patterns based on the historical data comprising: sampling each of a plurality of historical data points in the historical data using a sliding window of defined length; comparing each sampled historical data point with the reference pattern; and excluding, by the processor, samples of historical data points based on a pre-defined value.

4 The method as claimed in claim 1, further comprising: excluding subsequent samples of data points when the similarity value between the plurality of data points and at least one of the plurality of patterns is above the threshold value.

5. The method as claimed in claim 1, wherein determining the threshold value comprising: mapping each of the plurality of patterns with the historical data; and determining a plurality of similarity values between each of the plurality of patterns and the historical data, wherein the threshold value is determined based on the plurality of similarity values. The method as claimed in claim 1, wherein the one or more exclusion conditions indicate patterns corresponding to pre-defined events to be excluded from the plurality of augmented patterns.

7 A method for identifying patterns in process data of industrial systems, the method comprising: receiving, by a processor, a reference pattern from one or more sources; generating, by the processor, a plurality of augmented patterns corresponding to the reference pattern based on historical data associated with a process in an industrial system; and filtering, by the processor, a plurality of patterns from the plurality of augmented patterns, based on one or more exclusion conditions, using an Artificial Intelligence (Al) model, wherein the Al model is trained using context data associated with the reference pattern and corresponding process knowledge.

8 The method as claimed in claim 7, wherein generating the plurality of augmented patterns corresponding to the reference pattern based on the historical data comprising: identifying patterns in the historical data similar to the reference pattern, including time variations with respect to the reference pattern; identifying patterns in the historical data similar to the reference pattern that are subject to noise signals; and generating the plurality of augmented patterns based on the identification. The method as claimed in claim 8, wherein the plurality of augmented patterns is generated based on the historical data in a recursive manner. 0 A system for identifying patterns in process data of industrial systems, the system comprises: a processor; and a memory, wherein the memory stores processor-executable instructions, which, on execution, causes the processor to: receive real-time process data comprising a plurality of data points; determine a similarity value of the plurality of data points by comparing the plurality of data points with each of a plurality of patterns; determine that the similarity value of the plurality of data points is above a threshold value for at least one pattern of the plurality of patterns; and notify on a device the at least one pattern and the determined similarity value, wherein the plurality of patterns is generated by: receiving a reference pattern from one or more sources; generating a plurality of augmented patterns corresponding to the reference pattern based on historical data associated with the process; and filtering the plurality of patterns from the plurality of augmented patterns, based on one or more exclusion conditions, using an Artificial Intelligence (Al) model trained on the historical data. A system for identifying pre-defined patterns in process data of industrial systems, the system comprising: a processor; and a memory, wherein the memory stores processor-executable instructions, which, on execution, causes the processor to: receive a reference pattern from one or more sources; generate a plurality of augmented patterns corresponding to the reference pattern based on historical data associated with a process in an industrial system; and filter a plurality of patterns from the plurality of augmented patterns, based on one or more exclusion conditions, using an Artificial Intelligence (Al) model, wherein the Al model is trained using context data associated with the reference pattern and corresponding process knowledge.