Production line energy consumption monitoring system driven by intelligent optimization algorithm

Abstract

The invention provides a production line energy consumption monitoring system driven by an intelligent optimization algorithm, and relates to the technical field of computer processing, and the system comprises a data obtaining module which obtains image data collected by an industrial camera in real time, and uploads the image data through a timestamp; the data arrangement module is used for extracting based on the acquired image data according to the extracted target features to obtain a data set; the data processing module is used for extracting the image data of the data set, analyzing the image data to obtain a data subset of the continuous windows, obtaining the productivity of the data subset of the continuous windows, and performing subtraction to obtain the attenuation of the adjacent windows; and the data analysis module is used for solving the capacity attenuation rate of the continuous windows on the basis of the obtained attenuation amount of the adjacent windows, and evaluating the future capacity of the target characteristic on the basis of the capacity attenuation rate. According to the invention, the monitoring accuracy and timeliness are improved, the energy consumption cost is reduced, and the overall operation efficiency of the production line is improved.

Description

Technical Field

[0001] The present invention relates to the field of computer processing technologies, and particularly to an energy consumption monitoring system for a production line driven by an intelligent optimization algorithm. Background Art

[0002] Production line monitoring systems include fully intelligent unmanned production lines, semi-intelligent production lines, and labor-intensive production lines. The purpose of monitoring the operation status of the production line is to prevent potential accidents and monitor the operation status of the equipment on the production line, thereby reducing the occurrence of accidents.

[0003] Referring to Chinese Patent, Publication No.: CN104765322A, a disclosed production line monitoring system; And Chinese Patent, Publication No.: CN109597361A, a disclosed production line monitoring system and a production line monitoring method.

[0004] In the prior art including the above two patents, it mainly focuses on how to prevent potential accidents and monitor the operation status of equipment, so as to prevent the occurrence of accidents and the handling after the equipment stops operating. That is to say, the purpose is to ensure the healthy operation of the production line. And how to monitor the energy consumption of the production line, that is, if the work efficiency of the equipment or workers declines, the energy consumption remains unchanged within the same time unit, and the production capacity decreases, then in terms of the side, it is considered that the energy consumption increases. Therefore, how to obtain the production capacity of the production line to judge the energy consumption status, and perform feedback and processing to ensure that the energy consumption remains unchanged within the same time unit and the production capacity decline is maintained within a predetermined range is expected to be well solved. Summary of the Invention

[0005] In view of the above technical problems, the technical solution adopted by the present invention is an energy consumption monitoring system for a production line driven by an intelligent optimization algorithm, including: A data acquisition module that real-time acquires image data collected by an industrial camera and uploads it through a time stamp; A data sorting module that extracts based on the acquired image data and according to the extracted target features to obtain a data set; A data processing module that extracts the image data of the data set, analyzes it, obtains data subsets of consecutive windows, and obtains the production capacity of the data subsets of consecutive windows, takes the difference, and obtains the attenuation amount between adjacent windows; A data analysis module that calculates the production capacity attenuation rate of the consecutive windows based on the obtained attenuation amount between adjacent windows, and evaluates the future production capacity of the target features based on the production capacity attenuation rate; A data feedback module that matches the obtained evaluation with the execution regulations in the database and performs reporting and feedback.

[0006] Preferably, the data acquisition module includes: A factory building data acquisition unit, which is arranged in the factory building and is used to collect the overall image data in the factory building, labeled as X; A section data acquisition unit, which is used to collect the production lines in the above-mentioned factory building and divide the production lines according to a predetermined length, labeled as h0, h1,..., hn; A production output data acquisition unit, which is installed on the production line and arranges industrial cameras according to the division standard of the production line in the section data acquisition unit, and is used to collect the production quantity per unit time of this section of length, labeled as f0, f1,..., fn; A first data feedback unit, which formats the data according to the same time unit: time {x, (h0, f0), (h1, f1),..., (hn, fn)}.

[0007] Preferably, the data sorting module includes: An image preprocessing unit, which performs mean filtering - median filtering - Gaussian filtering on the acquired image data once to obtain a denoised picture; An image conversion unit, which converts the denoised picture into a grayscale image and performs enhancement processing on the grayscale image to obtain a clearly recognizable picture; A pixel unit extraction unit, which creates a grid for the clearly recognizable picture, labels the pixel points that can be recognized as features, and compares them with the target features to determine the type of the pixel points that can be recognized as features currently; A data integration unit, which classifies the same or similar features of the picture based on the determined type of the pixel points that can be recognized as features currently to obtain multiple sub - data constituting a data set.

[0008] Preferably, the sub - data includes the image data of the pixel points that can be recognized as features of the same type extracted in chronological order.

[0009] Preferably, the data processing module includes the following steps: S11. Extract a data set containing image data, and the image data in the data set is in a time series; S12. Divide the image data in the data set into a plurality of continuous data windows, and each data window contains a certain number of continuous image data; S13. For each data window, extract the image data therein to form a data subset of continuous windows, and each data subset contains the feature information of all the image data in the corresponding window; S14. For each data subset, calculate the production capacity value corresponding to the data subset according to a preset production capacity evaluation model, so as to obtain the correlation between specific features or processing results in the image data and the production capacity; S15. For consecutive data subsets, calculate the difference between the production capacity values of two adjacent data subsets to obtain the production capacity attenuation amount of adjacent windows, and the attenuation amount reflects the change in production capacity from one data window to the next data window; S16. Output the calculated production capacity attenuation amount of adjacent windows.

[0010] Preferably, obtaining the correlation between specific features or processing results in the image data and the production capacity in step S14 includes: S141. Select specific features that may be related to the production capacity from the image data or perform necessary preprocessing to extract effective features, and the effective features include the number of objects, size, shape, position, color, texture, brightness, and contrast; S142. Collect a certain number of image data with known production capacity values as training samples and label the production capacity values of these samples; S143. Use the labeled training samples to construct a production capacity evaluation model based on linear regression; S144. Use an independent validation data set to verify the trained model; S145. After training and verification, determine the final production capacity evaluation model and apply it to the production capacity evaluation of actual image data. During the evaluation process, the model will output the corresponding production capacity prediction value according to the specific features or processing results in the input image data.

[0011] Preferably, the calculation of the attenuation amount of adjacent windows includes: S21. Initialize an empty list or array to store the production capacity attenuation amount of adjacent windows.

[0012] S22. Traverse the production capacity data list, starting from the second element (i.e., the production capacity value of the second data window), and calculate the production capacity attenuation amount between the current window and the previous window. The calculation formula is: attenuation amount = current window production capacity value - previous window production capacity value.

[0013] S23. Add the calculated attenuation amount to the initialized list; S24. Format and output the list or array storing the attenuation amount.

[0014] Preferably, the data analysis module includes: A data preparation and preprocessing unit that inputs the calculated attenuation amount data of adjacent windows and uses the input production capacity data of consecutive windows as the basis for calculating the attenuation rate; A data evaluation unit, which obtains the decay rate of consecutive periods based on the root, calculates the average decay rate by taking the difference of consecutive windows, and takes the difference between the decay rate of each window and the average decay rate to obtain the starting point of the window time with a negative value, and determines the starting point of the current production capacity decline and the future production capacity during decline.

[0015] A data sorting unit binds the starting point of the current production capacity decline and the future production capacity during decline to target features to obtain evaluation data.

[0016] The present invention has at least the following beneficial effects: By obtaining and analyzing the image data on the production line in real time, and combining advanced algorithms and data processing technologies, it realizes precise monitoring of the production line capacity and intelligent evaluation of the energy consumption status. The system can timely detect signs of production capacity decline and accurately judge the energy consumption status, so as to take effective measures for feedback and processing to ensure the healthy operation and high-efficiency output of the production line. Compared with traditional methods, the present invention significantly improves the accuracy and timeliness of monitoring, reduces the energy consumption cost, and improves the overall operation efficiency of the production line. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0018] Figure 1 It is a module diagram of a production line energy consumption monitoring system driven by an intelligent optimization algorithm provided in Embodiment 1 of the present invention; Figure 2 It is a unit architecture diagram of a data acquisition module provided in Embodiment 1 of the present invention; Figure 3 It is a unit architecture diagram of a data sorting module provided in Embodiment 1 of the present invention; Figure 4 It is a flowchart of a data processing module provided in Embodiment 1 of the present invention; Figure 5 It is a unit architecture diagram of a data analysis module provided in Embodiment 1 of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0019] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0020] It should be noted that the terms "first", "second", etc. in the specification, claims and above-mentioned drawings of the present invention are used to distinguish similar objects, and do not necessarily describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of the present invention described here can be implemented in an order other than those illustrated or described here. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or server comprising a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices. Embodiment 1

[0021] This embodiment provides a production line energy consumption monitoring system driven by an intelligent optimization algorithm, including modules, such as Figure 1 shown: The data acquisition module acquires the image data collected by the industrial camera in real time and uploads it with a timestamp; Specifically, as Figure 2 shown, the data acquisition module includes: The plant data acquisition unit is arranged in the plant and is used to collect the overall image data in the plant, labeled as X; The section data acquisition unit is used to collect the production line in the above-mentioned plant and divide the production line into predetermined lengths, labeled as h0, h1,..., hn; The output data acquisition unit is installed on the production line and arranges industrial cameras according to the division standard of the production line in the section data acquisition unit. It is used to collect the production quantity per unit time of this section length, labeled as f0, f1,..., fn; The first data feedback unit formats the data according to the same time unit: time {x, (h0, f0), (h1, f1),..., (hn, fn)}.

[0022] The above technology ensures the accuracy and timeliness of the data by acquiring the image data collected by the industrial camera in real time and uploading the information with a timestamp. Collecting the overall image data in the plant provides a basis for evaluating the overall production environment. Dividing the production line into predetermined lengths helps to accurately evaluate the production capacity of each section of the production line. Then, collecting the production quantity per unit time through industrial cameras provides direct data for production capacity evaluation. Secondly, integrating the data according to time units ensures the continuity and comparability of the data.

[0023] The data sorting module extracts a data set based on the acquired image data and according to the extracted target features; Specifically, as Figure 3 shown, the data sorting module includes: An image preprocessing unit that performs mean filtering - median filtering - Gaussian filtering on the acquired image data once to obtain a denoised picture; An image conversion unit that converts the denoised picture into a grayscale image and performs enhancement processing on the grayscale image to obtain a clearly recognizable picture; A pixel unit extraction unit that creates a grid for the clearly recognizable picture, identifies the pixel points that can be recognized as features, and compares them with the target features to determine the type of the pixel points that can be recognized as features currently; A data integration unit that classifies the same or similar features of the picture based on the determined type of the pixel points that can be recognized as features currently to obtain multiple sub - data that make up the data set.

[0024] The sub - data includes the image data of the pixel points that can be recognized as features of the same type extracted in chronological order.

[0025] The above - mentioned technology extracts target features based on image data, forms a data set, and provides a reliable data basis for subsequent analysis. Through multiple filtering processes, image noise is effectively removed and image quality is improved. Then, the image is converted into a grayscale image and enhanced, which helps with feature extraction and recognition. Finally, by creating a grid and identifying feature pixel points, precise extraction of image features is achieved. Then, classifying the same or similar features forms multiple sub - data that make up the data set, which provides convenience for subsequent analysis.

[0026] Furthermore, the sub - data includes the image data of the pixel points that can be recognized as features of the same type extracted in chronological order. This definition enables the system to more precisely track and analyze specific features or events on the production line, thereby more accurately judging the signs of production capacity decline and energy consumption status.

[0027] A data processing module that extracts the image data of the data set, analyzes it, obtains data subsets of consecutive windows, and obtains the production capacity of the data subsets of consecutive windows, and takes the difference to obtain the attenuation amount between adjacent windows; Specifically, as Figure 4 shown, the data processing module includes the following steps: S11. Extract the data set containing image data, and the image data in the data set is in chronological order; S12. Divide the image data in the data set into multiple consecutive data windows, and each data window contains a certain number of consecutive image data; S13. For each data window, extract the image data therein to form a data subset of consecutive windows, where each data subset contains the feature information of all the image data within the corresponding window. S14. For each data subset, according to the preset production capacity evaluation model, calculate the production capacity value corresponding to this data subset to obtain the correlation between specific features or processing results in the image data and the production capacity. S15. For consecutive data subsets, calculate the difference between the production capacity values of two adjacent data subsets to obtain the production capacity attenuation amount of adjacent windows. The attenuation amount reflects the change in production capacity from one data window to the next. S16. Output the calculated production capacity attenuation amount of adjacent windows.

[0028] The correlation between specific features or processing results in the image data and the production capacity obtained in step S14 includes: S141. Select specific features in the image data that may be related to the production capacity or perform necessary preprocessing to extract effective features. The effective features include the number of objects, size, shape, position, color, texture, brightness, and contrast. S142. Collect a certain number of image data with known production capacity values as training samples and label the production capacity values of these samples. S143. Use the labeled training samples to construct a production capacity evaluation model based on linear regression. S144. Use an independent validation data set to validate the trained model. S145. After training and validation, determine the final production capacity evaluation model and apply it to the production capacity evaluation of actual image data. During the evaluation process, the model will output the corresponding production capacity prediction value according to the specific features or processing results in the input image data.

[0029] In the above technology, by analyzing the data subsets of consecutive windows and calculating the production capacity attenuation amount of adjacent windows, the change trend of production capacity can be detected in a timely manner. Dividing the image data into consecutive multiple data windows helps to analyze the continuous change of production capacity. Then, by constructing a production capacity evaluation model, the quantitative analysis of the correlation between specific features in the image data and the production capacity is realized. Then, by calculating the production capacity attenuation amount of adjacent windows, the downward trend of production capacity can be detected in a timely manner, providing an early warning for decision-making. Further, by selecting specific features that may be related to the production capacity and performing preprocessing, the accuracy of production capacity evaluation is improved. Then, a production capacity evaluation model is constructed based on linear regression and validated using a validation data set to ensure the reliability and accuracy of the model. Finally, the model can output the corresponding production capacity prediction value according to the specific features or processing results in the input image data, providing a scientific basis for decision-making.

[0030] A data analysis module, based on the obtained attenuation amounts of adjacent windows, calculates the production capacity attenuation rate of consecutive windows, and evaluates the future production capacity of the target feature based on the production capacity attenuation rate; Specifically, the calculation of the attenuation amount of adjacent windows includes: S21. Initialize an empty list or array to store the production capacity attenuation amounts of adjacent windows.

[0031] S22. Traverse the production capacity data list, starting from the second element (i.e., the production capacity value of the second data window), and calculate the production capacity attenuation amount between the current window and the previous window. The calculation formula is: attenuation amount = current window production capacity value - previous window production capacity value.

[0032] S23. Add the calculated attenuation amount to the initialized list. S24. Format and output the list or array storing the attenuation amounts.

[0033] Furthermore, as Figure 5 shown, the data analysis module includes: A data preparation and preprocessing unit, which inputs the calculated attenuation amount data of adjacent windows, and uses the production capacity data of the input consecutive windows as the basis for calculating the attenuation rate; A data evaluation unit, based on the obtained attenuation rates of consecutive periods, calculates the average attenuation rate by taking the difference between consecutive windows, and then takes the difference between the attenuation rate of each window and the average attenuation rate to obtain the starting point of the window time with a negative value, thereby determining the starting point of the current production capacity decline and the future declining working production capacity.

[0034] A data sorting unit binds the starting point of the current production capacity decline and the future declining working production capacity to the target feature to obtain evaluation data.

[0035] In the above technology, calculating the production capacity attenuation amount of adjacent windows and storing it in a list realizes the quantitative analysis of the production capacity change trend, providing data support for determining the starting point of the production capacity decline and the future declining working production capacity.

[0036] A data feedback module, based on the obtained evaluation, matches the implementation regulations in the database and conducts reporting and feedback.

[0037] In the above technology, based on the attenuation amount data for intelligent evaluation, the starting point of the production capacity decline and the future declining working production capacity are determined, and the data integration unit binds the evaluation results to the target feature to form complete evaluation data.

[0038] As can be seen from the above, by obtaining and analyzing the image data on the production line in real time, combined with advanced algorithms and data processing technologies, the accurate monitoring of the production line capacity and the intelligent evaluation of the energy consumption status are realized. The system can timely detect the signs of production capacity decline and accurately judge the energy consumption status, so as to take effective measures for feedback and processing to ensure the healthy operation and high-efficiency output of the production line. Compared with the traditional method, the present invention significantly improves the accuracy and timeliness of monitoring, reduces the energy consumption cost, and improves the overall operation efficiency of the production line. Embodiment 2

[0039] An embodiment of the present invention provides a non-transitory computer-readable storage medium, in which at least one instruction or at least one program segment is stored, and at least one instruction or at least one program segment is loaded and executed by a processor to implement the steps: Obtain the image data collected by the industrial camera in real time and upload it through the time stamp; Based on the obtained image data, and extract according to the extracted target features to obtain a data set; Extract the image data of the data set and analyze it to obtain the data subsets of consecutive windows, and obtain the production capacity of the data subsets of consecutive windows, and take the difference to obtain the attenuation amount of adjacent windows; Based on the obtained attenuation amount of adjacent windows, calculate the production capacity attenuation rate of consecutive windows, and evaluate the future production capacity of the target features based on the production capacity attenuation rate; Based on the obtained evaluation, match the execution regulations in the database and report and feedback.

[0040] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database, or other medium used in the various embodiments provided in this application can include non-volatile and / or volatile memories. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and Rambus dynamic RAM (RDRAM), etc.

[0041] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, only the above-mentioned division of each functional unit and module is used as an example. In actual applications, the above functions can be allocated to different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. Embodiment III

[0042] An embodiment of the present invention provides an electronic device, including a processor and a memory. At least one instruction or at least one program segment is stored in the memory. The at least one instruction or the at least one program segment is loaded and executed by the processor to implement the steps of: Real-time acquisition of image data collected by an industrial camera and uploading through a timestamp; Based on the acquired image data, and extracting according to the extracted target features to obtain a data set; Extract the image data of the data set and perform analysis to obtain a data subset of consecutive windows, and obtain the production capacity of the data subset of consecutive windows, and take the difference to obtain the attenuation amount of adjacent windows; Based on the obtained attenuation amount of adjacent windows, calculate the production capacity attenuation rate of consecutive windows, and evaluate the future production capacity of the target feature based on the production capacity attenuation rate; Based on the obtained evaluation, match the implementation regulations in the database and give feedback reports.

[0043] The above are only the preferred embodiments of the present invention, and do not impose any form of limitation on the present invention. Although the present invention has been disclosed above with the preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art can make some changes or modifications to equivalent embodiments by using the above-disclosed technical content within the scope of the technical solution of the present invention. However, as long as the content does not depart from the technical solution of the present invention, any simple modifications, equivalent changes and modifications made to the above embodiments based on the technical essence of the present invention still fall within the scope of the technical solution of the present invention.

Claims

1. A production line energy consumption monitoring system driven by an intelligent optimization algorithm, characterized in that: include: Data acquisition module, which acquires image data collected by industrial cameras in real time and uploads it with timestamp; A data sorting module, based on the acquired image data and according to the extracted target features, extracts to obtain a data set; A data processing module extracts image data of the data set and analyzes it to obtain data subsets of consecutive windows, and obtains the capacity of the data subsets of consecutive windows, and makes a difference to obtain the attenuation of adjacent windows; A data analysis module, based on the obtained attenuation of the adjacent windows, obtains the capacity attenuation rate of the consecutive windows, and evaluates the future capacity of the target feature based on the capacity attenuation rate; The data feedback module matches the implementation regulations in the database based on the obtained evaluation and provides reporting feedback.

2. According to the intelligent optimization algorithm driven production line energy consumption monitoring system of claim 1, it is characterized in that: The data acquisition module comprises: A plant data acquisition unit, which is arranged in the plant and used to collect overall image data in the plant, is marked as X; A bid section data acquisition unit, which is used to collect data of the production lines in the above-mentioned factory building and divide the production lines into predetermined lengths, marked as h0, h1, ..., hn; The production data acquisition unit is set up on the production line and arranges industrial cameras according to the division standard of the production line in the bid section data acquisition unit, and is used to collect the production quantity per unit time of the section length, which is marked as f0, f1, ..., fn; The first data feedback unit converts the data into the format of time {x, (h0, f0), (h1, f1), ..., (hn, fn)} according to the same time unit.

3. According to claim 1, a production line energy consumption monitoring system driven by an intelligent optimization algorithm is characterized in that: The data sorting module comprises: An image preprocessing unit, which performs mean filtering-median filtering-Gaussian filtering on the acquired image data once to obtain a denoised image; An image conversion unit converts the denoised image into a grayscale image and performs enhancement processing on the grayscale image to obtain a clearly recognizable image; A pixel unit extraction unit creates a grid for a clearly identifiable image, identifies pixels that can be identified as features, and compares them with the target features to determine the type of the current pixels that can be identified as features; The data integration unit classifies the same or similar features of the image based on the type of the pixel point that can be identified as a feature at present, and obtains a plurality of sub-data constituting a data set.

4. The production line energy consumption monitoring system driven by an intelligent optimization algorithm according to claim 3 is characterized in that: The sub-data includes image data of pixel points of the same type that can be identified as features and extracted in time sequence.

5. The production line energy consumption monitoring system driven by an intelligent optimization algorithm according to claim 1 is characterized in that: The data processing module comprises the following steps: S11, extracting a data set containing image data, wherein the image data in the data set is in time series; S12, dividing the image data in the data set into a plurality of continuous data windows, each data window containing a certain amount of continuous image data; S13, for each data window, extracting the image data therein to form data subsets of consecutive windows, each data subset containing feature information of all image data in the corresponding window; S14. For each data subset, the capacity value corresponding to the data subset is calculated according to a preset capacity evaluation model to obtain a correlation relationship between a specific feature or processing result in the image data and the capacity; S15. For continuous data subsets, calculate the difference between the capacity values ​​of two adjacent data subsets to obtain the capacity attenuation of adjacent windows, where the attenuation reflects the change of capacity from one data window to the next data window; S16: Output the calculated capacity attenuation of the adjacent windows.

6. The production line energy consumption monitoring system driven by an intelligent optimization algorithm according to claim 5 is characterized in that: The step S14 of obtaining the correlation between the specific features or processing results in the image data and the production capacity includes: S141, selecting specific features that may be related to production capacity from the image data or performing necessary preprocessing to extract effective features, wherein the effective features include object quantity, size, shape, position, color, texture, brightness, and contrast; S142, collecting a certain amount of image data with known capacity values ​​as training samples, and marking the capacity values ​​of these samples; S143. Use the labeled training samples to build a capacity assessment model based on linear regression; S144. Use an independent validation dataset to validate the trained model; S145. After training and verification, the final capacity assessment model is determined and applied to the capacity assessment of actual image data. During the assessment process, the model will output the corresponding capacity prediction value based on the specific features or processing results in the input image data.

7. The production line energy consumption monitoring system driven by an intelligent optimization algorithm according to claim 1 is characterized in that: The attenuation calculation of the adjacent window includes: S21, initializing an empty list or array for storing the capacity attenuation of adjacent windows; S22, traverse the capacity data list, start from the second element (that is, the capacity value of the second data window), calculate the capacity attenuation between the current window and the previous window, and the calculation formula is: attenuation = current window capacity value - previous window capacity value; S23, adding the calculated attenuation to the initialized list; S24. Format and output the list or array storing the attenuation amounts.

8. The production line energy consumption monitoring system driven by an intelligent optimization algorithm according to claim 1 is characterized in that: The data analysis module includes: The data preparation and preprocessing unit inputs the calculated attenuation data of adjacent windows and inputs the capacity data of consecutive windows as the basis for calculating the attenuation rate; The data evaluation unit obtains the decay rate of continuous cycles, and makes a difference between continuous windows to obtain the average decay rate. It also makes a difference between the decay rate of each window and the average decay rate to obtain the starting point of the window time with a negative value, and determines the starting point of the current capacity decline and the future decline work capacity. The data sorting unit binds the current capacity decline starting point and the future decline working capacity with the target characteristics to obtain evaluation data.

9. A non-transitory computer-readable storage medium, wherein at least one instruction or at least one program is stored in the non-transitory computer-readable storage medium, characterized in that: The at least one instruction or the at least one program is loaded and executed by the processor to implement the method of the production line energy consumption monitoring system driven by the intelligent optimization algorithm as described in any one of claims 1-8.

10. An electronic device, characterized in that: It includes a processor and a memory, wherein the memory stores at least one instruction or at least one program, and the at least one instruction or the at least one program is loaded and executed by the processor to implement the method of the production line energy consumption monitoring system driven by the intelligent optimization algorithm as described in any one of claims 1-8.

Images