Factory equipment evaluation method and system based on artificial intelligence
Through the factory equipment evaluation method based on artificial intelligence, dynamic correction learning tree and multi-factor data evaluation, the subjectivity and inaccuracy of traditional methods are solved, more accurate equipment evaluation and optimization are achieved, and production efficiency and products are improved. quality.
Patent Information
- Application Number
- CN202410725685.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-06-06
- Publication Date
- 2024-11-05
- Estimated Expiration
- 2044-06-06
AI Technical Summary
The traditional factory equipment evaluation method is subjective, difficult to quantify, inaccurate evaluation, time-consuming and labor-consuming, and cannot distinguish the equipment in detail, resulting in errors in the subsequent analysis process, inaccurate results, affecting production efficiency.
Using an artificial intelligence-based factory equipment evaluation method, data is collected through sensors, a dynamic correction learning tree is established, equipment file levels are divided, production capacity is defined, evaluation model is established, and comprehensive evaluation is combined with multi-factor data to optimize maintenance plans and resource allocation.
Improve the efficiency and accuracy of equipment management, reduce human misjudgment, optimize resource allocation, improve production efficiency and product quality, promptly discover potential problems and performance declining trends, and avoid the impact of equipment failure on production.
Smart Images

Figure CN118297486B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of intelligent factory equipment, and in particular to a factory equipment evaluation method and system based on artificial intelligence. Background Art
[0002] With the rapid development and application of artificial intelligence technology, its application in the industrial field is gradually increasing. The evaluation of factory equipment is an important task, which can help enterprises understand the performance, efficiency and reliability of equipment, so as to make reasonable decisions, improve production efficiency and reduce costs.
[0003] Traditional factory equipment evaluation methods mainly rely on experience and manual measurement. This method has the problems of strong subjectivity, difficulty in quantification, inaccurate evaluation, time-consuming and labor-intensive. Then the existing technology still has the following problems: it cannot distinguish the status of factory equipment in detail, does not fit the actual situation, and causes errors in the subsequent evaluation and analysis process; during the analysis process, the reference variables and factors are single, lacking comprehensive analysis coverage, resulting in inaccurate results and serious impact on factory production efficiency; it is impossible to comprehensively consider the status and situation of factory equipment for evaluation, so there is a lack of corresponding decision-making and reasonable resource allocation.
[0004] In modern factory production, the performance and status of factory equipment are crucial to production efficiency and product quality. Therefore, an artificial intelligence-based factory equipment evaluation method is needed. Summary of the invention
[0005] The artificial intelligence-based factory equipment evaluation method and system provided by the present invention aims to improve the reliability and stability of factory equipment by analyzing the historical data and operating conditions of the equipment based on artificial intelligence technology; improve the efficiency and accuracy of equipment management, reduce human misjudgments and delays; optimize maintenance plans and resource allocation, and improve production efficiency and quality.
[0006] The technical solution of the present invention is specifically as follows:
[0007] The factory equipment evaluation method based on artificial intelligence includes the following steps:
[0008] S1. Collect factory and factory equipment data information through sensors and monitoring equipment, pre-process the collected raw data of factory equipment, and classify factory equipment according to the reliability and maintenance requirements of factory equipment;
[0009] S2. Based on the data information of the factory and factory equipment, a dynamic correction learning tree is established to obtain the correction parameter value of the factory equipment production capacity and adjust the factory equipment production capacity;
[0010] S3. Establish a factory equipment evaluation model based on the adjusted factory equipment production capacity and other relevant factory equipment data information.
[0011] Further, step S1 specifically includes:
[0012] The factory equipment grades include: high-level equipment, medium-level equipment, and low-level equipment;
[0013] For high-level equipment, define the production capacity of the factory equipment as ,but ;
[0014] For mid-level equipment, the production capacity of the factory equipment is defined as ,but ;
[0015] For low-level equipment, define the production capacity of factory equipment as ,but ;
[0016] in, represents the standard factory equipment production capacity; t represents the recorded elapsed time; Indicates the adjustment parameters corresponding to high-level equipment; Indicates the adjustment parameters corresponding to the mid-level equipment; Indicates the tuning parameters corresponding to the low-level device.
[0017] Further, step S2 specifically includes:
[0018] The dynamic correction learning tree is established, the data information of multiple factors is integrated into a unified feature vector, and the output of the dynamic correction learning tree is summarized through the determination analysis function of the dynamic correction learning tree.
[0019] Further, step S2 specifically includes:
[0020] In the dynamic correction learning tree, the best segmentation point is identified by maximizing information gain and the interaction between features; based on the segmentation decision made, the judgment analysis value of the feature vector of the correction parameter of the production capacity of different plant equipment is obtained, and then the final correction parameter of the production capacity of the plant equipment is obtained. .
[0021] Further, step S2 specifically includes:
[0022] Pre-set factory equipment production capacity correction parameters ,if , then the adjusted factory equipment production capacity is , ;if , then the adjusted factory equipment production capacity is , ;if , then the adjusted factory equipment production capacity is , .
[0023] Further, in step S3, the plant equipment evaluation model, the specific process is as follows:
[0024] ;
[0025] in, A set of parameters for the impact of factory equipment on the environment, including but not limited to noise, vibration, and exhaust emissions; represents the set of operation and maintenance costs of factory equipment; Represents the production capacity set of factory equipment; Represents the set of assessments of the task completion status of factory equipment; Represents the output results of the factory equipment evaluation network model.
[0026] Further, step S3 specifically includes:
[0027] Based on sensors and intelligent monitoring devices, each factory equipment is evaluated according to the completion status of the production tasks of each equipment in the factory production. The specific process is as follows:
[0028] ;
[0029] in, Indicates the task status of the factory equipment plan, ; N represents the total number of factory equipment, ; Indicates the nth device The evaluation parameters of task completion; ,in, Indicates the nth device parameter; Indicates The difficulty of completing the task; Indicates the operating efficiency of factory equipment; Represents the adaptive factor.
[0030] The factory equipment evaluation system based on artificial intelligence includes the following contents:
[0031] Data acquisition and processing module, grade classification module, parameter correction module, production capacity adjustment module, factory equipment evaluation module, and early warning module;
[0032] The data acquisition and processing module is responsible for collecting and processing data related to factory equipment through sensors, monitoring systems, and maintenance logs; cleaning, integrating, and converting the collected data;
[0033] The grade classification module divides the factory equipment into grades according to the reliability and maintenance requirements of the factory equipment, so as to better classify and compare the equipment;
[0034] The correction parameter module is used to combine the data information of the factory and factory equipment to establish a dynamic correction learning tree to obtain the correction parameter of the factory equipment production capacity;
[0035] The production capacity adjustment module is used to compare the factory equipment production capacity correction parameter value with the pre-set factory equipment production capacity correction parameter value, and adjust and optimize the production capacity according to the comparison result;
[0036] The factory equipment evaluation module evaluates and analyzes factory equipment based on the collected equipment data and pre-established models; discovers potential problems and performance degradation trends of equipment, and supports decision-making and optimization;
[0037] The early warning module is used to monitor abnormal conditions and trend changes of equipment, trigger early warnings and reminders, and promptly notify relevant personnel to help the factory take timely maintenance measures.
[0038] 1. The present invention can better match the performance of equipment and production requirements by classifying factory equipment and initially defining production capacity, thereby improving production efficiency; more effective maintenance plans and strategies can be formulated based on the reliability and maintenance requirements of the equipment; by reasonably defining production capacity, arranging maintenance activities, reducing equipment failures and downtime, and improving equipment reliability and availability; by defining the production capacity of factory equipment, according to the performance and capacity of the equipment, production tasks, human resources and raw material supply can be reasonably arranged to maximize the potential of the equipment and improve production efficiency, ensuring the stability and consistency of the equipment during the production process.
[0039] 2. The invention uses data analysis technology to monitor factory equipment through dynamic correction of learning trees, helps to achieve continuous production capacity optimization, and discovers potential bottlenecks, optimization opportunities and improvement points; by maximizing information gain and considering the feature interaction of correction parameters, the optimal split point can be determined more accurately, and the data samples can be divided into more distinctive and similar subsets, thereby improving the accuracy and generalization ability of the model; through reasonable split points and feature combinations, the key factors of the correction parameters of the production capacity of factory equipment can be better captured, thereby providing more comprehensive insights and decision support; according to the weights and importance of different feature vectors, the correction parameters of the production capacity of factory equipment are determined in a personalized manner, and customized corrections are made according to the characteristics and needs of different equipment, providing correction parameters that are more in line with the actual situation, improving production efficiency, optimizing resource utilization and improving product quality.
[0040] 3. The present invention can provide a more accurate correction of the production capacity of factory equipment by comparing the correction parameter of the production capacity of factory equipment with the pre-set correction parameter of the production capacity of factory equipment. By comparing and analyzing the actual production situation, the actual problems are discovered and the correction parameters are adjusted, thereby more accurately reflecting the actual production capacity and performance of the equipment, achieving continuous improvement in production capacity, and providing data support for subsequent factory equipment evaluation models.
[0041] 4. The present invention can comprehensively consider the adjusted factory equipment production capacity and other relevant data information through the factory equipment evaluation model, and comprehensively evaluate the overall performance and benefits of the equipment, as well as the contribution of the equipment to the factory production goals; based on the evaluation results of the model, decision makers can make corresponding decisions to optimize the use and management of equipment and improve the factory's production efficiency and economic benefits; it can also help discover potential problems and performance degradation trends of equipment, provide early warnings and guidance, so as to take maintenance measures in time to avoid serious impact of equipment failure on production. BRIEF DESCRIPTION OF THE DRAWINGS
[0042] Figure 1 A flowchart of the artificial intelligence-based factory equipment evaluation method of the present invention;
[0043] Figure 2 It is a module diagram of the artificial intelligence-based factory equipment evaluation system of the present invention. DETAILED DESCRIPTION
[0044] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods. It should also be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.
[0045] See attached Figure 1, this embodiment provides a factory equipment evaluation method based on artificial intelligence, comprising the following steps:
[0046] S1. Collect the operation data of factory equipment in real time through sensors, monitoring equipment, etc., including parameters such as temperature, pressure, vibration, etc. Perform pre-processing operations such as noise removal, outlier processing, and data cleaning on the collected raw data to ensure the accuracy and reliability of the evaluation results.
[0047] The factory equipment is divided into grades according to the reliability and maintenance requirements of the factory equipment. Specifically, it is divided into high-level equipment, medium-level equipment, and low-level equipment. The production capacity of the factory equipment is set according to the grade classification of the factory equipment, and the factory equipment is optimized and improved in a timely manner. The specific process is as follows:
[0048] When the factory equipment is classified as high-level equipment, it means that it has higher reliability and lower maintenance requirements. It is considered to be key equipment, which is essential to the production and operation of the factory and can undertake high-load factory production tasks. The production capacity of the factory equipment is defined as ,but ;
[0049] When the factory equipment is of medium grade, it means that it has certain reliability and maintenance requirements, plays a medium-important role in the factory's production, and undertakes part of the production tasks; the production capacity of the factory equipment is defined as ,but ;
[0050] When the factory equipment is of low grade, it means that the reliability is low and the maintenance requirements are high. It plays a secondary role in factory production, but may require relatively frequent maintenance and has a relatively low load in the production process. The production capacity of factory equipment is defined as ,but ;
[0051] in, represents the standard factory equipment production capacity; t represents the recorded elapsed time; Indicates the adjustment parameters corresponding to high-level equipment; Indicates the adjustment parameters corresponding to the mid-level equipment; Indicates the tuning parameters corresponding to the low-level device.
[0052] The present invention can better match the performance of equipment and production requirements by classifying factory equipment and initially defining production capacity, thereby improving production efficiency; more effective maintenance plans and strategies can be formulated based on the reliability and maintenance requirements of the equipment. For example, equipment of different grades may require different maintenance frequencies, repair cycles or spare parts inventories. By reasonably defining production capacity and arranging maintenance activities, equipment failures and downtime can be reduced, and equipment reliability and availability can be improved; the production capacity of factory equipment is defined, and according to the performance and capacity of the equipment, production tasks, human resources and raw material supply can be reasonably arranged to maximize the use of equipment potential and improve production efficiency, thereby ensuring the stability and consistency of equipment during the production process.
[0053] S2. Based on the data information of the factory and factory equipment, a dynamic correction learning tree is established to obtain the correction parameter value of the factory equipment production capacity; the factory equipment production capacity correction parameter value is pre-set, the factory equipment production capacity correction parameter value is compared with the pre-set factory equipment production capacity correction parameter value, and the factory equipment production capacity is adjusted according to the comparison result.
[0054] Based on the data information of the factory and factory equipment, a dynamic correction learning tree is established to obtain the correction parameters of the factory equipment production capacity. When calculating the correction parameters of the factory equipment production capacity, it cannot be calculated by one or two single factors, and multiple factors need to be considered for comprehensive calculation. Therefore, a dynamic correction learning tree is established to process data information from different sources and discover potential associations between data, such as: environmental factors, the operating speed of factory equipment, raw material quality and supply data, maintenance and fault record data; and merge them into a unified feature vector. The specific calculation process is as follows:
[0055] ;
[0056] in, The characteristic vector representing the correction parameter of the production capacity of the factory equipment; Indicates the control coefficient of environmental factors, including temperature, humidity, light intensity and other related information; Indicates the impact of temperature on the production capacity of factory equipment; Indicates the impact of humidity on the production capacity of factory equipment; represents a constant coefficient; represents the deviation of light intensity; N represents the total number of equipment in the factory; represents the learning factor used for the operating speed of the plant equipment; The fusion coefficient representing the rate of change of the running speed; It represents the rate of change of the operating speed of the nth plant equipment in the tth time step; Indicates the restriction coefficient of maintenance and fault record on ICBC equipment production capacity; B indicates the number of fault record data; Table 1 shows the performance of the factory equipment after maintenance at time step t for the bth fault condition; It indicates the dependence coefficient of factory equipment production capacity on raw material quality and supply; M indicates the total amount of raw material category; represents the raw material quality score of the mth category; Q represents the conversion matrix, which can be used to understand the correlation between raw material quality and supply conditions; Indicates the total supply of raw materials; Indicates the weight coefficient of the raw material category.
[0057] In the established dynamic correction learning tree, the optimal segmentation point is identified, and the accuracy of segmentation is improved and the stability of the calculation process is guaranteed by maximizing information gain and fully considering the interaction between features. , when maximizing information gain, use To represent, represents the data set, d represents the total number of categories in it, that is, the specific process is as follows:
[0058] ;
[0059] Specifically, the entropy of the parent node is , ; The dataset Divide into V subsets, , each subset The corresponding feature value is the sample set v, subset The entropy of , ;
[0060] in, The segmentation criteria representing the best segmentation point; Indicates category In the dataset The probability of Representation Subset Medium Category The probability of The balance coefficient representing the split point; The pth element of the characteristic vector representing the correction parameter of the plant equipment production capacity; Indicates the split boundary.
[0061] The output of the comprehensive dynamic correction learning tree, the process is as follows:
[0062] ;
[0063] in, The decision analysis function representing the dynamic modified learning tree, i.e., summarizing the output of the dynamic modified learning tree; represents the equalization weight coefficient; represents the weight of the learning tree; Indicates the generated A dynamically modified learning tree for a specific vector Dynamic output.
[0064] According to the segmentation decision made, the characteristic vector of the correction parameter of the production capacity of different factory equipment is obtained, and then the final correction parameter of the production capacity of the factory equipment is obtained. .
[0065] Pre-set factory equipment production capacity correction parameters , the factory equipment production capacity correction parameter Compare with the preset factory equipment production capacity correction parameter, and adjust the factory equipment production capacity according to the comparison result. Make adjustments, including .
[0066] if , then the adjusted factory equipment production capacity is , ;
[0067] if , then the adjusted factory equipment production capacity is , ;
[0068] if , then the adjusted factory equipment production capacity is , .
[0069] The present invention uses data analysis technology to monitor factory equipment through dynamic correction of learning trees, helps to achieve continuous production capacity optimization, and discovers potential bottlenecks, optimization opportunities and improvement points; by maximizing information gain and considering the feature interaction of correction parameters, the optimal split point can be determined more accurately, and the data samples can be divided into subsets with more discrimination and similarity, thereby improving the accuracy and generalization ability of the model; through reasonable split points and feature combinations, the key factors of the correction parameters of the production capacity of factory equipment can be better captured, thereby providing more comprehensive insights and decision support; according to the weights and importance of different feature vectors, the correction parameters of the production capacity of factory equipment are determined in an individualized manner, and customized corrections are performed according to the characteristics and requirements of different equipment, providing correction parameters that are more in line with the actual situation, improving production efficiency, optimizing resource utilization and improving product quality.
[0070] By comparing the factory equipment production capacity correction parameters with the pre-set factory equipment production capacity correction parameters, a more accurate factory equipment production capacity correction can be provided. Through comparative analysis, the actual production situation can be understood, existing problems can be discovered and the correction parameters can be adjusted, thereby more accurately reflecting the actual production capacity and performance of the equipment, achieving continuous production capacity improvement, and providing data support for subsequent factory equipment evaluation models.
[0071] S3. Combine the adjusted factory equipment production capacity and other relevant factory equipment data information to establish a factory equipment evaluation model. The specific process is as follows:
[0072] ;
[0073] in, A set of parameters for the impact of factory equipment on the environment, including but not limited to noise, vibration, exhaust emissions, etc.; represents the set of operation and maintenance costs of factory equipment; Represents the production capacity set of factory equipment; Represents the set of assessments of the task completion status of factory equipment; Represents the output results of the factory equipment evaluation network model.
[0074] further, , The number of elements in each subset of the set is ; , It represents the total amount of the set parameters of the operation and maintenance cost of the plant equipment; , Indicates the total amount of factory equipment production capacity set parameters; , Represents the total amount of factory equipment task completion status assessment set parameters.
[0075] Based on sensors and intelligent monitoring devices, each factory equipment is evaluated according to the completion status of the production tasks of each equipment in the factory production. The specific process is as follows:
[0076] ;
[0077] in, Indicates the task status of the factory equipment plan, ; N represents the total number of factory equipment, ; Indicates the nth device The evaluation parameters of task completion;
[0078] Specifically, ,in, Indicates the nth device parameter; Indicates The difficulty of completing the task; Indicates the operating efficiency of factory equipment; Represents the adaptive factor.
[0079] Calculate the output results of the factory equipment evaluation network model. The specific process is as follows:
[0080] ;
[0081] in, Indicates the impact of factory equipment on the environment; They represent the corresponding weight coefficients, indicating the contribution of different data sets to the evaluation of factory equipment; represents the adjustment coefficient; It represents the average cost of operating and maintaining the factory equipment.
[0082] Then, by monitoring and analyzing the output of the evaluation model, thresholds are set to detect abnormal conditions and trend changes in factory equipment. When the model detects abnormal conditions or trend changes in equipment, an early warning and reminder mechanism can be triggered to notify relevant personnel to pay attention to the status of the equipment. In this way, relevant personnel can take timely action and conduct further investigation and analysis to determine the specific cause and solution of the equipment problem.
[0083] The present invention can comprehensively consider the adjusted factory equipment production capacity and other relevant data information through the factory equipment evaluation model, and comprehensively evaluate the overall performance and benefits of the equipment, as well as the contribution of the equipment to the factory production goals; based on the evaluation results of the model, decision makers can make corresponding decisions to optimize the use and management of equipment and improve the factory's production efficiency and economic benefits; it can also help discover potential problems and performance degradation trends of equipment, provide early warnings and guidance, so as to take maintenance measures in time to avoid serious impacts of equipment failures on production.
[0084] See attached Figure 2 , this embodiment provides a factory equipment evaluation system based on artificial intelligence, including the following contents:
[0085] Data acquisition and processing module, grade classification module, parameter correction module, production capacity adjustment module, factory equipment evaluation module, and early warning module;
[0086] The data acquisition and processing module is responsible for collecting and processing data related to factory equipment, obtaining equipment operation data such as working hours, output, fault records, etc. through sensors, monitoring systems, maintenance logs, etc.; cleaning, integrating and converting the collected data for subsequent analysis and evaluation.
[0087] The grade classification module divides the factory equipment into grades according to the reliability and maintenance requirements of the factory equipment, so as to better classify and compare the equipment;
[0088] The correction parameter module is used to combine the data information of the factory and factory equipment to establish a dynamic correction learning tree to obtain the correction parameter of the factory equipment production capacity;
[0089] The production capacity adjustment module is used to compare the factory equipment production capacity correction parameter value with the pre-set factory equipment production capacity correction parameter value, and adjust and optimize the production capacity according to the comparison result;
[0090] The factory equipment evaluation module is the core of the entire system. It evaluates and analyzes factory equipment based on the collected equipment data and pre-established models. It can identify equipment problems and performance degradation trends, and support decision-making and optimization.
[0091] The early warning module is used to monitor abnormal conditions and trend changes of equipment, trigger early warnings and reminders, and promptly notify relevant personnel to help factories take timely maintenance measures to avoid major impacts of equipment failures on production.
[0092] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0093] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0094] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0095] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the technical features required by the present invention are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.
[0096] The above contents are only for explaining the technical idea of the present invention and cannot be used to limit the protection scope of the present invention. Any changes made on the basis of the technical solution in accordance with the technical idea proposed by the present invention shall fall within the protection scope of the present invention.
Claims
1. The factory equipment evaluation method based on artificial intelligence is characterized by: The following steps are involved: S1. Collect factory and factory equipment data information through sensors and monitoring equipment, pre-process the collected raw data of factory equipment, and classify factory equipment according to the reliability and maintenance requirements of factory equipment; S2. Based on the data information of the factory and factory equipment, a dynamic correction learning tree is established to obtain the correction parameter value of the factory equipment production capacity. The specific calculation process is as follows: ; in, The characteristic vector representing the correction parameter of the production capacity of the factory equipment; represents the control coefficient of environmental factors; Indicates the impact of temperature on the production capacity of factory equipment; Indicates the impact of humidity on the production capacity of factory equipment; represents a constant coefficient; represents the deviation of light intensity; N represents the total number of equipment in the factory; represents the learning factor used for the operating speed of the plant equipment; The fusion coefficient representing the rate of change of the running speed; It represents the rate of change of the operating speed of the nth plant equipment in the tth time step; Indicates the restriction coefficient of maintenance and fault record on ICBC equipment production capacity; B indicates the number of fault record data; Table 1 shows the performance of the factory equipment after maintenance at time step t for the bth fault condition; It indicates the dependence coefficient of factory equipment production capacity on raw material quality and supply; M indicates the total amount of raw material category; represents the raw material quality score of the mth category; Q represents the conversion matrix, which can be used to understand the correlation between raw material quality and supply conditions; Indicates the total supply of raw materials; Indicates the weight coefficient of the raw material category; and adjusts the production capacity of the factory equipment; S3. Establish a factory equipment evaluation model based on the adjusted factory equipment production capacity and other relevant factory equipment data information.
2. The method for evaluating factory equipment based on artificial intelligence according to claim 1, characterized in that: The step S1 specifically includes: The factory equipment grades include: high-level equipment, medium-level equipment, and low-level equipment; For high-level equipment, define the production capacity of the factory equipment as ,but ; For mid-level equipment, the production capacity of the factory equipment is defined as ,but ; For low-level equipment, define the production capacity of factory equipment as ,but ; in, represents the standard factory equipment production capacity; t represents the recorded elapsed time; Indicates the adjustment parameters corresponding to high-level equipment; Indicates the adjustment parameters corresponding to the mid-level equipment; Indicates the tuning parameters corresponding to the low-level device.
3. The method for evaluating factory equipment based on artificial intelligence according to claim 1, characterized in that: The step S2 specifically includes: In the dynamic correction learning tree, the optimal segmentation point is identified by maximizing information gain and considering the interaction between features; the feature vector of the correction parameter of the production capacity of the factory equipment , when maximizing information gain, use To represent, represents the data set, d represents the total number of categories in it, that is, the process is as follows: ; Among them, the entropy of the parent node is , ; The dataset Divide into V subsets, , each subset The corresponding feature value is the sample set v, subset The entropy of , ; in, The segmentation criteria representing the best segmentation point; Indicates category In the dataset The probability of Representation Subset Medium Category The probability of The balance coefficient representing the split point; The first eigenvector representing the correction parameter of the plant equipment production capacity elements; Indicates the segmentation boundary; According to the segmentation decision made, the characteristic vector of the correction parameter of the production capacity of different factory equipment is obtained, and then the final correction parameter of the production capacity of the factory equipment is obtained. .
4. The artificial intelligence-based factory equipment evaluation method according to claim 2 or 3, characterized in that: The step S2 specifically includes: Pre-set factory equipment production capacity correction parameters ,if , then the adjusted factory equipment production capacity is , ;if , then the adjusted factory equipment production capacity is , ;if , then the adjusted factory equipment production capacity is , .
5. The method for evaluating factory equipment based on artificial intelligence according to claim 1, characterized in that: In step S3, the plant equipment evaluation model, the specific process is as follows: ; in, A set of parameters for the impact of factory equipment on the environment, including but not limited to noise, vibration, and exhaust emissions; represents the set of operation and maintenance costs of factory equipment; Represents the production capacity set of factory equipment; Represents the set of assessments of the task completion status of factory equipment; Represents the output results of the factory equipment evaluation network model.
6. The artificial intelligence-based factory equipment evaluation method according to claim 5, characterized in that: The step S3 specifically includes: Based on sensors and intelligent monitoring devices, each factory equipment is evaluated according to the completion status of the production tasks of each equipment in the factory production. The specific process is as follows: ; in, Indicates the task status of the factory equipment plan, ; N represents the total number of factory equipment, ; Indicates the nth device The evaluation parameters of task completion; ,in, Indicates the nth device parameter; Indicates The difficulty of completing the task; Indicates the operating efficiency of factory equipment; Represents the adaptive factor.
7. An artificial intelligence-based factory equipment evaluation system, applied to the artificial intelligence-based factory equipment evaluation method according to claim 1, characterized in that: Includes the following: Data acquisition and processing module, grade classification module, parameter correction module, production capacity adjustment module, factory equipment evaluation module, and early warning module; The data acquisition and processing module is responsible for collecting and processing data related to factory equipment through sensors, monitoring systems, and maintenance logs; cleaning, integrating, and converting the collected data; The grade classification module divides the factory equipment into grades according to the reliability and maintenance requirements of the factory equipment, so as to better classify and compare the equipment; The correction parameter module is used to establish a dynamic correction learning tree based on the data information of the factory and factory equipment to obtain the correction parameter of the production capacity of the factory equipment; The production capacity adjustment module is used to compare the factory equipment production capacity correction parameter with the preset factory equipment production capacity correction parameter, and adjust and optimize the production capacity according to the comparison result; The plant equipment evaluation module evaluates and analyzes plant equipment based on the collected equipment data and pre-established models; discovers potential problems and performance degradation trends of equipment, and supports decision-making and optimization; The early warning module is used to monitor abnormal conditions and trend changes of equipment, trigger early warnings and reminders, and promptly notify relevant personnel to help the factory take timely maintenance measures.
