Terminal table production line intelligent management and control system and method for new energy vehicles

Abstract

The application discloses a line intelligent management and control system and method for a terminal table for new energy vehicles, and relates to the technical field of line management and control.The system comprises the following steps: analyzing machines in the line based on a production line database, establishing machine correlation, assigning tasks to the line, establishing task allocation results, producing the terminal table for new energy vehicles based on the task allocation results, recording machine production data, performing collaborative and balanced evaluation through the machine production data and machine correlation, establishing a first optimized management and control scheme, establishing an optimization function, and performing intelligent management and control of the production line.The system solves the technical problems of the current terminal table line management and control, such as the difficulty in collecting and analyzing production data in real time, the lack of flexibility in task allocation, low equipment utilization and production efficiency, and poor quality, realizes the intelligent production of the terminal table line, and achieves the technical effects of improving the production efficiency and product performance of the terminal table line.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of production line management and control, and particularly relates to a production line intelligent management and control system and method for a terminal table for a new energy vehicle. BACKGROUND

[0002] With the high attention to environmental protection and sustainable development in the world, the rapid development of the new energy vehicle industry and the wide application of intelligent and automatic technologies, the new energy vehicle market presents an explosive growth trend as an important choice to replace traditional fuel vehicles. In the production process of the new energy vehicle, the terminal table as a key component for electrical connection is particularly important for the performance and safety of the vehicle. On the one hand, with the expansion of the production scale, how to ensure the quality and consistency of the terminal table becomes an important challenge for enterprises. On the other hand, with the application of intelligent and automatic technologies, how to improve the production efficiency of the terminal table becomes a problem to be solved.

[0003] Therefore, in the current production line management and control technology for the terminal table for a new energy vehicle, there are technical problems such as difficulty in real-time and effective collection and analysis of production data, insufficient flexibility in task allocation, low equipment utilization rate and production efficiency of the terminal table production line, and poor quality. SUMMARY

[0004] The present application provides a production line intelligent management and control system and method for a terminal table for a new energy vehicle, which uses collaborative and balanced evaluation, establishment of an optimization function and other technical means to solve the technical problems of difficulty in real-time and effective collection and analysis of production data, insufficient flexibility in task allocation, low equipment utilization rate and production efficiency of the terminal table production line, and poor quality in the existing production line management and control of the terminal table for a new energy vehicle, realizes the intelligentization of the terminal table production line, and achieves the technical effects of improving the production efficiency of the terminal table production line and the performance of the product.

[0005] The application provides a line intelligent management and control system for a terminal table of a new energy vehicle, and the system comprises: a machine correlation establishment module, which is used for connecting a production line of the terminal table of the new energy vehicle, establishing a production line database, performing machine analysis in the production line based on the production line database, and establishing machine correlation, wherein the machine correlation comprises upper and lower level cooperative correlation and same level processing correlation; a task allocation result establishment module, which is used for obtaining a production line task, performing task allocation on the production line task based on the production line database, and establishing a task allocation result; a machine production data recording module, which is used for producing the terminal table of the new energy vehicle based on the task allocation result in the production line, and recording machine production data; a first optimization management and control scheme establishment module, which is used for performing cooperative balance evaluation through the machine production data and the machine correlation, establishing a first optimization management and control scheme based on the cooperative balance evaluation result, and performing the cooperative balance evaluation as follows: S1: performing upper and lower level cooperation adaptability analysis of a same production line based on the upper and lower level cooperative correlation and the machine production data, and establishing a first adaptation set; S2: performing adaptation analysis of same level interaction based on the same level processing correlation and the machine production data, and establishing a second adaptation set; S3: performing cooperative balance evaluation based on the first adaptation set and the second adaptation set, and establishing a cooperative balance evaluation result; and a production line intelligent management and control module, which is used for establishing an optimization function, the optimization function being a target function of balancing machine load and reducing total delay, performing task allocation reconstruction under the first optimization management and control scheme through the optimization function, and performing intelligent management and control of the production line according to the task allocation reconstruction result and the first optimization management and control scheme.

[0006] In a possible implementation manner, the production line intelligent management and control module further performs the following processing: analyzing the machine production data to obtain machine average load;

[0007] The optimization function is established as follows:

[0008]

[0009] wherein EQU is the optimization function, and α and β are weight factors of delay balance and load balance respectively, c j is the completion time of task j, d j is the deadline of task j, n is the number of tasks, MaxLoad i is the maximum load of machine i, AvgLoad is the machine average load, and m is the total number of machines.

[0010] In a possible implementation, the production line intelligent management and control module further performs the following processing: setting a single task execution constraint, which is a constraint that a single task needs to be continuously executed on an assigned machine, and setting the following:

[0011]

[0012] wherein x ij is a binary variable, x ij is 1 if task j is assigned to machine i, and 0 otherwise; setting a machine conflict constraint, which is a constraint that machine i can only execute one task at the same time;

[0013] establishing a load calculation formula as follows:

[0014]

[0015] wherein Load i represents the total load of machine i, and p ij is the processing time of task j on machine i; performing task reassignment under a first optimization management and control scheme through the single task execution constraint and the machine conflict constraint, performing reconfiguration result evaluation optimization based on the load calculation formula and the optimization function, and completing task allocation reconfiguration.

[0016] In a possible implementation, the production line intelligent management and control module further performs the following processing: performing machine evaluation based on the production line database, establishing a steady-state coefficient of machine production; performing task evaluation on the line task, establishing a grade constraint of a simultaneous zone task; performing matching constraint of the task based on the grade constraint and the steady-state coefficient, and performing task reassignment under a first optimization management and control scheme based on the matching constraint, the single task execution constraint, and the machine conflict constraint.

[0017] In a possible implementation, the first optimization management and control scheme establishment module further performs the following processing: obtaining a unit penalty factor of machine adjustment; performing penalty analysis of a scheme corresponding to a collaborative balance evaluation result through the unit penalty factor, generating a penalty analysis result; obtaining an improvement analysis of the collaborative balance evaluation result relative to a task allocation result, establishing an improvement fitting result; performing breakthrough analysis of machine scheduling through the improvement fitting result and the penalty analysis result; and if a breakthrough analysis result meets a preset limited threshold, establishing the first optimization management and control scheme based on the collaborative balance evaluation result.

[0018] In a possible implementation, the node transition influence probability obtaining module further performs the following processing: a machine database is established based on the production line database, and multi-dimensional feature extraction is performed through the machine database; an abnormality recognition model is constructed based on the multi-dimensional feature extraction result; periodic sampling of the production product cycle of the machine is performed, machine state evaluation is performed based on the periodic sampling result, and an abnormality recognition period is established; in the abnormality recognition period, data acquisition of the machine is performed by calling the Internet of Things sensor, and the data acquisition result is input into the abnormality recognition model to generate a predictive abnormality recognition result; machine maintenance management is performed through the predictive abnormality recognition result.

[0019] In a possible implementation, the first optimization control scheme establishing module further performs the following processing: adaptive analysis of the yield is performed to establish a first adaptive result; quality adaptive analysis of the production product is performed to establish a second adaptive result; collaboration adaptability analysis of the superior and the subordinate of the same production line is performed based on the first adaptive result and the second adaptive result to establish a first adaptive set.

[0020] The application also provides a production line intelligent control method for a terminal table for a new energy vehicle, which comprises the following steps: based on a life cycle of a green product, taking a life cycle node as a time sequence chain node and a time sequence relationship of the life cycle, a cycle time sequence chain is constructed; based on the cycle time sequence chain, a node operator is configured, the node operator being used for performing environmental influence degree analysis on each life cycle node; through the node operator, an environmental influence analysis result of the life cycle node is obtained; based on the cycle time sequence chain, a Markov chain model framework is constructed, node transition probability learning is performed through a sample case, and transition influence probability of each node is obtained; environmental influence analysis of each life cycle node and the whole life cycle is performed by using the transition influence probability and the environmental influence analysis result of the life cycle node, and a green product evaluation result is obtained, the green product evaluation result comprising environmental influence of each life cycle node and environmental influence of the whole life cycle.

[0021] The production line intelligent control system and method for the terminal table for the new energy vehicle are used to perform machine analysis in the production line based on a production line database, establish machine correlation, perform task allocation on the production line task, establish a task allocation result, perform production of the terminal table for the new energy vehicle based on the task allocation result, and record machine production data; through the machine production data and the machine correlation, collaborative balance evaluation is performed, a first optimization control scheme is established, an optimization function is established, and intelligent control of the production line is performed. The technical problems of the existing terminal table production line control, such as difficulty in real-time and effective collection and analysis of production data, insufficient flexibility of task allocation, low equipment utilization rate and production efficiency of the terminal table production line, and poor quality are solved, the intelligentization of the terminal table production line is realized, and the technical effects of improving the production efficiency and product performance of the terminal table production line are achieved. BRIEF DESCRIPTION OF DRAWINGS

[0022] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings of the embodiments of the present disclosure will be briefly introduced below, and the flowcharts are used to illustrate the operations performed by the system according to the embodiments of the present disclosure. It should be understood that the foregoing or the following operations are not necessarily performed in sequence. On the contrary, various steps can be processed in reverse order or simultaneously according to needs. Meanwhile, other operations can be added to these processes, or one or more steps of operations can be removed from these processes.

[0023] Figure 1 The structure schematic diagram of the production line intelligent management and control system of the terminal table for new energy vehicles provided by the embodiments of the present application is shown.

[0024] Figure 2 The flowchart of the production line intelligent management and control method of the terminal table for new energy vehicles provided by the embodiments of the present application is shown.

[0025] The reference signs are explained: machine association establishment module 10, task allocation result establishment module 20, machine production data record module 30, first optimization management and control scheme establishment module 40, production line intelligent management and control module 50. DETAILED DESCRIPTION

[0026] The above description is only a summary of the technical solutions of the present application. In order to more clearly understand the technical means of the present application, the content of the specification can be implemented, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the following specific embodiments of the present application are described.

[0027] In order to make the purposes, technical solutions and advantages of the present application more clear, the present application will be further described in detail below with reference to the drawings, and the described embodiments should not be regarded as limiting the present application. All other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0028] In the following description, "some embodiments" are referred, which describe a subset of all possible embodiments, but it can be understood that "some embodiments" can be the same subset or different subset of all possible embodiments, and can be combined with each other without conflict, the term "first\second" referred to only distinguishes similar objects, and does not represent a specific order for the objects. The terms "include" and "have" and any variations thereof, are intended to cover non-exclusive inclusion, for example, a process, system, product or server including a series of steps or units does not have to be limited to those steps or units clearly listed, but can include other steps or modules not clearly listed or inherent to these processes, products or devices, unless otherwise defined, all technical and scientific terms used herein have the same meaning as understood by those skilled in the art belonging to the technical field of the present application. The terms used herein are only for the purpose of describing the embodiments of the present application.

[0029] The embodiments of the present application provide a production line intelligent management and control system for a terminal table of a new energy vehicle, as shown in Figure 1 The system comprises:

[0030] The machine association establishing module 10 is used to connect the production line of the terminal block for new energy vehicles, establish a production line database, analyze the machines in the production line based on the production line database, and establish machine association, wherein the machine association includes upper and lower level cooperative association and same level processing association. The production line of the terminal block for new energy vehicles is connected, the production line database is established, the machines in the production line are analyzed, and the machine association is established. Specifically, the production line database is a data set or database for storing and managing relevant information of the entire production line, such as machine equipment information, production process data, raw material usage data, product quality detection data, and process data. Through the production line database, various data in the production process can be tracked in real time. The machine analysis in the production line refers to detailed analysis of the machine equipment in the production line based on the production line database, which may include the running efficiency, failure rate, maintenance record, etc. of the equipment. Through the analysis of the production line equipment, the running condition of the equipment can be understood, and possible problems can be predicted. Machine association refers to the connection and cooperative working relationship between different devices of the production line of the terminal block for new energy vehicles, including upper and lower level cooperative association and same level processing association. The upper and lower level cooperative association refers to the cooperative working relationship between machine equipment in different processes in the same production process. For example, in the production process of the terminal block, multiple processes such as stamping, welding, and assembly are required. In these processes, different machine equipment needs to work cooperatively according to the predetermined order and rules to ensure the continuity and stability of production. The same level processing association refers to the parallel processing relationship between the same machine equipment in the same process. For example, in the production line of two terminal blocks, the machine equipment in the assembly process. Through the establishment of machine association, the automation and intelligentization of the production process can be realized, and the production efficiency and product quality of the terminal block production line can be improved.

[0031] The task allocation result establishing module 20 is used for obtaining a production line task, performing task allocation on the production line task based on the production line database, and establishing a task allocation result. The production line task is obtained and task allocation is performed to obtain the task allocation result. Specifically, obtaining the production line task refers to determining production requirements and production targets, including customer orders, sales plans, and production plans, such as product models, quantities, and the like. When the production line task is obtained, the actual production capacity and resource status of the production line also need to be considered. After the production line task is determined, task allocation is performed according to information in the production line database, for example, by using a model allocation method, a task allocation method, a flow line allocation method, a load balancing method, and the like. According to product production process requirements, production line equipment capacity, personnel technical capacity, and other factors, the production task is reasonably allocated to each production line or work group. At the same time, the priority and urgency of the task are considered. After the task allocation is completed, the task allocation result is established. Specifically, the task allocation result determines the specific task, task priority, required resources, and other information of each production line or work group, realizes fine management and control of the production task, and further improves production efficiency.

[0032] The machine production data recording module 30 is used for producing a terminal table for a new energy automobile based on the task allocation result of the production line, and recording machine production data. According to the pre-prepared task allocation result, the related machine equipment on the production line is started, the actual production process of the terminal table is performed, and the operation data of the machine equipment, that is, the machine production data, is recorded and collected in real time during the production process. Specifically, according to the task allocation result, it is determined which production lines or machine equipment need to participate in this production task. Then, according to the predetermined production plan, the machine equipment on the production line is started, and the machine equipment starts production according to the preset process flow and parameters, including material processing, assembly, testing, and other links. During the production process, the production data of the machine equipment is automatically collected and recorded by using technical means such as sensors, data acquisition cards, and RFID, including the running state, running time, processing parameters, yield, and pass rate of the equipment.

[0033] The first optimization control scheme establishment module 40 is configured to establish a first optimization control scheme based on the collaborative balance evaluation result by the machine production data and the machine correlation. The collaborative balance evaluation is based on the running state of the entire production line and the collaborative working condition between the machines and devices, and is used to evaluate the overall performance and efficiency of the production line. Based on the evaluation result, the first optimization control scheme is established. Specifically, the collaborative balance of the entire production line is evaluated by comprehensively considering the machine production data and the machine correlation analysis result. The evaluation may include evaluating the flow, equipment utilization, production cycle and failure rate of the production line. The collaborative balance level of the current production line is determined by comparing the historical data or industry standards. Based on the collaborative balance evaluation result, the key links and machine devices that need to be optimized are determined, and specific optimization measures are formulated, such as adjusting the production plan, optimizing the process flow, improving the equipment performance, and strengthening the equipment maintenance, to obtain the first optimization control scheme.

[0034] The collaborative balance evaluation is as follows:

[0035] S1: Perform upper and lower level collaboration adaptability analysis based on the upper and lower level collaborative correlation and the machine production data to establish a first adaptation set. The upper and lower level collaboration adaptability analysis based on the upper and lower level collaborative correlation and the machine production data is performed to establish a first adaptation set for evaluating and optimizing the collaboration efficiency between different machines and devices on the production line. The goal is to identify which machines or device combinations can work best in collaboration to improve the efficiency, stability and product quality of production, including the adaptability of product size and yield. Specifically, the upper and lower level collaboration adaptability analysis refers to analyzing the performance of different machines and devices when working collaboratively based on the collected machine production data and upper and lower level collaborative correlation, and evaluating the collaborative efficiency of processing speed and capacity matching. Based on the result of the upper and lower level collaboration adaptability analysis, the machine and device combinations with high collaborative efficiency are selected, and these combinations are sorted into a first adaptation set.

[0036] S2: Perform an adaptation analysis of peer interaction based on the peer processing association and the machine production data to establish a second adaptation set. The adaptation analysis of peer interaction based on the peer processing association and the machine production data refers to the evaluation of the interaction efficiency and compatibility of machines and equipment at the same level (i.e., parallel processing or within the same process) on the production line, identifying machine and equipment combinations that can work efficiently, reduce conflicts and waste in peer processing, and thus establishing an optimized equipment combination set, i.e., a second adaptation set. Specifically, the adaptation analysis of peer interaction refers to analyzing the performance of peer equipment in the interaction process using the collected machine production data and peer processing association, including evaluating the overall production efficiency, resource utilization, etc. Based on the results of the adaptation analysis of peer interaction, select machine and equipment combinations with high synergy efficiency and good compatibility to maximize the synergy advantage between peer equipment, reduce conflicts and waste, improve the efficiency and stability of the entire production line, and organize these combinations into an adaptation set, i.e., a second adaptation set.

[0037] S3: Perform a synergy balance evaluation based on the first adaptation set and the second adaptation set to establish a synergy balance evaluation result. The synergy balance evaluation based on the first adaptation set and the second adaptation set to establish a synergy balance evaluation result refers to considering the upper and lower level collaboration adaptability and peer interaction adaptability between different machines and equipment on the production line to evaluate the synergy balance performance of the entire production line, and forming a comprehensive evaluation result accordingly. For example, use statistical analysis, etc. to quantitatively evaluate the equipment combinations in the first adaptation set and the second adaptation set, determine the performance of each equipment combination in each synergy balance indicator, and according to the actual demand and priority of the production line, assign weights to each synergy balance indicator, weight each equipment combination in each synergy balance indicator, and establish a synergy balance evaluation result, which can be a ranked list or a report or chart containing detailed information, which can clearly show which equipment combinations perform well in synergy balance, which have deficiencies, and possible improvement directions.

[0038] The production line intelligent management and control module 50 is used for establishing an optimization function, the optimization function is a target function balancing machine load and reducing total delay, task allocation reconstruction under a first optimization management and control scheme is performed through the optimization function, and intelligent management and control of the production line is performed according to the task allocation reconstruction result and the first optimization management and control scheme. The optimization function is established, and task allocation reconstruction is performed through the function to achieve the goal of balancing machine load and reducing total delay, and then intelligent management and control of the production line is performed. Specifically, the optimization function (or optimization target function) is a mathematical function used to describe the indicators that need to be optimized in a specific problem. The goal is to balance machine load and reduce total delay. Specifically, machine load balancing refers to balancing the working time and task amount of machine devices on the production line to avoid overloading of some devices while other devices are idle, thereby ensuring product quality and improving overall production efficiency and device utilization. Reducing total delay refers to optimizing the production process, reducing waiting time between production processes, and improving the response speed and throughput of the production line. Task allocation reconstruction refers to reassigning tasks on the production line to each machine device under the first optimization management and control scheme, while considering the capabilities of the machines, characteristics of the tasks, and layout of the production line. Evaluating machine capabilities refers to understanding the performance, status, and available time of each machine device. Analyzing task characteristics refers to understanding the requirements, time consumption, and priority of each production line task. Intelligent management and control of the production line refers to using advanced automation technology to monitor, dynamically adjust, and optimize the production line in real time according to the task allocation reconstruction result and the first optimization management and control scheme. Specifically, through sensors, actuators, and other devices, the running state, machine load, task progress, and other information of the production line are monitored in real time, and task allocation and production processes are dynamically adjusted to adapt to changes in the production line, thereby achieving intelligent management and control and optimization of the production line and improving production efficiency and device utilization.

[0039] The production line intelligent management and control system for terminal tables of new energy vehicles according to the embodiment of the application can effectively collect and analyze production data in real time, improve the flexibility of task allocation, and improve the utilization rate of equipment and the production efficiency of the terminal table production line, thereby improving the production efficiency and product performance of the terminal table production line. The production line intelligent management and control system for terminal tables of new energy vehicles includes a machine association establishment module 10, a task allocation result establishment module 20, a machine production data recording module 30, a first optimization management and control scheme establishment module 40, and a production line intelligent management and control module 50.

[0040] Below, the specific configuration of the production line intelligent management and control module 50 will be described in detail. The production line intelligent management and control module 50 can further comprise: analyzing the machine production data to obtain the average load of the machine. Analyzing the machine production data to obtain the average load of the machine means that, through data processing analysis, information related to the load of the machine is extracted from the machine production data, and the average load of the machine is calculated. It also includes establishing an optimization function as follows:

[0041]

[0042] wherein EQU is the optimization function, and a and b are weight factors for balancing the delay and load balance, respectively, c j is the completion time of task j, d j is the deadline of task j, n is the number of tasks, MaxLoad i is the maximum load of machine i, AvgLoad is the average load of the machine, and m is the total number of machines.

[0043] Below, the specific configuration of the production line intelligent management and control module 50 will be described in detail. The production line intelligent management and control module 50 can further comprise: setting a single task execution constraint, which is a constraint that a single task needs to be executed continuously on the assigned machine. The constraint that a single task needs to be executed continuously on the assigned machine means that, in the process of task scheduling or execution, if a task is assigned to a certain machine device for execution, it must be completed continuously on that machine, and cannot be interrupted or transferred to other machine devices for continuous execution. The single task execution constraint is set as follows:

[0044]

[0045] wherein x ij is a binary variable, and if task j is assigned to machine i, x ij is 1, otherwise it is 0. Specifically, in mathematics and logic, the symbol represents all or for any, indicates for all tasks j. It also includes setting a machine conflict constraint, which is a constraint that machine i can only execute one task at the same time. The load calculation formula is established as follows:

[0046]

[0047] wherein Load i represents the total load of machine i, and p ijis the processing time of task j on machine i. Further comprising, task reassignment under the first optimization control scheme is performed by single task execution constraints and machine conflict constraints, and the reconstruction result is evaluated and optimized based on the load calculation formula and the optimization function, and the task allocation reconstruction is completed. Based on the current task allocation scheme, task reassignment under the first optimization control scheme is performed by single task execution constraints and machine conflict constraints, and the task reassignment is ensured to meet the above constraints. After task reassignment, the system uses the load calculation formula and the optimization function to evaluate the effect of the new allocation scheme, for example, calculates the performance indicators such as the new machine load, task execution time, etc., and compares with the previous scheme. If the new scheme is better (i.e. better meets the optimization function), the system adopts this new allocation scheme; otherwise, continue to search for other possible allocation schemes until the optimal solution is found or a certain stopping condition is met, and finally the optimal task allocation scheme is found, and the task allocation reconstruction is completed.

[0048] The specific configuration of the production line intelligent management and control module 50 will be described in detail below. The production line intelligent management and control module 50 can further include: machine evaluation based on the production line database, and establishment of a steady-state coefficient of machine production. By analyzing historical data in the production line database, the stability and performance of the machine in the production process are evaluated, and a steady-state coefficient is determined for each machine. Specifically, this steady-state coefficient can be used as a quantitative indicator to measure machine performance, predict future performance of the machine, or compare performance between machines. According to the machine evaluation results of the historical data, a steady-state coefficient is defined for each machine. The steady-state coefficient can be a value between 0 and 1, where 1 represents the best and most stable machine performance, and 0 represents the worst and most unstable machine performance. It also includes task evaluation of the production line tasks, and establishment of a hierarchical constraint of concurrent tasks. Task evaluation refers to a comprehensive evaluation of each task on the production line based on multiple dimensions such as task urgency, overall impact on the production line, and required resources, to determine their priority, importance, complexity, etc. Concurrent tasks refer to multiple tasks performed in the same time period on the production line. Specifically, due to the limited resources and physical limitations of the production line, these tasks may interact during execution. In order to ensure that concurrent tasks can be orderly and efficiently performed, a hierarchical constraint needs to be established. The hierarchical constraint assigns a priority or level to each concurrent task based on the results of the task evaluation, to ensure that tasks with high priority can have priority in obtaining the required resources during execution, reducing waiting and delays caused by resource competition. Through hierarchical constraints, the relationship between concurrent tasks can be better coordinated, and the overall efficiency and stability of the production line can be improved. It also includes matching constraints of tasks based on the hierarchical constraints and the steady-state coefficients, and task reallocation under the first optimization control scheme based on the matching constraints, single task execution constraints, and machine conflict constraints. Matching constraints refer to the rules or conditions used to match tasks with machines using hierarchical constraints and steady-state coefficients, such as matching between task requirements and machine capabilities. Then, through matching constraints, single task execution constraints, and machine conflict constraints, task reallocation under the first optimization control scheme is performed, i.e. considering all constraint conditions, and then according to some optimization goal (such as minimizing total execution time, maximizing throughput, minimizing machine load imbalance, etc.), the tasks are reallocated to find a task allocation scheme that optimizes the optimization goal under the premise of meeting all constraint conditions or approaches the optimal solution.

[0049] In the following, the specific configuration of the first optimization control scheme establishment module 40 will be described in detail. The first optimization control scheme establishment module 40 can further include obtaining a unit penalty factor of machine adjustment. Machine adjustment refers to the preparation activities that the machine needs to perform when switching from one task to another in the terminal production line. The unit penalty factor is a value used to represent the time loss caused by each machine adjustment. For example, in the terminal production line environment, if there is a time loss for each machine adjustment, the subsequent optimization control scheme is established to redistribute the task order to reduce the total number of adjustments and improve production efficiency. It also includes performing penalty analysis on the scheme corresponding to the collaborative and balanced evaluation result through the unit penalty factor to generate a penalty analysis result. A series of possible decision schemes are determined, including different task allocations. For each decision scheme, the corresponding penalty value is calculated using the corresponding unit penalty factor. The penalty value generally represents the negative impact of the scheme on system performance, such as time loss of machine adjustment, decrease in equipment utilization, etc. Collaborative and balanced evaluation is a comprehensive consideration of penalty value, scheme feasibility, equipment utilization, production efficiency, etc. The goal is to find a decision scheme that is balanced or optimal in multiple dimensions. According to the result of the collaborative and balanced evaluation, the penalty analysis result can better understand the impact of different decision schemes on system performance, thereby making more informed decisions. For example, if the penalty value of a certain scheme is high, the decision maker may consider adjusting the scheme to reduce its negative impact on system performance. It also includes obtaining an improvement analysis of the collaborative and balanced evaluation result relative to the task allocation result to establish an improvement fitting result. In a multi-task environment, the task allocation scheme obtained by the collaborative and balanced method is compared with the original or unoptimized task allocation scheme to quantitatively analyze the performance improvement brought by the collaborative and balanced method, and a mathematical model is established to fit this improvement effect. Specifically, the performance of the task allocation scheme obtained by the collaborative and balanced evaluation method is compared with the original task allocation scheme to quantify the performance improvement brought by the collaborative and balanced method. The performance improvement brought by the collaborative and balanced method is analyzed in depth, for example, the source of the improvement (such as reducing the conflict between tasks, improving the utilization efficiency of resources, etc.), the degree of improvement (such as the percentage of performance improvement), and the stability of the improvement (i.e. whether the improvement effect is consistent under different conditions). Finally, a prediction model or regression model is established to fit the performance improvement brought by the collaborative and balanced method to obtain the improvement fitting result. It also includes performing breakthrough analysis of machine scheduling through the improvement fitting result and the penalty analysis result. In machine device scheduling, the improvement fitting result and the penalty analysis result obtained by the collaborative and balanced evaluation are used to analyze the potential improvement points in the current machine scheduling strategy in depth, thereby guiding how to optimize the machine scheduling scheme to break through the existing performance limit. If the breakthrough analysis result meets the preset limit threshold, the first optimization control scheme is established based on the collaborative and balanced evaluation result.The limit threshold refers to a preset critical value for judging whether the result of the breakthrough analysis meets the requirements according to historical data. In the optimization process of machine scheduling or task allocation, when the result of the breakthrough analysis (i.e., analyzing the effect of the current scheduling strategy in breaking through the performance limit) reaches or exceeds a preset certain limit threshold, an optimized management and control scheme, i.e., the first optimized management and control scheme, will be developed based on the result of the collaborative balance evaluation.

[0050] In the following, the specific configuration of the first optimized management and control scheme establishment module 40 will be described in detail. The first optimized management and control scheme establishment module 40 can further include: establishing a machine database based on the production line database, and performing multi-dimensional feature extraction through the machine database. The machine database is established based on various machine data of the production line, such as machine model, running state, production parameters, fault records, etc., and the feature dimensions to be extracted from the machine database are determined, including performance parameters, running state, fault mode and service life of the machine equipment, etc. Multi-dimensional features are extracted from these data for subsequent model construction, better understanding of machine performance, etc., so as to optimize the production process, improve production efficiency and quality. It also includes constructing an anomaly identification model based on the multi-dimensional feature extraction results, using random forest, neural network, etc. to construct an anomaly identification model based on the multi-dimensional feature extraction results, and performing anomaly identification on real-time machine data to ensure the stability and safety of the production process. It also includes performing periodic sampling inspection of the production of the machine, evaluating the state of the machine based on the periodic sampling inspection results, and establishing an anomaly identification period. According to the type, usage frequency, working environment, etc. of the machine, a suitable periodic sampling inspection plan is developed, and the frequency, time, product type, specific method, etc. of the sampling inspection are specified. According to the plan, the products produced by the machine are periodically sampled, and the state of the machine is evaluated based on the results of the periodic sampling inspection, including the running stability, production efficiency, product quality, etc. of the machine. According to the results of the machine state evaluation, an anomaly identification period is established to realize real-time monitoring and anomaly warning of the machine running state, ensuring the stability and safety of the production process. It also includes calling Internet of Things sensors to perform data collection of the machine under the anomaly identification period, and inputting the data collection results into the anomaly identification model to generate predictive anomaly identification results. Within the anomaly identification period, the Internet of Things sensors are called to collect data from the machine, i.e., the Internet of Things sensors monitor various running parameters of the machine in real time, such as temperature, pressure, vibration, current, etc. The collected data is input into the constructed anomaly identification model, which automatically identifies the anomalies in the machine running and generates predictive anomaly identification results, such as binary classification results (normal / abnormal) or specific anomaly types and degrees. It also includes performing machine maintenance management through the predictive anomaly identification results.

[0051] Next, the specific configuration of the first optimization management and control scheme establishment module 40 will be described in detail. The S1 in the first optimization management and control scheme establishment module 40, which performs collaborative and balanced evaluation, further includes: performing an adaptive analysis of the yield to establish a first adaptive result. Based on market demand, resource availability, equipment capacity, production cost and other factors, a suitable yield level is determined, i.e. the first adaptive result. It also includes performing a quality adaptive analysis of the production product to establish a second adaptive result. Based on market demand, customer expectations, product characteristics and cost-effectiveness, a quality adaptive strategy for the production product is determined to establish the second adaptive result, which clearly defines the quality level and quality requirements of the production product. It also includes performing a collaborative adaptability analysis of the same production line based on the first adaptive result and the second adaptive result to establish a first adaptive set. Based on the first adaptive result (usually about yield adaptation) and the second adaptive result (about product quality adaptation), the collaborative adaptability analysis of the same production line is performed to ensure that each link (upstream and downstream) of the production line can work collaboratively in the two key dimensions of yield and quality to maximize overall efficiency and benefit. Specifically, based on the first and second adaptive results, the collaborative adaptability between each link of the production line is evaluated, including whether the capacity of each link matches, whether the quality standards are consistent, whether the information transmission is smooth, etc. According to the evaluation results, collaborative strategies are developed or adjusted to optimize the overall performance and efficiency of the production line. After optimization, the adaptive parameters (including yield and quality) of each link are integrated into a set, i.e. the first adaptive set, which contains the best adaptive parameters of each link of the production line to ensure that they can work collaboratively to maximize overall efficiency.

[0052] In the foregoing, with reference to Figure 1 The production line intelligent management and control system for the terminal table of new energy vehicles according to the embodiments of the present application is described in detail. Next, the production line intelligent management and control method for the terminal table of new energy vehicles according to the embodiments of the present application will be described. Figure 2 The production line intelligent management and control method for the terminal table of new energy vehicles according to the embodiments of the present application will be described.

[0053] The production line intelligent management and control method for the terminal table of new energy vehicles, as Figure 2As shown, the method comprises: connecting the production line of the terminal table for new energy vehicles, establishing a production line database, analyzing the machines in the production line based on the production line database, and establishing machine association, wherein the machine association comprises upper and lower level cooperative association and same level processing association; obtaining a production line task, performing task allocation based on the production line database, and establishing a task allocation result; producing the terminal table for new energy vehicles based on the production line and the task allocation result, and recording machine production data; performing cooperative balance evaluation through the machine production data and the machine association, establishing a first optimization control scheme based on the cooperative balance evaluation result, and the cooperative balance evaluation is as follows: S1: performing upper and lower level cooperation adaptability analysis of the same production line based on the upper and lower level cooperative association and the machine production data, and establishing a first adaptation set; S2: performing adaptation analysis of same level interaction based on the same level processing association and the machine production data, and establishing a second adaptation set; S3: performing cooperative balance evaluation based on the first adaptation set and the second adaptation set, and establishing a cooperative balance evaluation result; establishing an optimization function, the optimization function being a target function of balancing machine load and reducing total delay, performing task allocation reconstruction under the first optimization control scheme through the optimization function, and performing intelligent control of the production line according to the task allocation reconstruction result and the first optimization control scheme.

[0054] In a possible implementation, the method further comprises: analyzing the machine production data, obtaining the average load of the machines, and establishing the optimization function as follows:

[0055]

[0056] wherein EQU is the optimization function, and α and β are weight factors of balancing delay and load balance respectively, c j is the completion time of task j, d j is the deadline of task j, n is the number of tasks, MaxLoad i is the maximum load of machine i, AvgLoad is the average load of the machines, and m is the total number of machines.

[0057] In a possible implementation, the method further comprises: setting a single task execution constraint, the single task execution constraint being a constraint that a single task needs to be executed continuously on the allocated machine, and the single task execution constraint is set as follows:

[0058]

[0059] wherein x ij is a binary variable, and if task j is allocated to machine i, then x ij1, otherwise 0; setting a machine conflict constraint, which is a constraint that machine i can only execute one task at the same time; establishing a load calculation formula as follows:

[0060]

[0061] wherein Load i characterizing the total load of machine i, p ij is the processing time of task j in machine i; performing task reassignment under the first optimization control scheme through the single-task execution constraint and the machine conflict constraint, evaluating optimization based on the load calculation formula and the optimization function, and completing task allocation reconstruction.

[0062] In a possible implementation, the task reassignment under the first optimization control scheme through the single-task execution constraint and the machine conflict constraint further includes: performing machine evaluation based on the production line database, establishing a steady-state coefficient of machine production; performing task evaluation on the line tasks, establishing a grade constraint of simultaneous zone tasks; performing matching constraint of the tasks based on the grade constraint and the steady-state coefficient, and performing task reassignment under the first optimization control scheme based on the matching constraint, the single-task execution constraint, and the machine conflict constraint.

[0063] In a possible implementation, the first optimization control scheme based on the collaborative balance evaluation result further includes: obtaining a unit penalty factor of machine adjustment; performing penalty analysis of the scheme corresponding to the collaborative balance evaluation result through the unit penalty factor, generating a penalty analysis result; obtaining an improvement analysis of the collaborative balance evaluation result relative to the task allocation result, establishing an improvement fitting result; performing breakthrough analysis of machine scheduling through the improvement fitting result and the penalty analysis result; if the breakthrough analysis result meets a preset limited threshold, establishing the first optimization control scheme based on the collaborative balance evaluation result.

[0064] In a possible implementation, the line intelligent control method of the terminal table for new energy vehicles further includes: establishing a machine database based on the production line database, and performing multi-dimensional feature extraction through the machine database; constructing an abnormality recognition model based on the multi-dimensional feature extraction result; performing production product cycle sampling inspection of the machine, performing machine state evaluation based on the cycle sampling inspection result, and establishing an abnormality recognition cycle; in the abnormality recognition cycle, calling an Internet of Things sensor to perform data collection of the machine, inputting the data collection result into the abnormality recognition model, and generating a predictive abnormality recognition result; performing machine maintenance management through the predictive abnormality recognition result.

[0065] In a possible implementation, the line intelligent management and control method of the terminal table for new energy vehicles further comprises: performing yield adaptation analysis to establish a first adaptation result; performing quality adaptation analysis of the production products to establish a second adaptation result; performing superior-inferior collaboration adaptation analysis of the same production line based on the first adaptation result and the second adaptation result to establish a first adaptation set.

[0066] The line intelligent management and control system of the terminal table for new energy vehicles provided in the embodiments of the present application can execute the line intelligent management and control method of the terminal table for new energy vehicles provided in any of the embodiments of the present application, and has the corresponding function modules and beneficial effects of the execution method.

[0067] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, however, any number of different modules can be used and run on the user terminal and / or server, and each unit and module included is only divided according to the functional logic, but is not limited to the above division, as long as the corresponding functions can be realized; in addition, the specific names of each functional unit are only for the convenience of mutual differentiation, and do not limit the protection scope of the present application.

[0068] The above specific embodiments do not constitute a limitation on the protection scope of the present application. Those skilled in the art should understand that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A line intelligent management and control system for a terminal table for new energy vehicles, characterized in that, The system comprises: A machine association establishment module for connecting a production line of a terminal table for a new energy vehicle, establishing a production line database, performing in-line machine analysis based on the production line database, and establishing machine association, wherein the machine association comprises superior-inferior collaborative association and peer processing association; A task allocation result establishment module for obtaining a line task, performing task allocation on the line task based on the production line database, and establishing a task allocation result; A machine production data recording module for producing a terminal table for a new energy vehicle based on the task allocation result in a production line and recording machine production data; A first optimization control scheme establishment module for performing collaborative balance evaluation through the machine production data and the machine association, establishing a first optimization control scheme based on the collaborative balance evaluation result, and performing collaborative balance evaluation as follows: S1: performing superior-inferior collaboration fitness analysis of the same production line based on the superior-inferior collaborative association and the machine production data, and establishing a first adaptation set; S2: performing adaptation analysis of peer interaction based on the peer processing association and the machine production data, and establishing a second adaptation set; S3: performing collaborative balance evaluation based on the first adaptation set and the second adaptation set, and establishing a collaborative balance evaluation result; A production line intelligent control module for establishing an optimization function, the optimization function being a target function balancing machine load and reducing total delay, performing task allocation reconstruction under the first optimization control scheme through the optimization function, and performing intelligent control of the production line according to the task allocation reconstruction result and the first optimization control scheme.

2. The line intelligent management and control system of the terminal table for new energy vehicles according to claim 1, characterized in that, The optimization function establishment further comprises: Analyzing the machine production data to obtain machine average load; Establishing an optimization function as follows: where EQU is the optimization function, a and b are the weight factors for balancing the delay and load balance, respectively, c j is the completion time of task j, d j is the deadline of task j, n is the number of tasks, MaxLoad i is the maximum load of machine i, AvgLoad is the average load of machines, and m is the total number of machines. 3.The line intelligent management and control system of the terminal table for new energy vehicles according to claim 2, characterized in that, The task allocation reconstruction under the first optimization control scheme through the optimization function further comprises: Setting a single task execution constraint, which is a constraint that a single task needs to be continuously executed on an allocated machine, and is set as follows: where x ij is a binary variable, x ij is 1 if task j is assigned to machine i, and 0 otherwise. Setting a machine conflict constraint, which is a constraint that machine i can only execute one task at the same time; Establishing a load calculation formula as follows: where Load i characterizes the total load of machine i, p ij is the processing time of task j at machine i; Performing task reallocation under the first optimization control scheme through the single task execution constraint and the machine conflict constraint, and performing reconstruction result evaluation optimization based on the load calculation formula and the optimization function to complete task allocation reconstruction.

4. The line intelligent management and control system of the terminal table for new energy vehicles according to claim 3, characterized in that, The task reallocation under the first optimization control scheme through the single task execution constraint and the machine conflict constraint further comprises: Performing machine evaluation based on the production line database to establish a steady-state coefficient of machine production; Performing task evaluation on the line task to establish a level constraint of concurrent tasks; Performing matching constraint of tasks based on the level constraint and the steady-state coefficient, and performing task reallocation under the first optimization control scheme based on the matching constraint, the single task execution constraint, and the machine conflict constraint.

5. The line intelligent management and control system of the terminal table for new energy vehicles according to claim 1, characterized in that, The first optimization control scheme based on the collaborative and balanced evaluation result further includes: Obtaining a unit penalty factor adjusted by the machine; Performing penalty analysis on the scheme corresponding to the collaborative and balanced evaluation result through the unit penalty factor to generate a penalty analysis result; Obtaining an improvement analysis of the collaborative and balanced evaluation result relative to the task allocation result to establish an improvement fitting result; Performing breakthrough analysis of the machine scheduling through the improvement fitting result and the penalty analysis result; If the breakthrough analysis result meets a preset limited threshold, the first optimization control scheme is established based on the collaborative and balanced evaluation result. 6.The line intelligent management and control system of the terminal table for new energy vehicles according to claim 1, characterized in that, The system further includes: Establishing a machine database based on the production line database and performing multi-dimensional feature extraction through the machine database; Constructing an abnormality identification model based on the multi-dimensional feature extraction result; Performing production product cycle sampling of the machine, performing machine state evaluation based on the cycle sampling result, and establishing an abnormality identification cycle; In the abnormality identification cycle, calling the Internet of Things sensor to perform data collection of the machine, inputting the data collection result into the abnormality identification model, and generating a predictive abnormality identification result; Performing machine maintenance management through the predictive abnormality identification result.

7. The line intelligent management and control system of the terminal table for new energy vehicles according to claim 1, characterized in that, The S1 further includes: Performing adaptation analysis of the yield to establish a first adaptation result; Performing quality adaptation analysis of the production product to establish a second adaptation result; Performing upper and lower level collaboration adaptability analysis of the same production line based on the first adaptation result and the second adaptation result to establish a first adaptation set.

8. A terminal table production line intelligent management and control method for new energy vehicles, characterized in that, The method is applied to the production line intelligent control system of the terminal table for new energy vehicles in claim 1, and the method includes: Connecting the production line of the terminal table for new energy vehicles, establishing a production line database, performing machine analysis in the production line based on the production line database, and establishing machine correlation, wherein the machine correlation includes upper and lower level collaborative correlation and same level processing correlation; Obtaining a production line task, performing task allocation on the production line task based on the production line database, and establishing a task allocation result; Producing the terminal table for new energy vehicles based on the task allocation result in the production line, and recording machine production data; Performing collaborative and balanced evaluation through the machine production data and the machine correlation, establishing a first optimization control scheme based on the collaborative and balanced evaluation result, and the collaborative and balanced evaluation is as follows: S1: Performing upper and lower level collaboration adaptability analysis of the same production line based on the upper and lower level collaborative correlation and the machine production data to establish a first adaptation set; S2: Performing adaptation analysis of same level interaction based on the same level processing correlation and the machine production data to establish a second adaptation set; S3: Performing collaborative and balanced evaluation based on the first adaptation set and the second adaptation set to establish a collaborative and balanced evaluation result; Establishing an optimization function, the optimization function being a target function balancing machine load and reducing total delay, performing task allocation reconstruction under the first optimization control scheme through the optimization function, and performing intelligent control of the production line according to the task allocation reconstruction result and the first optimization control scheme. The system further includes: Establishing a machine database based on the production line database and performing multi-dimensional feature extraction through the machine database; Constructing an abnormality identification model based on the multi-dimensional feature extraction result; Performing production product cycle sampling of the machine, performing machine state evaluation based on the cycle sampling result, and establishing an abnormality identification cycle; In the abnormality identification cycle, calling the Internet of Things sensor to perform data collection of the machine, inputting the data collection result into the abnormality identification model, and generating a predictive abnormality identification result; Performing machine maintenance management through the predictive abnormality identification result. The S1 further includes: Performing adaptation analysis of the yield to establish a first adaptation result; Performing quality adaptation analysis of the production product to establish a second adaptation result; Performing upper and lower level collaboration adaptability analysis of the same production line based on the first adaptation result and the second adaptation result to establish a first adaptation set. The method is applied to the production line intelligent control system of the terminal table for new energy vehicles in claim 1, and the method includes: Connecting the production line of the terminal table for new energy vehicles, establishing a production line database, performing machine analysis in the production line based on the production line database, and establishing machine correlation, wherein the machine correlation includes upper and lower level collaborative correlation and same level processing correlation; Obtaining a production line task, performing task allocation on the production line task based on the production line database, and establishing a task allocation result; Producing the terminal table for new energy vehicles based on the task allocation result in the production line, and recording machine production data; Performing collaborative and balanced evaluation through the machine production data and the machine correlation, establishing a first optimization control scheme based on the collaborative and balanced evaluation result, and the collaborative and balanced evaluation is as follows: S1: Performing upper and lower level collaboration adaptability analysis of the same production line based on the upper and lower level collaborative correlation and the machine production data to establish a first adaptation set; S2: Performing adaptation analysis of same level interaction based on the same level processing correlation and the machine production data to establish a second adaptation set; S3: Performing collaborative and balanced evaluation based on the first adaptation set and the second adaptation set to establish a collaborative and balanced evaluation result; Establishing an optimization function, the optimization function being a target function balancing machine load and reducing total delay, performing task allocation reconstruction under the first optimization control scheme through the optimization function, and performing intelligent control of the production line according to the task allocation reconstruction result and the first optimization control scheme.

Images