A method, system and device for balancing workstations and allocating resources for a wiring harness production line

By collecting and analyzing real-time data of the production line, dynamically adjusting station task allocation and resource allocation, and using intelligent multi-factor and hybrid heuristic algorithms, the problem of inefficiency of the production line is solved and the production efficiency and resource utilization are improved.

CN118469265BActive Publication Date: 2024-12-03CHANGCHUN E PLUS TECH CO LTD +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410939226.1
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-07-15
Publication Date
2024-12-03
Estimated Expiration
2044-07-15

AI Technical Summary

Technical Problem

The data analysis of station balance and resource allocation of online harness production line is not accurate enough, resulting in inaccurate station and task allocation and resource allocation, resulting in inefficiency of production line.

Method used

By collecting real-time data of the production line for preprocessing and intelligent analysis, building prediction models, dynamically adjusting station task allocation and resource allocation, and using intelligent multi-factor dynamic balanced allocation algorithm and hybrid heuristic resource optimization algorithm to generate optimization solutions.

Benefits of technology

It achieves real-time grasp of production conditions, improves production efficiency, ensures that tasks are allocated to appropriate stations, optimizes resource allocation, and reduces production cycles and downtime.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118469265B_ABST
    Figure CN118469265B_ABST
Patent Text Reader

Abstract

The present invention relates to the field of data processing, and in particular to a method, system and device for workstation balancing and resource allocation of a wiring harness production line. The content includes: collecting and preprocessing real-time production data, further performing intelligent analysis, and obtaining analysis results; constructing a prediction model to predict the preprocessed real-time production data and obtain prediction results; dynamically adjusting the workstation task allocation based on the workstation task load analysis results in the analysis results; optimizing the allocation based on the prediction results to obtain optimized workstation task allocation adjustment suggestions; allocating resources for equipment and personnel on the production line based on the equipment and personnel utilization analysis results in the analysis results and the optimized workstation task allocation adjustment suggestions; optimizing resource allocation based on the prediction results to obtain an optimized resource allocation plan. The technical problems of inaccurate data analysis and low production line efficiency during workstation balancing and resource allocation of wiring harness production lines are solved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of data processing, and in particular to a method, system and device for balancing workstations and allocating resources for a wiring harness production line. Background Art

[0002] In modern manufacturing, the efficiency and flexibility of production lines are crucial to the competitiveness of enterprises. With the continuous development of industrial automation and intelligent manufacturing technology, traditional production line management methods can no longer meet the increasingly complex and changing production needs. Therefore, the introduction of data collection, intelligent analysis and optimization and deployment technology has become the key to improving production efficiency and resource utilization.

[0003] Traditional production line management usually relies on manual experience and fixed scheduling rules, lacks effective use of real-time data, and cannot quickly respond to changes in the production environment. During the production process, problems such as idle equipment, waiting personnel, and uneven workstation load often occur, resulting in low production efficiency and increased costs. In addition, the formulation and adjustment of production plans often lack scientific basis, making it difficult to discover and solve production bottlenecks in a timely manner.

[0004] However, the above technology has at least the following technical problems: insufficiently accurate data analysis during workstation balance and resource allocation in the wiring harness production line, and low production line efficiency caused by inaccurate workstation and task allocation and resource allocation. Summary of the invention

[0005] The present invention provides a method, system and device for balancing workstations and allocating resources of a wiring harness production line, so as to solve the technical problems of low production line efficiency caused by inaccurate data analysis, inaccurate workstation and task allocation and inaccurate resource allocation during workstation balancing and resource allocation of the wiring harness production line.

[0006] A method, system and device for balancing workstations and allocating resources for a wiring harness production line of the present invention specifically include the following technical solutions:

[0007] A method for balancing workstations and allocating resources for a wiring harness production line comprises the following steps:

[0008] S1. Collect real-time production data from all links of the production line and pre-process the real-time production data; perform intelligent analysis on the pre-processed real-time production data to obtain analysis results; build a prediction model, input the pre-processed real-time production data into the prediction model, obtain prediction results, and use the prediction results as prediction feedback;

[0009] S2. Based on the workstation task load analysis results in the analysis results, dynamically adjust the workstation task allocation, and optimize the allocation based on the prediction feedback to obtain the optimized workstation task allocation adjustment suggestions;

[0010] S3. Based on the equipment utilization and personnel utilization analysis results in the analysis results and the optimized workstation task allocation adjustment suggestions, allocate resources for equipment and personnel on the production line; optimize resource allocation based on prediction feedback to obtain an optimized resource allocation plan.

[0011] Preferably, the S1 specifically includes:

[0012] The pre-processed real-time production data is intelligently analyzed using a comprehensive production efficiency analysis algorithm to obtain grading results; the analysis results include workstation task load analysis results, equipment utilization rate and personnel utilization rate analysis results.

[0013] Preferably, the S2 specifically includes:

[0014] In the process of dynamically adjusting the workstation task allocation, an intelligent multi-factor dynamic balanced allocation algorithm is introduced.

[0015] Preferably, the S2 specifically includes:

[0016] The specific implementation process of the intelligent multi-factor dynamic balanced allocation algorithm is as follows:

[0017] Define influencing factors, including task time requirements, task priority, task urgency, current load of the workstation, processing capacity of the workstation, idle time of the workstation, equipment status of the workstation and predicted feedback; calculate task priority weights based on task priority, urgency and time requirements; calculate workstation load balance index based on current load, processing capacity and idle time of the workstation; calculate workstation adaptability index based on current load, idle time, processing capacity and equipment status of the workstation; calculate task adaptability weights based on task priority, urgency and time requirements; construct a task allocation matrix based on task priority weights, predicted feedback, workstation load balance index, workstation adaptability index and task adaptability weights, and perform dynamic allocation to generate a task allocation plan.

[0018] Preferably, the S2 specifically includes:

[0019] After the task allocation is completed, the load information of the workstation is updated, and the workstation load balance index is recalculated based on the updated workstation load information, and the task allocation plan is updated in real time to obtain optimized workstation task allocation adjustment suggestions.

[0020] Preferably, the S3 specifically includes:

[0021] In the process of allocating resources for equipment and personnel on the production line, an intelligent resource allocation optimization algorithm is introduced.

[0022] Preferably, the S3 specifically includes:

[0023] In the process of implementing the intelligent resource allocation optimization algorithm, the optimization objectives, objective functions and constraints are defined.

[0024] Preferably, the S3 specifically includes:

[0025] In the process of optimizing resource allocation, a hybrid heuristic resource optimization algorithm is introduced to obtain the optimized resource allocation plan.

[0026] A wiring harness production line workstation balancing and resource allocation device, used to implement a wiring harness production line workstation balancing and resource allocation method, comprising the following parts:

[0027] Data collection and analysis unit, forecasting unit, deployment and optimization unit;

[0028] The data collection and analysis unit collects real-time production data from all links of the production line through data acquisition equipment, and performs pre-processing and intelligent analysis on the real-time production data to obtain analysis results;

[0029] The prediction unit is connected to the data collection and analysis unit, and predicts the pre-processed real-time production data by building a prediction model to obtain the prediction result;

[0030] The deployment and optimization unit is connected to the prediction unit and the data collection and analysis unit. It dynamically adjusts the workstation task allocation based on the analysis and prediction results, and deploys and optimizes the resources of the equipment and personnel on the production line.

[0031] A wiring harness production line workstation balancing and resource allocation system is used to implement a wiring harness production line workstation balancing and resource allocation method, including the following parts:

[0032] Data collection module, data analysis module, learning and prediction module, intelligent workstation balance module, resource allocation optimization module;

[0033] The data acquisition module collects the real-time production data of each link of the production line, pre-processes the real-time production data, and transmits the pre-processed real-time production data to the data analysis module;

[0034] The data analysis module performs intelligent analysis on the pre-processed real-time production data to obtain analysis results, including workstation task load analysis results, equipment utilization rate and personnel utilization rate analysis results; the analysis results are transmitted to the intelligent workstation balancing module and the resource allocation optimization module;

[0035] The learning and prediction module builds a prediction model, processes the preprocessed real-time production data through the prediction model, obtains the prediction results, and sends the prediction results as prediction feedback to the intelligent workstation balancing module and resource allocation optimization module;

[0036] The intelligent workstation balancing module dynamically adjusts the workstation task allocation based on the workstation task load analysis results in the analysis results, optimizes the allocation based on the prediction feedback, obtains the optimized workstation task allocation adjustment suggestions, and transmits the optimized workstation task allocation adjustment suggestions to the resource allocation optimization module;

[0037] The resource allocation optimization module allocates resources for equipment and personnel on the production line based on the equipment utilization and personnel utilization analysis results in the analysis results and the optimized workstation task allocation adjustment suggestions, and optimizes based on the predicted feedback to obtain the optimized resource allocation plan.

[0038] The beneficial effects of the technical solution of the present invention are:

[0039] 1. By collecting and preprocessing data from all aspects of the production line in real time, the production situation can be instantly understood. The comprehensive production efficiency analysis algorithm is used to intelligently analyze the data, and the task load analysis results, equipment utilization rate and personnel utilization rate analysis results of each workstation are comprehensively and quickly obtained, which helps to timely discover production bottlenecks, optimize resource allocation, and improve overall production efficiency.

[0040] 2. By comprehensively considering task priority, workstation load balance, task urgency, workstation idle time, equipment status and predictive feedback, task allocation can be dynamically adjusted according to real-time production data. Using the intelligent multi-factor dynamic balanced allocation algorithm, an accurate task allocation plan can be generated to ensure that each task is assigned to the most suitable workstation and improve production efficiency. Optimize allocation by introducing predictive feedback. The calculation of the workstation adaptability index enables the workstation balance and resource allocation system of the wire harness production line to adjust task allocation according to the load, idle time and equipment status of the workstation, which improves the adaptability and flexibility of the workstation balance and resource allocation system of the wire harness production line.

[0041] 3. Introducing intelligent resource allocation optimization algorithm By comprehensively considering production costs, equipment utilization and workstation load balance, the optimal resource allocation plan can be formulated. Using a hybrid heuristic resource optimization algorithm, the optimal solution is continuously approached in each iteration, thereby improving the overall efficiency of the production line and reducing production cycles and downtime. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 A flow chart of a method for balancing workstations and allocating resources for a wiring harness production line according to the present invention;

[0043] Figure 2 A connection diagram of a workstation balancing and resource allocation device for a wiring harness production line according to the present invention;

[0044] Figure 3This is a structural diagram of a wiring harness production line workstation balancing and resource allocation system described in the present invention. DETAILED DESCRIPTION

[0045] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the technical scheme in the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiment of the present invention. Obviously, the described embodiment is only a part of the embodiment of the present invention, not all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0046] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0047] The following is a detailed description of a specific scheme of a wiring harness production line workstation balancing and resource allocation method, system and device provided by the present invention in conjunction with the accompanying drawings.

[0048] See attached Figure 1 , which shows a flow chart of a method for balancing workstations and allocating resources for a wiring harness production line provided by an embodiment of the present invention, the method comprising the following steps:

[0049] S1. Collect real-time production data from all links of the production line and pre-process the real-time production data; perform intelligent analysis on the pre-processed real-time production data to obtain analysis results; build a prediction model, input the pre-processed real-time production data into the prediction model, obtain prediction results, and use the prediction results as prediction feedback;

[0050] Real-time production data of each link of the production line is collected through data collection equipment such as sensors. The real-time production data includes sensor data such as equipment status, production progress, and workstation load, workstation task data such as task volume and completion time, and personnel information data such as skill level and workload;

[0051] The collected real-time production data is preprocessed using existing preprocessing technologies such as data cleaning, format conversion, outlier processing, and data integration to obtain preprocessed real-time production data; the preprocessing technology is a technical means well known to those skilled in the art and will not be described in detail here;

[0052] Based on the pre-processed real-time production data, the comprehensive production efficiency analysis algorithm is used for intelligent analysis to obtain the analysis results of the task load of each workstation, the equipment utilization rate, and the personnel utilization rate. The specific implementation process is as follows:

[0053] Analyze the task load of each workstation; calculate the task load of each workstation based on the pre-processed real-time production data;

[0054] ,

[0055] in, It is The task load of the workstation is a combination of time, difficulty, and harmonic mean adjusted task load, reflecting the overall pressure of the workstation when performing tasks; It is Workstation No. The time of the task, ; It is The total number of tasks at the workstation; It is Workstation No. The difficulty of the task reflects the complexity and difficulty of the task; is the total available time of the workstation; It is Workstation No. The time of the task, ; is the number of tasks used to calculate the harmonic mean; It is Workstation No. The time of the task, ; is the number of tasks used to compute the additional logarithmic terms of the harmonic mean; All are integers; is the harmonic mean adjustment term for task time, based on Workstation No. Time of task Calculates the harmonic mean of all completed task times to balance the impact of task time on load. is an additional logarithmic adjustment of the harmonic mean, based on Workstation No. Time of task The calculation provides additional logarithmic adjustments to enhance the accuracy of the load calculations.

[0056] For equipment utilization analysis, calculate the utilization rate of each device based on pre-processed real-time production data.

[0057] ,

[0058] in, It is Equipment utilization rate reflects the efficiency of equipment use; It is Equipment The time of the next run; is the total time of the device, which means the total time in the evaluation period, including the device operation time and idle time; It is Equipment The idle time indicates that the device is idle for the first time. The total idle time between the first shutdown and the next restart; Indicates the total number of runs; Indicates the total number of idle times; It is a composite measure of all running times, using square root and logarithmic operations to smooth the data and emphasize the impact of long running time on equipment utilization; It is the logarithmic transformation of the total time, which is used to smooth the total time data and reduce the impact of outliers; It is an adjustment item of the harmonic mean of idle time, which reduces the negative impact of long-term idle time on equipment utilization through square root and reciprocal operations.

[0059] For personnel utilization analysis; calculate the utilization rate of each worker based on pre-processed real-time production data.

[0060] ,

[0061] in, It is Worker utilization rate reflects the worker's work efficiency; It is Workers The time of the work; is the total working time of the worker; A worker The total number of tasks; It is the natural logarithm function, which is used to perform logarithmic transformation on the data to smooth the data and reduce the influence of extreme values ​​on the results; It is to prevent the input of the logarithmic function from being zero and to smooth the effect of the working time; A worker The harmonic mean adjustment term of rest time indicates the distribution of workers' rest time; It is Workers The time for the next break; A worker The total number of breaks.

[0062] The analysis results are obtained through the above process, and the analysis results include workstation task load analysis results, equipment utilization rate and personnel utilization rate analysis results.

[0063] Through the comprehensive production efficiency analysis algorithm, various indicators of the production line can be effectively analyzed, providing detailed analysis results of workstation task load, equipment utilization and personnel utilization. The accuracy and reliability of the analysis results are ensured, providing a solid data foundation for intelligent workstation balance and resource allocation optimization.

[0064] Furthermore, historical production data of the production line is collected and existing preprocessing technologies such as data cleaning, format conversion, outlier processing, and data integration are used for data preprocessing to obtain preprocessed historical production data of the production line. Then, based on expert experience, an existing machine learning algorithm is selected to build a prediction model, and the prediction model is trained and verified to realize predictive analysis of production data. The preprocessed real-time production data is processed through the prediction model to obtain prediction results, which are used as prediction feedback; the prediction results include equipment status prediction, production progress prediction, workstation load prediction, and task completion prediction.

[0065] S2. Based on the workstation task load analysis results in the analysis results, dynamically adjust the workstation task allocation, and optimize the allocation based on the prediction feedback to obtain the optimized workstation task allocation adjustment suggestions;

[0066] Based on the workstation task load analysis results in the analysis results, the intelligent multi-factor dynamic balanced allocation algorithm is used to dynamically adjust the workstation task allocation, and optimize the allocation based on the prediction feedback to obtain the optimized workstation task allocation adjustment suggestions. The specific implementation process is as follows:

[0067] An optimized task allocation plan is generated by comprehensively considering task priority, workstation load balance, task urgency, workstation idle time, equipment status and real-time performance.

[0068] Define multidimensional influencing factors;

[0069] It is The time requirement of each task (completion time); It is The priority of each task; It is The urgency of the task; It is The current load of each workstation; It is Processing capacity of each workstation; It is Idle time of each workstation; It is Equipment status of each workstation; is the prediction feedback, indicating the task At the workstation Possibility of completion;

[0070] Calculate task priority weights;

[0071] ,

[0072] in, It is The priority weight of a task combines the task's priority, urgency, and time requirements.

[0073] Calculate the workstation load balance index;

[0074] ,

[0075] in, It is The load balance index of each workstation combines the current load, processing capacity and idle time of the workstation.

[0076] Calculate the workstation adaptability index;

[0077] ,

[0078] in, It is The adaptability index of each workstation combines the current load, idle time, processing capacity and equipment status of the workstation.

[0079] Calculate task adaptability weights;

[0080] ,

[0081] in, It is The adaptability weight of a task combines the task's priority, urgency, and time requirements.

[0082] Construct a task allocation matrix;

[0083] ,

[0084] in, Indicates the total number of tasks; Indicates that the task Assign to workstation fitness; it combines task priority weight, prediction feedback, workstation load balancing index, workstation adaptability index and task adaptability weight.

[0085] Dynamic allocation;

[0086] ,

[0087] in, Indicates the total number of workstations; Representation Task Assign to workstation The probability of taking into account the influence of the load balance index of the workstation, and normalizing the fitness into probability.

[0088] Optimize the allocation plan; time requirements for each task , according to the task Assign to workstation Probability Generate a task allocation plan, that is, select The task is assigned to the workstation with the largest value.

[0089] After the task allocation is completed, the load information of the workstation is updated, and the load balance index of the workstation is recalculated based on the updated load information of the workstation, so that the allocation plan is updated in real time, thereby obtaining an optimized workstation task allocation adjustment suggestion.

[0090] Through the intelligent multi-factor dynamic balanced allocation algorithm, combined with task priority, workstation load balance, task urgency, workstation idle time, equipment status and predictive feedback, the optimal allocation of intelligent workstation tasks is achieved, accurate task allocation suggestions are generated, and the efficiency and coordination of the production line are improved.

[0091] S3. Based on the equipment utilization and personnel utilization analysis results in the analysis results and the optimized workstation task allocation adjustment suggestions, allocate resources for equipment and personnel on the production line; optimize resource allocation based on prediction feedback to obtain an optimized resource allocation plan.

[0092] Based on the analysis results of equipment utilization and personnel utilization, the optimized workstation task allocation adjustment suggestions and prediction feedback, the intelligent resource allocation optimization algorithm is used to allocate and optimize resources to obtain the optimized resource allocation plan. The specific implementation process is as follows:

[0093] Define optimization goals; clarify specific goals for resource allocation optimization, including minimizing production costs, maximizing equipment utilization, and balancing workstation loads;

[0094] Define the objective function;

[0095] ,

[0096] in, represents the total production cost; Indicates the device Complete the task Costs; Indicates personnel Complete the task Costs; Indicates the device On Task The allocation status on ; Indicates personnel On Task The allocation status on ; Indicates the device To the task Utilization rate; Indicates personnel To the task Utilization rate; and To adjust the parameters, used to balance the weights of different objectives; is the total number of tasks; is the total number of devices; is the total number of personnel.

[0097] Constraints;

[0098] Each task must be processed by at least one device and person, the availability of devices and people, resource usage restrictions; as well as optimization constraints based on prediction feedback, equipment utilization constraints:

[0099] ,

[0100] in, Indicates the device On Task Predicted load on Representation Task time requirements; Indicates the device Total available working hours, reflecting the equipment The total time that can be used.

[0101] Personnel utilization restrictions:

[0102] ,

[0103] in, Indicates personnel On Task Predicted load on Indicates personnel Total available working hours, reflecting personnel The total time available for work.

[0104] In order to achieve the above goals, a hybrid heuristic resource optimization algorithm is introduced by combining the advantages of genetic algorithm and simulated annealing algorithm. The specific implementation process includes initializing the population and generating a set of random initial solutions as the initial population. The fitness of each solution is calculated using the objective function, and the parent individuals are selected according to the fitness using the expert experience method. The selected parent individuals are crossovered to generate child individuals. The child individuals are mutated to increase the diversity of solutions and obtain new solutions. After crossover and mutation, the new solution is simulated annealing to increase the probability of jumping out of the local optimum. The population is further updated to replace the parent individuals with the child individuals to form a new population.

[0105] Repeat the above steps until the stopping condition is reached (such as reaching the number of iterations or the fitness threshold), and the optimal solution is obtained. According to the optimal solution, the equipment and personnel of the production line are optimized for resource allocation to obtain the optimized resource allocation plan.

[0106] The intelligent resource allocation optimization algorithm can not only effectively optimize the configuration of production line equipment and personnel, but also use predictive feedback information to further improve the optimization effect, thereby improving production efficiency and reducing production costs.

[0107] According to the above method embodiment, another embodiment of the present invention provides a wiring harness production line station balancing and resource allocation device, referring to the attached Figure 2 , the device includes the following parts:

[0108] Data collection and analysis unit, forecasting unit, deployment and optimization unit;

[0109] The data collection and analysis unit collects real-time production data of each link of the production line through data collection equipment such as sensors, and performs pre-processing and intelligent analysis on the collected real-time production data to obtain analysis results;

[0110] The prediction unit is connected to the data collection and analysis unit, and predicts the pre-processed real-time production data by building a prediction model to obtain the prediction result;

[0111] The deployment and optimization unit is connected to the prediction unit and the data collection and analysis unit. It dynamically adjusts the workstation task allocation based on the analysis and prediction results, and deploys and optimizes the resources of the equipment and personnel on the production line.

[0112] According to the above device and method embodiments, another embodiment of the present invention further provides a wiring harness production line station balancing and resource allocation system, referring to the attached Figure 3 The system includes the following parts:

[0113] Data collection module, data analysis module, learning and prediction module, intelligent workstation balance module, resource allocation optimization module;

[0114] Among them, the data acquisition module and the data analysis module are attached Figure 2 The data collection and analysis unit in the wiring harness production line workstation balancing and resource allocation device shown in the figure is a component of the data collection and analysis unit in the wiring harness production line workstation balancing and resource allocation device shown in the figure; the learning and prediction module is an additional Figure 2 The prediction unit in the workstation balancing and resource allocation device of the wiring harness production line shown in the figure; the intelligent workstation balancing module and the resource allocation optimization module are attached Figure 2 The components of the deployment and optimization unit in the workstation balancing and resource deployment device of the wiring harness production line shown;

[0115] The data acquisition module collects the real-time production data of each link of the production line, pre-processes the collected real-time production data, and transmits the pre-processed real-time production data to the data analysis module;

[0116] The real-time production data includes sensor data such as equipment status, production progress, and workstation load, workstation task data such as task volume and completion time, and personnel information data such as skill level and workload;

[0117] The data analysis module performs intelligent analysis on the pre-processed real-time production data, obtains the analysis results, and transmits the analysis results to the intelligent workstation balancing module and the resource allocation optimization module;

[0118] The analysis results include the task load analysis results of each workstation, equipment utilization rate and personnel utilization rate analysis results;

[0119] The learning and prediction module uses a machine learning algorithm to learn the historical production line production data to obtain a prediction model, processes the pre-processed real-time production data obtained by the data acquisition module through the prediction model to obtain a prediction result, and sends the prediction result as prediction feedback to the intelligent workstation balancing module and the resource allocation optimization module;

[0120] The intelligent workstation balancing module dynamically adjusts the workstation task allocation based on the workstation task load analysis results in the analysis results provided by the data analysis module, and optimizes the allocation based on the prediction feedback provided by the learning and prediction module, obtains the optimized workstation task allocation adjustment suggestions, and transmits the optimized workstation task allocation adjustment suggestions to the resource allocation optimization module;

[0121] The resource allocation optimization module allocates resources for equipment and personnel on the production line based on the equipment utilization and personnel utilization analysis results provided by the data analysis module and the optimized workstation task allocation adjustment suggestions provided by the intelligent workstation balancing module, and optimizes based on the prediction feedback provided by the learning and prediction module to obtain an optimized resource allocation plan.

[0122] The order of the embodiments of the invention is for description only and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0123] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

[0124] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that the technical solutions described in the above embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention.

Claims

1. A method for balancing workstations and allocating resources in a wiring harness production line. It is characterized in that The following steps are involved: S1. Collect real-time production data from all links of the production line and pre-process the real-time production data; Perform intelligent analysis on the pre-processed real-time production data to obtain analysis results; at the same time, build a prediction model, input the pre-processed real-time production data into the prediction model, obtain prediction results, including equipment status prediction, production progress prediction, workstation load prediction, task completion prediction, and use the prediction results as prediction feedback; S2. Based on the workstation task load analysis results in the analysis results, dynamically adjust the workstation task allocation, and optimize the allocation based on the prediction feedback to obtain the optimized workstation task allocation adjustment suggestions; S3. Based on the analysis results of equipment utilization and personnel utilization and the optimized workstation task allocation adjustment suggestions, an intelligent resource allocation optimization algorithm is introduced to allocate resources for equipment and personnel on the production line. In the implementation process of the intelligent resource allocation optimization algorithm, the objective function is constrained by defining the optimization goal, setting the equipment utilization constraint and the personnel utilization constraint; Define optimization goals; clarify specific goals for resource allocation optimization, including minimizing production costs, maximizing equipment utilization, and balancing workstation loads; The objective function is calculated as follows: , in, represents the total production cost; Indicates the device Complete the task Costs; Indicates personnel Complete the task Costs; Indicates the device On Task The allocation status on ; Indicates personnel On Task The allocation status on ; Indicates the device To the task Utilization rate; Indicates personnel To the task Utilization rate; and To adjust the parameters; is the total number of tasks; is the total number of devices; is the total number of personnel; Resource allocation is optimized based on prediction feedback to obtain an optimized resource allocation plan.

2. The wiring harness production line station balancing and resource allocation method according to claim 1, It is characterized in that The S1 specifically includes: The pre-processed real-time production data is intelligently analyzed using a comprehensive production efficiency analysis algorithm to obtain analysis results; the analysis results include workstation task load analysis results, equipment utilization rate and personnel utilization rate analysis results.

3. The wiring harness production line station balancing and resource allocation method according to claim 1, It is characterized in that The S2 specifically includes: In the process of dynamically adjusting the workstation task allocation, an intelligent multi-factor dynamic balanced allocation algorithm is introduced. The specific implementation process is as follows: Define influencing factors, including task time requirements, task priority, task urgency, current load of the workstation, processing capacity of the workstation, idle time of the workstation, equipment status of the workstation and predicted feedback; calculate task priority weights based on task priority, urgency and time requirements; calculate workstation load balance index based on current load, processing capacity and idle time of the workstation; calculate workstation adaptability index based on current load, idle time, processing capacity and equipment status of the workstation; calculate task adaptability weights based on task priority, urgency and time requirements; construct a task allocation matrix based on task priority weights, predicted feedback, workstation load balance index, workstation adaptability index and task adaptability weights, and perform dynamic allocation to generate a task allocation plan.

4. The method for balancing workstations and allocating resources for a wiring harness production line according to claim 3, It is characterized in that The S2 specifically includes: After the task allocation is completed, the load information of the workstation is updated, and the workstation load balance index is recalculated based on the updated workstation load information, and the task allocation plan is updated in real time to obtain optimized workstation task allocation adjustment suggestions.

5. The method for balancing workstations and allocating resources for a wiring harness production line according to claim 1, It is characterized in that The S3 specifically includes: In the process of optimizing resource allocation, a hybrid heuristic resource optimization algorithm is introduced to obtain an optimized resource allocation plan; the specific implementation process of the hybrid heuristic resource optimization algorithm includes initializing the population and generating a set of random initial solutions as the initial population; using the objective function to calculate the fitness of each solution, and selecting the parent individual according to the fitness using the expert experience method; performing a crossover operation on the selected parent individuals to generate child individuals; performing a mutation operation on the child individuals to increase the diversity of solutions and obtain new solutions; after crossover and mutation, performing a simulated annealing operation on the new solution to increase the probability of jumping out of the local optimum; further updating the population, replacing the parent individuals with the child individuals to form a new population.

6. A wiring harness production line station balancing and resource allocation device, It is characterized in that The method for realizing the workstation balancing and resource allocation of a wiring harness production line according to any one of claims 1 to 5 comprises the following parts: Data collection and analysis unit, forecasting unit, deployment and optimization unit; The data collection and analysis unit collects real-time production data from all links of the production line through data acquisition equipment, and performs pre-processing and intelligent analysis on the real-time production data to obtain analysis results; The prediction unit is connected to the data collection and analysis unit, and predicts the pre-processed real-time production data by building a prediction model to obtain the prediction result; The deployment and optimization unit is connected to the prediction unit and the data collection and analysis unit. It dynamically adjusts the workstation task allocation based on the analysis and prediction results, and deploys and optimizes the resources of the equipment and personnel on the production line.

7. A wiring harness production line station balancing and resource allocation system, It is characterized in that The method for realizing the workstation balancing and resource allocation of a wiring harness production line according to any one of claims 1 to 5 comprises the following parts: Data collection module, data analysis module, learning and prediction module, intelligent workstation balance module, resource allocation optimization module; The data acquisition module collects the real-time production data of each link of the production line, pre-processes the real-time production data, and transmits the pre-processed real-time production data to the data analysis module; The data analysis module performs intelligent analysis on the pre-processed real-time production data to obtain analysis results, including workstation task load analysis results, equipment utilization rate and personnel utilization rate analysis results; the analysis results are transmitted to the intelligent workstation balancing module and the resource allocation optimization module; The learning and prediction module builds a prediction model, processes the preprocessed real-time production data through the prediction model, obtains the prediction results, and sends the prediction results as prediction feedback to the intelligent workstation balancing module and resource allocation optimization module; The intelligent workstation balancing module dynamically adjusts the workstation task allocation based on the workstation task load analysis results in the analysis results, optimizes the allocation based on the prediction feedback, obtains the optimized workstation task allocation adjustment suggestions, and transmits the optimized workstation task allocation adjustment suggestions to the resource allocation optimization module; The resource allocation optimization module allocates resources for equipment and personnel on the production line based on the equipment utilization and personnel utilization analysis results in the analysis results and the optimized workstation task allocation adjustment suggestions, and optimizes based on the predicted feedback to obtain the optimized resource allocation plan.