Intelligent monitoring management system and method for wire harness production line

Abstract

The invention discloses an intelligent monitoring management system and method for a wire harness production line, and relates to the technical field of wire harness manufacturing, and the method comprises the steps: extracting data of crimping force and mold temperature from historical wire harness production data, coding the data into a real number coding gene chain, generating an initial gene pool in combination with material attributes, and constructing a digital twin model; the method comprises the steps of simulating stress field distribution and a heat conduction effect in a wire harness crimping process through finite element simulation, obtaining a twinning predicted value, pre-verifying process parameters in an initial gene bank based on a digital twinning model, screening process parameter combinations with deformation errors smaller than an error threshold value, and issuing the process parameter combinations to a crimping machine through a production line control center. According to the method, data of real-time wire harness deformation quantity is obtained, the data of the real-time wire harness deformation quantity is compared with a twinborn predicted value frame by frame, a deformation error rate is generated, and an abnormal traceability report is generated based on the deformation error rate, pre-verification is performed by constructing an initial gene pool and combining a digital twinborn model, so that optimization of process parameters is more accurate and effective.

Description

Technical Field

[0001] The present invention relates to the technical field of wire harness manufacturing, in particular to an intelligent monitoring and management system and method for a wire harness production line. Background Art

[0002] With the iterative development of industrial technologies, the level of intelligence and automation of wire harness production lines has been continuously improved. In traditional technologies, wire harness production mainly relies on manual operations and simple mechanical auxiliary equipment, which is not only inefficient but also difficult to control the quality. In recent years, with the development of computer-aided design, finite element analysis, and digital twin technologies, the accuracy and efficiency of wire harness production have been significantly improved.

[0003] In the existing wire harness production monitoring and management technologies, there are still some deficiencies. On the one hand, there is a lack of intelligent methods for optimizing key process parameters such as pressing force and die temperature, and usually rely on experience or simple mathematical models for rough estimation, resulting in excessive deformation errors during the production process. On the other hand, the existing technologies lack an efficient and automated anomaly detection and handling mechanism. When an anomaly occurs in the production line, the existing monitoring and management mechanism cannot quickly locate the cause and provide an effective solution, and usually requires manual intervention, which is not only time-consuming but also error-prone. Summary of the Invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides an intelligent monitoring and management method for a wire harness production line to solve the problems of insufficient optimization of process parameters and untimely anomaly handling.

[0006] To solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, the present invention provides an intelligent monitoring and management method for a wire harness production line, which includes,

[0008] Extracting data of pressing force and die temperature from historical wire harness production data, encoding them into a real-number encoded gene chain, and generating an initial gene pool in combination with material properties;

[0009] Constructing a digital twin model, obtaining twin prediction values by simulating the stress field distribution and heat conduction effect during the wire harness pressing process through finite element simulation;

[0010] Based on the digital twin model, pre-verifying the process parameters in the initial gene pool, screening process parameter combinations with deformation errors less than the error threshold, and sending them to the press through the production line control center to obtain real-time wire harness deformation data;

[0011] Compare the data of the real-time wire harness deformation amount with the twin prediction values frame by frame to generate a deformation error rate, and generate an abnormal origin tracing report based on the deformation error rate;

[0012] Obtain abnormal parameters based on the abnormal origin tracing report, and perform mutation operations of bit flipping and block swapping. At the same time, combine the workshop environment data to dynamically compensate for the deviation of the abnormal parameters and generate initial optimization parameters;

[0013] Input the initial optimization parameters into the production line control center, monitor and dynamically adjust the crimping force to obtain the final optimization parameters. At the same time, integrate the wire harness production data to generate a monitoring and management report.

[0014] As a preferred solution of the intelligent monitoring and management method for the wire harness production line described in the present invention, wherein: the steps for obtaining the initial gene pool are as follows,

[0015] Use PCA to extract key thermal distribution features from the mold temperature, and combine the process features of the dynamic change rate and overshoot of the crimping force to construct a real-number encoded gene chain;

[0016] Fuse the real-number encoded gene chain with the properties of the yield strength and thermal expansion coefficient of the material, obtain constraint rules based on historical work order data, and combine the environmental dynamic compensation coefficient to generate an initial gene pool using an evolutionary algorithm.

[0017] As a preferred solution of the intelligent monitoring and management method for the wire harness production line described in the present invention, wherein: the process for obtaining the twin prediction values is as follows,

[0018] Perform three-dimensional geometric reconstruction of the crimping mold and wire harness terminals based on industrial CT scanning and reverse engineering method, and calibrate the spatial position and attitude of the mold using a laser tracker;

[0019] According to the spatial position and attitude of the mold, establish a multi-level parametric model integrating material properties, and integrate the real-time control signals of the production line control center as dynamic boundary conditions to construct a digital twin model;

[0020] Based on the digital twin model, use a non-linear finite element solver to perform multi-physical field coupled transient simulation to simulate the stress field distribution during the crimping process;

[0021] According to the simulated stress field distribution, combine the thermal-mechanical coupling algorithm to simulate the heat conduction effect between the mold and the wire harness, and use the adaptive mesh refinement method to dynamically track the plastic deformation characteristics of the high-strain area to generate twin prediction values.

[0022] As a preferred solution of the intelligent monitoring and management method for the wire harness production line described in the present invention, wherein: the process for obtaining the data of the real-time wire harness deformation amount is as follows,

[0023] The digital twin model extracts process parameters from the initial gene pool through industrial communication protocols, maps them to a non-linear finite element solver, and performs simulation verification by combining the Johnson-Cook plasticity model and the thermal-mechanical coupling algorithm;

[0024] After the simulation verification is completed, the DTW algorithm is used to obtain the deformation error, the deformation error is compared with the error threshold, and the process parameter combinations with qualified deformation errors are screened out based on the dynamic programming algorithm;

[0025] The process parameter combinations are transmitted to the production line control center. The production line control center dynamically updates the control parameters of the servo crimping equipment and synchronously triggers the laser displacement gauge to collect data on the real-time wire harness deformation.

[0026] As a preferred solution of the intelligent monitoring and management method for the wire harness production line described in the present invention, wherein: the process of obtaining the anomaly traceability report is as follows,

[0027] Align the time series of the real-time wire harness deformation data and the twin prediction values, calculate the absolute deformation error and the relative deformation error rate frame by frame, and perform weighted fusion to generate the error rate;

[0028] Analyze the error rate based on the random forest classification model to identify the anomaly type, and at the same time generate anomaly handling suggestions through EHM current fluctuation analysis and thermal expansion compensation analysis;

[0029] Integrate the anomaly type and the anomaly handling suggestions to generate an anomaly traceability report.

[0030] As a preferred solution of the intelligent monitoring and management method for the wire harness production line described in the present invention, wherein: the process of obtaining the initial optimization parameters is as follows,

[0031] Analyze the anomaly type in the anomaly traceability report to obtain the anomaly parameters;

[0032] Perform bit flip mutation based on the anomaly parameters, randomly select the flip position in the anomaly parameter sequence, and flip the numerical state with a preset probability;

[0033] After completing the bit flip mutation, perform block exchange mutation. Divide the anomaly parameters into functional blocks according to the process logic, and perform exchange and recombination between the same type of functional blocks on different production lines;

[0034] Input the anomaly parameters after bit flip and block exchange into the dynamic compensation mechanism, and monitor the temperature fluctuation in the workshop in real time. Dynamically adjust the crimping force value according to the temperature fluctuation through thermal expansion compensation to compensate for the deviation of the anomaly parameters and generate the initial optimization parameters.

[0035] As a preferred solution of the intelligent monitoring and management method for the wire harness production line described in the present invention, wherein: the steps of obtaining the final optimization parameters are as follows,

[0036] Input the initial optimization parameters into the production line control center, perform collaborative control based on the reinforcement learning model, dynamically compensate for the deformation deviation of the pressing force, and after SPC monitoring and anti-saturation safety protection, generate the final optimization parameters through wavelet denoising.

[0037] In a second aspect, the present invention provides an intelligent monitoring and management system for a wire harness production line, including a database construction module, a model simulation module, a verification module, an error analysis module, an optimization module, and a monitoring and adjustment module.

[0038] The database construction module is used to extract data on the pressing force and die temperature from historical wire harness production data, encode them into a real number encoded gene chain, and generate an initial gene pool in combination with material properties.

[0039] The model simulation module is used to construct a digital twin model, simulate the stress field distribution and heat conduction effect during the wire harness pressing process through finite element simulation, and obtain the twin prediction value.

[0040] The verification module is used to pre-verify the process parameters in the initial gene pool based on the digital twin model, screen the process parameter combinations with a deformation error less than the error threshold, and send them to the press through the production line control center to obtain data on the real-time wire harness deformation.

[0041] The error analysis module is used to compare the data on the real-time wire harness deformation with the twin prediction value frame by frame, generate a deformation error rate, and generate an abnormal traceability report based on the deformation error rate.

[0042] The optimization module is used to obtain abnormal parameters based on the abnormal traceability report, perform mutation operations of bit flipping and block swapping, and at the same time combine the workshop environment data to dynamically compensate for the deviation of the abnormal parameters and generate the initial optimization parameters.

[0043] The monitoring and adjustment module is used to input the initial optimization parameters into the production line control center, monitor and dynamically adjust the pressing force to obtain the final optimization parameters, and at the same time integrate the wire harness production data to generate a monitoring and management report.

[0044] In a third aspect, the present invention provides a computer device, including a memory and a processor, where the memory stores a computer program, and: when the computer program is executed by the processor, any step of the intelligent monitoring and management method for a wire harness production line as described in the first aspect of the present invention is implemented.

[0045] In a fourth aspect, the present invention provides a computer-readable storage medium, on which a computer program is stored, and: when the computer program is executed by the processor, any step of the intelligent monitoring and management method for a wire harness production line as described in the first aspect of the present invention is implemented.

[0046] The beneficial effects of the present invention are as follows: By constructing an initial gene pool and combining it with a digital twin model for pre-verification, the optimization of key process parameters such as crimping force and die temperature becomes more accurate and effective. It can comprehensively consider various factors in the production process, including material properties and environmental changes, thereby reducing deformation errors and improving the consistency and reliability of products. Secondly, a random forest classification model is used to analyze real-time wire harness deformation data and twin prediction values, automatically generating an abnormal traceability report and providing handling suggestions. This not only speeds up the identification of abnormal situations but also realizes intelligent management, reduces the dependence on manual intervention, and improves the response speed and stability of the production line. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] To more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0048] Figure 1 It is a flowchart of the intelligent monitoring and management method for the wire harness production line in Embodiment 1.

[0049] Figure 2 It is a schematic diagram of the intelligent monitoring and management system for the wire harness production line in Embodiment 1.

[0050] Figure 3 It is a schematic diagram of the process for obtaining the initial optimized parameters in Embodiment 1.

[0051] Figure 4 It is a schematic diagram of the intelligent monitoring and management method for the wire harness production line in Embodiment 1. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0052] To make the above objects, features, and advantages of the present invention more obvious and understandable, the following will provide a detailed description of the specific embodiments of the present invention with reference to the accompanying drawings of the specification.

[0053] Many specific details are set forth in the following description to facilitate a thorough understanding of the present invention. However, the present invention can also be implemented in other ways different from those described herein. Those skilled in the art can make similar extensions without departing from the connotation of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed below.

[0054] Secondly, the so-called "one embodiment" or "embodiment" herein refers to specific features, structures, or characteristics that can be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment that mutually excludes other embodiments.

[0055] Example 1. Refer to Figures 1 to 4 , which is the first embodiment of the present invention. This embodiment provides an intelligent monitoring and management method for a wire harness production line, including the following steps:

[0056] S1. Extract data of the crimping force and the mold temperature from the historical wire harness production data, encode them into a real-number encoded gene chain, and generate an initial gene pool in combination with the material properties.

[0057] Specifically, it includes the following steps.

[0058] Based on the historical wire harness production data, accurately locate through SQL query, and select the time series data containing the crimping force and the mold temperature. And extract key sample points based on the set time interval, such as the pressure value change during each crimping operation and the key node temperatures in the heating and cooling stages of the mold temperature. The data of the pressure value and the mold temperature usually exist in the form of time series, recording the process parameter changes in different production stages.

[0059] Preprocess the extracted data of the crimping force and the mold temperature. First, perform data cleaning, use statistical methods or machine learning algorithms, such as Z-score and isolation forest, to identify and process missing values and outliers. Then normalize the data through min-max scaling or standardization methods to ensure the consistency of scales between different features. Finally, segment the continuous time series data according to the complete production cycle of the wire harness to better capture the factors affecting the production quality of the wire harness.

[0060] Before constructing the real-number encoded gene chain, use PCA to extract key thermal distribution features from the mold temperature data. PCA is a dimensionality reduction technique that can identify several dimensions that have important impacts on wire harness production, thereby reducing the complexity of subsequent calculations. At the same time, considering process characteristics such as the dynamic change rate and overshoot of the crimping force, it is possible to better understand the problems that may occur during the crimping process. According to the key thermal distribution of the mold, the dynamic change rate and overshoot characteristics of the crimping force, construct a real-number encoded gene chain containing multi-dimensional features as the basis for further optimization.

[0061] After completing the construction of the real-number encoded gene chain, determine the yield strength and thermal expansion coefficient of the material. Select material samples and conduct tensile tests using a material testing machine, record the stress-strain curve, and determine the stress value when the material starts to undergo plastic deformation as the yield strength. At the same time, use a thermomechanical analyzer (TMA) to measure the dimensional changes of the material samples under controlled temperature change conditions, and determine the thermal expansion coefficient by calculating the length change rate of the material at different temperatures.

[0062] Combine the real - number - coded gene chain with the yield strength and thermal expansion coefficient of the material. This step ensures that the performance of the selected material meets the requirements of the production process under specific conditions. Then, obtain the constraint rules based on historical work order data. Here, the historical work order data not only includes the specific operation parameters of the production line but also the problems encountered and solutions in previous production. Based on this, formulate reasonable constraint conditions. In addition, considering the changes in the temperature and humidity of the workshop, adjust the real - number - coded gene chain using the environmental dynamic compensation coefficient. The environmental dynamic compensation coefficient is an adjustment factor calculated according to the actual temperature and humidity changes in the workshop. In specific operations, based on the historical temperature, humidity data, and process parameters of the workshop, construct an environment - adaptive dynamic compensation model to describe the impact of temperature and humidity changes on the behavior of the material. Then, use the historical wire harness production data to calibrate the environment - adaptive dynamic compensation model to ensure its accuracy and reliability. Next, apply a neural network to identify the most relevant features and quantify the degree of influence of these features on the process parameters, and output specific compensation coefficient values to correct the process parameters in the real - number - coded gene chain to adapt to different environmental conditions, ensuring that the production process parameters can be dynamically adjusted according to real - time environmental changes, thus guaranteeing the stability of the production process and the consistency of product quality. Finally, use an evolutionary algorithm to simulate the natural selection process. Through iterative selection, crossover, and mutation operations, gradually optimize the real - number - coded gene chain to finally form an initial gene pool;

[0063] Through the above operations, an initial gene pool of wire harness production data is constructed, realizing the deep integration of modern manufacturing technology and information technology, and greatly improving the intelligent level of wire harness production.

[0064] S2. Construct a digital twin model, and through finite - element simulation, simulate the stress - field distribution and heat - conduction effect during the wire harness crimping process to obtain twin prediction values.

[0065] Specifically, it includes the following operations,

[0066] In order to perform three-dimensional geometric reconstruction on the crimping die and wire harness terminals and obtain a three-dimensional model, industrial CT scanning technology is used to acquire the structured data of the high-precision geometric shape, density distribution, and material properties of the crimping die and wire harness terminals, and through reverse engineering, it is converted into a computer-aided design (CAD) model. This process not only requires a high-resolution scanning device but also professional software tools to process the scanned data to ensure that the generated three-dimensional model can truly reflect the geometric features of the crimping die and wire harness terminals. Then, a laser tracker is used to accurately calibrate the spatial position and attitude of the die. This step is crucial for the subsequent construction of the digital twin model because any minor position deviation may lead to inaccurate simulation results. The laser tracker determines the position of the crimping die by emitting a laser beam to the target point and measuring the time difference of the reflected beam. Its accuracy can reach the sub-millimeter level, effectively avoiding the generation of error data;

[0067] After obtaining the three-dimensional models of the crimping die and wire harness terminals, based on the spatial position and attitude of the die, a multi-level parametric model integrating material properties is established. Multi-level means not only considering the physical properties of the die itself, such as stiffness, density, etc., but also considering the interaction between different materials and the response of the entire crimping production equipment under different working conditions. For example, in a wire harness production line, there may be different thermal expansion coefficients between metal wires and plastic sheaths, and these differences need to be fully considered in the digital twin model. In addition, integrating the real-time control signals of the production line control center as dynamic boundary conditions is also one of the key steps in constructing the digital twin model. The real-time control signals are instructions or data continuously sent by the production line control center during the operation of the crimping production equipment, such as parameters like pressure and speed, which are used to dynamically adjust the state of the crimping production equipment and synchronize it to the digital twin model for simulation. Finally, data interaction and real-time update functions are achieved through MATLAB to complete the construction of the digital twin model;

[0068] Based on the digital twin model, a multi-physics field coupled transient simulation is carried out using a non-linear finite element solver (such as ANSYS or Abaqus). The non-linear finite element solver can simultaneously consider the interaction between multiple physical phenomena such as force and heat, thus more accurately simulating the stress field distribution during the crimping process. In specific operations, first, the simulation parameters are set, including material properties, boundary conditions, initial conditions, etc., and then the non-linear finite element solver is run to perform the calculation. Since the crimping process is a highly non-linear process involving various complex mechanisms such as plastic deformation and contact friction, it is particularly important to select an appropriate solution strategy. For example, an implicit integration scheme can be selected to improve stability, or an explicit integration scheme can be used to speed up the calculation;

[0069] After completing the simulation of the stress field distribution, further combine the thermal-mechanical coupling algorithm to simulate the heat conduction effect between the mold and the wire harness. The heat conduction effect can analyze how heat is transferred between different components and how this transfer affects the overall performance of the crimping production equipment. To better capture the behavioral characteristics of local high-temperature or high-strain regions, an adaptive mesh refinement technique is used to dynamically adjust the mesh density. The adaptive mesh refinement method can significantly improve the resolution of local details while maintaining the computational efficiency. For example, it automatically refines the mesh in the high-strain region, enabling the physical phenomena in this region to be described more precisely;

[0070] Integrate the stress field distribution data obtained from the simulation and the heat conduction effect data between the mold and the wire harness. The integrated data not only includes the pressure values and temperature changes at different positions but also reflects the specific patterns of material deformation and heat transfer. At the same time, to ensure accuracy, the root mean square error is used to correct the error of the integrated data, ensuring that the integrated data is as close to the actual situation as possible. Comprehensive analysis is performed on the error-corrected data to extract key performance indicators. The key performance indicators not only include the stress distribution and temperature change trend but may also cover other important information such as the degree of plastic deformation and the change in contact area. By analyzing the key performance indicators, various physical phenomena and their interaction mechanisms during the crimping process can be comprehensively understood. At the same time, all key performance indicators are summarized to form a twin prediction value, which not only provides a scientific basis for subsequent quality control but can also be used to optimize production process parameters, improve product quality and production efficiency. For example, by analyzing the potential problem points shown in the twin prediction value, measures can be taken in advance to avoid defect generation, thereby reducing the scrap rate and shortening the development cycle;

[0071] Through the above operations, not only can the accuracy and efficiency of wire harness production be greatly improved, but also the trial-and-error cost can be effectively reduced, laying a solid foundation for realizing intelligent wire harness manufacturing.

[0072] S3. Based on the digital twin model, pre-verify the process parameters in the initial gene pool, screen the process parameter combinations with deformation errors less than the error threshold, and send them to the crimping machine through the production line control center to obtain real-time wire harness deformation data.

[0073] Specifically, it includes the following steps:

[0074] The digital twin model extracts process parameters from the initial gene pool. The process parameters include key performance indicators such as crimping force and mold temperature. To apply the process parameters to actual simulations, they need to be mapped to a nonlinear finite element solver through an industrial communication protocol (such as PROFINET or Modbus);

[0075] After completing the process parameter mapping, start the nonlinear finite element solver to perform simulation verification. Here, the Johnson-Cook plasticity model combined with the thermal-mechanical coupling algorithm is used for simulation verification. The Johnson-Cook model is a constitutive equation widely used in metal plastic deformation analysis. It considers the influence of factors such as strain rate and temperature on material behavior. In specific operations, it is necessary to first define material properties and boundary conditions in the finite element software, and then set up the simulation environment according to the extracted process parameters. For example, in Abaqus, process parameters can be imported and simulation scenarios can be configured to ensure that each simulation can accurately reflect the status under actual production conditions. The core of simulation verification is to use advanced numerical methods to simulate various physical phenomena that may occur during the wire harness crimping process and evaluate their impact on the final wire harness performance;

[0076] After the simulation verification is completed, the DTW (Dynamic Time Warping) algorithm is used to calculate the deformation error. DTW is a technology used to measure the similarity between two time series. In particular, when the simulation verification result is inconsistent with the time series length of the real-time harness deformation data, DTW can effectively align the two sequences and calculate the similarity between them, thereby quantifying the deformation error. At the same time, the error threshold is defined based on the maximum deformation error value allowed by the production quality standard and process requirements, and the deformation error is compared with the error threshold to screen out the process parameter combination with a deformation error less than the error threshold, that is, the qualified process parameter combination. The screening process usually uses a dynamic programming algorithm to optimize the selection process to ensure that the selected process parameter combination can maximize production efficiency while ensuring quality;

[0077] After obtaining the process parameter combination that meets the requirements, it is transmitted to the production line control center through the industrial communication protocol to ensure the security and real-time performance of data transmission. After receiving the process parameters, the production line control center dynamically updates the control parameters of the servo crimping equipment and adjusts the operating conditions on the actual production line to match the results of the simulation verification. At the same time, the laser displacement meter is triggered to collect real-time data on the deformation of the wire harness. The laser displacement meter is a high-precision sensor that can provide sub-millimeter measurement accuracy, which is essential for capturing subtle deformation changes. For example, multiple laser displacement meters can be installed at the crimping head, die contact, and wire harness entry and exit areas of the crimping machine to monitor the deformation of the wire harness during the crimping process in real time, and feed back the real-time wire harness deformation data to the production line control center.

[0078] Analyze the obtained real-time wire harness deformation data, further verify the accuracy of the digital twin model, and identify possible improvement points. For example, when a large deviation is found between the simulation verification results and the real-time wire harness deformation data under certain specific conditions, the digital twin model parameters can be adjusted for optimization. In addition, machine learning algorithms can be used to deeply mine the historical wire harness deformation data to find potential patterns and rules, providing a reference for future process optimization. For example, a neural network model can be used to train a large amount of historical wire harness deformation data to identify the main factors affecting the deformation error, and the process parameters can be adjusted accordingly;

[0079] Through the above operations, not only can the quality and efficiency of wire harness production be significantly improved, but also a solid foundation can be provided for subsequent quality control and process optimization.

[0080] S4. Compare the real-time wire harness deformation data with the twin prediction values frame by frame to generate a deformation error rate, and generate an abnormal traceability report based on the deformation error rate.

[0081] Specifically, it includes the following steps:

[0082] Due to the existence of interference factors in the actual production environment, the DTW algorithm is used to align the real-time wire harness deformation data with the twin prediction values. After alignment, the absolute deformation error and the relative deformation error rate are calculated frame by frame. The absolute deformation error refers to the difference between the real-time wire harness deformation data and the twin prediction values, while the relative deformation error rate is the ratio of the absolute deformation error to the twin prediction values. In order to more comprehensively evaluate the error situation, a weighted fusion method is used to assign different weights to the importance of different positions, and finally a comprehensive error rate is generated. For example, the errors in key stress concentration areas or temperature-sensitive areas may be assigned higher weights to highlight the impact of these areas on the overall quality. The specific formula is as follows:

[0083]

[0084] Among them, E represents the comprehensive error rate, N represents the total number of wire harness deformation data, i represents the index of the wire harness deformation data, w(i) represents the weight of the i-th wire harness deformation data, α represents the adjustment coefficient of the absolute error and the relative error rate, E1(i) represents the absolute error of the i-th wire harness deformation data, and E2(i) represents the relative error rate of the i-th wire harness deformation data;

[0085] Analyze the comprehensive error rate using a random forest classification model with machine learning algorithms. In specific operations, first define the training dataset, including historical error rates and their corresponding labels, such as normal, slightly abnormal, severely abnormal, etc. Then use the Scikit-learn library in Python to train the random forest model. After training, use the random forest classification model to classify new error rate data and identify whether there are abnormal types in the current production process. The random forest classification model is a powerful ensemble learning method suitable for processing high-dimensional data and has good generalization ability. It makes predictions by constructing multiple decision trees and voting on the classification results, thereby improving the stability and accuracy of the random forest classification model. At the same time, to improve the classification accuracy, feature engineering is also required to extract more features that are helpful for classification. For example, statistical features such as mean and variance, frequency domain features after Fourier transform, and features of current fluctuations and temperature changes can be extracted from historical error rate data, which can help the random forest classification model better understand the data pattern and improve the classification effect;

[0086] In addition to the random forest model, other analysis methods can be combined to further refine the identification of abnormal types. For example, EHM (Electrical Health Monitoring) current fluctuation analysis can help detect whether the operation status of the crimping production equipment is normal by monitoring the change trend of the current to discover potential electrical faults. Thermal expansion compensation analysis is used to evaluate the impact of temperature changes on the behavior of wire harness materials, especially important when working in high-temperature environments. EHM current fluctuation analysis and thermal expansion compensation analysis not only provide more diagnostic information but also provide a basis for subsequent anomaly handling;

[0087] Based on the identified abnormal types and the diagnostic information provided by EHM current fluctuation analysis and thermal expansion compensation analysis, targeted treatment plans can be formulated. For example, when it is found that a certain section of the wire harness has a large deformation error and is accompanied by abnormal current fluctuations, it may indicate that the crimping force setting in this area is inappropriate or the mold is worn. At this time, it is recommended to adjust the crimping force parameters or replace the mold parts. Similarly, for deformation errors caused by temperature changes, thermal expansion compensation measures can be taken, such as optimizing cooling or adjusting the process temperature. To ensure the effectiveness and operability of the suggestions, it is usually necessary to customize the design in combination with the specific conditions and limitations of the production line. In addition, automated tools can be used to help quickly generate and implement these treatment suggestions, improving the response speed and efficiency of the production line control center. For example, Python can be used to automatically generate optimization suggestions and directly send them to the production line control center through industrial communication protocols to achieve automatic adjustment;

[0088] Integrate the relevant information of exception types and handling suggestions to generate a detailed exception traceability report. The report should not only include basic information such as exception types, occurrence locations, and timestamps, but also list in detail the handling suggestions and their expected effects for each exception. To enhance readability and interactivity, the exception traceability report is presented in a structured format of tables and charts. At the same time, create an interactive dashboard using Tableau and Power BI, enabling users to dynamically view the exception traceability report, which helps management quickly locate exceptions, promotes cross-departmental collaboration, and improves overall work efficiency;

[0089] Through the above operations, the exception handling efficiency in the wire harness production process has been significantly improved, cross-departmental collaboration has been promoted, and overall work efficiency and product consistency have been enhanced.

[0090] S5. Obtain the exception parameters based on the exception traceability report, perform mutation operations such as bit flipping and block swapping, and at the same time combine the workshop environment data to dynamically compensate for the deviation of the exception parameters to generate the initial optimized parameters.

[0091] Specifically, it includes the following steps.

[0092] To optimize the exception parameters in the wire harness crimping process, first conduct an in-depth analysis of the generated exception traceability report to identify specific exception types and their related exception parameters. For example, if the exception traceability report indicates that a certain section of the wire harness has a large deformation error at a specific time point, then the corresponding crimping force or die temperature may be the exception parameters that need to be adjusted. By parsing the detailed information in the report, such as the timestamp and location of the exception occurrence, the parameters causing the exception can be accurately located. Once the exception parameters are determined, the next step is to extract them and perform necessary cleaning processing to ensure data consistency and comparability;

[0093] After obtaining the preprocessed exception parameters, perform the bit flip mutation operation. The core of the flip mutation operation is to randomly select one or more positions in the exception parameter sequence and flip the numerical states at these positions with a certain preset probability. For example, for binary-encoded exception parameters, 0 becomes 1 and 1 becomes 0. For real-number encoding, the flip effect can be simulated by adding or subtracting a small perturbation value. In specific operations, Python can be used to utilize a random number generator (such as random) to determine the positions and probabilities of flipping, and verify the new parameters after the bit flip mutation to ensure their rationality. For example, the digital twin model can be called again for simulation verification to evaluate the impact of the new parameters on the production process, and the deformation of the wire harness under the new crimping force setting can be simulated using finite element analysis software (such as Abaqus or ANSYS) to confirm whether the expected effect is achieved;

[0094] On the basis of bit - flip mutation, further perform block - exchange mutation operation. First, define the process logic based on different process flows of the production line. Divide the abnormal parameters into different functional blocks according to the process logic. For example, during the crimping process, functional blocks can be defined according to different regions of the die and different stages of the process. The purpose of doing this is to better simulate the change patterns in actual production and make the mutation operation more in line with the actual situation. After completing the division of functional blocks, perform exchange and recombination between similar functional blocks on different production lines. This step aims to increase the exploration space through more diverse parameter combinations and help discover better solutions. For example, a set of process parameters can be selected from the functional block of one production line and replace the process parameters in the same functional block of another production line. In specific operations, Python can be used to automatically execute the block - exchange operation and record the results of each exchange for subsequent analysis;

[0095] Input the abnormal parameters after bit - flip and block - exchange into the dynamic compensation mechanism. At the same time, through the Industrial Internet of Things (IIoT) technology, connect the temperature sensor to the production line control center, real - time monitor the temperature data in the workshop, and transmit it to the production line control center to obtain the temperature fluctuation data;

[0096] Based on the temperature fluctuation data, use the thermal expansion compensation algorithm to dynamically adjust the crimping force value. The thermal expansion effect will cause changes in the material size, thus affecting the crimping quality. By analyzing the temperature fluctuation, judge the degree of expansion and contraction of the material, and accordingly adjust the crimping force, which can compensate for the deviation of abnormal parameters. For example, define the standard temperature value based on the production process requirements and material characteristics. When the temperature in the workshop is higher than the standard temperature value, reduce the crimping force to offset the excessive deformation of the material. When the temperature is lower than the standard temperature value, increase the crimping force to compensate for the material shrinkage effect;

[0097] Input the parameters processed by the dynamic compensation mechanism into the crimping production equipment for verification. By comparing the wire harness production data before and after input, evaluate the effect of parameter optimization. If the optimization effect meets the production expectations, it is considered that the initial optimization is successful. Otherwise, the operations of bit - flip, block - exchange, and temperature compensation need to be repeated until the best effect is achieved, and the initial optimized parameters are generated;

[0098] Through the above operations, not only significantly improve the quality and efficiency of wire harness production, but also provide a solid foundation for subsequent quality control and process optimization.

[0099] S6. Input the initial optimized parameters into the production line control center, monitor and dynamically adjust the crimping force to obtain the final optimized parameters, and at the same time integrate the wire harness production data to generate a monitoring and management report.

[0100] Specifically, it includes the following steps,

[0101] First, input the initial optimization parameters into the production line control center. In specific operations, the initial optimization parameters can be transmitted to the production line control center through the PROFINET industrial communication protocol. This automated transmission process not only improves work efficiency but also reduces the possibility of human errors;

[0102] Once the initial optimization parameters are input into the production line control center, the next step is to monitor the crimping force in real time and make dynamic adjustments. Continuously collect the crimping force and temperature data provided by the pressure sensor and temperature sensor, and dynamically adjust the crimping force based on the data of the crimping force and temperature. This real-time monitoring and adjustment mechanism ensures that even under changing environmental conditions, a high-quality wire harness crimping effect can be maintained. The dynamic adjustment step usually uses a PID controller to achieve closed-loop control, and the adjustment amount to be made is calculated by the PID controller to maintain the stability and accuracy of wire harness production;

[0103] To further optimize the initial optimization parameters, a reinforcement learning model is used for collaborative control. First, construct a reinforcement learning model, which is usually composed of a state space, an action space, and a reward function. The state space includes current process parameters such as crimping force and temperature, the action space is adjustable control variables such as increasing or decreasing the crimping force, and the reward function defines the goal such as minimizing the deformation error. The specific reinforcement learning algorithm used is Q-learning. The reinforcement learning model construction and training can be implemented using the TensorFlow framework in Python. During the training process, the reinforcement learning model will simulate different scenarios and try various adjustment strategies, gradually learning how to make the best decisions to achieve the goal. The trained reinforcement learning model will be deployed to the production line control center, receiving the crimping force and temperature data from the pressure sensor and temperature sensor in real time as state inputs and outputting corresponding action suggestions such as adjusting the crimping force;

[0104] In specific operations, the reinforcement learning model will predict the best action based on real-time wire harness production data. For example, when it detects an increase in the deformation error, the reinforcement learning model will suggest reducing the crimping force to reduce the deformation error. This dynamic adjustment mechanism improves the stability and efficiency of the production process. In addition, through continuous trial and error and learning, the reinforcement learning model can gradually find the optimal control strategy, making the production process more stable and efficient. For example, if the reinforcement learning model predicts that a certain adjustment may reduce the deformation error, it will suggest the production line control center to make the corresponding adjustment, which not only improves production efficiency but also enhances adaptability and flexibility;

[0105] After compensating for the deformation deviation of the pressing force dynamically through a reinforcement learning model, the statistical process control (SPC) technology is used to monitor the process parameters. SPC tracks the change trend of process parameters through control charts and discovers abnormal fluctuations in a timely manner. For example, relevant libraries in Python can be used to draw control charts to analyze whether the process parameters exceed the control limits. If abnormalities are found, the production line control center will issue an alarm so that timely measures can be taken. By means of real-time monitoring and early warning, potential problems can be discovered in a timely manner and corrective measures can be taken quickly to prevent the problems from further expanding. In addition, the early warning threshold can be set based on the safe operating range and quality standards of production. A warning can be issued in advance when the process parameters are close to the control limits so as to make preparations in advance. At the same time, in order to prevent the process parameters from exceeding their physical and design limits, an anti-saturation safety protection mechanism is set up, which usually involves setting upper and lower limit thresholds based on the quality standards and safe operating range of production equipment and processes. When the process parameters are close to or exceed the upper and lower limit thresholds, the production line will be automatically paused to prevent equipment damage or product quality decline;

[0106] The process parameters after SPC monitoring and anti-saturation safety protection are preprocessed to remove noise interference. Wavelet transform is an effective signal processing technology that can be used for noise reduction without losing important information. In specific operations, wavelet decomposition and reconstruction can be performed in Python. First, a suitable wavelet basis function is selected, and then the process parameters are decomposed layer by layer. The main features of the low-frequency components are extracted and the noise of the high-frequency components is removed. Finally, reconstruction is carried out to improve the accuracy of subsequent analysis. The parameters after wavelet noise reduction processing are regarded as the final optimized parameters, which have higher accuracy and stability and are suitable for the actual production environment. These final optimized parameters can be saved as a JSON configuration file for reference in subsequent batches of production to guide subsequent production activities;

[0107] In the process of obtaining the final optimized parameters, the production line control center will continuously collect various wire harness production data and integrate the data of the final optimized parameters to generate a detailed monitoring and management report, which includes not only the final optimized parameters but also the abnormal information in the production process, such as the type of abnormality, the location where it occurs, the timestamp, etc. In addition, reports in PDF or HTML format can be automatically generated for easy access;

[0108] Through the above operations, a monitoring and management report is generated, providing a comprehensive perspective for wire harness production, helping production and management personnel better understand and optimize the wire harness production process, and ensuring that each link can reach the best state.

[0109] This embodiment also provides an intelligent monitoring and management system for a wire harness production line, including: a database construction module, a model simulation module, a verification module, an error analysis module, an optimization module, a monitoring and adjustment module,

[0110] A database construction module, which is used to extract the data of the crimping force and the die temperature from the historical wire harness production data, encode them into a real-coded gene chain, and generate an initial gene pool in combination with the material properties;

[0111] A model simulation module, which is used to construct a digital twin model, simulate the stress field distribution and heat conduction effect during the wire harness crimping process through finite element simulation, and obtain the twin prediction values;

[0112] A verification module, which is used to pre-verify the process parameters in the initial gene pool based on the digital twin model, screen out the process parameter combinations with the deformation error less than the error threshold, and send them to the crimping machine through the production line control center to obtain the data of the real-time wire harness deformation;

[0113] An error analysis module, which is used to compare the data of the real-time wire harness deformation with the twin prediction values frame by frame, generate a deformation error rate, and generate an abnormal source tracing report based on the deformation error rate;

[0114] An optimization module, which is used to obtain abnormal parameters based on the abnormal source tracing report, perform mutation operations of bit flipping and block swapping, and at the same time combine the workshop environment data to dynamically compensate for the deviation of the abnormal parameters and generate the initial optimized parameters;

[0115] A monitoring and adjustment module, which is used to input the initial optimized parameters into the production line control center, monitor and dynamically adjust the crimping force to obtain the final optimized parameters, and at the same time integrate the wire harness production data to generate a monitoring and management report.

[0116] This embodiment also provides a computer device, which is applicable to the intelligent monitoring and management method of the wire harness production line, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement the intelligent monitoring and management method of the wire harness production line proposed in the above embodiment.

[0117] The computer device may be a terminal, which includes a processor, a memory, a communication interface, a display screen, and an input device connected via a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The communication interface of the computer device is used to communicate with external terminals in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a carrier network, NFC (Near Field Communication), or other technologies. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer covered on the display screen, or a button, a trackball, or a touchpad set on the computer device housing, or an external keyboard, touchpad, or mouse, etc.

[0118] This embodiment also provides a storage medium, on which a computer program is stored. When the program is executed by a processor, it implements the intelligent monitoring and management method for the wire harness production line as proposed in the above embodiment; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM for short), Electrically Erasable Programmable Read-Only Memory (EEPROM for short), Erasable Programmable Read Only Memory (EPROM for short), Programmable Red-Only Memory (PROM for short), Read-Only Memory (ROM for short), magnetic memory, flash memory, a magnetic disk, or an optical disc.

[0119] In summary, the present invention: By constructing an initial gene pool and combining it with a digital twin model for pre-verification, this makes the optimization of key process parameters such as the pressing force and die temperature more accurate and effective, and can consider various factors in the production process more comprehensively, including material properties and environmental changes, thereby reducing deformation errors and improving the consistency and reliability of products. Secondly, a random forest classification model is used to analyze the real-time wire harness deformation data and the twin prediction values, automatically generate an abnormal traceability report and provide processing suggestions, which not only speeds up the identification speed of abnormal situations, but also realizes intelligent management, reduces the dependence on manual intervention, and improves the response speed and stability of the production line.

[0120] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered within the scope of the claims of the present invention.

Claims

1. An intelligent monitoring and management method for a wire harness production line, characterized in that: Including, extracting the crimping force and die temperature data from the historical wire harness production data, encoding them into a real-number-encoded gene chain, and generating an initial gene pool by combining material properties; constructing a digital twin model, simulating the stress field distribution and heat conduction effect during the wire harness crimping process through finite element simulation, and obtaining the twin prediction value; based on the digital twin model, pre-verifying the process parameters in the initial gene pool, screening the process parameter combinations with deformation errors less than the error threshold, and sending them to the crimping machine through the production line control center to obtain the data of the real-time wire harness deformation; comparing the data of the real-time wire harness deformation with the twin prediction value frame by frame to generate a deformation error rate, and generating an abnormal traceability report based on the deformation error rate; obtaining abnormal parameters based on the abnormal traceability report, performing mutation operations of bit flipping and block swapping, and dynamically compensating the deviation of the abnormal parameters by combining the workshop environment data to generate the initial optimized parameters; inputting the initial optimized parameters into the production line control center, monitoring and dynamically adjusting the crimping force to obtain the final optimized parameters, and integrating the wire harness production data to generate a monitoring and management report.

2. The intelligent monitoring and management method of the wire harness production line according to claim 1, wherein: The steps for obtaining the initial gene pool are as follows: extracting key heat distribution features from the die temperature by using PCA, combining the process features of the dynamic change rate and overshoot of the crimping force, and constructing a real-number-encoded gene chain; fusing the real-number-encoded gene chain with the properties of the yield strength and thermal expansion coefficient of the material, obtaining the constraint rules based on the historical work order data, and generating the initial gene pool by using an evolutionary algorithm in combination with the environmental dynamic compensation coefficient.

3. The intelligent monitoring and management method of the wire harness production line according to claim 1, wherein: The process for obtaining the twin prediction value is as follows: performing three-dimensional geometric reconstruction on the crimping die and wire harness terminals based on industrial CT scanning and reverse engineering method, and calibrating the spatial position and attitude of the die by using a laser tracker; establishing a multi-level parametric model integrating material properties according to the spatial position and attitude of the die, and integrating the real-time control signals of the production line control center as dynamic boundary conditions to construct a digital twin model; based on the digital twin model, using a non-linear finite element solver to perform multi-physical field coupled transient simulation to simulate the stress field distribution during the crimping process; according to the simulated stress field distribution, simulating the heat conduction effect between the die and the wire harness by combining the thermal-mechanical coupling algorithm, and using the adaptive mesh refinement method to dynamically track the plastic deformation characteristics in the high-strain area to generate the twin prediction value.

4. The intelligent monitoring and management method for the wire harness production line according to claim 3, wherein: The process for obtaining the data of the real-time wire harness deformation is as follows: the digital twin model extracts the process parameters in the initial gene pool through an industrial communication protocol, maps them to the non-linear finite element solver, and performs simulation verification by combining the Johnson-Cook plasticity model and the thermal-mechanical coupling algorithm; after the simulation verification is completed, using the DTW algorithm to obtain the deformation error, comparing the deformation error with the error threshold, and screening out the process parameter combinations with qualified deformation errors based on the dynamic programming algorithm; transmitting the process parameter combination to the production line control center, and the production line control center dynamically updates the control parameters of the servo crimping equipment and synchronously triggers the laser displacement meter to collect the data of the real-time wire harness deformation.

5. The intelligent monitoring and management method for the wire harness production line according to claim 1, characterized in that: The process for obtaining the abnormal traceability report is as follows: Align the time series of real-time wire harness deformation data and twin prediction values, calculate the absolute deformation error and relative deformation error rate frame by frame, and perform weighted fusion to generate the error rate; Analyze the error rate based on the random forest classification model to identify the abnormal type, and at the same time generate abnormal handling suggestions through EHM current fluctuation analysis and thermal expansion compensation analysis; Integrate the abnormal type and abnormal handling suggestions to generate an abnormal traceability report.

6. The intelligent monitoring and management method for the wire harness production line according to claim 5, characterized in that: The process of obtaining the initial optimization parameters is as follows, Analyze the abnormal types in the abnormal traceability report to obtain abnormal parameters; Perform bit flip mutation based on the abnormal parameters, randomly select the flip positions in the abnormal parameter sequence, and flip the numerical state with a preset probability; After completing the bit flip mutation, perform block exchange mutation, divide the abnormal parameters into functional blocks according to the process logic, and perform exchange and recombination between the same type of functional blocks on different production lines; Input the abnormal parameters after bit flip and block exchange into the dynamic compensation mechanism, and monitor the temperature fluctuation in the workshop in real time. Dynamically adjust the crimping force value according to the temperature fluctuation through thermal expansion compensation to compensate for the deviation of the abnormal parameters and generate the initial optimization parameters.

7. The intelligent monitoring and management method for the wire harness production line according to claim 1, wherein: The steps of obtaining the final optimization parameters are as follows, Input the initial optimization parameters into the production line control center, perform collaborative control based on the reinforcement learning model, dynamically compensate the deformation deviation of the crimping force, and after SPC monitoring and anti-saturation safety protection, generate the final optimization parameters through wavelet denoising.

8. An intelligent monitoring and management system for a wire harness production line, based on the intelligent monitoring and management method of the wire harness production line according to any one of claims 1 to 7, characterized in that: Including a database construction module, a model simulation module, a verification module, an error analysis module, an optimization module, and a monitoring and adjustment module, The database construction module is used to extract the data of the crimping force and the die temperature from the historical wire harness production data, encode them into a real-number encoded gene chain, and generate an initial gene pool in combination with the material properties; The model simulation module is used to build a digital twin model, simulate the stress field distribution and heat conduction effect during the wire harness crimping process through finite element simulation, and obtain the twin prediction values; The verification module is used to pre-verify the process parameters in the initial gene pool based on the digital twin model, screen the process parameter combinations with deformation errors less than the error threshold, and send them to the crimping machine through the production line control center to obtain the data of the real-time wire harness deformation amount; The error analysis module is used to compare the data of the real-time wire harness deformation amount with the twin prediction values frame by frame to generate a deformation error rate, and generate an abnormal traceability report based on the deformation error rate; The optimization module is used to obtain abnormal parameters based on the abnormal traceability report, perform mutation operations of bit flip and block exchange, and at the same time combine the workshop environment data to dynamically compensate the deviation of the abnormal parameters and generate the initial optimization parameters; The monitoring and adjustment module is used to input the initial optimization parameters into the production line control center, monitor and dynamically adjust the crimping force to obtain the final optimization parameters, and at the same time integrate the wire harness production data to generate a monitoring and management report.

9. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that: When the processor executes the computer program, it implements the steps of the intelligent monitoring and management method for the wire harness production line according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, it implements the steps of the intelligent monitoring and management method for the wire harness production line according to any one of claims 1 to 7.

Images