Intelligent wire harness end part heat-shrinkable sleeve processing method and system

Abstract

The invention provides an intelligent wire harness end heat-shrinkable tubing processing method and system, and the method comprises the steps: S4, obtaining the infrared thermal imaging data of a wire harness end in a heat shrinkage process, analyzing the surface temperature distribution of a heat-shrinkable tubing through an image processing technology, and determining whether a local overheating or non-uniform shrinkage phenomenon exists or not; s6, according to the optimized heating scheme, a multi-point sensor is adopted to collect temperature data of a wire in the end portion of the wire harness, whether the wire is damaged due to overheating or not is judged, and a real-time temperature early warning signal is generated; s7, driving a self-adaptive adjusting system through a real-time temperature early warning signal, performing fine adjustment on the heat source power and the heating duration in combination with a dynamic adaptation algorithm, and determining final process parameters of uniform shrinkage of the heat-shrinkable sleeve; and S8, acquiring thermal shrinkage effect data after the final process parameters are executed, detecting the shape change trend of the end part of the wire harness through a three-dimensional scanning technology, and judging whether the process consistency reaches a preset standard or not. The wire harness machining quality and efficiency are effectively improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent processing technology, and particularly to an intelligent processing method and system for heat shrinkable sleeves at the end of wire harnesses. Background Art

[0002] As an indispensable key component in modern electronic devices, shielded wire harnesses are widely used in fields such as aerospace, automotive manufacturing, and communication. The quality of their production processes directly determines the performance stability and service life of products. High-quality shielded wire harnesses not only need to meet electromagnetic shielding requirements but also must ensure the reliability and consistency of end processing, which poses extremely high requirements for process technology.

[0003] Currently, with the improvement of device integration and the complexity of usage environments, the production process of shielded wire harnesses has become one of the core lifelines of the industry's development.

[0004] However, existing methods still have significant limitations in the end heat shrinkage treatment process. Traditional processes mostly adopt a single temperature control mode, which is difficult to adapt to the different requirements of different regions at the end of the wire harness, resulting in uneven shrinkage of the heat shrinkable sleeve or damage to the internal wires due to overheating. These defects are particularly prominent in high-reliability scenarios and directly affect the overall quality of the wire harness. Although the industry has tried to improve the production process through manual adjustment or simple temperature control devices, the effect is limited.

[0005] Existing solutions generally lack the ability to accurately control temperature distribution. Especially when facing complex wire harness structures and diverse material properties, it is difficult to achieve dynamic adaptation. In addition, the lack of visual monitoring and real-time feedback mechanisms during the heat shrinkage process further exacerbates the problem of difficult-to-guarantee process consistency. The core challenges are how to achieve differential temperature control for end heat shrinkage treatment and how to ensure uniform shrinkage of the heat shrinkable sleeve while avoiding overheating damage. These two technical factors directly determine the success or failure of the production process. Due to insufficient temperature control accuracy, it is difficult to effectively manage the regional temperature difference at the end of the wire harness; and the lack of real-time monitoring means increases the uncertainty of the heat shrinkage process, thus triggering consistency and reliability problems.

[0006] Therefore, how to develop a system that can accurately control the temperature of different regions at the end according to the structural characteristics and material properties of the wire harness has become a key problem to be solved urgently. This problem not only requires the process equipment to have an adaptive adjustment ability but also needs to introduce intelligent monitoring technology in the dynamic process to meet the technical requirements under complex working conditions. Only by breaking through these bottlenecks can the production process of shielded wire harnesses be promoted to a higher level. Summary of the Invention

[0007] In the first aspect of the present invention, there is provided an intelligent processing method for heat shrinkable sleeves at the end of wire harnesses, the method comprising: S1. Obtain the structure data of the wire harness end and the material property parameters. Collect the geometric shape information of the wire harness end and the thermal conductivity data of the heat shrinkable sleeve material through a scanning device, and determine the heat shrinkage demand distribution in different regions of the end; S2. According to the heat shrinkage demand distribution in different regions of the end, use a zoning modeling algorithm to generate a temperature control model. Divide the wire harness end into multiple independent temperature control regions, and obtain the target temperature curve for each region; S3. Through the preset temperature control model, obtain the real-time temperature output data from the heat source device. Dynamically adjust the heat source power for each temperature control region, and determine whether the temperature meets the requirements of the target temperature curve; S4. Obtain the infrared thermal imaging data of the wire harness end during the heat shrinkage process. Use image processing technology to analyze the surface temperature distribution of the heat shrinkable sleeve, and determine whether there are phenomena of local overheating or uneven shrinkage; S5. If the surface temperature distribution of the heat shrinkable sleeve exceeds the preset temperature distribution threshold, adjust the heat source power of the corresponding region through a feedback control algorithm, recalculate the temperature output in combination with the material property parameters, and obtain an optimized heating plan; S6. According to the optimized heating plan, use multi-point sensors to collect the temperature data of the internal wires at the wire harness end, determine whether the wires are at risk of damage due to overheating, and generate a real-time temperature warning signal; S7. Drive the adaptive adjustment system through the real-time temperature warning signal, and fine-tune the heat source power and heating duration in combination with the dynamic adaptation algorithm to determine the final process parameters for uniform shrinkage of the heat shrinkable sleeve; S8. Obtain the heat shrinkage effect data after the execution of the final process parameters. Detect the shape change trend of the wire harness end through three-dimensional scanning technology, and determine whether the process consistency meets the preset standard; S9. According to the analysis result of the shape change trend, use data fusion technology to iteratively optimize the temperature control model and the heat shrinkage effect data, and generate an intelligent monitoring database applicable to complex wire harness structures.

[0008] Optionally, in step S1, obtaining the structure data of the wire harness end and the material property parameters, collecting the geometric shape information of the wire harness end and the thermal conductivity data of the heat shrinkable sleeve material through a scanning device, and determining the heat shrinkage demand distribution in different regions of the end includes: Step S11. Collect the geometric shape data and structure information of the wire harness end through a scanning device to obtain the three-dimensional model data of the end region; Step S12. For the three-dimensional model data, use a finite element analysis tool to extract the thermal conductivity data of the heat shrinkable sleeve and determine the material property distribution; Step S13. Extract the heat conduction parameters from the material property distribution and judge the heat shrinkage demand difference in the end region; Step S14. If the shrinkage demand difference exceeds the difference threshold, partition the geometric shape data to obtain a regional distribution result. Step S15. According to the regional distribution result, use the bilinear interpolation algorithm to calculate the continuous change trend of the shrinkage demand and determine the optimized distribution parameters. Step S16. Through the optimized distribution parameters, obtain the shrinkage coverage plan for the end structure to get the final shrinkage demand distribution. Step S17. For the final shrinkage demand distribution, judge the shrinkage sleeve thickness requirements for each region and determine the adjustment plan for the end structure.

[0009] Optionally, in Step S14, if the shrinkage demand difference exceeds the difference threshold, partition the geometric shape data to obtain a regional distribution result, including: Step S141. By comparing the shrinkage demand with the demand threshold, judge the situation of exceeding the difference to obtain the trigger condition judgment result. Step S142. If the difference exceeds the difference threshold, extract the shape data from the geometric shape to obtain the set of data to be processed. Step S143. Use the grid division method to divide the shape data set into regions to obtain the preliminary regional distribution data. Step S144. According to the preliminary regional distribution data, use the bilinear interpolation algorithm to calculate the continuous change of demand judgment to obtain the optimized distribution parameters. Step S145. Extract the regional distribution characteristics from the optimized distribution parameters to obtain the final distribution result data. Step S146. For the final distribution result data, judge the regional characteristics of the shrinkage demand and determine the adjustment plan parameters. Step S147. Through the adjustment plan parameters, update the distribution of the shape data to obtain the processed data result.

[0010] Optionally, in Step S16, through the optimized distribution parameters, obtain the shrinkage coverage plan for the end structure to get the final shrinkage demand distribution, specifically including: Step S161. Through the preset initial thickness of the shrinkage material and the shrinkage rate optimization parameters, obtain the thickness distribution data of the end structure as the preliminary coverage data. Step S162. Use the NumPy library to generate a rectangular grid with a spacing of 1 mm, and extract the shrinkage coverage thickness of each grid unit from the preliminary coverage data to obtain the shrinkage coverage range division result. Step S163. Calculate the root mean square error between the range division result and the required thickness distribution, and determine the shrinkage rate corresponding to the minimum error as the matching parameter. Step S164. Generate a thickness increment and decrement matrix according to the matching parameter to obtain the adjusted plan data. Step S165: Use the interp2d function of SciPy to perform bilinear interpolation on the adjusted scheme data, calculate the thickness change gradient between grid nodes, and obtain a continuous thickness field as the feature distribution result; Step S166: For the feature distribution result, extract the regions where the thickness gradient is greater than the thickness gradient threshold, mark them as the shrinkage demand distribution regions of the end structure, and output as the final covering scheme.

[0011] Optionally, in step S17, for the final shrinkage demand distribution, judge the shrinkage sleeve thickness requirements of each region, and determine the adjustment scheme for the end structure, including: Step S171: Through the shrinkage demand distribution data, use Gaussian filtering to remove noise and then obtain the thickness characteristics of each region to generate thickness distribution data; Step S172: Use the percentile statistical method for the thickness distribution data to obtain the thickness range division result; Step S173: Compare the thickness range division result with the preset thickness standard interval, and calculate the proportion of the overlapping area as the matching degree parameter; Step S174: When the matching degree parameter is lower than the matching degree threshold, determine it as the region that needs to be adjusted; Step S175: According to the region coordinates where the matching degree parameter is lower than the matching degree threshold, determine the position coordinates where the end structure needs to be thickened or thinned, and generate a preliminary adjustment scheme including position marks; Step S176: Adopt the bilinear interpolation algorithm, with the adjustment position as the center point, calculate the thickness adjustment amount of the surrounding regions according to the distance weight, and output the thickness adjustment trend distribution map; Step S177: In the trend distribution map, mark the regions where the adjustment amount exceeds the preset thickness as the key adjustment areas, and the rest as the auxiliary adjustment areas; Step S178: Combine all the marked region coordinates and adjustment amount data to generate a final adjustment scheme including specific dimension parameters; Step S179: According to the coordinate-thickness mapping table in the final adjustment scheme, output the end structure processing drawing data.

[0012] Optionally, in step S5, if the surface temperature distribution of the shrinkage sleeve exceeds the preset temperature distribution threshold, adjust the heat source power of the corresponding region through the feedback control algorithm, recompute the temperature output in combination with the material characteristic parameters, and obtain the optimized heating scheme, including: Step S51: If the surface maximum temperature exceeds the second temperature threshold, obtain the real-time temperature matrix data through an infrared sensor; Step S52: Calculate the heat source power adjustment value using the proportional-integral algorithm based on the difference between the maximum value in the temperature matrix and the second temperature threshold. The algorithm parameters are obtained from the material thermal conductivity library to obtain the power adjustment scheme; Step S53: After executing the power adjustment scheme, collect the updated temperature matrix from the thermocouple array; Step S54: Extract the maximum value in the temperature matrix. If it still exceeds the second temperature threshold, perform secondary adjustment using the incremental PID algorithm. The PID parameters are set according to the material specific heat capacity library, and output the fine-tuned power value; Step S55: Drive the heating tube to work according to the fine-tuned power value, and trigger the temperature acquisition instruction after the work is completed; Step S56: Obtain the temperature matrix in the stable state from the infrared sensor, and calculate the mean square error between the temperature of each region and the target value; Step S57: If the mean square error is greater than the allowable error, analyze the trend of historical temperature data using the moving average method, and correct the power distribution ratio according to the trend slope; Step S58: Control the operation of the heating tube array according to the corrected power ratio, and continuously collect temperature matrix data during the operation; Step S59: Extract the highest temperature, the lowest temperature and the gradient change rate in the matrix as long-term optimization parameters and write them into the control log.

[0013] Optionally, in step S51, if the surface maximum temperature exceeds the second temperature threshold, obtain the real-time temperature matrix data through the infrared sensor, specifically including: Step S511: If the surface temperature exceeds the second temperature threshold, collect the real-time temperature matrix data through the infrared sensor to obtain the temperature matrix; Step S512: Generate a temperature distribution map according to the temperature value of each pixel point in the temperature matrix; Step S513: Extract the boundary region data with a width of 5 pixels in the outermost layer from the temperature matrix to obtain the boundary temperature set; Step S514: Use the Sobel operator to calculate the gradient values of each point of the horizontal gradient and the vertical gradient of the boundary temperature set to generate a gradient distribution; Step S515: If there are data points in the gradient distribution that exceed a preset multiple of the standard deviation of the gradient mean, they are determined as outliers; Step S516: Perform convolution operation on the temperature matrix with outliers to obtain a smoothed temperature matrix; Step S517: Calculate the standard deviation of the temperature in each partition of the smoothed temperature matrix as the fluctuation characteristic of the region; Step S518: Input the fluctuation characteristics of each partition into the PID controller, and adjust the partition control parameters of the corresponding heating tube according to the size of the standard deviation; Step S519, after parameter adjustment, drive the heating tube to operate and obtain the updated temperature matrix from the infrared sensor; Step S5110, when the standard deviation of the temperature matrix is less than the standard temperature value for several consecutive times, it is determined as a stable distribution.

[0014] Optionally, in step S8, obtain the heat shrinkage effect data after executing the final process parameters, detect the change trend of the shape of the wire harness end through three-dimensional scanning technology, and determine whether the process consistency meets the preset standard, including: Step S81, obtain the heat shrinkage effect data after executing the process parameters from the device through the sensor and store it as the initial data set; Step S82, use three-dimensional scanning technology to scan the end of the wire harness in the initial data set to obtain the shape feature point cloud data; Step S83, extract the contour information of the wire harness end from the shape feature point cloud data to determine the distribution characteristics of the shape change; Step S84, calculate the time series of the shape change according to the distribution characteristics to obtain the quantitative index of the change trend; Step S85, if the difference between the quantitative index of the change trend and the preset standard is less than the quantitative threshold, it is determined that the process consistency meets the requirements and the consistency label is output; Step S86, train the consistency label and the initial data set through the random forest algorithm to obtain the mapping model between the process parameters and the heat shrinkage effect; Step S87, predict the heat shrinkage effect of the new process parameters for the mapping model and determine whether it meets the preset standard.

[0015] Optionally, in step S9, according to the shape change trend analysis result, use the data fusion technology to iteratively optimize the temperature control model and the heat shrinkage effect data to generate an intelligent monitoring database applicable to complex wire harness structures, including: Step S91, obtain the trend analysis result through the shape change data and use time series analysis to determine the change pattern; Step S92, extract the features from the trend analysis result and use the weighted average method to integrate the temperature control parameters and the heat shrinkage effect data; Step S93, apply the gradient descent method to adjust the temperature control model for the fused data to obtain the optimized parameter set; Step S94, if the optimized parameter set meets the optimization threshold, generate a model applicable to complex wire harness structures and judge its applicability; Step S95, according to the structural characteristics of the complex wire harness, obtain the initial framework of the monitoring database and fill the content through interpolation; Step S96, use the random forest algorithm to perform intelligent classification on the monitoring database to determine the key monitoring points; Step S97: Adjust the iterative process of the gradient descent method through the data feedback of key monitoring points to obtain the final intelligent monitoring database.

[0016] In the second aspect of the present invention, an intelligent processing system for heat shrinkable sleeves at the end of a wire harness is provided. The intelligent processing of the heat shrinkable sleeves at the end of the wire harness is carried out by using the method described above. The system includes: A data acquisition module, which is used to obtain the wire harness end structure data and material characteristic parameters, collect the wire harness end geometry information and the heat conductivity data of the heat shrinkable sleeve material through a scanning device, and determine the heat shrinkage demand distribution in different regions of the end; A partitioned modeling module, which is used to generate a temperature control model by using a partitioned modeling algorithm according to the heat shrinkage demand distribution in different regions of the end, divide the wire harness end into multiple independent temperature control regions, and obtain the target temperature curve for each region; A temperature control module, which is used to obtain real-time temperature output data from a heat source device through a preset temperature control model, dynamically adjust the heat source power for each temperature control region, and determine whether the temperature meets the requirements of the target temperature curve; A thermal imaging analysis module, which is used to obtain the infrared thermal imaging data of the wire harness end during the heat shrinkage process, analyze the surface temperature distribution of the heat shrinkable sleeve by using image processing technology, and determine whether there are phenomena of local overheating or uneven shrinkage; A feedback adjustment module, which is used to, if the surface temperature distribution of the heat shrinkable sleeve exceeds the preset temperature distribution threshold, adjust the heat source power of the corresponding region through a feedback control algorithm, recalculate the temperature output in combination with the material characteristic parameters, and obtain an optimized heating scheme; A damage monitoring module, which is used to collect the temperature data of the internal wires at the end of the wire harness by using multiple-point sensors according to the optimized heating scheme, judge whether the wires have a risk of damage due to overheating, and generate a real-time temperature warning signal; A parameter optimization module, which is used to drive an adaptive adjustment system through the real-time temperature warning signal, and fine-tune the heat source power and heating duration in combination with a dynamic adaptation algorithm to determine the final process parameters for uniform shrinkage of the heat shrinkable sleeve; An effect detection module, which is used to obtain the heat shrinkage effect data after the execution of the final process parameters, detect the shape change trend of the wire harness end through three-dimensional scanning technology, and judge whether the process consistency meets the preset standard; A database generation module, which is used to iteratively optimize the temperature control model and the heat shrinkage effect data by using data fusion technology according to the shape change trend analysis result, and generate an intelligent monitoring database applicable to complex wire harness structures.

[0017] The present invention provides an intelligent processing method and system for heat shrinkable sleeves at the end of a wire harness. By using a scanning device to collect the structural data and material property parameters of the wire harness end, a temperature control model is generated in combination with a zoning modeling algorithm. The wire harness end is divided into multiple independent temperature control zones. During the heat shrinkage process, infrared thermal imaging data is obtained in real time, the surface temperature distribution of the heat shrinkable sleeve is analyzed, and the heat source power and heating duration are dynamically adjusted according to the internal wire temperature data collected by multi-point sensors.

[0018] Through an adaptive adjustment system and a dynamic adaptation algorithm, the present invention can ensure uniform shrinkage of the heat shrinkable sleeve and avoid overheating damage to the wires at the same time.

[0019] The present invention uses three-dimensional scanning technology to detect the shape change trend of the wire harness end, and optimizes the temperature control model through data fusion technology to generate an intelligent monitoring database applicable to complex wire harness structures, realizing precise control and intelligent supervision of the processing process of heat shrinkable sleeves at the wire harness end, and improving the quality and efficiency of wire harness processing. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 is a flowchart of an intelligent processing method for heat shrinkable sleeves at the end of a wire harness according to the present invention.

[0021] Figure 2 is a schematic structural diagram of an intelligent processing system for heat shrinkable sleeves at the end of a wire harness according to the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0022] The following will clearly and detailedly describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. The described embodiments are only a part of the embodiments of the present invention.

[0023] As Figure 1 , in the first aspect of the present invention, an intelligent processing method for heat shrinkable sleeves at the end of a wire harness is provided, which specifically includes: S1. Obtain the structural data and material property parameters of the wire harness end. Collect the geometric shape information of the wire harness end and the thermal conductivity data of the heat shrinkable sleeve material through a scanning device, and determine the heat shrinkage demand distribution of different regions at the end.

[0024] Optionally, this step further includes: Step S11. Collect the geometric shape data and structural information of the wire harness end through a scanning device to obtain the three-dimensional model data of the end region.

[0025] Step S12. For the three-dimensional model data, use a finite element analysis tool to extract the thermal conductivity data of the heat shrinkable sleeve and determine the material property distribution.

[0026] Step S13. Extract the heat conduction parameters from the material property distribution and judge the heat shrinkage demand differences in the end region.

[0027] Step S14, if the shrinkage demand difference exceeds the difference threshold, partition the geometric shape data to obtain a regional distribution result.

[0028] Step S15, according to the regional distribution result, use the bilinear interpolation algorithm to calculate the continuous change trend of the shrinkage demand and determine the optimized distribution parameters.

[0029] Optionally, use the following formula to calculate the shrinkage demand value:

[0030] where represents the interpolated shrinkage demand value, represents the shrinkage demand value of the known point, and represent the coordinates of the known point, and x and y represent the coordinates of the point to be determined.

[0031] Step S16, through the optimized distribution parameters, obtain the shrinkage coverage plan for the end structure to get the final shrinkage demand distribution.

[0032] Step S17, for the final shrinkage demand distribution, judge the shrinkage sleeve thickness requirements for each region and determine the adjustment plan for the end structure.

[0033] Specifically, collect the geometric shape data and structural information of the wire harness end through a scanning device to obtain the three-dimensional model data of the end region. This process aims to accurately capture the physical characteristics of the wire harness end.

[0034] Exemplarily, a high-precision laser scanner can be used to scan the end of an automotive wire harness to obtain a three-dimensional contour data with a length of 50 mm and a width of 20 mm, forming a three-dimensional point cloud model. This method can intuitively reflect the irregular shape of the end and lay a foundation for subsequent analysis. For the three-dimensional model data, use a finite element analysis tool to extract the thermal conductivity data of the shrinkage sleeve and determine the material property distribution. This link focuses on the quantification of material properties.

[0035] In a possible implementation, assume that the shrinkage sleeve material covering the wire harness end is polyolefin. The heat conduction process can be simulated through finite element software to obtain a distribution map of the thermal conductivity of about 0.2 W / m·K. This distribution map can reveal the change in heat conduction ability caused by material thickness and geometric differences in different regions of the end, which is helpful for precise design.

[0036] Extract the heat conduction parameters from the material property distribution and judge the shrinkage demand difference in the end region. This process is a preliminary assessment of the shrinkage demand.

[0037] Specifically, the analysis shows that the thermal conductivity near the connector area is relatively low, and stronger heat shrink protection may be required. In contrast, the thermal conductivity of the part far from the connector is relatively high, and the demand is relatively weak.

[0038] If the difference in heat shrinkage demand is such that the heat flux in the connector area is 30% higher than that in other areas, it can be determined that the demand difference is significant.

[0039] If the difference in heat shrinkage demand exceeds the preset difference threshold, the geometric shape data is partitioned to obtain the regional distribution result. This step reflects the refined management of complex structures.

[0040] For example, if the difference threshold is set at 20%, and when the difference in heat shrinkage demand between the connector area and the core area is detected to reach 35%, the end part can be divided into a high-demand area and a low-demand area. This kind of partitioning can effectively optimize the subsequent processing efficiency.

[0041] According to the regional distribution result, the bilinear interpolation algorithm is used to calculate the continuous change trend of heat shrinkage demand and determine the optimized distribution parameters. This method ensures the smoothness of the demand distribution.

[0042] In one embodiment, assuming that the heat shrinkage demand value of point A is 5 and that of point B is 3, the demand value of the intermediate point C is approximately 4 through interpolation calculation, forming a continuous heat shrinkage demand curve. This smooth transition can avoid stress concentration caused by mutations and improve the heat shrinkage effect.

[0043] Based on the optimized distribution parameters, the heat shrinkage coverage plan for the end structure is obtained, and the final heat shrinkage demand distribution is achieved. This process is the key to translating theory into practice.

[0044] Preferably, according to the interpolation result, a higher heat shrinkage coverage density is assigned to the connector area, such as adding a 2-mm-thick sleeve per square centimeter, while other areas maintain a 1-mm thickness. This solution can significantly improve the heat resistance and stability of the end part.

[0045] For the final heat shrinkage demand distribution, the heat shrinkage sleeve thickness requirements for each area are judged, and the adjustment plan for the end structure is determined. This step is to improve the overall design.

[0046] It can be understood that if the required thickness in the connector area is 2 mm while only 1 mm is needed in the core area, the adjustment plan may include adding an additional reinforcement sleeve layer at the connector. This differential design can reduce material waste while ensuring the protection effect.

[0047] It should be noted that the application of bilinear interpolation not only improves the accuracy of heat shrinkage demand but also reduces the risk of local overheating during the heat shrinkage process through continuity optimization.

[0048] In one embodiment, the adjusted end of the wire harness exhibits a more uniform temperature distribution during the high-temperature test, and the failure rate is reduced by approximately 15%. This technical effect indicates that the refined zoning and interpolation methods have obvious advantages in improving product quality.

[0049] For example, in actual production, the end of a wire harness with a length of 60 millimeters may require additional processing due to the high heat shrinkage requirements in the connector area. Through the above process, an adaptation solution can be quickly generated. This complete logical chain from data acquisition to parameter optimization ensures the efficiency and reliability of the solution, and at the same time provides technical support for large-scale production.

[0050] Optionally, in step S14, if the difference in heat shrinkage requirements exceeds the difference threshold, the geometric shape data is partitioned to obtain a regional distribution result, and it further includes: Step S141, by comparing the heat shrinkage requirement with the requirement threshold, determine the situation where the difference exceeds, and obtain a trigger condition determination result.

[0051] Step S142, if the difference exceeds the difference threshold, extract the shape data from the geometric shape to obtain a set of data to be processed.

[0052] Step S143, use the grid division method to divide the shape data set into regions to obtain preliminary regional distribution data.

[0053] Step S144, according to the preliminary regional distribution data, use the bilinear interpolation algorithm to calculate the continuous change of demand judgment to obtain optimized distribution parameters.

[0054] Step S145, extract the regional distribution characteristics from the optimized distribution parameters to obtain the final distribution result data.

[0055] Step S146, for the final distribution result data, judge the regional characteristics of the heat shrinkage requirement to determine the adjustment scheme parameters.

[0056] Step S147, through the adjustment scheme parameters, update the distribution of the shape data to obtain the processed data result.

[0057] Specifically, by comparing the heat shrinkage requirement with the preset requirement threshold to determine whether the difference exceeds, the core of this process lies in establishing a clear trigger condition.

[0058] For example, in the processing of the end of the wire harness, assume that the preset requirement threshold for heat shrinkage requirement is set to 5%. When the heat shrinkage requirement in a certain area reaches 7%, the difference exceeds the difference threshold, triggering subsequent processing.

[0059] It can be understood that this comparison method depends on the accuracy of the data. If the heat shrinkage requirement data collected by the scanning device is not accurate enough, it may lead to misjudgment.

[0060] Preferably, it is necessary to ensure that the equipment accuracy reaches the millimeter level to support the reliability of the triggering conditions.

[0061] In a possible implementation, if the difference exceeds the difference threshold, when extracting shape data from the geometry, point cloud data can be generated by a 3D scanner to obtain a set of data to be processed.

[0062] For example, the curved surface at the end of the wire harness may include a main trunk with a diameter of 10 mm and a branch with a diameter of 3 mm, and the point cloud data can fully reflect these features.

[0063] Specifically, this extraction process needs to consider the scanning angle and light interference to ensure the comprehensiveness of the data.

[0064] It should be noted that the higher the density of the point cloud data, the more guaranteed the accuracy of subsequent processing. When using the grid division method to divide the shape data set into regions, the end of the wire harness can be divided into multiple grid cells.

[0065] For example, an end region with a length of 50 mm can be divided into 10 grids at a unit of every 5 mm, and each grid independently records the shape characteristics.

[0066] Exemplarily, this division can intuitively reflect the shape changes of different parts of the end. For example, the grids in the branch region will show more intensive curvature changes.

[0067] In one embodiment, the grid division can also be dynamically adjusted according to the curvature magnitude. The grids in the regions with larger curvature are smaller to improve the fineness of the distributed data.

[0068] Calculate the continuous change of the demand judgment using the bilinear interpolation algorithm according to the preliminary regional distribution data. This process aims to smooth the discrete data.

[0069] For example, assume that the heat shrinkage demand of a certain grid cell is 6% and that of the adjacent cell is 4%. The demand value of the intermediate transition region can be calculated through bilinear interpolation to form a continuous change curve.

[0070] Specifically, this algorithm can effectively reduce the mutation between regions and ensure the rationality of the optimized distribution parameters.

[0071] Preferably, the boundary conditions of the grid cells can be combined during interpolation to further improve the smoothness of the calculation results.

[0072] When extracting the regional distribution characteristics from the optimized distribution parameters, the concentrated regions of the heat shrinkage demand can be concerned.

[0073] For example, in the region near the branch at the end of the wire harness, the heat shrinkage demand may be concentrated above 8%, while that in the main trunk region is only 3%.

[0074] In one embodiment, these high-demand areas can be marked by a feature extraction tool to form the final distribution result data. This feature extraction helps to quickly locate the parts that need to be adjusted with priority.

[0075] When judging the regional characteristics of the heat shrinkage demand for the final distribution result data, the adjustment priority can be set according to the demand value.

[0076] For example, the areas with a heat shrinkage demand exceeding 7% are adjusted first, and the areas with a heat shrinkage demand lower than 4% are adjusted second.

[0077] Specifically, this judgment can provide a clear direction for the subsequent scheme. For example, the high-demand areas may require thicker heat shrinkage sleeves.

[0078] Exemplarily, if the heat shrinkage demand of a certain branch area is 8%, it can be preliminarily determined that its thickness needs to be increased by 0.5 mm.

[0079] When updating the distribution of the shape data by adjusting the scheme parameters, the adjusted data can be fed back into the 3D model.

[0080] For example, the heat shrinkage thickness of the main trunk area is adjusted to 1 mm, and the branch area is adjusted to 1.5 mm to generate the processed data result.

[0081] It can be understood that this update process can ensure the uniformity and stability of the end structure, providing a reliable basis for subsequent processing.

[0082] For example, this method can also reduce material waste and improve the overall efficiency.

[0083] Optionally, in step S16, by using the optimized distribution parameters to obtain the heat shrinkage coverage scheme for the end structure and get the final heat shrinkage demand distribution, it further includes: Step S161, by using the preset initial thickness of the heat shrinkage material and the shrinkage rate optimization parameters, obtain the thickness distribution data of the end structure as the preliminary coverage data.

[0084] Step S162, use the NumPy library to generate a rectangular grid with a spacing of 1 mm, and extract the heat shrinkage coverage thickness of each grid unit from the preliminary coverage data to obtain the heat shrinkage coverage range division result.

[0085] Step S163, calculate the root mean square error between the range division result and the required thickness distribution, and determine the shrinkage rate corresponding to the minimum error as the matching parameter.

[0086] Step S164, generate a thickness increment and decrement matrix according to the matching parameter to obtain the adjusted scheme data.

[0087] Step S165: Use the interp2d function of SciPy to perform bilinear interpolation on the adjusted solution data, calculate the thickness change gradient between grid nodes, and obtain a continuous thickness field as the feature distribution result.

[0088] Step S166: For the feature distribution result, extract the regions where the thickness gradient is greater than the thickness gradient threshold, mark them as the shrinkage demand distribution regions of the end structure, and output as the final coverage solution.

[0089] Specifically, through the preset initial thickness and shrinkage rate optimization parameters of the heat shrinkable material, obtain the thickness distribution data of the end structure as the preliminary coverage data. The core of this process lies in establishing an initial hypothesis.

[0090] For example, assume that the initial thickness of the heat shrinkable material at the end of the wire harness is 1 mm and the shrinkage rate is 30%. Through these parameters, the thickness distribution after coverage can be preliminarily calculated.

[0091] Exemplarily, in the main trunk area of the wire harness, the initial thickness may remain at 0.7 mm, while in the branch area, due to the complex shape, the thickness may vary to 0.9 mm.

[0092] Specifically, this preliminary data provides a basic reference point for subsequent optimization.

[0093] It can be understood that the selection of the initial parameters needs to combine the actual performance of the material to ensure the feasibility of the preliminary coverage data.

[0094] Use the NumPy library to generate a rectangular grid with a spacing of 1 mm, extract the heat shrinkage coverage thickness of each grid cell from the preliminary coverage data, and obtain the heat shrinkage coverage range division result. This method aims to discretize continuous data.

[0095] For example, a 50-mm long end area of the wire harness can be divided into 50 grid cells, and each cell independently records the thickness value.

[0096] In a possible implementation, the grid thickness in the main trunk area may be evenly distributed around 0.7 mm, while the grid thickness in the branch area shows a local thickening trend, reaching 0.9 mm.

[0097] It should be noted that this division method facilitates subsequent analysis of the coverage characteristics of each region.

[0098] Calculate the root mean square error between the range division result and the required thickness distribution, and determine the shrinkage rate corresponding to the minimum error as the matching parameter. The key to this process lies in finding the best matching point.

[0099] For example, assume that the required thickness distribution requires a main trunk of 0.8 mm and branches of 1.0 mm, while the preliminary coverage data are 0.7 mm and 0.9 mm respectively. By adjusting the shrinkage rate to 35%, the error can be minimized.

[0100] Preferably, this method can quickly lock in the appropriate shrinkage rate parameters and provide a basis for subsequent adjustments.

[0101] Generating a thickness increase and decrease matrix based on the matching parameters to obtain the adjusted scheme data. This step is a key step in quantifying the optimization results.

[0102] Exemplarily, if the matching parameter is 35%, the main trunk area may need to be thickened by 0.1 mm and the branch area by 0.1 mm to form an increase and decrease matrix.

[0103] In one embodiment, the matrix can intuitively reflect the adjustment amount of each grid unit, ensuring that the thickness distribution is closer to the required value.

[0104] Specifically, this quantification method provides structured data for subsequent interpolation calculations.

[0105] Using the interp2d function of SciPy to perform bilinear interpolation on the adjusted scheme data, calculating the thickness change gradient between grid nodes, and obtaining a continuous thickness field as the feature distribution result. This process aims to eliminate the mutations between discrete data.

[0106] For example, if the thicknesses of two adjacent grids are 0.8 mm and 1.0 mm respectively, the transition region may show a smooth change of 0.9 mm after interpolation.

[0107] In one embodiment, this continuous thickness field can clearly show the trend of thickness change, facilitating subsequent feature extraction. For the feature distribution result, extract the regions where the thickness gradient is greater than a preset thickness gradient threshold, mark them as the heat shrinkage demand distribution regions of the end structure, and output as the final coverage scheme. This step focuses on identifying key regions.

[0108] For example, assume that the thickness gradient threshold is 0.2 mm / grid. If the gradient in the branch region reaches 0.3 mm / grid, it is marked as a high-demand region.

[0109] In one possible implementation, these marked regions can guide the key adjustments of the subsequent processing scheme.

[0110] Preferably, this method can effectively highlight the parts that need special attention and improve the pertinence of the coverage scheme.

[0111] Optionally, in step S17, for the final heat shrinkage demand distribution, judging the heat shrinkage sleeve thickness requirements of each region and determining the adjustment scheme for the end structure further includes: Step S171: Obtain the thickness characteristics of each region by thermal shrinkage demand distribution data, remove noise using Gaussian filtering, and generate thickness distribution data.

[0112] Step S172: Use the percentile statistical method for the thickness distribution data, calculate the 5% and 95% percentile values as the boundaries of the thickness change range, and obtain the thickness range division result.

[0113] Step S173: Compare the thickness range division result with the preset thickness standard interval, and calculate the proportion of the overlapping area as the matching degree parameter.

[0114] Step S174: When the matching degree parameter is lower than the matching degree threshold, it is determined as the area that needs to be adjusted.

[0115] Step S175: According to the area coordinates where the matching degree parameter is lower than the matching degree threshold, determine the position coordinates where the end structure needs to be thickened or thinned, and generate a preliminary adjustment plan including position marks.

[0116] Step S176: Adopt the bilinear interpolation algorithm, use the adjustment position as the center point, calculate the thickness adjustment amount of the surrounding area according to the distance weight, and output the thickness adjustment trend distribution map.

[0117] Step S177: In the trend distribution map, mark the areas where the adjustment amount exceeds the preset thickness of 5 mm as key adjustment areas, and the rest as auxiliary adjustment areas.

[0118] Step S178: Combine all the marked area coordinates and adjustment amount data to generate a final adjustment plan including specific dimension parameters.

[0119] Step S179: According to the coordinate-thickness mapping table in the final adjustment plan, output the processing drawing data of the end structure.

[0120] Specifically, obtain the thickness characteristics of each region by thermal shrinkage demand distribution data, remove noise using Gaussian filtering, and generate thickness distribution data.

[0121] For example, the original thickness data of a wire harness end region may contain fluctuations caused by measurement errors. Gaussian filtering can eliminate these noises through smoothing and retain the true thickness trend.

[0122] Exemplarily, if the thickness at a certain point in the original data jumps to 1.2 mm while the average of the surrounding area is 0.8 mm, it may be smoothed to 0.9 mm after filtering, which is more in line with the actual distribution.

[0123] Use the percentile statistical method for the thickness distribution data, calculate the 5% and 95% percentile values as the boundaries of the thickness change range, and obtain the thickness range division result.

[0124] Specifically, assume that there are 100 data points for the thickness of the end of a 50 - millimeter long wire harness. The 5th percentile may be 0.6 millimeters, and the 95th percentile is 1.1 millimeters. This range reflects the thickness fluctuation interval in most areas.

[0125] It can be understood that this method can effectively define the normal thickness range and avoid the interference of extreme values on subsequent analysis.

[0126] Compare the result of the thickness range division with the preset standard thickness interval, and calculate the proportion of the overlapping area as the matching degree parameter.

[0127] In a possible implementation, if the standard interval is from 0.7 millimeters to 1.0 millimeters, and the actual range is from 0.6 millimeters to 1.1 millimeters, the overlapping part is from 0.7 millimeters to 1.0 millimeters, and the proportion may be 70%.

[0128] It should be noted that this parameter intuitively reflects the degree of coincidence between the actual distribution and the requirements.

[0129] Preferably, when the matching degree parameter is less than 7, it is determined as the area that needs to be adjusted.

[0130] For example, if the matching degree of a certain branch area is only 60%, it indicates that its thickness distribution deviates significantly from the standard, and there may be problems such as insufficient coverage or excessive thickness.

[0131] Preferably, this determination method can quickly screen out the problem areas.

[0132] According to the area coordinates where the matching degree parameter is lower than the matching degree threshold, determine the position coordinates where the end structure needs to be thickened or thinned, and generate a preliminary adjustment plan including position marks.

[0133] Exemplarily, if the matching degree of a branch area is low and the average thickness is 0.6 millimeters, which is lower than the standard lower limit of 0.7 millimeters, it is marked as the area that needs to be thickened, and the coordinates are recorded as (20, 10).

[0134] In one embodiment, this plan provides a clear direction for subsequent adjustments.

[0135] Adopt the bilinear interpolation algorithm. With the adjustment position as the center point, calculate the thickness adjustment amount of the surrounding areas according to the distance weight, and output the thickness adjustment trend distribution map.

[0136] Specifically, if a certain point needs to be thickened by 0.2 millimeters, the adjacent points may be adjusted by 0.15 millimeters or 0.1 millimeters according to the distance, forming a smooth transition.

[0137] It can be understood that this method ensures a natural connection between the adjusted area and the surrounding areas. In the trend distribution map, the areas where the adjustment amount exceeds 5 millimeters are marked as key adjustment areas, and the rest are auxiliary adjustment areas.

[0138] For example, if the adjustment amount in the main trunk area reaches 5.5 mm, it is marked as the critical area, while if the adjustment amount in the branch is 2 mm, it is the auxiliary area.

[0139] In one embodiment, this classification facilitates the prioritized processing of significantly deviated areas.

[0140] Merge the coordinates of all marked areas and the adjustment amount data to generate a final adjustment plan containing specific dimensional parameters.

[0141] In one possible implementation, the plan may record that the main trunk coordinate (10, 5) is thickened by 0.3 mm and the branch coordinate (20, 10) is thickened by 0.2 mm to form a complete parameter table.

[0142] Preferably, this structured data facilitates processing and implementation.

[0143] For example, the drawing may mark that the thickness of a certain grid point is adjusted from 0.8 mm to 1.0 mm and is accompanied by position information.

[0144] It should be noted that this output provides intuitive guidance for actual production.

[0145] S2. According to the shrinkage demand distribution in different regions of the end part, use the zoning modeling algorithm to generate a temperature control model, divide the end part of the wire harness into multiple independent temperature control regions, and obtain the target temperature curve of each region.

[0146] Optionally, this step further includes: Step S21. Through the shrinkage demand data and the coordinates of the end part of the wire harness, use the k-means clustering algorithm to divide the end part of the wire harness into multiple independent temperature control regions. The clustering input is the normalized shrinkage strength and position matrix, and the output is the region division result.

[0147] Step S22. According to the division result, extract the average shrinkage demand of each region as the target temperature value.

[0148] Step S23. Starting from the target temperature value, use cubic spline interpolation to generate a continuous temperature curve, and the interpolation nodes are constrained such that the temperature gradient at the region boundaries is zero.

[0149] Step S24. For the generated temperature curve, compare the curve peak value with the temperature resistance upper limit of the wire harness material.

[0150] Step S25. If the temperature in a certain region exceeds the first temperature threshold, adjust the PID control parameters of that region, where the proportional coefficient is corrected inversely according to the overshoot amount, and the integral time is adjusted according to the steady-state error.

[0151] Step S26, optimize the PID parameters through the gradient descent algorithm, calculate the mean square error between the actual temperature curve and the target curve in each iteration, and update the parameters until the error is less than 5 degrees Celsius.

[0152] Step S27, regenerate the temperature control curves for each region according to the optimized PID parameters, and output the final temperature change sequence to the actuator.

[0153] Specifically, through the heat shrinkage demand data and the coordinates of the wire harness end, the k-means clustering algorithm is used to divide the wire harness end into multiple independent temperature control regions. The core of this process is to transform the complex heat shrinkage demand distribution into manageable regional units.

[0154] Exemplarily, the data of the end of an automotive wire harness with a length of 50 millimeters can be input into the algorithm. The normalized heat shrinkage intensity and position coordinates form a matrix, and after clustering, it is divided into three regions: a strong demand region near the connector, an intermediate transition region, and a weak demand region of the wire core. This division is based on data characteristics and can effectively reflect the heterogeneity of the end heat demand.

[0155] In a possible implementation, the mean value of the heat shrinkage demand for each region is extracted as the target temperature value according to the division result.

[0156] For example, the mean value of the strong demand region is 80 degrees Celsius, the transition region is 60 degrees Celsius, and the weak demand region is 40 degrees Celsius. This mean value reflects the central tendency of the heat shrinkage demand in the region and provides a benchmark for subsequent temperature control.

[0157] Specifically, the target temperature is set higher in the region near the connector due to the high heat shrinkage intensity, which helps to ensure the protection effect.

[0158] It should be noted that starting from the target temperature value, a continuous temperature curve is generated by cubic spline interpolation, and the boundary temperature gradient is constrained to zero, which can ensure a natural and smooth temperature transition between regions.

[0159] In an embodiment, assuming that the boundary temperature of the strong demand region is 80 degrees Celsius and the transition region is 60 degrees Celsius, a smooth curve is formed after interpolation, avoiding heat stress concentration caused by sudden changes. This method can improve the uniformity of the temperature distribution.

[0160] Comparing the peak value with the temperature resistance upper limit of the wire harness material for the generated temperature curve is a key step.

[0161] For example, if the temperature resistance upper limit of the material is 100 degrees Celsius and the peak value of the strong demand region reaches 90 degrees Celsius, no adjustment is required; if the peak value rises to 105 degrees Celsius, intervention is needed. This comparison can timely detect potential overheating risks.

[0162] If the temperature of a certain region exceeds the first temperature threshold, adjusting the PID control parameters is the coping strategy.

[0163] Preferably, if the overshoot in the strong demand area exceeds 5 degrees Celsius, the proportional coefficient can be reduced by 10% and the integral time can be extended by 20% to reduce the overshoot and stabilize the temperature. This adjustment is based on feedback and can quickly converge to the target value.

[0164] Optimize the PID parameters through the gradient descent algorithm, and calculate the mean square error between the actual and target temperature curves for each iteration until the error is less than 5 degrees Celsius.

[0165] For example, the initial error is 8 degrees Celsius and it drops to 4 degrees Celsius after 5 iterations, and the parameters tend to stabilize. This iterative optimization can significantly improve the control accuracy.

[0166] Regenerating the temperature control curves for each area according to the optimized PID parameters and outputting them to the actuator is the key to implementing the solution.

[0167] For example, the temperature curve in the strong demand area stabilizes at around 80 degrees Celsius, and the transition area smoothly drops to 60 degrees Celsius. This precise control can optimize the heat shrinkage process and improve the protection performance and service life of the wire harness end.

[0168] It can be understood that the above process forms a complete logical chain from data clustering to parameter optimization, which is applicable to the temperature control demand management of complex wire harness ends. Each link supports each other, ensuring the reliability and practicality of the solution.

[0169] S3. Obtain real-time temperature output data from the heat source device through a preset temperature control model, dynamically adjust the heat source power for each temperature control area, and determine whether the temperature meets the requirements of the target temperature curve.

[0170] Optionally, this step further includes: Step S31. Obtain real-time temperature data from the heat source device through a temperature sensor, calculate the temperature deviation for each temperature control area, and obtain a preliminary temperature distribution.

[0171] Step S32. According to the preliminary temperature distribution, use a PID controller to calculate the change amount of the heat source power for each temperature control area and determine the power adjustment plan.

[0172] Step S33. Convert the power adjustment plan into the output power of the heat source device through a PLC system and obtain the adjusted real-time temperature data.

[0173] Step S34. Use the sliding window algorithm to judge the temperature change trend. If the temperature change trend deviates from the target temperature curve, recalculate the power adjustment amount through a PID controller to obtain an optimized power distribution.

[0174] Step S35: According to the optimized power distribution, use the DCS system to adjust the operating parameters of the heat source equipment, obtain new temperature data, and determine whether it is close to the target temperature.

[0175] Step S36: By continuously monitoring the temperature data, use the support vector machine algorithm to analyze the matching degree between the temperature curve and the target temperature curve, and determine the final adjustment result.

[0176] Step S37: After obtaining the final adjustment result, update the heat source power through the SCADA system, and determine whether the temperature in each temperature control area meets the requirements of the target temperature curve.

[0177] Specifically, obtaining real-time temperature data from the heat source equipment through temperature sensors is the starting point of the entire temperature control process.

[0178] Exemplarily, assume that the end of an automotive wire harness is divided into three temperature control areas, and temperature sensors are respectively deployed at the core positions of each area to collect data in real time.

[0179] In a possible implementation, the temperature measured in the area near the connector is 82 degrees Celsius, the intermediate transition area is 58 degrees Celsius, and the wire core area is 42 degrees Celsius. By comparing with the target temperature, the deviation value is calculated, providing a basis for subsequent adjustments. This method can quickly reflect the temperature status of each area.

[0180] According to the preliminary temperature distribution, the PID controller calculates the change amount of the heat source power for each area.

[0181] It can be understood that the PID controller comprehensively judges the power adjustment direction through the three links of proportional, integral, and differential.

[0182] For example, the target temperature in the area near the connector is 80 degrees Celsius, and the actual temperature is too high. The controller may reduce the power output by 5%.

[0183] Specifically, the temperature in the middle area is too low, and the power needs to be increased by 3%. This on-demand adjustment can make the heat source output more in line with the actual needs.

[0184] Converting the power adjustment scheme into the output power of the heat source equipment through the PLC system is the key to the execution link.

[0185] In one embodiment, after the PLC receives the power change signal, it reduces the heat source power in the area near the connector from 100 watts to 95 watts, and increases the power in the transition area from 80 watts to 83 watts. After the adjustment, the sensor feeds back new temperature data to verify the effect. This real-time response mechanism improves the flexibility of control.

[0186] Using the sliding window algorithm to judge the temperature change trend is an important step in dynamic optimization.

[0187] Preferably, with a window length of 5 seconds, analyze the temperature data of the last 10 times. If the temperature in the area near the connector slowly rises from 82 degrees Celsius to 83 degrees Celsius and the trend deviates from the target, the PID controller will recalculate the power adjustment amount.

[0188] For example, the power may be reduced by another 2% to pull back the temperature. This method can capture subtle changes in a timely manner.

[0189] According to the optimized power distribution, the DCS system adjusts the operating parameters of the heat source equipment for further refined management.

[0190] It should be noted that the DCS system can adjust the air volume or heating time of the heat source according to the power distribution.

[0191] For example, after the power in the wire core area stabilizes, the air volume is reduced by 10%, and the temperature slowly approaches the target value of 40 degrees Celsius from 42 degrees Celsius. This globally coordinated method enhances the stability of the system.

[0192] Analyzing the matching degree between the temperature curve and the target curve through the support vector machine algorithm is the core technology for verifying the effect.

[0193] In a possible implementation, compare the real-time temperature curve with the target curve and calculate the matching degree score. If the score is lower than 90%, it indicates that the temperature fluctuation in the transition area is relatively large and further adjustment is required. This analysis based on machine learning can more accurately evaluate the control effect.

[0194] After obtaining the final adjustment result, the SCADA system updates the heat source power to ensure that the temperature in each area meets the requirements.

[0195] For example, the temperature in the area near the connector stabilizes at 80 degrees Celsius, the transition area is 60 degrees Celsius, and the wire core area is 40 degrees Celsius. The SCADA system can also record the data during the adjustment process for reference in subsequent optimization. This comprehensive monitoring method improves the traceability of the process.

[0196] It can be understood that from the sensor collection to the SCADA update, a complete set of real-time control chains are formed. Each link is driven by data and supported by algorithms, ensuring the accuracy of temperature management.

[0197] Exemplarily, the adjusted temperature distribution better meets the actual needs of the wire harness end, effectively improving the processing quality.

[0198] S4. Obtain the infrared thermal imaging data of the wire harness end during the heat shrinkage process, use image processing technology to analyze the surface temperature distribution of the heat shrinkable tube, and determine whether there are local overheating or uneven shrinkage phenomena.

[0199] Optionally, this step further includes: Step S41: Obtain the infrared thermal imaging data of the end of the wire harness during heat shrinkage to obtain the original thermal imaging image.

[0200] Step S42: Use Gaussian filtering to smooth the original thermal imaging image to obtain the smoothed temperature distribution image.

[0201] Step S43: Analyze the smoothed temperature distribution image using the Canny edge detection algorithm to determine the boundary characteristics of the surface temperature of the heat shrinkable sleeve.

[0202] Step S44: Calculate the gradient value of the temperature distribution for the boundary characteristics and determine whether there is a locally overheated area.

[0203] Step S45: Calculate the average temperature of each area in the temperature distribution image through the regional average temperature to obtain the distribution characteristics of uneven shrinkage.

[0204] Step S46: If the temperature gradient of the locally overheated area exceeds the preset temperature gradient threshold, use the pre-trained ResNet model to classify the temperature distribution image to determine the specific location of the abnormal area.

[0205] Step S47: According to the specific location of the abnormal area, use the K-means clustering algorithm to partition the surface temperature of the heat shrinkable sleeve to obtain the quantization result of uneven shrinkage.

[0206] Specifically, obtaining the infrared thermal imaging data of the end of the wire harness during heat shrinkage is the basis for analyzing the temperature distribution.

[0207] Exemplarily, the infrared thermal imager is deployed above the heat shrinkage equipment to capture in real time the thermal image formed by the surface temperature of the end of the wire harness.

[0208] In a possible implementation, when the heat shrinkable sleeve at the end of the wire harness is processed, the thermal imager records that the temperature in the area close to the terminal is shown in red, the middle area is yellow, and the end is green, reflecting the temperature distribution from high to low. This intuitive image data provides the original basis for subsequent processing.

[0209] Using Gaussian filtering to smooth the original thermal imaging image can effectively reduce noise interference.

[0210] It can be understood that Gaussian filtering highlights the main temperature distribution characteristics by blurring the image details.

[0211] For example, there may be fine noise points in the original image due to ambient light or equipment jitter. After Gaussian filtering, the boundary of the temperature area in the area close to the terminal is smoother and the temperature transition is more natural. This method enables subsequent analysis to focus more on the overall trend rather than local interference.

[0212] In one embodiment, the Canny edge detection algorithm is used to analyze the smoothed image to determine the temperature boundary features on the surface of the heat shrinkable sleeve.

[0213] Specifically, the algorithm identifies the edge lines where the temperature changes from high to low.

[0214] For example, the boundary line between the red high-temperature area and the yellow transition area near the terminal area is clearly outlined. This boundary feature extraction provides a key clue for judging whether the temperature distribution is uniform. Calculating the gradient value of the temperature distribution for the boundary feature can further reveal potential areas of local overheating.

[0215] Preferably, the gradient value is obtained by comparing the temperature differences of adjacent pixel points.

[0216] For example, the temperature near the terminal area drops sharply from 85 degrees Celsius to 60 degrees Celsius, resulting in a high gradient value, while the temperature in the middle area changes gently, resulting in a low gradient value. This analysis method can quickly locate the temperature anomaly points. Calculating the average temperature of each area can quantify the characteristics of uneven shrinkage.

[0217] In a possible implementation, the surface of the heat shrinkable sleeve is divided into three areas. The calculation results show that the average temperature of the area near the terminal is 82 degrees Celsius, the middle area is 58 degrees Celsius, and the end area is 45 degrees Celsius.

[0218] It should be noted that this average value comparison can intuitively reflect which areas have temperatures deviating from the expected values, helping to optimize the heat shrinkage process.

[0219] If the temperature gradient in the local overheating area exceeds a preset temperature gradient threshold, such as 10 degrees Celsius per centimeter, then the pre-trained ResNet model is used to classify the image to locate the abnormal area.

[0220] For example, due to the concentrated heat source in the terminal area, the temperature abnormally rises. The ResNet model analyzes through deep learning and marks this area as abnormal. This method combined with artificial intelligence can more accurately identify the problem location.

[0221] According to the specific location of the abnormal area, the K-means clustering algorithm is used to partition the surface temperature of the heat shrinkable sleeve to obtain a quantitative result of uneven shrinkage.

[0222] In one embodiment, the algorithm clusters the surface temperature into three categories: the high-temperature area is concentrated near the terminal, the uniform-temperature area is distributed in the middle, and the low-temperature area is near the end. This partitioning result provides data support for subsequent process adjustment and can effectively improve the processing uniformity of the heat shrinkable sleeve.

[0223] S5. If the surface temperature distribution of the heat shrinkable tube exceeds the preset temperature distribution threshold, the heat source power of the corresponding area is adjusted through a feedback control algorithm, and the temperature output is recalculated in combination with the material characteristic parameters to obtain an optimized heating scheme.

[0224] Optionally, this step further includes: Step S51. If the surface maximum temperature exceeds the second temperature threshold, real-time temperature matrix data is obtained through an infrared sensor.

[0225] Step S52. According to the difference between the maximum value in the temperature matrix and the second temperature threshold, the heat source power adjustment value is calculated using a proportional-integral algorithm, and the algorithm parameters are obtained from the material thermal conductivity library to obtain a power adjustment scheme.

[0226] Optionally, the following formula is used to calculate the heat source power adjustment value:

[0227] where, represents the heat source power adjustment value, represents the proportionality coefficient, represents the integral coefficient, represents the maximum value of the temperature matrix, represents the second temperature threshold.

[0228] Step S53. After executing the power adjustment scheme, the updated temperature matrix is collected from the thermocouple array.

[0229] Step S54. Extract the maximum value in the temperature matrix. If it still exceeds the second temperature threshold, secondary adjustment is performed using an incremental PID algorithm, and the PID parameters are set according to the material specific heat capacity library, and the fine-tuned power value is output.

[0230] Step S55. Drive the heating tube to work according to the fine-tuned power value, and trigger a temperature acquisition instruction after the work is completed.

[0231] Step S56. Obtain the temperature matrix in the stable state from the infrared sensor, and calculate the mean square error between the temperature of each area and the target value.

[0232] Step S57. If the mean square error is greater than the allowable error, the moving average method is used to analyze the trend of historical temperature data, and the power distribution ratio is corrected according to the trend slope.

[0233] Step S58. Control the operation of the heating tube array according to the corrected power ratio, and continuously collect temperature matrix data during the operation.

[0234] Step S59. Extract the highest temperature, the lowest temperature and the gradient change rate in the matrix as long-term optimization parameters and write them into the control log.

[0235] Specifically, the infrared sensor obtaining real-time temperature matrix data is an important means to monitor the heat shrinkage process.

[0236] Exemplarily, during the processing of heat shrinkable sleeves, the infrared sensor is installed above the equipment, covering the entire area of the wire harness end, and generating a matrix containing hundreds of temperature data in real time.

[0237] In a possible implementation, the sensor detects that the temperature near the terminal reaches 90 degrees Celsius, while the end is only 40 degrees Celsius. This matrix data provides a basic basis for subsequent analysis.

[0238] When adjusting the heat source power according to the difference between the maximum value in the temperature matrix and the second temperature threshold, the proportional-integral algorithm can quickly respond to temperature changes.

[0239] Specifically, if the preset second temperature threshold is 80 degrees Celsius, the maximum value of the matrix is 90 degrees Celsius, and the difference is 10 degrees Celsius, the algorithm will refer to the parameters of polyethylene materials in the material thermal conductivity library and calculate the specific value of power reduction.

[0240] For example, the power is reduced from 500 watts to 450 watts. This method ensures that the temperature gradually approaches the target value through dynamic adjustment.

[0241] The thermocouple array collecting the updated temperature matrix further verifies the adjustment effect.

[0242] In one embodiment, after the power is reduced, the thermocouple array shows that the temperature in the terminal area drops to 83 degrees Celsius, and the middle area is 60 degrees Celsius. The data update intuitively reflects the impact of power adjustment.

[0243] It should be noted that the high-precision characteristics of the thermocouple array make it suitable for capturing subtle changes. If the temperature still exceeds the second temperature threshold, when the incremental PID algorithm performs secondary adjustment, it will optimize the parameters according to the material specific heat capacity library.

[0244] Preferably, for polyethylene sleeves, the specific heat capacity data shows that the temperature change is relatively sensitive, so the PID algorithm sets a smaller incremental step size.

[0245] For example, the power is fine-tuned from 450 watts to 440 watts. This refined adjustment can effectively avoid overshoot.

[0246] After the fine-tuned power value drives the heating tube to work, a temperature acquisition instruction is triggered to ensure the system responds in a timely manner.

[0247] It can be understood that after the heating tube operates at 440 watts for 10 seconds, the sensor is triggered, and the collected temperature matrix shows that the overall temperature distribution tends to be stable. This mechanism improves the real-time performance of the process.

[0248] The temperature matrix in the steady state is used to calculate the mean square error to evaluate whether the temperature distribution meets the standard.

[0249] For example, the target value is 60 degrees Celsius, and the temperatures in each area of the matrix are 62 degrees Celsius, 59 degrees Celsius, and 61 degrees Celsius respectively. The mean square error is small, indicating that the distribution is relatively uniform. This quantitative analysis provides an objective basis for process optimization.

[0250] If the mean square error exceeds the allowable error, analyzing the trend of historical temperature data by the moving average method can find the root cause of the problem.

[0251] In one embodiment, the historical data shows that the temperature in the terminal area has been continuously high, and the trend slope shows an increase of 2 degrees Celsius per minute. Based on this, the power distribution ratio is corrected. For example, the power in the terminal area is reduced by 10%. This method guides the current adjustment through historical rules.

[0252] When controlling the operation of the heating tube array according to the corrected power ratio, continuously collect the temperature matrix data to ensure full controllability throughout the process.

[0253] Exemplarily, after the power in the terminal area is reduced to 400 watts, the temperature matrix shows that the high-temperature area shrinks, the temperature in the low-temperature area rises slightly, and the overall tends to balance. This dynamic monitoring improves the processing consistency. Extracting the highest temperature, the lowest temperature, and the gradient change rate in the matrix as long-term optimization parameters can provide a reference for subsequent production.

[0254] Specifically, the highest temperature of 85 degrees Celsius, the lowest temperature of 45 degrees Celsius, and the gradient change rate of 5 degrees Celsius per centimeter are recorded, reflecting the current process characteristics. This data accumulation helps to continuously improve the heat shrinkage process.

[0255] Optionally, in step S51, if the highest surface temperature exceeds the second temperature threshold, when obtaining the real-time temperature matrix data through the infrared sensor, it further includes: Step S511, if the surface temperature exceeds the second temperature threshold, collect the real-time temperature matrix data through the infrared sensor to obtain the temperature matrix.

[0256] Step S512, generate a temperature distribution map according to the temperature values of each pixel point in the temperature matrix.

[0257] Step S513, extract the boundary region data with a width of 5 pixels in the outermost layer from the temperature matrix to obtain the boundary temperature set.

[0258] Step S514, use the Sobel operator to calculate the horizontal gradient Gx and the vertical gradient Gy of the boundary temperature set, and according to the formula Obtain the gradient value G of each point and generate a gradient distribution.

[0259] Step S515: If there are data points in the gradient distribution that exceed the gradient mean ± 3 times the standard deviation, they are determined as outliers.

[0260] Step S516: For the temperature matrix with outliers, perform convolution operation using a 3×3 mean filter kernel to obtain a smoothed temperature matrix.

[0261] Step S517: Calculate the standard deviation of the temperature in each partition of the smoothed temperature matrix as the fluctuation characteristic of this area.

[0262] Step S518: Input the fluctuation characteristics of each partition into the PID controller, and adjust the partition control parameters of the corresponding heating tube according to the size of the standard deviation.

[0263] Step S519: After parameter adjustment, drive the heating tube to operate, and obtain the updated temperature matrix from the infrared sensor.

[0264] Step S5110: When the standard deviation of the temperature matrix is less than 0.5 °C for three consecutive times, it is determined as a stable distribution.

[0265] Specifically, collecting real-time temperature matrix data through an infrared sensor is an important way to monitor the processing of heat shrinkable tubes.

[0266] Exemplarily, when processing the end of a wire harness, the infrared sensor covers the entire heating area and generates a matrix containing hundreds of temperature points.

[0267] In one possible implementation, the sensor detects that the temperature in the area near the terminal is higher, while the temperature in the part far from the terminal is lower, and this data provides a basis for subsequent analysis.

[0268] Generating a temperature distribution map based on the temperature matrix can visually reflect the temperature change in the processing area.

[0269] Specifically, the temperature distribution map maps the temperature value of each pixel point to a color, with red representing high temperature and blue representing low temperature.

[0270] For example, the area near the terminal is shown in red and the end is in blue, and the operator can quickly identify the temperature difference.

[0271] Extracting the data of the outermost 5-pixel-width boundary area from the temperature matrix can effectively analyze the edge temperature characteristics.

[0272] In one embodiment, the temperature of the boundary area gradually decreases from the center to the outside. The data set shows that the edge temperature is 50 degrees Celsius, while the center is close to 80 degrees Celsius. This extraction method helps to focus on the heat dissipation situation at the boundary. Use the Sobel operator to calculate the gradient of the boundary temperature set, which can quantify the severity of the temperature change.

[0273] Preferably, the horizontal and vertical gradients reflect the transition speed of temperature from high to low.

[0274] For example, the gradient in the boundary area near the terminal is large, indicating a significant temperature drop, while the gradient at the end is relatively gentle. This analysis provides a basis for adjusting the heating strategy. If there are outliers in the gradient distribution, it may indicate local overheating or insufficient heat dissipation.

[0275] It should be noted that outliers usually appear at the terminal connections, resulting in sudden temperature changes due to the strong thermal conductivity of metals.

[0276] For example, if the gradient at a certain point exceeds three times the average gradient, it indicates abnormal temperature changes at this point and further processing is required. For outliers, performing a convolution operation with a 3×3 mean filter kernel can smooth the temperature matrix.

[0277] It can be understood that this method weakens the impact of mutations by taking the average of surrounding points.

[0278] For example, the temperature in a certain area is smoothed from 90 degrees Celsius to 85 degrees Celsius, reducing the risk of misjudging local overheating. Calculating the standard deviation of each partition in the smoothed temperature matrix can reflect the temperature fluctuations within the area.

[0279] In one embodiment, the standard deviation in the terminal area is 5 degrees Celsius, and in the middle area it is 2 degrees Celsius, indicating that the temperature distribution in the terminal part is not uniform enough. This eigenvalue guides subsequent adjustments. Inputting the fluctuation characteristics into a PID controller and adjusting the parameters of the heating tube according to the standard deviation can achieve precise temperature control.

[0280] Specifically, the power is reduced in the area with a large standard deviation, and remains stable in the area with a small standard deviation.

[0281] For example, the power in the terminal area is reduced from 500 watts to 450 watts to ensure that the temperature tends to be consistent. After parameter adjustment, an infrared sensor obtains the updated temperature matrix to verify the control effect.

[0282] Exemplarily, the adjusted matrix shows that the high-temperature area shrinks, the low-temperature area slightly increases, and the overall distribution is more balanced. This real-time feedback improves the reliability of processing. When the standard deviation of the temperature matrix is less than 0.5 degrees Celsius for three consecutive times, it indicates that the temperature distribution has stabilized.

[0283] For example, the temperatures in each area of the matrix are 60 degrees Celsius, 61 degrees Celsius, and 59 degrees Celsius respectively, and the standard deviation is extremely small, and the process meets the expectations. This determination method provides a reliable end mark for production.

[0284] S6. According to the optimized heating scheme, use multi-point sensors to collect the temperature data of the internal wires at the end of the wire harness, judge whether the wires are at risk of damage due to overheating, and generate a real-time temperature warning signal.

[0285] Optionally, this step further includes: Step S61: Using a multi-point sensor to collect temperature data of the internal wires from the end of the wire harness to obtain an original temperature sequence.

[0286] Step S62: Smoothing the original temperature sequence to obtain a smoothed temperature curve and determining the temperature change trend.

[0287] Step S63: Comparing according to the temperature change trend using a temperature change threshold. If the threshold is exceeded, it is determined that there is an overheating risk to obtain a risk identifier.

[0288] Step S64: For the risk identifier, combining with the material properties of the internal wires, evaluating the damage degree through logical judgment to obtain a damage assessment result.

[0289] Step S65: Extracting key features from the damage assessment result, classifying using a support vector machine algorithm, and determining whether a warning signal needs to be generated to obtain a classification result.

[0290] Step S66: Based on the classification result, if it is classified as high risk, generate a corresponding temperature warning signal to obtain a warning output.

[0291] Step S67: According to the warning output, update the temperature monitoring status at the end of the wire harness in real time to obtain adjusted monitoring parameters.

[0292] Specifically, using a multi-point sensor to collect temperature data of the internal wires from the end of the wire harness is an important way to monitor the internal state during the heat shrinkage process.

[0293] Exemplarily, the multi-point sensor can be a thermistor distributed along the axial direction of the wire harness, with 5 points arranged at intervals of 5 cm to collect the temperatures of different parts of the wire respectively, forming a sequence containing multiple data.

[0294] For example, the data collected in a certain acquisition are 50 °C, 55 °C, 60 °C, 65 °C, and 70 °C, reflecting the increasing temperature trend from the end to the inside. This method can intuitively capture the heat distribution inside the wire. Smoothing the original temperature sequence is to eliminate noise interference and highlight the trend. In one possible implementation, the moving average method can be used, taking the data of 3 adjacent points for averaging to obtain the smoothed sequence, such as 53 °C, 58 °C, and 65 °C. The smoothed curve shows that the temperature gradually increases from the end to the inside.

[0295] It can be understood that this processing retains the main change features, facilitating subsequent analysis.

[0296] Comparing the temperature change trend with a preset temperature change threshold is a key step in judging the risk.

[0297] Specifically, if the temperature change threshold is set to 60 degrees Celsius and 65 degrees Celsius in the smooth curve exceeds the temperature change threshold, it is marked as an overheating risk.

[0298] It should be noted that the setting of the temperature change threshold usually refers to the heat resistance limit of the wire insulation material, such as the upper heat resistance limit of polyvinyl chloride. This comparison method can quickly locate potential problems.

[0299] When evaluating the damage degree in combination with the material properties for risk identification, the logical judgment is based on the material characteristics.

[0300] In one embodiment, if the wire insulation layer is made of polyvinyl chloride with a heat resistance limit of 70 degrees Celsius, although the current temperature of 65 degrees Celsius has not reached the limit, it is close to the critical value, which may lead to a decrease in insulation performance. The evaluation result may indicate that the damage degree is minor, but it needs attention.

[0301] Extracting key features from the damage assessment results and using a support vector machine for classification is the core of intelligent judgment.

[0302] Preferably, the features include the maximum temperature of 65 degrees Celsius, the duration of 10 minutes, and the temperature gradient. The support vector machine classifies this as a medium risk based on the training data. The advantage of this algorithm is that it can integrate multi-dimensional information and improve the judgment accuracy.

[0303] Generating a warning signal based on the classification result is a direct measure for the protection system.

[0304] For example, if the classification is high risk, the system will issue an audible alarm and record the timestamp, such as "10:00 on March 27, 2025". This kind of warning can timely remind the operator to take measures to avoid further deterioration. Updating the monitoring status in real time according to the warning output is an embodiment of dynamic management.

[0305] In one embodiment, after the warning, the sensor acquisition frequency is increased, adjusted from once per minute to once every 30 seconds, and at the same time, the updated temperature sequence is recorded, such as 62 degrees Celsius, 60 degrees Celsius, and 58 degrees Celsius. This adjustment can more finely track the changes and ensure the process safety and controllability.

[0306] S7. Drive the adaptive adjustment system through the real-time temperature warning signal, and fine-tune the heat source power and heating duration in combination with the dynamic adaptation algorithm to determine the final process parameters for the uniform shrinkage of the heat shrinkable sleeve.

[0307] Optionally, this step further includes: Step S71. Obtain real-time temperature data through the sensor, and use the real-time temperature threshold to judge whether the temperature exceeds the warning value.

[0308] Step S72: If an early warning is triggered, the slope value of the most recent 10 temperature data is calculated using the moving average method as the change trend.

[0309] Step S73, inputting the slope value into the PID control algorithm, calculating the heat source power adjustment amount, and obtaining the adjusted power value.

[0310] Step S74, using the exponential smoothing method to predict the heating time according to the adjusted power value, and outputting the time correction value.

[0311] Step S75, extracting the casing diameter variance feature from the power value and the corrected duration, and determining whether it is less than 1 mm.

[0312] Step S76: if the conditions are met, the power and duration parameters are input into a finite element thermodynamics simulation tool, and the casing deformation data is output.

[0313] Step S77, adjusting the heat source power and heating time according to the simulation results to stabilize the sleeve diameter variance within 1 mm.

[0314] Specifically, obtaining real-time temperature data through sensors and using preset real-time temperature thresholds to determine whether the temperature exceeds the warning value are basic steps to ensure the safety of wire harness processing.

[0315] For example, the sensor can be a thermocouple, which is arranged at the end of the wiring harness to collect temperature data in real time. Assuming that the preset real-time temperature threshold is 60 degrees Celsius, and the temperature collected at a certain time is 62 degrees Celsius, an early warning is triggered when the real-time temperature threshold is exceeded. This method can quickly respond to abnormal situations.

[0316] In one possible implementation, the sensor collects data once a second to form a sequence, such as 58 degrees Celsius, 60 degrees Celsius, and 62 degrees Celsius, which clearly reflects the temperature change. If an early warning is triggered, the moving average method is used to calculate the slope value of the most recent 10 temperature data to determine the temperature change trend.

[0317] Specifically, 10 data points are collected, such as 50 degrees Celsius to 62 degrees Celsius, and the average slope of the difference values ​​of adjacent points is calculated.

[0318] For example, a positive slope value indicates that the temperature continues to rise. This trend analysis helps predict potential risks.

[0319] It should be noted that the selection of 10 data points can balance real-time performance and stability. Inputting the slope value into the PID control algorithm and calculating the heat source power adjustment amount are the keys to dynamic regulation.

[0320] Preferably, the PID determines that the temperature rises too fast based on the slope and reduces the power output.

[0321] For example, when the current power is 100 watts and the algorithm calculates an adjustment amount of -20 watts, a new power value of 80 watts is obtained.

[0322] It can be understood that such adjustment can effectively prevent overheating.

[0323] In one embodiment, the PID parameters are pre-tuned according to the harness material to ensure rapid response. According to the adjusted power value, predicting the heating duration using the exponential smoothing method is an important step in optimizing the process.

[0324] For example, the new power is 80 watts, the original duration is 15 minutes, and the smoothing method predicts a corrected value of 13 minutes. This prediction is weighted based on historical data and can adapt to power changes.

[0325] Specifically, the smoothing coefficient can be set to 0.3, indicating that the weight of recent data is higher. Extracting the variance characteristics of the sleeve diameter from the power value and the corrected duration and determining whether it is less than 1 mm is the core of quality control.

[0326] Exemplarily, after processing with a power of 80 watts and a duration of 13 minutes, the measured sleeve diameters are 5.1 mm, 5.0 mm, and 5.2 mm, and the variance is less than 1 mm, meeting the requirements.

[0327] In one embodiment, excessive variance may cause local overheating due to uneven power. This inspection can detect problems in a timely manner. If the conditions are met, inputting the power and duration parameters into a finite element thermodynamics simulation tool and outputting the sleeve deformation data is a refined analysis method.

[0328] For example, when inputting 80 watts and 13 minutes, the simulation results show that the deformation amount is 0.05 mm and the deformation is uniform.

[0329] Preferably, the simulation tool can also simulate the heat flow distribution to help optimize the parameters.

[0330] It should be noted that this method can improve the reliability of the design. Adjusting the heat source power and heating duration according to the simulation results to stabilize the sleeve diameter variance within 1 mm is an embodiment of closed-loop optimization.

[0331] In one possible implementation, if the deformation is too large, the power is finely adjusted to 75 watts and the duration is increased to 14 minutes. After adjustment, the measured diameter variance is 0.8 mm, and the stability is improved.

[0332] It can be understood that such iterative adjustment can ensure processing consistency and reduce the scrap rate.

[0333] S8, obtain the heat shrinkage effect data after the final process parameters are executed, detect the change trend of the shape of the harness end through three-dimensional scanning technology, and determine whether the process consistency meets the preset standard.

[0334] Optionally, this step further includes: Step S81: Obtain the heat shrinkage effect data after the process parameters are executed from the device through a sensor, and store it as an initial data set.

[0335] Step S82: Use three-dimensional scanning technology to scan the end of the wire harness in the initial data set to obtain shape feature point cloud data.

[0336] Step S83: Extract the contour information of the end of the wire harness from the shape feature point cloud data to determine the distribution characteristics of the shape change.

[0337] Step S84: Calculate the time series of the shape change according to the distribution characteristics to obtain a quantitative index of the change trend.

[0338] Step S85: If the difference between the quantitative index of the change trend and the preset standard is less than the quantization threshold, it is determined that the process consistency meets the requirements, and a consistency label is output.

[0339] Step S86: Train the consistency label and the initial data set through a random forest algorithm to obtain a mapping model between the process parameters and the heat shrinkage effect.

[0340] Step S87: Predict the heat shrinkage effect of the new process parameters for the mapping model, and determine whether the preset standard is met.

[0341] Specifically, obtaining the heat shrinkage effect data after the process parameters are executed from the device through a sensor and storing it as an initial data set is the basis for subsequent analysis.

[0342] For example, the sensor can be an infrared thermometer, which is arranged in the heat shrinkable sleeve processing area to collect temperature distribution data.

[0343] Exemplarily, after a certain processing, the surface temperatures of the sleeve are recorded as 55 degrees Celsius, 58 degrees Celsius, and 54 degrees Celsius to form an initial data set. This method can comprehensively reflect the actual situation of the heat shrinkage effect.

[0344] It should be noted that the storage of data can be sorted by time stamp for subsequent processing. Using three-dimensional scanning technology to scan the end of the wire harness in the initial data set to obtain shape feature point cloud data can visually present the geometric features after processing.

[0345] Specifically, a laser scanner is used to perform a full-range scan of the end of the wire harness to generate point cloud data containing thousands of coordinate points.

[0346] In a possible implementation, the scanning resolution is set to 0.1 mm to ensure capturing subtle shape changes.

[0347] Exemplarily, the scanning result shows that the point cloud at the edge of the wire harness end is dense, and the center is slightly sparse. This technology can provide a high-precision basis for shape analysis. Extracting the contour information of the wire harness end from the shape feature point cloud data and determining the distribution characteristics of shape changes are the key steps to quantify the heat shrinkage effect.

[0348] Preferably, the contour line can be extracted by an edge detection algorithm.

[0349] For example, after processing the point cloud data, the contour shows that the diameter of the sleeve changes from 6 mm to 5 mm after shrinkage, and the distribution characteristic is that the edge is smooth.

[0350] It can be understood that this analysis can reflect the uniformity of heat shrinkage and provide a basis for subsequent judgment. Calculating the time series of shape changes according to the distribution characteristics and obtaining a quantitative index of the change trend can dynamically monitor the processing process.

[0351] In one embodiment, the contour data of 5 consecutive scans are recorded, such as the diameter gradually changing from 6 mm to 5.2 mm and 5.1 mm, and the trend index of the time series is calculated.

[0352] Exemplarily, the trend shows a gentle decline. This quantification method helps to capture the change law. If the difference between the quantitative index of the change trend and the preset standard is less than the quantification threshold, it is determined that the process consistency meets the requirements, and a consistency label is output.

[0353] For example, the preset standard is that the diameter change rate is less than 0.2 mm, the actual index is 0.15 mm, and the difference is within the quantification threshold of 0.05 mm, which is marked as "consistent".

[0354] Specifically, this judgment can quickly screen qualified processes.

[0355] It should be noted that the quantification threshold can be adjusted according to the material to improve flexibility. Training the consistency label and the initial data set through the random forest algorithm to obtain a mapping model of process parameters and heat shrinkage effect is the core means of optimizing parameters.

[0356] In one possible implementation, by inputting data such as a temperature of 55 °C and a power of 90 W, the trained model can predict the heat shrinkage result.

[0357] Exemplarily, the model outputs a diameter change of 0.1 mm. This method can explore the deep relationship between parameters. Judging whether the heat shrinkage effect of the new process parameters predicted by the mapping model meets the preset standard is the verification link of process improvement.

[0358] For example, when the input power is 85 W, the predicted diameter change is 0.12 mm, which meets the requirement compared with the standard of 0.2 mm.

[0359] Preferably, such prediction can guide parameter adjustment and improve processing efficiency.

[0360] It can be understood that the application of the model can reduce the trial - and - error cost and ensure controllable results.

[0361] S9. According to the result of the shape change trend analysis, use the data fusion technology to iteratively optimize the temperature control model and the heat shrinkage effect data, and generate an intelligent monitoring database applicable to complex wire harness structures.

[0362] Optionally, this step further includes: Step S91. Obtain the trend analysis result through the shape change data, and use time - series analysis to determine the change pattern.

[0363] Step S92. Extract features from the trend analysis result, and use the weighted average method to integrate the temperature control parameters and the heat shrinkage effect data.

[0364] Step S93. For the fused data, apply the gradient descent method to adjust the temperature control model to obtain an optimized parameter set.

[0365] Step S94. If the optimized parameter set meets the optimization threshold, generate a model applicable to complex wire harness structures and judge its applicability.

[0366] Step S95. According to the structural characteristics of the complex wire harness, obtain the initial framework of the monitoring database and fill in the content through interpolation.

[0367] Step S96. Use the random forest algorithm to perform intelligent classification on the monitoring database to determine the key monitoring points.

[0368] Step S97. Through the data feedback of the key monitoring points, adjust the iterative process of the gradient descent method to obtain the final intelligent monitoring database.

[0369] Specifically, obtain the trend analysis result through the shape change data, and use time - series analysis to determine the change pattern.

[0370] It can be understood that time - series analysis can clearly present the law of the shape evolution of the wire harness end over time.

[0371] For example, continuously record the shape data of a certain wire harness end within 5 minutes after processing, and it is found that the diameter gradually decreases from 6 mm to 5.3 mm, showing a smooth downward pattern. This method deduces the future trend through historical data and lays a foundation for subsequent analysis.

[0372] Exemplarily, if the data points show a sudden acceleration in the change, it may indicate an abnormality in the processing process, and it is necessary to further check the equipment status. Extract features from the trend analysis result, and use the weighted average method to integrate the temperature control parameters and the heat shrinkage effect data.

[0373] Specifically, the weighted average method can balance the influence of different parameters.

[0374] For example, the temperature data are 55 degrees Celsius and 57 degrees Celsius respectively. A higher weight of 0.7 is assigned to the temperature, and a weight of 0.3 is assigned to the heat shrinkage effect data such as diameter change. After integration, a comprehensive eigenvalue is obtained. This way reflects the processing characteristics from multiple dimensions.

[0375] Preferably, if the temperature fluctuates greatly, the weight can be adjusted to highlight the stability factor, ensuring that the feature extraction is closer to the actual requirements. For the integrated data, the gradient descent method is applied to adjust the temperature control model to obtain an optimized parameter set.

[0376] In a possible implementation, the initial model sets the temperature to 60 degrees Celsius, but the integrated data shows that 55 degrees Celsius is more optimal. The gradient descent method adjusts to this value through multiple iterations.

[0377] Exemplarily, the adjusted parameter set may include a power of 88 watts and a time of 3 seconds. This optimization can improve the adaptability of the model to actual processing and reduce resource waste. If the optimized parameter set meets the preset optimization threshold, a model applicable to complex wire harness structures is generated to judge its applicability.

[0378] For example, the preset optimization threshold is that the diameter change is less than 0.2 mm, and the predicted value of the optimized parameter set is 0.18 mm. After meeting the requirements, a model is generated.

[0379] It should be noted that complex wire harnesses may involve multi-branch structures, and the model needs to verify its performance on different branches.

[0380] In one embodiment, the test shows that the shrinkage is uniform at the branch, proving the strong applicability of the model. This verification can ensure the reliability of the process in diverse scenarios. According to the structural characteristics of the complex wire harness, the initial framework of the monitoring database is obtained, and the content is filled by the interpolation method.

[0381] Specifically, the initial framework may only contain key node data, such as the end diameter. The interpolation method calculates the intermediate value through the existing data. For example, the diameters of two nodes are 5 mm and 5.2 mm respectively, and the intermediate value filled by interpolation is 5.1 mm. This method can quickly build a complete database to support subsequent monitoring. The random forest algorithm is used to classify the monitoring database intelligently to determine the key monitoring points.

[0382] In one embodiment, when inputting temperature, power, and shape data, the algorithm classifies the area where the temperature exceeds 58 degrees Celsius as the key point.

[0383] Exemplarily, during a certain analysis, it is found that the temperature of a certain node is on the high side and is marked as requiring key monitoring. This classification can accurately locate potential risk areas and improve the monitoring efficiency. Through the data feedback of key monitoring points, the iterative process of the gradient descent method is adjusted to obtain the final intelligent monitoring database.

[0384] For example, the monitoring point feedbacks that the temperature is on the high side, and the power is iteratively adjusted and reduced to 85 watts, and the optimization result is finally recorded in the database.

[0385] Preferably, the feedback data can also reveal long-term trends, such as continuous anomalies in a certain area requiring equipment maintenance.

[0386] It can be understood that this dynamic adjustment can continuously improve the database and support the continuous improvement of the process.

[0387] As Figure 2 shown, in the second aspect of the present invention, an intelligent processing system for heat-shrinkable sleeves at the end of a wire harness is provided. The heat-shrinkable sleeves at the end of the wire harness are intelligently processed by the method described above. The system mainly includes: A data acquisition module, which is used to obtain the structural data of the end of the wire harness and the material characteristic parameters, collect the geometric shape information of the end of the wire harness and the thermal conductivity data of the heat-shrinkable sleeve material through a scanning device, and determine the heat-shrinkage demand distribution of different regions at the end. A partition modeling module, which is used to generate a temperature control model by using a partition modeling algorithm according to the heat-shrinkage demand distribution of different regions at the end, divide the end of the wire harness into multiple independent temperature control regions, and obtain the target temperature curve of each region. A temperature control module, which is used to obtain real-time temperature output data from a heat source device through a preset temperature control model, dynamically adjust the heat source power for each temperature control region, and judge whether the temperature meets the requirements of the target temperature curve. A thermal imaging analysis module, which is used to obtain the infrared thermal imaging data of the end of the wire harness during the heat-shrinkage process, analyze the surface temperature distribution of the heat-shrinkable sleeve by using image processing technology, and determine whether there is local overheating or uneven shrinkage. A feedback adjustment module, which is used to adjust the heat source power of the corresponding region through a feedback control algorithm if the surface temperature distribution of the heat-shrinkable sleeve exceeds the preset temperature distribution threshold, recalculate the temperature output in combination with the material characteristic parameters, and obtain an optimized heating scheme. A damage monitoring module, which is used to collect the temperature data of the internal wires at the end of the wire harness by using a multi-point sensor according to the optimized heating scheme, judge whether the wires have a risk of damage due to overheating, and generate a real-time temperature warning signal. A parameter optimization module, which is used to drive an adaptive adjustment system through the real-time temperature warning signal, and fine-tune the heat source power and heating duration in combination with a dynamic adaptation algorithm to determine the final process parameters for uniform shrinkage of the heat-shrinkable sleeve. An effect detection module, which is used to obtain the heat shrinkage effect data after the execution of the final process parameters, detect the change trend of the shape of the wire harness end through three-dimensional scanning technology, and judge whether the process consistency reaches the preset standard; A database generation module, which is used to iteratively optimize the temperature control model and the heat shrinkage effect data by using data fusion technology according to the analysis result of the shape change trend, and generate an intelligent monitoring database applicable to complex wire harness structures.

[0388] The present invention provides an intelligent processing method and system for heat shrinkable sleeves at the end of a wire harness. The structure data and material property parameters of the wire harness end are collected by a scanning device, and a temperature control model is generated by combining a partition modeling algorithm. The wire harness end is divided into multiple independent temperature control regions. During the heat shrinkage process, infrared thermal imaging data is obtained in real time, the surface temperature distribution of the heat shrinkable sleeve is analyzed, and the heat source power and heating duration are dynamically adjusted according to the internal wire temperature data collected by a multi-point sensor.

[0389] The present invention can ensure uniform shrinkage of the heat shrinkable sleeve and avoid overheating damage to the wire through an adaptive adjustment system and a dynamic adaptation algorithm.

[0390] The present invention uses three-dimensional scanning technology to detect the change trend of the shape of the wire harness end, optimizes the temperature control model by using data fusion technology, generates an intelligent monitoring database applicable to complex wire harness structures, realizes precise control and intelligent supervision of the processing process of heat shrinkable sleeves at the end of the wire harness, and improves the quality and efficiency of wire harness processing.

[0391] The above are only the preferred embodiments of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the principle of the present invention, several improvements and supplements can still be made, and these improvements and supplements should also be regarded as the protection scope of the present invention.

Claims

1. A method for processing an intelligent heat shrink tubing at the end of a wiring harness, characterized in that: The method comprises: S1, obtaining the structural data and material characteristic parameters of the wire harness end, collecting the geometric shape information of the wire harness end and the thermal conductivity data of the heat shrink tubing material through a scanning device, and determining the heat shrink demand distribution of different areas of the end; S2, based on the heat shrinkage demand distribution in different areas of the end, a temperature control model is generated using a partition modeling algorithm to divide the wire harness end into multiple independent temperature control areas to obtain a target temperature curve for each area; S3, through the preset temperature control model, obtain the real-time temperature output data from the heat source equipment, dynamically adjust the heat source power for each temperature control area, and determine whether the temperature meets the target temperature curve requirements; S4, obtaining infrared thermal imaging data of the end of the wire harness during the heat shrinking process, and using image processing technology to analyze the surface temperature distribution of the heat shrink tubing to determine whether there is local overheating or uneven shrinkage; S5, if the surface temperature distribution of the heat shrink tubing exceeds the preset temperature distribution threshold, the heat source power of the corresponding area is adjusted through the feedback control algorithm, and the temperature output is recalculated in combination with the material characteristic parameters to obtain an optimized heating scheme; S6, according to the optimized heating scheme, a multi-point sensor is used to collect the temperature data of the wires inside the wire harness end, to determine whether the wires are at risk of damage due to overheating, and to generate a real-time temperature warning signal; S7, drives the adaptive adjustment system through real-time temperature warning signals, and fine-tunes the heat source power and heating time in combination with the dynamic adaptation algorithm to determine the final process parameters for uniform shrinkage of the heat shrink tubing; S8, obtaining the heat shrink effect data after the final process parameters are executed, detecting the shape change trend of the wire harness end by three-dimensional scanning technology, and judging whether the process consistency meets the preset standard; S9, based on the shape change trend analysis results, uses data fusion technology to iteratively optimize the temperature control model and heat shrink effect data to generate an intelligent monitoring database suitable for complex wiring harness structures.

2. The method according to claim 1, characterized in that: The step S1, obtaining the structure data and material characteristic parameters of the wire harness end, collecting the geometric shape information of the wire harness end and the thermal conductivity data of the heat shrink tubing material through a scanning device, and determining the heat shrink demand distribution of different areas of the end, includes: Step S11, collecting geometric shape data and structural information of the end of the wire harness by scanning equipment to obtain three-dimensional model data of the end area; Step S12, using a finite element analysis tool to extract thermal conductivity data of the heat shrink tubing for the three-dimensional model data, and determine the material property distribution; Step S13, extracting heat conduction parameters from the material property distribution to determine the difference in heat shrinkage requirements of the end regions; Step S14, if the difference in heat shrinkage requirements exceeds the difference threshold, partitioning the geometric shape data to obtain a regional distribution result; Step S15, according to the regional distribution result, a bilinear interpolation algorithm is used to calculate the continuous change trend of the heat shrinkage demand, and the optimized distribution parameters are determined; Step S16, obtaining a heat shrinkage coverage solution for the end structure through the optimized distribution parameters, and obtaining a final heat shrinkage demand distribution; Step S17, judging the heat shrink tubing thickness requirement of each area according to the final heat shrinkage requirement distribution, and determining an adjustment plan for the end structure.

3. The method according to claim 2, characterized in that In step S14, if the difference in heat shrinkage requirements exceeds the difference threshold, the geometric shape data is partitioned to obtain a regional distribution result, including: Step S141, by comparing the heat shrinkage demand with the demand threshold, determining whether the difference exceeds the limit, and obtaining a trigger condition determination result; Step S142, if the difference exceeds the difference threshold, extracting shape data from the geometric shape to obtain a data set to be processed; Step S143, using a grid division method to divide the shape data set into regions to obtain preliminary regional distribution data; Step S144, based on the preliminary regional distribution data, a bilinear interpolation algorithm is used to calculate the continuous change of demand judgment to obtain optimized distribution parameters; Step S145, extracting regional distribution features from the optimized distribution parameters to obtain final distribution result data; Step S146, judging the regional characteristics of heat shrinkage demand based on the final distribution result data, and determining adjustment scheme parameters; Step S147, by adjusting the scheme parameters, the distribution of the shape data is updated to obtain the processed data results.

4. The method according to claim 3, characterized in that: The step S16, obtaining the heat shrinkage coverage scheme of the end structure through the optimized distribution parameters to obtain the final heat shrinkage demand distribution, also includes: Step S161, obtaining thickness distribution data of the end structure as preliminary covering data by using preset initial thickness and shrinkage rate optimization parameters of the heat shrinkable material; Step S162, using the NumPy library to generate a rectangular grid with a spacing of 1 mm, extracting the heat shrinkable coverage thickness of each grid unit from the preliminary coverage data, and obtaining the heat shrinkable coverage range division result; Step S163, calculating the root mean square error between the range division result and the required thickness distribution, and determining the shrinkage rate corresponding to the minimum error as the matching parameter; Step S164, generating a thickness increase / decrease matrix according to the matching parameters to obtain adjusted solution data; Step S165, using the interp2d function of SciPy to perform bilinear interpolation on the adjusted solution data, calculate the thickness change gradient between the grid nodes, and obtain a continuous thickness field as a characteristic distribution result; Step S166, based on the characteristic distribution result, extract the area where the thickness gradient is greater than the thickness gradient threshold, mark it as the heat shrinkage requirement distribution area of ​​the end structure, and output it as the final coverage plan.

5. The method according to claim 4, characterized in that The step S17, judging the heat shrink tubing thickness requirements of each region according to the final heat shrinkage requirement distribution, and determining the adjustment plan of the end structure, includes: Step S171, using the heat shrinkage demand distribution data, removing noise by Gaussian filtering to obtain thickness characteristics of each region and generate thickness distribution data; Step S172, using percentile statistics method on thickness distribution data to obtain thickness range division results; Step S173, comparing the thickness range division result with the preset thickness standard interval, and calculating the overlapping area ratio as a matching parameter; Step S174, when the matching degree parameter is lower than the matching degree threshold, it is determined to be a region that needs to be adjusted; Step S175, determining the position coordinates where the end structure needs to be thickened or thinned based on the region coordinates where the matching parameter is lower than the matching threshold, and generating a preliminary adjustment plan including position marks; Step S176, using a bilinear interpolation algorithm, taking the adjustment position as the center point, calculating the thickness adjustment amount of the surrounding area according to the distance weight, and outputting a thickness adjustment trend distribution map; Step S177, in the trend distribution diagram, marking the area where the adjustment amount exceeds the preset thickness as the key adjustment area, and the rest as the auxiliary adjustment area; Step S178, merging all the marked area coordinates and the adjustment amount data to generate a final adjustment solution including specific size parameters; Step S179, outputting the end structure processing drawing data according to the coordinate-thickness mapping table in the final adjustment plan.

6. The method according to claim 1, characterized in that In step S5, if the surface temperature distribution of the heat shrink tubing exceeds a preset temperature distribution threshold, the heat source power of the corresponding area is adjusted by a feedback control algorithm, and the temperature output is recalculated in combination with the material characteristic parameters to obtain an optimized heating scheme, including: Step S51, if the maximum surface temperature exceeds the second temperature threshold, real-time temperature matrix data is acquired through an infrared sensor; Step S52, according to the difference between the maximum value in the temperature matrix and the second temperature threshold, a proportional integral algorithm is used to calculate the heat source power adjustment value, the algorithm parameters are obtained from the material thermal conductivity library, and a power adjustment scheme is obtained; Step S53, after executing the power adjustment scheme, collecting an updated temperature matrix from the thermocouple array; Step S54, extracting the maximum value in the temperature matrix, if it still exceeds the second temperature threshold, using the incremental PID algorithm for secondary adjustment, the PID parameters are set according to the material specific heat capacity library, and the power value after fine-tuning is output; Step S55, driving the heating tube to work according to the finely adjusted power value, and triggering a temperature acquisition instruction after the work is completed; Step S56, obtaining a temperature matrix in a stable state from the infrared sensor, and calculating the mean square error between the temperature of each area and the target value; Step S57, if the mean square error is greater than the allowable error, the moving average method is used to analyze the trend of the historical temperature data, and the power allocation ratio is corrected according to the trend slope; Step S58, controlling the operation of the heating tube array according to the corrected power ratio, and continuously collecting temperature matrix data during the operation; Step S59, extracting the highest temperature, the lowest temperature and the gradient change rate in the matrix as long-term optimization parameters and writing them into the control log.

7. The method according to claim 6, characterized in that The step S51, if the maximum surface temperature exceeds the second temperature threshold, acquires real-time temperature matrix data through an infrared sensor, and also includes: Step S511, if the surface temperature exceeds the second temperature threshold, collect real-time temperature matrix data through an infrared sensor to obtain a temperature matrix; Step S512, generating a temperature distribution map according to the temperature value of each pixel in the temperature matrix; Step S513, extracting the outermost 5-pixel width boundary area data from the temperature matrix to obtain a boundary temperature set; Step S514, using the Sobel operator to calculate the gradient value of each point of the lateral gradient and longitudinal gradient of the boundary temperature set to generate a gradient distribution; Step S515, if there is a data point in the gradient distribution whose standard deviation exceeds a preset multiple of the gradient mean, it is determined to be an outlier; Step S516, performing a convolution operation on the temperature matrix with abnormal values ​​to obtain a smoothed temperature matrix; Step S517, calculating the standard deviation of the temperature in each partition in the smoothed temperature matrix as the fluctuation characteristic of the area; Step S518, inputting the fluctuation characteristics of each partition into the PID controller, and adjusting the partition control parameters of the corresponding heating pipe according to the size of the standard deviation; Step S519, after the parameters are adjusted, the heating tube is driven to operate, and an updated temperature matrix is ​​obtained from the infrared sensor; Step S5110: When the standard deviation of the temperature matrix is ​​smaller than the standard temperature value for several consecutive times, it is determined to be a stable distribution.

8. The method according to claim 1, characterized in that: The step S8, obtaining the heat shrink effect data after the final process parameters are executed, detecting the shape change trend of the wire harness end by three-dimensional scanning technology, and judging whether the process consistency reaches the preset standard, includes: Step S81, obtaining heat shrinkage effect data after the process parameters are executed from the equipment through a sensor, and storing it as an initial data set; Step S82, using a three-dimensional scanning technology to scan the wire harness end in the initial data set to obtain shape feature point cloud data; Step S83, extracting the contour information of the wire harness end from the shape feature point cloud data, and determining the distribution characteristics of the shape change; Step S84, calculating the time series of shape changes according to the distribution characteristics to obtain a quantitative index of the change trend; Step S85, if the difference between the quantitative index of the change trend and the preset standard is less than the quantitative threshold, it is judged that the process consistency meets the requirements and a consistency label is output; Step S86, training the consistency labels and the initial data set by using a random forest algorithm to obtain a mapping model between process parameters and heat shrinkage effects; Step S87, predicting the heat shrinkage effect of the new process parameters based on the mapping model, and determining whether it meets the preset standards.

9. The method according to claim 1, characterized in that: The step S9, based on the shape change trend analysis result, uses data fusion technology to iteratively optimize the temperature control model and the heat shrink effect data to generate an intelligent monitoring database suitable for complex wiring harness structures, including: Step S91, obtaining trend analysis results through shape change data, and determining the change pattern by time series analysis; Step S92, extracting features from the trend analysis results, and integrating the temperature control parameters and the heat shrinkage effect data using a weighted average method; Step S93, applying the gradient descent method to the fused data to adjust the temperature control model to obtain an optimized parameter set; Step S94, if the optimized parameter set meets the optimization threshold, a model suitable for the complex wiring harness structure is generated to determine its applicability; Step S95, obtaining the initial framework of the monitoring database according to the structural characteristics of the complex wiring harness, and filling the content by interpolation; Step S96, using the random forest algorithm to intelligently classify the monitoring database and determine key monitoring points; Step S97, adjusting the iterative process of the gradient descent method through data feedback from key monitoring points to obtain the final intelligent monitoring database.

10. An intelligent wire harness end heat shrink tubing processing system, characterized in that: The method according to any one of claims 1 to 9 is used to perform intelligent processing on the heat shrink tubing at the end of the wiring harness, and the system comprises: The data acquisition module is used to obtain the structural data and material characteristic parameters of the wire harness end, collect the geometric shape information of the wire harness end and the thermal conductivity data of the heat shrink tubing material through the scanning device, and determine the heat shrink demand distribution in different areas of the end; The partition modeling module is used to generate a temperature control model based on the heat shrinkage demand distribution in different areas of the end using a partition modeling algorithm, divide the wire harness end into multiple independent temperature control areas, and obtain the target temperature curve of each area; The temperature control module is used to obtain real-time temperature output data from the heat source equipment through a preset temperature control model, dynamically adjust the heat source power for each temperature control area, and determine whether the temperature meets the target temperature curve requirements; Thermal imaging analysis module, used to obtain infrared thermal imaging data of the ends of the wire harness during the heat shrink process, and use image processing technology to analyze the surface temperature distribution of the heat shrink tubing to determine whether there is local overheating or uneven shrinkage; The feedback adjustment module is used to adjust the heat source power of the corresponding area through the feedback control algorithm if the surface temperature distribution of the heat shrink tubing exceeds the preset temperature distribution threshold, and recalculate the temperature output in combination with the material characteristic parameters to obtain an optimized heating scheme; The damage monitoring module is used to collect the temperature data of the wires inside the wire harness end using multi-point sensors according to the optimized heating scheme, determine whether the wires are at risk of damage due to overheating, and generate a real-time temperature warning signal; The parameter optimization module is used to drive the adaptive adjustment system through real-time temperature warning signals, and fine-tune the heat source power and heating time in combination with the dynamic adaptation algorithm to determine the final process parameters for uniform shrinkage of the heat shrink tubing; The effect detection module is used to obtain the heat shrink effect data after the final process parameters are executed, detect the shape change trend of the wire harness end through 3D scanning technology, and determine whether the process consistency meets the preset standard; The database generation module is used to iteratively optimize the temperature control model and heat shrink effect data based on the shape change trend analysis results, using data fusion technology to generate an intelligent monitoring database suitable for complex wiring harness structures.

Images