An intelligent wire harness production management system and method

Abstract

The present invention relates to the technical field of wire harness production, and specifically provides an intelligent wire harness production management system and method. The system includes a visual quality inspection module, an energy consumption efficiency optimization module, a production stability integration module, a life cycle analysis module, and an intelligent adjustment decision-making module. With the present invention, through real-time visual inspection, surface defects of wire harnesses can be accurately identified, greatly reducing the reliance on manual inspection, effectively reducing inspection errors, and improving the speed and accuracy of inspection. Through real-time data analysis of the production cycle and energy consumption, the system automatically adjusts to the optimal production cycle, improving the energy utilization efficiency of the equipment and optimizing the production process. Through in-depth analysis of production stability and life cycle data, potential equipment failures and maintenance requirements can be predicted, and interventions can be made in advance to avoid production interruptions, thereby extending the service life of the equipment and reducing maintenance costs. While improving production efficiency and product quality, the production management of wire harnesses becomes more efficient.

Description

Technical Field

[0001] The present invention relates to the technical field of wire harness production, and particularly to an intelligent wire harness production management system and method. Background Art

[0002] The wire harness production field involves the design, manufacturing, and testing of wire harnesses. A wire harness is an aggregate of multiple wires used to transmit electricity and signals in complex systems such as automobiles, airplanes, and household appliances. These wires are subjected to specific bundling and protection to meet various mechanical, environmental, and electrical requirements. The key aspects of wire harness production technology include precise circuit design, automated cutting, terminal installation, quality inspection, and final assembly.

[0003] Among them, an intelligent wire harness production management system is a system integrating data processing and automation technologies, mainly used to improve the efficiency and quality of wire harness production. This system can automatically adjust the operations on the production line to adapt to changes in production requirements and optimize the production process. It can also implement functions such as resource management, predictive maintenance, and quality control, aiming to reduce human errors in the production process, shorten the production cycle, improve product quality, and achieve the goal of cost reduction.

[0004] The existing technologies rely on post-production inspections or intermittent reviews, resulting in an extended production cycle and an increased scrap rate. There is a lack of the ability to dynamically optimize production tempo and energy consumption, often leading to problems such as energy waste and inconsistent production efficiency. In addition, the existing technologies do not integrate effective equipment failure prediction and maintenance requirement analysis, which easily leads to sudden shutdowns and production interruptions, not only affecting the stability of the production plan but also easily causing high emergency repair costs, making the production management process of wire harnesses more difficult. Summary of the Invention

[0005] The purpose of the present invention is to solve the deficiencies existing in the prior art and to propose an intelligent wire harness production management system and method.

[0006] To achieve the above purpose, the present invention adopts the following technical solution: An intelligent wire harness production management system, the system includes:

[0007] The visual quality inspection module, based on key nodes of the production line, captures the surface image of the wire harness through a camera, analyzes the surface texture, color distribution, edge features, and reflectivity data of the wire harness, identifies abnormal areas on the surface of the wire harness, and generates a surface quality assessment log;

[0008] The energy consumption efficiency optimization module, based on the surface quality assessment log, analyzes the energy consumption data and production tempo data of the production line equipment, conducts a correlation analysis on the energy consumption fluctuation range and the mean value of the production tempo within the interval, identifies the optimal tempo configuration of energy consumption and production efficiency, and obtains the energy consumption tempo configuration parameters;

[0009] The production stability integration module collects raw material batch information, process parameters, and equipment operation status data based on the energy consumption beat configuration parameters, analyzes the correlation between the data, judges the stability of the production process, calculates the stability index of each production parameter, and obtains the production stability metric.

[0010] The life cycle analysis module analyzes the maintenance records and operating conditions of the finished wire harness according to the production stability metric, evaluates the failure incidence rate during the service life cycle, and predicts potential failure trends based on the correlation between the failure rate and production parameters, obtaining life prediction analysis data.

[0011] The improvement of the present invention is that the surface quality assessment log includes the uniformity level, the insulation layer integrity score, and the scratch depth index; the energy consumption beat configuration parameters include the energy consumption reduction ratio, the beat stability rating, and the efficiency improvement ratio; the production stability metric specifically refers to the material consistency level, the process stability score, and the equipment status index; the life prediction analysis data includes the failure probability assessment information, the component life prediction information, and the maintenance cycle extension situation.

[0012] The improvement of the present invention is that the visual quality detection module includes:

[0013] The image capture sub-module, based on the key nodes of the production line, collects the wire harness surface texture, color distribution, edge features, and reflectivity data through camera equipment, preprocesses the image data, adjusts the exposure value and contrast, and generates standardized image data.

[0014] The surface feature calculation sub-module quantifies and calculates the surface color distribution uniformity, edge gradient change rate, and reflectivity offset based on the standardized image data, using the formula:

[0015] ;

[0016] Obtain the surface consistency index , where is the total number of calculation points, is the color deviation of the -th point, is the gradient deviation of the -th point, is the reflectivity deviation of the -th point;

[0017] The quality assessment sub-module, based on the surface consistency index, compares it with the quality benchmark, identifies the abnormal areas on the wire harness surface, marks their coordinate ranges, and generates a surface quality assessment log.

[0018] The improvement of the present invention is that the energy consumption efficiency optimization module includes:

[0019] Based on the surface quality assessment log, the production rhythm data calculation sub-module analyzes the production rhythm data of the production line equipment, calculates the mean and variance of the rhythm, screens the degree of rhythm fluctuation within the cycle, determines the rhythm interval with low fluctuation, and generates a stable rhythm interval.

[0020] Based on the stable rhythm interval, the energy consumption fluctuation analysis sub-module obtains the equipment energy consumption data for the corresponding time period, conducts a correlation analysis of the energy consumption fluctuation and the rhythm mean, and uses the formula:

[0021] ;

[0022] Obtain the energy consumption-rhythm correlation coefficient , where is the energy consumption value at the th moment, is the rhythm value at the th moment, and are respectively the mean and standard deviation of the energy consumption, and are respectively the mean and standard deviation of the rhythm, is the total number of time points;

[0023] Based on the energy consumption-rhythm correlation coefficient, the rhythm configuration optimization sub-module identifies the rhythm interval with the optimal energy consumption and production efficiency, and extracts the rhythm configuration parameters of this interval to obtain the energy consumption-rhythm configuration parameters.

[0024] The improvement of the present invention is that the production stability integration module includes:

[0025] Based on the energy consumption-rhythm configuration parameters, the raw material adaptability sub-module collects the batch information of the wire harness raw materials, analyzes the differences between the attributes of different batches, compares with the historical stable production data, judges the adaptability of the raw material batches, and obtains the batch adaptability data;

[0026] The process deviation calculation sub-module calls the batch adaptability data, collects the wire harness process parameters, analyzes the deviation degree of each process parameter from the optimal process parameter, and uses the formula:

[0027] ;

[0028] Obtain the process parameter deviation index , where represents the th process parameter, represents the optimal process parameter reference value, represents the influence weight of the th process parameter, represents the total number of parameters;

[0029] The stability measurement sub-module calls the process parameter deviation index, obtains the operation status data of the production line equipment, analyzes the adaptability between the equipment status and the process parameters, judges the stability of the production process, and obtains the production stability measurement value.

[0030] The improvement of the present invention is that the life cycle analysis module includes:

[0031] The stability analysis sub-module analyzes the maintenance records and working conditions of the finished wire harness according to the production stability measurement, evaluates the maintenance cycle and the rate of change of the working conditions, screens the wire harness data with stability lower than the benchmark, and obtains the working condition stability screening result;

[0032] The fault evaluation sub-module, based on the working condition stability screening result, extracts the fault occurrence time series, calculates the fault occurrence frequency per unit time, analyzes the correlation between the fault occurrence frequency and the production parameters, and uses the formula:

[0033] ;

[0034] Obtain the fault incidence distribution, where, represents the average failure rate per unit time, represents the th observed fault occurrence frequency, represents the th expected fault frequency corresponding to the production parameters, represents the number of observations;

[0035] The life prediction sub-module calls the fault incidence distribution, calculates the change trend of the failure rate in the differential time interval, identifies the time interval where the increase rate of the failure rate exceeds the threshold, establishes the life decay curve, and obtains the life prediction analysis data.

[0036] The improvement of the present invention is that the system further includes:

[0037] The intelligent adjustment decision module analyzes the production adjustment direction based on the life prediction analysis data, re-adjusts the wire harness process parameters, predicts the equipment energy consumption and product quality after adjustment, updates the production management settings, and obtains the wire harness management adjustment result;

[0038] The wire harness management adjustment result is specifically the parameter adjustment range, the expected improvement in energy consumption, and the expected quality improvement.

[0039] The improvement of the present invention is that the intelligent adjustment decision module includes:

[0040] The adjustment direction analysis sub-module analyzes the production adjustment direction based on the life prediction analysis data, calculates the equipment operation stability under the current working conditions, and judges the range of change of the key parameters required for production adjustment, and obtains the production adjustment direction data;

[0041] The parameter optimization sub-module calls the production adjustment direction data, analyzes the matching degree of different process parameter combinations to the production adjustment direction, and uses the formula:

[0042] ;

[0043] Calculate the adaptability score under the parameter combination, and obtain the optimized configuration of process parameters. Among them, is the influence value of the th group of process parameters on the equipment life prediction, is the adaptability of the th group of parameters to the production adjustment direction, is the equipment energy consumption of the th group of parameter combinations, is the equipment energy consumption benchmark value, represents the total number of parameters;

[0044] The energy consumption and quality prediction sub-module calls the optimized configuration of the process parameters, combines the equipment energy consumption and product quality data, predicts the impact of the adjusted wire harness process parameters on production efficiency and product quality, updates the production management settings, and obtains the wire harness management adjustment result.

[0045] An intelligent wire harness production management method, which is executed based on the above intelligent wire harness production management system, includes the following steps:

[0046] S1: Based on the key nodes of the production line, capture the surface image of the wire harness through a camera, analyze the surface texture, color distribution, edge features and reflectivity data of the wire harness, judge the surface uniformity, scratch depth and insulation layer integrity, identify the abnormal areas on the wire harness surface, and generate a surface quality assessment log;

[0047] S2: Based on the surface quality assessment log, analyze the energy consumption data and production beat data of the production line equipment, screen the beat intervals with low fluctuations within the cycle, and conduct a correlation analysis on the energy consumption fluctuation range and the average production beat within the interval to identify the optimal beat configuration of energy consumption and production efficiency, and obtain the energy consumption beat configuration parameters;

[0048] S3: Based on the energy consumption beat configuration parameters, collect the raw material batch information, process parameters and equipment operation status data, judge the stability of the production process, and calculate the stability index of each production parameter to obtain the production stability metric;

[0049] S4: According to the production stability metric, analyze the maintenance records and working conditions of the finished wire harness, evaluate the failure rate within the service life cycle, and predict the potential failure trend to obtain the life prediction analysis data;

[0050] S5: Analyze the production adjustment direction based on the life prediction analysis data, readjust the harness process parameters, predict the energy consumption of the equipment and the product quality after adjustment, update the production management settings, and obtain the harness management adjustment result.

[0051] Compared with the prior art, the advantages and positive effects of the present invention are as follows:

[0052] In the present invention, through real-time visual inspection, surface defects of the harness can be accurately identified, greatly reducing the reliance on manual inspection, effectively reducing detection errors and improving the speed and accuracy of detection. Through real-time data analysis of the beat and energy consumption, the system automatically adjusts to the optimal production beat, improving the energy use efficiency of the equipment and optimizing the production process. Through in-depth analysis of production stability and life cycle data, potential equipment failures and maintenance requirements can be predicted, and intervention can be carried out in advance to avoid production interruptions, thereby extending the service life of the equipment and reducing maintenance costs. While improving production efficiency and product quality, the production management of the harness is made more efficient. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1 It is a module diagram of an intelligent harness production management system proposed by the present invention;

[0054] Figure 2 It is a flow chart of the visual quality inspection module in the present invention;

[0055] Figure 3 It is a flow chart of the energy consumption efficiency optimization module in the present invention;

[0056] Figure 4 It is a flow chart of the production stability integration module in the present invention;

[0057] Figure 5 It is a flow chart of the life cycle analysis module in the present invention;

[0058] Figure 6 It is a flow chart of the intelligent adjustment decision module in the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0059] In order to make the objectives, technical solutions and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0060] In the description of the present invention, it should be understood that the orientation or positional relationship indicated by terms such as "length", "width", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. is based on the orientation or positional relationship shown in the drawings. It is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation to the present invention. In addition, in the description of the present invention, the meaning of "a plurality of" is two or more, unless otherwise specifically defined.

[0061] Embodiment: Please refer to Figure 1 , the present invention provides a technical solution: An intelligent wire harness production management system includes:

[0062] The visual quality inspection module is based on the key nodes of the production line. It captures the surface images of the wire harness through a camera, analyzes the surface texture, color distribution, edge features, and reflectivity data of the wire harness, judges the surface uniformity, scratch depth, and insulation layer integrity, and compares them with the quality benchmark to identify the abnormal areas on the surface of the wire harness and generate a surface quality assessment log;

[0063] The energy consumption efficiency optimization module is based on the surface quality assessment log. It analyzes the energy consumption data and production rhythm data of the production line equipment. By calculating the mean and variance of the rhythm, it screens the rhythm intervals with low fluctuations within the cycle, and conducts a correlation analysis on the energy consumption fluctuation range and the production rhythm mean within the interval to identify the optimal rhythm configuration of energy consumption and production efficiency and obtain the energy consumption rhythm configuration parameters;

[0064] The production stability integration module is based on the energy consumption rhythm configuration parameters. It collects the raw material batch information, process parameters, and equipment operation status data, analyzes the correlation between the data, judges the stability of the production process, calculates the stability index of each production parameter, determines the optimal production conditions, and obtains the production stability metric;

[0065] The life cycle analysis module analyzes the maintenance records and operating conditions of the finished wire harness according to the production stability metric, evaluates the failure rate within the service life cycle, and predicts the potential failure trend based on the correlation between the failure rate and the production parameters to obtain the life prediction analysis data;

[0066] The intelligent adjustment decision module analyzes the production adjustment direction based on the life prediction analysis data, re-adjusts the wire harness process parameters, predicts the equipment energy consumption and product quality after adjustment, updates the production management settings, and obtains the wire harness management adjustment result.

[0067] The production cycle / cycle time specifically refers to the interval time between the continuous completion of two identical products (or two services, or two batches of products), that is, the average time required to complete one product. Cycle time is usually used to define the unit output time of a specific process or link in a process.

[0068] The key nodes of the production line refer to the specific positions or stages that have the greatest impact on the entire production process, which are the production line stages or positions that potentially affect product quality and are monitored at these points.

[0069] The surface quality assessment log includes the uniformity level, the insulation layer integrity score, and the scratch depth index. The energy consumption cycle configuration parameters include the energy consumption reduction ratio, the cycle stability rating, and the efficiency improvement ratio. The production stability metric specifically refers to the material consistency level, the process stability score, and the equipment status index. The life prediction analysis data includes the failure probability assessment information, the component life prediction information, and the extended maintenance cycle. The results of the harness management adjustment are specifically the parameter adjustment range, the expected improvement in energy consumption, and the expected quality improvement.

[0070] Please refer to Figure 2 , the visual quality inspection module includes:

[0071] The image capture sub-module is based on the key nodes of the production line and collects data on the surface texture, color distribution, edge features, and reflectivity of the harness through camera equipment. It preprocesses the image data, adjusts the exposure value and contrast, and generates standardized image data;

[0072] Determine the shooting parameters of the camera, including shutter speed, exposure value, and focal length, to ensure the clarity and stability of the imaging. For example, set the shutter speed to 1 / 500 second, the exposure value EV to 0.3, and the focal length fixed at 25mm to ensure that the acquired images do not appear blurred. At the same time, use the high dynamic range (HDR) mode to process the reflective areas to prevent saturation problems caused by excessive reflectivity. The acquired image data will be stored in a standard format, such as the RAW format, to ensure that image details are not lost, and then preprocessing will be performed. The preprocessing mainly includes color correction, edge sharpening, and contrast enhancement. The color correction uses the gray world algorithm to keep the image colors consistent. For example, for an area with a red reference value (RGB: 200, 50, 50), if the color value in the captured image shifts to (RGB: 180, 45, 40), then adjust the parameters through color gain to correct it to the reference value. Edge sharpening enhances the clarity of the image edges through Laplacian filtering so that the edge morphology of the wire harness can be detected more accurately during the subsequent feature extraction process. The contrast adjustment uses the histogram equalization method to enhance the sense of hierarchy of the image and make the color distribution more uniform for subsequent color distribution calculations. For example, if the overall brightness of the image is concentrated in the gray range of 0 - 120, then adjust it to 0 - 255 through histogram stretching to make the bright and dark areas evenly distributed. The preprocessed image data is normalized to generate normalized image data.

[0073] The surface feature calculation sub-module quantifies and calculates the surface color distribution uniformity, edge gradient change rate, and reflectivity offset based on the normalized image data, using the formula:

[0074] ;

[0075] Obtain the surface consistency index , where is the total number of calculation points, representing the total number of pixel points selected on the wire harness surface for analysis, is the color deviation of the th point, indicating the difference between the color of this point and the reference color, is the gradient deviation of the th point, indicating the difference between the gradient of the edge feature of this point and the reference gradient, is the reflectivity deviation of the th point, indicating the difference between the reflectivity of this point and the reference reflectivity;

[0076] If there are 3 different data points: , and , substitute them into the formula to calculate point 1:

[0077] ;

[0078] For point 2:

[0079] ;

[0080] For point 3:

[0081] ;

[0082] Calculate :

[0083] ;

[0084] The result shows that the surface consistency index reflects the overall uniformity of the wire harness surface in the selected sample area. The higher this value, the greater the variations in color, edge gradient, and reflectivity, indicating more obvious deviations in surface features. If exceeds the quality benchmark, it indicates that there are surface abnormalities in this area.

[0085] The quality assessment sub-module compares the surface consistency index with the quality benchmark, identifies the abnormal areas on the wire harness surface, marks their coordinate ranges, and generates a surface quality assessment log;

[0086] Call the calculation result of the surface consistency index , and set the quality benchmark threshold. For example, the benchmark . If the of a certain area is lower than this benchmark value, it is determined that there are quality problems in this area. Assume that in a certain area, the calculated is lower than the benchmark value , then this area is determined as an abnormal area, and its abnormal nature is further analyzed. If the color deviation exceeds the set threshold (such as exceeding 15), it is classified as a color abnormality. If the gradient deviation exceeds the set threshold (such as exceeding 0.6), it is classified as an edge damage. If the reflectivity deviation exceeds the threshold (such as exceeding 0.1), it is classified as a reflectivity abnormality. For each abnormal area, record its coordinate information. For example, if the center coordinates of an abnormal area are (250, 180), mark its coordinates in the log and attach the abnormal category to generate a surface quality assessment log.

[0087] Please refer to Figure 3 , the energy consumption efficiency optimization module includes:

[0088] Based on the surface quality assessment log, the production beat data calculation sub-module analyzes the production beat data of the production line equipment, calculates the mean and variance of the beats, screens the degree of beat fluctuations within the cycle, determines the beat intervals with low fluctuations, and generates stable beat intervals;

[0089] Obtain the production cycle time data of the production line equipment. The acquisition of production cycle time data usually comes from the production timestamp information recorded by the PLC (Programmable Logic Controller). For example, within a production cycle, record the timestamps of each product passing through a certain key node, and calculate the time intervals between adjacent products to obtain the production cycle time data. Suppose a production line produces 30 products in 10 minutes, then the average production cycle time is 10 minutes ÷ 30 = 20 seconds per piece. After obtaining all the production cycle time data, calculate the mean and variance of the cycle times. The mean calculation method is the arithmetic mean of all the production cycle time data, and the variance calculation method is the average of the squares of the differences between all the production cycle time data and the mean. For example, suppose the cycle time data within a certain production cycle is {19, 20, 21, 18, 22} seconds, then the mean calculation is as follows: ; and the variance calculation is as follows: ; Then, screen the degree of cycle time fluctuation within the cycle, and judge whether the fluctuation within a certain cycle time interval is low. Usually, the standard deviation is used as the measurement index. Set a certain threshold. If the standard deviation is less than the threshold, it is considered that the cycle time interval has low fluctuation. Suppose the fluctuation threshold is 2.5 seconds, then if the calculated standard deviation is 1.41 seconds (the standard deviation is the square root of the variance), then this interval can be selected into the stable cycle time interval to obtain the cycle time interval data that meets the fluctuation requirements.

[0090] The energy consumption fluctuation analysis sub-module, based on the stable cycle time interval, obtains the equipment energy consumption data for the corresponding time period, and conducts an analysis of the correlation between energy consumption fluctuation and the cycle time mean, using the formula:

[0091] ;

[0092] Obtain the energy consumption-cycle time correlation coefficient , where is the energy consumption value at the th moment, representing the energy consumption measurement at a specific time point, is the cycle time value at the th moment, representing the production cycle time measurement at a specific time point, and are respectively the mean and standard deviation of the energy consumption, used to calculate from all the measured energy consumption data and used to measure the magnitude of the energy consumption value fluctuation, and are respectively the mean and standard deviation of the cycle time, used to calculate from all the measured production cycle time data and used to measure the magnitude of the production cycle time fluctuation, is the total number of time points;

[0093] Obtain the equipment energy consumption data for the corresponding time period. The energy consumption data is usually collected by smart meters or energy monitoring systems. For example, the energy consumption data of equipment on the production line within different beat intervals can be collected by sensors. Suppose the energy consumption data of a certain production equipment within a 5-minute beat interval is 2.5, 2.6, 2.4, 2.7, and 2.5 kWh, then the calculation of the average energy consumption is as follows:

[0094] ;

[0095] Then calculate the standard deviation of the energy consumption data:

[0096] ;

[0097] Similarly, calculate the average production beat and standard deviation of this interval. If the beat data is {19, 20, 21, 18, 22} seconds, then: , ;

[0098] Then substitute the parameters into the formula to calculate the energy consumption-beat correlation coefficient EG:

[0099] ;

[0100] ;

[0101] Obtain the energy consumption-beat correlation coefficient , which indicates that within this beat interval, there is a negative correlation between energy consumption and beat changes, that is, when the production beat increases, the energy consumption will slightly decrease.

[0102] Based on the energy consumption-beat correlation coefficient, the beat configuration optimization sub-module identifies the beat interval with the optimal energy consumption and production efficiency, and extracts the beat configuration parameters of this interval to obtain the energy consumption-beat configuration parameters;

[0103] If the energy consumption-beat correlation coefficient is high, it indicates that the beat has a strong influence on energy consumption, and the beat parameters can be further optimized. If the value range of the energy consumption-beat correlation coefficient EG of a certain production line is [-1, 1], when EG approaches 1, it indicates that the energy consumption increases when the beat increases, and when EG approaches -1, it indicates that the energy consumption decreases when the beat increases. At this time, the beat interval with a larger negative value of EG should be preferentially selected. For example, as calculated above , then this beat interval is a better choice. By extracting the average beat and fluctuation range of this interval, parameters with the lowest energy consumption and stable beat are set. For example, assume that within this interval, the average beat is 20 seconds and the fluctuation range is ±2 seconds, then the beat configuration parameter can be taken as 20 seconds / unit (fluctuation range ±2 seconds) to obtain the energy consumption-beat configuration parameters.

[0104] Please refer to Figure 4 , the production stability integration module includes:

[0105] The raw material adaptability sub-module configures parameters based on the energy consumption beat, collects the information of the wire harness raw material batches, analyzes the differences between the attributes of different batches, compares with the historical stable production data, judges the adaptability of the raw material batches, and obtains the batch adaptability data;

[0106] Collect the batch information of the wire harness raw materials, classify the collected data by batches, and record the key attributes such as the composition content, particle size distribution, and humidity of each batch of raw materials. Use sensors to measure the raw material attribute parameters. For example, the particle size distribution can be measured by a laser particle size analyzer, the composition content can be analyzed by an X-ray fluorescence spectrometer, and the humidity can be obtained by an infrared moisture analyzer. For the raw materials of the same batch, multiple measurements are required and the average value is taken to reduce the measurement error. After obtaining the raw material data of each batch, calculate the attributes of the raw materials of different batches, and calculate the difference degree between the attributes of different batches of raw materials through the Euclidean distance formula. The calculation formula is as follows: , where represents the difference in raw material attributes between the th batch and the th batch, and respectively represent the th and th values of the th attribute of the th batch and the

[0107] For the historical stable production data, extract the stable batches and calculate the difference degree between them and the current batch. If the difference degree is lower than the set threshold, it is determined that the adaptability of this batch is good, otherwise the adaptability is determined to be low. This adaptability data can be used for subsequent process parameter adjustment to obtain the batch adaptability data.

[0107] The process deviation calculation sub-module calls the batch adaptability data, collects the wire harness process parameters, analyzes the deviation degree of each process parameter from the optimal process parameter, and uses the formula:

[0108] ;

[0109] Obtain the process parameter deviation index , where represents the th process parameter, represents the optimal process parameter reference value, represents the influence weight of the th process parameter, represents the total number of parameters;

[0110] In historical data, the optimal temperature is usually maintained at 170 °C, the pressure at 75 MPa, and the stirring rate at 320 rpm. Real-time monitoring is carried out on the data of the current production batch. Suppose at a certain moment, the measured temperature is 180 °C, the pressure is 80 MPa, and the measured stirring rate is 300 rpm. Assume that the weights of all process parameters are equal, that is, each weight is 0.3. Compare and calculate the actual monitored data with the optimal values:

[0111] For temperature: the difference , for pressure: the difference , for stirring rate: the difference . Apply the difference values to the formula and calculate:

[0112] ;

[0113] The deviation index of the current process parameters from the optimal parameters is 52.5. The result is relatively high, indicating that there is a large deviation between the current production state and the optimal process parameters. This value can be used to further analyze the need for process adjustment or predicted production problems, so as to adjust production parameters in a timely manner to achieve more stable production efficiency.

[0114] The stability metric sub-module calls the process parameter deviation index, obtains the operation status data of the production line equipment, analyzes the fitness of the equipment status and process parameters, judges the stability of the production process, and obtains the production stability metric value;

[0115] Normalize the equipment status data to make it have the same numerical scale as the process parameters, and calculate the fitness of the equipment status and process parameters. Specifically, the change trend of the equipment power consumption with the adjustment of process parameters can be calculated. For example, when the temperature rises, if the increase in power consumption is small, it indicates that the fitness of the process parameters and the equipment status is high, otherwise it is low. To further quantify the fitness, calculate the correlation coefficient between the process parameter deviation index and the change in the equipment operation status. If the correlation coefficient is within the range of [0.8, 1], the production process is considered stable. If it is between [0.5, 0.8], the production process is considered to have fluctuations. If it is below 0.5, the production process is considered unstable. Through the above judgment, the production stability metric value is obtained.

[0116] Please refer to Figure 5 , the life cycle analysis module includes:

[0117] The stability analysis sub-module analyzes the maintenance records and working conditions of the finished product wire harness according to the production stability metric, evaluates the maintenance cycle and the rate of change of working conditions, screens the wire harness data with stability lower than the benchmark, and obtains the working condition stability screening result;

[0118] Calculate the average value of the maintenance cycle and the mean square deviation of the working condition change rate to ensure the data accuracy of the maintenance cycle and the working condition change. For example, in Workshop A, the maintenance records show that in the past year, the intervals between each maintenance are 40 days, 45 days, 38 days, and 42 days. Calculate the average value to be 41.25 days. The mean square deviation of the maintenance cycle reflects the variability of the maintenance interval. Further, based on the maintenance cycle and the working condition change rate data, screen out the harness data whose stability is lower than the industry benchmark (such as the average maintenance cycle is less than 35 days or more than 50 days). This data can be used for further quality control and improvement strategies to obtain the screening results of the working condition stability.

[0119] Based on the screening results of the working condition stability, the fault assessment sub-module extracts the fault occurrence time series, calculates the fault occurrence frequency per unit time, and analyzes the correlation between the fault occurrence frequency and the production parameters. Use the formula:

[0120] ;

[0121] Obtain the fault incidence distribution, where represents the average fault rate per unit time, represents the th observed fault occurrence frequency, represents the th expected fault frequency corresponding to the production parameter, represents the number of observations;

[0122] In the records of the past year, if the number of faults and the number of production days per month are as follows:

[0123] 2 faults in January (20 production days), 3 faults in February (18 production days), 0 faults in March (22 production days), 5 faults in April (21 production days), 1 fault in May (23 production days), 4 faults in June (19 production days). Calculate the actual fault frequency for each month , using the formula ;

[0124] For January , for February , for March , for April , for May , for June ;

[0125] Then, use data analysis to analyze the correlation between the fault occurrence frequency and the production parameters. For each month are respectively: 0.1, 0.15, 0.05, 0.2, 0.09, and 0.18, and perform the calculation:

[0126] ;

[0127] The results show that, considering the production parameters, the actual failure occurrence frequency is on average about 82.3% higher than the expected value, which can help identify problems or conditions existing in the production process, thereby optimizing the production process and reducing the future failure rate.

[0128] The life prediction sub-module calls the failure rate distribution, calculates the change trend of the failure rate within different time intervals, identifies the time intervals where the increase in the failure rate exceeds the threshold, establishes a life decay curve, and obtains life prediction analysis data;

[0129] By analyzing the change trend of the failure rate, for example, when calculating the increase in the failure rate, if it is found that the failure rate has been continuously rising by more than 10% for three consecutive months, then mark this time interval as a high-risk period. Then identify those time intervals where the increase in the failure rate exceeds a preset threshold (such as 15%). For example, it is found from the data that the failure rate rises from 0.25 times per day to 0.4 times per day from May to July, with an increase rate of 60%, significantly exceeding the threshold, and define this period as a critical maintenance interval. Establish a life decay curve through the data to predict the remaining life of the equipment, so as to perform preventive maintenance before the equipment reaches the preset risk threshold and obtain life prediction analysis data.

[0130] Please refer to Figure 6 , the intelligent adjustment decision module includes:

[0131] The adjustment direction analysis sub-module analyzes the production adjustment direction based on the life prediction analysis data, calculates the operation stability of the equipment under the current working conditions, and determines the change range of the key parameters required for production adjustment, so as to obtain production adjustment direction data;

[0132] Extract the operation status data of the equipment under the current working conditions, which includes the workload, temperature, vibration frequency, historical maintenance records, etc. of the equipment. By calculating the standardized deviation of each parameter, determine the operation stability index of the equipment, and set the reference value as the average operation stability in the past six months to judge whether the current equipment is in a normal operation state. For example, if the deviation of the equipment vibration frequency is greater than 10%, it indicates that the equipment status is abnormal. Calculate the stability volatility of the equipment under different load conditions, and use the sliding window technique to segmentally analyze the operation fluctuation within 30 days to obtain the operation stability trend of the equipment. Compare the change rate of the stability trend. If the change rate exceeds the set threshold of 10%, it indicates that the production parameters need to be adjusted. Further combine the equipment load and production rhythm data to analyze the change range of the key parameters required for production adjustment. For example, if the equipment load is in a high-load state for a long time (>85%), the production rhythm needs to be reduced. If the fluctuation frequency of the equipment load exceeds 5Hz, the production scheduling strategy needs to be adjusted to obtain production adjustment direction data.

[0133] The parameter optimization sub-module calls the production adjustment direction data, analyzes the matching degree of different combinations of process parameters to the production adjustment direction, and uses the formula:

[0134] ;

[0135] Calculate the adaptability score under the parameter combination , and obtain the optimized configuration of process parameters. Among them, is the influence value of the th group of process parameters on the equipment life prediction, is the adaptability of the th group of parameters to the production adjustment direction, is the equipment energy consumption of the th group of parameter combinations, is the equipment energy consumption benchmark value, represents the total number of parameters;

[0136] Set the comparison group: different combinations of key process parameters such as temperature control, tension, and current load, and calculate the actual influence of each group of parameters. The influence is obtained through experimental data. For example, in a standardized production environment, when the temperature adjustment increases by 5°C, the operating efficiency of the equipment decreases by 0.5%, when the tension increases by 1 kN, the equipment maintenance frequency increases by 0.2%, and when the current load increases by 10 A, the energy consumption increases by 1 kW. Based on the data, calculate the adaptability score of the process parameter combination. If the total number of parameters is 3, there are the following data:

[0137] , and are 0.85, 0.78, and 0.80 respectively, representing the influence values on the life;

[0138] , and are 0.92, 0.89, and 0.91 respectively, representing the adaptability, which is a normalized weight coefficient, specifically reflecting how well this group of parameter combinations meets the requirements of the current production target and adjustment direction;

[0139] , and are 120 kW, 130 kW, and 125 kW respectively, representing the equipment energy consumption under different process parameter combinations;

[0140] , and are all set to 110 kW, the equipment energy consumption benchmark value.

[0141] Calculate the adaptability score according to the parameters as follows:

[0142] ;

[0143] ;

[0144] The result shows how to calculate the adaptability score of each process parameter combination based on experimental data and the requirements of production adjustment directions. This score can help determine the parameter configuration that best suits the current production needs.

[0145] The energy consumption and quality prediction sub-module calls the optimized configuration of process parameters, combines the equipment energy consumption and product quality data, predicts the impact of the adjusted harness process parameters on production efficiency and product quality, updates the production management settings, and obtains the harness management adjustment result;

[0146] Combining the equipment energy consumption and product quality data, first calculate the energy consumption change rate under the optimized parameters. For example, compare the energy consumption per unit time before and after optimization, set the reference value as the average energy consumption in the past 30 days, calculate the energy consumption volatility. If the volatility is lower than ±5%, it is considered that the optimized parameters are stable. At the same time, collect product quality indicators, including tensile strength, conductivity, yield, etc., and match them with the optimized parameters after normalization. For example, if the tensile strength is in the range of 180 - 200 MPa and the conductivity is in the range of 58 - 60 S / m, it is considered that the optimized parameters meet the quality standards. Finally, combined with the production stability analysis, update the production management settings to obtain the harness management adjustment result.

[0147] An intelligent harness production management method includes the following steps:

[0148] S1: Based on the key nodes of the production line, capture the surface image of the harness through a camera, analyze the surface texture, color distribution, edge features and reflectivity data of the harness, judge the surface uniformity, scratch depth and insulation layer integrity, identify the abnormal areas on the harness surface, and generate a surface quality assessment log;

[0149] S2: Based on the surface quality assessment log, analyze the energy consumption data and production beat data of the production line equipment, screen the beat intervals with low fluctuations within the cycle, and conduct a correlation analysis on the energy consumption fluctuation range and the production beat mean value within the interval to identify the optimal beat configuration of energy consumption and production efficiency, and obtain the energy consumption beat configuration parameters;

[0150] S3: Based on the energy consumption beat configuration parameters, collect the raw material batch information, process parameters and equipment operation status data, judge the stability of the production process, and calculate the stability index of each production parameter to obtain the production stability metric;

[0151] S4: Analyze the maintenance records and operating conditions of the finished wire harness according to the production stability metric, evaluate the failure incidence rate during the service life cycle, predict the potential failure trend, and obtain the life prediction analysis data;

[0152] S5: Based on the life prediction analysis data, analyze the production adjustment direction, readjust the wire harness process parameters, predict the equipment energy consumption and product quality after adjustment, update the production management settings, and obtain the wire harness management adjustment result.

[0153] The above is only a preferred embodiment of the present invention and does not limit the present invention in other forms. Any person skilled in the art may use the disclosed technical content to make changes or modifications into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change, and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution content of the present invention still fall within the protection scope of the technical solution of the present invention.

Claims

1. An intelligent wiring harness production management system, characterized in that, The system includes: The visual quality inspection module, based on the key nodes of the production line, captures the surface images of the wire harness through a camera, analyzes the surface texture, color distribution, edge features and reflectivity data of the wire harness, identifies the abnormal areas on the wire harness surface, and generates a surface quality assessment log; The energy consumption efficiency optimization module, based on the surface quality assessment log, analyzes the energy consumption data and production rhythm data of the production line equipment, conducts a correlation analysis on the energy consumption fluctuation range and the average production rhythm within the interval, identifies the optimal rhythm configuration of energy consumption and production efficiency, and obtains the energy consumption rhythm configuration parameters; The production stability integration module, based on the energy consumption rhythm configuration parameters, collects the raw material batch information, process parameters and equipment operation status data, analyzes the correlation between the data, judges the stability of the production process, and calculates the stability index of each production parameter to obtain the production stability metric; The life cycle analysis module, according to the production stability metric, analyzes the maintenance records and working conditions of the finished wire harness, evaluates the failure rate during the service life cycle, and predicts the potential failure trend based on the correlation between the failure rate and production parameters to obtain the life prediction analysis data.

2. The intelligent wire harness production management system according to claim 1, wherein The surface quality assessment log includes the uniformity level, the insulation layer integrity score, and the scratch depth index. The energy consumption rhythm configuration parameters include the energy consumption reduction ratio, the rhythm stability rating, and the efficiency improvement ratio. The production stability metric specifically refers to the material consistency level, the process stability score, and the equipment status index. The life prediction analysis data includes the failure probability assessment information, the component life prediction information, and the extended maintenance period situation.

3. The intelligent wire harness production management system according to claim 1, wherein, The visual quality inspection module includes: The image capture sub-module, based on the key nodes of the production line, collects the surface texture, color distribution, edge features and reflectivity data of the wire harness through the camera device, preprocesses the image data, adjusts the exposure value and contrast, and generates the standardized image data; The surface feature calculation sub-module, based on the standardized image data, quantitatively calculates the surface color distribution uniformity, the edge gradient change rate and the reflectivity offset amount, using the formula: ； Obtain the surface consistency index , where is the total number of calculation points, is the color deviation of the th point, is the gradient deviation of the th point, is the reflectance deviation of the th point; The quality assessment sub-module, based on the surface consistency index, compares it with the quality benchmark, identifies the abnormal areas on the wire harness surface, marks their coordinate ranges, and generates a surface quality assessment log.

4. The intelligent wire harness production management system according to claim 1, characterized in that, The energy consumption efficiency optimization module includes: The rhythm data calculation sub-module, based on the surface quality assessment log, analyzes the production rhythm data of the production line equipment, calculates the mean and variance of the rhythm, screens the degree of rhythm fluctuation within the period, determines the rhythm interval with low fluctuation, and generates a stable rhythm interval; The energy consumption fluctuation analysis sub-module, based on the stable rhythm interval, obtains the equipment energy consumption data for the corresponding time period, conducts a correlation analysis on the energy consumption fluctuation and the rhythm mean, using the formula: ； Obtain the energy consumption beat correlation coefficient EG, where, is the energy consumption value at the -th moment, is the beat value at the -th moment, and are the mean and standard deviation of the energy consumption respectively, and are the mean and standard deviation of the beat respectively, is the total number of time points; The rhythm configuration optimization sub-module, based on the energy consumption rhythm correlation coefficient, identifies the optimal rhythm interval of energy consumption and production efficiency, and extracts the rhythm configuration parameters of this interval to obtain the energy consumption rhythm configuration parameters.

5. The intelligent wire harness production management system according to claim 1, characterized in that, The production stability integration module includes: The raw material adaptability sub-module collects the batch information of the wire harness raw materials based on the energy consumption beat configuration parameters, analyzes the differences between the attributes of different batches, compares them with the historical stable production data, judges the adaptability of the raw material batches, and obtains the batch adaptability data; The process deviation calculation sub-module calls the batch adaptability data, collects the wire harness process parameters, analyzes the deviation degree of each process parameter from the optimal process parameter, and uses the formula: ； Obtain the process parameter deviation index , where represents the th process parameter, represents the optimal process parameter reference value, represents the influence weight of the th process parameter, represents the total number of parameters; The stability measurement sub-module calls the process parameter deviation index, obtains the operation status data of the production line equipment, analyzes the matching degree between the equipment status and the process parameters, judges the stability of the production process, and obtains the production stability measurement.

6. The intelligent wire harness production management system according to claim 1, characterized in that The life cycle analysis module includes: The stability analysis sub-module analyzes the maintenance records and working conditions of the finished wire harness according to the production stability measurement, evaluates the maintenance cycle and the rate of change of the working conditions, screens the wire harness data with stability lower than the benchmark, and obtains the working condition stability screening result; The fault assessment sub-module extracts the fault occurrence time series based on the working condition stability screening result, calculates the fault occurrence frequency per unit time, and analyzes the correlation between the fault occurrence frequency and the production parameters, using the formula: ； Obtain the failure rate distribution, where represents the average failure rate per unit time, represents the th observed failure occurrence frequency, represents the expected failure frequency corresponding to the production parameters at the th time, represents the number of observations; The life prediction sub-module calls the fault incidence distribution, calculates the change trend of the failure rate in different time intervals, identifies the time intervals where the increase rate of the failure rate exceeds the threshold, establishes a life decay curve, and obtains the life prediction analysis data.

7. The intelligent wire harness production management system according to claim 1, wherein The system further includes: The intelligent adjustment decision module analyzes the production adjustment direction based on the life prediction analysis data, re-adjusts the wire harness process parameters, predicts the equipment energy consumption and product quality after adjustment, updates the production management settings, and obtains the wire harness management adjustment result; The wire harness management adjustment result specifically includes the parameter adjustment range, the expected improvement in energy consumption, and the expected improvement in quality.

8. The intelligent wire harness production management system according to claim 7, wherein, The intelligent adjustment decision module includes: The adjustment direction analysis sub-module analyzes the production adjustment direction based on the life prediction analysis data, calculates the operation stability of the equipment under the current working condition, and judges the range of key parameter changes required for production adjustment, and obtains the production adjustment direction data; The parameter optimization sub-module calls the production adjustment direction data, analyzes the matching degree of different process parameter combinations to the production adjustment direction, using the formula: ； Calculate the adaptability score under the parameter combination , obtain the optimized configuration of process parameters, where is the influence value of the th group of process parameters on the equipment life prediction, is the adaptability of the th group of parameters to the production adjustment direction, is the equipment energy consumption of the th group of parameter combinations, is the equipment energy consumption reference value, represents the total number of parameters; The energy consumption and quality prediction sub-module calls the optimized configuration of the process parameters, combines the equipment energy consumption and product quality data, predicts the impact of the adjusted wire harness process parameters on the production efficiency and product quality, updates the production management settings, and obtains the wire harness management adjustment result.

9. An intelligent wire harness production management method, characterized in that, Implemented according to the intelligent wire harness production management system described in any one of claims 1-8, including the following steps: S1: Based on the key nodes of the production line, capture the surface image of the wire harness through a camera, analyze the surface texture, color distribution, edge features and reflectivity data of the wire harness, judge the surface uniformity, scratch depth and insulation layer integrity, identify the abnormal areas on the wire harness surface, and generate a surface quality assessment log; S2: Based on the surface quality assessment log, analyze the energy consumption data and production rhythm data of the production line equipment, screen the rhythm intervals with low fluctuations during the screening period, and conduct a correlation analysis on the energy consumption fluctuation range and the average production rhythm within the interval to identify the optimal rhythm configuration of energy consumption and production efficiency, and obtain the energy consumption rhythm configuration parameters; S3: Based on the energy consumption rhythm configuration parameters, collect raw material batch information, process parameters, and equipment operation status data, judge the stability of the production process, and calculate the stability index of each production parameter to obtain the production stability metric; S4: According to the production stability metric, analyze the maintenance records and working conditions of the finished wire harness, evaluate the failure incidence rate during the service life cycle, and predict potential failure trends to obtain the life prediction analysis data; S5: Based on the life prediction analysis data, analyze the production adjustment direction, readjust the wire harness process parameters, predict the equipment energy consumption and product quality after adjustment, and update the production management settings to obtain the wire harness management adjustment result.

Images