Electronic wire harness intelligent high temperature resistance test method based on dynamic temperature monitoring

Abstract

The invention discloses an electronic wire harness intelligent high temperature resistance test method based on dynamic temperature monitoring, and the method comprises the steps: collecting multi-region temperature data through a sensor array, and dynamically adjusting the measurement point density and sampling frequency for a region with a higher temperature change rate; for a local high-temperature area, sampling points are increased, a high-temperature micro-change monitoring mechanism is triggered, and micro-change of the temperature is recorded in real time; according to a temperature gradient change trend, dynamic adjustment parameters of a key area are extracted, and density distribution of measuring points is optimized; meanwhile, optimal utilization of computing resources is also considered, and the density of measuring points in a temperature stable region is properly reduced; through continuous monitoring and algorithm parameter optimization, stable high temperature evaluation is finally realized, and the temperature evaluation error is controlled within 1 DEG C. According to the dynamic self-adaptive temperature monitoring method, the temperature monitoring precision and efficiency during operation of the electronic wire harness are remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent manufacturing, and particularly to an intelligent high-temperature resistance testing method for electronic wire harnesses based on dynamic temperature monitoring. Background Art

[0002] As an indispensable core component in the fields of modern industry and technology, the performance of electronic wire harnesses in high-temperature environments is directly related to the reliability and safety of the system. With the increasing demand for high-temperature tolerance in fields such as aerospace, automotive electronics, and energy equipment, developing accurate and efficient high-temperature resistance evaluation methods has become a key issue. The stability and lifespan of electronic wire harnesses at extreme temperatures are not only the basis for technological innovation but also a necessary condition for ensuring the safe operation of equipment.

[0003] However, current evaluation methods often struggle to balance accuracy and efficiency, limiting their applicability in complex application scenarios. Existing high-temperature resistance evaluation methods mostly rely on traditional models with fixed measuring point intervals, usually using evenly distributed measuring points for temperature acquisition. In the face of uneven or dynamically changing temperature fields, this method is prone to insufficient data in local high-temperature regions or resource waste. Especially in scenarios with significant temperature gradients, fixed intervals cannot flexibly adapt to the severity of temperature changes, resulting in evaluation results that are either too rough, ignoring minor changes, or too redundant, increasing unnecessary computational burdens. These limitations make it difficult for existing methods to meet the dual requirements of high precision and high efficiency.

[0004] In this field, the core challenge focuses on how to achieve dynamic matching between the measuring point density and temperature changes. Specifically, the uncertainty of the temperature change rate, the real-time adjustment ability of the measuring point interval, and the optimal allocation of computing resources have become technical bottlenecks that urgently need to be broken through. Since the temperature change rate varies significantly in different regions and time periods, the unresolved dynamic adjustment problem will cause the evaluation system to be difficult to accurately capture local high-temperature micro-changes and also unable to effectively reduce resource consumption when the temperature is stable. In addition, the intelligent control of the measuring point density involves the coordination of algorithms and real-time data processing, increasing the complexity of technical implementation. These problems directly affect the accuracy and practicality of the evaluation.

[0005] Therefore, how to adaptively adjust the measuring point interval according to the temperature change rate of the electronic wire harness to balance capturing high-temperature micro-changes and optimizing computing resources has become the key problem of this research. Solving this problem will provide a new technical path for improving the accuracy and efficiency of high-temperature resistance evaluation. Summary of the Invention

[0006] To solve the above technical problems, the present invention provides an intelligent high-temperature resistance testing method for electronic wire harnesses based on dynamic temperature monitoring, including: S1. Collect the temperature values of multiple regions during the operation of the electronic wire harness through a sensor array. Mark the initial measuring point positions for the regions where the temperature change rate exceeds 1.5 times the average value to obtain the basic temperature distribution data set; S2. Calculate the temperature change rate of each region from the basic temperature distribution data set. If the temperature change rate exceeds the first change rate threshold, increase the measuring point density of the corresponding region by 50% to determine the dynamic measuring point density distribution scheme; S3. Adjust the measuring point interval according to the dynamic measuring point density distribution scheme. Obtain a high-frequency acquisition instruction once per second for the regions where the temperature change rate exceeds the first change rate threshold to obtain the measured point layout data after real-time adjustment; S4. Perform data acquisition from the measured point layout data after real-time adjustment. Double the number of sampling points for the local high-temperature regions where the temperature exceeds the first temperature threshold. If the temperature exceeds the second temperature threshold, trigger the high-temperature micro-variation monitoring mechanism to record the minute changes once per second to obtain the high-temperature micro-variation characteristic data; S5. Analyze the temperature gradient change trend based on the high-temperature micro-variation characteristic data. Extract the key region dynamic adjustment parameters from the regions where the temperature gradient is greater than the temperature gradient threshold to determine the optimized measuring point density distribution; S6. Reconfigure the computing resources according to the optimized measuring point density distribution. If the computing resource occupancy is lower than the resource threshold, reduce the measuring point density of the stable regions where the temperature change rate is lower than the second change rate threshold by 30% to obtain the acquisition scheme after resource optimization; S7. Continuously monitor the temperature field change according to the acquisition scheme after resource optimization. Judge the stable state from the regions where the high-temperature micro-variation amplitude is lower than the amplitude threshold to obtain the final measured point interval adjustment data; S8. Update the acquisition frequency of the sensor array from the final measured point interval adjustment data. Co-optimize the algorithm parameters for the temperature change rate and the local high-temperature characteristics to make the temperature evaluation error less than 1°C to obtain the stable high-temperature evaluation data.

[0007] Optionally, the step S1, which collects the temperature values of multiple regions during the operation of the electronic wire harness through a sensor array, marks the initial measuring point positions for the regions where the temperature change rate exceeds 1.5 times the average value to obtain the basic temperature distribution data set, includes: Step S11. Collect the temperature values of multiple regions during operation through a sensor array to obtain the basic temperature distribution data set; Step S12. Calculate the temperature change rate of each region for the basic temperature distribution data set and determine the regions where the change rate exceeds 1.5 times the average value; Step S13. If the temperature change rate exceeds 1.5 times the average value, mark the initial measuring point positions in the exceeded regions to obtain the marked data set; Step S14: Extract the temperature distribution features from the marked dataset, and use the K-means clustering algorithm to divide the temperature anomaly regions; Step S15: Analyze the spatio-temporal change trend of the operating temperature through the temperature anomaly regions to obtain the change trend distribution; Step S16: Perform smoothing processing on the change trend distribution to obtain an optimized temperature distribution model; Step S17: Use the optimized temperature distribution model to predict potential anomaly regions and judge the distribution law of the anomaly regions.

[0008] Optionally, in step S2, calculate the temperature change rate of each region from the basic temperature distribution dataset. If the temperature change rate exceeds the first change rate threshold, increase the measurement point density of the corresponding region by 50% to determine the dynamic measurement point density distribution scheme, including: Step S21: Obtain the temperature distribution data from the basic dataset, process it by region division, and calculate the temperature change rate value of each region; Step S22: If the temperature change rate value exceeds the first change rate threshold, perform a boosting operation on the measurement point density of the corresponding region to obtain the adjusted density data; Step S23: Update the dynamic distribution with the adjusted density data to generate a preliminary distribution scheme; Step S24: Extract the change trend from the preliminary distribution scheme, and perform data smoothing processing on the change trend to obtain a smoothed distribution result; Step S25: Detect the anomaly regions through the smoothed distribution result. If there are anomaly regions, recalculate the temperature change rate value of the anomaly regions and update the dynamic distribution; Step S26: Obtain the updated dynamic distribution data, and determine the final distribution scheme in combination with the region division; Step S27: Output the measurement point density adjustment result according to the final distribution scheme to complete the dynamic measurement point density distribution processing.

[0009] Optionally, in step S3, adjust the measurement point interval according to the dynamic measurement point density distribution scheme, and obtain a high-frequency acquisition instruction once per second for the regions where the temperature change rate exceeds the first change rate threshold to obtain the real-time adjusted measurement point layout data, including: Step S31: Obtain the temperature change data through the sensor network and determine the regions where the change rate exceeds the first change rate threshold; Step S32: Generate a high-frequency acquisition instruction for the regions where the change rate exceeds to obtain the sampling data once per second; Step S33: Process the sampling data using the K-means clustering algorithm to judge the adjustment requirement of the measurement point interval; Step S34: Update the measurement point density distribution scheme according to the adjustment requirement to obtain the real-time updated measurement point layout data; Step S35: Extract region-targeted features from the real-time layout data to determine the temperature change trend; Step S36: Optimize the acquisition instruction through trend analysis to obtain the sampling frequency adjustment data for the next cycle; Step S37: Process the adjustment data using a decision tree algorithm to determine the final layout of the measuring point density distribution.

[0010] Optionally, in step S4: Perform data acquisition from the measured point layout data after real-time adjustment. Double the number of sampling points for local high-temperature regions where the temperature exceeds the first temperature threshold. If the temperature exceeds the second temperature threshold, trigger the high-temperature micro-variation monitoring mechanism to record minute changes once per second to obtain high-temperature micro-variation feature data, including: Step S41: Obtain initial data through the pre-established measured point layout, and perform an adjustment to double the number of sampling points for local high-temperature regions to obtain the extended data acquisition result; Step S42: Extract the temperature value from the extended data acquisition result. If the temperature value exceeds the second temperature threshold, activate the micro-variation monitoring mechanism to obtain the minute change data recorded per second; Step S43: Classify the minute change data using a support vector machine algorithm to determine the high-temperature micro-variation feature data; Step S44: Calculate the change trend through the high-temperature micro-variation feature data to obtain the trend direction and amplitude information; Step S45: Adjust the distribution of the number of sampling points according to the trend direction and amplitude information to obtain the optimized measured point layout data; Step S46: Re-acquire data from the optimized measured point layout data to determine whether there are still temperature-exceeding regions, and obtain the updated high-temperature region distribution; Step S47: Repeat the above micro-variation monitoring and feature extraction for the updated high-temperature region distribution to obtain the final high-temperature micro-variation feature data.

[0011] Optionally, in step S5: Analyze the temperature gradient change trend based on the high-temperature micro-variation feature data, extract key region dynamic adjustment parameters from the regions where the temperature gradient is greater than the temperature gradient threshold, and determine the optimized measuring point density distribution, including: Step S51: Obtain the temperature gradient value from the high-temperature micro-variation feature data, and use the gradient calculation method to generate the change trend distribution; Step S52: According to the change trend distribution, use the threshold judgment method to extract the regions where the temperature gradient is greater than the temperature gradient threshold to determine the key region range; Step S53: For the key region range, use the Kriging interpolation method to adjust the parameters to generate the dynamically adjusted parameter set; Step S54: Obtain the measuring point distribution characteristics from the dynamically adjusted parameter set, determine whether the measuring point density is greater than 10 per square kilometer, and determine the preliminary density distribution; Step S55: Through the preliminary density distribution, use the Thiessen polygon method to optimize the measuring point layout and generate the optimized measuring point density distribution; Step S56: Extract the distribution plan from the optimized measuring point density distribution, determine whether the plan covers more than 90% of the high-temperature micro-variation characteristic data area, and determine the final distribution plan; Step S57: According to the final distribution plan, use ArcGIS to generate the visualization result of the high-temperature micro-variation characteristic data and obtain the complete analysis output.

[0012] Optionally, in step S6, reconfigure the computing resources from the optimized measuring point density distribution. If the computing resource occupancy is lower than the resource threshold, reduce the measuring point density in the stable area where the temperature change rate is lower than the second change rate threshold by 30% to obtain the acquisition plan after resource optimization, including: Step S61: Obtain the computing resource occupancy data through the optimized measuring point density distribution and determine whether the resource occupancy is lower than the resource threshold; Step S62: If the resource occupancy is lower than the resource threshold, extract the temperature change rate data from the measuring point density distribution and use the temperature change rate analysis tool to determine the stable area where the temperature change rate is lower than the second change rate threshold; Step S63: For the measuring point density data in the stable area, use the density adjustment tool to reduce the measuring point density by 30% to obtain the adjusted density distribution; Step S64: Adopt the adjusted density distribution, use the resource monitoring tool to recalculate the resource occupancy, and determine whether the resource optimization requirements are met; Step S65: According to the optimized resource status, use the rule engine to generate a new acquisition plan and obtain the measuring point configuration after resource optimization; Step S66: Extract the temperature change rate and resource occupancy data from the new acquisition plan, and use the optimization judgment tool to determine whether further adjustment is still required to obtain the final acquisition plan; Step S67: According to the final acquisition plan, use the density adjustment tool to adjust the measuring point density distribution and determine the operating parameters after resource optimization.

[0013] Optionally, in step S7, continuously monitor the temperature field change according to the acquisition plan after resource optimization, judge the stable state from the area where the high-temperature micro-variation amplitude is lower than the amplitude threshold, and obtain the final measuring point interval adjustment data, including: Step S71: Obtain the temperature field change data through the acquisition plan and extract the micro-variation amplitude characteristics for the high-temperature area; Step S72: Determine whether it is lower than the amplitude threshold from the high-temperature micro-variation amplitude data. If it is lower than the amplitude threshold, it is determined that the area has reached a stable state; Step S73: Calculate the preliminary adjustment value of the measuring point interval based on the temperature distribution characteristics of the stable state area; Step S74: Verify the measuring point interval adjustment value using continuous monitoring data. Determine the accuracy of the adjustment value by comparing the temperature change amplitudes before and after the adjustment; Step S75: Perform resource optimization processing on the adjustment value to generate an optimized measuring point distribution plan; Step S76: Update the acquisition plan according to the optimized measuring point distribution plan to obtain the final temperature field monitoring data; Step S77: Extract the temperature change trend characteristics from the final monitoring data to judge the persistence of the stable state of the temperature field.

[0014] Optionally, in step S8, update the acquisition frequency of the sensor array from the final measuring point interval adjustment data, and co-optimize the algorithm parameters for the temperature change rate and local high-temperature characteristics, so that the temperature evaluation error is lower than 1°C to obtain stable high-temperature evaluation data, including: Step S81: Obtain the initial acquisition frequency data through the sensor array, and adjust the acquisition frequency according to the measuring point interval to obtain the preliminary frequency distribution; Step S82: Extract temperature data from the preliminary frequency distribution, calculate the temperature change rate using the difference method, extract the change trend from the temperature change rate, and determine the basis for dynamic adjustment; Step S83: If the change trend exceeds the change threshold, adjust the algorithm parameters by the gradient descent method to obtain an optimized parameter set; Step S84: Process the local high-temperature data using the optimized parameter set, extract the high-temperature distribution from the local high-temperature characteristics, and obtain feature-enhanced data; Step S85: Update the acquisition frequency through the feature-enhanced data, recalculate the change value for the temperature change rate, and judge whether the evaluation error is reduced; Step S86: If the evaluation error does not meet the standard, process the high-temperature characteristics through the random forest algorithm to obtain stable high-temperature data; Step S87: Adjust the operating frequency of the sensor array according to the stable high-temperature data, and generate the final high-temperature evaluation data from the adjusted frequency.

[0015] The present invention discloses an intelligent high-temperature resistance test method for electronic wire harnesses based on dynamic temperature monitoring. This method collects multi-region temperature data through a sensor array and dynamically adjusts the measurement point density and sampling frequency for regions with a relatively high temperature change rate. For local high-temperature regions, the present invention increases the sampling points and triggers a high-temperature micro-variation monitoring mechanism to record the minute temperature changes in real time. According to the trend of temperature gradient changes, the present invention extracts key regions to dynamically adjust parameters and optimize the measurement point density distribution. At the same time, the present invention also considers the optimal utilization of computing resources and appropriately reduces the measurement point density for temperature-stable regions. Through continuous monitoring and algorithm parameter optimization, the present invention finally achieves stable high-temperature evaluation, controlling the temperature evaluation error within 1°C. This dynamically adaptive temperature monitoring method significantly improves the temperature monitoring accuracy and efficiency during the operation of electronic wire harnesses. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 is a flowchart of an intelligent high-temperature resistance test method for electronic wire harnesses based on dynamic temperature monitoring according to the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0017] In order to make the objectives, technical solutions, and advantages of the present invention clearer, the present invention will be described in detail below with reference to the accompanying drawings and specific embodiments.

[0018] As Figure 1 shown, an intelligent high-temperature resistance test method for electronic wire harnesses based on dynamic temperature monitoring provided by the present invention includes: S1. Collect the temperature values of multiple regions during the operation of the electronic wire harness through a sensor array, mark the initial measurement point positions for regions where the temperature change rate exceeds 1.5 times the average value, and obtain a basic temperature distribution dataset.

[0019] Optionally, this step further includes: Step S11. Collect the temperature values of multiple regions during operation through a sensor array to obtain a basic temperature distribution dataset.

[0020] Step S12. Calculate the temperature change rate of each region for the basic temperature distribution dataset and determine the regions where the change rate exceeds 1.5 times the average value.

[0021] Step S13. If the temperature change rate exceeds 1.5 times the average value, mark the initial measurement point positions in the exceeded regions to obtain a marked dataset.

[0022] Step S14. Extract the temperature distribution characteristics from the marked dataset and use the K-means clustering algorithm to divide the temperature abnormal regions.

[0023] Optionally, the following formula is used to calculate the temperature anomaly index: ;

[0024] where, R represents the temperature anomaly index, represents the temperature value at the i-th point, μ represents the regional average temperature, σ represents the temperature standard deviation, and n represents the total number of sampling points.

[0025] Step S15: Analyze the spatio-temporal variation trend of the operating temperature through the temperature anomaly region to obtain the variation trend distribution.

[0026] Step S16: Perform smoothing processing on the variation trend distribution to obtain an optimized temperature distribution model.

[0027] Specifically, based on the spatio-temporal variation trend distribution of the temperature anomaly region, the system uses the Gaussian smoothing algorithm to optimize the temperature distribution model. The temperature data is smoothed by a Gaussian kernel function with a sliding window size of 5 time points. For example, the temperatures of a certain region at 5 consecutive time points are 25°C, 26°C, 27°C, 28°C, and 29°C respectively. After Gaussian smoothing, the temperature value of this region stabilizes at about 27°C, reducing data fluctuations. Subsequently, the system combines the time series analysis method and uses the autoregressive integrated moving average model (ARIMA) to predict the smoothed temperature data. For example, after training the model with historical temperature data, the predicted temperature variation trend of a certain region within the next 10 seconds is gradually rising from 28°C to 32°C. On this basis, the system uses the clustering algorithm to classify the temperature anomaly regions, and uses the K-means clustering algorithm to divide the regions with similar temperature variation trends into the same category. For example, the regions with a temperature change rate between 2°C / second and 4°C / second are divided into one category, and the regions with a temperature change rate above 5°C / second are divided into another category. Through the clustering results, the system further analyzes the distribution law of potential anomaly regions. For example, it is found that the temperature anomaly regions are mostly concentrated in the middle section of the electronic wire harness, and the temperature changes in the anomaly regions are periodic, with a significant temperature fluctuation occurring every 30 seconds. Finally, the system integrates these analysis results into the judgment result of the distribution law of potential anomaly regions, providing a basis for the subsequent monitoring of the operating state of the electronic wire harness.

[0028] According to the marked temperature distribution data set, use the K-means clustering algorithm to divide the temperature anomaly regions, analyze the spatio-temporal variation trend of the anomaly regions to obtain the variation trend distribution, and perform smoothing processing on it to obtain an optimized temperature distribution prediction model, thereby judging the distribution law of the anomaly regions.

[0029] Step S17: Use the optimized temperature distribution model to predict potential anomaly regions and judge the distribution law of the anomaly regions.

[0030] Specifically, the multi-region temperature values during the operation of the electronic wire harness are collected through a sensor array. Distributed temperature sensors are arranged in multiple key areas of the electronic wire harness. For example, a sensor is set every 10 centimeters to ensure the comprehensiveness of temperature monitoring. The sensor array collects temperature data at a frequency of once per second and uploads it to the data processing center in real time through a wireless transmission module. The data processing center first preprocesses the collected temperature data, including removing noise and outliers. The filtering algorithm used is the Kalman filter, making the data smoother and more reliable. Next, the temperature change rate of each region is calculated. The temperature difference between adjacent time points is calculated by the difference method and then divided by the time interval to obtain the change rate.

[0031] For example, the temperatures of a certain region at two consecutive time points are 23°C and 28°C respectively, and the time interval is 1 second. Then the temperature change rate is 5°C / second. Then, the average value of the temperature change rates of all regions is calculated, assumed to be 0°C / second. For the regions where the temperature change rate exceeds 1.5 times the average value, that is, the regions where the change rate is greater than 5°C / second, they are marked as the initial measurement point positions.

[0032] For example, the change rate of a certain region is 8°C / second, exceeding 1.5 times the average value, so it is marked as the initial measurement point. Finally, the temperature data of all marked regions are integrated to form a basic temperature distribution dataset for subsequent analysis and optimization. Through the above steps, the system can automatically identify temperature abnormal regions and provide data support for the safe operation of the electronic wire harness.

[0033] According to the spatio-temporal change trend distribution of the temperature abnormal regions, a smoothing processing method is used to optimize the temperature distribution model, and the judgment result of the distribution law of potential abnormal regions is obtained.

[0034] Specifically, based on the labeled temperature distribution dataset, the system uses the K-means clustering algorithm to divide the temperature anomaly regions. The number of clustering centers is set to 3. The distance from each data point to the clustering center is calculated through the Euclidean distance, and the temperature data is divided into three categories: low-temperature region (18°C to 22°C), medium-temperature region (23°C to 27°C), and high-temperature region (28°C to 32°C). Subsequently, the system conducts a spatio-temporal change trend analysis on the high-temperature regions, extracts the temperature change rate every 10 seconds, and finds that the high-temperature regions show a trend of rising first and then falling in the time dimension. For example, the temperature change rates of a certain region within 10 consecutive seconds are 5°C / second, 8°C / second, 2°C / second, 9°C / second, and 6°C / second. To reduce the impact of data fluctuations on trend analysis, the system uses the moving average algorithm to smooth the temperature change rate, sets the window size to 3, and the smoothed temperature change rates are 7°C / second, 0°C / second, and 9°C / second. Based on the smoothed data, the system uses the exponential smoothing method to construct a temperature distribution prediction model, sets the smoothing coefficient to 3, and predicts that the temperature in the high-temperature region will rise from 29°C to 31°C within the next 5 seconds. By analyzing the prediction results, the system finds that the high-temperature regions are mostly concentrated near the device heat sinks, and the temperature change trend is positively correlated with the device operation load. For example, when the device load increases by 10%, the temperature in the high-temperature region rises by approximately 5°C.

[0035] S2. Calculate the temperature change rate of each region from the basic temperature distribution dataset. If the temperature change rate exceeds the first change rate threshold of 5°C / minute, increase the measurement point density of the corresponding region by 50% to determine the dynamic measurement point density distribution scheme.

[0036] Optionally, this step further includes: Step S21. Obtain the temperature distribution data from the basic dataset, process it by region division, and calculate the temperature change rate values of each region.

[0037] Step S22. If the temperature change rate value exceeds the first change rate threshold, perform an increase operation on the measurement point density of the corresponding region to obtain the adjusted density data.

[0038] Step S23. Update the dynamic distribution with the adjusted density data to generate a preliminary distribution scheme.

[0039] Step S24. Extract the change trend from the preliminary distribution scheme and perform data smoothing processing on the change trend to obtain the smoothed distribution result.

[0040] Step S25. Detect the abnormal regions through the smoothed distribution result. If abnormal regions exist, recalculate the temperature change rate values of the abnormal regions and update the dynamic distribution.

[0041] Step S26. Obtain the updated dynamic distribution data and determine the final distribution scheme in combination with the region division.

[0042] Step S27: Output the measurement point density adjustment result according to the final distribution plan to complete the dynamic measurement point density distribution process.

[0043] Specifically, extract the temperature values of each region from the temperature distribution basic dataset. Assume that the initial temperature of a certain region is 25°C and the temperature after one minute is 32°C. Then the temperature change rate is (32 - 25) / 1 = 7°C / minute. If the preset first change rate threshold is 5°C / minute, then 7°C / minute exceeds the first change rate threshold. At this time, the system automatically increases the measurement point density of this region by 50%. Assume that the original measurement point density is 10 per square meter, and after the increase, it is 15 per square meter. By this method of dynamically adjusting the measurement point density, regions with large temperature changes can be monitored more precisely to ensure the accuracy and real-time nature of the data. The system will dynamically adjust the measurement point density of each region according to the real-time temperature change rate to form an optimized measurement point distribution plan, thereby improving the overall monitoring effect.

[0044] S3: Adjust the measurement point interval according to the dynamic measurement point density distribution plan, obtain a high-frequency acquisition instruction once per second for the region where the temperature change rate exceeds the first change rate threshold of 5°C / minute, and get the real-time adjusted measurement point layout data.

[0045] Optionally, this step further includes: Step S31: Obtain temperature change data through the sensor network and determine the regions where the change rate exceeds the first change rate threshold.

[0046] Step S32: Generate a high-frequency acquisition instruction for the regions where the change rate exceeds, and obtain sampling data once per second.

[0047] Step S33: Process the sampling data using the K-means clustering algorithm to judge the adjustment requirement of the measurement point interval.

[0048] Step S34: Update the measurement point density distribution plan according to the adjustment requirement to obtain the real-time updated measurement point layout data.

[0049] Step S35: Extract region-specific features from the real-time layout data to determine the temperature change trend.

[0050] Step S36: Optimize the acquisition instruction through trend analysis to obtain the sampling frequency adjustment data for the next cycle.

[0051] Step S37: Process the adjustment data using the decision tree algorithm to judge the final layout of the measurement point density distribution plan.

[0052] Specifically, based on the dynamic measurement point density distribution plan, the system first preliminarily divides the monitoring area using an adaptive grid division algorithm according to the change characteristics of the temperature field.

[0053] For example, in the initial stage, the system is based on a 10-meter by 10-meter grid to cover the entire monitoring area. Then, the system calculates the temperature changes within each grid by analyzing the historical data of temperature sensors in real time. When the temperature change within a certain grid exceeds 5°C, the system automatically subdivides the grid into smaller sub-grids, such as 2 meters by 2 meters, in order to more precisely capture the temperature fluctuations. In the refined grid, the system generates high-frequency acquisition instructions once per second to ensure the real-time and accuracy of temperature data. At the same time, the system merges adjacent grids with high change rates through optimization algorithms, such as the K-means clustering algorithm, to form a reasonable measurement point layout.

[0054] For example, when the temperature changes in two adjacent grids both exceed 5°C, the system merges them into a larger measurement point area to reduce redundant data and improve the monitoring efficiency. Finally, the system outputs the real-time adjusted measurement point layout data, including information such as measurement point coordinates and acquisition frequency, providing reliable data support for subsequent temperature monitoring and analysis.

[0055] S4. Perform data acquisition from the real-time adjusted measurement point layout data, double the number of sampling points for local high-temperature areas where the temperature exceeds the first temperature threshold of 80°C. If the temperature exceeds the preset second temperature threshold of 90°C, trigger the high-temperature micro-variation monitoring mechanism to record minute changes once per second to obtain high-temperature micro-variation characteristic data.

[0056] Optionally, this step further includes: Step S41. Obtain initial data through the pre-established measurement point layout, and perform an adjustment to double the number of sampling points for local high-temperature areas to obtain the expanded data acquisition result.

[0057] Step S42. Extract the temperature values from the expanded data acquisition result. If the temperature value exceeds the second temperature threshold, activate the micro-variation monitoring mechanism to obtain the minute change data recorded once per second.

[0058] Step S43. Classify the minute change data using the support vector machine algorithm to determine the high-temperature micro-variation characteristic data.

[0059] Step S44. Calculate the change trend through the high-temperature micro-variation characteristic data to obtain the trend direction and amplitude information.

[0060] Step S45. Adjust the sampling point distribution according to the trend direction and amplitude information to obtain the optimized measurement point layout data.

[0061] Step S46. Re-acquire data from the optimized measurement point layout data, and determine whether there are still temperature-exceeding areas to obtain the updated high-temperature area distribution.

[0062] Step S47: Repeat the above-mentioned micro-variation monitoring and feature extraction for the updated high-temperature area distribution to obtain the final high-temperature micro-variation feature data.

[0063] Specifically, data collection is performed from the real-time adjusted measuring point layout data. First, the current temperature distribution is obtained through the sensor network. Assume the initial number of measuring points is 100, distributed on the surface of the device. When the temperature in a local area is detected to exceed 80 °C, the system automatically doubles the number of sampling points in that area. For example, if the original number of measuring points in a certain high-temperature area is 10, it becomes 20 after the increase, ensuring that the density of data collection is high enough to capture the details of temperature changes. If the temperature further rises above 90 °C, the system immediately triggers the high-temperature micro-variation monitoring mechanism, records the minute changes once per second, and uses time series analysis methods combined with the Kalman filtering algorithm to smooth the temperature data and extract the characteristics of temperature changes.

[0064] For example, at a certain moment, the temperature rises from 91 °C to 93 °C. The system records this minute change and analyzes its frequency characteristics through the FFT (Fast Fourier Transform) algorithm to identify whether there are periodic fluctuations. These high-temperature micro-variation feature data will be used for subsequent fault prediction and health management to help engineers accurately judge the operating state of the device and early warning of potential fault risks.

[0065] S5: Analyze the temperature gradient change trend based on the high-temperature micro-variation feature data, extract the key area dynamic adjustment parameters from the area where the temperature gradient is greater than the temperature gradient threshold of 2 °C / cm, and determine the optimized measuring point density distribution.

[0066] Optionally, this step also includes: Step S51: Obtain the temperature gradient value from the high-temperature micro-variation feature data and generate the change trend distribution using the gradient calculation method.

[0067] Step S52: According to the change trend distribution, use the threshold judgment method to extract the area where the temperature gradient is greater than the temperature gradient threshold and determine the key area range.

[0068] Step S53: For the key area range, use the Kriging interpolation method to adjust the parameters and generate a set of dynamically adjusted parameters.

[0069] Step S54: Obtain the measuring point distribution characteristics from the set of dynamically adjusted parameters, and judge whether the measuring point density is greater than 10 per square kilometer to determine the preliminary density distribution.

[0070] Step S55: Through the preliminary density distribution, use the Thiessen polygon method to optimize the measuring point layout and generate the optimized measuring point density distribution.

[0071] Step S56: Extract the distribution plan from the optimized measurement point density distribution, determine whether the plan covers more than 90% of the high-temperature micro-variation characteristic data area, and determine the final distribution plan.

[0072] Step S57: According to the final distribution plan, use ArcGIS to generate the visualization result of the high-temperature micro-variation characteristic data, and obtain the complete analysis output.

[0073] Specifically, in the analysis of high-temperature micro-variation characteristics, first collect temperature data through sensors, use the Gaussian filtering algorithm to smooth the original data, remove the influence of noise, and set the filtering parameter as σ = 5. Then, use the spatial interpolation method (such as Kriging interpolation) to generate the temperature gradient distribution map, and set the interpolation step size to 1 cm. In the temperature gradient analysis, set the temperature gradient threshold to 2 °C / cm, and use the region growing algorithm to extract the key areas where the gradient is greater than 2 °C / cm, and set the seed point growth threshold to 5 °C to ensure the connectivity of the areas. In the key areas, based on the calculation of the discreteness of temperature changes, use the K-means clustering algorithm to dynamically adjust the distribution of measurement points, with the number of clustering centers being 5 and the number of iterations being 100 times. By calculating the temperature standard deviation in the area, optimize the measurement point density, increase the measurement point density in the high-gradient area to 4 points per square centimeter, and reduce it to 1 point per square centimeter in the low-gradient area. Finally, according to the optimized measurement point density distribution, redeploy the sensors to ensure the accuracy and representativeness of the monitoring data.

[0074] S6: Reconfigure the computing resources from the optimized measurement point density distribution. If the computing resource occupancy is lower than 70% of the resource threshold, then reduce the measurement point density in the stable area where the temperature change rate is lower than the second change rate threshold of 1 °C / minute by 30% to obtain the acquisition plan after resource optimization.

[0075] Optionally, this step further includes: Step S61: Obtain the computing resource occupancy data through the optimized measurement point density distribution, and determine whether the resource occupancy is lower than 70% of the resource threshold.

[0076] Step S62: If the resource occupancy is lower than 70% of the resource threshold, then extract the temperature change rate data from the measurement point density distribution, and use the temperature change rate analysis tool to determine the stable area where the temperature change rate is lower than 1 °C / minute.

[0077] Step S63: For the measurement point density data in the stable area, use the density adjustment tool to reduce the measurement point density by 30% to obtain the adjusted density distribution.

[0078] Step S64: Adopt the adjusted density distribution, use the resource monitoring tool to recalculate the resource occupancy, and determine whether it meets the resource optimization requirements.

[0079] Step S65: According to the optimized resource status, use the rule engine to generate a new acquisition plan and obtain the measuring point configuration after resource optimization.

[0080] Step S66: Extract the temperature change rate and resource occupancy data from the new acquisition plan, and use the optimization judgment tool to determine whether further adjustment is still required to obtain the final acquisition plan.

[0081] Step S67: According to the final acquisition plan, use the density adjustment tool to adjust the measuring point density distribution and determine the operating parameters after resource optimization.

[0082] Specifically, in the optimized measuring point density distribution, reconfiguration is performed based on the occupancy of computing resources. First, the computing resource utilization rate of each node is collected in real time through the monitoring system. If it is found that the computing resource occupancy rate in a certain area is lower than the resource threshold of 70%, the measuring point density adjustment algorithm is started.

[0083] For example, in a certain temperature field simulation, the system detects that the computing resource occupancy rate in a certain area is 65%, which is lower than the resource threshold. At the same time, through the temperature change rate analysis module, it is found that the temperature change rate in this area is stable below 8 °C / minute, meeting the definition of a stable area. The system then calls the density optimization algorithm to reduce the measuring point density in this area by 30%, from the original 100 measuring points to 70 measuring points. At the same time, the interpolation algorithm is used to supplement the missing data to ensure that the simulation accuracy is not significantly affected. The specific algorithm uses an optimization method based on gradient descent to determine the optimal measuring point distribution through iterative calculation. While reducing the density, the computing resource allocation is dynamically adjusted, and the released computing resources are allocated to high-change rate areas, such as hot spots where the temperature change rate is higher than 2 °C / minute, thereby improving the overall simulation efficiency. Through this process, the system realizes the dynamic optimization configuration of computing resources, reducing resource waste and ensuring the data acquisition accuracy in key areas.

[0084] S7: Continuously monitor the temperature field change according to the acquisition plan after resource optimization, judge the stable state from the area where the high-temperature micro-variation amplitude is lower than the amplitude threshold of 0.5 °C, and obtain the final measuring point interval adjustment data.

[0085] Optionally, this step further includes: Step S71: Obtain the temperature field change data through the acquisition plan and extract the micro-variation amplitude characteristics for the high-temperature area.

[0086] Step S72: Judge from the high-temperature micro-variation amplitude data whether it is lower than the amplitude threshold. If it is lower than the preset threshold, it is determined that the area reaches a stable state.

[0087] Step S73: Based on the temperature distribution characteristics of the stable state area, calculate the preliminary adjustment value of the measuring point interval.

[0088] Step S74, using the continuous monitoring data to verify the measurement point interval adjustment value, and determining the accuracy of the adjustment value by comparing the temperature change amplitude before and after the adjustment.

[0089] Step S75: performing resource optimization processing on the adjustment value to generate an optimized measurement point distribution plan.

[0090] Step S76, updating the acquisition plan according to the optimized measurement point distribution plan to obtain the final temperature field monitoring data.

[0091] Step S77, extracting the temperature change trend characteristics from the final monitoring data to determine the continuity of the stable state of the temperature field.

[0092] Specifically, in the resource-optimized acquisition scheme, the temperature field changes are first monitored in real time through a distributed temperature sensor network, and the sampling frequency is set to once per minute to ensure high-precision data acquisition. For the collected temperature data, the sliding average algorithm is used for preprocessing, and the window size is 10 minutes to eliminate the influence of random noise. Then, based on the preprocessed data, the temperature field is smoothed using the Gaussian filter algorithm, and the standard deviation is set to 2 to further highlight the overall trend of the temperature field. By comparing the temperature field data at consecutive time points, the temperature change amplitude of each area is calculated. When the temperature change amplitude of a certain area is less than 5°C for 30 consecutive minutes, it is determined that the area has reached a stable state. For stable areas, the dynamic adjustment algorithm is used to optimize the measurement point interval. The specific method is: the initial measurement point interval is adjusted from 5 meters to 10 meters, and an adaptive adjustment mechanism based on the temperature gradient is introduced. When the temperature gradient is less than 1°C / meter, the measurement point interval is further expanded to 15 meters. Finally, through simulation verification, the optimized measurement point interval scheme significantly reduces resource consumption while ensuring monitoring accuracy, and the overall acquisition efficiency is improved by about 30%. Throughout the entire process, all algorithms and parameters are executed through an automated system to ensure the real-time and accuracy of the data.

[0093] S8, update the sensor array acquisition frequency based on the final measurement point interval adjustment data, and coordinately optimize the algorithm parameters based on the temperature change rate and local high temperature characteristics to make the temperature evaluation error less than 1°C and obtain stable high temperature evaluation data.

[0094] Optionally, this step also includes: Step S81, obtaining initial acquisition frequency data through the sensor array, adjusting the acquisition frequency according to the measurement point interval, and obtaining a preliminary frequency distribution.

[0095] Step S82, extracting temperature data from the preliminary frequency distribution, using the differential method to calculate the temperature change rate, extracting the change trend from the temperature change rate, and determining the basis for dynamic adjustment.

[0096] Step S83: If the change trend exceeds the change threshold, adjust the algorithm parameters by the gradient descent method to obtain an optimized parameter set.

[0097] Step S84: Process the local high-temperature data with the optimized parameter set, extract the high-temperature distribution from the local high-temperature features to obtain feature-enhanced data.

[0098] Step S85: Update the acquisition frequency through the feature-enhanced data, recalculate the change value for the temperature change rate, and determine whether the evaluation error is reduced.

[0099] Step S86: If the evaluation error does not meet the standard, process the high-temperature features through the random forest algorithm to obtain stable high-temperature data.

[0100] Step S87: Adjust the operating frequency of the sensor array according to the stable high-temperature data, and generate the final high-temperature evaluation data from the adjusted frequency.

[0101] Specifically, during the temperature monitoring process, initial data is first collected through a sensor array. The measurement point interval is set to 10 cm, and the acquisition frequency is 10 times per second to ensure high-density data coverage. Based on the initial collected data, the temperature change rate is analyzed, and the least squares method is used to fit the temperature change curve. It is found that the temperature change rate reaches 5°C per second in a local area. To optimize the acquisition frequency, a dynamic adjustment algorithm is introduced to adjust the acquisition frequency in real time according to the temperature change rate. When the temperature change rate exceeds 3°C per second, the acquisition frequency is increased to 20 times per second to ensure data accuracy. At the same time, for local high-temperature features, the Gaussian filtering algorithm is used to smooth the data, eliminate noise interference, and extract the core temperature value of the high-temperature area. By jointly optimizing the algorithm parameters, the standard deviation of the Gaussian filter is set to 2°C to ensure that the temperature evaluation error in the local high-temperature area is controlled within 8°C. Finally, through multiple iterative optimizations, the stability of the high-temperature evaluation data output by the system is significantly improved, and the evaluation error is stably lower than 1°C, meeting the requirements of high-precision temperature monitoring.

[0102] An intelligent high-temperature resistance test method for electronic wire harnesses based on dynamic temperature monitoring disclosed by the present invention. This method collects multi-region temperature data through a sensor array, dynamically adjusts the measurement point density and sampling frequency for regions with a high temperature change rate; for local high-temperature regions, the present invention increases the sampling points and triggers a high-temperature micro-variation monitoring mechanism to record the minute temperature changes in real time; according to the temperature gradient change trend, the present invention extracts key regions to dynamically adjust parameters and optimize the measurement point density distribution; at the same time, the present invention also considers the optimized utilization of computing resources and appropriately reduces the measurement point density for temperature-stable regions; through continuous monitoring and algorithm parameter optimization, the present invention finally achieves stable high-temperature evaluation, controlling the temperature evaluation error within 1°C. This dynamically adaptive temperature monitoring method significantly improves the temperature monitoring accuracy and efficiency during the operation of electronic wire harnesses.

[0103] As described above, it is only a preferred specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention, according to the technical solution and inventive concept of the present invention, making equivalent substitutions or changes should be covered within the protection scope of the present invention.

Claims

1. An intelligent high-temperature resistance test method for electronic wire harnesses based on dynamic temperature monitoring, characterized in that The method includes: S1. Collect multi-region temperature values during the operation of the electronic wire harness through a sensor array. Mark the initial measurement point positions for the regions where the temperature change rate exceeds 1.5 times the average value to obtain a basic temperature distribution data set. S2. Calculate the temperature change rate of each region from the basic temperature distribution data set. If the temperature change rate exceeds the first change rate threshold, increase the measurement point density of the corresponding region by 50% to determine a dynamic measurement point density distribution scheme. S3. Adjust the measurement point interval according to the dynamic measurement point density distribution scheme. Obtain a high-frequency acquisition instruction once per second for the regions where the temperature change rate exceeds the first change rate threshold to obtain the measured point layout data after real-time adjustment. S4. Perform data acquisition from the measured point layout data after real-time adjustment. Double the number of sampling points for the local high-temperature regions where the temperature exceeds the first temperature threshold. If the temperature exceeds the second temperature threshold, trigger the high-temperature micro-variation monitoring mechanism to record the minute changes once per second to obtain high-temperature micro-variation characteristic data. S5. Analyze the temperature gradient change trend based on the high-temperature micro-variation characteristic data. Extract the key region dynamic adjustment parameters from the regions where the temperature gradient is greater than the temperature gradient threshold to determine the optimized measurement point density distribution. S6. Reconfigure the computing resources according to the optimized measurement point density distribution. If the computing resource occupancy is lower than the resource threshold, reduce the measurement point density of the stable regions where the temperature change rate is lower than the second change rate threshold by 30% to obtain an acquisition scheme after resource optimization. S7. Continuously monitor the temperature field change according to the acquisition scheme after resource optimization. Judge the stable state from the regions where the high-temperature micro-variation amplitude is lower than the amplitude threshold to obtain the final measured point interval adjustment data. S8. Update the acquisition frequency of the sensor array from the final measured point interval adjustment data. Optimize the algorithm parameters in collaboration with the temperature change rate and local high-temperature characteristics so that the temperature evaluation error is lower than 1°C to obtain stable high-temperature evaluation data.

2. The method according to claim 1, characterized in that, The step S1, collecting multi-region temperature values during the operation of the electronic wire harness through a sensor array, marking the initial measurement point positions for the regions where the temperature change rate exceeds 1.5 times the average value to obtain a basic temperature distribution data set, includes: Step S11. Collect multi-region temperature values during operation through a sensor array to obtain a basic temperature distribution data set. Step S12. Calculate the temperature change rate of each region for the basic temperature distribution data set to determine the regions where the change rate exceeds 1.5 times the average value. Step S13. If the temperature change rate exceeds 1.5 times the average value, mark the initial measurement point positions in the exceeded regions to obtain the marked data set. Step S14. Extract the temperature distribution characteristics from the marked data set and use the K-means clustering algorithm to divide the temperature abnormal regions. Step S15. Analyze the spatio-temporal change trend of the operating temperature through the temperature abnormal regions to obtain the change trend distribution. Step S16. Perform smoothing processing on the change trend distribution to obtain an optimized temperature distribution model. Step S17. Use the optimized temperature distribution model to predict potential abnormal regions and judge the distribution law of the abnormal regions.

3. The method according to claim 1, characterized in that, In step S2, calculate the temperature change rate of each region from the basic temperature distribution dataset. If the temperature change rate exceeds the first change rate threshold, increase the measurement point density of the corresponding region by 50% to determine the dynamic measurement point density distribution scheme, including: Step S21, obtain the temperature distribution data through the basic dataset, process it according to regional division, and calculate the temperature change rate value of each region; Step S22, if the temperature change rate value exceeds the first change rate threshold, perform an increase operation on the measurement point density of the corresponding region to obtain the adjusted density data; Step S23, update the dynamic distribution with the adjusted density data to generate a preliminary distribution scheme; Step S24, extract the change trend from the preliminary distribution scheme, and perform data smoothing processing on the change trend to obtain the smoothed distribution result; Step S25, detect abnormal regions through the smoothed distribution result. If abnormal regions exist, recalculate the temperature change rate value of the abnormal regions and update the dynamic distribution; Step S26, obtain the updated dynamic distribution data, and determine the final distribution scheme in combination with the regional division; Step S27, output the measurement point density adjustment result according to the final distribution scheme to complete the dynamic measurement point density distribution process.

4. The method according to claim 1, wherein In step S3, adjust the measurement point interval according to the dynamic measurement point density distribution scheme, and obtain the high-frequency acquisition instruction once per second for the region where the temperature change rate exceeds the first change rate threshold to obtain the real-time adjusted measurement point layout data, including: Step S31, obtain the temperature change data through the sensor network and determine the region where the change rate exceeds the first change rate threshold; Step S32, generate a high-frequency acquisition instruction for the region where the change rate exceeds to obtain the sampling data once per second; Step S33, process the sampling data using the K-means clustering algorithm to judge the adjustment requirement of the measurement point interval; Step S34, update the measurement point density distribution scheme according to the adjustment requirement to obtain the real-time updated measurement point layout data; Step S35, extract the region-specific features from the real-time layout data to determine the temperature change trend; Step S36, optimize the acquisition instruction through the change trend analysis to obtain the sampling frequency adjustment data for the next cycle; Step S37, process the adjustment data using the decision tree algorithm to judge the final layout of the measurement point density distribution scheme.

5. The method according to claim 1, characterized in that In step S4, perform data acquisition from the real-time adjusted measurement point layout data, double the number of sampling points for the local high-temperature region where the temperature exceeds the first temperature threshold. If the temperature exceeds the second temperature threshold, trigger the high-temperature micro-variation monitoring mechanism to record the minute changes once per second to obtain the high-temperature micro-variation characteristic data, including: Step S41, obtain the initial data through the pre-established measurement point layout, and perform the adjustment of doubling the number of sampling points for the local high-temperature region to obtain the extended data acquisition result; Step S42, extract the temperature value from the extended data acquisition result. If the temperature value exceeds the second temperature threshold, activate the micro-variation monitoring mechanism to obtain the minute change data recorded once per second; Step S43, classify the minute change data using the support vector machine algorithm to determine the high-temperature micro-variation characteristic data; Step S44: Calculate the change trend based on the high-temperature micro-variation feature data to obtain the trend direction and amplitude information; Step S45: Adjust the sampling point distribution according to the trend direction and amplitude information to obtain the optimized measuring point layout data; Step S46: Re-collect data from the optimized measuring point layout data, determine whether there are still temperature-exceeding areas, and obtain the updated high-temperature area distribution; Step S47: Repeat the above micro-variation monitoring and feature extraction for the updated high-temperature area distribution to obtain the final high-temperature micro-variation feature data.

6. The method according to claim 1, characterized in that, In the said Step S5, analyze the temperature gradient change trend based on the high-temperature micro-variation feature data, extract key areas from the areas where the temperature gradient is greater than the temperature gradient threshold to dynamically adjust parameters, and determine the optimized measuring point density distribution, including: Step S51: Obtain the temperature gradient values from the high-temperature micro-variation feature data and generate a change trend distribution using the gradient calculation method; Step S52: According to the change trend distribution, use the threshold judgment method to extract the areas where the temperature gradient is greater than the temperature gradient threshold and determine the key area range; Step S53: For the key area range, use the Kriging interpolation method to adjust parameters and generate a dynamically adjusted parameter set; Step S54: Obtain the measuring point distribution characteristics from the dynamically adjusted parameter set, determine whether the measuring point density is greater than 10 per square kilometer, and determine the preliminary density distribution; Step S55: Through the preliminary density distribution, use the Thiessen polygon method to optimize the measuring point layout and generate the optimized measuring point density distribution; Step S56: Extract the distribution plan from the optimized measuring point density distribution, determine whether the plan covers more than 90% of the high-temperature micro-variation feature data area, and determine the final distribution plan; Step S57: According to the final distribution plan, use ArcGIS to generate the visualization result of the high-temperature micro-variation feature data to obtain the complete analysis output.

7. The method according to claim 1, characterized in that In the said Step S6, reconfigure the computing resources from the optimized measuring point density distribution. If the computing resource occupancy is lower than the resource threshold, reduce the measuring point density in the stable areas where the temperature change rate is lower than the second change rate threshold by 30% to obtain the resource-optimized acquisition plan, including: Step S61: Obtain the computing resource occupancy data through the optimized measuring point density distribution and determine whether the resource occupancy is lower than the resource threshold; Step S62: If the resource occupancy is lower than the resource threshold, extract the temperature change rate data from the measuring point density distribution and use the temperature change rate analysis tool to determine the stable areas where the temperature change rate is lower than the second change rate threshold; Step S63: For the measuring point density data in the stable areas, use the density adjustment tool to reduce the measuring point density by 30% to obtain the adjusted density distribution; Step S64: Adopt the adjusted density distribution and use the resource monitoring tool to recalculate the resource occupancy to determine whether the resource optimization requirements are met; Step S65: According to the optimized resource status, use the rule engine to generate a new acquisition plan to obtain the resource-optimized measuring point configuration; Step S66: Extract the temperature change rate and resource occupancy data from the new acquisition plan and use the optimization judgment tool to determine whether further adjustment is still required to obtain the final acquisition plan; Step S67: According to the final acquisition plan, use the density adjustment tool to adjust the measuring point density distribution and determine the operating parameters after resource optimization.

8. The method according to claim 1, characterized in that, In step S7: Continuously monitor the temperature field change according to the acquisition plan after resource optimization, judge the stable state from the area where the micro-variation amplitude of the high temperature is lower than the amplitude threshold, and obtain the final measuring point interval adjustment data, including: Step S71: Obtain the temperature field change data through the acquisition plan, and extract the micro-variation amplitude characteristics for the high temperature area; Step S72: Judge whether it is lower than the amplitude threshold from the high temperature micro-variation amplitude data. If it is lower than the amplitude threshold, determine that the area reaches the stable state; Step S73: Based on the temperature distribution characteristics of the stable state area, calculate the preliminary adjustment value of the measuring point interval; Step S74: Use the continuously monitored data to verify the measuring point interval adjustment value, and determine the accuracy of the adjustment value by comparing the temperature change amplitudes before and after the adjustment; Step S75: Conduct resource optimization processing on the adjustment value to generate an optimized measuring point distribution plan; Step S76: Update the acquisition plan according to the optimized measuring point distribution plan to obtain the final temperature field monitoring data; Step S77: Extract the temperature change trend characteristics from the final monitoring data to judge the persistence of the stable state of the temperature field.

9. The method according to claim 1, wherein In step S8: Update the acquisition frequency of the sensor array from the final measuring point interval adjustment data, and co-optimize the algorithm parameters for the temperature change rate and local high temperature characteristics to make the temperature evaluation error less than 1°C and obtain the stable high temperature evaluation data, including: Step S81: Obtain the initial acquisition frequency data through the sensor array, and adjust the acquisition frequency according to the measuring point interval to obtain the preliminary frequency distribution; Step S82: Extract the temperature data from the preliminary frequency distribution, use the difference method to calculate the temperature change rate, extract the change trend from the temperature change rate, and determine the basis for dynamic adjustment; Step S83: If the change trend exceeds the change threshold, adjust the algorithm parameters by the gradient descent method to obtain the optimized parameter set; Step S84: Process the local high temperature data with the optimized parameter set, and extract the high temperature distribution from the local high temperature characteristics to obtain the feature enhanced data; Step S85: Update the acquisition frequency through the feature enhanced data, recalculate the change value for the temperature change rate, and judge whether the evaluation error is reduced; Step S86: If the evaluation error does not meet the standard, process the high temperature characteristics by the random forest algorithm to obtain the stable high temperature data; Step S87: Adjust the operating frequency of the sensor array according to the stable high temperature data, and generate the final high temperature evaluation data from the adjusted frequency.

Images