CN117471227A

CN117471227A - Automobile wire harness parameter performance test method and test system

Info

Publication number: CN117471227A
Application number: CN202311820441.1A
Authority: CN
Inventors: 吕杰中
Original assignee: Shenzhen Emtek Co ltd
Current assignee: Shenzhen Emtek Co ltd
Priority date: 2023-12-27
Filing date: 2023-12-27
Publication date: 2024-01-30
Anticipated expiration: 2043-12-27
Also published as: CN117471227B

Abstract

The invention relates to the field of artificial intelligence, and discloses an automobile wire harness parameter performance test method and system, which are used for improving the accuracy of automobile wire harness parameter performance test. The method comprises the following steps: carrying out electric parameter measurement and signal transmission test on the automobile wire harness based on various different environmental parameter combinations to obtain electric measurement data and signal transmission data; performing attribute classification and feature extraction to obtain multiple electrical parameters and electrical measurement feature sets, multiple signal parameters and signal transmission feature sets; analyzing influence factors to obtain influence weights; performing feature weighting and vector conversion to obtain an electrical measurement feature vector and a signal transmission feature vector; and inputting the electrical measurement feature vector and the signal transmission feature vector into an automobile wire harness parameter performance analysis model to perform parameter performance analysis and wire harness fault prediction, so as to obtain a target wire harness performance index and a target fault probability prediction value.

Description

Automobile wire harness parameter performance test method and test system

Technical Field

The invention relates to the field of artificial intelligence, in particular to a method and a system for testing the performance of automobile wire harness parameters.

Background

The automobile wire harness is an important electrical component in the vehicle and is responsible for connecting various sensors, control units, lamplight, motors and other devices to realize electrical signal transmission in the vehicle. As the level of automotive electronics increases, the complexity and importance of vehicle wiring harnesses is also increasing. To ensure performance, safety and reliability of a vehicle, it is becoming critical to conduct comprehensive parametric performance testing and fault prediction on automotive wiring harnesses.

Modern automotive wiring harnesses are commonly used under a variety of environmental conditions, including different temperatures, humidities and vibration frequencies. Therefore, research on how to perform comprehensive electrical parameter measurement and signal transmission test under various environmental parameter combinations and how to effectively analyze the test data becomes a key problem for improving the performance test efficiency and accuracy of the automobile wire harness.

Disclosure of Invention

The invention provides a method and a system for testing the performance of automobile wire harness parameters, which are used for improving the accuracy of the performance test of the automobile wire harness parameters.

The first aspect of the invention provides a method for testing the parameter performance of an automobile wire harness, which comprises the following steps:

Based on a plurality of different environmental parameter combinations, carrying out electric parameter measurement and signal transmission test on the automobile wire harness to obtain electric measurement data and signal transmission data of each environmental parameter combination;

performing attribute classification and feature extraction on the electrical measurement data to obtain multiple electrical parameters and electrical measurement feature sets, and performing attribute classification and feature extraction on the signal transmission data to obtain multiple signal parameters and signal transmission feature sets;

performing influence factor analysis on multiple environmental parameters and the multiple electrical parameters to obtain a first influence weight, and performing influence factor analysis on multiple environmental parameters and the multiple signal parameters to obtain a second influence weight;

performing feature weighting and vector conversion on the electrical measurement feature set based on the first influence weight to obtain an electrical measurement feature vector, and performing feature weighting and vector conversion on the signal transmission feature set based on the second influence weight to obtain a signal transmission feature vector;

inputting the electrical measurement feature vector and the signal transmission feature vector into a preset automobile wire harness parameter performance analysis model to perform parameter performance analysis and wire harness fault prediction, and obtaining a target wire harness performance index and a target fault probability prediction value.

With reference to the first aspect, in a first implementation manner of the first aspect of the present invention, the performing, based on a plurality of different environmental parameter combinations, electrical parameter measurement and signal transmission testing on an automotive harness to obtain electrical measurement data and signal transmission data of each environmental parameter combination includes:

defining an environmental parameter combination, the environmental parameter combination comprising: temperature, humidity and vibration frequency;

acquiring a temperature tolerance range of an automobile wire harness, dividing a plurality of corresponding gradient test temperatures according to the temperature tolerance range, acquiring a humidity parameter interval of the automobile wire harness, dividing a plurality of corresponding gradient test humidities according to the humidity parameter interval, acquiring a vibration frequency threshold of the automobile wire harness, and dividing a plurality of corresponding gradient test vibration frequencies according to the vibration frequency threshold;

performing parameter combination on the plurality of gradient test temperatures, the plurality of gradient test humidity and the plurality of gradient test vibration frequencies to generate a plurality of different environment parameter combinations;

based on the plurality of different environment parameter combinations, performing performance test on the automobile wire harness, performing electrical parameter measurement on the automobile wire harness to obtain original measurement data of each environment parameter combination, and performing signal transmission test on the automobile wire harness to obtain original transmission data of each environment parameter combination;

And respectively carrying out data denoising and data standardization processing on the original measurement data and the original transmission data to obtain electric measurement data and signal transmission data of each environment parameter combination.

With reference to the first aspect, in a second implementation manner of the first aspect of the present invention, performing attribute classification and feature extraction on the electrical measurement data to obtain multiple electrical parameters and electrical measurement feature sets, and performing attribute classification and feature extraction on the signal transmission data to obtain multiple signal parameters and signal transmission feature sets, where the method includes:

acquiring a plurality of electrical parameter tags, the plurality of electrical parameter tags comprising: the method comprises the steps of obtaining a plurality of signal transmission indexes including transmission rate, signal-to-noise ratio and signal jitter simultaneously by using current, voltage and resistance;

performing attribute classification on the electrical measurement data based on the plurality of electrical parameter labels to obtain a plurality of electrical parameters, and performing attribute classification on the signal transmission data based on the plurality of signal transmission indexes to obtain a plurality of signal parameters;

respectively performing parameter curve fitting on the plurality of electrical parameters to obtain a plurality of electrical parameter curves, and respectively performing parameter curve fitting on the plurality of signal parameters to obtain a plurality of signal parameter curves;

Extracting curve characteristic points of the plurality of electrical parameter curves respectively to obtain electrical measurement characteristics of each electrical parameter, and carrying out set conversion on the electrical measurement characteristics of each electrical parameter to obtain an electrical measurement characteristic set;

and respectively extracting curve characteristic points of the plurality of signal parameter curves to obtain signal transmission characteristics of each signal parameter, and performing set conversion on the signal transmission characteristics of each signal parameter to obtain a signal transmission characteristic set.

With reference to the first aspect, in a third implementation manner of the first aspect of the present invention, performing an influence factor analysis on a plurality of environmental parameters and the plurality of electrical parameters to obtain a first influence weight, and performing an influence factor analysis on a plurality of environmental parameters and the plurality of signal parameters to obtain a second influence weight, where the method includes:

performing correlation analysis on a plurality of environmental parameters and a plurality of electrical parameters to obtain a first correlation coefficient of each environmental parameter and a plurality of electrical parameters;

analyzing the importance of each environmental parameter and each electrical parameter according to the first correlation coefficient to obtain a first initial weight corresponding to each electrical measurement characteristic;

Inputting the first initial weight into a preset first single-factor cloud model to carry out influence weight solving to obtain a first influence weight corresponding to each electrical measurement characteristic;

performing correlation analysis on multiple environmental parameters and the multiple signal parameters to obtain a second correlation coefficient of each environmental parameter and the multiple signal parameters;

analyzing the importance of each environmental parameter and signal parameter according to the second correlation coefficient to obtain a second initial weight corresponding to each signal transmission characteristic;

and inputting the second initial weight into a preset second single-factor cloud model to carry out influence weight solving, so as to obtain a second influence weight corresponding to each electrical measurement feature.

With reference to the first aspect, in a fourth implementation manner of the first aspect of the present invention, the performing feature weighting and vector conversion on the electrical measurement feature set based on the first impact weight to obtain an electrical measurement feature vector, and performing feature weighting and vector conversion on the signal transmission feature set based on the second impact weight to obtain a signal transmission feature vector, where the performing step includes:

based on the first influence weight corresponding to each electrical measurement feature, respectively carrying out weighted calculation on each electrical measurement feature in the electrical measurement feature set to obtain a plurality of weighted measurement features of each environmental parameter combination;

Carrying out feature serialization on a plurality of weighted measurement features of each environment parameter combination to generate a measurement feature sequence of each environment parameter combination, and carrying out normalized vector mapping on the measurement feature sequences to obtain an electrical measurement feature vector of each environment parameter combination;

based on the second influence weight corresponding to each electrical measurement feature, respectively carrying out weighted calculation on each signal transmission feature in the signal transmission feature set to obtain a plurality of weighted transmission features of each environment parameter combination;

and carrying out feature serialization on a plurality of weighted transmission features of each environment parameter combination to generate a transmission feature sequence of each environment parameter combination, and carrying out normalized vector mapping on the transmission feature sequence to obtain signal transmission feature vectors of each environment parameter combination.

With reference to the first aspect, in a fifth implementation manner of the first aspect of the present invention, inputting the electrical measurement feature vector and the signal transmission feature vector into a preset automotive harness parameter performance analysis model to perform parameter performance analysis and harness fault prediction, to obtain a target harness performance index and a target fault probability prediction value, includes:

Vector fusion is carried out on the electrical measurement feature vector and the signal transmission feature vector, and a target feature evaluation vector of each environmental parameter combination is generated;

inputting the target feature evaluation vector into a preset automobile wire harness parameter performance analysis model, wherein the automobile wire harness parameter performance analysis model comprises a parameter performance analysis network and a wire harness fault prediction network;

respectively extracting features of the target feature evaluation vectors through a double-layer bidirectional threshold circulation unit in the parameter performance analysis network to obtain target high-dimensional feature vectors of each environmental parameter combination, and carrying out parameter performance regression analysis on the target high-dimensional feature vectors through a logistic regression layer in the parameter performance analysis network to obtain target harness performance indexes;

and respectively carrying out harness fault prediction on the target feature evaluation vectors of each environmental parameter combination through the harness fault prediction network to obtain a target fault probability prediction value.

With reference to the first aspect, in a sixth implementation manner of the first aspect of the present invention, the performing, by the wire harness fault prediction network, wire harness fault prediction on the target feature evaluation vectors of each environmental parameter combination to obtain a target fault probability prediction value includes:

Inputting the target feature evaluation vectors into the harness fault prediction network, respectively, the harness fault prediction network comprising: a plurality of bi-directional long short time memory layers, a first full connection layer, and a second full connection layer;

extracting features of the target feature evaluation vectors of each environment parameter combination through each two-way long and short-time memory layer respectively to obtain a plurality of target hidden feature vectors;

performing feature fusion on the plurality of target hidden feature vectors through the first full-connection layer to obtain target fusion hidden features;

and predicting the probability of the harness failure of the target fusion hidden feature through the second full-connection layer to obtain a predicted value of the probability of the target failure.

The second aspect of the invention provides an automobile wire harness parameter performance test system, which comprises:

the test module is used for carrying out electric parameter measurement and signal transmission test on the automobile wire harness based on a plurality of different environment parameter combinations to obtain electric measurement data and signal transmission data of each environment parameter combination;

the characteristic extraction module is used for carrying out attribute classification and characteristic extraction on the electrical measurement data to obtain a plurality of electrical parameters and electrical measurement characteristic sets, and carrying out attribute classification and characteristic extraction on the signal transmission data to obtain a plurality of signal parameters and signal transmission characteristic sets;

The analysis module is used for carrying out influence factor analysis on various environmental parameters and the various electrical parameters to obtain a first influence weight, and carrying out influence factor analysis on various environmental parameters and the various signal parameters to obtain a second influence weight;

the conversion module is used for carrying out feature weighting and vector conversion on the electrical measurement feature set based on the first influence weight to obtain an electrical measurement feature vector, and carrying out feature weighting and vector conversion on the signal transmission feature set based on the second influence weight to obtain a signal transmission feature vector;

and the prediction module is used for inputting the electrical measurement feature vector and the signal transmission feature vector into a preset automobile wire harness parameter performance analysis model to perform parameter performance analysis and wire harness fault prediction, so as to obtain a target wire harness performance index and a target fault probability prediction value.

A third aspect of the present invention provides an automotive harness parameter performance test apparatus, comprising: a memory and at least one processor, the memory having instructions stored therein; the at least one processor invokes the instructions in the memory to cause the automotive harness parameter performance test device to perform the automotive harness parameter performance test method described above.

A fourth aspect of the present invention provides a computer-readable storage medium having instructions stored therein that, when run on a computer, cause the computer to perform the above-described automotive harness parameter performance test method.

According to the technical scheme provided by the invention, the electrical parameter measurement and the signal transmission test are carried out on the automobile wire harness based on various different environmental parameter combinations, so that electrical measurement data and signal transmission data are obtained; performing attribute classification and feature extraction to obtain multiple electrical parameters and electrical measurement feature sets, multiple signal parameters and signal transmission feature sets; analyzing influence factors to obtain influence weights; performing feature weighting and vector conversion to obtain an electrical measurement feature vector and a signal transmission feature vector; the invention can more comprehensively evaluate the performance of the automobile wire harness under various actual working conditions by testing based on various different environment parameter combinations, and is beneficial to improving the authenticity and reliability of the test. The system adopts the attribute classification and the feature extraction of the electrical parameters and the signal transmission data, so that the system can extract key information from a large amount of test data, thereby being beneficial to reducing the complexity of the data and improving the sensitivity to the key parameters. Influence factor analysis on environmental parameters and electrical parameters is introduced, and the influence degree of each factor on the performance of the automobile wire harness is accurately described through weight calculation, so that the performance problem and the optimization direction can be more accurately positioned. Through feature weighting and vector conversion, each test feature is integrated into a more comprehensive electrical measurement feature vector and a signal transmission feature vector, so that model input is simplified, model processing efficiency is improved, and through inputting the feature vector into a preset automobile wire harness parameter performance analysis model, wire harness performance can be comprehensively analyzed, wire harness fault prediction can be performed, and further accuracy of automobile wire harness parameter performance test is improved.

Drawings

FIG. 1 is a schematic diagram of an embodiment of a method for testing the performance of automotive harness parameters according to an embodiment of the present invention;

FIG. 2 is a flow chart of attribute classification and feature extraction in an embodiment of the invention;

FIG. 3 is a flow chart of influence factor analysis in an embodiment of the invention;

FIG. 4 is a flow chart of feature weighting and vector conversion in accordance with an embodiment of the present invention;

FIG. 5 is a schematic diagram of an embodiment of an automotive harness parametric performance test system according to an embodiment of the present invention;

fig. 6 is a schematic diagram of an embodiment of an apparatus for testing the performance of parameters of an automotive harness according to an embodiment of the present invention.

Detailed Description

The embodiment of the invention provides a method and a system for testing the performance of automobile wire harness parameters, which are used for improving the accuracy of the performance test of the automobile wire harness parameters. The terms "first," "second," "third," "fourth" and the like in the description and in the claims and in the above drawings, if any, are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments described herein may be implemented in other sequences than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed or inherent to such process, method, article, or apparatus.

For ease of understanding, the following describes a specific flow of an embodiment of the present invention, referring to fig. 1, and an embodiment of a method for testing the performance of an automotive harness parameter in an embodiment of the present invention includes:

s101, carrying out electric parameter measurement and signal transmission test on an automobile wire harness based on a plurality of different environment parameter combinations to obtain electric measurement data and signal transmission data of each environment parameter combination;

it is to be understood that the execution body of the present invention may be an automobile wire harness parameter performance test system, and may also be a terminal or a server, which is not limited herein. The embodiment of the invention is described by taking a server as an execution main body as an example.

Specifically, the server defines a combination of environmental parameters including temperature, humidity, and vibration frequency. These parameters will be used to test the performance of the automotive wiring harness. For example, temperature may be defined in degrees celsius (° C), humidity may be defined in percent, and vibration frequency may be defined in hertz (Hz). To test performance in different environments, the tolerance ranges of the automotive harness in terms of these parameters were obtained. For example, the temperature tolerance range may be between-40 ℃ and 85 ℃, the humidity parameter interval may be between 20% and 90%, and the vibration frequency threshold may be between 10Hz and 100 Hz. These ranges will help determine the gradient and range of the test. Depending on the acquired environmental parameter range, multiple gradients may be divided, for example one gradient per 10 ℃, one gradient per 10% humidity, and one gradient per 10 Hz. By combining these gradients, a variety of different combinations of environmental parameters can be generated. For example, the test may be performed at-40 ℃, 20% humidity and 10Hz vibration frequency, or at 85 ℃, 90% humidity and 100Hz vibration frequency. This will create a variety of different test conditions. And performing performance test on the automobile wire harness based on the generated different environment parameter combinations. This includes electrical parameter measurement and signal transmission testing. Raw measurement data and raw transmission data are collected under each test condition. These data will capture the performance of the harness under different environmental conditions. And carrying out data denoising and data standardization processing on the original measurement data and the original transmission data. This will help reduce interference and noise in the data and make the data comparable and analyzable. Denoising may employ filtering techniques, while normalization may scale the data to the same scale.

S102, performing attribute classification and feature extraction on the electrical measurement data to obtain multiple electrical parameters and electrical measurement feature sets, and performing attribute classification and feature extraction on the signal transmission data to obtain multiple signal parameters and signal transmission feature sets;

specifically, the server obtains a plurality of electrical parameter tags and a plurality of signal transmission indexes, such as current, voltage, resistance, transmission rate, signal-to-noise ratio and signal jitter. These parameters and indices will be used for data classification and feature extraction to comprehensively evaluate the performance of the automotive wiring harness. The electrical measurement data and the signal transmission data are classified to obtain a plurality of electrical parameters and signal parameters. And classifying parameters such as current, voltage, resistance and the like in the electrical measurement data according to the electrical parameter labels. Meanwhile, indexes such as transmission rate, signal-to-noise ratio, signal jitter and the like in the signal transmission data are classified according to the signal transmission indexes. This will help organize the data for further analysis. After each attribute classification, information about the electrical and signal parameters is extracted from the raw data using feature extraction techniques, such as statistical, spectral, time-domain, and frequency-domain features. For example, for current data, statistical features such as mean, variance, peak, etc. may be extracted, or spectral analysis may be performed to obtain frequency features. The server performs parameter curve fitting to obtain a plurality of electrical parameter curves and a plurality of signal parameter curves. For each electrical and signal parameter, a curve fit is performed using a suitable mathematical model. For example, for current-time data, linear regression or polynomial fitting may be used to obtain a fitted model of the current curve. Also, for transmission rate data, curve fitting may be employed to obtain a model of the change in rate over time. And the server extracts curve characteristic points of the parameter curve to obtain an electrical measurement characteristic and a signal transmission characteristic. On the electrical parameter curve and the signal parameter curve, key feature points such as a maximum value, a minimum value, an inflection point, a peak and a trough can be extracted. These feature points can be used to describe the properties of the curve, such as the peak value of the current or the maximum value of the signal transmission rate. The server performs set conversion on the electrical measurement characteristics and the signal transmission characteristics to obtain an electrical measurement characteristic set and a signal transmission characteristic set. Feature points and feature values extracted from each of the electrical parameters and signal parameters are combined into a feature set. These feature sets will contain comprehensive information about the electrical measurement data and signaling data, which can be used for performance analysis and fault prediction. For example, assume that one of the electrical parameters is current. The server classifies the attributes of the current data and extracts statistical characteristics such as mean, variance, peak value and the like. The server uses curve fitting techniques to fit the current data to a curve model, such as linear regression. The server extracts the maximum and minimum values of the curve as the electrical measurement characteristics of the current. Also, for signal transmission data, the server extracts the maximum value of the transmission rate and the average value of the signal-to-noise ratio as the signal transmission characteristics. All of these feature sets are converted into one electrical measurement feature set and one signaling feature set that will help to more fully understand the performance and potential failure of the harness.

S103, performing influence factor analysis on multiple environmental parameters and multiple electrical parameters to obtain a first influence weight, and performing influence factor analysis on multiple environmental parameters and multiple signal parameters to obtain a second influence weight;

it should be noted that the server performs correlation analysis on a plurality of environmental parameters and a plurality of electrical parameters to obtain a first correlation coefficient of each environmental parameter and a plurality of electrical parameters. For example, statistical methods, such as pearson correlation coefficients or spearman scale correlation coefficients, are used to measure the correlation between the environmental parameter and the electrical parameter. This will produce a series of first correlation coefficients reflecting the degree of correlation between the respective environmental parameter and the electrical parameter. The server analyzes the importance of each environmental parameter and each electrical parameter according to the first correlation coefficient to obtain a first initial weight corresponding to each electrical measurement feature. And determining the importance of each environmental parameter to the electrical parameter according to the magnitude of the first correlation coefficient. Higher correlation coefficients represent greater importance. This will result in a first initial weight for each electrical measurement feature. And the server inputs the first initial weight into a preset first single-factor cloud model to carry out influence weight solving so as to obtain a first influence weight corresponding to each electrical measurement characteristic. The first initial weight is taken into account using a one-factor cloud model or a weight distribution model to determine a first impact weight for each electrical measurement feature. This will take into account the influence of the individual features in combination, depending on the relevance and importance. The server performs correlation analysis on the plurality of environmental parameters and the plurality of signal parameters to obtain a second correlation coefficient of each environmental parameter and the plurality of signal parameters. The correlation between the environmental parameter and the signal parameter is measured using the same statistical method, such as pearson correlation coefficient or spearman scale correlation coefficient. This will produce a series of second correlation coefficients reflecting the degree of correlation between the respective environmental parameter and the signal parameter. The server analyzes the importance of each environmental parameter and signal parameter according to the second correlation coefficient to obtain a second initial weight corresponding to each signal transmission characteristic. And determining the importance of each environmental parameter to the signal parameter according to the magnitude of the second correlation coefficient. Higher correlation coefficients represent greater importance. This will result in a second initial weight for each signal transmission feature. And the server inputs the second initial weight into a preset second single-factor cloud model to carry out influence weight solving so as to obtain a second influence weight corresponding to each signal transmission characteristic. Correlation and importance are comprehensively considered by using the second initial weight and the single factor cloud model to determine a second impact weight of each signal transmission characteristic. For example, assume that there are a variety of environmental parameters (temperature, humidity, vibration frequency) and a variety of electrical parameters (current, voltage, resistance). The server performs correlation analysis to find that there is a relatively high positive correlation between current and temperature, a negative correlation between voltage and humidity, and no obvious correlation between resistance and vibration frequency. According to the result of the correlation analysis, the server determines that the current has the greatest effect on temperature and the voltage has the greatest effect on humidity. This results in a first initial weight for each electrical measurement feature. The server uses a single factor cloud model to consider the first initial weights to determine a first impact weight for each electrical measurement feature in consideration of both relevance and importance. Also, the server performs a correlation analysis to find a correlation between the environmental parameter and the signal parameter. For example, there is a certain correlation between transmission rate and temperature. Based on the results of the correlation analysis, the server determines that the temperature has a greater impact on the transmission rate. This results in a second initial weight for each signal transmission characteristic. The server uses the second initial weights and the second one-factor cloud model to consider correlations and importance to determine a second impact weight for each signal transmission characteristic. These first and second impact weights will be used for further performance analysis and fault prediction to fully understand the performance and safety of the automotive wiring harness. This approach may help manufacturers to discover potential problems ahead of time, thereby improving the reliability and safety of automotive wiring harnesses.

S104, carrying out feature weighting and vector conversion on the electrical measurement feature set based on the first influence weight to obtain an electrical measurement feature vector, and carrying out feature weighting and vector conversion on the signal transmission feature set based on the second influence weight to obtain a signal transmission feature vector;

specifically, according to the first influence weight corresponding to each electrical measurement feature, the server performs weighted calculation on each electrical measurement feature in the electrical measurement feature set. This weighting process takes into account the importance of each feature under different combinations of environmental parameters. The result of the weighted calculation is a plurality of weighted measurement features for each combination of environmental parameters that reflect the importance of the electrical parameters under different environmental conditions. The server performs feature serialization for the plurality of weighted measurement features. The purpose of feature serialization is to organize the features into a sequence in a certain order for subsequent processing. In this step, the server generates a sequence of measured characteristics for each combination of environmental parameters. The feature sequence is normalized vector mapped to ensure that the features have the same scale. Because different features have different units of measure and ranges of values. Normalization maps them into similar ranges for easier comparison and analysis. The result is an electrical measurement feature vector for each combination of environmental parameters, where each vector contains weighted and normalized measurement features. For the signal transmission feature, the server uses a similar method. Based on the second influence weight corresponding to each signal transmission characteristic, the server performs weighted calculation on each signal transmission characteristic in the signal transmission characteristic set to obtain a plurality of weighted transmission characteristics of each environment parameter combination. These plurality of weighted transmission features are feature serialized to generate a transmission feature sequence for each combination of environmental parameters. And carrying out normalized vector mapping on the transmission characteristic sequences to obtain signal transmission characteristic vectors of each environment parameter combination.

S105, inputting the electrical measurement feature vector and the signal transmission feature vector into a preset automobile wire harness parameter performance analysis model to perform parameter performance analysis and wire harness fault prediction, and obtaining a target wire harness performance index and a target fault probability prediction value.

Specifically, the server combines the electrical measurement feature vector and the signal transmission feature vector to generate a target feature evaluation vector for each combination of environmental parameters. This step is to integrate the different types of features together for subsequent analysis. And inputting the target characteristic evaluation vector into a preset automobile wire harness parameter performance analysis model. This model includes a parametric performance analysis network and a harness fault prediction network. Together they are used to analyze the performance of the wiring harness and the predicted faults. In the parameter performance analysis network, a double-layer bidirectional threshold circulation unit is used for extracting the characteristics of the target characteristic evaluation vector. This step helps capture key features in the data to better understand the performance of the harness. The result is a target high-dimensional feature vector for each combination of environmental parameters. And then, carrying out parameter performance regression analysis on the target high-dimensional feature vector through a logistic regression layer. This process helps determine performance metrics of the wiring harness, such as current, voltage, and resistance. The result is target harness performance metrics that can be used to evaluate the performance level of the harness. In the wire harness fault prediction network, the wire harness fault prediction is carried out on the target characteristic evaluation vector of each environmental parameter combination. This step is used to estimate the probability of a wire harness failure. The result is a target fault probability prediction value that helps predict potential fault conditions for the harness. Through the series of steps, the server can comprehensively analyze the electrical measurement characteristics and the signal transmission characteristics to obtain the performance index and the fault probability of the wire harness. This provides critical information for maintaining and improving the automotive wiring harness to ensure its performance and reliability. For example, assume that the server obtains an electrical measurement feature vector and a signal transmission feature vector, and then merges them into a target feature evaluation vector. By inputting these vectors into the automotive harness parametric performance analysis model, the server derives the performance metrics of the harness, such as values of current, voltage, and resistance. Meanwhile, the server can also obtain a predicted value of the probability of the fault of the wire harness so as to predict potential problems in advance.

In the embodiment of the invention, the electrical parameter measurement and the signal transmission test are carried out on the automobile wire harness based on a plurality of different environmental parameter combinations, so as to obtain electrical measurement data and signal transmission data; performing attribute classification and feature extraction to obtain multiple electrical parameters and electrical measurement feature sets, multiple signal parameters and signal transmission feature sets; analyzing influence factors to obtain influence weights; performing feature weighting and vector conversion to obtain an electrical measurement feature vector and a signal transmission feature vector; the invention can more comprehensively evaluate the performance of the automobile wire harness under various actual working conditions by testing based on various different environment parameter combinations, and is beneficial to improving the authenticity and reliability of the test. The system adopts the attribute classification and the feature extraction of the electrical parameters and the signal transmission data, so that the system can extract key information from a large amount of test data, thereby being beneficial to reducing the complexity of the data and improving the sensitivity to the key parameters. Influence factor analysis on environmental parameters and electrical parameters is introduced, and the influence degree of each factor on the performance of the automobile wire harness is accurately described through weight calculation, so that the performance problem and the optimization direction can be more accurately positioned. Through feature weighting and vector conversion, each test feature is integrated into a more comprehensive electrical measurement feature vector and a signal transmission feature vector, so that model input is simplified, model processing efficiency is improved, and through inputting the feature vector into a preset automobile wire harness parameter performance analysis model, wire harness performance can be comprehensively analyzed, wire harness fault prediction can be performed, and further accuracy of automobile wire harness parameter performance test is improved.

In a specific embodiment, the process of executing step S101 may specifically include the following steps:

(1) Defining an environmental parameter combination, the environmental parameter combination comprising: temperature, humidity and vibration frequency;

(2) Acquiring a temperature tolerance range of an automobile wire harness, dividing a plurality of corresponding gradient test temperatures according to the temperature tolerance range, acquiring a humidity parameter interval of the automobile wire harness, dividing a plurality of corresponding gradient test humidities according to the humidity parameter interval, acquiring a vibration frequency threshold of the automobile wire harness, and dividing a plurality of corresponding gradient test vibration frequencies according to the vibration frequency threshold;

(3) Parameter combination is carried out on a plurality of gradient test temperatures, a plurality of gradient test humidity and a plurality of gradient test vibration frequencies, so as to generate a plurality of different environment parameter combinations;

(4) Based on a plurality of different environment parameter combinations, performing performance test on the automobile wire harness, performing electrical parameter measurement on the automobile wire harness to obtain original measurement data of each environment parameter combination, and performing signal transmission test on the automobile wire harness to obtain original transmission data of each environment parameter combination;

(5) And respectively carrying out data denoising and data standardization processing on the original measurement data and the original transmission data to obtain electric measurement data and signal transmission data of each environmental parameter combination.

Specifically, the server defines a combination of environmental parameters including temperature, humidity, and vibration frequency. These parameters are important factors affecting the performance of automotive wiring harnesses. The temperature range is a critical environmental parameter because the automotive wiring harness operates in cold winter and hot summer. For testing, it is necessary to obtain the temperature tolerance range of the automotive harness, i.e. under which temperature conditions it can function properly. According to this range, the temperature is divided into a plurality of gradients to cover the entire range. Humidity is also a critical environmental parameter, as humid conditions adversely affect the wire harness. Also, it is necessary to acquire a humidity parameter section of the automobile harness and divide a plurality of gradient test humidities according to the section. The vibration frequency threshold refers to an upper limit of the vibration frequency that the wire harness can withstand. This threshold value needs to be obtained and a plurality of gradient test vibration frequencies are divided according to it. Parameter combinations are performed on the plurality of gradient test temperatures, humidity and vibration frequencies to generate a plurality of different environmental parameter combinations. This will ensure that the server covers a variety of actual operating conditions. Based on these different environmental parameter combinations, performance tests were performed on the automotive wiring harness. This includes electrical parameter measurements and signal transmission testing of the wiring harness. Through these tests, the server obtains raw measurement data and raw transmission data for each combination of environmental parameters. And carrying out data denoising and data standardization processing on the original measured data and the original transmission data to obtain electric measured data and signal transmission data of each environment parameter combination. The denoising process is helpful to eliminate noise and interference introduced in the test process so as to ensure the accuracy of data. At the same time, data normalization ensures that all data have similar dimensions for subsequent analysis and comparison. For example, assume that the server first determines that the harness is operating properly in the temperature range of-40 ℃ to 85 ℃, the humidity range is 20% to 90%, and the vibration frequency threshold is 100Hz. The server divides the temperature into one gradient every 10 ℃, the humidity into one gradient every 10%, and the vibration frequency into one gradient every 20 Hz. This results in a variety of different combinations of environmental parameters, such as-30 ℃, 50% humidity, 80Hz vibration frequency, etc. The server performs performance testing, including electrical parameter measurement and signaling testing, on each combination. For electrical parameter measurements, the server records data on current, voltage, and resistance. For signal transmission testing, the server checks for metrics such as transmission rate, signal-to-noise ratio, and signal jitter. Through the data processing step, the server obtains electrical measurement data and signal transmission data for each combination of environmental parameters, which can be used for further performance analysis and fault prediction. This approach can ensure the reliability and performance of automotive wiring harnesses under various environmental conditions.

In a specific embodiment, as shown in fig. 2, the process of executing step S102 may specifically include the following steps:

s201, acquiring a plurality of electrical parameter labels, wherein the plurality of electrical parameter labels comprise: the method comprises the steps of obtaining a plurality of signal transmission indexes including a transmission rate, a signal-to-noise ratio and signal jitter simultaneously by using current, voltage and resistance;

s202, classifying the attributes of the electrical measurement data based on a plurality of electrical parameter labels to obtain a plurality of electrical parameters, and classifying the attributes of the signal transmission data based on a plurality of signal transmission indexes to obtain a plurality of signal parameters;

s203, respectively performing parameter curve fitting on a plurality of electrical parameters to obtain a plurality of electrical parameter curves, and respectively performing parameter curve fitting on a plurality of signal parameters to obtain a plurality of signal parameter curves;

s204, extracting curve characteristic points of a plurality of electrical parameter curves respectively to obtain electrical measurement characteristics of each electrical parameter, and performing set conversion on the electrical measurement characteristics of each electrical parameter to obtain an electrical measurement characteristic set;

s205, extracting curve characteristic points of the plurality of signal parameter curves respectively to obtain signal transmission characteristics of each signal parameter, and performing set conversion on the signal transmission characteristics of each signal parameter to obtain a signal transmission characteristic set.

In particular, a plurality of electrical parameter tags and a plurality of signal transmission indicators are obtained, the tags including current, voltage, resistance, transmission rate, signal to noise ratio and signal jitter. These parameters and metrics are key factors in evaluating the performance of the wire harness. And classifying the attributes of the electrical measurement data based on the plurality of electrical parameter labels to obtain a plurality of electrical parameters. Meanwhile, based on a plurality of signal transmission indexes, attribute classification is carried out on the signal transmission data so as to obtain a plurality of signal parameters. This classification process may ensure that the server classifies the data according to different attributes, ready for subsequent analysis. A parametric curve fit is performed on the plurality of electrical parameters, which will produce a plurality of electrical parameter curves. Also, a parametric curve fitting is performed on the plurality of signal parameters to obtain a plurality of signal parameter curves. These curves help to understand the trend of the parameter and index changes. And respectively extracting curve characteristic points of the plurality of electrical parameter curves. These feature points may be maxima, minima, slopes, etc. of the curve. These feature point extraction processes will provide electrical measurement features for each electrical parameter. And extracting curve characteristic points of the plurality of signal parameter curves to obtain signal transmission characteristics of each signal parameter. These feature points may include a minimum value of signal-to-noise ratio, a maximum value of transmission rate, etc. And carrying out set conversion on the electrical measurement characteristics of each electrical parameter and the signal transmission characteristics of each signal parameter to obtain an electrical measurement characteristic set and a signal transmission characteristic set. These feature sets will contain data of various feature points and curves for subsequent analysis and modeling. For example, assume that the test parameters include current, voltage, and transmission rate, etc. The server classifies the attributes of the current data to obtain current parameters, and then performs parameter curve fitting to obtain a current parameter curve. Feature points, such as maximum and minimum values, are then extracted from the current parameter curve to construct an electrical measurement feature of the current. Meanwhile, attribute classification is carried out on the transmission rate data to obtain transmission rate parameters, and parameter curve fitting is carried out to obtain a transmission rate parameter curve. Feature points, such as maximum transmission rate, are extracted from the transmission rate parameter curve to construct signal transmission features of the transmission rate. In this way, the server obtains an electrical measurement feature set and a signaling feature set that can be used for further analysis and modeling to evaluate the performance of the wiring harness and predict potential faults.

In a specific embodiment, as shown in fig. 3, the process of executing step S103 may specifically include the following steps:

s301, performing correlation analysis on various environmental parameters and various electrical parameters to obtain a first correlation coefficient of each environmental parameter and the various electrical parameters;

s302, analyzing the importance of each environmental parameter and each electrical parameter according to the first correlation coefficient to obtain a first initial weight corresponding to each electrical measurement characteristic;

s303, inputting a first initial weight into a preset first single-factor cloud model to carry out influence weight solving, so as to obtain a first influence weight corresponding to each electrical measurement characteristic;

s304, performing correlation analysis on various environmental parameters and various signal parameters to obtain a second correlation coefficient of each environmental parameter and various signal parameters;

s305, analyzing the importance of each environmental parameter and signal parameter according to the second correlation coefficient to obtain a second initial weight corresponding to each signal transmission characteristic;

s306, inputting a second initial weight into a preset second single-factor cloud model to carry out influence weight solving, and obtaining a second influence weight corresponding to each electrical measurement feature.

Specifically, a correlation analysis between a plurality of environmental parameters and a plurality of electrical parameters is performed to calculate a first correlation coefficient between each environmental parameter and the plurality of electrical parameters. This will help the server to know how much different environmental factors affect the electrical parameters. For example, the server may find that high temperature has a higher dependence on current and humidity has a lower dependence on voltage. The importance of each of the environmental parameters and the electrical parameters is analyzed based on the first correlation coefficient. This may be achieved by ranking the relevance coefficients. For example, if the temperature and current correlation coefficient is highest, the effect of temperature on current will be considered most important. And inputting the first initial weight into a preset first single-factor cloud model to solve the influence weight. The cloud model is a mathematical model for calculating the impact weights of different factors. This model will take into account the correlation of the various environmental and electrical parameters and assign weights to reflect their extent of influence. Through the model, the server obtains a first impact weight corresponding to each electrical measurement feature. Also, correlation analysis is performed on the plurality of environmental parameters and the plurality of signal parameters to calculate a second correlation coefficient between each environmental parameter and the plurality of signal parameters. This will help the server to know how much different environmental factors affect the signal parameters. The importance of each of the environmental parameters and the signal parameters is analyzed based on the second correlation coefficient. Again, which environmental parameters are most important for the influence of the signal parameters is determined by ranking the correlation coefficients. And inputting the second initial weight into a preset second single-factor cloud model to carry out influence weight solving. This model will take into account the correlation of the various environmental parameters and signal parameters and assign weights to reflect their extent of influence. Through this model, the server obtains a second impact weight corresponding to each signal transmission characteristic. For example, it is assumed that the correlation coefficient between temperature and current is found to be 0.8 and the correlation coefficient between humidity and current is found to be 0.4 after the correlation analysis is performed by the server. This indicates that the temperature has a greater effect on the current. Thus, in cloud model solving, the temperature will be assigned a higher weight to reflect its effect on the current. Also, if the correlation coefficient between the vibration frequency and the transmission rate is 0.7 and the correlation coefficient between the humidity and the transmission rate is 0.5, the vibration frequency will be weighted higher in the cloud model to reflect its influence on the transmission rate. Through these analyses and cloud model solutions, the server determines the impact weights for each of the electrical measurement features and signal transmission features to better understand harness performance and fault prediction. This helps to formulate a more accurate performance assessment and fault prediction model.

In a specific embodiment, as shown in fig. 4, the process of executing step S104 may specifically include the following steps:

s401, respectively carrying out weighted calculation on each electrical measurement feature in the electrical measurement feature set based on the first influence weight corresponding to each electrical measurement feature to obtain a plurality of weighted measurement features of each environmental parameter combination;

s402, carrying out feature serialization on a plurality of weighted measurement features of each environmental parameter combination to generate a measurement feature sequence of each environmental parameter combination, and carrying out normalized vector mapping on the measurement feature sequence to obtain an electrical measurement feature vector of each environmental parameter combination;

s403, respectively carrying out weighted calculation on each signal transmission characteristic in the signal transmission characteristic set based on the second influence weight corresponding to each electrical measurement characteristic to obtain a plurality of weighted transmission characteristics of each environment parameter combination;

s404, carrying out feature serialization on a plurality of weighted transmission features of each environment parameter combination to generate a transmission feature sequence of each environment parameter combination, and carrying out normalized vector mapping on the transmission feature sequence to obtain a signal transmission feature vector of each environment parameter combination.

Specifically, the server performs a weighted calculation on each of the electrical measurement features in the electrical measurement feature set based on the first impact weight corresponding to each of the electrical measurement features. Each electrical measurement feature will get a weight value based on its first impact weight and then multiply it with the actual measurement value. This will generate a plurality of weighted measurement features for each combination of environmental parameters. For example, assume that the server has three electrical measurement features: current, voltage and resistance, and their first impact weights are 0.6, 0.4 and 0.3, respectively. For a particular combination of environmental parameters, the server measures 10A current, 220V voltage, and 5 Ω resistance. The server performs weighted calculation according to the weight to obtain: weighted current=0.6×10a=6, weighted voltage=0.4×220v=88, weighted resistance=0.3×5Ω=1.5. These weighting values represent weighted measurement characteristics for a particular combination of environmental parameters. Feature serialization is performed for a plurality of weighted measurement features for each combination of environmental parameters. This means that the weighting values are combined into a sequence representing the electrical measurement characteristics of each combination of environmental parameters. For example, for the above-described combination of environmental parameters, the server obtains an electrical measurement signature sequence: [6, 88,1.5]. And carrying out normalized vector mapping on the measurement characteristic sequence. This step is to ensure that each feature is on the same scale for comparison and analysis. Typically, normalization may employ a linear transformation, mapping the eigenvalues into a range of 0 to 1. For example, if the server employs linear normalization, the electrical measurement signature sequence described above maps to: [0.06,0.88,0.015]. The same procedure applies to the signal transmission feature. Based on the second impact weight corresponding to each electrical measurement feature, the server performs a weighted calculation on each signal transmission feature in the signal transmission feature set, generates weighted transmission features, and combines them into a signal transmission feature sequence. And carrying out normalized vector mapping on the signal transmission characteristic sequence to obtain a signal transmission characteristic vector. These electrical measurement feature vectors and signal transmission feature vectors will be used for further analysis and performance evaluation to achieve the objectives of automotive harness parametric performance testing.

In a specific embodiment, the process of executing step S105 may specifically include the following steps:

(1) Vector fusion is carried out on the electrical measurement feature vector and the signal transmission feature vector, and a target feature evaluation vector of each environmental parameter combination is generated;

(2) Inputting the target feature evaluation vector into a preset automobile wire harness parameter performance analysis model, wherein the automobile wire harness parameter performance analysis model comprises a parameter performance analysis network and a wire harness fault prediction network;

(3) Respectively extracting features of the target feature evaluation vectors through a double-layer bidirectional threshold circulation unit in the parameter performance analysis network to obtain target high-dimensional feature vectors of each environmental parameter combination, and carrying out parameter performance regression analysis on the target high-dimensional feature vectors through a logistic regression layer in the parameter performance analysis network to obtain target harness performance indexes;

(4) And respectively carrying out harness fault prediction on the target feature evaluation vectors of each environmental parameter combination through a harness fault prediction network to obtain a target fault probability prediction value.

Specifically, the server performs vector fusion on the electrical measurement feature vector and the signal transmission feature vector. This may employ a simple vector join or other fusion method to generate a target feature evaluation vector for each combination of environmental parameters. This step helps to integrate electrical and signal transmission characteristics for a more comprehensive performance assessment. For example, if the electrical measurement feature vector is [0.06,0.88,0.015], the signal transmission feature vector is [0.7,0.9,0.5], then they are simply connected to obtain the target feature evaluation vector: [0.06,0.88,0.015,0.7,0.9,0.5]. The server inputs the target characteristic evaluation vector into a preset automobile wire harness parameter performance analysis model. This model typically includes a parametric performance analysis network and a harness fault prediction network. And through a parameter performance analysis network, particularly a double-layer bidirectional threshold circulation unit and a logistic regression layer, the server performs feature extraction and parameter performance regression analysis on the target feature evaluation vector so as to obtain a target high-dimensional feature vector and a target wire harness performance index of each environment parameter combination. This helps determine the performance of the wire harness under various environmental conditions. For example, through a parametric performance analysis network, a server maps target feature evaluation vectors into high-dimensional feature vectors, and then analyzes these high-dimensional features using a logistic regression layer to obtain target harness performance metrics, such as performance scores or categories. And through a wire harness fault prediction network, the server predicts the wire harness fault of the target feature evaluation vector of each environmental parameter combination so as to obtain a target fault probability prediction value. This helps to estimate the likelihood of a wire harness failing under different conditions. For example, the harness failure prediction network may output a failure probability for each combination of environmental parameters, such as a harness failure probability under high temperature, high humidity, and high vibration frequency conditions. In this way, the server comprehensively considers the performance under the combination of the electrical measurement characteristics, the signal transmission characteristics and different environmental parameters, thereby more comprehensively evaluating the performance of the automobile wire harness and predicting potential faults. This provides a powerful support for improving the reliability and safety of automotive wiring harnesses.

In a specific embodiment, the performing step performs, through a wire harness fault prediction network, wire harness fault prediction on the target feature evaluation vectors of each environmental parameter combination, and the process of obtaining the target fault probability prediction value may specifically include the following steps:

(1) Inputting the target feature evaluation vectors into a harness failure prediction network, respectively, the harness failure prediction network comprising: a plurality of bi-directional long short time memory layers, a first full connection layer, and a second full connection layer;

(2) Extracting features of the target feature evaluation vectors of each environment parameter combination through each two-way long and short-time memory layer respectively to obtain a plurality of target hidden feature vectors;

(3) Feature fusion is carried out on a plurality of target hidden feature vectors through a first full connection layer, so that target fusion hidden features are obtained;

(4) And predicting the probability of the harness failure of the target fusion hidden feature through the second full-connection layer to obtain a predicted value of the probability of the target failure.

In particular, the method comprises the steps of,

the method for testing the performance of the parameters of the automobile wire harness in the embodiment of the invention is described above, and the system for testing the performance of the parameters of the automobile wire harness in the embodiment of the invention is described below, referring to fig. 5, one embodiment of the system for testing the performance of the parameters of the automobile wire harness in the embodiment of the invention includes:

The test module 501 is configured to perform electrical parameter measurement and signal transmission test on an automobile wire harness based on a plurality of different environmental parameter combinations, so as to obtain electrical measurement data and signal transmission data of each environmental parameter combination;

the feature extraction module 502 is configured to perform attribute classification and feature extraction on the electrical measurement data to obtain multiple electrical parameters and electrical measurement feature sets, and perform attribute classification and feature extraction on the signal transmission data to obtain multiple signal parameters and signal transmission feature sets;

the analysis module 503 is configured to perform influence factor analysis on multiple environmental parameters and the multiple electrical parameters to obtain a first influence weight, and perform influence factor analysis on multiple environmental parameters and the multiple signal parameters to obtain a second influence weight;

the conversion module 504 is configured to perform feature weighting and vector conversion on the electrical measurement feature set based on the first impact weight to obtain an electrical measurement feature vector, and perform feature weighting and vector conversion on the signal transmission feature set based on the second impact weight to obtain a signal transmission feature vector;

the prediction module 505 is configured to input the electrical measurement feature vector and the signal transmission feature vector into a preset automotive harness parameter performance analysis model to perform parameter performance analysis and harness fault prediction, so as to obtain a target harness performance index and a target fault probability prediction value.

Through the cooperative cooperation of the components, the electrical parameter measurement and the signal transmission test are carried out on the automobile wire harness based on a plurality of different environmental parameter combinations, so that electrical measurement data and signal transmission data are obtained; performing attribute classification and feature extraction to obtain multiple electrical parameters and electrical measurement feature sets, multiple signal parameters and signal transmission feature sets; analyzing influence factors to obtain influence weights; performing feature weighting and vector conversion to obtain an electrical measurement feature vector and a signal transmission feature vector; the invention can more comprehensively evaluate the performance of the automobile wire harness under various actual working conditions by testing based on various different environment parameter combinations, and is beneficial to improving the authenticity and reliability of the test. The system adopts the attribute classification and the feature extraction of the electrical parameters and the signal transmission data, so that the system can extract key information from a large amount of test data, thereby being beneficial to reducing the complexity of the data and improving the sensitivity to the key parameters. Influence factor analysis on environmental parameters and electrical parameters is introduced, and the influence degree of each factor on the performance of the automobile wire harness is accurately described through weight calculation, so that the performance problem and the optimization direction can be more accurately positioned. Through feature weighting and vector conversion, each test feature is integrated into a more comprehensive electrical measurement feature vector and a signal transmission feature vector, so that model input is simplified, model processing efficiency is improved, and through inputting the feature vector into a preset automobile wire harness parameter performance analysis model, wire harness performance can be comprehensively analyzed, wire harness fault prediction can be performed, and further accuracy of automobile wire harness parameter performance test is improved.

The system for testing the parameter performance of the automobile wire harness in the embodiment of the invention is described in detail from the perspective of a modularized functional entity in fig. 5, and the device for testing the parameter performance of the automobile wire harness in the embodiment of the invention is described in detail from the perspective of hardware processing in the following.

Fig. 6 is a schematic structural diagram of an apparatus for testing performance of automotive harness parameters according to an embodiment of the present invention, where the apparatus 600 may have a relatively large difference due to different configurations or performances, and may include one or more processors (central processing units, CPU) 610 (e.g., one or more processors) and a memory 620, and one or more storage media 630 (e.g., one or more mass storage devices) storing application programs 633 or data 632. Wherein the memory 620 and the storage medium 630 may be transitory or persistent storage. The program stored in the storage medium 630 may include one or more modules (not shown), each of which may include a series of instruction operations in the automobile harness parameter performance test apparatus 600. Still further, the processor 610 may be configured to communicate with the storage medium 630 to execute a series of instruction operations in the storage medium 630 on the vehicle harness parameter performance test apparatus 600.

The automobile harness parameter performance test apparatus 600 may also include one or more power supplies 640, one or more wired or wireless network interfaces 650, one or more input/output interfaces 660, and/or one or more operating systems 631, such as Windows Server, mac OS X, unix, linux, freeBSD, and the like. It will be appreciated by those skilled in the art that the automotive wiring harness parameter performance testing apparatus structure shown in fig. 6 is not limiting of the automotive wiring harness parameter performance testing apparatus and may include more or fewer components than shown, or may combine certain components, or a different arrangement of components.

The invention also provides an automobile wire harness parameter performance test device, which comprises a memory and a processor, wherein the memory stores computer readable instructions, and when the computer readable instructions are executed by the processor, the processor executes the steps of the automobile wire harness parameter performance test method in the embodiments.

The present invention also provides a computer readable storage medium, which may be a non-volatile computer readable storage medium, and may also be a volatile computer readable storage medium, where instructions are stored in the computer readable storage medium, where the instructions, when executed on a computer, cause the computer to perform the steps of the method for testing the performance of the automotive harness parameter.

It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, which are not repeated herein.

The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied essentially or in part or all of the technical solution or in part in the form of a software product stored in a storage medium, including instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a read-only memory (ROM), a random access memory (random access memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.

The above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. The automobile wire harness parameter performance test method is characterized by comprising the following steps of:

2. The method for testing the performance of the parameters of the automobile wire harness according to claim 1, wherein the electrical parameter measurement and the signal transmission test are performed on the automobile wire harness based on a plurality of different environmental parameter combinations, so as to obtain electrical measurement data and signal transmission data of each environmental parameter combination, and the method comprises the following steps:

3. The method for testing the performance of the automotive harness parameters according to claim 1, wherein the performing attribute classification and feature extraction on the electrical measurement data to obtain a plurality of electrical parameters and electrical measurement feature sets, and performing attribute classification and feature extraction on the signal transmission data to obtain a plurality of signal parameters and signal transmission feature sets, includes:

4. The method for testing the performance of the automotive harness parameters according to claim 3, wherein the performing the influence factor analysis on the plurality of environmental parameters and the plurality of electrical parameters to obtain a first influence weight, and performing the influence factor analysis on the plurality of environmental parameters and the plurality of signal parameters to obtain a second influence weight, includes:

5. The method for testing the performance of the automotive harness parameter according to claim 4, wherein the performing feature weighted sum vector conversion on the electrical measurement feature set based on the first influence weight to obtain an electrical measurement feature vector, and performing feature weighted sum vector conversion on the signal transmission feature set based on the second influence weight to obtain a signal transmission feature vector, comprises:

6. The method for testing the performance of the automotive harness parameters according to claim 5, wherein inputting the electrical measurement feature vector and the signal transmission feature vector into a preset automotive harness parameter performance analysis model for parameter performance analysis and harness fault prediction to obtain a target harness performance index and a target fault probability prediction value comprises:

7. The method for testing the performance of the automotive harness parameters according to claim 6, wherein the performing, by the harness fault prediction network, the harness fault prediction on the target feature evaluation vector of each environmental parameter combination to obtain the target fault probability prediction value includes:

8. An automotive wiring harness parameter performance test system, characterized in that the automotive wiring harness parameter performance test system comprises:

9. An automobile wire harness parameter performance test device, characterized in that the automobile wire harness parameter performance test device comprises: a memory and at least one processor, the memory having instructions stored therein;

the at least one processor invokes the instructions in the memory to cause the automotive harness parameter performance testing apparatus to perform the automotive harness parameter performance testing method of any one of claims 1-7.

10. A computer readable storage medium having instructions stored thereon, wherein the instructions when executed by a processor implement the method for testing the performance of automotive harness parameters of any one of claims 1-7.