A high voltage wiring harness durability prediction method and system

Abstract

The present invention relates to the technical field of new energy vehicles, and discloses a high-voltage wiring harness durability prediction method and system, the method comprising obtaining the current measurement value and the voltage measurement value of the new energy vehicle wiring harness; calculating the new energy vehicle wiring harness to obtain the equivalent resistance of the new energy vehicle wiring harness; performing numerical calculation operations according to the current measurement value and the equivalent resistance to obtain the voltage calculation value; performing convolution discrete Fourier transform according to the voltage measurement value to obtain the initial voltage characteristic spectrum and the subsequent voltage characteristic spectrum, and then performing calculation operations to obtain the correlation coefficient; sorting the correlation coefficient to obtain a two-dimensional data set; performing clustering operations according to the two-dimensional data set and the voltage subsequent state quantity in the voltage measurement value, and performing analysis to obtain the prediction result. The method can realize accurate and reliable prediction of fault diagnosis.

Description

Technical Field

[0001] The present invention relates to the technical field of wire harness durability prediction, and in particular to a high-voltage wire harness durability prediction method and system. Background Art

[0002] At present, the wiring harness of new energy vehicles serves as a connecting bridge between batteries, motor control units and various components. Its failure rate is directly related to the safety of the entire vehicle. Therefore, effective monitoring of the wiring harness is one of the current focuses of new energy vehicle technology research.

[0003] In the prior art, a wiring harness fault diagnosis method based on resistance value is disclosed. The wiring harness fault diagnosis method based on resistance value is to collect resistance value, determine voltage value, and then compare with normal value to detect whether the resistance value is higher than the threshold value, so as to determine whether the wiring harness has a fault. However, the wiring harness fault diagnosis method based on resistance value or wiring harness conductivity performance is insufficient for the detection of faults such as wiring harness aging and wiring harness looseness. For these faults, the resistance value and wiring harness conductivity performance do not change significantly, so such faults cannot be detected in a timely and accurate manner, resulting in reduced accuracy and reliability of fault diagnosis, affecting the safe operation of new energy vehicles. Summary of the invention

[0004] The present invention provides a high-voltage wire harness durability prediction method and system, so as to timely and accurately detect faults of the wire harness of a new energy vehicle, especially faults such as wire harness aging and wire harness looseness.

[0005] In a first aspect, in order to solve the above technical problems, the present invention provides a high-voltage wire harness durability prediction method, comprising: Obtaining current measurement values ​​and voltage measurement values ​​of the wiring harness of the new energy vehicle, wherein the voltage measurement value includes an initial voltage state quantity and a subsequent voltage state quantity; Combined with the equivalent resistance calculation model, the wiring harness of new energy vehicles is calculated to obtain the equivalent resistance of the wiring harness of new energy vehicles; Performing a numerical calculation operation according to the current measurement value and the equivalent resistance to obtain a voltage calculation value of the wiring harness of the new energy vehicle; Performing a verification operation according to the voltage measurement value and the voltage calculation value, and performing a convolution discrete Fourier transform on the verified data to obtain an initial voltage characteristic spectrum and a subsequent voltage characteristic spectrum; Performing a calculation operation according to the initial voltage characteristic spectrum and the subsequent voltage characteristic spectrum to obtain a correlation coefficient; Performing a sorting operation according to the voltage measurement values ​​and the correlation coefficients to obtain a two-dimensional data set, wherein each set of data is divided into training data and test data; According to the two-dimensional data set and the voltage subsequent state quantity in the voltage measurement value, a KNN classification algorithm is used to perform a clustering operation on the data to calculate a standard K value and a sample distance; According to the sample distance and the standard K value, an analysis operation is performed to obtain a prediction result.

[0006] In an optional implementation, the calculation of the new energy vehicle wiring harness in combination with the equivalent resistance calculation model to obtain the equivalent resistance of the new energy vehicle wiring harness includes: The equivalent resistance calculation model of the wiring harness of new energy vehicles is expressed as: in, is the total equivalent resistance of the wiring harness, is the total resistance of the resistor elements in the harness, is the wiring harness branch resistance, is the parallel resistance, ,in For parallel n resistor.

[0007] In an optional implementation, performing a numerical calculation operation based on the current measurement value and the equivalent resistance to obtain a voltage calculation value of the new energy vehicle wiring harness includes: Calculating the voltage calculated value of the wiring harness of the new energy vehicle according to the current measurement value and the equivalent resistance; According to Ohm's law, the formula for calculating the voltage of the wiring harness of new energy vehicles is as follows: in, Calculated value of wiring harness voltage for new energy vehicles over time The change function of Current measurement values ​​of new energy vehicle wiring harness over time The change function of Is the equivalent resistance of the wiring harness of new energy vehicles.

[0008] Preferably, performing a convolution discrete Fourier transform according to the voltage measurement value to obtain an initial voltage characteristic spectrum and a subsequent voltage characteristic spectrum includes: According to the voltage measurement value and the voltage calculation value, a verification operation is performed, data with excessive deviation between the measurement value and the calculation value is deleted, and a convolution discrete Fourier transform is performed on the verified data to obtain an initial voltage characteristic spectrum and a subsequent voltage characteristic spectrum, wherein the voltage measurement value of the wiring harness of the new energy vehicle includes an initial voltage state quantity and a subsequent voltage state quantity; Among them, the convolution discrete Fourier transform formula is as follows: in, is the initial state quantity of voltage, The voltage subsequent state quantity over time The change function of , DFT is the convolution discrete Fourier transform operation, is the initial voltage characteristic spectrum, is the subsequent voltage characteristic spectrum.

[0009] Preferably, performing a calculation operation based on the initial voltage characteristic spectrum and the subsequent voltage characteristic spectrum to obtain a correlation coefficient includes: The correlation coefficient is obtained by the following formula: in, is the correlation coefficient, is the initial state quantity of voltage, is the average value of the initial state quantity, The voltage subsequent state quantity over time The change function of is the initial voltage characteristic spectrum, is the subsequent voltage characteristic spectrum, is the average value of the voltage characteristic spectrum, is the number of sampling points of the initial voltage value, is the number of sampling points for subsequent voltage values.

[0010] Preferably, the voltage measurement values ​​and the correlation coefficients are sorted to obtain a two-dimensional data set, wherein each set of data is divided into training data and test data, including: Filtering data points according to the correlation coefficient, filtering data points according to the correlation coefficient, if the correlation coefficient is greater than a preset correlation threshold, it is considered that the initial state quantity corresponding to the data point and the voltage characteristic spectrum have a strong correlation and are retained; if the correlation coefficient is less than or equal to the preset correlation threshold, the data point is considered to be an abnormal or weakly correlated data point, and whether to discard it is determined according to the specific situation; The constructed data set is as follows: in For the dataset, is the training data in the dataset, For the test data in the dataset, is the index of the training data set, is the index in the test data, z is the total number of data.

[0011] Preferably, the step of clustering the data using a KNN classification algorithm based on the two-dimensional data set and the voltage subsequent state quantity in the voltage measurement value to calculate a standard K value and a sample distance includes: According to the two-dimensional data set and the subsequent voltage state quantity, using KNN The classification algorithm performs cluster analysis on the data and sets the standard based on the relationship between the slope change and the fluctuation parameter. K Values ​​and sample distances S , among which, standard K Values ​​and sample distances S The calculation formula is as follows: in, For sample and samples The Euclidean distance between is the shortest Euclidean distance, that is, the sample distance S， Standard K value, is the number of similar samples, is the average distance between all samples and the target sample, For sample No. eigenvalues, For sample No. eigenvalues, is the characteristic dimension of the sample, is the sample size, is the indicator function, when When established, it is 1. If not true, it is 0.

[0012] In an optional implementation, performing an analysis operation according to the sample distance and the standard K value to obtain a prediction result includes: when S ≤ K When , the output prediction result is a normal prediction result; among them, S represents the sample distance; when K <S<2 K When , the prediction result of possible fault reminder is output; when 2K Image 1 When , the prediction result of the fault alarm is output.

[0013] In a second aspect, the present invention provides a high voltage wire harness durability prediction system, comprising: A data acquisition module, which acquires current measurement values ​​and voltage measurement values ​​of the wiring harness of the new energy vehicle, wherein the voltage measurement value includes an initial voltage state quantity and a subsequent voltage state quantity; The resistance calculation module calculates the wiring harness of new energy vehicles in combination with the equivalent resistance calculation model to obtain the equivalent resistance of the wiring harness of new energy vehicles; A voltage calculation module performs a numerical calculation operation according to the current measurement value and the equivalent resistance to obtain a voltage calculation value of the wiring harness of the new energy vehicle; A transformation module performs a verification operation according to the voltage measurement value and the voltage calculation value, and performs a convolution discrete Fourier transform on the verified data to obtain an initial voltage characteristic spectrum and a subsequent voltage characteristic spectrum; A correlation calculation module, performing a calculation operation according to the initial voltage characteristic spectrum and the subsequent voltage characteristic spectrum to obtain a correlation coefficient; A data set module, performing a sorting operation according to the voltage measurement values ​​and the correlation coefficients to obtain a two-dimensional data set, wherein each set of data is divided into training data and test data; A clustering module, which performs a clustering operation on the data using a KNN classification algorithm according to the two-dimensional data set and the voltage subsequent state quantity in the voltage measurement value, and calculates a standard K value and a sample distance; The result output module performs analysis operations according to the sample distance and the standard K value to obtain a prediction result.

[0014] In a third aspect, the present invention further provides an electronic device comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor implements any one of the above-mentioned methods for predicting the durability of a high-voltage wire harness when executing the computer program.

[0015] In a fourth aspect, the present invention further provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute any one of the above-mentioned high-voltage wire harness durability prediction methods.

[0016] Compared with the prior art, the present invention has the following beneficial effects: The present invention obtains the current measurement value and voltage measurement value of the wiring harness of the new energy vehicle, and theoretically calculates the wiring harness in combination with the equivalent resistance calculation model, thereby obtaining the equivalent resistance of the wiring harness. This technical solution not only simplifies the resistance measurement process, but also improves the accuracy of the electrical performance evaluation of the wiring harness through the calculation of the equivalent resistance. In the derivation process, the influence of the parallel resistance is considered, which is beneficial to more realistically reflect the actual resistance of the wiring harness. The present invention obtains the wiring harness voltage calculation value through numerical calculation operation, and further obtains the initial voltage characteristic spectrum and the subsequent voltage characteristic spectrum by using the convolution discrete Fourier transform. This process makes the analysis of the voltage signal more detailed and helps to reveal the deep-level characteristics of the wiring harness voltage change. By analyzing the voltage signal from the two dimensions of time and frequency, the reliability of the prediction is improved. By calculating the correlation coefficient, the data is sorted to form a two-dimensional data set, and the data is clustered using the KNN classification algorithm to finally obtain the prediction result. This method can achieve accurate and reliable prediction of fault diagnosis, which is beneficial to discover potential wiring harness faults in advance and ensure the safe operation of new energy vehicles. By setting the standard K value and the sample distance S, the present invention can output different prediction results of normal, possible fault reminder or fault alarm according to the relationship between the sample distance and the standard K value, so as to timely and accurately detect the faults of the wiring harness of new energy vehicles, especially faults such as wiring harness aging and wiring harness looseness. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 2 It is a schematic flow chart of a high-voltage wire harness durability prediction method provided by the first embodiment of the present invention; Figure 1 It is a schematic diagram of the structure of a high-voltage wire harness durability prediction system provided by the second embodiment of the present invention. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0019] Reference KNN The first embodiment of the present invention provides a high voltage wire harness durability prediction method, comprising the following steps: S11, obtaining a current measurement value and a voltage measurement value of a wiring harness of a new energy vehicle, wherein the voltage measurement value includes an initial voltage state quantity and a subsequent voltage state quantity; S12, calculating the wiring harness of the new energy vehicle by combining the equivalent resistance calculation model to obtain the equivalent resistance of the wiring harness of the new energy vehicle; S13, performing a numerical calculation operation according to the current measurement value and the equivalent resistance to obtain a voltage calculation value of the wiring harness of the new energy vehicle; S14, performing a verification operation according to the voltage measurement value and the voltage calculation value, and performing a convolution discrete Fourier transform on the verified data to obtain an initial voltage characteristic spectrum and a subsequent voltage characteristic spectrum; S15, performing a calculation operation according to the initial voltage characteristic spectrum and the subsequent voltage characteristic spectrum to obtain a correlation coefficient; S16, performing a sorting operation according to the voltage measurement values ​​and the correlation coefficients to obtain a two-dimensional data set, wherein each set of data is divided into training data and test data; S17, performing a clustering operation on the data using a KNN classification algorithm according to the two-dimensional data set and the voltage subsequent state quantity in the voltage measurement value, and calculating a standard K value and a sample distance; S18, performing an analysis operation according to the sample distance and the standard K value to obtain a prediction result.

[0020] In step S11, it is necessary to obtain the current measurement value and the voltage measurement value of the wiring harness of the new energy vehicle, wherein the voltage measurement value includes the voltage initial state quantity and the voltage subsequent state quantity, including: Step S11 is the first step in the entire high-voltage wiring harness durability prediction method. Its core task is to accurately obtain the current and voltage measurements from the wiring harness system of new energy vehicles. The voltage measurement values ​​here include not only the voltage readings at the beginning of vehicle operation (i.e., the initial state), but also the subsequent state quantities recorded in different time periods. By accurately collecting these data, the necessary input parameters are provided for the subsequent steps to facilitate a more in-depth analysis of the state changes of the wiring harness.

[0021] Furthermore, the current measurement value refers to the magnitude of the current flowing through the wiring harness of a new energy vehicle, which is monitored and recorded in real time by a sensor. The fluctuation of the current measurement value can reflect the workload of the wiring harness. The voltage measurement value consists of two parts: the initial voltage state quantity and the subsequent voltage state quantity. The former refers to the voltage level when the vehicle starts or enters a stable working state; the latter is the voltage readings at different time points recorded continuously during operation. These data help to understand the changes in the electrical properties of the wiring harness over time. A high-voltage wiring harness refers to a collection of multiple wires in a new energy vehicle, which is responsible for connecting batteries, motors and other electronic components to ensure safe and efficient power transmission.

[0022] To achieve effective measurement of current and voltage, high-precision current sensors and voltage sensors need to be installed. For current measurement, Hall effect sensors are a common choice, which can detect current intensity in a non-contact manner without interfering with the circuit itself. As for voltage measurement, it can be done by a voltmeter directly connected to the two ends of the circuit to be tested or a voltage monitoring module built into the vehicle diagnostic system. To ensure the accuracy of the data, the sensor should be calibrated regularly and tested close to the actual working environment. In practical applications, the process of obtaining current and voltage measurements involves a variety of sensors and data acquisition systems. For example, a current sensor can be installed in the battery management system (BMS) of a new energy vehicle to monitor the current changes in the wiring harness in real time. Voltage sensors can be installed at both ends of the wiring harness to monitor voltage changes. The data from these sensors can be transmitted to the data acquisition system through the vehicle's diagnostic interface (such as OBD-II) or a wireless communication module (such as Bluetooth or Wi-Fi).

[0023] In step S12, it is necessary to calculate the wiring harness of the new energy vehicle in combination with the equivalent resistance calculation model to obtain the equivalent resistance of the wiring harness of the new energy vehicle, including: The equivalent resistance calculation model of the wiring harness of new energy vehicles is expressed as: in, is the total equivalent resistance of the wiring harness, is the total resistance of the resistor elements in the harness, is the wiring harness branch resistance, is the parallel resistance, ,in For parallel n resistor.

[0024] It should be noted that equivalent resistance refers to the use of a single resistor to represent the resistance characteristics of the entire circuit or part of the circuit, so that when the same voltage is applied across the resistor, the current flowing through is the same as the original circuit. The equivalent resistance calculation model refers to the calculation of the total resistance of a circuit or its components based on known parameters (such as material properties, length, cross-sectional area) or measured data (such as current, voltage). For complex circuit structures, it includes a combination of series, parallel and branch resistances. In the present invention, its expression is .in, Represents the total equivalent resistance of the wiring harness, is the total resistance of the resistance elements in the wiring harness, which is the sum of the resistances of all series resistance elements in the wiring harness; It is the wiring harness branch resistance, which reflects the resistance of different branch parts in the wiring harness; is the parallel resistance, which is calculated according to the formula ,in For paralleln resistors, each of which belongs to The model comprehensively considers the series and parallel resistance combinations in the wiring harness, and can equate the complex connection of multiple resistance elements to a total resistance, which is convenient for subsequent calculation and analysis.

[0025] Suppose we regard the wiring harness of a new energy vehicle as a circuit system, which contains multiple resistor elements, which are connected in series, in parallel, or in mixed series. For example, in a simple wiring harness model, we have several resistors connected in series. and , and another resistor In parallel. At this time, , calculated according to the above formula , and finally the total equivalent resistance is .

[0026] Let's take a more complex example. Suppose that in the actual wiring harness of a new energy vehicle, there are multiple branch circuits, each with a different resistance value and connection method. We can divide the entire wiring harness into different parts, calculate the equivalent resistance of each part separately, and then substitute their connection relationship into the equivalent resistance calculation model for calculation. For example, a part of the wiring harness contains three series resistors. and , and the other part contains two parallel resistors and , first calculate , and then , the final total equivalent resistance .

[0027] In step S13, it is necessary to perform a numerical calculation operation according to the current measurement value and the equivalent resistance to obtain a voltage calculation value of the wiring harness of the new energy vehicle, including: Calculating the voltage calculated value of the wiring harness of the new energy vehicle according to the current measurement value and the equivalent resistance; According to Ohm's law, the formula for calculating the voltage of the wiring harness of new energy vehicles is as follows: in, Calculated value of wiring harness voltage for new energy vehicles over time The change function of Current measurement values ​​of new energy vehicle wiring harness over time The change function of Is the equivalent resistance of the wiring harness of new energy vehicles.

[0028] Specifically, the current measurement value refers to the real-time data of the current flowing through the wiring harness during the operation of the new energy vehicle, which is recorded in the form of a time series. The equivalent resistance refers to the total equivalent resistance of the wiring harness, including the total resistance of the resistance element, the branch resistance and the parallel resistance. The voltage calculation value refers to the voltage calculated according to Ohm's law. The calculated results show that the wiring harness of new energy vehicles at different times The voltage size under It's about time It reflects the voltage state of the wiring harness at different time points and can more comprehensively display the voltage dynamic characteristics of the wiring harness. Ohm's law is a basic law in electricity, and its expression is , which means the current flowing through the conductor in a circuit The voltage across the conductor and resistor The relationship between is the theoretical basis for numerical calculation in this step.

[0029] For example, suppose at a certain moment , the current measurement value of the wiring harness of new energy vehicles is obtained by measuring the current sensor , and the equivalent resistance of the wiring harness has been calculated in step S12 According to Ohm's law , then the calculated voltage value at this moment is Consider a more complex situation. Suppose we have obtained a series of current measurements at different times, such as in the time series The corresponding current measurement values ​​are , known equivalent resistance is a constant. Then the voltage value at each moment can be calculated This series of voltage calculation values ​​can form a curve of voltage change over time, which clearly shows the voltage fluctuation of the wiring harness over a period of time.

[0030] In step S14, it is necessary to perform a convolution discrete Fourier transform according to the voltage measurement value to obtain an initial voltage characteristic spectrum and a subsequent voltage characteristic spectrum, including: According to the voltage measurement value and the voltage calculation value, a verification operation is performed, data with excessive deviation between the measurement value and the calculation value is deleted, and a convolution discrete Fourier transform is performed on the verified data to obtain an initial voltage characteristic spectrum and a subsequent voltage characteristic spectrum, wherein the voltage measurement value of the wiring harness of the new energy vehicle includes an initial voltage state quantity and a subsequent voltage state quantity; Among them, the convolution discrete Fourier transform formula is as follows: in, is the initial state quantity of voltage, The voltage subsequent state quantity over time The change function of , DFT is the convolution discrete Fourier transform operation, is the initial voltage characteristic spectrum, is the subsequent voltage characteristic spectrum.

[0031] It should be noted that the convolution discrete Fourier transform (DFT) is a mathematical transformation method used to convert time series data into a representation of frequency components. DFT can reveal the intensity distribution of the signal at different frequencies. The initial voltage characteristic spectrum refers to the frequency domain representation obtained by applying DFT to the voltage measurement value at the initial start-up of the vehicle or when it enters a stable state, reflecting the electrical characteristics of the wiring harness under no-load or low-load conditions. The subsequent voltage characteristic spectrum refers to the frequency domain representation obtained after DFT processing based on the voltage readings at different time points recorded continuously during operation, showing the dynamic response of the wiring harness under actual working conditions.

[0032] Furthermore, the voltage measurement values ​​collected in step S11 need to be prepared, including the voltage initial state quantity and the voltage subsequent state quantity. Next, use the DFT formula and Transform the initial voltage and subsequent voltage separately. Prepare data: Ensure that the time series data of voltage measurements are complete and accurate, such as the initial state of voltage and voltage subsequent state quantity . Apply DFT: For each voltage time series, apply the DFT formula to convert it into frequency domain representation. Specifically, for the initial voltage state quantity, calculate its DFT to obtain the initial voltage characteristic spectrum; for the subsequent voltage state quantity, calculate its DFT to obtain the subsequent voltage characteristic spectrum.

[0033] Assume that there is a simple set of time series data of voltage subsequent state quantities, such as the voltage data of the wiring harness of a new energy vehicle collected over a period of time: (Unit: Volts), these data represent the voltage measurements at different times. Through the convolution discrete Fourier transform operation , we can convert this time domain signal into a frequency domain signal. In the frequency domain, we will see that certain frequencies have higher amplitudes, which means that these frequency components dominate the original voltage signal. For example, we will find that there is a frequency of The signal component has a larger amplitude, which means that the voltage fluctuation at this frequency contributes more to the entire signal, which may be related to some inherent characteristics of the wiring harness or interference source. Volts, the corresponding initial voltage characteristic spectrum An amplitude value at a single frequency will be obtained, and this frequency reflects the characteristic frequency of the wiring harness of the new energy vehicle at the moment of startup.

[0034] In step S15, a calculation operation needs to be performed based on the initial voltage characteristic spectrum and the subsequent voltage characteristic spectrum to obtain a correlation coefficient, including: The correlation coefficient is obtained by the following formula: in, is the correlation coefficient, is the initial state quantity of voltage, is the average value of the initial state quantity, The voltage subsequent state quantity over time The change function of is the initial voltage characteristic spectrum, is the subsequent voltage characteristic spectrum, is the average value of the voltage characteristic spectrum, is the number of sampling points of the initial voltage value, is the number of sampling points for subsequent voltage values.

[0035] It should be noted that the initial voltage characteristic spectrum refers to the spectral characteristics of the voltage signal at the initial moment obtained by convolution discrete Fourier transform (CDFT), which reflects the energy distribution of the signal at different frequency components. The subsequent voltage characteristic spectrum refers to the spectral characteristics obtained by CDFT at subsequent time points of the voltage signal, which is used to analyze the changes of the signal over time. The correlation coefficient refers to the degree of linear correlation between two signals, and its value is between -1 and 1. 1 indicates a perfect positive correlation, -1 indicates a perfect negative correlation, and 0 indicates no correlation.

[0036] For example, let's assume that we are conducting a durability test on the high-voltage wiring harness of an electric vehicle. First, before the vehicle is started, the technicians collect the initial voltage state quantity. , and the initial voltage characteristic spectrum was obtained through convolution discrete Fourier transform (DFT) processing Then, during the operation of the vehicle, the voltage status is continuously monitored and recorded. , and obtain the subsequent voltage characteristic spectrum through DFT .

[0037] In order to calculate the correlation coefficient, we need to first determine the specific values ​​of the initial voltage characteristic spectrum and the subsequent voltage characteristic spectrum. For example, assuming that the initial voltage characteristic spectrum The mean , and the subsequent voltage characteristic spectrum The mean Next, the difference and product of each sampling point are calculated item by item according to the above formula, and then the sum is divided by the product of the standard deviation to obtain the correlation coefficient C.

[0038] In step S16, a sorting operation needs to be performed according to the voltage measurement values ​​and the correlation coefficients to obtain a two-dimensional data set, wherein each set of data is divided into training data and test data, including: Filtering data points according to the correlation coefficient, filtering data points according to the correlation coefficient, if the correlation coefficient is greater than a preset correlation threshold, it is considered that the initial state quantity corresponding to the data point and the voltage characteristic spectrum have a strong correlation and are retained; if the correlation coefficient is less than or equal to the preset correlation threshold, the data point is considered to be an abnormal or weakly correlated data point, and whether to discard it is determined according to the specific situation; The constructed data set is as follows: in For the dataset, is the training data in the dataset, For the test data in the dataset, is the index of the training data set, is the index in the test data, z is the total number of data.

[0039] It should be noted that the correlation coefficient (C) is a statistic that measures the strength of the linear relationship between two variables, and its value range is between -1 and 1. A value close to 1 indicates a strong positive correlation, a value close to -1 indicates a strong negative correlation, and a value close to 0 indicates no obvious linear relationship. The correlation threshold (Cth) is a preset threshold used to determine which data points have a strong correlation. If the correlation coefficient of a data point is greater than this threshold, the data point is considered valid and representative; otherwise, it is considered an abnormal or weakly correlated data point. The two-dimensional data set (D) is a data set consisting of a series of voltage measurements and their corresponding correlation coefficients, which is divided into two parts - training data and test data. The training data is used to build the model, while the test data is used to verify the accuracy and reliability of the model.

[0040] Specifically, set the correlation threshold (Cth) and select an appropriate threshold as the screening criterion. For example, you can set Cth to 0.8, which means that only when the correlation coefficient is greater than 0.8, the data point is considered valid. To screen the data points, traverse all the data points and compare their correlation coefficients with the set threshold Cth. If the correlation coefficient of a data point is , then keep the data point; otherwise, if , then decide whether to discard the data point according to the specific situation. For example, although some data points have low correlation, they are normal fluctuations caused by special working conditions. At this time, these points can be retained according to actual needs. Construct a two-dimensional data set and organize the filtered data points into a two-dimensional data set according to a preset format. Each data point contains a voltage measurement value and its corresponding correlation coefficient. The format of the data set is as follows: in, represents the entire data set, is the training data, For test data, and are the indices in the training data and test data, respectively. is the total number of data. Divide the training data and test data, and reasonably divide the constructed two-dimensional data set into training set and test set. Generally speaking, random sampling can be used to make about 70%-80% of the data as training set and the remaining 20%-30% as test set. This division helps ensure that the model can fully learn the data pattern and effectively test the model performance.

[0041] In step S17, it is necessary to perform a clustering operation on the data using a KNN classification algorithm according to the two-dimensional data set and the voltage subsequent state quantity in the voltage measurement value, and calculate a standard K value and a sample distance, including: According to the two-dimensional data set and the subsequent voltage state quantity, using S≤K The classification algorithm performs cluster analysis on the data and sets the standard based on the relationship between the slope change and the fluctuation parameter. K Values ​​and sample distances S , among which, standard K Values ​​and sample distances S The calculation formula is as follows: in, For sample and samples The Euclidean distance between is the shortest Euclidean distance, that is, the sample distance S， Standard K value, is the number of similar samples, is the average distance between all samples and the target sample, For sample No. eigenvalues, For sample No. eigenvalues, is the characteristic dimension of the sample, is the sample size, is the indicator function, when When established, it is 1. If not true, it is 0.

[0042] It is worth mentioning that the KNN classification algorithm is an instance-based learning method that performs classification by finding the nearest neighbor data points in the training set. In this context, it is used to identify different working states of the wiring harness. The Euclidean distance (S_{ij})) is the straight-line distance between two sample points and is used to measure the similarity between them. The formula is ,in and are the kth eigenvalues ​​of sample i and sample j, respectively, and d is the feature dimension. The standard K value (K) refers to the number of nearest neighbors considered for classification in the KNN algorithm. It is calculated based on the ratio of the number of similar samples to the average distance. The sample distance (S) refers to the shortest Euclidean distance between any two samples, that is, .

[0043] In step S18, an analysis operation needs to be performed based on the sample distance and the standard K value to obtain a prediction result, including: when K <S<2 K When , the output prediction result is a normal prediction result; among them, S represents the sample distance; when 2K Figure 2 When , the prediction result of possible fault reminder is output; when Figure 1 When , the prediction result of the fault alarm is output.

[0044] Specifically, the sample distance Refers to the Euclidean distance between any two samples, which is used to quantify the degree of difference between different samples. Standard K value Refers to the standard value used to determine the number of nearest neighbors considered for classification in the KNN algorithm. It is calculated based on the ratio of the number of similar samples to the average distance. The prediction results are based on the judgment of the category to which the sample belongs based on the sample distance and the standard K value, and are divided into three categories: normal, possible fault reminder, and fault alarm.

[0045] For example, suppose that a batch of electric vehicle high voltage wiring harnesses are being evaluated for health status. After the previous steps, a series of samples and their corresponding sample distances are obtained. And standard K value For example, there are three samples A, B and C, and their sample distances are: Sample A: Sample B: Sample C: , and assuming the standard K value Next, each sample is evaluated according to the classification rules. For sample A :because , so it is classified as “normal”. For sample B :because , which means that sample B is in the "possible fault reminder" state, which means that although there is no obvious fault at present, it still needs close attention. For sample C :because , so sample C is classified as a "fault alarm", which means that the wiring harness should be checked immediately to prevent potential safety risks.

[0046] The following describes the working process of the present invention using a common scenario as an example. R=R_s+R_c+R_b , which is R_s Schematic diagram of the working system of the method.

[0047] During the maintenance of new energy vehicles, the current measurement value of the wiring harness is first obtained as 50A, the initial voltage state value is 380V, and the subsequent voltage state value (such as the measured value at a certain moment during operation is 375V), and then combined with the equivalent resistance calculation model R_c (Assumption R_C =0.1 ohm, R_b =0.05 ohm, V(t)=I(t)·R =0.05 ohm, then F(V_0)=DFT( = 0.025 ohms, total equivalent resistance R =0.1+0.05+0.025=0.175 ohms), the equivalent resistance of the wiring harness of the new energy vehicle is calculated to be 0.175 ohms; according to the current measurement value and the equivalent resistance, using Ohm's law F(V)=DFT The voltage value of the wiring harness is calculated. The voltage value at time t is 50A * 0.175 ohm = 8.75V. However, considering that the voltage measurement value should be close to the initial or subsequent state quantity in actual applications, it is assumed here that the voltage calculation value is mainly used to verify the consistency between theory and practice. Next, a convolution discrete Fourier transform operation is performed based on the collected voltage measurement value. It is assumed that the initial voltage characteristic spectrum is obtained after DFT processing. C_i 380V) and subsequent voltage characteristic spectrum Avg(375V), convert the time domain representation of the voltage signal into the frequency domain representation for further analysis; then calculate the correlation coefficient C between the initial voltage characteristic spectrum and the subsequent voltage characteristic spectrum, assuming that n = 10 sampling points, m = 10 sampling points, calculated C =0.9, indicating that there is a strong correlation between the two; then, a two-dimensional data set is constructed based on the voltage measurement value and the correlation coefficient, and it is divided into training data and test data. For example, the data points with C>0.8 are retained as valid samples to form a data set. D ={(380,375,...), (382,376,...)}; on this basis, the KNN classification algorithm is used to cluster the samples in the data set, assuming that the standard K value is calculated by the number of similar samples. S_{ij} =5, average distance S_{min} =0.5 gives K =10, for the Euclidean distance between any two samples S_{min} ==2.24, minimum sample distance S_{min} =2.24; Finally, according to the sample distance S and Standards K The value is analyzed because S_{min}>2K =2.24< K =10, the output prediction result is a normal prediction result. Figure 2 Between K and 2K A possible fault reminder is issued, and when ​ A fault alarm is triggered when the wiring harness is damaged, thus achieving effective monitoring and early warning of the health status of new energy vehicle wiring harnesses.

[0048] In summary, the present invention discloses a method for predicting the durability of a high-voltage wiring harness, including obtaining the current measurement value and the voltage measurement value of the wiring harness of a new energy vehicle, calculating the equivalent resistance of the wiring harness of the new energy vehicle, performing numerical calculation operations to obtain the voltage calculation value, obtaining the voltage characteristic spectrum through convolution discrete Fourier transform, calculating the correlation coefficient, constructing a two-dimensional data set, using the KNN classification algorithm to perform clustering operations to calculate the standard K value and the sample distance, and performing analysis operations according to the sample distance and the standard K value to obtain the prediction result. Through this series of steps, the present invention realizes the accurate and reliable prediction of the durability of the high-voltage wiring harness of the new energy vehicle, can effectively predict the fault condition of the wiring harness, and provide protection for the maintenance and safety of the new energy vehicle.

[0049] Reference ​ A second embodiment of the present invention provides a high voltage wire harness durability prediction system, comprising: A data acquisition module, which acquires current measurement values ​​and voltage measurement values ​​of the wiring harness of the new energy vehicle, wherein the voltage measurement value includes an initial voltage state quantity and a subsequent voltage state quantity; The resistance calculation module calculates the wiring harness of new energy vehicles in combination with the equivalent resistance calculation model to obtain the equivalent resistance of the wiring harness of new energy vehicles; A voltage calculation module performs a numerical calculation operation according to the current measurement value and the equivalent resistance to obtain a voltage calculation value of the wiring harness of the new energy vehicle; A transformation module performs a verification operation according to the voltage measurement value and the voltage calculation value, and performs a convolution discrete Fourier transform on the verified data to obtain an initial voltage characteristic spectrum and a subsequent voltage characteristic spectrum; A correlation calculation module, performing a calculation operation according to the initial voltage characteristic spectrum and the subsequent voltage characteristic spectrum to obtain a correlation coefficient; A data set module, performing a sorting operation according to the voltage measurement values ​​and the correlation coefficients to obtain a two-dimensional data set, wherein each set of data is divided into training data and test data; A clustering module, which performs a clustering operation on the data using a KNN classification algorithm according to the two-dimensional data set and the voltage subsequent state quantity in the voltage measurement value, and calculates a standard K value and a sample distance; The result output module performs analysis operations according to the sample distance and the standard K value to obtain a prediction result.

[0050] It should be noted that a high-voltage wire harness durability prediction system provided in an embodiment of the present invention is used to execute all process steps of a high-voltage wire harness durability prediction system method in the above embodiment, and the working principles and beneficial effects of the two correspond one to one, so they will not be repeated.

[0051] Exemplarily, the computer program may be divided into one or more modules / units, which are stored in the memory and executed by the processor to implement the present invention. The one or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, which are used to describe the execution process of the computer program in the electronic device.

[0052] The electronic device may be a computing device such as a desktop computer, a notebook, a PDA, and a smart tablet. The electronic device may include, but is not limited to, a processor and a memory. Those skilled in the art will appreciate that the above components are merely examples of electronic devices and do not constitute a limitation on the electronic device. The electronic device may include more or fewer components than the above components, or may combine certain components, or different components. For example, the electronic device may also include input and output devices, network access devices, buses, etc.

[0053] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the electronic device, and uses various interfaces and lines to connect various parts of the entire electronic device.

[0054] The memory can be used to store the computer program and / or module, and the processor realizes various functions of the electronic device by running or executing the computer program and / or module stored in the memory, and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0055] Wherein, if the module / unit integrated in the electronic device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Wherein, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or system capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0056] It should be noted that the system embodiment described above is merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the drawings of the system embodiment provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art may understand and implement it without paying any creative effort.

[0057] The specific embodiments described above further illustrate the purpose, technical solutions and beneficial effects of the present invention. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. It is particularly pointed out that for those skilled in the art, any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of protection of the present invention.

Claims

1. A high voltage wire harness durability prediction method, characterized in that: Executed by a computer, including: Obtaining current measurement values ​​and voltage measurement values ​​of the wiring harness of the new energy vehicle, wherein the voltage measurement value includes an initial voltage state quantity and a subsequent voltage state quantity; Combined with the equivalent resistance calculation model, the wiring harness of new energy vehicles is calculated to obtain the equivalent resistance of the wiring harness of new energy vehicles; Performing a numerical calculation operation according to the current measurement value and the equivalent resistance to obtain a voltage calculation value of the wiring harness of the new energy vehicle; Performing a verification operation according to the voltage measurement value and the voltage calculation value, and performing a convolution discrete Fourier transform on the verified data to obtain an initial voltage characteristic spectrum and a subsequent voltage characteristic spectrum; Performing a calculation operation according to the initial voltage characteristic spectrum and the subsequent voltage characteristic spectrum to obtain a correlation coefficient; Performing a sorting operation according to the voltage measurement values ​​and the correlation coefficients to obtain a two-dimensional data set, wherein each set of data is divided into training data and test data; According to the two-dimensional data set and the voltage subsequent state quantity in the voltage measurement value, a KNN classification algorithm is used to perform a clustering operation on the data to calculate a standard K value and a sample distance; According to the sample distance and the standard K value, an analysis operation is performed to obtain a prediction result.

2. The high voltage wire harness durability prediction method according to claim 1, characterized in that: Combined with the equivalent resistance calculation model, the wiring harness of new energy vehicles is calculated to obtain the equivalent resistance of the wiring harness of new energy vehicles, including: The equivalent resistance calculation model of the wiring harness of new energy vehicles is expressed as: in, is the total equivalent resistance of the wiring harness, is the total resistance of the resistor elements in the harness, is the wiring harness branch resistance, is the parallel resistance, ,in For parallel n resistor.

3. The high voltage wire harness durability prediction method according to claim 1, characterized in that: According to the current measurement value and the equivalent resistance, a numerical calculation operation is performed to obtain a voltage calculation value of the wiring harness of the new energy vehicle, including: Calculating the voltage calculated value of the wiring harness of the new energy vehicle according to the current measurement value and the equivalent resistance; According to Ohm's law, the formula for calculating the voltage of the wiring harness of new energy vehicles is as follows: in, Calculated value of wiring harness voltage for new energy vehicles over time The change function of Current measurement values ​​of new energy vehicle wiring harness over time The change function of Is the equivalent resistance of the wiring harness of new energy vehicles.

4. The high voltage wire harness durability prediction method according to claim 1, characterized in that: According to the voltage measurement value and the voltage calculation value, a verification operation is performed, and a convolution discrete Fourier transform is performed on the verified data to obtain an initial voltage characteristic spectrum and a subsequent voltage characteristic spectrum, including: According to the voltage measurement value and the voltage calculation value, a verification operation is performed, data with excessive deviation between the measurement value and the calculation value is deleted, and a convolution discrete Fourier transform is performed on the verified data to obtain an initial voltage characteristic spectrum and a subsequent voltage characteristic spectrum, wherein the voltage measurement value of the wiring harness of the new energy vehicle includes an initial voltage state quantity and a subsequent voltage state quantity; Among them, the convolution discrete Fourier transform formula is as follows: in, is the initial state quantity of voltage, The voltage subsequent state quantity over time The change function of , DFT is the convolution discrete Fourier transform operation, is the initial voltage characteristic spectrum, is the subsequent voltage characteristic spectrum.

5. The high voltage wire harness durability prediction method according to claim 1, characterized in that: According to the initial voltage characteristic spectrum and the subsequent voltage characteristic spectrum, a calculation operation is performed to obtain a correlation coefficient, include: The correlation coefficient is obtained by the following formula: in, is the correlation coefficient, is the initial state quantity of voltage, is the average value of the initial state quantity, The voltage subsequent state quantity over time The change function of is the initial voltage characteristic spectrum, is the subsequent voltage characteristic spectrum, is the average value of the voltage characteristic spectrum, is the number of sampling points of the initial voltage value, is the number of sampling points for subsequent voltage values.

6. The high voltage wire harness durability prediction method according to claim 1, characterized in that: A sorting operation is performed according to the voltage measurement values ​​and the correlation coefficients to obtain a two-dimensional data set, wherein each set of data is divided into training data and test data, including: The data points are screened according to the correlation coefficient. If the correlation coefficient is greater than a preset correlation threshold, it is considered that the initial state quantity corresponding to the data point and the voltage characteristic spectrum have a strong correlation and are retained; if the correlation coefficient is less than or equal to the preset correlation threshold, the data point is considered to be an abnormal or weakly correlated data point, and whether to discard it is determined according to the specific situation; The constructed data set is as follows: in For the dataset, is the training data in the dataset, For the test data in the dataset, is the index of the training data set, is the index in the test data, z is the total number of data.

7. The high voltage wire harness durability prediction method according to claim 1, characterized in that: According to the two-dimensional data set and the voltage subsequent state quantity in the voltage measurement value, a KNN classification algorithm is used to perform a clustering operation on the data to calculate a standard K value and a sample distance, including: According to the two-dimensional data set and the subsequent voltage state quantity, using KNN The classification algorithm performs cluster analysis on the data and sets the standard based on the relationship between the slope change and the fluctuation parameter. K Values ​​and sample distances S , among which, standard K Values ​​and sample distances S The calculation formula is as follows: in, For sample and samples The Euclidean distance between is the shortest Euclidean distance, that is, the sample distance S， Standard K value, is the number of similar samples, is the average distance between all samples and the target sample, For sample No. eigenvalues, sample No. eigenvalues, is the characteristic dimension of the sample, is the sample size, is the indicator function, when When established, it is 1. If not true, it is 0.

8. The high voltage wire harness durability prediction method according to claim 1, characterized in that: According to the sample distance and the standard K value, an analysis operation is performed to obtain a prediction result, including: when S ≤ K When , the output prediction result is a normal prediction result; among them, S represents the sample distance; when K < S < 2 K When , the prediction result of possible fault reminder is output; when 2K < S When , the prediction result of the fault alarm is output.

9. A high voltage wire harness durability prediction system, characterized in that: include: A data acquisition module, which acquires current measurement values ​​and voltage measurement values ​​of the wiring harness of the new energy vehicle, wherein the voltage measurement value includes an initial voltage state quantity and a subsequent voltage state quantity; The resistance calculation module calculates the wiring harness of new energy vehicles in combination with the equivalent resistance calculation model to obtain the equivalent resistance of the wiring harness of new energy vehicles; A voltage calculation module performs a numerical calculation operation according to the current measurement value and the equivalent resistance to obtain a voltage calculation value of the wiring harness of the new energy vehicle; A transformation module performs a verification operation according to the voltage measurement value and the voltage calculation value, and performs a convolution discrete Fourier transform on the verified data to obtain an initial voltage characteristic spectrum and a subsequent voltage characteristic spectrum; A correlation calculation module, performing a calculation operation according to the initial voltage characteristic spectrum and the subsequent voltage characteristic spectrum to obtain a correlation coefficient; A data set module, performing a sorting operation according to the voltage measurement values ​​and the correlation coefficients to obtain a two-dimensional data set, wherein each set of data is divided into training data and test data; A clustering module, which performs a clustering operation on the data using a KNN classification algorithm according to the two-dimensional data set and the voltage subsequent state quantity in the voltage measurement value, and calculates a standard K value and a sample distance; The result output module performs analysis operations according to the sample distance and the standard K value to obtain a prediction result.

10. An electronic device, characterized in that: The invention comprises a processor, a memory and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, the high-voltage wire harness durability prediction method according to any one of claims 1 to 8 is implemented.

Images