A method and system for predicting insulation performance of high-voltage wiring harness of new energy vehicles

Abstract

The present invention discloses a method and system for predicting the insulation performance of a high-voltage wiring harness of a new energy vehicle. The method includes: obtaining the operating state of the high-voltage wiring harness of the new energy vehicle, performing dynamic synchronous data acquisition operations according to the operating state of the high-voltage wiring harness of the new energy vehicle, and obtaining an insulation performance index set; performing normalization processing according to the insulation performance index set to obtain standardized insulation data; performing key factor particle division according to a preset factor set and the standardized insulation data to obtain key factor particles; performing correlation degree calculation according to the key factor particles through a quantum annealing algorithm to obtain a factor particle correlation matrix; performing iterative optimization according to the factor particle correlation matrix through a quantum particle swarm optimization algorithm to generate an insulation performance prediction matrix; performing insulation performance calculation based on the insulation performance prediction matrix to obtain insulation performance prediction data. The method can achieve comprehensive and accurate prediction of the insulation performance of the high-voltage wiring harness of the new energy vehicle.

Description

Technical Field

[0001] The present invention relates to the technical field of wire harness insulation, and in particular to a method and system for predicting insulation performance of a high-voltage wire harness of a new energy vehicle. Background Art

[0002] With the popularization of new energy vehicles and the widespread application of high-voltage wiring harness technology, the insulation performance of high-voltage wiring harness, as the core component of vehicle power transmission, is directly related to the safety and reliability of the entire vehicle. Since the high-voltage wiring harness of new energy vehicles is in a high-voltage, high-current working environment for a long time, the insulation material is easily affected by various factors such as temperature, humidity, and mechanical stress, resulting in the gradual degradation of insulation performance. Therefore, real-time monitoring and prediction of the insulation performance of high-voltage wiring harnesses is of great significance for preventing insulation failures and ensuring the safe operation of vehicles.

[0003] In the existing technology, by deploying temperature, humidity, current and other sensors on the high-voltage wire harness, real-time operation data is collected, and the insulation performance is evaluated by combining the threshold judgment method. Some existing technologies use historical data to build statistical models (such as regression analysis, time series analysis, etc.) to predict the degradation trend of insulation performance. Existing methods mostly rely on a single type of sensor data, which makes it difficult to fully reflect the insulation performance degradation law of the high-voltage wire harness under the coupling of multiple factors.

[0004] In summary, the existing technology has the problems of incomplete data collection and insufficient prediction accuracy. Summary of the invention

[0005] The present invention provides a method and system for predicting the insulation performance of a high-voltage wire harness of a new energy vehicle, so as to achieve a comprehensive and accurate prediction of the insulation performance of the high-voltage wire harness of a new energy vehicle.

[0006] In the first aspect, in order to solve the above technical problems, the present invention provides a method for predicting the insulation performance of a high-voltage wiring harness of a new energy vehicle, comprising:

[0007] According to the operating state of the high-voltage wire harness of the new energy vehicle, a data dynamic synchronous collection operation is performed to obtain an insulation performance index set;

[0008] According to the insulation performance index set, normalization processing is performed to obtain standardized insulation data;

[0009] According to the preset factor set and the standardized insulation data, key factor particles are divided to obtain key factor particles;

[0010] According to the key factor particles, the correlation degree is calculated by quantum annealing algorithm to obtain the factor particle correlation matrix;

[0011] According to the factor particle association matrix, an iterative optimization is performed through a quantum particle swarm optimization algorithm to generate an insulation performance prediction matrix;

[0012] Based on the insulation performance prediction matrix, insulation performance calculation is performed to obtain insulation performance prediction data.

[0013] As an optional implementation, the data dynamic synchronous acquisition operation is performed according to the operating state of the high-voltage wire harness of the new energy vehicle to obtain an insulation performance index set, including:

[0014] According to the operating state, a dynamic sensor group matching operation is performed to obtain synchronized multi-source sensor data;

[0015] According to the synchronous multi-source sensor data, an insulation performance degradation model matching operation is performed to obtain an insulation performance index set;

[0016] The operating states include driving state, charging state and stationary state.

[0017] As an optional implementation manner, performing normalization processing according to the insulation performance indicator set to obtain standardized insulation data includes:

[0018] According to the insulation performance index set, a value range matching operation is performed to obtain a normalized threshold value corresponding to each index;

[0019] According to the normalization threshold, a linear normalization conversion operation is performed to obtain standardized conversion data;

[0020] According to the standardized conversion data, a data dimension alignment operation is performed to obtain standardized insulation data.

[0021] As an optional implementation manner, the key factor granules are divided according to the preset factor set and the standardized insulation data to obtain the key factor granules, including:

[0022] Performing a factor correlation analysis operation according to the preset factor set and the standardized insulation data to obtain a factor correlation matrix;

[0023] According to the factor correlation matrix, a clustering operation is performed to obtain an initial factor particle set;

[0024] According to the initial factor granule set, a weight calculation operation is performed to obtain a weight value of each factor granule;

[0025] According to the weight value, a key factor screening operation is performed to obtain key factor particles.

[0026] As an optional implementation manner, the factor correlation analysis operation is performed according to the preset factor set and the standardized insulation data to obtain a factor correlation matrix, including:

[0027] According to the preset factor set and the standardized insulation data, a fuzzy membership calculation operation is performed to obtain a fuzzy membership value of each factor;

[0028] According to the fuzzy membership value, a fuzzy relationship construction operation is performed to obtain a fuzzy relationship matrix between factors;

[0029] According to the fuzzy relationship matrix, a fuzzy clustering analysis operation is performed to obtain a factor correlation matrix;

[0030] The calculation formula for the fuzzy membership calculation is as follows:

[0031]

[0032] in, Indicates Standardized insulation data for the The membership value of fuzzy clustering of factor sets; represents a natural constant; represents the adjustment coefficient; Indicates Standardized insulation data values ​​of the factors; Indicates The central value of the fuzzy clustering of the factor set; Indicates The standard deviation of fuzzy clustering of factor sets.

[0033] As an optional implementation, the calculation formula of the weight calculation operation is as follows:

[0034]

[0035] in, Indicates The weight value of each factor particle; Indicates The number of factors contained in each factor particle; Indicates The average correlation coefficient of each factor particle; It represents the sum of weighted contributions of all factor particles, and m represents the number of factor particles.

[0036] As an optional implementation, the correlation degree is calculated according to the key factor particles by using a quantum annealing algorithm to obtain a factor particle correlation matrix, including:

[0037] According to the key factor particles, a quantum bit encoding operation is performed to obtain quantum state representation data;

[0038] Performing a Hamiltonian construction operation according to the quantum state representation data to obtain a quantum annealing model;

[0039] According to the quantum annealing model, an annealing optimization operation is performed to obtain an optimal correlation solution;

[0040] According to the optimal association solution, a matrix reconstruction operation is performed to obtain a factor-grain association matrix.

[0041] As an optional implementation, the step of performing iterative optimization based on the factor particle association matrix by using a quantum particle swarm optimization algorithm to generate an insulation performance prediction matrix includes:

[0042] According to the factor particle association matrix, a quantum particle swarm initialization operation is performed to obtain an initial particle swarm;

[0043] Performing a fitness calculation operation according to the initial particle group to obtain a particle fitness value;

[0044] According to the particle fitness value, a quantum state update operation is performed to obtain an updated particle swarm;

[0045] Performing iterative optimization operations according to the updated particle swarm to obtain an optimal solution set;

[0046] According to the optimal solution set, a matrix generation operation is performed to obtain an insulation performance prediction matrix.

[0047] As an optional implementation manner, performing insulation performance calculation based on the insulation performance prediction matrix to obtain insulation performance prediction data includes:

[0048] Performing a data extraction operation according to the insulation performance prediction matrix to obtain a prediction characteristic value;

[0049] Performing a weighted sum operation according to the predicted characteristic values ​​to obtain a comprehensive insulation performance score;

[0050] According to the comprehensive insulation performance score, a threshold judgment operation is performed to obtain an insulation performance status classification;

[0051] According to the insulation performance status classification, a data mapping operation is performed to obtain insulation performance prediction data.

[0052] In a second aspect, the present invention provides an insulation performance prediction system for a high-voltage wiring harness of a new energy vehicle, comprising:

[0053] The status acquisition module is used to obtain the operating status of the high-voltage wiring harness of new energy vehicles;

[0054] A data acquisition module, used to perform dynamic and synchronous data acquisition operations according to the operating status of the high-voltage wire harness of the new energy vehicle to obtain an insulation performance index set;

[0055] A data processing module, used for performing normalization processing according to the insulation performance index set to obtain standardized insulation data;

[0056] A key partitioning module, used to partition key factor particles according to a preset factor set and the standardized insulation data to obtain key factor particles;

[0057] A correlation calculation module is used to calculate the correlation according to the key factor particles through a quantum annealing algorithm to obtain a factor particle correlation matrix;

[0058] A quantum optimization module, used for iteratively optimizing the factor particle association matrix through a quantum particle swarm optimization algorithm to generate an insulation performance prediction matrix;

[0059] The performance prediction module is used to perform insulation performance calculation based on the insulation performance prediction matrix to obtain insulation performance prediction data.

[0060] Compared with the prior art, the present invention has the following beneficial effects:

[0061] (1) The present invention uses dynamic sensor group matching technology to collect multi-source heterogeneous data such as temperature, humidity, current, and mechanical stress in real time for different operating states (driving, charging, and stationary), breaking through the limitations of single sensor data. Combining fuzzy membership calculation and factor granularity division, it realizes accurate modeling of multi-factor coupling effects and significantly improves the ability to capture complex mechanisms of insulation degradation;

[0062] (2) The present invention solves the problem of multi-sensor dimension differences through linear normalization threshold dynamic matching technology; combined with the data dimension alignment algorithm, it ensures that sensor data with different sampling frequencies are strictly synchronized on the time axis;

[0063] (3) The present invention innovatively combines the quantum annealing algorithm with quantum particle swarm optimization, constructs a correlation matrix through quantum bit encoding, and uses quantum parallelism to accelerate the search for the global optimal solution, thereby improving the convergence speed and effectively reducing the correlation calculation error;

[0064] (4) Based on the insulation performance comprehensive scoring and threshold judgment module, the present invention can output the insulation level (normal, warning, fault) in real time, and generate a quantitative prediction curve through data mapping, effectively identifying potential failure risks in real time and optimizing operation and maintenance decisions. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] Figure 1It is a schematic flow chart of a method for predicting insulation performance of a high-voltage wiring harness of a new energy vehicle provided by an embodiment of the present invention;

[0066] Figure 2 It is a schematic diagram of the structure of an insulation performance prediction system for a high-voltage wire harness of a new energy vehicle provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0067] 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.

[0068] Reference Figure 1 The first embodiment of the present invention provides a method for predicting the insulation performance of a high-voltage wire harness of a new energy vehicle, comprising the following steps:

[0069] S11, obtaining the operating status of the high-voltage wiring harness of the new energy vehicle;

[0070] S12, performing a dynamic synchronous data collection operation according to the operating state of the high-voltage wire harness of the new energy vehicle to obtain an insulation performance index set;

[0071] S13, performing normalization processing according to the insulation performance index set to obtain standardized insulation data;

[0072] S14, dividing the key factor particles according to the preset factor set and the standardized insulation data to obtain key factor particles;

[0073] S15, calculating the correlation degree according to the key factor particles by using a quantum annealing algorithm to obtain a factor particle correlation matrix;

[0074] S16, performing iterative optimization according to the factor particle association matrix through a quantum particle swarm optimization algorithm to generate an insulation performance prediction matrix;

[0075] S17, performing insulation performance calculation based on the insulation performance prediction matrix to obtain insulation performance prediction data.

[0076] In step S11, the operating status of the high-voltage wire harness of the new energy vehicle is obtained.

[0077] It should be noted that the acquisition and feature extraction of the high-voltage wire harness operating status refers to the real-time collection of the current, temperature and vibration parameters of the high-voltage wire harness through multi-source sensors. This operation provides basic data support for subsequent insulation failure warning and life prediction.

[0078] In step S12, according to the operating state of the high-voltage wire harness of the new energy vehicle, a data dynamic synchronous acquisition operation is performed to obtain an insulation performance index set, including:

[0079] According to the operating state, a dynamic sensor group matching operation is performed to obtain synchronized multi-source sensor data;

[0080] According to the synchronous multi-source sensor data, an insulation performance degradation model matching operation is performed to obtain an insulation performance index set;

[0081] The operating states include driving state, charging state and stationary state.

[0082] It should be noted that the dynamic synchronous data acquisition operation refers to obtaining relevant operating status data in real time according to the operating status of the high-voltage wire harness of the new energy vehicle, and collecting and synchronizing the data of different sensors through the collaborative work of multi-source sensors. This operation plays an important role in the insulation performance monitoring of the high-voltage wire harness of new energy vehicles, and can provide real-time and accurate basic data for subsequent insulation performance evaluation. In an embodiment of the present invention, the dynamic synchronous data acquisition operation includes real-time acquisition of operating status data, dynamic matching and synchronization of sensor groups, and merging and processing steps of multi-source data. In the monitoring process of the high-voltage wire harness of new energy vehicles, the dynamic synchronous acquisition operation can significantly improve the consistency and accuracy of the data, provide reliable input data for insulation performance prediction, and ensure the accuracy of subsequent processing.

[0083] Among them, the real-time data acquisition operation refers to obtaining relevant operating status data in real time according to the operating status of the high-voltage wiring harness of the new energy vehicle. Through sensors and monitoring equipment, data including driving status, charging status and static status are collected, and these data are converted into operating status data sets. This operation is the basis for the prediction of the insulation performance of the high-voltage wiring harness, and provides key input data for subsequent data processing and model matching. The dynamic sensor group matching operation refers to the synchronous matching of data collected by different sensors based on the real-time acquired operating status data. Through the real-time coordination of multi-source sensor data, data time delay and acquisition error are eliminated, ensuring that data obtained from different sensors (including temperature sensors and humidity sensors) can be processed at the same time point. This operation can ensure the synchronization and consistency of multi-source data. The insulation performance degradation model matching operation refers to the application of the established insulation performance degradation model to data matching based on the synchronous multi-source sensor data, and calculate the insulation performance index set of the high-voltage wiring harness. The model predicts and quantifies the insulation resistance, insulation average resistance, insulation withstand voltage value and insulation leakage current index of the high-voltage wiring harness based on the data collected by the sensor. Through this operation, the insulation performance of the high-voltage wiring harness can be evaluated in real time, providing a scientific basis for subsequent performance prediction and maintenance decisions. Through the above steps, the dynamic and synchronous data collection operation can efficiently convert the operating status of the high-voltage wire harness of new energy vehicles into a useful set of insulation performance indicators, ensure the accuracy of subsequent prediction operations, and provide protection for the safety of new energy vehicles.

[0084] In step S13, the insulation performance index set is normalized to obtain standardized insulation data, including:

[0085] According to the insulation performance index set, a value range matching operation is performed to obtain a normalized threshold value corresponding to each index;

[0086] According to the normalization threshold, a linear normalization conversion operation is performed to obtain standardized conversion data;

[0087] According to the standardized conversion data, a data dimension alignment operation is performed to obtain standardized insulation data.

[0088] It should be noted that the normalization operation refers to the standardization of the data in the insulation performance index set through numerical range matching, linear normalization conversion and data dimension alignment steps. This operation plays an important role in the prediction of high-voltage wire harness insulation performance, and can provide data of a unified scale for subsequent analysis, so that the data of each performance index can be effectively compared and analyzed. In an embodiment of the present invention, the normalization operation is based on the numerical range of each insulation performance index, and the data is standardized through linear conversion, and the consistency of the data is ensured through dimensional alignment, so as to provide reliable basic data for subsequent performance prediction.

[0089] Among them, the numerical range matching operation refers to determining the numerical range of each indicator according to the insulation performance indicator set, and matching them to obtain the normalized threshold of each indicator. Through this operation, the data of different insulation performance indicators are standardized to a unified numerical range, providing a matching benchmark for the subsequent linear normalization conversion operation. This operation can eliminate the dimensional differences of each indicator in the original data and ensure the accuracy of the normalization process. The linear normalization conversion operation refers to mapping the data of each insulation performance indicator to a unified standardized scale using a linear conversion method based on the normalization threshold. Through linear conversion, the original insulation performance data can be unified to a specified standard range, such as an interval of 0 to 1, thereby ensuring the comparability and consistency of the data between different dimensions. The data dimension alignment operation refers to performing data dimension alignment based on the standardized conversion data to ensure that the data of each insulation performance indicator is compared in the same dimension. Specifically, the improved dynamic time warping (DTW) algorithm is first used to achieve the synchronous calibration of the timestamps of multi-source data; then, the spatial grid mapping is reconstructed based on the three-dimensional topological model of the high-voltage wire harness, and the radial basis function (RBF) neural network is used to spatially interpolate the non-uniform data of discrete sensor nodes to generate a standardized three-dimensional data cube with a resolution of 5mm; finally, through the multi-physics field dimension fusion conversion matrix, the logarithmic normalization (current), piecewise linear normalization (temperature) and power law normalization (vibration) methods are used to achieve dimensional normalization. Through this operation, standardized data of different dimensions can be unified into a shared coordinate system, eliminating the deviation between dimensions and ensuring that the subsequent data analysis can accurately reflect the relationship between various indicators.

[0090] In step S14, the key factor granules are divided according to the preset factor set and the standardized insulation data to obtain the key factor granules, including:

[0091] Performing a factor correlation analysis operation according to the preset factor set and the standardized insulation data to obtain a factor correlation matrix;

[0092] According to the factor correlation matrix, a clustering operation is performed to obtain an initial factor particle set;

[0093] According to the initial factor granule set, a weight calculation operation is performed to obtain a weight value of each factor granule;

[0094] According to the weight value, a key factor screening operation is performed to obtain key factor particles.

[0095] It is worth noting that the key factor granular division operation refers to the division of key factor granules that affect the insulation performance of the high-voltage wire harness by analyzing and processing the preset factor set and standardized insulation data. This operation plays an important role in the prediction of the insulation performance of the high-voltage wire harness, and can help screen out the most influential factors, providing an accurate basis for subsequent insulation performance prediction. In an embodiment of the present invention, the key factor granular division operation is implemented based on factor correlation analysis, clustering, weight calculation and key factor screening steps. Through these operations, the key factors that affect the insulation performance can be effectively identified, and representative factor data can be provided for subsequent performance evaluation.

[0096] Among them, the factor correlation analysis operation refers to analyzing the correlation between the factors according to the preset factor set and the standardized insulation data to obtain the factor correlation matrix. Through this operation, the relationship between different factors can be identified to ensure that the factors with greater impact on the insulation performance can be screened out in the subsequent steps, thereby laying the foundation for the granular division of key factors. The clustering division operation refers to grouping the factors according to the factor correlation matrix using a clustering algorithm to obtain an initial factor granular set. Through this operation, factors with high similarity can be classified into one category, thereby effectively reducing the complexity of subsequent analysis and conducting targeted analysis on factors of different categories. In an embodiment of the present invention, the clustering algorithm used is the fuzzy C-means clustering algorithm. Of course, according to the actual application scenario and user needs, the clustering algorithm can also use other clustering algorithms such as the possibility C-means clustering algorithm, which is not limited to the present invention. Specifically, first, the first factor in the factor correlation matrix is ​​grouped into two categories. Row vector , as the first The associated eigenvectors of the factors; then randomly generate the membership matrix ,satisfy ,in is the preset number of clusters; after that, the cluster centers are updated alternately and membership , the objective function is:

[0097]

[0098] Among them, m=2 is the fuzzy factor, represents the objective function, n is the number of columns of the vector; the update formula is:

[0099]

[0100]

[0101] Finally, when the rate of change of the objective function value between two adjacent iterations is less than the threshold Or it stops when the maximum number of iterations (such as 100) is reached, outputs the membership matrix U, and assigns factors with membership > 0.7 to corresponding clusters to form an initial factor particle set.

[0102] The weight calculation operation refers to calculating the weight value of each factor particle according to the initial factor particle set. Through this operation, a weight value can be assigned to each factor particle, thereby indicating the degree of influence of the factor particle on the insulation performance prediction result. The weight calculation operation is essential to ensure the accurate screening of key factor particles. The key factor screening operation refers to screening out the key factor particles that affect the insulation performance of the high-voltage wire harness according to the weight value. Through this operation, the factors that have the greatest impact on the insulation performance can be effectively identified, thereby further improving the accuracy and reliability of the prediction model. In the embodiment of the present invention, the screening threshold is set to 0.1. Of course, according to the actual application scenario and user needs, the screening threshold can also be set to other values ​​such as 0.05, 0.12, etc., and the present invention does not limit this. Specifically, the key factor screening operation first presets the screening threshold; then traverses all factor particles, and if its weight is greater than the screening threshold, it is determined to be a key factor particle; then the key factor particle set is output to complete the key factor screening.

[0103] In this embodiment, the factor correlation analysis operation is performed according to the preset factor set and the standardized insulation data to obtain a factor correlation matrix, including:

[0104] According to the preset factor set and the standardized insulation data, a fuzzy membership calculation operation is performed to obtain a fuzzy membership value of each factor;

[0105] According to the fuzzy membership value, a fuzzy relationship construction operation is performed to obtain a fuzzy relationship matrix between factors;

[0106] According to the fuzzy relationship matrix, a fuzzy clustering analysis operation is performed to obtain a factor correlation matrix;

[0107] The calculation formula for the fuzzy membership calculation is as follows:

[0108]

[0109] in, Indicates Standardized insulation data for the The membership value of fuzzy clustering of factor sets; represents a natural constant; represents the adjustment coefficient; Indicates Standardized insulation data values ​​of the factors; Indicates The central value of the fuzzy clustering of the factor set; Indicates The standard deviation of fuzzy clustering of factor sets.

[0110] It should be noted that the factor correlation analysis operation refers to analyzing the correlation between the preset factor set and the standardized insulation data through fuzzy membership calculation, fuzzy relationship construction and fuzzy cluster analysis steps. This operation can reveal the relationship between different factors and provide a scientific basis for the subsequent key factor granular division. In an embodiment of the present invention, the factor correlation analysis operation is implemented based on fuzzy membership calculation, fuzzy relationship construction and fuzzy cluster analysis steps. Through these steps, the degree of correlation between various factors can be effectively identified, and further help to screen out the factors that have the greatest impact on insulation performance.

[0111] It is worth noting that the fuzzy membership calculation operation refers to calculating the fuzzy membership value of each factor based on the preset factor set and the standardized insulation data. This operation quantifies the relationship between factors and data by calculating the membership value of each standardized insulation data to the fuzzy clustering of each factor set, thereby providing the necessary basic data for the subsequent fuzzy relationship construction. The fuzzy relationship construction operation refers to constructing a fuzzy relationship matrix between factors based on the fuzzy membership value. This operation integrates the membership values ​​of each factor to establish a fuzzy relationship matrix between factors, providing strong data support for subsequent clustering analysis. The fuzzy relationship matrix reflects the degree of mutual dependence and correlation between different factors. The fuzzy clustering analysis operation refers to grouping factors using a fuzzy clustering algorithm based on the fuzzy relationship matrix to obtain a factor correlation matrix. Through this operation, factors with higher correlation can be aggregated to provide a more accurate basis for subsequent factor granularity division and weight calculation. Specifically, the fuzzy membership value is obtained by the following calculation formula:

[0112]

[0113] in, Indicates Standardized insulation data for the The membership value of the fuzzy clustering of the factor set indicates the degree of membership of the standardized insulation data in the specific factor set. The closer it is to 1, the higher the membership, and the closer it is to 0, the lower the membership. It represents a natural constant, usually with a value of about 2.71828. It plays a role of smoothing and exponential decay in the calculation of fuzzy membership, helping to adjust the calculation results of membership to keep them within a reasonable range. Represents the adjustment coefficient, which is used to control the decay rate of the fuzzy membership. The size of affects the relationship between data points and fuzzy cluster centers in membership calculation. When it is larger, the membership value is more sensitive to the distance, and vice versa. It is determined by experiments and data fitting. The optimal value of , ensuring that the membership value can accurately reflect the influence of each factor; Indicates All insulation data will be normalized to obtain standardized insulation data values. This is the standardized data value, indicating the The location of the data points in the normalized space; Indicates The central value of the fuzzy clustering of a factor set is the "center" position or representative value of the factor set. This central value is determined by calculating the average value or cluster center of all relevant factors in fuzzy clustering analysis. It represents the central tendency of the data points in the cluster and reflects the main characteristics of the factor set; Indicates The standard deviation of the fuzzy clustering of a factor set is an indicator to measure the distribution range of data in the cluster. The larger the standard deviation, the wider the distribution of data points in the cluster. On the contrary, it means that the data points are more concentrated. The calculation of is based on the differences of all data points in the factor set, reflecting the degree of discreteness of the clustering.

[0114] It should be noted that the calculation formula of the weight calculation operation is as follows:

[0115]

[0116] in, Indicates The weight value of each factor particle reflects the The contribution of each factor particle to the final prediction result. The larger the weight value, the greater the influence of the factor particle on the prediction result, and vice versa. Indicates The number of factors contained in a factor particle reflects the range of characteristics represented by the factor particle. The more factors a factor particle contains, the more comprehensive the information contained in the particle. Indicates The average correlation coefficient of a factor particle indicates the strength of the correlation between the factors within the factor particle. This coefficient is obtained by calculating the correlation between the factors within the particle. The larger the coefficient is, the stronger the correlation between the member factors of the factor particle is, and the smaller the coefficient is, the weaker the correlation is. It represents the sum of the weighted contributions of all factor particles. It calculates the comprehensive contribution of all factor particles to the insulation performance prediction after weighting. The weighted contribution takes into account the number of factors contained in each factor particle and the correlation of its internal factors, so as to comprehensively evaluate the influence of all factor particles. m represents the number of factor particles.

[0117] In step S15, the correlation degree is calculated according to the key factor particles by using a quantum annealing algorithm to obtain a factor particle correlation matrix, including:

[0118] According to the key factor particles, a quantum bit encoding operation is performed to obtain quantum state representation data;

[0119] Performing a Hamiltonian construction operation according to the quantum state representation data to obtain a quantum annealing model;

[0120] According to the quantum annealing model, an annealing optimization operation is performed to obtain an optimal correlation solution;

[0121] According to the optimal association solution, a matrix reconstruction operation is performed to obtain a factor-grain association matrix.

[0122] It should be noted that the correlation calculation operation in the quantum annealing algorithm refers to the calculation of the correlation between key factor particles through quantum bit encoding, Hamiltonian construction and annealing optimization steps. This operation can help establish a relationship matrix between factor particles in the prediction of high-voltage wire harness insulation performance, providing a scientific basis for subsequent data analysis and prediction. In an embodiment of the present invention, the quantum annealing algorithm can efficiently calculate the optimal correlation between each factor particle through the process of quantum bit encoding, Hamiltonian construction and annealing optimization, thereby accurately revealing the influence of each factor particle on the prediction result.

[0123] The quantum bit encoding operation refers to converting the data of each key factor particle into quantum state representation data through the quantum bit encoding method according to the key factor particle. Through quantum bit encoding, classical data can be effectively converted into a form that can be processed by quantum computing, so that the subsequent quantum annealing optimization can better utilize the advantages of quantum computing and provide efficient computing and solving processes. Specifically, the standardized data of each key factor particle is first , normalized to fall into the unit interval; then the normalized eigenvalue is mapped to the rotation angle of the quantum bit, and the RY gate is used to realize the preparation of the single quantum bit state; finally, the controlled phase gate (CZ) is applied to the factor particles with high correlation to generate an entangled state to express the coupling relationship between the factors, thereby obtaining the characteristic data of the quantum state representation. The Hamiltonian construction operation refers to constructing a Hamiltonian model suitable for the quantum annealing algorithm according to the quantum state representation data. The Hamiltonian guides the quantum system to transition from a high energy state to a low energy state by describing the energy state of the system. Specifically, in the quantum annealing framework, the Hamiltonian is an operator that describes the energy state of the quantum system, and its mathematical essence is a Hermitian matrix. Each quantum state of the system corresponds to the eigenvalue (energy) of the Hamiltonian, and the lowest energy state corresponds to the optimal solution of the problem. Quantum annealing drives the system from the initial easy-to-solve Hamiltonian to the problem Hamiltonian through the time-varying Hamiltonian. The process of building the Hamiltonian model includes: first, mapping each key factor particle to a spin variable in the Ising model, corresponding to the measurement result of the quantum bit ( ): , This shows that the factor particles have a positive effect on the insulation performance. It shows that the factor particles have a negative impact on the insulation performance; then the Hamiltonian is constructed, which consists of coupling terms, magnetic field terms and constraint terms: ;in, represents the coupling term, reflecting the correlation strength between factor particles, where is the correlation coefficient between factor particles (from the correlation matrix), is the factor particle weight (obtained by the weight calculation operation), is the normalization factor (adapting to hardware limitations) represents the magnetic field term, reflecting the independent influence of a single factor particle, is the adjustment coefficient (the contribution of the control weight to the magnetic field term), Represents a constraint item, ensuring that mutually exclusive factor particles are not activated at the same time.

[0124] By constructing a Hamiltonian model, the optimization goal of the problem can be converted into an energy minimization problem of the quantum system, so that the quantum annealing algorithm can efficiently solve the optimal correlation between the factor particles. The annealing optimization operation refers to optimizing the calculation through the quantum annealing algorithm according to the quantum annealing model to obtain the optimal correlation solution. The quantum annealing algorithm simulates the annealing process in quantum mechanics, allowing the system to jump between multiple energy states and eventually find the global optimal solution. Specifically, first construct the Hamiltonian model Mapping to quantum annealing hardware; then, designing the annealing path To balance quantum tunneling and thermal fluctuation effects: ; Use quantum effects to break through local optimality and apply additional transverse field disturbances to high-weight factor particles; Perform multiple rounds of annealing sampling according to the above process, and then perform majority voting on the chain-embedded physical quantum bits to remove solutions that violate the constraints and obtain the optimal correlation solution. In this step, the annealing optimization process can efficiently calculate the optimal correlation between factor particles, providing a basis for constructing the factor particle correlation matrix. The matrix reconstruction operation refers to the reconstruction of the factor particle correlation matrix based on the optimal correlation solution. The matrix reconstruction operation refers to the process of dynamically adjusting the original factor particle correlation matrix based on the optimal correlation solution obtained by quantum annealing (i.e., the combination of spin variable values ​​of each factor). Specifically, firstly, based on the activation state of the factor particles in the optimal solution (taking +1 or -1), the association relationships with significant positive or negative effects on the target (such as insulation performance) are identified; then, the correlation coefficients in the factor weights and coupling terms are combined to enhance the strength of the association between the synergistic factors that are activated at the same time and weaken the negative correlation between the conflicting factors; at the same time, the adjusted association values ​​are constrained to the range that the hardware can handle through the normalization factor, and the statistical properties of the original matrix (such as symmetry) are retained, and finally an updated association matrix that can reflect the actual physical association and adapt to the hardware limitations of quantum annealing is generated. By converting the optimal association solution into a matrix form, the strength of the relationship between each factor particle can be effectively represented, providing important data support for subsequent factor particle analysis and prediction models.

[0125] In step S16, the factor particle association matrix is ​​iteratively optimized by a quantum particle swarm optimization algorithm to generate an insulation performance prediction matrix, including:

[0126] According to the factor particle association matrix, a quantum particle swarm initialization operation is performed to obtain an initial particle swarm;

[0127] Performing a fitness calculation operation according to the initial particle group to obtain a particle fitness value;

[0128] According to the particle fitness value, a quantum state update operation is performed to obtain an updated particle swarm;

[0129] Performing iterative optimization operations according to the updated particle swarm to obtain an optimal solution set;

[0130] According to the optimal solution set, a matrix generation operation is performed to obtain an insulation performance prediction matrix.

[0131] It should be noted that the iterative optimization operation in the quantum particle swarm optimization algorithm refers to optimizing the factor particle association matrix through initializing the particle swarm, fitness calculation, quantum state update and iterative optimization steps to generate the final insulation performance prediction matrix. This operation can accurately adjust the prediction results through the iterative process of the quantum particle swarm optimization algorithm, so that the final insulation performance prediction matrix can accurately reflect the relationship between each factor particle and provide accurate insulation performance prediction. Through this algorithm, it can ensure that the contribution and prediction error of each factor particle are optimized in the case of multi-dimensional and complex relationships, and further improve the accuracy of the prediction.

[0132] Among them, the quantum particle swarm initialization operation refers to initializing the quantum particle swarm according to the factor particle association matrix. By initializing the particle swarm and setting the initial position and speed of each particle, the initialization of the quantum particle swarm provides an initial solution for the subsequent optimization process. This step ensures that the particle swarm can cover the entire search space and provides a good starting point for finding the optimal solution. The fitness calculation operation refers to calculating the fitness value of each particle based on the initial particle swarm. The fitness value is used to measure the quality of the current solution of each particle. The larger the fitness value, the closer the solution of the particle is to the optimal solution. Specifically, the formula for fitness calculation is as follows:

[0133]

[0134] Among them, F represents the particle fitness value, which reflects the quality of the particle's solution. The higher the fitness value, the closer the particle's current solution is to the optimal solution. Indicates The actual observed value of each factor particle is the data obtained from actual measurement or monitoring, which represents the real insulation performance index of the high-voltage wire harness under the current operating state. For example, It is the actual insulation resistance and insulation withstand voltage value; Indicates The predicted value of each factor particle is the insulation performance prediction value calculated by the current model or algorithm based on the input data. The predicted value represents the expected insulation performance of the model under given conditions; - ) indicates the The error between the actual value and the predicted value of each factor particle reflects the deviation between the model prediction and the actual data. The smaller the error, the closer the predicted value is to the actual value, and the better the prediction effect of the model.

[0135] It is worth noting that the quantum state update operation refers to updating the particle position and velocity in the particle swarm according to the particle fitness value. Specifically, firstly, the average value of the optimal position of all individuals in the particle swarm is calculated ( ): ,in, represents the number of particle swarms, Indicates The particle in The individual optimal position of dimension is obtained; then, the dynamic potential well center is generated according to the individual optimal and group optimal: , Indicates that the group dimension; finally, a new position is generated by wave function collapse, replacing the traditional speed update and dynamically adjusting the search range. Through quantum state update, each particle moves towards the optimal solution in the search space, and the adjustment of the particle's position and speed is based on its fitness value and the update strategy of quantum computing. This operation can effectively guide the particle swarm to converge to the global optimal solution in the quantum particle swarm optimization algorithm. The iterative optimization operation refers to performing multiple iterative optimizations according to the updated particle swarm until the optimal solution set is found. Specifically, the position of each particle in the particle swarm is first adjusted based on the quantum state update formula to generate a new generation of particle swarm. The position update of each particle depends on its individual historical optimal position, the global optimal position of the group, and the dynamic contraction-expansion coefficient; then, the fitness value of each particle in the new generation of particle swarm is calculated; thereafter, if the current fitness value of the particle is better than its individual historical optimal value, it is updated. ; If there is a particle whose fitness value is better than the global optimal value of the group, update t; the final termination condition is: when the preset maximum number of iterations is 500, the iteration is terminated and the optimal solution set is output. Through the iterative process, the particle swarm will continuously adjust the position and speed of the particles so that the overall solution gradually approaches the optimal solution. Iterative optimization can ensure that the most suitable solution is found in complex multi-dimensional optimization problems. The matrix generation operation refers to generating the final insulation performance prediction matrix based on the optimal solution set. By converting the particle positions in the optimal solution set into a matrix form, an insulation performance prediction matrix representing the correlation between each factor particle can be obtained, providing accurate reference data for subsequent prediction analysis.

[0136] In step S17, the insulation performance calculation is performed based on the insulation performance prediction matrix to obtain insulation performance prediction data, including:

[0137] Performing a data extraction operation according to the insulation performance prediction matrix to obtain a prediction characteristic value;

[0138] Performing a weighted sum operation according to the predicted characteristic values ​​to obtain a comprehensive insulation performance score;

[0139] According to the comprehensive insulation performance score, a threshold judgment operation is performed to obtain an insulation performance status classification;

[0140] According to the insulation performance status classification, a data mapping operation is performed to obtain insulation performance prediction data.

[0141] It should be noted that the insulation performance calculation operation refers to a series of processing steps on the insulation performance prediction matrix to finally obtain the insulation performance prediction data. This operation can further evaluate the insulation state of the high-voltage wire harness based on the prediction matrix calculated by the model and provide a basis for subsequent decision-making. In an embodiment of the present invention, the insulation performance calculation operation is implemented through data extraction, weighted summation, threshold judgment and data mapping steps to ensure that the final insulation performance prediction data can accurately reflect the actual insulation performance of the high-voltage wire harness.

[0142] Among them, the data extraction operation refers to extracting key predicted characteristic values ​​from the insulation performance prediction matrix. This operation selects key features related to insulation performance according to the data in the matrix as input data for subsequent calculation and analysis. The weighted summation operation refers to weighted summation of the predicted characteristic values ​​according to certain weights to obtain a comprehensive insulation performance score. Through weighted summation, the contribution of different features to insulation performance can be fully considered, and the influence of each feature in the final score can be adjusted according to the weight. This step helps us comprehensively evaluate the comprehensive impact of various factors on the insulation performance of the high-voltage wire harness. In an embodiment of the present invention, the predicted characteristic values ​​include the temperature, humidity, and insulation resistance of the wire harness, and the weights are set to 0.4, 0.3, and 0.3, respectively. Of course, according to different actual application scenarios and user needs, the weights of the features can be set to other values, such as 0.5, 0.2, 0.3, etc., and the present invention does not limit this. The threshold judgment operation refers to setting a suitable threshold according to the comprehensive insulation performance score to judge the insulation performance state of the high-voltage wire harness. By comparing the comprehensive score with the preset threshold, it is determined whether the safety standard is met, and the insulation performance is classified to distinguish different states, such as "good", "warning" or "fault". In an embodiment of the present invention, assuming that the set threshold is 500, if the comprehensive score is greater than 500, it means that the insulation performance is good; if the comprehensive score is between 300 and 500, it indicates a warning state; if the comprehensive score is less than 300, it indicates a fault state. For example, if the calculated comprehensive score is 350, it is judged as a warning state according to the threshold. Of course, depending on the actual application scenario and user needs, the threshold can be set to other values, such as 400, 600, etc., and the present invention is not limited to this. The data mapping operation refers to converting the classification results into specific insulation performance prediction data according to the insulation performance status classification. Specifically, the state category is first converted back to the score value interval; then, a probability weighted numerical calculation is performed, and the classification probability vector is used to calculate the predicted insulation performance. Calculate the predicted value: Through the mapping operation, the prediction results can be visualized or converted into specific numerical indicators, which is convenient for subsequent use and analysis.

[0143] Reference Figure 2The second embodiment of the present invention provides a system for predicting insulation performance of a high-voltage wire harness of a new energy vehicle, comprising:

[0144] The status acquisition module is used to obtain the operating status of the high-voltage wiring harness of new energy vehicles;

[0145] A data acquisition module, used to perform dynamic and synchronous data acquisition operations according to the operating status of the high-voltage wire harness of the new energy vehicle to obtain an insulation performance index set;

[0146] A data processing module, used for performing normalization processing according to the insulation performance index set to obtain standardized insulation data;

[0147] A key partitioning module, used to partition key factor particles according to a preset factor set and the standardized insulation data to obtain key factor particles;

[0148] A correlation calculation module is used to calculate the correlation according to the key factor particles through a quantum annealing algorithm to obtain a factor particle correlation matrix;

[0149] A quantum optimization module, used for iteratively optimizing the factor particle association matrix through a quantum particle swarm optimization algorithm to generate an insulation performance prediction matrix;

[0150] The performance prediction module is used to perform insulation performance calculation based on the insulation performance prediction matrix to obtain insulation performance prediction data.

[0151] It should be noted that the insulation performance prediction system for a high-voltage wire harness of a new energy vehicle provided in an embodiment of the present invention is used to execute all the process steps of the insulation performance prediction method for a high-voltage wire harness of a new energy vehicle in the above-mentioned embodiment. The working principles and beneficial effects of the two correspond one to one, and therefore will not be repeated here.

[0152] In the present invention, by acquiring the operating status of the high-voltage wire harness of new energy vehicles in real time and combining the dynamic sensor group matching operation, the synchronous collection of multi-source sensor data is realized, and then the insulation performance index set is matched by numerical range, linear normalization conversion and data dimension alignment operations to generate standardized insulation data. Through the combination of key factor granularity division and weight optimization, quantum annealing algorithm and quantum particle swarm optimization algorithm, as well as real-time prediction and dynamic adjustment, the comprehensiveness, accuracy and real-time performance of the insulation performance prediction of the high-voltage wire harness of new energy vehicles are improved, effectively solving the problems of incomplete data collection and insufficient prediction accuracy in the prior art.

[0153] The embodiment of the present invention further provides a terminal device. The terminal device includes: a processor, a memory, and a computer program stored in the memory and executable on the processor, such as a program for predicting the insulation performance of a high-voltage wire harness of a new energy vehicle. When the processor executes the computer program, the steps in the above-mentioned embodiments of the method for predicting the insulation performance of a high-voltage wire harness of a new energy vehicle are implemented, such as Figure 1 Alternatively, the processor implements the functions of each module / unit in the above-mentioned system embodiments when executing the computer program.

[0154] 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 terminal device.

[0155] The terminal device may be a computing device such as a desktop computer, a notebook, a PDA, and a smart tablet. The terminal 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 terminal devices and do not constitute a limitation on the terminal device. The terminal device may include more or fewer components than the above components, or may combine certain components, or different components. For example, the terminal device may also include input and output devices, network access devices, buses, etc.

[0156] 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. The general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the terminal device, and uses various interfaces and lines to connect various parts of the entire terminal device.

[0157] The memory can be used to store the computer program and / or module, and the processor realizes various functions of the terminal 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.

[0158] Wherein, if the module / unit integrated in the terminal 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.

[0159] 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.

[0160] 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 method for predicting the insulation performance of a high-voltage wiring harness for a new energy vehicle, characterized in that: include: Obtain the operating status of the high-voltage wiring harness of new energy vehicles; According to the operating state of the high-voltage wire harness of the new energy vehicle, a data dynamic synchronous collection operation is performed to obtain an insulation performance index set; According to the insulation performance index set, normalization processing is performed to obtain standardized insulation data; According to the preset factor set and the standardized insulation data, key factor particles are divided to obtain key factor particles; According to the key factor particles, the correlation degree is calculated by quantum annealing algorithm to obtain the factor particle correlation matrix, including: According to the key factor particles, a quantum bit encoding operation is performed to obtain quantum state representation data; Performing a Hamiltonian construction operation according to the quantum state representation data to obtain a quantum annealing model; According to the quantum annealing model, an annealing optimization operation is performed to obtain an optimal correlation solution; According to the optimal association solution, a matrix reconstruction operation is performed to obtain a factor particle association matrix; According to the factor particle association matrix, an iterative optimization is performed through a quantum particle swarm optimization algorithm to generate an insulation performance prediction matrix; Based on the insulation performance prediction matrix, insulation performance calculation is performed to obtain insulation performance prediction data.

2. The insulation performance prediction method of the high-voltage wire harness of a new energy vehicle according to claim 1 is characterized in that: According to the operation state of the high-voltage wire harness of the new energy vehicle, a data dynamic synchronous acquisition operation is performed to obtain an insulation performance index set, including: According to the operating state, a dynamic sensor group matching operation is performed to obtain synchronized multi-source sensor data; According to the synchronous multi-source sensor data, an insulation performance degradation model matching operation is performed to obtain an insulation performance index set; The operating states include driving state, charging state and stationary state.

3. The insulation performance prediction method of the high-voltage wire harness of a new energy vehicle according to claim 1 is characterized in that: The step of performing normalization processing according to the insulation performance index set to obtain standardized insulation data includes: According to the insulation performance index set, a value range matching operation is performed to obtain a normalized threshold value corresponding to each index; According to the normalization threshold, a linear normalization conversion operation is performed to obtain standardized conversion data; According to the standardized conversion data, a data dimension alignment operation is performed to obtain standardized insulation data.

4. The insulation performance prediction method of the high-voltage wire harness of a new energy vehicle according to claim 1 is characterized in that: The step of dividing the key factor particles according to the preset factor set and the standardized insulation data to obtain the key factor particles includes: Performing a factor correlation analysis operation according to the preset factor set and the standardized insulation data to obtain a factor correlation matrix; According to the factor correlation matrix, a clustering operation is performed to obtain an initial factor particle set; According to the initial factor granule set, a weight calculation operation is performed to obtain a weight value of each factor granule; According to the weight value, a key factor screening operation is performed to obtain key factor particles.

5. The insulation performance prediction method of the high-voltage wire harness of a new energy vehicle according to claim 4 is characterized in that: The step of performing a factor correlation analysis operation according to the preset factor set and the standardized insulation data to obtain a factor correlation matrix includes: According to the preset factor set and the standardized insulation data, a fuzzy membership calculation operation is performed to obtain a fuzzy membership value of each factor; According to the fuzzy membership value, a fuzzy relationship construction operation is performed to obtain a fuzzy relationship matrix between factors; According to the fuzzy relationship matrix, a fuzzy clustering analysis operation is performed to obtain a factor correlation matrix; The calculation formula for the fuzzy membership calculation is as follows: in, Indicates Standardized insulation data for the The membership value of fuzzy clustering of factor sets; represents a natural constant; represents the adjustment coefficient; Indicates Standardized insulation data values; Indicates The central value of the fuzzy clustering of the factor set; Indicates The standard deviation of fuzzy clustering of factor sets.

6. The insulation performance prediction method of the high-voltage wire harness of a new energy vehicle according to claim 4 is characterized in that: The calculation formula of the weight calculation operation is as follows: in, Indicates The weight value of each factor particle; Indicates The number of factors contained in each factor particle; Indicates The average correlation coefficient of each factor particle; It represents the sum of weighted contributions of all factor particles, and m represents the number of factor particles.

7. The insulation performance prediction method of the high-voltage wire harness of a new energy vehicle according to claim 1 is characterized in that: The step of iteratively optimizing the factor particle association matrix by using a quantum particle swarm optimization algorithm to generate an insulation performance prediction matrix includes: According to the factor particle association matrix, a quantum particle swarm initialization operation is performed to obtain an initial particle swarm; Performing a fitness calculation operation according to the initial particle group to obtain a particle fitness value; According to the particle fitness value, a quantum state update operation is performed to obtain an updated particle swarm; Performing iterative optimization operations according to the updated particle swarm to obtain an optimal solution set; According to the optimal solution set, a matrix generation operation is performed to obtain an insulation performance prediction matrix.

8. The insulation performance prediction method of the high-voltage wire harness of a new energy vehicle according to claim 1 is characterized in that: The step of performing insulation performance calculation based on the insulation performance prediction matrix to obtain insulation performance prediction data includes: Performing a data extraction operation according to the insulation performance prediction matrix to obtain a prediction characteristic value; Performing a weighted sum operation according to the predicted characteristic values ​​to obtain a comprehensive insulation performance score; According to the comprehensive insulation performance score, a threshold judgment operation is performed to obtain an insulation performance status classification; According to the insulation performance status classification, a data mapping operation is performed to obtain insulation performance prediction data.

9. A system for predicting the insulation performance of a high-voltage wiring harness for a new energy vehicle, characterized in that: A method for predicting the insulation performance of a high-voltage wiring harness for a new energy vehicle according to any one of claims 1 to 8, comprising: The status acquisition module is used to obtain the operating status of the high-voltage wiring harness of new energy vehicles; A data acquisition module, used to perform dynamic and synchronous data acquisition operations according to the operating status of the high-voltage wire harness of the new energy vehicle to obtain an insulation performance index set; A data processing module, used for performing normalization processing according to the insulation performance index set to obtain standardized insulation data; A key partitioning module, used to partition key factor particles according to a preset factor set and the standardized insulation data to obtain key factor particles; A correlation calculation module is used to calculate the correlation according to the key factor particles through a quantum annealing algorithm to obtain a factor particle correlation matrix; A quantum optimization module, used for iteratively optimizing the factor particle association matrix through a quantum particle swarm optimization algorithm to generate an insulation performance prediction matrix; The performance prediction module is used to perform insulation performance calculation based on the insulation performance prediction matrix to obtain insulation performance prediction data.

Images