A Method for Predicting the Safety Performance and Service Life of a New Energy Vehicle Charging Pile

Abstract

The present invention proposes a method for predicting the safety performance and lifespan of a new energy vehicle charging pile, including: collecting data from real-time operation monitoring devices of the new energy vehicle charging pile; constructing a degradation model of key components to evaluate the lifespan degradation trend of the current charging pile; adopting a time decay model based on the remaining lifespan of the current charging pile; constructing a group lifespan prediction model to predict the overall remaining lifespan of the charging pile group in the micro-region according to the failure risk probability of the current charging pile; using micro-region environmental data combined with dynamic load characteristics to evaluate the current load optimization strategy; designing a load optimization strategy to maximize the overall lifespan of the charging pile group in the micro-region, and generating an active maintenance plan based on the priority maintenance list. The present invention realizes the full-process closed-loop management from data collection to load modeling, lifespan prediction and active optimization, and provides an efficient and accurate solution for the safety performance and lifespan management of charging piles.

Description

Technical Field

[0001] The present invention belongs to the field of new energy vehicle charging piles, and particularly relates to a method for predicting the safety performance and life of new energy vehicle charging piles. Background Art

[0002] As the core facility of the electric vehicle charging network, the operation safety and life prediction of new energy vehicle charging piles have always been the focus of attention of operators. The core function of the charging pile is to provide stable and efficient charging services for new energy vehicles. However, during long-term use, the safety performance and the life of key components of the charging pile will be affected by various factors, such as power quality fluctuations, user charging behaviors, environmental conditions (such as temperature and humidity), and dynamic changes in load distribution. Currently, many charging pile operators adopt life management methods based on fixed thresholds or single-component monitoring. Such methods have the following defects:

[0003] Dynamic load factors are not fully considered: When multiple charging piles operate together in a micro-region, there are usually significant differences in the load distribution of different charging piles. For example, frequently used charging piles may accelerate aging due to long-term overload operation, while underutilized charging piles have insufficient life utilization. However, existing technologies mostly analyze the static life of a single charging pile, ignoring the overall impact of load dynamic changes on the life of a group of charging piles.

[0004] Insufficient modeling of key component deterioration: Key components of the charging pile (such as power modules, heat dissipation systems, and connecting cables) will experience performance degradation due to multiple factors such as voltage fluctuations and environmental temperature and humidity during long-term operation. Currently, many life prediction methods fail to accurately model the natural deterioration process of components, but simply evaluate them through empirical thresholds. This method is difficult to predict the remaining life of components and cannot accurately identify high-risk components.

[0005] Lack of an active optimization mechanism: The existing charging pile maintenance mode is mostly passive, that is, maintenance or replacement is carried out only after the equipment fails. This not only increases the risk of unplanned downtime but also may lead to low utilization of resources within the group.

[0006] In view of the above defects, there is an urgent need for a new method that organically combines dynamic load, component deterioration, and active optimization to provide accurate life prediction and safety performance management capabilities, and provide effective decision-making support for charging pile operators. Summary of the Invention

[0007] The object of the present invention is to propose a method for predicting the safety performance and life of new energy vehicle charging piles, a method for predicting the safety performance and life of new energy vehicle charging piles that combines the dynamic load distribution in a micro-region with a key component deterioration model, and overcomes the limitations of traditional methods by introducing a new collaborative analysis and active optimization mechanism.

[0008] To achieve the above object, the present invention provides a method for predicting the safety performance life of a new energy vehicle charging pile, and the method includes the following steps:

[0009] Collect the real-time operation monitoring device data of the new energy vehicle charging pile, construct a micro-region load interaction graph by using the load correlation of the charging pile, and use a custom graph embedding method to extract dynamic load features in the micro-region load interaction graph to obtain dynamic load features. The dynamic load features are time series matrices, representing the dynamic load states of each charging pile in the micro-region, and each row corresponds to the comprehensive features of a charging pile; wherein, the real-time operation monitoring device data includes the load rate of the charging pile, the usage frequency of the charging pile, the load peak distribution of the charging pile, the load correlation between any two charging piles, and the micro-region environment data;

[0010] Construct a key component deterioration model based on the real-time operation monitoring device data to evaluate the life deterioration trend of the current charging pile, obtain the unit time deterioration rate of the current charging pile, and predict the remaining life of the current charging pile according to the unit time deterioration rate of the current charging pile;

[0011] Adopt a time decay model based on the remaining life of the current charging pile to calculate the failure risk probability of the current charging pile, and obtain the failure risk probability of the current charging pile;

[0012] Construct a group life prediction model to predict the overall remaining life of the charging pile group in the micro-region according to the failure risk probability of the current charging pile, and generate a priority maintenance list according to the failure risk probability of the current charging pile and the remaining life of the current charging pile to ensure the minimization of the operation risk of the charging piles in the group;

[0013] Use the micro-region environment data combined with the dynamic load features to evaluate the current load optimization strategy, calculate the potential improvement amount of the load optimization on the group life, and obtain the group life improvement potential;

[0014] Design a load optimization strategy to maximize the overall life of the charging pile group in the micro-region, generate an active maintenance plan based on the priority maintenance list, select the charging piles that need to replace components, and optimize in combination with the dynamic load. According to the optimized load distribution, design a dynamic shunt strategy to adjust the user load to low-load devices, and achieve the maximization of the group life through gradient optimization and regularization constraints.

[0015] Further, the micro-region load interaction graph is constructed as follows:

[0016] Node represents the th charging pile in the micro-region;

[0017] Edge weight is the load correlation , reflecting the load correlation intensity between charging piles, is defined as follows:

[0018] ;

[0019] Among them, represents the load rate of the th charging pile at time ; and the load rate of the th charging pile at time ; is the covariance of the load rates; represents the standard deviation of the load rate of the th charging pile at time ; is the standard deviation of the load rate of the th charging pile at time ; is the standard deviation of the load rate of the th charging pile at time

[0020] Use a custom graph embedding method to extract dynamic load features from the micro-region load interaction graph, obtaining dynamic load features, specifically including:

[0021] For each node , summarize the features of its first-order neighborhood:

[0022] ;

[0023] Among them, is the first-order neighborhood aggregation feature of the th charging pile at time ; represents the set of neighborhood nodes of ; is the feature vector of the neighbor node , including , is the usage frequency of the th charging pile at time , is the load peak distribution of the th charging pile at time ;

[0024] Combine the environmental data , and normalize and update the features of all nodes:

[0025] ;

[0026] Among them, is the final feature representation of the node ; is the weight matrix; is the bias term; is the activation function for non - linear mapping;

[0027] The finally obtained load feature is a time - series matrix representing the dynamic load status of each charging pile in the micro - region. Each row corresponds to the comprehensive feature of a charging pile, and the output form is:

[0028] ;

[0029] where is the micro - region load feature matrix; is the th charging pile's comprehensive load feature at time .

[0030] Furthermore, the key component deterioration model is expressed as:

[0031] ;

[0032] where is the unit - time deterioration rate of the key component of the th charging pile; is the influence function of the dynamic load feature on deterioration, represented by the non - linear combination of the dynamic load feature matrix ; is the square term of voltage, reflecting the stress effect of high voltage on the component; is the current term, reflecting the heat loss of the component caused by large current; is the combined term of micro - region environmental data, used to quantify the influence of external conditions such as temperature and humidity; , , and are the weights of the corresponding terms; is the regularization additional term, used to capture the special effect of the voltage - current interaction on the component's accelerated aging, expressed as:

[0033] ;

[0034] Predicting the remaining life of the current charging pile according to the unit - time deterioration rate of the current charging pile is expressed as:

[0035] ;

[0036] where is the remaining life of the current charging pile; is the initial design life; is the cumulative deterioration value, obtained by integrating the deterioration rate formula.

[0037] Furthermore, the failure risk probability is calculated as follows:

[0038] ;

[0039] wherein is the cumulative deterioration.

[0040] Furthermore, it is characterized in that the group life prediction model is expressed as:

[0041] ;

[0042] wherein is the overall remaining life of the charging pile group in the micro-region; is the failure risk of the th charging pile, weighted by adjusting the life through ; is the life improvement function of the dynamic load and environmental conditions, used to capture the positive effect of load optimization; is the adjustment factor, controlling the influence proportion of load optimization on the overall life; is the total number of charging piles in the group;

[0043] The priority repair list is generated according to the priority score, and the calculation is as follows:

[0044] ;

[0045] wherein is the priority score of the th charging pile; is the load abnormality, capturing the abnormal deviation of the load characteristics; is the abnormality weight coefficient, controlling the influence of abnormal load on the priority; sorted from high to low according to to generate the priority repair list , where a high score represents the necessity of priority repair.

[0046] Furthermore, the life improvement function of the dynamic load and environmental conditions is designed as follows:

[0047] ;

[0048] wherein is the load abnormality, quantifying the part of the load characteristics that deviates from the normal range, used to deduct the negative factors of life improvement; is the abnormal load deduction coefficient, adjusting the weight of the influence of abnormal load on life.

[0049] Furthermore, the current load optimization strategy is evaluated using micro-region environmental data combined with dynamic load characteristics, and the potential increase in the group lifespan due to load optimization is calculated to obtain the group lifespan improvement potential, which is calculated as follows:

[0050] ;

[0051] where, is the potential increase in the group lifespan due to load optimization.

[0052] Furthermore, the optimization objective of the load optimization strategy is:

[0053] ;

[0054] where, is the overall lifespan of the optimized group; is the current group lifespan; is the load variance of the th charging pile after optimization, used to quantify the load balance; is the load balance adjustment coefficient, weighing the priorities of balance and lifespan improvement.

[0055] Furthermore, the generation of an active maintenance plan based on the priority maintenance list is expressed as:

[0056] ;

[0057] where, is the maintenance decision of the th charging pile, 1 indicates that maintenance is required, and 0 indicates that maintenance is not required; is the threshold ratio of the remaining lifespan, used to determine whether equipment with a short lifespan needs to be actively replaced; is the risk threshold, used to determine whether equipment with a high failure risk needs to replace key components;

[0058] The charging piles that meet the maintenance conditions are sorted by and incorporated into the maintenance plan one by one, and the final maintenance list is output.

[0059] Furthermore, the dynamic shunt strategy is expressed as:

[0060] ;

[0061] where, is the optimized load distribution; is the learning rate, used to control the gradient adjustment step size; is the gradient of the lifespan improvement potential with respect to the load distribution, guiding the load optimization direction; is the load smoothing regularization term, used to reduce load jumps and fluctuations, and is defined as: ;

[0062] wherein is the set of neighbor nodes of

[0063] The beneficial technical effects of the present invention are at least as follows:

[0064] Aiming at the deficiencies of the prior art, the present invention can accurately identify faults in complex and changeable scenarios and adopt intelligent response strategies. Its main innovation points are as follows:

[0065] The present invention regards multiple charging piles in a micro-region as a collaborative group, collects and models the real-time load distribution characteristics of each charging pile, and constructs a dynamic load interaction model between charging piles using a graph neural network (GCN) to analyze the collaborative impact of load distribution on the life of a single charging pile in the group. This innovation point solves the problem in the existing methods of ignoring the overall impact of load dynamic changes on the life of charging piles and provides a more accurate group life prediction ability.

[0066] The present invention introduces multi-dimensional monitoring data (such as current, voltage, ambient temperature and humidity, etc.) and combines with maintenance history records, and adopts a method combining physical drive and data drive to accurately fit the degradation curve of key components of the charging pile and predict its remaining life and failure risk. Different from the traditional empirical evaluation method, this method improves the accuracy of life prediction through degradation modeling and provides specific high-risk component guidelines for operators.

[0067] Aiming at the group life prediction and component degradation results, the present invention generates an active maintenance plan and a load regulation strategy through an optimization algorithm. For example, by adjusting the load distribution, the pressure on high-load charging piles is reduced, and components with critical life are replaced in advance to avoid unplanned outages. This innovation point solves the problem of the lack of an active optimization mechanism in the existing technology and greatly improves the resource utilization rate and operation reliability of the charging pile. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] The present invention is further described with reference to the accompanying drawings, but the embodiments in the drawings do not constitute any limitation to the present invention. For those of ordinary skill in the art, other drawings can also be obtained according to the following drawings without creative efforts.

[0069] Figure 1 is a flowchart of a method for predicting the safety performance life of a new energy vehicle charging pile according to the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0070] Embodiments of the present invention will be described in detail below. Examples of the embodiments are shown in the accompanying drawings, where the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the accompanying drawings are exemplary and are only used to explain the present invention and should not be construed as a limitation of the present invention.

[0071] As Figure 1 shown, a method for predicting the safety performance life of a new energy vehicle charging pile provided by an embodiment of the present invention includes:

[0072] S1. Collect real-time operation monitoring device data of the new energy vehicle charging pile, construct a micro-region load interaction graph using the load correlation of the charging pile, and extract dynamic load features in the micro-region load interaction graph using a custom graph embedding method to obtain dynamic load features. The dynamic load features are a time series matrix representing the dynamic load states of each charging pile in the micro-region, and each row corresponds to the comprehensive features of a charging pile; wherein, the real-time operation monitoring device data includes the load rate of the charging pile, the usage frequency of the charging pile, the load peak distribution of the charging pile, the load correlation between any two charging piles, and micro-region environment data.

[0073] Specifically, this step is the basis of the entire patent solution and aims to provide accurate load feature data for subsequent life prediction and optimization. By constructing the load interaction graph of the charging pile and extracting dynamic load features , the load distribution and interaction relationship of the charging piles in the micro-region are captured. This load feature matrix, as an important input for the subsequent steps, reflects the synergy effect and dynamic change characteristics among the charging piles.

[0074] Among them, the input data includes the following parts, all of which are from the real-time operation monitoring device of the charging pile:

[0075] : The load rate (the ratio of the charging power to the maximum power) of the th charging pile at time ;

[0076] : The usage frequency (the number of charging times per unit time) of the th charging pile at time ;

[0077] : The load peak distribution of the th charging pile at time ;

[0078] : The load correlation between the th and th charging piles at time The load correlation, calculated as the correlation coefficient of the two load time series;

[0079] : Micro-region environmental data (such as multi-dimensional vectors of temperature and humidity).

[0080] The input data has been cleaned, normalized, and time-aligned through preprocessing steps to ensure data continuity and availability.

[0081] Furthermore, using the load correlation of charging piles Construct a micro-region load interaction graph :

[0082] Nodes represent the th charging pile within the micro-region;

[0083] Edge weights are , reflecting the strength of the load correlation between charging piles, and are defined as follows:

[0084] ;

[0085] where represents and 's covariance; represents 's standard deviation; represents 's standard deviation. The load interaction graph dynamically reflects the synergy of the load distribution between different charging piles and is the core basis for subsequent analysis.

[0086] Furthermore, use a custom graph embedding method to extract dynamic load features . Graph embedding includes the following steps:

[0087] Neighborhood aggregation: For each node , summarize the features of its first-order neighborhood (i.e., directly connected charging pile nodes):

[0088] ;

[0089] where is the first-order neighborhood aggregation feature of the th charging pile at time ; represents 's set of neighborhood nodes; is the feature vector of neighbor node , containing .

[0090] Furthermore, global feature update: Combining environmental data , normalize and update all node features:

[0091] ;

[0092] Among them, is the final feature representation of node ; is the weight matrix; is the bias term; is the activation function for non - linear mapping.

[0093] The finally obtained load feature is a time - series matrix representing the dynamic load status of each charging pile in the micro - region. Each row corresponds to the comprehensive feature of a charging pile, and the output form is:

[0094] ;

[0095] Among them, is the micro - region load feature matrix; is the th charging pile's comprehensive load feature at time .

[0096] It can be understood that the load feature will be used in the key component degradation model in the subsequent steps, providing the dynamic load behavior data of the charging pile as an important influencing factor for component life assessment.

[0097] S2. Construct a key component degradation model based on real - time operation monitoring device data to evaluate the life degradation trend of the current charging pile, obtain the unit - time degradation rate of the current charging pile, and predict the remaining life of the current charging pile according to the unit - time degradation rate of the current charging pile.

[0098] Among them, to evaluate the life degradation trend of the key components of the charging pile, the following targeted formula is designed to fully reflect the complex relationship between the dynamic load characteristics of the charging pile and the component performance decay:

[0099] Degradation rate formula:

[0100] ;

[0101] Among them, is the unit - time degradation rate of the key components of the th charging pile; is the influence function of the dynamic load feature on degradation, represented by the non - linear combination of ; is the square term of voltage, reflecting the stress effect of high voltage on components; is the current term, reflecting the heat loss of the component due to high current; is a combined term of environmental data, used to quantify the influence of external conditions such as temperature and humidity; is a regularization additional term, used to capture the special effect of the voltage and current interaction on the accelerated aging of the component;

[0102] ;

[0103] This design takes into account the complex influence of the non - linear interaction between voltage and current on the deterioration of the component.

[0104] Furthermore, based on the above deterioration rate formula, calculate the remaining life of the th key component of the charging pile :

[0105] ;

[0106] Among them, is the remaining life of the th key component at time ; is the initial design life; is the cumulative deterioration value, obtained by integrating the deterioration rate formula.

[0107] To ensure the reliability of the calculation, the cumulative deterioration value is dynamically adjusted every time a key environmental change (such as extreme high temperature or sudden high load) occurs to reflect the true life state.

[0108] S3. Based on the remaining life of the current charging pile, adopt the time - decay model to calculate the failure risk probability of the current charging pile, and obtain the failure risk probability of the current charging pile.

[0109] Specifically, based on the remaining life , define the failure risk probability of the component, and calculate it using the time - decay model:

[0110] ;

[0111] Among them, is the failure risk probability of the th key component at time ; is the cumulative deterioration; is the initial design life. This formula combines the calculation results of the deterioration rate formula, correlates the remaining life of the component with the failure probability, and is used to evaluate the fault risk during real - time operation.

[0112] S4. Build a group life prediction model to predict the overall remaining life of the charging pile group in the micro-region based on the failure risk probability of the current charging pile. At the same time, generate a priority maintenance list according to the failure risk probability of the current charging pile and the remaining life of the current charging pile to ensure the minimization of the operation risk of the charging piles in the group.

[0113] Specifically, when predicting the life of the charging pile group in the micro-region, the individual life , failure risk and the combined effect of dynamic load on life need to be comprehensively considered. The following model is proposed:

[0114] Overall life formula:

[0115] ;

[0116] Among them, is the overall remaining life of the charging pile group in the micro-region; is the remaining life of the th charging pile; is the failure risk of the th charging pile, and adjusts the weighting of life through ; is the life improvement function of dynamic load and environmental conditions, used to capture the positive effect of load optimization; is the adjustment factor, controlling the influence ratio of load optimization on the overall life; is the total number of charging piles in the group.

[0117] Life improvement function design: Considers the improvement effect of load characteristics and environmental conditions on life, and is specifically defined as:

[0118] ;

[0119] Among them, is the dynamic load characteristic of the th charging pile; is the environmental condition vector; is the load abnormality degree, quantifying the part of the load characteristic that deviates from the normal range, used to deduct the negative factors of life improvement; is the abnormal load deduction coefficient, adjusting the weight of the influence of abnormal load on life. This formula dynamically adjusts the positive and negative effects brought by optimization in life assessment by combining load distribution and environmental conditions.

[0120] Furthermore, according to and , comprehensively considering the dynamic load characteristics, generate a priority maintenance list to ensure the minimization of the operation risk of the charging piles in the group:

[0121] Priority score:

[0122] ;

[0123] Among them, is the priority score of the th charging pile; is the load abnormality degree, capturing the abnormal deviation of the load characteristics; is the abnormality degree weight coefficient, controlling the impact of abnormal load on the priority.

[0124] Sort in descending order according to to generate a priority repair list , where a high score represents the necessity of priority repair.

[0125] S5. Evaluate the current load optimization strategy by combining the micro-region environmental data with the dynamic load characteristics, calculate the potential improvement in the group life due to the load optimization, and obtain the group life improvement potential.

[0126] Specifically, to optimize the life of the charging piles in the micro-region, evaluate the life improvement potential brought by the load optimization:

[0127] Potential formula:

[0128] ;

[0129] Among them, is the potential improvement in the group life due to the load optimization; is the life improvement function. By calculating , the actual value of the current load optimization strategy can be dynamically evaluated, providing data support for subsequent active optimization and planning.

[0130] S6. Design a load optimization strategy to maximize the overall life of the charging pile group in the micro-region, generate an active maintenance plan based on the priority repair list, select the charging piles that need to replace components, and optimize in combination with the dynamic load. According to the optimized load distribution, design a dynamic shunt strategy to adjust the user load to low-load devices, and maximize the group life through gradient optimization and regularization constraints.

[0131] Specifically, in the load optimization, it is necessary to balance the reasonable distribution of load balance and device utilization rate on the basis of maximizing the group life. For this purpose, design the following innovative formula:

[0132] Optimization goal: Maximize the overall life after optimization :

[0133] ;

[0134] Among them, is the overall optimized group life; is the current group life; is the life improvement potential optimized for the load; After optimization, for the th charging pile, the load variance is used to quantify the load balance; is the load balance adjustment coefficient, weighing the priorities of balance and life improvement. In this formula, the load balance is achieved by introducing the load variance term to avoid the problem of excessive load on individual charging piles during the optimization process. The core of the optimization lies in adjusting the value so that it can not only achieve life improvement but also avoid excessive unevenness in the load distribution.

[0135] Furthermore, the proactive maintenance plan selects the charging piles that need component replacement based on the priority maintenance list and the equipment status, and optimizes it in combination with the dynamic load:

[0136] Maintenance decision formula:

[0137] ;

[0138] Among them, is the maintenance decision for the th charging pile. 1 indicates that maintenance is required, and 0 indicates that maintenance is not required; is the threshold ratio of the remaining life, used to determine whether equipment with a short life needs to be proactively replaced; is the risk threshold, used to determine whether equipment with a high failure risk needs to replace key components. The charging piles that meet the maintenance conditions are sorted according to and included in the maintenance plan one by one to output the final maintenance list.

[0139] Furthermore, according to the optimized load distribution, a dynamic shunt strategy is designed to adjust the user load to low-load equipment:

[0140] Load adjustment formula:

[0141] ;

[0142] Among them, is the optimized load distribution; is the learning rate, used to control the gradient adjustment step size; is the gradient of the life improvement potential with respect to the load distribution, guiding the load optimization direction; is the load smoothing regularization term, used to reduce load jumps and fluctuations, defined as: ;

[0143] Among them is the set of neighbor nodes. The smoothing regularization term ensures the continuity of the load distribution among the neighborhoods, avoiding overly abrupt load transfers.

[0144] This step combines load optimization and proactive maintenance to achieve the dual goals of lifespan improvement and load balancing through gradient optimization and regularization constraints. The innovation of the solution lies in the dynamic adjustment of the load distribution and the accuracy of the maintenance plan, significantly improving the overall lifespan and operating efficiency of the group.

[0145] Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0146] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division, and there can be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Additionally, the couplings, direct couplings, or communication connections shown or discussed among each other can be through some interfaces. The indirect couplings or communication connections of the devices or units can be in electrical, mechanical, or other forms.

[0147] If the described functions are implemented in the form of software function units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The foregoing storage medium includes: USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs, and other various media that can store program codes.

[0148] Although the embodiments of the present invention have been shown and described, those skilled in the art can understand that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the claims and their equivalents.

Claims

1. A method for predicting the safety performance life of a new energy vehicle charging pile, characterized in that: The method comprises the following steps: Collect the real-time operation monitoring equipment data of the new energy vehicle charging piles, use the load correlation of the charging piles to build a micro-region load interaction graph, use a custom graph embedding method to extract dynamic load features in the micro-region load interaction graph, and obtain dynamic load features. The dynamic load features are time series matrices that represent the dynamic load status of each charging pile in the micro-region, and each row corresponds to the comprehensive features of a charging pile; wherein the real-time operation monitoring equipment data includes the load rate of the charging pile, the usage frequency of the charging pile, the load peak distribution of the charging pile, the load correlation of two random charging piles, and the micro-region environmental data; Constructing a key component degradation model based on real-time operation monitoring equipment data to evaluate the life degradation trend of the current charging pile, obtaining the unit time degradation rate of the current charging pile, and predicting the remaining life of the current charging pile based on the unit time degradation rate of the current charging pile; Based on the remaining life of the current charging pile, a time decay model is used to calculate the failure risk probability of the current charging pile, and the failure risk probability of the current charging pile is obtained; Construct a group life prediction model to predict the overall remaining life of the charging pile group in the micro-area according to the failure risk probability of the current charging pile. At the same time, generate a priority maintenance list based on the failure risk probability of the current charging pile and the remaining life of the current charging pile to ensure that the operation risk of the charging piles in the group is minimized; Use micro-regional environmental data combined with dynamic load characteristics to evaluate the current load optimization strategy, calculate the potential improvement in group life due to load optimization, and obtain the potential for group life improvement; Design a load optimization strategy to maximize the overall life of the charging pile group in the micro-area, generate an active maintenance plan based on the priority maintenance list, select the charging piles that need to replace parts, and optimize them in combination with the dynamic load. According to the optimized load distribution, design a dynamic diversion strategy to adjust the user load to the low-load equipment, and maximize the group life through gradient optimization and regularization constraints.

2. A method for predicting the safety performance life of a new energy vehicle charging pile according to claim 1, characterized in that: The micro-area load interaction diagram is constructed as follows: node Indicates the first Charging stations; Edge Weight Load dependency , reflects the load correlation strength between charging piles and is defined as follows: ； in, Indicates Charging stations at the time Load rate and Charging stations at the time Load rate The covariance of Indicates Charging stations at the time Load rate The standard deviation of Indicates Charging stations at the time Load rate The standard deviation of A customized graph embedding method is used to extract dynamic load features in the micro-area load interaction graph to obtain dynamic load features, including: For each node , summarizing the characteristics of its first-order neighbors: ； in, It is Charging stations at the time The first-order neighborhood aggregation characteristics of express The set of neighboring nodes; Neighbor node The feature vector of , For the Charging stations at the time Frequency of use, For the Charging stations at the time Load peak distribution; Incorporating environmental data , normalize and update all node features: ； in, Is a node The final feature representation of is the weight matrix; is the bias term; Is an activation function, used for nonlinear mapping; The resulting load characteristics It is a time series matrix, which represents the dynamic load status of each charging pile in the micro area. Each row corresponds to the comprehensive characteristics of a charging pile. The output form is: ； in, is the micro-region load characteristic matrix; It is Charging stations at the time The comprehensive load characteristics.

3. A method for predicting the safety performance life of a new energy vehicle charging pile according to claim 1, characterized in that: The key component degradation model is expressed as: ； in, It is The degradation rate per unit time of key components of each charging pile; is the influence function of dynamic load characteristics on degradation, through the dynamic load characteristic matrix Nonlinear combination representation of ; is the voltage square term, reflecting the stress effect of high voltage on components; is the current term, reflecting the heat loss of components caused by large current; is environmental data, used to quantify the impact of external conditions; , , and is the weight of the corresponding item; is a regularization additional term used to capture the special effect of voltage and current interaction on accelerated aging of components, expressed as: ； The remaining life of the current charging pile is predicted according to the unit time degradation rate of the current charging pile, which is expressed as: ； in, The remaining life of the current charging pile; is the initial design life; is the cumulative degradation value, obtained by integrating the degradation rate formula.

4. A method for predicting the safety performance life of a new energy vehicle charging pile according to claim 1, characterized in that: The probability of failure risk , calculated as follows: ； in, For cumulative degradation, is the initial design life.

5. A method for predicting the safety performance life of a new energy vehicle charging pile according to any one of claims 3 or 4, characterized in that: The group life prediction model is expressed as: ； in, is the overall remaining life of the charging pile group in the micro area; It is The failure risk of each charging pile is Adjusting the weighting of life expectancy; is the life improvement function of dynamic load and environmental conditions, used to capture the positive effect of load optimization; is the adjustment factor, controlling the proportion of load optimization’s impact on overall life; is the total number of charging posts in the group; The remaining life of the current charging pile; The priority repair list is generated based on the priority score, calculated as follows: ； in, It is The priority score of each charging station; is the load anomaly degree, capturing the abnormal deviation of load characteristics; is the abnormality weight coefficient, which controls the impact of abnormal load on priority; according to Sort from high to low to generate a priority maintenance list , where a high score represents the necessity of priority maintenance, for environmental data; is the load characteristic matrix of the i-th charging pile.

6. A method for predicting the safety performance life of a new energy vehicle charging pile according to claim 5, characterized in that: The life improvement function of the dynamic load and environmental conditions The design is as follows: ； in, Load abnormality, which quantifies the part of the load characteristic that deviates from the normal range and is used to deduct the negative factors of life extension; It is the abnormal load deduction coefficient, which adjusts the weight of the impact of abnormal load on life.

7. A method for predicting the safety performance life of a new energy vehicle charging pile according to claim 5, characterized in that: The current load optimization strategy is evaluated by using micro-area environmental data combined with dynamic load characteristics, and the potential improvement of group life due to load optimization is calculated to obtain the potential improvement of group life, which is calculated as follows: ； in, Potential improvement in group lifespan for load optimization.

8. A method for predicting the safety performance life of a new energy vehicle charging pile according to claim 7, characterized in that: The optimization goal of the load optimization strategy is: ； in, is the overall lifespan of the optimized group; is the current group lifespan; After optimization The load variance of each charging pile is used to quantify the load balance; It is the load balancing adjustment coefficient, which weighs the priority between load balancing and life improvement.

9. A method for predicting the safety performance life of a new energy vehicle charging pile according to claim 5, characterized in that: The active maintenance plan is generated based on the priority maintenance list, which is expressed as: ； in, For the The maintenance decision of each charging pile, 1 means maintenance is needed, and 0 means no maintenance is needed; The threshold ratio of the remaining life is used to determine whether the equipment with a short life needs to be replaced proactively; is the risk threshold to determine whether the equipment with a higher risk of failure needs to replace key components; is the failure risk probability; Press the charging pile that meets the maintenance conditions Sort them, include them into the maintenance plan one by one, and output the final maintenance list.

10. A method for predicting the safety performance life of a new energy vehicle charging pile according to claim 8, characterized in that: The dynamic diversion strategy is expressed as: ； in, is the load characteristic matrix, For optimized load distribution; is the learning rate, which is used to control the gradient adjustment step size; The potential for life improvement is related to the gradient of load distribution, guiding the direction of load optimization; is a load smoothing regularization term used to reduce load jump fluctuations and is defined as: ； in yes The set of neighbor nodes.

Images