Electric vehicle charging intelligent management system based on multi-source data analysis

Abstract

The invention discloses an electric vehicle charging intelligent management system based on multi-source data analysis, and relates to the technical field of electric vehicle charging, and the electric vehicle charging intelligent management system is characterized in that information is extracted from multi-source data including historical charging data HC, driving behavior data Db, geographic position information GP and seasonal factors TS, and a PCA feature extraction technology is used to extract the multi-source data including historical charging data HC, driving behavior data Db, geographic position information GP and seasonal factors TS; the system can generate more personalized and accurate charging schemes according to actual conditions and preferences of different users. The system can dynamically adjust the charging time, the charging amount and the place according to the specific charging habit, the driving route and the seasonal factor of the user, so that the charging experience is more intelligent, and the charging time T, the charging amount Q and the charging station selection D of the historical charging data HC are subjected to feature extraction through the PCA technology. The system converts high-dimensional data into multi-dimensional features Z and generates a feature matrix HZ, so that the redundancy of the data is reduced, key features are reserved, and the efficiency of data analysis is greatly improved.

Description

Technical Field

[0001] The present invention relates to the technical field of electric vehicle charging, and in particular to an electric vehicle charging intelligent management system based on multi-source data analysis. Background Art

[0002] As an important part of ITS, the intelligent charging management system aims to provide personalized charging solutions and improve the charging efficiency of electric vehicles through intelligent algorithms and multi-source data analysis. Electric vehicle charging involves data sources in multiple dimensions, such as historical charging data, driving behavior, geographic location, and seasonal factors. These data can be analyzed and processed by the intelligent management system to provide users with charging solutions that better meet their personal needs.

[0003] In the invention patent with application publication number CN215552653U, an intelligent management system for electric vehicle charging piles based on big data is disclosed. The management system warns maintenance personnel through maintenance warnings of charging piles. When the charging pile is damaged, the charging head on it cannot be charged. When the current owner uses the charging head to connect the electric car, no current passes through the charging head. After the current detection system detects that no current passes through the charging head, it will simultaneously transmit this signal to the warning system, maintenance reminder system and field reminder system. The warning system can warn the current owner that the charging pile cannot be used.

[0004] However, the above functions make it difficult for drivers to find the most suitable charging station for themselves. At present, the current status of electric vehicle charging systems mainly relies on users' manual decisions or simple charging station management systems. There are many shortcomings, and they fail to effectively consider users' personalized needs, driving habits and driving routes, resulting in the charging process being too mechanical and unable to flexibly respond to actual needs. This charging method lacking intelligent analysis can easily cause users to encounter problems such as long charging time, unreasonable distribution of charging stations, and large fluctuations in charging costs during the charging process. Summary of the invention

[0005] In view of the deficiencies in the prior art, the present invention provides an electric vehicle charging intelligent management system based on multi-source data analysis, which solves the problems mentioned in the background technology.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: an electric vehicle charging intelligent management system based on multi-source data analysis, including a data acquisition module, a data preprocessing module, a feature extraction and weight distribution module, a personalized charging plan generation module, a user feedback and learning module and a system monitoring and maintenance module; The data acquisition module collects multi-source data in real time through sensors and vehicle-mounted devices, including the user's historical charging data H C , driving behavior data Db , Geographic location information G P and seasonal factor T S , forming the original data set W X ; The data preprocessing module processes the original data set W X Perform cleaning, denoising and normalization to obtain the multi-source data set W; The feature extraction and weight allocation module extracts features including charging time T, charging amount Q and charging station selection D from the multi-source data set W by using PCA feature extraction technology; The personalized charging plan generation module generates a charging plan based on the output of the weighted recommendation model and the user's charging needs, including the optimal charging time T C , optimal charging capacity Q C and the best charging location D LOC ; The user feedback and learning module records the user's feedback on the charging solution and adjusts the weight allocation strategy; The system monitoring and maintenance module monitors the status of the car during charging in real time, detects anomalies and faults, and performs regular evaluations.

[0007] Preferably, the data acquisition module includes a sensor data acquisition unit and a data integration and storage unit; The sensor data acquisition unit collects historical charging data H C , driving behavior data D b , Geographic location information G P and seasonal factor T S Collect historical charging data H C The driving behavior data D is extracted and composed by performing fixed-cycle extraction on the interaction records of the charging pile communication equipment. b The geographic location information G is collected by the vehicle ECU P The seasonal factor T is collected through the vehicle's GPS module. S Obtained through time and date information in the system; Among them, the historical charging data H C Including charging time T, charging amount Q, charging power P C and charging station selection D; driving behavior data D b Including average speed, driving time and driving pattern; The data integration and storage unit processes the historical charging data H collected by the sensor data collection unit. C , driving behavior data D b , Geographic location information G P and seasonal factor T SPerform preliminary integration to form the original data set W X .

[0008] Preferably, the data preprocessing module includes a data cleaning and denoising unit and a data normalization unit; The data cleaning and denoising unit processes the original data set W X Perform cleaning and denoising, where cleaning includes missing value processing and denoising includes using a smoothing filter to remove noise; Missing value processing for the original data set W X Perform missing filling processing to obtain the original filled data set W Xf , and then fill the original data set W Xf Use a smoothing filter to perform denoising and obtain the original denoised data set W XS ; The data normalization unit normalizes the original denoised data set W XS Perform normalization processing to obtain the multi-source data set W.

[0009] Preferably, the feature extraction and weight allocation module includes a feature extraction unit and a weight allocation unit; The feature extraction unit extracts historical charging data H from the multi-source data set W C , by using PCA to analyze the historical charging data H in the multi-source dataset W C Extract and obtain the features of user charging time T, charging amount Q and charging station selection D to form multidimensional feature Z , and perform feature matrix conversion to obtain the feature matrix HZ: The characteristic matrix HZ is transformed by the following transformation formula: ; Where P represents the transformation matrix of PCA; The characteristic matrix HZ is linearly combined to obtain the weighted characteristic matrix HZ: HZ ; In the formula, Respectively represent the preset weight values ​​of charging time T, charging amount Q and charging station selection D, and the preset weight value of charging time T , the preset weight value of the charge amount Q and the preset weight value of charging station selection D , forming a weight value group .

[0010] Preferably, the personalized charging scheme generation module includes a scheme generation unit and a scheme optimization unit; The solution generation unit obtains the weighted feature matrix HZ and weight group after weighting processing according to the feature extraction and weight distribution module. , for different regions, calculate the comprehensive score S of each region and obtain the optimal charging time T C , optimal charging capacity Q C and the best charging location D LOC ; The comprehensive score S is obtained by the following formula: S ; In the formula, represents the i-th eigenvalue of the j-th region, and Parameters representing the nonlinear contribution of the feature, represents the squared influence of the description feature, Represents the logarithmic change of the feature; According to the comprehensive score S, get the time period with the highest score , the highest scoring charging capacity and the highest scoring charging locations : , , ; In the formula, They represent the score of charging time, the score of charging amount and the score of charging location respectively; Based on the time period with the highest score Get the best charging time T C ; The optimal charging time T C Obtained by the following formula: T C ; In the formula, Pr represents the remaining power of the car, Ce represents the charging efficiency, Indicates the effect of seasons on charging efficiency: high efficiency in summer and low efficiency in winter; Based on the highest score charge Get the best charging amount Q C ; Q C ; In the formula, Indicates the total capacity of the vehicle battery, soc indicates the percentage of remaining power, ranging from 0 to 1. Indicates the reserved power required for future driving; Based on the highest scoring charging locations Get the best charging locationLOC ; The best charging location D LOC Obtained by the following formula: D LOC ; Where D LOC Indicates the best charging location, specifically the recommended charging station, Indicates the distance between the user's location and the charging station. represents the load factor of the charging station, represents the adjustment factor, Represents the minimum function.

[0011] Preferably, the solution optimization unit adjusts the solution according to the current needs of the user, external conditions and the current battery status of the vehicle. The solution optimization unit optimizes the optimal charging time T by using a constrained optimization algorithm. C and the best charging location D LOC Make adjustments; The constraint formula is: Optimal charging time T C ; Best charging location D LOC ; In the formula, Indicates the charging time range accepted by the user. Indicates the charging location accepted by the user.

[0012] Preferably, the user feedback and learning module includes a feedback recording unit and a reinforcement learning optimization unit; After the user completes charging, the feedback recording unit collects the user's feedback data and records the user's satisfaction; The feedback score F is defined by using to represent the user satisfaction; The user's satisfaction F is obtained by the following formula: F ; In the formula, Represent the weights of charging time, charging amount and charging location respectively, R L represents the user's satisfaction rating for the charging location, Indicates the optimal charging time T C The difference between the actual charging time and Indicates the optimal charge capacity Q C The difference between the actual charge and max Indicates the peak value of charging time, Q max Indicates the peak value of the charge level.

[0013] Preferably, the reinforcement learning optimization unit uses a Q-learning algorithm to learn according to feedback data and gradually adjust the weight allocation strategy; Using the Q-learning algorithm, define The value of performing action a in state s is to increase the user's satisfaction F; The formula of the Q-learning algorithm is: ; In the formula, s represents the current user charging demand and historical behavior, a represents the charging solution recommended by the system, represents the learning rate, represents the discount factor, Indicates the next state after executing action a.

[0014] Preferably, the system monitoring and maintenance module includes a real-time monitoring unit and a maintenance optimization unit; The real-time monitoring unit is responsible for real-time monitoring of parameters during the charging process, including current, voltage, charging power, charging speed and temperature changes; When the charging power and charging speed fluctuate abnormally within a period of time, the alarm mechanism is triggered and the abnormal information is sent to the user.

[0015] An electric vehicle charging intelligent management system based on multi-source data analysis, wherein the maintenance optimization unit responds according to abnormal conditions detected by the real-time monitoring unit, including adjusting the charging power, suspending charging, and switching the charging mode.

[0016] The present invention provides an electric vehicle charging intelligent management system based on multi-source data analysis, which has the following beneficial effects: (1) By collecting data from multiple sources including historical charging data H C , driving behavior data D b , Geographic location information G P and seasonal factor T S By extracting information from the data and using PCA feature extraction technology, the system can generate more personalized and accurate charging plans based on the actual conditions and preferences of different users. The system can dynamically adjust the charging time, charging amount and location based on the user's specific charging habits, driving routes and seasonal factors, making the charging experience more intelligent and convenient, and improving user satisfaction and usage experience.

[0017] (2) Through the sensor data acquisition unit, the system realizes the comprehensive collection of multi-dimensional data, including historical charging data H C , driving behavior data D b , Geographic location information G P and seasonal factor TS . Through rich data dimensions, the system can understand the user's charging needs more accurately and dynamically adjust the charging plan according to the actual environment and user behavior, significantly improving the accuracy and effectiveness of personalized recommendations. The data integration and storage unit will initially integrate the collected multi-source data to form the original data set WX, laying the foundation for subsequent data analysis and processing. The introduction of the data preprocessing module, especially the design of the data cleaning and denoising unit and the data normalization unit, solves the problems of data noise interference and inconsistent data formats in traditional systems.

[0018] (3) PCA technology is used to analyze the historical charging data H C The system extracts features of charging time T, charging amount Q and charging station selection D, converts high-dimensional data into multi-dimensional features Z and generates a feature matrix HZ. This method reduces the redundancy of data, removes irrelevant noise information, retains key features, and greatly improves the efficiency of data analysis. Compared with the traditional analysis mode based on raw data, PCA reduces the computational complexity and ensures more accurate charging plan recommendations; the weight allocation unit dynamically adjusts the weight values ​​of charging time T, charging amount Q and charging station selection D according to the historical behavior and preferences of different users by linearly combining and weighting the feature matrix HZ.

[0019] (4) A comprehensive score S is calculated for different regions, so that the system can provide personalized charging recommendations in different areas. In the formula, the nonlinear contribution parameter and square term of the eigenvalue are used to take into account the complex environmental factors during charging, and the trend of charging behavior is accurately described by the logarithmic change of the characteristic. Compared with traditional methods, the comprehensive score S can reflect the real-time power load, weather, user preferences and other factors in the user's area, thereby improving the adaptability and accuracy of charging solutions in various regions. The charging time T is calculated by the formula C The optimization not only considers the power and charging efficiency, but also takes into account the impact of seasonal factors on charging efficiency, thus avoiding power waste in extreme weather conditions. The system can recommend an optimal charging capacity Q that meets driving needs and does not waste charging time. C . BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 This is a flowchart diagram of an electric vehicle charging intelligent management system based on multi-source data analysis in the present invention. DETAILED DESCRIPTION

[0021] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0022] Example 1 The present invention provides an electric vehicle charging intelligent management system based on multi-source data analysis. Figure 1 , including data acquisition module, data preprocessing module, feature extraction and weight allocation module, personalized charging plan generation module, user feedback and learning module and system monitoring and maintenance module; The data acquisition module collects multi-source data in real time through sensors and vehicle-mounted devices, including the user's historical charging data H C , driving behavior data D b , Geographic location information G P and seasonal factor T S , forming the original data set W X ; The data preprocessing module processes the original data set W X Perform cleaning, denoising and normalization to obtain the multi-source data set W; The feature extraction and weight allocation module extracts features including charging time T, charging amount Q and charging station selection D from the multi-source data set W by using PCA feature extraction technology; The personalized charging plan generation module generates a charging plan based on the output of the weighted recommendation model and the user's charging needs, including the optimal charging time T C , optimal charging capacity Q C and the best charging location D LOC ; The user feedback and learning module records the user's feedback on the charging solution and adjusts the weight allocation strategy; The system monitoring and maintenance module monitors the status of the car during charging in real time, detects anomalies and faults, and performs regular evaluations.

[0023] In this embodiment, by collecting data from multiple sources including historical charging data H C , driving behavior data D b , Geographic location information G P and seasonal factor T SBy extracting information from the data and using PCA feature extraction technology, the system can generate more personalized and accurate charging plans based on the actual conditions and preferences of different users. The system can dynamically adjust the charging time, charging amount and location based on the user's specific charging habits, driving routes and seasonal factors, making the charging experience more intelligent and convenient, and improving user satisfaction and usage experience.

[0024] Through the user feedback and learning module, the system uses the user's feedback on the generated plan to continuously adjust the weight allocation strategy and use the reinforcement learning algorithm to continuously optimize the charging plan recommendation. The system monitoring and maintenance module ensures the stability of the entire system during operation, promptly discovers and solves potential abnormalities or faults, and ensures that users can get stable services. The system gives a comprehensive score S to the charging plan in each region. The system can combine the multi-dimensional factors of charging time T, charging amount Q, and charging station selection D to provide users with personalized charging plans in different regions, maximize the use of charging resources, avoid charging congestion during peak hours, improve charging efficiency, and save charging costs.

[0025] Example 2 This embodiment is explained in Example 1, please refer to Figure 1 ,Specifically: the data acquisition module includes a sensor data acquisition unit and a data integration and storage unit; The sensor data acquisition unit collects historical charging data H C , driving behavior data D b , Geographic location information G P and seasonal factor T S Collect historical charging data H C The driving behavior data D is extracted and composed by performing fixed-cycle extraction on the interaction records of the charging pile communication equipment. b The geographic location information G is collected by the vehicle ECU P The seasonal factor T is collected through the vehicle's GPS module. S Obtained through time and date information in the system; Among them, the historical charging data H C Including charging time T, charging amount Q, charging power P C and charging station selection D; driving behavior data D b Including average speed, driving time and driving pattern; The data integration and storage unit processes the historical charging data H collected by the sensor data collection unit. C , driving behavior data D b , Geographic location information G P and seasonal factor T S Perform preliminary integration to form the original data set W XThe data preprocessing module includes a data cleaning and denoising unit and a data normalization unit; The data cleaning and denoising unit processes the original data set W X Perform cleaning and denoising, where cleaning includes missing value processing and denoising includes using a smoothing filter to remove noise; Missing value processing for the original data set W X Perform missing filling processing to obtain the original filled data set W Xf , and then fill the original data set W Xf Use a smoothing filter to perform denoising and obtain the original denoised data set W XS ; The data normalization unit normalizes the original denoised data set W XS Perform normalization processing to obtain the multi-source data set W.

[0026] In this embodiment, through the sensor data acquisition unit, the system realizes the comprehensive acquisition of multi-dimensional data, including historical charging data H C , driving behavior data D b , Geographic location information G P and seasonal factor T S . Through rich data dimensions, the system can understand the user's charging needs more accurately, and dynamically adjust the charging plan according to the actual environment and user behavior, significantly improving the accuracy and effectiveness of personalized recommendations. The data integration and storage unit will preliminarily integrate the collected multi-source data to form the original data set WX, laying the foundation for subsequent data analysis and processing. The introduction of the data preprocessing module, especially the design of the "data cleaning and denoising unit" and the "data normalization unit", solves the problems of data noise interference and inconsistent data formats in traditional systems. Missing value processing and the use of smoothing filters to remove noise ensure the integrity and reliability of the original data. Data normalization further eliminates the dimensional differences between different data types, enabling multi-source data to be analyzed and processed under the same standard, improving the accuracy of data analysis results.

[0027] Example 3 This embodiment is explained in Example 2. Please refer to Figure 1 ,Specifically: the feature extraction and weight allocation module includes a feature extraction unit and a weight allocation unit; The feature extraction unit extracts historical charging data H from the multi-source data set W C , by using PCA to analyze the historical charging data H in the multi-source dataset W C Extract and obtain the features of user charging time T, charging amount Q and charging station selection D to form multidimensional feature Z , and perform feature matrix conversion to obtain the feature matrix HZ: The characteristic matrix HZ is transformed by the following transformation formula: ; Where P represents the transformation matrix of PCA; The characteristic matrix HZ is linearly combined to obtain the weighted characteristic matrix HZ: HZ ; In the formula, Respectively represent the preset weight values ​​of charging time T, charging amount Q and charging station selection D, and the preset weight value of charging time T , the preset weight value of the charge amount Q and the preset weight value of charging station selection D , forming a weight value group .

[0028] In this embodiment, the historical charging data H is analyzed by PCA technology. C The charging time T, charging amount Q and charging station selection D are extracted, and the system converts high-dimensional data into multi-dimensional features Z and generates a feature matrix HZ. This method reduces the redundancy of data, removes irrelevant noise information, retains key features, and greatly improves the efficiency of data analysis. Compared with the traditional analysis mode based on raw data, PCA reduces the computational complexity and ensures more accurate charging plan recommendations; the weight allocation unit dynamically adjusts the weight values ​​of charging time T, charging amount Q and charging station selection D according to the historical behavior and preferences of different users by linearly combining and weighting the feature matrix HZ. The feature matrix HZ is weighted by the preset weight values ​​to generate the weighted feature matrix HZ. This dynamic adjustment mechanism of the feature matrix can automatically optimize the recommendation model as the user behavior data changes, making the generation of charging plans more intelligent and adaptive.

[0029] Example 4 This embodiment is explained in Example 3, please refer to Figure 1 , specifically: the personalized charging scheme generation module includes a scheme generation unit and a scheme optimization unit; The solution generation unit obtains the weighted feature matrix HZ and weight group after weighting processing according to the feature extraction and weight distribution module. , for different regions, calculate the comprehensive score S of each region and obtain the optimal charging time T C , optimal charging capacity Q C and the best charging location D LOC ; The comprehensive score S is obtained by the following formula: S ; In the formula, represents the i-th eigenvalue of the j-th region, and Parameters representing the nonlinear contribution of the feature, represents the squared influence of the description feature, Represents the logarithmic change of the feature; According to the comprehensive score S, get the time period with the highest score , the highest scoring charging capacity and the highest scoring charging locations : , , ; In the formula, They represent the score of charging time, the score of charging amount and the score of charging location respectively; Based on the time period with the highest score Get the best charging time T C ; The optimal charging time T C Obtained by the following formula: T C ; In the formula, Pr represents the remaining power of the car, Ce represents the charging efficiency, Indicates the effect of season on charging efficiency; Based on the highest score charge Get the best charging amount Q C ; Q C ; In the formula, Indicates the total capacity of the vehicle battery, soc indicates the percentage of remaining power, ranging from 0 to 1. Indicates the reserved power required for future driving; Based on the highest scoring charging locations Get the best charging location LOC ; The best charging location D LOC Obtained by the following formula: D LOC ; Where D LOC Indicates the best charging location, specifically the recommended charging station, Indicates the distance between the user's location and the charging station. represents the load factor of the charging station, represents the adjustment factor, Represents the minimum function In this embodiment, a comprehensive score S is calculated for different regions, so that the system can provide personalized charging suggestions in different areas. In the formula, the nonlinear contribution parameter and square term of the eigenvalue are used to take into account the complex environmental factors during charging, and the trend of charging behavior is accurately described by the logarithmic change of the characteristic. Compared with the traditional method, the comprehensive score S can reflect the real-time power load, weather, user preferences and other factors in the user's area, and improve the adaptability and accuracy of the charging plan in various regions. The charging time T is calculated by the formula C The optimization not only considers the power and charging efficiency, but also takes into account the impact of seasonal factors on charging efficiency, thus avoiding power waste in extreme weather conditions. The system can recommend an optimal charging capacity Q that meets driving needs and does not waste charging time. C Compared with the traditional fixed charging amount recommendation, this embodiment is more flexible and energy-saving.

[0030] In terms of charging location recommendations, the system uses D LOC The formula takes into account the distance between the user's current location and the charging station, the load factor of the charging station, and the adjustment factor, ensuring that the charging station selected by the user is convenient and not overcrowded. At the same time, the introduction of the minimum function ensures that the user can always choose a charging station with the lowest load, avoiding the problem of long waiting time for charging. Compared with the ordinary charging station recommendation method, this embodiment greatly improves the rationality of charging station selection and user experience through the comprehensive calculation of load factor and distance.

[0031] Example 5 An intelligent management system for electric vehicle charging based on multi-source data analysis, please refer to Figure 1 Specifically: the solution optimization unit adjusts the solution according to the current needs of the user, external conditions and the current battery status of the vehicle. The solution optimization unit uses a constraint optimization algorithm to optimize the optimal charging time T C and the best charging location D LOC Make adjustments; The constraint formula is: Optimal charging time T C ∈[T min ,T max ]; Best charging location D LOC ∈[D LOC,min ,D LOC,max ]; Where, T min ,T maxIndicates the charging time range accepted by the user, D LOC,min ,D LOC,max Indicates the charging location accepted by the user.

[0032] The user feedback and learning module includes a feedback recording unit and a reinforcement learning optimization unit; After the user completes charging, the feedback recording unit collects the user's feedback data and records the user's satisfaction; The feedback score F is defined by using to represent the user satisfaction; The user's satisfaction F is obtained by the following formula: F ; In the formula, Represent the weights of charging time, charging amount and charging location respectively, R L represents the user's satisfaction rating for the charging location, Indicates the optimal charging time T C The difference between the actual charging time and Indicates the optimal charge capacity Q C The difference between the actual charge and max Indicates the peak value of charging time, Q max Indicates the peak value of the charge level.

[0033] The reinforcement learning optimization unit learns according to the feedback data by using the Q-learning algorithm and gradually adjusts the weight allocation strategy; Using the Q-learning algorithm, define The value of performing action a in state s is to increase the user's satisfaction F; The formula of the Q-learning algorithm is: ; In the formula, s represents the current user charging demand and historical behavior, a represents the charging solution recommended by the system, represents the learning rate, represents the discount factor, Indicates the next state after executing action a.

[0034] The system monitoring and maintenance module includes a real-time monitoring unit and a maintenance optimization unit; The real-time monitoring unit is responsible for real-time monitoring of parameters during the charging process, including current, voltage, charging power, charging speed and temperature changes; When the charging power and charging speed fluctuate abnormally within a period of time, the alarm mechanism is triggered and the abnormal information is sent to the user.

[0035] The maintenance optimization unit responds according to the abnormal situation detected by the real-time monitoring unit, including adjusting the charging power, suspending charging, and switching the charging mode.

[0036] In this embodiment, the optimal charging time T is obtained by using a constraint optimization algorithm by the solution optimization unit. C and charging location D LOC Adjustments are made to ensure that the charging plan is more in line with the user's current needs and acceptance range. This constrained optimization can dynamically balance user expectations and actual conditions to ensure the efficiency and flexibility of the charging process. Through the user feedback and learning module, the system collects user feedback data after each charging is completed, and uses the satisfaction score F to quantitatively evaluate the user's charging experience. The system not only records user feedback on charging time, charging amount and charging location, but also gradually adjusts the system's weight distribution strategy through the Q-learning algorithm in reinforcement learning.

[0037] The system monitoring and maintenance module monitors key parameters of the charging process, including current, voltage, charging power, charging speed, and temperature changes, through a real-time monitoring unit, and can detect anomalies in the charging process and issue early warnings. For example, when the charging power or speed fluctuates abnormally, the system will automatically trigger the alarm mechanism and notify the user to ensure the safety of the charging process. In addition, based on the abnormal detection results of the real-time monitoring unit, the maintenance optimization unit automatically executes corresponding response measures, including adjusting the charging power, suspending charging, or switching charging modes, which greatly improves the safety and stability of the system and avoids potential charging failures and risks.

[0038] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An electric vehicle charging intelligent management system based on multi-source data analysis, characterized by: It includes data acquisition module, data preprocessing module, feature extraction and weight distribution module, personalized charging plan generation module, user feedback and learning module and system monitoring and maintenance module; The data acquisition module collects multi-source data in real time through sensors and vehicle-mounted equipment, including the user's historical charging data H C , driving behavior data D b , Geographic location information G P and seasonal factor T S , forming the original data set W X ; The data preprocessing module processes the original data set W X Perform cleaning, denoising and normalization to obtain a multi-source data set W; The feature extraction and weight allocation module extracts features including charging time T, charging amount Q and charging station selection D from the multi-source data set W by using PCA feature extraction technology; The personalized charging plan generation module generates a charging plan based on the output of the weighted recommendation model and the user's charging needs, including the optimal charging time T C , optimal charging capacity Q C and the best charging location D LOC ; The user feedback and learning module records the user's feedback on the charging solution and adjusts the weight allocation strategy; The system monitoring and maintenance module monitors the status of the car during charging in real time, detects anomalies and faults, and performs regular evaluations.

2. The electric vehicle charging intelligent management system based on multi-source data analysis according to claim 1 is characterized by: The data acquisition module includes a sensor data acquisition unit and a data integration and storage unit; The sensor data acquisition unit collects historical charging data H C , driving behavior data D b , Geographic location information G P and seasonal factor T S Collect historical charging data H C The driving behavior data D is extracted and composed by performing fixed-cycle extraction on the interaction records of the charging pile communication equipment. b The geographic location information G is collected by the vehicle ECU P The seasonal factor T is collected through the vehicle's GPS module. S Obtained through time and date information in the system; Among them, the historical charging data H C Including charging time T, charging amount Q, charging power P C and charging station selection D; driving behavior data D b Including average speed, driving time and driving pattern; The data integration and storage unit processes the historical charging data H collected by the sensor data collection unit. C , driving behavior data D b , Geographic location information G P and seasonal factor T S Perform preliminary integration to form the original data set W X .

3. The electric vehicle charging intelligent management system based on multi-source data analysis according to claim 1 is characterized by: The data preprocessing module includes a data cleaning and denoising unit and a data normalization unit; The data cleaning and denoising unit processes the original data set W X Perform cleaning and denoising, where cleaning includes missing value processing and denoising includes using a smoothing filter to remove noise; Missing value processing for the original data set W X Perform missing filling processing to obtain the original filled data set W Xf , and then fill the original data set W Xf Use a smoothing filter to perform denoising and obtain the original denoised data set W XS ; The data normalization unit normalizes the original denoised data set W XS Perform normalization processing to obtain the multi-source data set W.

4. The electric vehicle charging intelligent management system based on multi-source data analysis according to claim 1 is characterized by: The feature extraction and weight allocation module includes a feature extraction unit and a weight allocation unit; The feature extraction unit extracts historical charging data H from the multi-source data set W C , by using PCA to analyze the historical charging data H in the multi-source dataset W C Extract and obtain the features of user charging time T, charging amount Q and charging station selection D to form multidimensional feature Z , and perform feature matrix conversion to obtain the feature matrix HZ: The characteristic matrix HZ is transformed by the following transformation formula: ； Where P represents the transformation matrix of PCA; The characteristic matrix HZ is linearly combined to obtain the weighted characteristic matrix HZ: HZ ; In the formula, Respectively represent the preset weight values ​​of charging time T, charging amount Q and charging station selection D, and the preset weight value of charging time T , the preset weight value of the charge amount Q and the preset weight value of charging station selection D , forming a weight value group .

5. The electric vehicle charging intelligent management system based on multi-source data analysis according to claim 4 is characterized by: The personalized charging scheme generation module includes a scheme generation unit and a scheme optimization unit; The solution generation unit obtains the weighted feature matrix HZ and weight group after weighting processing according to the feature extraction and weight distribution module. , for different regions, calculate the comprehensive score S of each region and obtain the optimal charging time T C , optimal charging capacity Q C and the best charging location D LOC ; The comprehensive score S is obtained by the following formula: S ； In the formula, represents the i-th eigenvalue of the j-th region, and Parameters representing the nonlinear contribution of the feature, represents the squared influence of the description feature, Represents the logarithmic change of the feature; According to the comprehensive score S, get the time period with the highest score , the highest scoring charging capacity and the highest scoring charging locations : ， ， ； In the formula, They represent the score of charging time, the score of charging amount and the score of charging location respectively; Based on the time period with the highest score Get the best charging time T C ; The optimal charging time T C Obtained by the following formula: T C ； In the formula, Pr represents the remaining power of the car, Ce represents the charging efficiency, Indicates the effect of season on charging efficiency; Based on the highest score charge Get the best charging amount Q C ; Q C ； In the formula, Indicates the total capacity of the vehicle battery, soc indicates the percentage of remaining power, ranging from 0 to 1. Indicates the reserved power required for future driving; Based on the highest scoring charging locations Get the best charging location LOC ; The best charging location D LOC Obtained by the following formula: D LOC ； Where D LOC Indicates the best charging location, specifically the recommended charging station, Indicates the distance between the user's location and the charging station. represents the load factor of the charging station, represents the adjustment factor, Represents the minimum function.

6. The electric vehicle charging intelligent management system based on multi-source data analysis according to claim 5 is characterized by: The scheme optimization unit adjusts the scheme according to the current needs of the user, external conditions and the current battery status of the vehicle. The scheme optimization unit uses a constraint optimization algorithm to optimize the optimal charging time T. C and the best charging location D LOC Make adjustments; The constraint formula is: Optimal charging time T C ; Best charging location D LOC ; In the formula, Indicates the charging time range accepted by the user. Indicates the charging location accepted by the user.

7. The electric vehicle charging intelligent management system based on multi-source data analysis according to claim 1 is characterized by: The user feedback and learning module includes a feedback recording unit and a reinforcement learning optimization unit; After the user completes charging, the feedback recording unit collects the user's feedback data and records the user's satisfaction; The feedback score F is defined by using to represent the user satisfaction; The user's satisfaction F is obtained by the following formula: F ； In the formula, Represent the weights of charging time, charging amount and charging location respectively, R L represents the user's satisfaction rating for the charging location, Indicates the optimal charging time T C The difference between the actual charging time and Indicates the optimal charge capacity Q C The difference between the actual charge and max Indicates the peak value of charging time, Q max Indicates the peak value of the charge level.

8. The electric vehicle charging intelligent management system based on multi-source data analysis according to claim 7 is characterized by: The reinforcement learning optimization unit learns according to the feedback data by using the Q-learning algorithm and gradually adjusts the weight allocation strategy; Using the Q-learning algorithm, define The value of performing action a in state s is to increase the user's satisfaction F; The formula of the Q-learning algorithm is: ； In the formula, s represents the current user charging demand and historical behavior, a represents the charging solution recommended by the system, represents the learning rate, represents the discount factor, Indicates the next state after executing action a.

9. The electric vehicle charging intelligent management system based on multi-source data analysis according to claim 1 is characterized by: The system monitoring and maintenance module includes a real-time monitoring unit and a maintenance optimization unit; The real-time monitoring unit is responsible for real-time monitoring of parameters during the charging process, including current, voltage, charging power, charging speed and temperature changes; When the charging power and charging speed fluctuate abnormally within a period of time, the alarm mechanism is triggered and the abnormal information is sent to the user.

10. The electric vehicle charging intelligent management system based on multi-source data analysis according to claim 9 is characterized in that: The maintenance optimization unit responds according to the abnormal situation detected by the real-time monitoring unit, including adjusting the charging power, suspending charging, and switching the charging mode.

Images