Automobile charging efficiency optimization method and system based on AI algorithm

Abstract

The invention relates to the technical field of automobile charging, and discloses an automobile charging efficiency optimization method and system based on an AI algorithm, and the method comprises the steps: analyzing a vehicle travel rule and a vehicle charging demand of a target vehicle, collecting battery energy efficiency information corresponding to the target vehicle, and planning a charging time slot sequence of the target vehicle at a charging station; calculating charging idle probabilities of the charging piles in different time slots, calculating a charging pile utilization rate corresponding to each charging pile in the charging station, and setting a charging guide strategy corresponding to the charging station; calculating a capacity utilization index of the target vehicle in the charging process, and planning a charging efficiency optimization path of the target vehicle in the charging station through a preset AI optimization algorithm; querying battery operation and maintenance information corresponding to the target vehicle, and calculating a battery energy attenuation rate of the target vehicle; and formulating a charging efficiency optimization strategy of the target vehicle in the charging station, and executing charging processing on the target vehicle to obtain a charging result. According to the invention, the automobile charging efficiency optimization effect can be improved.

Description

Technical Field

[0001] The present invention relates to an automobile charging efficiency optimization method and system based on an AI algorithm, and belongs to the technical field of automobile charging. Background Art

[0002] With the vigorous development of the global automobile industry and the rapid rise of the new energy vehicle market, the number of electric vehicles has increased significantly year by year, which has led to an increasing demand for car charging, thus putting higher requirements on car charging efficiency.

[0003] In the current field of automobile charging, traditional charging management methods mainly rely on pre-set fixed charging strategies and simple control systems. Usually, unified charging power, charging time and other parameters are set according to the basic parameters of the charging pile and the approximate specifications of the vehicle battery. The charging pile control system then performs charging operations according to these fixed settings. For example, most charging piles simply charge according to the capacity and nominal voltage of the battery, using a fixed current and voltage mode, without fully considering factors such as the actual use of the vehicle, the real-time status of the battery, and the overall operating status of the charging station. Although this traditional charging method can achieve basic charging functions, it has many disadvantages. Due to the lack of accurate analysis of the vehicle's real-time driving data, the health of the battery, and the charging needs, the optimization effect of the vehicle's charging efficiency is reduced. Summary of the invention

[0004] The present invention provides an automobile charging efficiency optimization method and system based on an AI algorithm, the main purpose of which is to improve the optimization effect of automobile charging efficiency.

[0005] To achieve the above purpose, the present invention provides a method for optimizing automobile charging efficiency based on an AI algorithm, comprising: Acquire a target vehicle to be analyzed and its corresponding charging station, collect vehicle access information corresponding to the target vehicle, analyze the vehicle travel pattern and vehicle charging demand of the target vehicle based on the vehicle access information, collect battery energy efficiency information corresponding to the target vehicle, and plan the charging time slot sequence of the target vehicle at the charging station in combination with the vehicle travel pattern, the vehicle charging demand and the battery energy efficiency information; Collect historical charging data and real-time operating conditions of each charging pile in the charging station, calculate the charging idle probability of the charging pile in different time slots based on the real-time operating conditions, calculate the charging pile utilization rate corresponding to each charging pile in the charging station based on the historical charging data, and set the charging guidance strategy corresponding to the charging station in combination with the charging idle probability and the charging pile utilization rate; Record the charging and discharging data set corresponding to the target vehicle, calculate the capacity utilization index of the target vehicle during the charging process based on the charging and discharging data set, and plan the charging efficiency optimization path of the target vehicle at the charging station by combining the capacity utilization index and the charging guidance strategy through a preset AI optimization algorithm; Querying the battery operation and maintenance information corresponding to the target vehicle, and calculating the battery energy attenuation rate of the target vehicle based on the battery operation and maintenance information; In combination with the battery energy decay rate, the charging efficiency optimization path and the charging time slot sequence, a charging efficiency optimization strategy for the target vehicle in the charging station is formulated, and based on the charging efficiency optimization strategy, the charging process for the target vehicle is executed to obtain a charging result.

[0006] Optionally, planning a charging time slot sequence of the target vehicle at the charging station in combination with the vehicle travel pattern, the vehicle charging demand and the battery energy efficiency information includes: Perform feature mining and analysis on the vehicle travel patterns to obtain key travel features; Based on the vehicle charging demand, determining the charging power and expected charging cycle corresponding to the target vehicle; Analyzing the optimal charging interval of the battery of the target vehicle based on the battery energy efficiency information; In combination with the key travel characteristics, the charging power, the expected charging cycle and the optimal battery charging interval, a charging time slot sequence of the target vehicle at the charging station is planned.

[0007] Optionally, the feature mining and analysis of the vehicle travel pattern to obtain key travel features includes: Extracting information on the vehicle travel pattern to obtain travel pattern information; Calculating information entropy corresponding to the travel pattern information, and filtering out key travel pattern information in the travel pattern information based on the information entropy; Extracting features from the key travel pattern information to obtain initial travel features; The feature importance corresponding to the initial travel feature is calculated by the following formula: Among them, A represents the feature importance corresponding to the initial travel feature, represents the feature vector corresponding to the ath feature in the initial travel features, represents the feature vector corresponding to the a+1th feature in the initial travel feature, a and a+1 represent the feature sequence numbers corresponding to the initial travel feature, and t represents the number corresponding to the initial travel feature; Based on the feature importance, feature filtering is performed on the initial travel features to obtain key travel features.

[0008] Optionally, the calculating, based on the real-time operating condition, the charging idle probability of the charging pile in different time slots includes: Performing data integration processing on the real-time operating conditions to obtain a real-time operating condition data set; Performing data correction processing on the real-time operating condition data set to obtain a target operating condition data set; Dividing the target working condition data set into time slots to obtain time slot idle data; Based on the time slot idle data, determine the charging time slot length and the number of time slots corresponding to the charging pile; Combining the duration of the charging time slot and the number of time slots, the charging idle probability of the charging pile in different time slots is calculated by the following formula: Where D represents the probability of charging piles being idle at different time slots. represents the duration of the bth time slot in the charging time slot, It represents the status identifier of the bth time slot in the charging time slot duration, b represents the sequence number corresponding to the charging time slot duration, and q represents the number of charging time slot durations.

[0009] Optionally, the calculating, based on the historical charging data, the charging pile utilization rate corresponding to each charging pile in the charging station includes: Cleaning the historical charging data to obtain cleaned charging data; Performing charging record statistics on the cleaning charging data to obtain a charging record set; Performing time period statistics on the charging record set to obtain the effective charging time period; The theoretical available time corresponding to each charging pile in the charging station is queried, and the charging pile utilization rate corresponding to each charging pile in the charging station is calculated by combining the theoretical available time and the effective charging period.

[0010] Optionally, the calculating, based on the charging and discharging energy data set, a capacity utilization index of the target vehicle during the charging process includes: Extracting a charging subset from the charging and discharging energy data set, and sorting the charging subset to obtain an ordered charging subset; Identify a full charge capacity extreme value in the ordered charging subset, and calculate a single charge extreme capacity corresponding to the target vehicle based on the full charge capacity extreme value; The theoretical battery capacity of the target vehicle is queried, and the capacity utilization index of the target vehicle during the charging process is calculated by combining the single charging extreme capacity and the theoretical battery capacity through the following formula: Where G represents the capacity utilization index of the target vehicle during the charging process, It represents the maximum capacity of a single charge, and H represents the theoretical battery capacity.

[0011] Optionally, combining the capacity utilization index and the charging guidance strategy to plan a charging efficiency optimization path for the target vehicle at the charging station through a preset AI optimization algorithm includes: According to the capacity utilization index, the battery of the target vehicle is graded to obtain battery grade information; Querying the status record information corresponding to each charging pile in the charging station, and eliminating the charging piles in the charging station in combination with the battery level information, the charging guidance strategy and the status record information to obtain candidate charging piles; Acquire traffic condition information of the candidate charging pile, and evaluate the traffic congestion degree corresponding to the candidate charging pile according to the traffic condition information; Performing coordinate positioning on the target vehicle and the candidate charging pile respectively to obtain vehicle coordinate positioning and charging pile positioning; Combining the vehicle coordinate positioning and the charging pile positioning, calculating the charging range between the target vehicle and the candidate charging pile; Combining the charging trip and the traffic congestion degree, calculating the charging efficiency score of the candidate charging pile using the AI ​​optimization algorithm; The charging efficiency optimization path of the target vehicle at the charging station is planned by combining the charging efficiency score, the vehicle coordinate positioning and the charging pile positioning.

[0012] Optionally, evaluating the traffic congestion degree corresponding to the candidate charging pile according to the traffic condition information includes: Based on the traffic condition information, calculate the road traffic flow and road speed corresponding to the candidate charging pile; Querying the road criteria corresponding to each traffic road in the traffic condition information, and determining the road traffic flow threshold and road speed extreme value corresponding to each traffic road in the candidate charging pile based on the road criteria; In combination with the road traffic volume, the road speed, the road traffic volume threshold and the road speed extreme value, the congestion index corresponding to the candidate charging pile is calculated by the following formula: Among them, L represents the congestion index corresponding to the candidate charging pile, represents the road traffic volume of the e-th traffic road among the candidate charging piles, represents the road traffic flow threshold of the e-th traffic road among the candidate charging piles, represents the road speed of the e-th traffic road among the candidate charging piles, represents the road speed extreme value of the e-th traffic road among the candidate charging piles, e represents the traffic road sequence number of the candidate charging pile, and r represents the number of traffic roads of the candidate charging piles; The traffic congestion degree corresponding to the candidate charging pile is evaluated according to the congestion index.

[0013] Optionally, the calculating the battery energy decay rate of the target vehicle based on the battery operation and maintenance information includes: Extracting key operation and maintenance information and its corresponding operation and maintenance indicators from the battery operation and maintenance information; Based on the key operation and maintenance information, calculating the indicator capacity degradation factor corresponding to the operation and maintenance indicator; Analyzing the relevance of the operation and maintenance indicator to the battery of the target vehicle, and allocating an indicator relevance weight corresponding to the operation and maintenance indicator based on the battery relevance; The battery energy decay rate of the target vehicle is calculated by combining the indicator capacity degradation factor and the indicator associated weight.

[0014] In order to solve the above problems, the present invention also provides a vehicle charging efficiency optimization system based on an AI algorithm, the system comprising: A charging time slot sequence planning module is used to obtain a target vehicle to be analyzed and its corresponding charging station, collect vehicle access information corresponding to the target vehicle, analyze the vehicle travel pattern and vehicle charging demand of the target vehicle based on the vehicle access information, collect battery energy efficiency information corresponding to the target vehicle, and plan the charging time slot sequence of the target vehicle at the charging station in combination with the vehicle travel pattern, the vehicle charging demand and the battery energy efficiency information; A charging guidance strategy setting module, used to collect historical charging data and real-time operating conditions of each charging pile in the charging station, calculate the charging idle probability of the charging pile in different time slots based on the real-time operating conditions, calculate the charging pile utilization rate corresponding to each charging pile in the charging station based on the historical charging data, and set the charging guidance strategy corresponding to the charging station in combination with the charging idle probability and the charging pile utilization rate; A charging efficiency optimization path planning module is used to record the charging and discharging data set corresponding to the target vehicle, calculate the capacity utilization index of the target vehicle during the charging process based on the charging and discharging data set, and plan the charging efficiency optimization path of the target vehicle at the charging station through a preset AI optimization algorithm in combination with the capacity utilization index and the charging guidance strategy; A battery energy decay rate calculation module, used to query the battery operation and maintenance information corresponding to the target vehicle, and calculate the battery energy decay rate of the target vehicle based on the battery operation and maintenance information; The charging management module is used to formulate a charging efficiency optimization strategy for the target vehicle in the charging station based on the battery energy decay rate, the charging efficiency optimization path and the charging time slot sequence, and execute charging processing for the target vehicle based on the charging efficiency optimization strategy to obtain a charging result.

[0015] Compared with the problems described in the background technology, the present invention plans the charging time slot sequence of the target vehicle at the charging station by combining the vehicle travel pattern, the vehicle charging demand and the battery energy efficiency information, thereby improving the operating efficiency of the charging station and the charging convenience of the vehicle. Furthermore, the present invention collects the historical charging data and the real-time operating conditions of each charging pile to fully understand the operating status of the charging station, and calculates the charging idle probability of the charging pile in different time slots based on the real-time operating conditions. The charging idle probability can be used to understand the availability and idle possibility of the charging pile in different time slots, so as to plan the vehicle charging arrangement in advance and improve the rationality of charging resource allocation. Furthermore, the present invention calculates the capacity utilization index of the target vehicle during the charging process based on the charging and discharging energy data set. , can accurately understand the charging efficiency of the vehicle battery, and provide a key basis for the subsequent optimization path of the charging efficiency of the target vehicle at the charging station. Furthermore, the present invention calculates the battery energy decay rate of the target vehicle based on the battery operation and maintenance information, and can understand the degree of decline in the energy release capacity of the battery of the target vehicle during use, thereby providing a basis for the formulation of the subsequent charging efficiency optimization strategy of the target vehicle in the charging station. The present invention formulates the charging efficiency optimization strategy corresponding to the target vehicle by combining the battery energy decay rate, the charging efficiency optimization path and the charging time slot sequence. The comprehensive multi-dimensional information can greatly improve the accuracy and adaptability of the strategy, and based on the charging efficiency optimization strategy, the charging process of the target vehicle is executed, thereby improving the optimization effect of the vehicle charging efficiency. Therefore, the vehicle charging efficiency optimization method and system based on the AI ​​algorithm provided in the embodiment of the present invention can improve the optimization effect of the vehicle charging efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1A schematic diagram of a flow chart of a method for optimizing vehicle charging efficiency based on an AI algorithm provided in one embodiment of the present invention; Figure 2 A schematic diagram of a module for implementing the method for optimizing automobile charging efficiency based on an AI algorithm provided in one embodiment of the present invention.

[0017] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings in conjunction with the embodiments. DETAILED DESCRIPTION

[0018] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0019] The embodiment of the present application provides a method for optimizing automobile charging efficiency based on an AI algorithm. The execution subject of the method for optimizing automobile charging efficiency based on an AI algorithm includes but is not limited to at least one of the electronic devices such as a server and a terminal that can be configured to execute the method provided in the embodiment of the present application. In other words, the method for optimizing automobile charging efficiency based on an AI algorithm can be executed by software or hardware installed on a terminal device or a server device. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc.

[0020] Embodiment 1: Reference Figure 1 FIG. 1 is a flow chart of a method for optimizing vehicle charging efficiency based on an AI algorithm according to an embodiment of the present invention. In this embodiment, the method for optimizing vehicle charging efficiency based on an AI algorithm includes: S1. Acquire a target vehicle to be analyzed and its corresponding charging station, collect vehicle access information corresponding to the target vehicle, analyze the vehicle travel pattern and vehicle charging demand of the target vehicle based on the vehicle access information, collect battery energy efficiency information corresponding to the target vehicle, and plan a charging time slot sequence for the target vehicle at the charging station in combination with the vehicle travel pattern, the vehicle charging demand and the battery energy efficiency information.

[0021] The present invention plans the charging time slot sequence of the target vehicle at the charging station by combining the vehicle travel pattern, the vehicle charging demand and the battery energy efficiency information, thereby improving the operation efficiency of the charging station and the charging convenience of the vehicle, wherein the vehicle access information covers the vehicle's arrival time, expected stay time, vehicle type and the like; the vehicle travel pattern includes the vehicle's daily driving route, usage frequency, common parking location and the like, such as whether the vehicle travels at a fixed time period every day, or whether it has different driving modes on weekdays and weekends; the vehicle charging demand can be determined based on factors such as the vehicle's battery capacity, remaining power, and the expected charging time set by the user; the battery energy efficiency information includes the battery's energy efficiency performance under different charging states, the battery's health status (such as the degree of battery aging reflected by the internal resistance), etc., which can be obtained through the on-board battery management system (BMS) and the communication interface with the vehicle.

[0022] In detail, the planning of the charging time slot sequence of the target vehicle at the charging station in combination with the vehicle travel pattern, the vehicle charging demand and the battery energy efficiency information includes: Perform feature mining and analysis on the vehicle travel patterns to obtain key travel features; Based on the vehicle charging demand, determining the charging power and expected charging cycle corresponding to the target vehicle; Analyzing the optimal charging interval of the battery of the target vehicle based on the battery energy efficiency information; In combination with the key travel characteristics, the charging power, the expected charging cycle and the optimal battery charging interval, a charging time slot sequence of the target vehicle at the charging station is planned.

[0023] Among them, the key travel characteristics are key information that can reflect the vehicle travel habits and patterns, such as high-frequency travel periods, long-term parking periods, etc., which are extracted after feature mining and analysis of the vehicle travel patterns. The charging power is the power value that needs to be replenished according to the remaining battery power, capacity and user usage needs of the target vehicle. The expected charging cycle is the time range expected to complete charging based on the comprehensive user itinerary, daily usage habits, etc. of the target vehicle. The optimal battery charging range is the power range of the target vehicle with high energy conversion efficiency and conducive to healthy battery charging, which is obtained based on the analysis of battery energy efficiency information.

[0024] Further, based on the vehicle charging demand, the charging power and expected charging cycle corresponding to the target vehicle are determined by using a power demand calculation model and a time estimation method. Based on the vehicle charging demand, for example, when the remaining battery power of the vehicle is 30%, the total battery capacity is 60 kWh, and the power consumption corresponding to the estimated mileage of the user in the next day is about 40 kWh, the charging power corresponding to the target vehicle is determined to be 10 kWh through a power demand calculation model (such as a simple power balance formula: required charging power = expected power consumption - remaining power); at the same time, based on the user's daily travel habits, the vehicle is usually parked between 7 pm and 10 pm and the user expects to complete charging within this time period, and the expected charging cycle is determined to be 3 hours using a time estimation method (such as a time statistical model based on historical travel data); based on the battery energy efficiency information, the optimal charging interval of the battery of the target vehicle is analyzed with the help of a battery performance analysis tool and an energy efficiency monitoring data processing method, such as based on the battery energy efficiency information, such as the energy conversion efficiency data of the battery at different charging power and power levels recorded by the on-board battery management system, with the help of a battery performance analysis tool (such as a professional battery data analysis software The target vehicle has the highest battery energy conversion efficiency when the battery power is between 40% and 80% and the charging power is about 10 kilowatts, thereby determining this interval as the optimal battery charging interval; combining the key travel characteristics, the charging power, the expected charging cycle and the optimal battery charging interval, the charging time slot sequence of the target vehicle at the charging station is planned through an intelligent optimization scheduling algorithm and a dynamic time slot allocation strategy, such as combining the key travel characteristics (such as the vehicle is from 9 a.m. to 6 p.m. every weekday) travel, and park in a parking lot near the charging station for the rest of the time), the charging power, the expected charging cycle and the optimal charging range of the battery, and plan the charging time slot sequence of the target vehicle at the charging station through an intelligent optimization scheduling algorithm (such as a charging pile allocation strategy based on a greedy algorithm) and a dynamic time slot allocation strategy (such as dynamically adjusting the charging time slot according to the real-time idleness of the charging pile and the arrival time of the vehicle), for example, arranging the vehicle to charge at an idle charging pile that is suitable for the optimal charging range of the battery from 6:30 pm to 9:30 pm, so as to meet the charging needs of the vehicle and ensure charging efficiency and convenience.

[0025] Further, as an optional embodiment of the present invention, the feature mining analysis of the vehicle travel pattern to obtain key travel features includes: Extracting information on the vehicle travel pattern to obtain travel pattern information; Calculating information entropy corresponding to the travel pattern information, and filtering out key travel pattern information in the travel pattern information based on the information entropy; Extracting features from the key travel pattern information to obtain initial travel features; The feature importance corresponding to the initial travel feature is calculated by the following formula: Among them, A represents the feature importance corresponding to the initial travel feature, represents the feature vector corresponding to the ath feature in the initial travel features, represents the feature vector corresponding to the a+1th feature in the initial travel feature, a and a+1 represent the feature sequence numbers corresponding to the initial travel feature, and t represents the number corresponding to the initial travel feature; Based on the feature importance, feature filtering is performed on the initial travel features to obtain key travel features.

[0026] Among them, the travel pattern information is the regular content presented by vehicle travel, the information entropy is an indicator corresponding to the travel pattern information for measuring its uncertainty and other conditions, the key travel pattern information is the more important and critical part of the travel pattern information, the initial travel features are the relevant features extracted from the key travel pattern information, and the feature importance indicates the importance of the initial travel features.

[0027] Furthermore, the vehicle travel pattern information can be extracted through an identification method to obtain travel pattern information, such as an OCR recognition method; the information entropy corresponding to the travel pattern information can be calculated through the Shannon entropy algorithm; when the information entropy is greater than a preset entropy value, the key travel pattern information in the travel pattern information is screened out, and the preset entropy value can be set to 0.8, or it can be set according to the actual application scenario; the key travel pattern information can be feature extracted through the principal component analysis method to obtain initial travel features; based on the feature importance, a threshold-based screening strategy is used, for example, the initial travel features with a feature importance lower than 0.6 are discarded, and the initial travel features are feature filtered to obtain key travel features.

[0028] S2. Collect historical charging data and real-time operating conditions of each charging pile in the charging station, calculate the charging idle probability of the charging pile in different time slots based on the real-time operating conditions, calculate the charging pile utilization rate corresponding to each charging pile in the charging station based on the historical charging data, and set the charging guidance strategy corresponding to the charging station in combination with the charging idle probability and the charging pile utilization rate.

[0029] By collecting the historical charging data and the real-time operating conditions of each charging pile, the present invention can fully understand the operating status of the charging station, and calculate the charging idle probability of the charging pile in different time slots based on the real-time operating conditions. The charging idle probability can be used to understand the availability and idle possibility of the charging pile in different time slots, so as to plan vehicle charging arrangements in advance and improve the rationality of charging resource allocation.

[0030] Among them, the historical charging data covers detailed records of the start time, end time, charging power, charging current, voltage, etc. of each charging of the charging pile in a certain period in the past. The real-time operating conditions include real-time information such as the current connection status of each charging pile (idle, occupied, faulty, etc.), the remaining charging time estimate of the charging vehicle being charged, and the real-time output power of the charging pile. The charging idle probability refers to the possibility that the charging pile is idle and available for use within a specific time slot. The charging pile utilization rate reflects the proportion of the time that the charging pile is actually occupied for charging in a historical period of time to the total available time.

[0031] Specifically, the calculating the charging idle probability of the charging pile in different time slots based on the real-time operating condition includes: Performing data integration processing on the real-time operating conditions to obtain a real-time operating condition data set; Performing data correction processing on the real-time operating condition data set to obtain a target operating condition data set; Dividing the target working condition data set into time slots to obtain time slot idle data; Based on the time slot idle data, determine the charging time slot length and the number of time slots corresponding to the charging pile; Combining the duration of the charging time slot and the number of time slots, the charging idle probability of the charging pile in different time slots is calculated by the following formula: Where D represents the probability of charging piles being idle at different time slots. represents the duration of the bth time slot in the charging time slot, It represents the status identifier of the bth time slot in the charging time slot duration, b represents the sequence number corresponding to the charging time slot duration, and q represents the number of charging time slot durations.

[0032] Among them, the real-time operating condition data set is a data set formed by integrating various information in the real-time operating condition, such as the connection status of the charging pile, the estimated remaining charging time of the charging vehicle, the real-time output power of the charging pile, etc. The time slot idle data is data about the idle status of each time slot extracted from the target operating condition data set (that is, the relevant data for analysis after the real-time operating condition data set is divided according to rules). The charging time slot duration and the number of time slots are related indicators corresponding to the charging pile for measuring the time scale and the number of divisions that can be allocated for use in different time intervals. The state identifier is the identification information used to characterize the charging pile as being idle or occupied during the corresponding period of the charging time slot duration.

[0033] Furthermore, by building a data middle platform, the real-time operating condition data from different sensors, smart meters and charging pile control systems can be extracted, converted and loaded using ETL (Extract, Transform, Load) tools to complete data integration and obtain a real-time condition data set; the real-time condition data set can be corrected by combining a rule-based outlier detection algorithm with manual review to remove erroneous data and repair outliers to obtain a target condition data set; the target condition data set can be divided into time slots in units of half an hour or one hour or other fixed time periods according to business needs by using a scheduled task script with a preset fixed duration to obtain time slot idle data; based on the time slot idle data, the time slot statistical analysis algorithm is used in combination with the configuration parameters of the charging pile to determine the charging time slot duration and the number of time slots corresponding to the charging pile, such as comprehensively judging the appropriate charging time slot duration for each charging pile based on factors such as the maximum continuous working time of the charging pile and the charging efficiency change node, and determining the number of time slots based on the operating time of the charging station and the time slot division granularity; when the state identifier of the bth time slot in the charging time slot duration is in an idle state, =1; when the status flag of the bth time slot in the charging time slot duration is in the charging state, =0.

[0034] The present invention calculates the charging pile utilization rate corresponding to each charging pile in the charging station based on the historical charging data. The charging pile utilization rate can be used to understand the proportion of time that the charging piles have been occupied in the past, and the busyness of each charging pile can be clearly known, thereby improving the accuracy of setting the subsequent charging guidance strategy corresponding to the charging station. The charging pile utilization rate refers to the percentage of the time that each charging pile in the charging station is actually used to charge the vehicle within a certain historical time period, which accounts for the total time that the charging pile can theoretically provide charging services, and is used to measure the frequency of use of the charging pile.

[0035] Specifically, the calculating the charging pile utilization rate corresponding to each charging pile in the charging station based on the historical charging data includes: Cleaning the historical charging data to obtain cleaned charging data; Performing charging record statistics on the cleaning charging data to obtain a charging record set; Performing time period statistics on the charging record set to obtain the effective charging time period; The theoretical available time corresponding to each charging pile in the charging station is queried, and the charging pile utilization rate corresponding to each charging pile in the charging station is calculated by combining the theoretical available time and the effective charging period.

[0036] Among them, the cleaning charging data is the pure data obtained after removing abnormal data caused by equipment failure, data transmission errors and other factors from the historical charging data; the charging record set is a complete charging record set corresponding to each charging pile formed after the cleaning charging data is classified and summarized according to the charging pile identification and the relevant charging information is integrated; the effective charging period duration is the actual duration used for charging in each interval determined after the charging record set is divided into time intervals and statistics; the theoretical available duration is the duration that can be used for charging services for each charging pile in the charging station under ideal conditions, taking into account factors such as its own configuration and operating time.

[0037] Furthermore, the historical charging data can be cleaned by a box plot method to obtain cleaned charging data; the charging record statistics of the cleaned charging data can be performed by a grouping aggregation algorithm based on the unique identification code of the charging pile, and the records of the same charging pile can be grouped together to obtain a charging record set; the charging record set can be statistically analyzed for time periods by setting a time window (such as dividing by day, week, or month) and using a time series analysis tool to accurately extract the start and end time of effective charging in each time period and calculate the duration to obtain the effective charging time period duration; the theoretical available time corresponding to each charging pile in the charging station can be queried by connecting to the database of the charging station management system and using structured query language (SQL); the ratio of the effective charging time period duration to the theoretical available time can be calculated to obtain the charging pile utilization rate corresponding to each charging pile in the charging station.

[0038] The present invention sets a charging guidance strategy corresponding to the charging station by combining the charging idle probability and the charging pile utilization rate, which can greatly improve the operating efficiency of the charging station, accurately allocate vehicles to idle charging piles according to the real-time idle probability, reduce user waiting time, and optimize user charging experience. Among them, the charging guidance strategy is an action guide corresponding to the charging station for guiding vehicles to charge in an orderly manner, giving full play to the efficiency of charging piles, and achieving multiple goals such as efficient operation of the charging station, user satisfaction, and reasonable allocation of resources. Furthermore, the charging guidance strategy corresponding to the charging station is set in combination with the charging idle probability and the charging pile utilization rate. For example, during the peak electricity consumption period on weekday evenings, the system monitoring found that the probability of idle charging of some charging piles was low and the utilization rate remained high for a long time. At this time, for the newly connected charging demand, the guidance strategy can guide the vehicle to the charging piles with high idle probability and low utilization rate, and give appropriate discounts to attract users, which can not only relieve the pressure of popular charging piles, but also increase the frequency of use of idle piles; for example, if a certain area is congested due to large-scale activities, even if there are idle charging piles, after combining the idle probability and utilization rate analysis, the guidance strategy can also suspend the recommendation of charging piles in the area to avoid aggravating traffic congestion and ensure the balance between charging station operation and smooth surrounding traffic.

[0039] S3. Record the charging and discharging data set corresponding to the target vehicle, calculate the capacity utilization index of the target vehicle during the charging process based on the charging and discharging data set, and plan the charging efficiency optimization path of the target vehicle at the charging station through a preset AI optimization algorithm in combination with the capacity utilization index and the charging guidance strategy.

[0040] The present invention calculates the capacity utilization index of the target vehicle during the charging process based on the charging and discharging energy data set, thereby accurately understanding the charging efficiency of the vehicle battery and providing a key basis for the subsequent charging efficiency optimization path of the target vehicle at the charging station. The charging and discharging energy data set is a data set of multi-dimensional energy-related information such as charging power, discharging power, charging time, and discharging time recorded by on-board monitoring equipment and interaction with external charging facilities during the charging and discharging process of the target vehicle. The capacity utilization index represents the battery utilization efficiency of the target vehicle during the charging process. Furthermore, the recording of the charging and discharging energy data set corresponding to the target vehicle can be achieved by high-precision on-board sensors on the vehicle.

[0041] In detail, the calculating the capacity utilization index of the target vehicle during the charging process based on the charging and discharging energy data set includes: Extracting a charging subset from the charging and discharging energy data set, and sorting the charging subset to obtain an ordered charging subset; Identify a full charge capacity extreme value in the ordered charging subset, and calculate a single charge extreme capacity corresponding to the target vehicle based on the full charge capacity extreme value; The theoretical battery capacity of the target vehicle is queried, and the capacity utilization index of the target vehicle during the charging process is calculated by combining the single charging extreme capacity and the theoretical battery capacity through the following formula: Where G represents the capacity utilization index of the target vehicle during the charging process, It represents the maximum capacity of a single charge, and H represents the theoretical battery capacity.

[0042] Among them, the charging subset is a subset formed by extracting and integrating all charging-related data separately after classification, screening and processing in the charging and discharging energy data set; the ordered charging subset is a set obtained by arranging and sorting the charging subsets in chronological order of charging time; the full charge capacity extreme value is the maximum power value that can be reached in multiple charging processes in the ordered charging subset; the single charging extreme capacity is the maximum power capacity that can be reached by the target vehicle in a single charging behavior; the theoretical battery capacity is the upper limit of the power capacity of the target vehicle under ideal conditions based on factors such as its battery design specifications.

[0043] Optionally, a charging subset in the charging and discharging energy data set can be extracted through an intelligent screening algorithm, which is compiled by a programming language. The charging subset can be sorted through a time series sorting algorithm (such as an improved quick sorting algorithm) to obtain an ordered charging subset; the full charge capacity extreme value in the ordered charging subset can be identified through a traversal comparison module with an extreme value search function, and based on the full charge capacity extreme value, the single charging extreme capacity corresponding to the target vehicle can be accurately calculated in combination with a battery health status assessment model and a charging condition correction coefficient, and the health status corresponding to the vehicle battery is calculated through the battery health status assessment model, and health status × charging condition correction coefficient × full charge capacity extreme value = single charging extreme capacity; the theoretical battery capacity of the target vehicle can be queried through real-time interaction with the vehicle manufacturer's cloud database.

[0044] The present invention plans the charging efficiency optimization path of the target vehicle at the charging station by combining the capacity utilization index and the charging guidance strategy through a preset AI optimization algorithm. On the one hand, it can accurately match the most suitable charging pile according to the capacity utilization of the vehicle battery. For example, when the capacity utilization index is low, it can guide the vehicle to a pile with a battery detection and repair function, thereby improving charging safety and battery life. On the other hand, combined with the charging guidance strategy, it can make full use of the charging station resources, allocate vehicles according to the idle probability, reduce the user waiting time, optimize the overall charging experience, and alleviate the surrounding traffic congestion to achieve efficient operation of the charging station. Among them, the preset AI optimization algorithm is based on artificial intelligence technologies such as machine learning and deep learning, comprehensively considering multiple factors such as the battery status of the target vehicle, the real-time idle probability of each charging pile at the charging station, the charging power, and the surrounding traffic conditions, and constructing a mathematical model and an intelligent decision-making mechanism to achieve the optimal path planning algorithm set; the charging efficiency optimization path is the best route planned by the target vehicle at the charging station by comprehensively considering the charging efficiency, battery health maintenance, and traffic convenience to achieve the shortest charging time, minimum battery loss, and the highest resource utilization rate.

[0045] In detail, the combining of the capacity utilization index and the charging guidance strategy and planning of the charging efficiency optimization path of the target vehicle at the charging station through a preset AI optimization algorithm include: According to the capacity utilization index, the battery of the target vehicle is graded to obtain battery grade information; Querying the status record information corresponding to each charging pile in the charging station, and eliminating the charging piles in the charging station in combination with the battery level information, the charging guidance strategy and the status record information to obtain candidate charging piles; Acquire traffic condition information of the candidate charging pile, and evaluate the traffic congestion degree corresponding to the candidate charging pile according to the traffic condition information; Performing coordinate positioning on the target vehicle and the candidate charging pile respectively to obtain vehicle coordinate positioning and charging pile positioning; Combining the vehicle coordinate positioning and the charging pile positioning, calculating the charging range between the target vehicle and the candidate charging pile; Combining the charging trip and the traffic congestion degree, calculating the charging efficiency score of the candidate charging pile using the AI ​​optimization algorithm; The charging efficiency optimization path of the target vehicle at the charging station is planned by combining the charging efficiency score, the vehicle coordinate positioning and the charging pile positioning.

[0046] Among them, the battery level information is the level of the battery of the target vehicle based on performance, capacity, health and other aspects; the status record information is the operating status record of each charging pile in the charging station, including usage time, number of failures, charging efficiency, etc.; the candidate charging pile is an individual charging pile in the charging station that can be selected as a charging pile for the target vehicle; the traffic road condition information is data related to traffic conditions such as real-time traffic flow, vehicle speed, road construction and accidents on the surrounding roads of the candidate charging pile; the traffic congestion degree is a quantitative indicator corresponding to the candidate charging pile that reflects the smoothness or congestion of the surrounding roads; the vehicle coordinate positioning and the charging pile positioning are respectively the coordinate information of the geographical locations of the target vehicle and the candidate charging pile; the charging trip is the driving route and distance between the target vehicle and the candidate charging pile; the charging efficiency score is a quantitative score of the candidate charging pile that measures the quality of its charging effect after comprehensively considering factors such as charging efficiency, stability, and compatibility.

[0047] Furthermore, according to the capacity utilization index, the battery of the target vehicle can be graded through the built-in intelligent grading algorithm module to obtain battery grade information. The algorithm module maps the capacity utilization index to different battery health grades based on a large amount of historical charging data and a battery performance attenuation model; a real-time connection can be established with the charging station management system database to query the status record information corresponding to each charging pile in the charging station, and the charging piles in the charging station can be eliminated by using a rule-based intelligent screening program in combination with the battery grade information, the charging guidance strategy and the status record information to obtain candidate charging piles. If the battery grade shows that the battery is in good health, If the battery condition is not good, the intelligent screening program will eliminate those charging piles with excessive charging power and may accelerate battery loss according to the battery maintenance rules in the charging guidance strategy. Secondly, referring to the status record information of the charging pile, the charging piles that are in failure, under maintenance, or the current load is too high, and the queuing time is estimated to be too long are also excluded. Only the charging piles that are adapted to the current status of the battery, idle and can provide charging services stably are left as candidate charging piles, ensuring that the subsequent charging of the vehicle is safe and efficient without long waiting; the traffic road condition information of the candidate charging piles can be collected collaboratively through the sensor network deployed on the surrounding roads and the traffic big data platform; the vehicle-mounted satellite positioning system can be used to communicate with the charging pile terminal The geographic information identification module respectively coordinates the target vehicle and the candidate charging pile to obtain the vehicle coordinate positioning and the charging pile positioning; in combination with the vehicle coordinate positioning and the charging pile positioning, the charging range from the target vehicle to the candidate charging pile can be calculated by the Euclidean distance algorithm; in combination with the charging range and the traffic congestion degree, the charging efficiency score of the candidate charging pile is calculated by using the AI ​​optimization algorithm, such as first estimating the additional power and time cost consumed by the vehicle on the way to each candidate charging pile based on the traffic congestion degree, for example, severely congested sections will greatly increase the time consumption and power loss, and then combined with the known charging range, the candidate charging piles are comprehensively considered. The AI ​​optimization algorithm allocates the preset weights for the charging pile's own charging power, idle probability, and whether it is compatible with the vehicle's battery type, and then weights and sums these factors to ultimately derive a charging efficiency score that accurately reflects the pros and cons of each candidate charging pile. The AI ​​optimization algorithm combines the charging efficiency score, the vehicle coordinate positioning, and the charging pile positioning to plan the charging efficiency optimization path for the target vehicle at the charging station, starting with the vehicle coordinate positioning and ending with the charging pile positioning of each candidate charging pile, to construct multiple potential charging paths, and selects the charging efficiency optimization path for the target vehicle at the charging station from the potential charging paths based on the numerical value of the charging efficiency score.

[0048] Further, as an optional embodiment of the present invention, the evaluating the traffic congestion degree corresponding to the candidate charging pile according to the traffic condition information includes: Based on the traffic condition information, calculate the road traffic flow and road speed corresponding to the candidate charging pile; Querying the road criteria corresponding to each traffic road in the traffic condition information, and determining the road traffic flow threshold and road speed extreme value corresponding to each traffic road in the candidate charging pile based on the road criteria; In combination with the road traffic volume, the road speed, the road traffic volume threshold and the road speed extreme value, the congestion index corresponding to the candidate charging pile is calculated by the following formula: Among them, L represents the congestion index corresponding to the candidate charging pile, represents the road traffic volume of the e-th traffic road among the candidate charging piles, represents the road traffic flow threshold of the e-th traffic road among the candidate charging piles, represents the road speed of the e-th traffic road among the candidate charging piles, represents the road speed extreme value of the e-th traffic road among the candidate charging piles, e represents the traffic road sequence number of the candidate charging pile, and r represents the number of traffic roads of the candidate charging piles; The traffic congestion degree corresponding to the candidate charging pile is evaluated according to the congestion index.

[0049] Among them, the road traffic flow and the road speed are relevant indicators corresponding to the candidate charging pile that reflect the traffic conditions of the traffic road where the candidate charging pile is located, the road criterion is the specification or judgment standard corresponding to each traffic road in the traffic condition information, the road traffic flow threshold and the road speed extreme value are the limited or critical reference values ​​corresponding to each traffic road in the candidate charging pile, and the congestion index is a quantitative value corresponding to the candidate charging pile that reflects the degree of congestion on the traffic road where the candidate charging pile is located.

[0050] Furthermore, based on the traffic condition information, the road traffic volume and road speed corresponding to the candidate charging pile are calculated, the number of vehicles passing through each monitoring point and the corresponding time interval are extracted from the traffic condition information, the number of vehicles passing through the monitoring point per unit time is accumulated, and the road traffic volume is calculated, and then, according to the start and end time and the driving distance of the vehicle on the road section recorded by the monitoring equipment, the average road speed is calculated using the formula of distance divided by time, so as to obtain the road traffic volume and road speed corresponding to the candidate charging pile; the road criteria corresponding to each traffic road in the traffic condition information can be queried through the website of the government traffic management department, and based on the traffic flow record information and speed record information in the road criteria, the road rules can be calculated. The information is used to determine the road traffic flow threshold and road speed extreme value corresponding to each traffic road in the candidate charging pile; the traffic congestion degree corresponding to the candidate charging pile is evaluated according to the value of the congestion index. For example, when the congestion index is in the range of 0-0.3, it indicates that vehicles on the road where the candidate charging pile is located are traveling smoothly, the traffic congestion degree is low, and the time taken by the car owner to charge is relatively short; if the congestion index is in the range of 0.3-0.7, it means that the road is congested to a certain extent, the traffic congestion degree is medium, and the car owner needs to reserve more time to go there to avoid delaying the charging journey; and when the congestion index exceeds 0.7, it means that the traffic congestion is serious, the traffic congestion degree is high, and the road to the candidate charging pile may be blocked for a long time.

[0051] S4. Query the battery operation and maintenance information corresponding to the target vehicle, and calculate the battery energy decay rate of the target vehicle based on the battery operation and maintenance information.

[0052] The present invention calculates the battery energy decay rate of the target vehicle based on the battery operation and maintenance information, so as to understand the degree of reduction in the energy release capacity of the battery of the target vehicle during use, thereby providing a basis for the subsequent formulation of a charging efficiency optimization strategy for the target vehicle in the charging station, wherein the battery operation and maintenance information refers to the maintenance, care, fault records, etc. of the battery corresponding to the target vehicle during use, and the battery energy decay rate indicates the degree of reduction in the energy release capacity of the battery of the target vehicle during use.

[0053] In detail, the calculating the battery energy decay rate of the target vehicle based on the battery operation and maintenance information includes: Extracting key operation and maintenance information and its corresponding operation and maintenance indicators from the battery operation and maintenance information; Based on the key operation and maintenance information, calculating the indicator capacity degradation factor corresponding to the operation and maintenance indicator; Analyzing the relevance of the operation and maintenance indicator to the battery of the target vehicle, and allocating an indicator relevance weight corresponding to the operation and maintenance indicator based on the battery relevance; The battery energy decay rate of the target vehicle is calculated by combining the indicator capacity degradation factor and the indicator associated weight.

[0054] Among them, the key operation and maintenance information is the specific information in the battery operation and maintenance information that plays a key role in the calculation of the battery energy decay rate. The operation and maintenance indicators are the information types corresponding to the key operation and maintenance information, such as charging and discharging, temperature and battery structure. The indicator capacity degradation factor is a quantitative value that measures the degree of degradation of the battery capacity caused by the operation and maintenance indicators. The battery correlation degree is the degree of influence of the operation and maintenance indicators on the battery performance and energy decay of the target vehicle. The indicator correlation weight is a weight value assigned to each operation and maintenance indicator based on the battery correlation degree, which reflects its relative importance in calculating the battery energy decay rate.

[0055] Furthermore, the key operation and maintenance information and its corresponding operation and maintenance indicators in the battery operation and maintenance information can be extracted through a classification algorithm, such as a decision tree algorithm; based on the key operation and maintenance information, the indicator capacity degradation factor corresponding to the operation and maintenance indicator is calculated according to a pre-constructed battery capacity degradation model and combined with relevant industry experience data. First, the model is built based on the electrochemical principle of the battery, and comprehensively considers multiple factors such as battery type, charge and discharge characteristics, and temperature influence, and quantifies these complex relationships into mathematical expressions. For example, for lithium-ion batteries, the model is modeled according to the change law of the reaction rate of electrode materials under different charge and discharge rates. Then, calibration and optimization are performed in combination with a large amount of similar battery operation and maintenance experience data accumulated in the industry over a long period of time. These data cover the actual situation of battery capacity attenuation under different working conditions and usage durations, such as the degradation data of batteries of a certain type of electric vehicles that are frequently started and stopped in congested urban roads and in high temperature environments. The model parameters can be accurately corrected, so as to accurately calculate the indicator capacity degradation factor corresponding to the operation and maintenance indicator according to the key operation and maintenance information input model; the operation and maintenance indicator can be analyzed for the battery relevance of the target vehicle through an in-depth battery performance and operation and maintenance data correlation analysis method. For example, when studying the operation and maintenance indicator of charge and discharge depth, a large amount of vehicle battery operation and maintenance data is collected, and the performance indicators such as the battery internal resistance change and capacity retention rate at different charge and discharge depths are compared. It is found that when the charge and discharge depth is often in the range of 80%-100%, the battery internal resistance increases rapidly in a short period of time, and the capacity retention rate drops sharply, which clearly shows the close correlation between the two; based on the battery correlation, the indicator correlation weight corresponding to the operation and maintenance indicator can be allocated through the expert scoring method; combined with the indicator capacity degradation factor and the indicator correlation weight, the battery energy decay rate of the target vehicle can be calculated through the weighted sum method.

[0056] S5. Combining the battery energy decay rate, the charging efficiency optimization path and the charging time slot sequence, formulate a charging efficiency optimization strategy for the target vehicle in the charging station, and based on the charging efficiency optimization strategy, perform charging processing on the target vehicle to obtain a charging result.

[0057] The present invention formulates a charging efficiency optimization strategy corresponding to the target vehicle by combining the battery energy decay rate, the charging efficiency optimization path and the charging time slot sequence. The comprehensive multi-dimensional information can greatly improve the accuracy and adaptability of the strategy, and based on the charging efficiency optimization strategy, the charging process of the target vehicle is executed, thereby improving the optimization effect of the vehicle charging efficiency. Among them, the charging efficiency optimization strategy is a specific operation method taken by the target vehicle to improve efficiency when charging at a charging station.

[0058] The steps for formulating the charging efficiency optimization strategy corresponding to the target vehicle are as follows: assuming that the battery energy decay rate of the target vehicle is low, there are many known effective charging efficiency optimization paths, and the selectable charging time slot sequence is better (for example, the time slot when the charging station is in a low power consumption period and there are few vehicles in the queue), the efficient fast charging mode is preferentially adopted to make full use of the high-quality charging time slots at this time, and the output parameters of the charging pile, such as voltage and current, are quickly adjusted according to the established optimization path to make them accurately adapt to the current state of the vehicle battery to achieve fast charging. At the same time, unnecessary battery balancing operations are reduced. Because the battery state is good, the balancing time can be saved. Only simple monitoring is performed at the end of charging to ensure that the power of each single cell in the battery pack is balanced. In addition, real-time vehicle data, such as battery temperature, is continuously collected to fine-tune the charging power according to slight changes in temperature to prevent overheating, thereby further improving Charging efficiency: Assuming that the target vehicle has a high battery energy decay rate, a limited charging efficiency optimization path, and a poor charging time slot sequence (a time slot during peak power consumption and with many waiting vehicles), it switches to the intelligent trickle charging mode to avoid large currents from damaging severely decayed batteries, replans the charging efficiency optimization path, and gives priority to methods that cause less damage to the battery and can increase the power within a limited time slot. For example, the charging current is adjusted in stages, with a small current in the early stage to wake up the battery, an appropriate current increase in the middle stage, and a slow reduction in the later stage. In response to the problem of tight time slots, negotiate with the charging station management system to strive for special permission to jump the queue or extend the charging time. If this is not possible, use the on-board energy storage device to power some low-power systems in the vehicle during the waiting time slot to reduce the standby consumption of the vehicle battery, thereby generating a charging efficiency optimization strategy corresponding to the target vehicle.

[0059] Compared with the problems described in the background technology, the present invention plans the charging time slot sequence of the target vehicle at the charging station by combining the vehicle travel pattern, the vehicle charging demand and the battery energy efficiency information, thereby improving the operating efficiency of the charging station and the charging convenience of the vehicle. Furthermore, the present invention collects the historical charging data and the real-time operating conditions of each charging pile to fully understand the operating status of the charging station, and calculates the charging idle probability of the charging pile in different time slots based on the real-time operating conditions. The charging idle probability can be used to understand the availability and idle possibility of the charging pile in different time slots, so as to plan the vehicle charging arrangement in advance and improve the rationality of charging resource allocation. Furthermore, the present invention calculates the capacity utilization index of the target vehicle during the charging process based on the charging and discharging energy data set. , can accurately understand the charging efficiency of the vehicle battery, and provide a key basis for the subsequent optimization path of the charging efficiency of the target vehicle at the charging station. Furthermore, the present invention calculates the battery energy decay rate of the target vehicle based on the battery operation and maintenance information, and can understand the degree of decline in the energy release capacity of the battery of the target vehicle during use, thereby providing a basis for the formulation of the subsequent charging efficiency optimization strategy of the target vehicle in the charging station. The present invention formulates the charging efficiency optimization strategy corresponding to the target vehicle by combining the battery energy decay rate, the charging efficiency optimization path and the charging time slot sequence. The comprehensive multi-dimensional information can greatly improve the accuracy and adaptability of the strategy, and based on the charging efficiency optimization strategy, the charging process of the target vehicle is executed, thereby improving the optimization effect of the vehicle charging efficiency. Therefore, the vehicle charging efficiency optimization method and system based on the AI ​​algorithm provided in the embodiment of the present invention can improve the optimization effect of the vehicle charging efficiency.

[0060] Embodiment 2: like Figure 2 The figure shows a functional module diagram of a vehicle charging efficiency optimization system based on an AI algorithm according to the present invention.

[0061] The automobile charging efficiency optimization system 200 based on AI algorithm described in the present invention can be installed in an electronic device. According to the functions implemented, the automobile charging efficiency optimization system based on AI algorithm can include a charging time slot sequence planning module 201, a charging guidance strategy setting module 202, a charging efficiency optimization path planning module 203, a battery energy decay rate calculation module 204 and a charging management module 205. The module described in the present invention can also be referred to as a unit, which refers to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, which are stored in the memory of the electronic device.

[0062] In the embodiment of the present invention, the functions of each module / unit are as follows: The charging time slot sequence planning module 201 is used to obtain the target vehicle to be analyzed and its corresponding charging station, collect the vehicle access information corresponding to the target vehicle, analyze the vehicle travel pattern and vehicle charging demand of the target vehicle based on the vehicle access information, collect the battery energy efficiency information corresponding to the target vehicle, and plan the charging time slot sequence of the target vehicle at the charging station in combination with the vehicle travel pattern, the vehicle charging demand and the battery energy efficiency information; The charging guidance strategy setting module 202 is used to collect the historical charging data and real-time operating conditions of each charging pile in the charging station, calculate the charging idle probability of the charging pile in different time slots based on the real-time operating conditions, calculate the charging pile utilization rate corresponding to each charging pile in the charging station based on the historical charging data, and set the charging guidance strategy corresponding to the charging station in combination with the charging idle probability and the charging pile utilization rate; The charging efficiency optimization path planning module 203 is used to record the charging and discharging data set corresponding to the target vehicle, calculate the capacity utilization index of the target vehicle during the charging process based on the charging and discharging data set, and plan the charging efficiency optimization path of the target vehicle at the charging station through a preset AI optimization algorithm in combination with the capacity utilization index and the charging guidance strategy; The battery energy decay rate calculation module 204 is used to query the battery operation and maintenance information corresponding to the target vehicle, and calculate the battery energy decay rate of the target vehicle based on the battery operation and maintenance information; The charging management module 205 is used to formulate a charging efficiency optimization strategy for the target vehicle in the charging station based on the battery energy decay rate, the charging efficiency optimization path and the charging time slot sequence, and execute charging processing for the target vehicle based on the charging efficiency optimization strategy to obtain a charging result.

[0063] In detail, each module in the vehicle charging efficiency optimization system 200 based on the AI ​​algorithm in the embodiment of the present invention is used in the same manner as described above. Figure 1 The same technical means are used as the method for optimizing automobile charging efficiency based on AI algorithm described in the specification and can produce the same technical effects, so I will not go into details here.

[0064] It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0065] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. A method for optimizing automobile charging efficiency based on AI algorithm, characterized in that: The method comprises: Acquire a target vehicle to be analyzed and its corresponding charging station, collect vehicle access information corresponding to the target vehicle, analyze the vehicle travel pattern and vehicle charging demand of the target vehicle based on the vehicle access information, collect battery energy efficiency information corresponding to the target vehicle, and plan the charging time slot sequence of the target vehicle at the charging station in combination with the vehicle travel pattern, the vehicle charging demand and the battery energy efficiency information; Collect historical charging data and real-time operating conditions of each charging pile in the charging station, calculate the charging idle probability of the charging pile in different time slots based on the real-time operating conditions, calculate the charging pile utilization rate corresponding to each charging pile in the charging station based on the historical charging data, and set the charging guidance strategy corresponding to the charging station in combination with the charging idle probability and the charging pile utilization rate; Record the charging and discharging data set corresponding to the target vehicle, calculate the capacity utilization index of the target vehicle during the charging process based on the charging and discharging data set, and plan the charging efficiency optimization path of the target vehicle at the charging station by combining the capacity utilization index and the charging guidance strategy through a preset AI optimization algorithm; Querying the battery operation and maintenance information corresponding to the target vehicle, and calculating the battery energy attenuation rate of the target vehicle based on the battery operation and maintenance information; In combination with the battery energy decay rate, the charging efficiency optimization path and the charging time slot sequence, a charging efficiency optimization strategy for the target vehicle in the charging station is formulated, and based on the charging efficiency optimization strategy, the charging process for the target vehicle is executed to obtain a charging result.

2. The method for optimizing automobile charging efficiency based on AI algorithm as claimed in claim 1, characterized in that: The step of planning the charging time slot sequence of the target vehicle at the charging station in combination with the vehicle travel pattern, the vehicle charging demand and the battery energy efficiency information includes: Perform feature mining and analysis on the vehicle travel patterns to obtain key travel features; Based on the vehicle charging demand, determining the charging power and expected charging cycle corresponding to the target vehicle; Analyzing the optimal charging interval of the battery of the target vehicle based on the battery energy efficiency information; In combination with the key travel characteristics, the charging power, the expected charging cycle and the optimal battery charging interval, a charging time slot sequence of the target vehicle at the charging station is planned.

3. The method for optimizing automobile charging efficiency based on AI algorithm as claimed in claim 2, characterized in that: The feature mining and analysis of the vehicle travel pattern is performed to obtain key travel features, including: Extracting information on the vehicle travel pattern to obtain travel pattern information; Calculating information entropy corresponding to the travel pattern information, and filtering out key travel pattern information in the travel pattern information based on the information entropy; Extracting features from the key travel pattern information to obtain initial travel features; The feature importance corresponding to the initial travel feature is calculated by the following formula: Among them, A represents the feature importance corresponding to the initial travel feature, represents the feature vector corresponding to the ath feature in the initial travel features, represents the feature vector corresponding to the a+1th feature in the initial travel feature, a and a+1 represent the feature sequence numbers corresponding to the initial travel feature, and t represents the number corresponding to the initial travel feature; Based on the feature importance, feature filtering is performed on the initial travel features to obtain key travel features.

4. The method for optimizing automobile charging efficiency based on AI algorithm according to claim 1, characterized in that: The calculating, based on the real-time operating condition, the charging idle probability of the charging pile in different time slots includes: Performing data integration processing on the real-time operating conditions to obtain a real-time operating condition data set; Performing data correction processing on the real-time operating condition data set to obtain a target operating condition data set; Dividing the target working condition data set into time slots to obtain time slot idle data; Based on the time slot idle data, determine the charging time slot length and the number of time slots corresponding to the charging pile; Combining the duration of the charging time slot and the number of time slots, the charging idle probability of the charging pile in different time slots is calculated by the following formula: Where D represents the probability of idle charging of the charging pile in different time slots, represents the duration of the bth time slot in the charging time slot, It represents the status identifier of the bth time slot in the charging time slot duration, b represents the sequence number corresponding to the charging time slot duration, and q represents the number of charging time slot durations.

5. The method for optimizing automobile charging efficiency based on AI algorithm according to claim 1, characterized in that: The calculating, based on the historical charging data, the charging pile utilization rate corresponding to each charging pile in the charging station comprises: Cleaning the historical charging data to obtain cleaned charging data; Performing charging record statistics on the cleaning charging data to obtain a charging record set; Performing time period statistics on the charging record set to obtain the effective charging time period; The theoretical available time corresponding to each charging pile in the charging station is queried, and the charging pile utilization rate corresponding to each charging pile in the charging station is calculated by combining the theoretical available time and the effective charging period.

6. The method for optimizing automobile charging efficiency based on AI algorithm according to claim 1, characterized in that: The calculating, based on the charging and discharging energy data set, a capacity utilization index of the target vehicle during the charging process includes: Extracting a charging subset from the charging and discharging energy data set, and sorting the charging subset to obtain an ordered charging subset; Identify a full charge capacity extreme value in the ordered charging subset, and calculate a single charge extreme capacity corresponding to the target vehicle based on the full charge capacity extreme value; The theoretical battery capacity of the target vehicle is queried, and the capacity utilization index of the target vehicle during the charging process is calculated by combining the single charging extreme capacity and the theoretical battery capacity through the following formula: Where G represents the capacity utilization index of the target vehicle during the charging process, It represents the maximum capacity of a single charge, and H represents the theoretical battery capacity.

7. The method for optimizing automobile charging efficiency based on AI algorithm according to claim 1, characterized in that: The combining of the capacity utilization index and the charging guidance strategy to plan the charging efficiency optimization path of the target vehicle at the charging station through a preset AI optimization algorithm includes: According to the capacity utilization index, the battery of the target vehicle is graded to obtain battery grade information; Querying the status record information corresponding to each charging pile in the charging station, and eliminating the charging piles in the charging station in combination with the battery level information, the charging guidance strategy and the status record information to obtain candidate charging piles; Acquire traffic condition information of the candidate charging pile, and evaluate the traffic congestion degree corresponding to the candidate charging pile according to the traffic condition information; Performing coordinate positioning on the target vehicle and the candidate charging pile respectively to obtain vehicle coordinate positioning and charging pile positioning; Combining the vehicle coordinate positioning and the charging pile positioning, calculating the charging range between the target vehicle and the candidate charging pile; Combining the charging trip and the traffic congestion degree, calculating the charging efficiency score of the candidate charging pile using the AI ​​optimization algorithm; The charging efficiency optimization path of the target vehicle at the charging station is planned by combining the charging efficiency score, the vehicle coordinate positioning and the charging pile positioning.

8. The method for optimizing automobile charging efficiency based on AI algorithm as claimed in claim 7, characterized in that: The step of evaluating the traffic congestion degree corresponding to the candidate charging pile according to the traffic condition information includes: Based on the traffic condition information, calculate the road traffic flow and road speed corresponding to the candidate charging pile; Querying the road criteria corresponding to each traffic road in the traffic condition information, and determining the road traffic flow threshold and road speed extreme value corresponding to each traffic road in the candidate charging pile based on the road criteria; In combination with the road traffic volume, the road speed, the road traffic volume threshold and the road speed extreme value, the congestion index corresponding to the candidate charging pile is calculated by the following formula: Among them, L represents the congestion index corresponding to the candidate charging pile, represents the road traffic volume of the e-th traffic road among the candidate charging piles, represents the road traffic flow threshold of the e-th traffic road among the candidate charging piles, represents the road speed of the e-th traffic road among the candidate charging piles, represents the road speed extreme value of the e-th traffic road among the candidate charging piles, e represents the traffic road sequence number of the candidate charging pile, and r represents the number of traffic roads of the candidate charging piles; The traffic congestion degree corresponding to the candidate charging pile is evaluated according to the congestion index.

9. The method for optimizing automobile charging efficiency based on AI algorithm as claimed in claim 1, characterized in that: The calculating the battery energy decay rate of the target vehicle based on the battery operation and maintenance information includes: Extracting key operation and maintenance information and its corresponding operation and maintenance indicators from the battery operation and maintenance information; Based on the key operation and maintenance information, calculating the indicator capacity degradation factor corresponding to the operation and maintenance indicator; Analyzing the relevance of the operation and maintenance indicator to the battery of the target vehicle, and allocating an indicator relevance weight corresponding to the operation and maintenance indicator based on the battery relevance; The battery energy decay rate of the target vehicle is calculated by combining the indicator capacity degradation factor and the indicator associated weight.

10. A car charging efficiency optimization system based on AI algorithm, characterized in that: The system comprises: A charging time slot sequence planning module is used to obtain a target vehicle to be analyzed and its corresponding charging station, collect vehicle access information corresponding to the target vehicle, analyze the vehicle travel pattern and vehicle charging demand of the target vehicle based on the vehicle access information, collect battery energy efficiency information corresponding to the target vehicle, and plan the charging time slot sequence of the target vehicle at the charging station in combination with the vehicle travel pattern, the vehicle charging demand and the battery energy efficiency information; A charging guidance strategy setting module, used to collect historical charging data and real-time operating conditions of each charging pile in the charging station, calculate the charging idle probability of the charging pile in different time slots based on the real-time operating conditions, calculate the charging pile utilization rate corresponding to each charging pile in the charging station based on the historical charging data, and set the charging guidance strategy corresponding to the charging station in combination with the charging idle probability and the charging pile utilization rate; A charging efficiency optimization path planning module is used to record the charging and discharging data set corresponding to the target vehicle, calculate the capacity utilization index of the target vehicle during the charging process based on the charging and discharging data set, and plan the charging efficiency optimization path of the target vehicle at the charging station through a preset AI optimization algorithm in combination with the capacity utilization index and the charging guidance strategy; A battery energy decay rate calculation module, used to query the battery operation and maintenance information corresponding to the target vehicle, and calculate the battery energy decay rate of the target vehicle based on the battery operation and maintenance information; The charging management module is used to formulate a charging efficiency optimization strategy for the target vehicle in the charging station based on the battery energy decay rate, the charging efficiency optimization path and the charging time slot sequence, and execute charging processing for the target vehicle based on the charging efficiency optimization strategy to obtain a charging result.

Images