A vehicle power supply intelligent control system and method based on artificial intelligence

Abstract

The present invention discloses a vehicle power supply intelligent control system and method based on artificial intelligence, belonging to the field of vehicle power supply intelligent control technology. The system of the present invention includes: a data acquisition and analysis module, a historical feature extraction and modeling module, a historical vehicle power supply scheme evaluation and optimization module, a real-time path planning and battery status monitoring module and a real-time power supply intelligent control module; the data acquisition and analysis module is responsible for acquiring the historical data of the target vehicle, analyzing and establishing a historical driving event database; the historical feature extraction and modeling module extracts the historical data features and establishes an ideal power supply demand model; the historical vehicle power supply scheme evaluation and optimization module evaluates the historical power supply scheme and adjusts and optimizes the unreasonable scheme; the real-time path planning and battery status monitoring module performs real-time path planning and battery monitoring to determine the arrival capability; the real-time power supply intelligent control module performs intelligent power supply control on the vehicle.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle power supply intelligent control, and in particular to an artificial intelligence-based vehicle power supply intelligent control system and method. Background Art

[0002] With the increasing severity of global environmental problems and the continuous adjustment of energy structure, new energy vehicles such as electric vehicles and hybrid vehicles have become an important development direction of the future automobile market. Compared with traditional internal combustion engine vehicles, these new energy vehicles not only have the environmental advantage of zero emissions, but also can effectively reduce dependence on traditional fuel resources, thereby alleviating energy supply pressure and environmental pollution problems. Therefore, in the design and operation of electric and hybrid vehicles, the efficiency and intelligence of the vehicle power supply control system have become key technical challenges.

[0003] However, although the existing vehicle power supply control systems can meet basic needs, most of them implement vehicle power supply control based on fixed rules set at the factory. These rules may not fully consider the various dynamic factors during vehicle use, such as driving habits, road conditions, weather, etc., resulting in the vehicle power supply control system being not smart and efficient enough; in addition, when the battery is about to run out of power, the driver often faces the risk of sudden power shortage, which seriously affects driving safety. Summary of the invention

[0004] The purpose of the present invention is to provide an artificial intelligence-based vehicle power supply intelligent control system and method to solve the problems raised in the above background technology.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0006] A vehicle power supply intelligent control method based on artificial intelligence, the method comprising the following steps:

[0007] Step S100. Utilize the vehicle-mounted sensor and the cloud server to obtain the historical data of the target vehicle, analyze the historical data of the target vehicle, obtain several historical driving events of the target vehicle, associate the historical data of the target vehicle with the historical driving events, and thus form a historical driving event database of the target vehicle;

[0008] Step S200. For each historical driving event in the historical driving event database of the target vehicle, extract the corresponding historical data, analyze the historical data, and thus obtain the corresponding historical feature vector; analyze the historical feature vector of each historical driving event of the target vehicle to obtain the ideal power demand corresponding to the historical driving event of the target vehicle;

[0009] Step S300. According to the historical driving events of the target vehicle, obtain the corresponding historical vehicle power supply plan, and obtain the corresponding actual power supply based on the historical vehicle power supply plan; analyze the ideal power supply demand and the actual power supply corresponding to the historical driving events of the target vehicle, judge the rationality of the historical vehicle power supply plan, and process the historical vehicle power supply plan accordingly according to the judgment result;

[0010] Step S400. When the user starts the target vehicle, the destination of the target vehicle is obtained, and based on the currently collected real-time data, it is determined whether the target vehicle can reach the destination; if not, the corresponding notification information is output; if so, historical driving events are matched according to the real-time data, and the corresponding vehicle power supply plan is output based on the historical driving events.

[0011] Furthermore, step S100 includes:

[0012] S101. The historical data includes driving data, environmental data and battery status data of the target vehicle; wherein the driving data of the target vehicle refers to the vehicle operation data of the user when driving the target vehicle, including driving speed, braking frequency, driving distance, current location and road condition information, etc.; environmental data refers to the relevant data of the environment in which the target vehicle is located, specifically weather information; battery status data refers to the operating status data of the battery of the target vehicle, including the remaining battery power, battery temperature, etc.;

[0013] S102. According to the driving data of the target vehicle, several historical driving events are identified, the historical data of the target vehicle is divided according to the time period of the historical driving events, and the historical driving data of the same time period are associated with the historical data, so as to form a historical driving event database of the target vehicle; the historical driving events simultaneously meet the following conditions: the time period T from the start to the stop of the target vehicle is greater than or equal to the threshold Q1, and the position of the target vehicle changes and the driving distance S is greater than or equal to the threshold Q2. Each historical driving event includes key information such as the starting point, destination, driving time and driving distance.

[0014] By using on-board sensors and cloud servers to obtain historical data of the target vehicle, and correlating and analyzing driving data, environmental data, and battery status data, a historical driving event database of the target vehicle is formed. This step can provide detailed historical driving background and provide data support for subsequent intelligent decision-making.

[0015] Further, step S200 includes:

[0016] S201. Traverse the historical driving event database of the target vehicle, for each historical driving event, retrieve the historical data associated with the corresponding historical driving event from the historical driving event database, analyze the historical data, and thus extract the corresponding historical data features;

[0017] S202. The extracted historical data features are converted into a format, and different types of historical data features are visualized for analysis. The specific visualization analysis process is as follows: the historical data features are classified according to their types. For each historical data feature, the data points corresponding to the historical data feature values ​​are sequentially represented on a line graph in chronological order, and the slopes of the line segments connecting two adjacent data points are sequentially calculated to obtain a slope set K. For each historical data corresponding to a historical driving event, a slope set K of the historical data features corresponding to the corresponding historical data is extracted, and the relationship between the slope sets K of different types of historical data features is analyzed. If the slope sets K satisfy a linear relationship, the slope sets satisfying the linear relationship are converted into the slope sets K. The slope set K of the system is summarized, and the corresponding elements are represented on the radar chart in chronological order, where the number of axes of the radar chart is equal to the number of slope sets K that satisfy the linear relationship, and the number of axes of the radar chart is greater than or equal to 3; and adjacent data points are connected in sequence to obtain closed polygons, and the area of ​​the corresponding polygons is calculated, and the obtained polygon area is used as the fusion feature value of the slope set K that satisfies the linear relationship; all historical data features are traversed in sequence to form a historical feature vector V, and V=[V_D,V_E,V_B], where V_D, V_E and V_B represent the historical feature vector composed of the fusion feature values ​​corresponding to the driving data, environmental data and battery status data respectively;

[0018] S203. Obtain the historical feature vectors of the target vehicle, calculate the similarity between the historical feature vectors of the target vehicle, and classify the historical feature vectors with equal similarity into one category; for each category of historical feature vectors, obtain the corresponding battery consumption according to the battery status data corresponding to the historical feature vector, correspond the historical feature vectors with the corresponding battery consumption, take the average value of the battery consumption corresponding to each category of historical feature vectors as the ideal power demand H, and calculate the average value of each element of the corresponding historical feature vector as the ideal feature vector VH; obtain all ideal feature vectors VH and the ideal power demand H, and construct the power demand model G of the target vehicle, and the corresponding expression is: , where a represents the influencing factor, and f(VH) represents the functional relationship between the ideal feature vector VH and the ideal power supply demand of the target vehicle; for the target vehicle power supply demand model G, the historical feature vector V is input, and according to the similarity between the historical feature vector V and the ideal feature vector VH, the ideal power supply demand H corresponding to the ideal feature vector VH with the largest similarity is matched, thereby outputting the corresponding ideal power supply demand G.

[0019] For each historical driving event, the corresponding historical data features are extracted, and format conversion and visual analysis are performed. This includes the average speed, acceleration, vehicle load and other features of the driving data. By analyzing the historical data features, a historical feature vector is established, laying the foundation for the calculation of the ideal power supply demand and the establishment of the power supply model; and by fusion of historical data features, data features with the same trend are retained, and the total amount of feature data is shortened, making the analysis more comprehensive.

[0020] Furthermore, step S300 includes:

[0021] S301. For each historical driving event in the historical driving event database of the target vehicle, obtain the corresponding historical vehicle power supply plan, and obtain the corresponding actual power supply M based on the historical vehicle power supply plan; analyze the actual power supply M and the ideal power supply demand G corresponding to the target vehicle power supply demand model, and calculate the deviation relationship between the two, so as to obtain the deviation value F between the actual power supply M and the ideal power supply demand G, and F=|MG| / (M+G);

[0022] S302. Obtain the deviation value F between the actual power supply M and the ideal power supply demand G of all historical driving events, and compare the relationship between the deviation value F and the deviation threshold value f; if the deviation value F is less than or equal to the deviation threshold value f, the corresponding historical vehicle power supply plan is reasonable; if the deviation value F is greater than the deviation threshold value f, the corresponding historical vehicle power supply plan is unreasonable; according to the category to which the historical feature vectors corresponding to the historical driving events belong, the historical driving events corresponding to the historical feature vectors of the same category are marked according to the rationality judgment result of the historical vehicle power supply plan, and the historical driving events with reasonable historical vehicle power supply plans are marked as A1, and the historical driving events with unreasonable historical vehicle power supply plans are marked as A2; the historical vehicle power supply plans of the historical driving events marked as A1 in the historical driving events corresponding to each category of historical feature vectors are used as reference adjustment templates; for the historical driving events marked as A2 in the corresponding historical driving events, the similarity between the historical feature vectors of the historical driving events marked as A2 and the historical feature vectors of the historical driving events marked as A1 is calculated, and the reference adjustment template corresponding to the historical driving event marked as A1 with the largest similarity is selected to adjust the historical power supply plan of the historical driving event marked as A2, and the adjusted historical power supply plan replaces the historical power supply plan before the adjustment.

[0023] Based on the historical feature vector, the ideal power demand corresponding to the historical driving events of the target vehicle is calculated. , the relationship between the historical feature vector and the ideal power supply demand is modeled, where a represents the influencing factor and f(VH) represents the functional relationship between the feature vector and the power supply demand, which enables the system to predict and optimize the vehicle's power supply demand based on historical data.

[0024] Furthermore, step S400 includes:

[0025] S401. When the user starts the target vehicle, the destination of the target vehicle is obtained, and the corresponding driving path is automatically generated according to the current position and destination of the target vehicle, so as to obtain the driving distance S1; and the corresponding environmental data is obtained based on the driving path, and the battery status data of the current target vehicle is obtained, and the above environmental data and battery status data are used as real-time data, and the historical data corresponding to the historical driving event are matched according to the real-time data, and the maximum driving distance S0 in the historical data corresponding to the same environmental data and battery status data is obtained; the driving distance S1 is compared with the maximum driving distance S0. If the driving distance S1 is greater than or equal to the maximum driving distance S0, a prompt message of insufficient battery power is output to the relevant personnel; if the driving distance S1 is less than the maximum driving distance S0, go to S402;

[0026] S402. Acquire historical driving events that match the real-time data, and obtain corresponding historical power supply plans based on the matched historical driving events, and perform intelligent power supply control on the target vehicle according to the historical power supply plans.

[0027] When the user starts the target vehicle and sets the destination, the system matches historical driving events according to real-time data and generates a corresponding power supply plan based on the matching results. By comparing the real-time driving distance with the maximum driving distance in the historical data, the system can predict and warn of low battery conditions, or provide a real-time intelligent power supply control plan; for historical power supply plans, the system evaluates the deviation between the actual power supply and the ideal power supply demand to determine its rationality. Unreasonable power supply plans are marked and adjusted, and the power supply strategy is continuously improved through learning and optimization of historical data to improve overall efficiency and reliability.

[0028] An artificial intelligence-based vehicle power supply intelligent control system, the system includes: a data acquisition and analysis module, a historical feature extraction and modeling module, a historical vehicle power supply scheme evaluation and optimization module, a real-time path planning and battery status monitoring module, and a real-time power supply intelligent control module;

[0029] The data acquisition and analysis module is responsible for acquiring the historical data of the target vehicle from the on-board sensors and cloud servers. The historical data includes driving data, environmental data, and battery status data; analyzing the historical data, identifying historical driving events, and establishing a historical driving event database for the target vehicle;

[0030] The historical feature extraction and modeling module traverses the historical driving event database and extracts the corresponding historical data features for each historical driving event. The historical data features are converted into historical feature vectors, and the historical feature vectors are classified and the ideal power supply demand model is established according to their similarity. This module is responsible for evaluating the battery consumption pattern of the target vehicle under different historical scenarios and provides a basis for subsequent intelligent power supply control.

[0031] The historical vehicle power supply plan evaluation and optimization module obtains the historical vehicle power supply plan based on historical driving events, compares and analyzes it with the ideal power supply demand model, evaluates the deviation between the actual power supply and the ideal power supply demand, judges the rationality of the historical vehicle power supply plan, and adjusts and optimizes the unreasonable historical vehicle power supply plan;

[0032] Real-time route planning and battery status monitoring module When the user starts the target vehicle, the destination of the target vehicle is obtained, and the route is planned based on real-time data, and the current battery status data is monitored to determine whether the destination can be reached; if the battery power is insufficient, corresponding prompt information is provided; if the destination can be reached, the corresponding real-time power supply plan is output according to the real-time data matching historical driving events;

[0033] The real-time power supply intelligent control module matches historical driving events based on real-time data, obtains corresponding historical power supply plans, and performs real-time power supply intelligent control on the target vehicle according to the historical power supply plans; ensuring that the vehicle can effectively manage battery power supply during driving to achieve optimal energy utilization efficiency and driving safety.

[0034] Further, the data acquisition and analysis module includes a data acquisition unit and a historical data analysis unit;

[0035] The data acquisition unit is responsible for acquiring the historical data of the target vehicle from the on-board sensors and the cloud server. The historical data includes driving data, environmental data and battery status data. The historical data analysis unit analyzes the acquired historical data, identifies and extracts historical driving events, thereby forming a historical driving event database of the target vehicle.

[0036] Further, the historical feature extraction and modeling module includes a historical driving event extraction unit, a historical feature extraction unit, and a historical feature modeling unit;

[0037] The historical driving event extraction unit extracts historical driving events based on historical data; the historical feature extraction unit extracts historical feature vectors from each historical driving event, including the features of driving data, environmental data and battery status data; the historical feature modeling unit constructs the historical feature vectors of the target vehicle, calculates the similarity between the feature vectors, and establishes an ideal power supply demand model.

[0038] Further, the historical vehicle power supply scheme evaluation and optimization module includes a historical vehicle power supply scheme acquisition unit, a power supply actual evaluation unit, and a power supply scheme optimization unit;

[0039] The historical vehicle power supply plan acquisition unit acquires the power supply plan of the historical vehicle according to the historical driving events; the actual power supply evaluation unit evaluates the deviation between the actual power supply of the historical power supply plan and the ideal power supply demand; the power supply plan optimization unit adjusts the rationality of the historical vehicle power supply plan according to the evaluation result and optimizes the power supply plan.

[0040] Furthermore, the real-time path planning and battery status monitoring module includes a path planning unit, a battery status monitoring unit and a real-time data matching unit;

[0041] The path planning unit generates the driving path of the target vehicle according to the destination set by the user; the battery status monitoring unit monitors the current battery status of the target vehicle and determines whether the current power level can enable the target vehicle to reach the destination. If not, the corresponding notification information is output; if yes, further analysis is performed; the real-time data matching unit matches the real-time acquired data with the historical data to determine the historical driving events and power supply plans that match the current environment and battery status.

[0042] Compared with the prior art, the beneficial effects achieved by the present invention are:

[0043] By analyzing the historical data and driving events of the target vehicle, the system can provide personalized power supply solutions based on the vehicle's specific historical behavior patterns and environmental conditions, which can more effectively manage battery use, extend battery life, and improve the vehicle's energy efficiency. When the user starts the vehicle, the system can match the current real-time data (such as location, destination, battery status, etc.) with historical data to dynamically generate a power supply solution suitable for the current conditions. This real-time adaptability can ensure that the vehicle can operate safely and efficiently under different conditions. For historical power supply solutions, the system evaluates the deviation between the actual power supply and the ideal power supply demand, judges its rationality, marks and adjusts unreasonable power supply solutions, and continuously improves power supply strategies through learning and optimization of historical data to improve overall efficiency and reliability. The system not only considers driving data, but also includes environmental data (such as weather information) and battery status data. The comprehensive analysis of these data can predict battery consumption in advance and help users make adequate preparations and decisions before traveling. By outputting real-time notification information, the system can promptly warn users of low battery conditions, thereby improving users' sense of security and overall driving experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0045] Figure 1 It is a schematic diagram of a vehicle power supply intelligent control system module based on artificial intelligence of the present invention. DETAILED DESCRIPTION

[0046] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0047] See also Figure 1 , the present invention provides a technical solution:

[0048] An artificial intelligence-based vehicle power supply intelligent control system, the system includes: a data acquisition and analysis module, a historical feature extraction and modeling module, a historical vehicle power supply scheme evaluation and optimization module, a real-time path planning and battery status monitoring module, and a real-time power supply intelligent control module;

[0049] The data acquisition and analysis module is responsible for acquiring the historical data of the target vehicle from the on-board sensors and cloud servers. The historical data includes driving data, environmental data, and battery status data; analyzing the historical data, identifying historical driving events, and establishing a historical driving event database for the target vehicle;

[0050] The historical feature extraction and modeling module traverses the historical driving event database and extracts the corresponding historical data features for each historical driving event. The historical data features are converted into historical feature vectors, and the historical feature vectors are classified and the ideal power supply demand model is established according to their similarity. This module is responsible for evaluating the battery consumption pattern of the target vehicle under different historical scenarios and provides a basis for subsequent intelligent power supply control.

[0051] The historical vehicle power supply plan evaluation and optimization module obtains the historical vehicle power supply plan based on historical driving events, compares and analyzes it with the ideal power supply demand model, evaluates the deviation between the actual power supply and the ideal power supply demand, judges the rationality of the historical vehicle power supply plan, and adjusts and optimizes the unreasonable historical vehicle power supply plan;

[0052] Real-time route planning and battery status monitoring module When the user starts the target vehicle, the destination of the target vehicle is obtained, and the route is planned based on real-time data, and the current battery status data is monitored to determine whether the destination can be reached; if the battery power is insufficient, corresponding prompt information is provided; if the destination can be reached, the corresponding real-time power supply plan is output according to the real-time data matching historical driving events;

[0053] The real-time power supply intelligent control module matches historical driving events based on real-time data, obtains corresponding historical power supply plans, and performs real-time power supply intelligent control on the target vehicle according to the historical power supply plans; ensuring that the vehicle can effectively manage battery power supply during driving to achieve optimal energy utilization efficiency and driving safety.

[0054] The data acquisition and analysis module includes a data acquisition unit and a historical data analysis unit;

[0055] The data acquisition unit is responsible for acquiring the historical data of the target vehicle from the on-board sensors and the cloud server. The historical data includes driving data, environmental data and battery status data. The historical data analysis unit analyzes the acquired historical data, identifies and extracts historical driving events, thereby forming a historical driving event database of the target vehicle.

[0056] The historical feature extraction and modeling module includes a historical driving event extraction unit, a historical feature extraction unit, and a historical feature modeling unit;

[0057] The historical driving event extraction unit extracts historical driving events based on historical data; the historical feature extraction unit extracts historical feature vectors from each historical driving event, including the features of driving data, environmental data and battery status data; the historical feature modeling unit constructs the historical feature vectors of the target vehicle, calculates the similarity between the feature vectors, and establishes an ideal power supply demand model.

[0058] The historical vehicle power supply scheme evaluation and optimization module includes a historical vehicle power supply scheme acquisition unit, a power supply actual evaluation unit, and a power supply scheme optimization unit;

[0059] The historical vehicle power supply plan acquisition unit acquires the power supply plan of the historical vehicle according to the historical driving events; the actual power supply evaluation unit evaluates the deviation between the actual power supply of the historical power supply plan and the ideal power supply demand; the power supply plan optimization unit adjusts the rationality of the historical vehicle power supply plan according to the evaluation result and optimizes the power supply plan.

[0060] The real-time path planning and battery status monitoring module includes a path planning unit, a battery status monitoring unit and a real-time data matching unit;

[0061] The path planning unit generates the driving path of the target vehicle according to the destination set by the user; the battery status monitoring unit monitors the current battery status of the target vehicle and determines whether the current power level can enable the target vehicle to reach the destination. If not, the corresponding notification information is output; if yes, further analysis is performed; the real-time data matching unit matches the real-time acquired data with the historical data to determine the historical driving events and power supply plans that match the current environment and battery status.

[0062] A vehicle power supply intelligent control method based on artificial intelligence, the method comprising the following steps:

[0063] Step S100. Utilize the vehicle-mounted sensor and the cloud server to obtain the historical data of the target vehicle, analyze the historical data of the target vehicle, obtain several historical driving events of the target vehicle, associate the historical data of the target vehicle with the historical driving events, and thus form a historical driving event database of the target vehicle;

[0064] Step S200. For each historical driving event in the historical driving event database of the target vehicle, extract the corresponding historical data, analyze the historical data, and thus obtain the corresponding historical feature vector; analyze the historical feature vector of each historical driving event of the target vehicle to obtain the ideal power demand corresponding to the historical driving event of the target vehicle;

[0065] Step S300. According to the historical driving events of the target vehicle, obtain the corresponding historical vehicle power supply plan, and obtain the corresponding actual power supply based on the historical vehicle power supply plan; analyze the ideal power supply demand and the actual power supply corresponding to the historical driving events of the target vehicle, judge the rationality of the historical vehicle power supply plan, and process the historical vehicle power supply plan accordingly according to the judgment result;

[0066] Step S400. When the user starts the target vehicle, the destination of the target vehicle is obtained, and based on the currently collected real-time data, it is determined whether the target vehicle can reach the destination; if not, the corresponding notification information is output; if so, historical driving events are matched according to the real-time data, and the corresponding vehicle power supply plan is output based on the historical driving events.

[0067] Step S100 includes:

[0068] S101. The historical data includes driving data, environmental data and battery status data of the target vehicle; wherein the driving data of the target vehicle refers to the vehicle operation data of the user when driving the target vehicle, including driving speed, braking frequency, driving distance, current location and road condition information, etc.; environmental data refers to the relevant data of the environment in which the target vehicle is located, specifically weather information; battery status data refers to the operating status data of the battery of the target vehicle, including the remaining battery power, battery temperature, etc.;

[0069] S102. According to the driving data of the target vehicle, several historical driving events are identified, the historical data of the target vehicle is divided according to the time period of the historical driving events, and the historical driving data of the same time period are associated with the historical data, so as to form a historical driving event database of the target vehicle; the historical driving events simultaneously meet the following conditions: the time period T from the start to the stop of the target vehicle is greater than or equal to the threshold Q1, and the position of the target vehicle changes and the driving distance S is greater than or equal to the threshold Q2. Each historical driving event includes key information such as the starting point, destination, driving time and driving distance.

[0070] By using on-board sensors and cloud servers to obtain historical data of the target vehicle, and correlating and analyzing driving data, environmental data, and battery status data, a historical driving event database of the target vehicle is formed. This step can provide detailed historical driving background and provide data support for subsequent intelligent decision-making.

[0071] Step S200 includes:

[0072] S201. Traverse the historical driving event database of the target vehicle, for each historical driving event, retrieve the historical data associated with the corresponding historical driving event from the historical driving event database, analyze the historical data, and thus extract the corresponding historical data features;

[0073] S202. The extracted historical data features are converted into a format, and different types of historical data features are visualized for analysis. The specific visualization analysis process is as follows: the historical data features are classified according to their types. For each historical data feature, the data points corresponding to the historical data feature values ​​are sequentially represented on a line graph in chronological order, and the slopes of the line segments connecting two adjacent data points are sequentially calculated to obtain a slope set K. For each historical data corresponding to a historical driving event, a slope set K of the historical data features corresponding to the corresponding historical data is extracted, and the relationship between the slope sets K of different types of historical data features is analyzed. If the slope sets K satisfy a linear relationship, the slope sets satisfying the linear relationship are converted into the slope sets K. The slope set K of the system is summarized, and the corresponding elements are represented on the radar chart in chronological order, where the number of axes of the radar chart is equal to the number of slope sets K that satisfy the linear relationship, and the number of axes of the radar chart is greater than or equal to 3; and adjacent data points are connected in sequence to obtain closed polygons, and the area of ​​the corresponding polygons is calculated, and the obtained polygon area is used as the fusion feature value of the slope set K that satisfies the linear relationship; all historical data features are traversed in sequence to form a historical feature vector V, and V=[V_D,V_E,V_B], where V_D, V_E and V_B represent the historical feature vector composed of the fusion feature values ​​corresponding to the driving data, environmental data and battery status data respectively;

[0074] In this embodiment, taking driving data as an example, assuming that the driving data of a historical driving event includes driving speed, acceleration, vehicle load, steering operation, etc., for this historical driving event, the following features are extracted from the driving data: average speed, maximum acceleration, vehicle load change, steering frequency or steering angle change;

[0075] For the above driving data features, a line graph is drawn in chronological order. For each driving data feature, the slope of the line connecting adjacent data points is calculated to obtain a slope set K;

[0076] For example, suppose the features extracted from historical driving events include:

[0077] Average speed: [60,65,70,72,68] (unit: km / h);

[0078] Maximum acceleration: [2.5, 3.0, 3.2, 2.8, 2.6] (unit: m / s²);

[0079] Vehicle load change: [+100,+120,+110,+105,+115] (unit: kg);

[0080] Steering frequency or angle change: [+5,+8,+7,+6,+7] (unit: times or degrees);

[0081] Calculate the slope set K of each feature separately

[0082] Analyze whether there is a linear relationship between the slope sets K of each driving data feature.

[0083] Assuming that the average speed and the maximum acceleration and the slope set K of the vehicle load change have a linear relationship, they are summarized;

[0084] The slope set K that satisfies the linear relationship is plotted on the radar chart in chronological order, wherein the number of axes of the radar chart is equal to the number of slope sets K that satisfy the linear relationship, and the number of axes of the radar chart is greater than or equal to 3; when the number of axes of the radar chart is less than 3, one of the historical data features is retained;

[0085] Adjacent data points are connected to form a closed polygon, and its area is calculated as the fused feature value of the slope set K of the average speed, maximum acceleration, and vehicle load change.

[0086] S203. Obtain the historical feature vectors of the target vehicle, calculate the similarity between the historical feature vectors of the target vehicle, and classify the historical feature vectors with equal similarity into one category; for each category of historical feature vectors, obtain the corresponding battery consumption according to the battery status data corresponding to the historical feature vector, correspond the historical feature vectors with the corresponding battery consumption, take the average value of the battery consumption corresponding to each category of historical feature vectors as the ideal power demand H, and calculate the average value of each element of the corresponding historical feature vector as the ideal feature vector VH; obtain all ideal feature vectors VH and the ideal power demand H, and construct the power demand model G of the target vehicle, and the corresponding expression is: , where a represents the influencing factor, and f(VH) represents the functional relationship between the ideal feature vector VH and the ideal power supply demand of the target vehicle; for the target vehicle power supply demand model G, the historical feature vector V is input, and according to the similarity between the historical feature vector V and the ideal feature vector VH, the ideal power supply demand H corresponding to the ideal feature vector VH with the largest similarity is matched, thereby outputting the corresponding ideal power supply demand G.

[0087] For each historical driving event, the corresponding historical data features are extracted, and format conversion and visual analysis are performed. This includes the average speed, acceleration, vehicle load and other features of the driving data. By analyzing the historical data features, a historical feature vector is established, laying the foundation for the calculation of the ideal power supply demand and the establishment of the power supply model; and by fusion of historical data features, data features with the same trend are retained, and the total amount of feature data is shortened, making the analysis more comprehensive.

[0088] Step S300 includes:

[0089] S301. For each historical driving event in the historical driving event database of the target vehicle, obtain the corresponding historical vehicle power supply plan, and obtain the corresponding actual power supply M based on the historical vehicle power supply plan; analyze the actual power supply M and the ideal power supply demand G corresponding to the target vehicle power supply demand model, and calculate the deviation relationship between the two, so as to obtain the deviation value F between the actual power supply M and the ideal power supply demand G, and F=|MG| / (M+G);

[0090] S302. Obtain the deviation value F between the actual power supply M and the ideal power supply demand G of all historical driving events, and compare the relationship between the deviation value F and the deviation threshold value f; if the deviation value F is less than or equal to the deviation threshold value f, the corresponding historical vehicle power supply plan is reasonable; if the deviation value F is greater than the deviation threshold value f, the corresponding historical vehicle power supply plan is unreasonable; according to the category to which the historical feature vectors corresponding to the historical driving events belong, the historical driving events corresponding to the historical feature vectors of the same category are marked according to the rationality judgment result of the historical vehicle power supply plan, and the historical driving events with reasonable historical vehicle power supply plans are marked as A1, and the historical driving events with unreasonable historical vehicle power supply plans are marked as A2; the historical vehicle power supply plans of the historical driving events marked as A1 in the historical driving events corresponding to each category of historical feature vectors are used as reference adjustment templates; for the historical driving events marked as A2 in the corresponding historical driving events, the similarity between the historical feature vectors of the historical driving events marked as A2 and the historical feature vectors of the historical driving events marked as A1 is calculated, and the reference adjustment template corresponding to the historical driving event marked as A1 with the largest similarity is selected to adjust the historical power supply plan of the historical driving event marked as A2, and the adjusted historical power supply plan replaces the historical power supply plan before the adjustment.

[0091] Based on the historical feature vector, the ideal power demand corresponding to the historical driving events of the target vehicle is calculated. , the relationship between the historical feature vector and the ideal power supply demand is modeled, where a represents the influencing factor and f(VH) represents the functional relationship between the feature vector and the power supply demand, which enables the system to predict and optimize the vehicle's power supply demand based on historical data.

[0092] Step S400 includes:

[0093] S401. When the user starts the target vehicle, the destination of the target vehicle is obtained, and the corresponding driving path is automatically generated according to the current position and destination of the target vehicle, so as to obtain the driving distance S1; and the corresponding environmental data is obtained based on the driving path, and the battery status data of the current target vehicle is obtained, and the above environmental data and battery status data are used as real-time data, and the historical data corresponding to the historical driving event are matched according to the real-time data, and the maximum driving distance S0 in the historical data corresponding to the same environmental data and battery status data is obtained; the driving distance S1 is compared with the maximum driving distance S0. If the driving distance S1 is greater than or equal to the maximum driving distance S0, a prompt message of insufficient battery power is output to the relevant personnel; if the driving distance S1 is less than the maximum driving distance S0, go to S402;

[0094] S402. Acquire historical driving events that match the real-time data, and obtain corresponding historical power supply plans based on the matched historical driving events, and perform intelligent power supply control on the target vehicle according to the historical power supply plans.

[0095] When the user starts the target vehicle and sets the destination, the system matches historical driving events according to real-time data and generates a corresponding power supply plan based on the matching results. By comparing the real-time driving distance with the maximum driving distance in the historical data, the system can predict and warn of low battery conditions, or provide a real-time intelligent power supply control plan; for historical power supply plans, the system evaluates the deviation between the actual power supply and the ideal power supply demand to determine its rationality. Unreasonable power supply plans are marked and adjusted, and the power supply strategy is continuously improved through learning and optimization of historical data to improve overall efficiency and reliability.

[0096] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0097] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A vehicle power supply intelligent control method based on artificial intelligence, characterized in that: The method comprises the following steps: Step S100. Utilize the vehicle-mounted sensor and the cloud server to obtain the historical data of the target vehicle, analyze the historical data of the target vehicle, obtain several historical driving events of the target vehicle, associate the historical data of the target vehicle with the historical driving events, and thus form a historical driving event database of the target vehicle; Step S100 includes: S101. The historical data includes driving data, environmental data and battery status data of the target vehicle; wherein the driving data of the target vehicle refers to the vehicle operation data when the user is driving the target vehicle, the environmental data refers to the relevant data of the environment in which the target vehicle is located, and the battery status data refers to the operating status data of the battery of the target vehicle; S102. According to the driving data of the target vehicle, a number of historical driving events are identified, the historical data of the target vehicle is divided according to the time period of the historical driving events, and the historical driving data of the same time period are associated with the historical data, so as to form a historical driving event database of the target vehicle; the historical driving events simultaneously meet the following conditions: the time period T from the start to the stop of the target vehicle is greater than or equal to the threshold value Q1, and the position of the target vehicle changes and the driving distance S is greater than or equal to the threshold value Q2; Step S200. For each historical driving event in the historical driving event database of the target vehicle, extract the corresponding historical data, analyze the historical data, and thus obtain the corresponding historical feature vector; analyze the historical feature vector of each historical driving event of the target vehicle to obtain the ideal power demand corresponding to the historical driving event of the target vehicle; Step S200 includes: S201. Traverse the historical driving event database of the target vehicle, for each historical driving event, retrieve the historical data associated with the corresponding historical driving event from the historical driving event database, analyze the historical data, and thus extract the corresponding historical data features; S202. The extracted historical data features are converted into a format, and different types of historical data features are visualized for analysis. The specific visualization analysis process is as follows: the historical data features are classified according to their types. For each historical data feature, the data points corresponding to the historical data feature values ​​are sequentially represented on a line graph in chronological order, and the slopes of the line segments connecting two adjacent data points are sequentially calculated to obtain a slope set K. For each historical data corresponding to a historical driving event, a slope set K of the historical data features corresponding to the corresponding historical data is extracted, and the relationship between the slope sets K of different types of historical data features is analyzed. If the slope sets K satisfy a linear relationship, the slope sets satisfying the linear relationship are converted into the slope sets K. The slope set K of the system is summarized, and the corresponding elements are represented on the radar chart in chronological order, where the number of axes of the radar chart is equal to the number of slope sets K that satisfy the linear relationship, and the number of axes of the radar chart is greater than or equal to 3; and adjacent data points are connected in sequence to obtain closed polygons, and the area of ​​the corresponding polygons is calculated, and the obtained polygon area is used as the fusion feature value of the slope set K that satisfies the linear relationship; all historical data features are traversed in sequence to form a historical feature vector V, and V=[V_D,V_E,V_B], where V_D, V_E and V_B represent the historical feature vector composed of the fusion feature values ​​corresponding to the driving data, environmental data and battery status data respectively; S203. Obtain the historical feature vectors of the target vehicle, calculate the similarity between the historical feature vectors of the target vehicle, and classify the historical feature vectors with equal similarity into one category; for each category of historical feature vectors, obtain the corresponding battery consumption according to the battery status data corresponding to the historical feature vector, correspond the historical feature vectors with the corresponding battery consumption, take the average value of the battery consumption corresponding to each category of historical feature vectors as the ideal power demand H, and calculate the average value of each element of the corresponding historical feature vector as the ideal feature vector VH; obtain all ideal feature vectors VH and the ideal power demand H, construct the target vehicle power demand model G, and the corresponding expression is: G(H)=a*f(VH), where a represents the influencing factor, and f(VH) represents the functional relationship between the ideal feature vector VH and the ideal power demand of the target vehicle; for the target vehicle power demand model G, input the historical feature vector V, and according to the similarity between the historical feature vector V and the ideal feature vector VH, match the ideal power demand H corresponding to the ideal feature vector VH with the greatest similarity, thereby outputting the corresponding ideal power demand G; Step S300. According to the historical driving events of the target vehicle, obtain the corresponding historical vehicle power supply plan, and obtain the corresponding actual power supply based on the historical vehicle power supply plan; analyze the ideal power supply demand and the actual power supply corresponding to the historical driving events of the target vehicle, judge the rationality of the historical vehicle power supply plan, and process the historical vehicle power supply plan accordingly according to the judgment result; Step S400. When the user starts the target vehicle, the destination of the target vehicle is obtained, and based on the currently collected real-time data, it is determined whether the target vehicle can reach the destination; if not, the corresponding notification information is output; if so, historical driving events are matched according to the real-time data, and the corresponding vehicle power supply plan is output based on the historical driving events.

2. According to claim 1, a vehicle power supply intelligent control method based on artificial intelligence is characterized in that: The step S300 includes: S301. For each historical driving event in the historical driving event database of the target vehicle, obtain the corresponding historical vehicle power supply plan, and obtain the corresponding actual power supply M based on the historical vehicle power supply plan; analyze the actual power supply M and the ideal power supply demand G corresponding to the target vehicle power supply demand model, and calculate the deviation relationship between the two, so as to obtain the deviation value F between the actual power supply M and the ideal power supply demand G, and F=|MG| / (M+G); S302. Obtain the deviation value F between the actual power supply M and the ideal power supply demand G of all historical driving events, and compare the relationship between the deviation value F and the deviation threshold value f; if the deviation value F is less than or equal to the deviation threshold value f, the corresponding historical vehicle power supply plan is reasonable; if the deviation value F is greater than the deviation threshold value f, the corresponding historical vehicle power supply plan is unreasonable; according to the category to which the historical feature vectors corresponding to the historical driving events belong, the historical driving events corresponding to the historical feature vectors of the same category are marked according to the rationality judgment result of the historical vehicle power supply plan, and the historical driving events with reasonable historical vehicle power supply plans are marked as A1, and the historical driving events with unreasonable historical vehicle power supply plans are marked as A2; the historical vehicle power supply plans of the historical driving events marked as A1 in the historical driving events corresponding to each category of historical feature vectors are used as reference adjustment templates; for the historical driving events marked as A2 in the corresponding historical driving events, the similarity between the historical feature vectors of the historical driving events marked as A2 and the historical feature vectors of the historical driving events marked as A1 is calculated, and the reference adjustment template corresponding to the historical driving event marked as A1 with the largest similarity is selected to adjust the historical power supply plan of the historical driving event marked as A2, and the adjusted historical power supply plan replaces the historical power supply plan before the adjustment.

3. The vehicle power supply intelligent control method based on artificial intelligence according to claim 2 is characterized in that: The step S400 includes: S401. When the user starts the target vehicle, the destination of the target vehicle is obtained, and the corresponding driving path is automatically generated according to the current position and destination of the target vehicle, so as to obtain the driving distance S1; and the corresponding environmental data is obtained based on the driving path, and the battery status data of the current target vehicle is obtained, and the above environmental data and battery status data are used as real-time data, and the historical data corresponding to the historical driving event are matched according to the real-time data, and the maximum driving distance S0 in the historical data corresponding to the same environmental data and battery status data is obtained; the driving distance S1 is compared with the maximum driving distance S0. If the driving distance S1 is greater than or equal to the maximum driving distance S0, a prompt message of insufficient battery power is output to the relevant personnel; if the driving distance S1 is less than the maximum driving distance S0, go to S402; S402. Acquire historical driving events that match the real-time data, and obtain corresponding historical power supply plans based on the matched historical driving events, and perform intelligent power supply control on the target vehicle according to the historical power supply plans.

4. An artificial intelligence-based vehicle power supply intelligent control system, applied to any one of the artificial intelligence-based vehicle power supply intelligent control methods in claims 1-3, characterized in that: The system includes: a data acquisition and analysis module, a historical feature extraction and modeling module, a historical vehicle power supply scheme evaluation and optimization module, a real-time path planning and battery status monitoring module, and a real-time power supply intelligent control module; The data acquisition and analysis module is responsible for acquiring historical data of the target vehicle from the vehicle-mounted sensors and the cloud server, wherein the historical data includes driving data, environmental data and battery status data; analyzing the historical data, identifying historical driving events, and establishing a historical driving event database of the target vehicle; The historical feature extraction and modeling module traverses the historical driving event database, extracts the corresponding historical data features for each historical driving event, converts the historical data features into historical feature vectors, and classifies and establishes an ideal power supply demand model according to the similarity of the historical feature vectors; The historical vehicle power supply scheme evaluation and optimization module obtains the historical vehicle power supply scheme according to the historical driving events, and compares and analyzes it with the ideal power supply demand model, evaluates the deviation between the actual power supply and the ideal power supply demand, judges the rationality of the historical vehicle power supply scheme, and adjusts and optimizes the unreasonable historical vehicle power supply scheme; When the user starts the target vehicle, the real-time route planning and battery status monitoring module obtains the destination of the target vehicle, and performs route planning based on real-time data, monitors the current battery status data, and determines whether the destination can be reached; if the battery power is insufficient, corresponding prompt information is provided; if the destination can be reached, the real-time data is matched with historical driving events, and the corresponding real-time power supply plan is output; The real-time power supply intelligent control module matches historical driving events based on real-time data, obtains corresponding historical power supply plans, and performs real-time power supply intelligent control on the target vehicle according to the historical power supply plans.

5. According to claim 4, the vehicle power supply intelligent control system based on artificial intelligence is characterized in that: The data acquisition and analysis module includes a data acquisition unit and a historical data analysis unit; The data acquisition unit is responsible for acquiring historical data of the target vehicle from on-board sensors and cloud servers, wherein the historical data includes driving data, environmental data and battery status data; the historical data analysis unit analyzes the acquired historical data, identifies and extracts historical driving events, thereby forming a historical driving event database of the target vehicle.

6. The vehicle power supply intelligent control system based on artificial intelligence according to claim 4 is characterized in that: The historical feature extraction and modeling module includes a historical driving event extraction unit, a historical feature extraction unit and a historical feature modeling unit; The historical driving event extraction unit extracts historical driving events based on historical data; the historical feature extraction unit extracts historical feature vectors from each historical driving event, including features of driving data, environmental data and battery status data; the historical feature modeling unit constructs historical feature vectors of the target vehicle, calculates the similarity between feature vectors, and establishes an ideal power supply demand model.

7. The vehicle power supply intelligent control system based on artificial intelligence according to claim 4 is characterized in that: The historical vehicle power supply scheme evaluation and optimization module includes a historical vehicle power supply scheme acquisition unit, a power supply actual evaluation unit and a power supply scheme optimization unit; The historical vehicle power supply scheme acquisition unit acquires the historical vehicle power supply scheme according to the historical driving events; The actual power supply evaluation unit evaluates the deviation between the actual power supply of the historical power supply plan and the ideal power supply demand; the power supply plan optimization unit adjusts the rationality of the historical vehicle power supply plan according to the evaluation result and optimizes the power supply plan.

8. The vehicle power supply intelligent control system based on artificial intelligence according to claim 4 is characterized in that: The real-time path planning and battery status monitoring module includes a path planning unit, a battery status monitoring unit and a real-time data matching unit; The path planning unit generates a driving path for the target vehicle according to a destination set by a user; The battery status monitoring unit monitors the current battery status of the target vehicle and determines whether the current power level enables the target vehicle to reach the destination. If not, a corresponding notification message is output; if yes, further analysis is performed. The real-time data matching unit matches the data acquired in real time with the historical data to determine the historical driving events and power supply solutions that match the current environment and battery status.

Images