An electric vehicle safety supervision system and method based on artificial intelligence
Through the electric vehicle safety supervision system based on artificial intelligence, a dynamic digital plane model is established using radar sensor groups, intelligently analyze and judge overtaking conditions and control acceleration rates, solving the safety hazards and energy waste problems of electric vehicles when overtaking, and improving safety and energy efficiency.
Patent Information
- Application Number
- CN202311241628.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2023-09-25
- Publication Date
- 2024-11-15
- Estimated Expiration
- 2043-09-25
AI Technical Summary
Due to the high acceleration rate of electric vehicles, they are prone to traffic accidents when overtaking and cause unreasonable energy consumption when overtaking. It is difficult for the existing technology to effectively supervise their safety.
An electric vehicle safety supervision system based on artificial intelligence is adopted to collect vehicle peripheral information through a radar sensor group, establish a dynamic digital plane model, intelligently analyze and determine whether there are overtaking conditions, and intelligently control the vehicle acceleration rate based on the judgment results.
It reduces the probability of traffic accidents, avoids unreasonable energy consumption, and improves the safety and energy efficiency of electric vehicles.
Smart Images

Figure CN117253301B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of artificial intelligence technology, and in particular to an electric vehicle safety supervision system and method based on artificial intelligence. Background Art
[0002] Electric vehicles are vehicles that use electricity as a power source and are driven by electric motors. They are new energy vehicles. The advent of electric vehicles means that the automotive industry will enter a new era. At the same time, electric vehicles are widely accepted by people due to their low noise, diversity, no pollution, simple structure and high energy efficiency.
[0003] Since electric vehicles have a higher acceleration rate than fuel vehicles, they can increase their speed faster during driving. Accelerating to change lanes and overtake is prone to safety accidents. If you find that you cannot overtake when accelerating to overtake, slowing down will cause energy loss. Although electric vehicles are equipped with energy recovery systems, they cannot achieve 100% recovery and there will still be energy consumption. Therefore, how to regulate the safety of electric vehicles has become a technical problem that needs to be solved urgently.
[0004] Therefore, people are in urgent need of an electric vehicle safety supervision system and method based on artificial intelligence to solve the above technical problems. Summary of the invention
[0005] The purpose of the present invention is to provide an electric vehicle safety supervision system and method based on artificial intelligence to solve the problems raised in the prior art.
[0006] To achieve the above object, the present invention provides the following technical solution: an electric vehicle safety supervision method based on artificial intelligence, the electric vehicle safety supervision method comprising the following steps:
[0007] S1. Collect information data about the surrounding area of the vehicle using a radar sensor group, and integrate the collected information data;
[0008] S2. Processing the data information collected by the radar sensor group to establish a dynamic digital plane model for vehicle safety supervision;
[0009] S3. Intelligently analyze the targets in the dynamic digital plane model to determine the judgment data for vehicle safety supervision;
[0010] S4, judging whether the vehicle currently has conditions for accelerating to overtake using the overtaking analysis unit according to the judgment data determined in S3;
[0011] S5. Based on the judgment result of S4, selectively perform intelligent control on the vehicle acceleration rate.
[0012] According to the above technical solution, in S1, the information data collected by the radar sensor group constitutes a set Q = {Q1, Q2, Q3, ..., Q n}, where Q n Represents the set of data collected by the nth radar sensor;
[0013] Q i ={q1,q2,q3,...,q m}, where Q i represents the set of data collected by the i-th radar sensor, q m It represents the mth data collected by the i-th radar sensor. The radar sensor collects information data once every time interval t.
[0014] According to the above technical solution, in S2, the establishment of the dynamic digital plane model includes the following steps:
[0015] S201, using a radar sensor to detect the distance L between the vehicle and the vehicle in front j , according to the vehicle distance value L j Establish a plane position model with the preceding vehicle;
[0016] S202, using a radar sensor to detect the distance value S between the two sides of the road j , according to the distance value S j Determine the lane to which the vehicle belongs;
[0017] S203: Using a radar sensor to detect the distance value p between the vehicle and the other lane. j , according to the distance value p j Establish a planar position model with vehicles in other lanes;
[0018] S204. Establish a dynamic digital plane model according to the results of S201-S203.
[0019] According to the above technical solution, in S3, the intelligent analysis of the dynamic digital plane model includes the following steps:
[0020] S301, determining the lane to which the vehicle belongs, and when the vehicle is in an edge lane, starting intelligent analysis of the dynamic digital plane model;
[0021] S302: Determine the distance between the vehicle and the vehicle in front, which is L j , determine the vehicle speed as V0, according to the vehicle distance value L j Change and the speed of the vehicle, determine the speed of the front vehicle as V1;
[0022] S303, using a plurality of radar sensors to detect other vehicles in front of the vehicle, obtaining detection data, and forming a set P = {p1, p2, p3, ..., p s}, where s represents the data collected by s radar sensors;
[0023] When the detection data in set P is greater than the set threshold, it is judged as invalid data;
[0024] Find the mutation point of the detection data in set P according to the following formula:
[0025] *p=|p k+1 -p k |;
[0026] Where *p represents the absolute value of the difference between two adjacent detection data in set P;
[0027] When *p≥a, it indicates that the mutation point requirement is met, and the data p k or p k+1 is the mutation point data;
[0028] Further analysis was performed according to the following formula;
[0029] *p=p k+1 -p k ;
[0030] When *p'≥a, p k is the mutation point data;
[0031] When *p'<-a, p k+1 is the mutation point data;
[0032] When *p<a, it indicates that the mutation point requirement is not met. k and p k+1 None of them are mutation point data, where a represents the set mutation point judgment threshold and a is a positive number;
[0033] Because the detection of other vehicles in front and side utilizes several radar sensors, the angle between the detection directions of every two adjacent radar sensors is α. By analyzing and interpreting the mutation points, the error caused by the length of the vehicle in front and side on the subsequent data analysis can be reduced.
[0034] S304: When there are other vehicles in front of the vehicle, there will be two mutation point data p in the set P. e and p f , e, f∈[1,s]; because when a row of radar sensors at different angles detect other vehicles in front of the side, since other vehicles have a certain length, there will inevitably be mutation points in the detection data in the area near the front of other vehicles and the parking space;
[0035] S305, extract mutation point data p e and p f Corresponding radar sensor information, obtain the angle β between the radar sensor and the vehicle's forward direction e and β f ;
[0036] Compare Beta e and β f The smaller of the two is used as the data, which is defined as β min , the corresponding detection data is p min ;
[0037] S306, according to the extracted usage data β min And the detection data p min , calculate the distance D between the vehicle in front and the vehicle in front in the direction of vehicle travel according to the following formula: j ;
[0038] D j =L j -cos(β min )*p min ;
[0039] According to D j And the speed of the front vehicle V1, analysis shows that the speed of the vehicle in front is V2.
[0040] According to the above technical solution, in S4, the overtaking analysis unit is used to judge the analysis result:
[0041] When D j ≥u and L j When ≥w, it is judged that the overtaking condition is met;
[0042] When D j <u or L j When <w, it is determined that the overtaking condition is not met;
[0043] w=γ1*V0+γ2*V1+Ω1;
[0044] u=γ1*V0+γ3*V2+Ω2;
[0045] Among them, γ1, γ2, γ3 represent setting coefficients, Ω1 and Ω2 represent error factors;
[0046] Because under different vehicle speed conditions, for L j The requirements are different. When the vehicle speed is slow, L j The distance can be appropriately smaller. When the vehicle speed is faster, L jThe distance needs to be larger, and when the speed V2 of the vehicle in front is greater than the speed V0 of the vehicle, the threshold u also needs to be adjusted. The factors affecting the threshold w are the speed of the vehicle in front and the speed of the vehicle, and the factors affecting the threshold u are the speed of the vehicle in front and the speed of the vehicle. Therefore, the threshold w and the threshold u need to be constantly changed and adjusted;
[0047] In S5, when the current state of the vehicle meets the overtaking condition, the vehicle acceleration rate is not controlled;
[0048] When the current state of the vehicle does not meet the overtaking conditions, the acceleration control unit is used to control the acceleration rate of the vehicle.
[0049] Through the above technical solution, when it is determined that overtaking cannot be completed, the acceleration rate of the vehicle will be controlled. Because the acceleration rate of electric vehicles is higher than that of ordinary fuel vehicles, some drivers often make dangerous driving behaviors when overtaking due to the high acceleration rate, which is prone to traffic accidents. At the same time, when the driver finds that he cannot overtake, he has to brake urgently. Although electric vehicles have energy recovery systems, it will still cause unnecessary consumption of energy. Therefore, controlling the acceleration rate of electric vehicles can not only reduce the probability of traffic accidents, but also avoid energy consumption.
[0050] A safety supervision system for electric vehicles, the system comprising a radar sensor group for collecting information data, installed in front of a vehicle, for detecting information data within a range of at least 180° in front of the vehicle, a data integration unit for processing the information data collected by the radar sensor group, a digital analysis module for analyzing the data integrated by the data integration unit, and an overtaking analysis unit for judging whether there are overtaking conditions according to the digital analysis module.
[0051] According to the above technical solution, the system further includes a label adding unit for adding labels to several radar sensors of the radar sensor group.
[0052] According to the above technical solution, the data integrated by the data integration unit is sent to the model building unit, and the model building unit is used to build a dynamic digital plane model of the current position of the vehicle according to the information data collected by the radar sensor group.
[0053] According to the above technical solution, the digital analysis module includes a lane positioning unit, a distance analysis unit and a vehicle speed comparison unit;
[0054] The lane positioning unit is used to analyze and locate the current lane of the vehicle according to the data information collected by the radar sensor group. The distance analysis unit is used to detect the vertical distance between other vehicles according to the detection data of the radar sensor group. The vehicle speed comparison unit is used to compare the vehicle speeds between other vehicles and cooperate with the distance analysis unit to determine the change in the vertical distance between other vehicles.
[0055] According to the above technical solution, the system further includes an acceleration control unit for controlling the acceleration rate of the vehicle when the overtaking analysis unit determines that there is no condition for accelerating to overtake.
[0056] Compared with the prior art, the beneficial effects of the present invention are as follows: the present application judges the current state of the vehicle, analyzes whether there are overtaking conditions, and then controls the acceleration rate of the vehicle. Because the acceleration rate of electric vehicles is higher than that of ordinary fuel vehicles, some drivers often make dangerous driving behaviors when overtaking due to the high acceleration rate, which is prone to traffic accidents. At the same time, when the driver finds that he cannot overtake, he has to brake urgently. Although the electric vehicle has an energy recovery system, it still causes unnecessary consumption of energy. Therefore, controlling the acceleration rate of the electric vehicle can not only reduce the probability of traffic accidents, but also avoid energy consumption. BRIEF DESCRIPTION OF THE DRAWINGS
[0057] Figure 1 A schematic diagram of the steps of an artificial intelligence-based electric vehicle safety supervision method of the present invention;
[0058] Figure 2 A schematic diagram of the connection relationship of an electric vehicle safety supervision system based on artificial intelligence of the present invention;
[0059] Figure 3 A schematic diagram of a dynamic digital plane model of an electric vehicle safety supervision system and method based on artificial intelligence according to the present invention;
[0060] Figure 4 A schematic diagram of a radar sensor group of an electric vehicle safety supervision system and method based on artificial intelligence of the present invention. DETAILED DESCRIPTION
[0061] 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.
[0062] like Figure 1 to Figure 4As shown, the present invention provides the following technical solution, an electric vehicle safety supervision method based on artificial intelligence, the electric vehicle safety supervision method comprising the following steps:
[0063] S1. Collect information data about the surrounding area of the vehicle using a radar sensor group, and integrate the collected information data;
[0064] The information data collected by the radar sensor group constitutes a set Q = {Q1, Q2, Q3, ..., Q n}, where Q n Represents the set of data collected by the nth radar sensor. For example, n is 7, which represents the left radar sensor, the right radar sensor, the front radar sensor, the left 30° radar sensor, the left 60° radar sensor, the right 30° radar sensor, and the right 60° radar sensor.
[0065] Q i ={q1,q2,q3,...,q m}, where Q i represents the set of data collected by the i-th radar sensor, q m It represents the mth data collected by the i-th radar sensor. The radar sensor collects information data once every time interval t.
[0066] S2. Processing the data information collected by the radar sensor group to establish a dynamic digital plane model for vehicle safety supervision;
[0067] The establishment of a dynamic digital plane model includes the following steps:
[0068] S201, using a radar sensor to detect the distance L between the vehicle and the vehicle in front j , according to the vehicle distance value L j Establish a plane position model with the preceding vehicle;
[0069] S202, using a radar sensor to detect the distance value S between the two sides of the road j , according to the distance value S j Determine the lane to which the vehicle belongs;
[0070] S203: Using a radar sensor to detect the distance value p between the vehicle and the other lane. j , according to the distance value p j Establish a planar position model with vehicles in other lanes;
[0071] S204. Establish a dynamic digital plane model according to the results of S201-S203.
[0072] S3. Intelligently analyze the targets in the dynamic digital plane model to determine the judgment data for vehicle safety supervision;
[0073] The intelligent analysis of the dynamic digital plane model includes the following steps:
[0074] S301, determining the lane to which the vehicle belongs, and when the vehicle is in an edge lane, starting intelligent analysis of the dynamic digital plane model, wherein the edge lane refers to the lanes on both sides, for example, if the current expressway is a two-way eight-lane highway, then the first lane and the fourth lane are edge lanes;
[0075] S302: Determine the distance between the vehicle and the vehicle in front, which is L j , determine the vehicle speed as V0, according to the vehicle distance value L j Change and the speed of the vehicle, determine the speed of the front vehicle as V1;
[0076] S303, using a plurality of radar sensors to detect other vehicles in front of the vehicle, obtaining detection data, and forming a set P = {p1, p2, p3, ..., p s}, where s represents the data collected by s radar sensors;
[0077] When the detection data in set P is greater than the set threshold, it is judged as invalid data;
[0078] Because when the detection data is greater than the set threshold, it means that the radar sensor collects vehicle information from non-adjacent lanes, but from vehicles one lane away. The presence of a vehicle one lane away does not affect the vehicle's lane change, so it is invalid data;
[0079] Find the mutation point of the detection data in set P according to the following formula:
[0080] *p=|p k+1 -p k |;
[0081] Where *p represents the absolute value of the difference between two adjacent detection data in set P;
[0082] When *p≥a, it indicates that the mutation point requirement is met, and the data p k or p k+1 is the mutation point data;
[0083] In order to further analyze and determine the mutation point data, further analysis was performed according to the following formula;
[0084] *p'=p k+1 -p k ;
[0085] When *p'≥a, p kis the mutation point data;
[0086] When *p'<-a, p k+1 is the mutation point data;
[0087] When *p<a, it indicates that the mutation point requirement is not met. k and p k+1 None of them are mutation point data, where a represents the set mutation point judgment threshold and a is a positive number;
[0088] Because the detection of other vehicles in front and side utilizes several radar sensors, the angle between the detection directions of every two adjacent radar sensors is α. By analyzing and interpreting the mutation points, the error caused by the length of the vehicle in front and side on the subsequent data analysis can be reduced.
[0089] S304: When there are other vehicles in front of the vehicle, there will be two mutation point data p in the set P. e and p f , e, f∈[1,s]; because when a row of radar sensors at different angles detect other vehicles in front of the side, since other vehicles have a certain length, there will inevitably be mutation points in the detection data in the area near the front of other vehicles and the parking space;
[0090] S305, extract mutation point data p e and p f Corresponding radar sensor information, obtain the angle β between the radar sensor and the vehicle's forward direction e and β f ;
[0091] Compare Beta e and β f The smaller of the two is used as the data, which is defined as β min , the corresponding detection data is p min ;
[0092] S306, according to the extracted usage data β min And the detection data p min , calculate the distance D between the vehicle in front and the vehicle in front in the direction of vehicle travel according to the following formula: j ;
[0093] D j =L j -cos(β min )*p min ;
[0094] According to D j And the speed of the front vehicle V1, analysis shows that the speed of the vehicle in front is V2.
[0095] S4, judging whether the vehicle currently has conditions for accelerating to overtake using the overtaking analysis unit according to the judgment data determined in S3;
[0096] In S4, the overtaking analysis unit is used to judge the analysis result:
[0097] When D j ≥u and L j When ≥w, it is judged that the overtaking condition is met;
[0098] When D j <u or L j When <w, it is determined that the overtaking condition is not met;
[0099] w=γ1*V0+γ2*V1+Ω1;
[0100] u=γ1*V0+γ3*V2+Ω2;
[0101] Among them, γ1, γ2, γ3 represent setting coefficients, Ω1 and Ω2 represent error factors;
[0102] Because under different vehicle speed conditions, for L j The requirements are different. When the vehicle speed is slow, L j The distance can be appropriately smaller. When the vehicle speed is faster, L j The distance needs to be larger, and when the speed V2 of the vehicle in front is greater than the speed V0 of the vehicle, the threshold u also needs to be adjusted. The factors affecting the threshold w are the speed of the vehicle in front and the speed of the vehicle, and the factors affecting the threshold u are the speed of the vehicle in front and the speed of the vehicle. Therefore, the threshold w and the threshold u need to be constantly changed and adjusted;
[0103] S5. Based on the judgment result of S4, selectively perform intelligent control on the vehicle acceleration rate.
[0104] When the vehicle's current state meets the overtaking conditions, the vehicle's acceleration rate is not controlled;
[0105] When the current state of the vehicle does not meet the overtaking conditions, the acceleration control unit is used to control the acceleration rate of the vehicle.
[0106] Through the above technical solution, when it is determined that overtaking cannot be completed, the acceleration rate of the vehicle will be controlled. Because the acceleration rate of electric vehicles is higher than that of ordinary fuel vehicles, some drivers often make dangerous driving behaviors when overtaking due to the high acceleration rate, which is prone to traffic accidents. At the same time, when the driver finds that he cannot overtake, he has to brake urgently. Although electric vehicles have energy recovery systems, it will still cause unnecessary consumption of energy. Therefore, controlling the acceleration rate of electric vehicles can not only reduce the probability of traffic accidents, but also avoid energy consumption.
[0107] An electric vehicle safety monitoring system, the system includes a radar sensor group for collecting information data, which is installed in front of the vehicle and is used to detect information data within a range of at least 180 degrees in front of the vehicle, a data integration unit for processing the information data collected by the radar sensor group, and a digital analysis module for analyzing the data integrated by the data integration unit.
[0108] The digital analysis module includes a lane positioning unit, a distance analysis unit and a vehicle speed comparison unit;
[0109] The lane positioning unit is used to analyze and locate the current lane of the vehicle according to the data information collected by the radar sensor group. The distance analysis unit is used to detect the vertical distance between other vehicles according to the detection data of the radar sensor group. The vehicle speed comparison unit is used to compare the vehicle speeds between other vehicles and cooperate with the distance analysis unit to determine the change in the vertical distance between other vehicles.
[0110] An overtaking analysis unit that determines whether overtaking conditions exist based on the digital analysis module.
[0111] The system also includes a label adding unit for adding labels to several radar sensors of the radar sensor group, so as to organize the collected data information and facilitate subsequent analysis and calling.
[0112] The data integrated by the data integration unit is sent to the model building unit, and the model building unit is used to build a dynamic digital plane model of the current position of the vehicle according to the information data collected by the radar sensor group.
[0113] The system also includes an acceleration control unit, which is used to control the vehicle's acceleration rate when the overtaking analysis unit determines that there are no conditions for accelerating to overtake, so as to avoid safety hazards and energy waste caused by the owner accelerating to overtake. The acceleration rate refers to the rate at which the electric vehicle speed increases.
[0114] Embodiment 1:
[0115] There are 13 radar sensors installed in front of the electric vehicle, forming a radar sensor group;
[0116] The left radar sensor and the right radar sensor are used to determine that the current road is a two-way four-lane road and that the vehicle is currently in the left lane;
[0117] The distance value detected by the front radar sensor is L j , the current vehicle speed is V0, and as the collected data is updated, the speed of the preceding vehicle is calculated to be V1;
[0118] The radar sensor detects other vehicles in front of the vehicle and obtains detection data to form a set P = {p1, p2, p3, p4, p5};
[0119] Find the mutation point of the detection data in set P according to the following formula:
[0120] *p=|p2-p1|=4;
[0121] *p=|p3-p2|=0.25;
[0122] *p=|p4-p3|=7;
[0123] *p=|p5-p4|=0.15;
[0124] Where *p represents the absolute value of the difference between two adjacent detection data in set P;
[0125] *p≥a=1, indicating that the mutation point requirement is met, and data p2 or p1 or p4 or p5 are mutation point data;
[0126] Further analysis was performed according to the following formula;
[0127] *p'=p2-p1=-4;
[0128] *p'=p5-p4=6;
[0129] *p'≥a=1, p5 is the mutation point data;
[0130] *p'<-a=-1, p2 is the mutation point data;
[0131] Extract the radar sensor information corresponding to the mutation point data p2 and p5, and obtain the angles β2=60° and β5=15° between the radar sensor and the forward direction of the vehicle;
[0132] Compare the sizes of β2 and β5, extract the smaller one of them as the used data, defined as β min =15°, the corresponding detection data is p min =7;
[0133] Based on the extracted usage data β min And the detection data p min , calculate the distance D between the vehicle in front and the vehicle in front in the direction of vehicle travel according to the following formula: j ;
[0134] D j =L j -cos(β min )*p min =40-0.97*7=33.21;
[0135] According to D j And the speed of the front vehicle V1, analysis shows that the speed of the vehicle in front is V2.
[0136] Use the overtaking analysis unit to judge the analysis results:
[0137] D j ≥u=20 and L j ≥w=30, it is judged that the overtaking condition is met;
[0138] w=γ1*V0+γ2*V1+Ω1;
[0139] u=γ1*V0+γ3*V2+Ω2;
[0140] Among them, γ1, γ2, γ3 represent setting coefficients, Ω1 and Ω2 represent error factors;
[0141] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.
Claims
1. An electric vehicle safety supervision method based on artificial intelligence, characterized in that: The electric vehicle safety supervision method comprises the following steps: S1. Collect information data about the surrounding area of the vehicle using a radar sensor group, and integrate the collected information data; S2. Processing the data information collected by the radar sensor group to establish a dynamic digital plane model for vehicle safety supervision; S3. Intelligently analyze the targets in the dynamic digital plane model to determine the judgment data for vehicle safety supervision; S4, judging whether the vehicle currently has conditions for accelerating to overtake using the overtaking analysis unit according to the judgment data determined in S3; S5. Based on the judgment result of S4, selectively and intelligently control the acceleration rate of the vehicle; In S3, the intelligent analysis of the dynamic digital plane model includes the following steps: S301, determining the lane to which the vehicle belongs, and when the vehicle is in an edge lane, starting intelligent analysis of the dynamic digital plane model; S302: Determine the distance between the vehicle and the vehicle in front, which is L j , determine the vehicle speed as V0, according to the vehicle distance value L j Change and the speed of the vehicle, determine the speed of the front vehicle as V1; S303, using a plurality of radar sensors to detect other vehicles in front of the vehicle, obtaining detection data, and forming a set P = {p1, p2, p3, ..., p s }, where s represents the data collected by s radar sensors; When the detection data in set P is greater than the set threshold, it is judged as invalid data; Find the mutation point of the detection data in set P according to the following formula: *p=|p k+1 -p k |; Where *p represents the absolute value of the difference between two adjacent detection data in set P; When *p≥a, it indicates that the mutation point requirement is met, and the data p k or p k+1 is the mutation point data; Further analysis was performed according to the following formula; *p’=p k+1 -p k ; When *p'≥a, p k is the mutation point data; When *p ’ When <-a, p k+1 is the mutation point data; When *p<a, it indicates that the mutation point requirement is not met. k and p k+1 None of them are mutation point data, where a represents the set mutation point judgment threshold and a is a positive number; S304: When there are other vehicles in front of the vehicle, there will be two mutation point data p in the set P. e and p f , e, f∈[1,s]; S305, extract mutation point data p e and p f Corresponding radar sensor information, obtain the angle β between the radar sensor and the vehicle's forward direction e and β f ; Compare Beta e and β f The smaller of the two is used as the data, which is defined as β min , the corresponding detection data is p min ; S306, according to the extracted usage data β min And the detection data p min , calculate the distance D between the vehicle in front and the vehicle in front in the direction of vehicle travel according to the following formula: j ; D j =L j -cos(β min )*p min ; According to D j and the speed of the vehicle in front V1, the speed of the vehicle in front is analyzed to be V2; in S4, the overtaking analysis unit is used to judge the analysis result: When D j ≥u and L j When ≥w, it is judged that the overtaking condition is met; When D j <u or L j When <w, it is determined that the overtaking condition is not met; w=γ1*V0+γ2*V1+Ω1; u=γ1*V0+γ3*V2+Ω2; Among them, γ1, γ2, γ3 represent setting coefficients, Ω1 and Ω2 represent error factors; In S5, when the current state of the vehicle meets the overtaking condition, the vehicle acceleration rate is not controlled; When the current state of the vehicle does not meet the overtaking conditions, the acceleration control unit is used to control the acceleration rate of the vehicle.
2. The electric vehicle safety supervision method based on artificial intelligence according to claim 1 is characterized in that: In S1, the information data collected by the radar sensor group constitutes a set Q = {Q1, Q2, Q3, ..., Q n }, where Q n Represents the set of data collected by the nth radar sensor; Q i ={q1,q2,q3,...,q m }, where Q i represents the set of data collected by the i-th radar sensor, q m It represents the mth data collected by the i-th radar sensor. The radar sensor collects information data once every time interval t.
3. The electric vehicle safety supervision method based on artificial intelligence according to claim 2 is characterized in that: In S2, the establishment of the dynamic digital plane model includes the following steps: S201, using a radar sensor to detect the distance L between the vehicle and the vehicle in front j , according to the vehicle distance value L j Establish a plane position model with the preceding vehicle; S202, using a radar sensor to detect the distance value S between the two sides of the road j , according to the distance value S j Determine the lane to which the vehicle belongs; S203: Using a radar sensor to detect the distance value p between the vehicle and the other lane. j , according to the distance value p j Establish a planar position model with vehicles in other lanes; S204. Establish a dynamic digital plane model according to the results of S201-S203.
4. An electric vehicle safety supervision system for implementing the electric vehicle safety supervision method based on artificial intelligence according to any one of claims 1 to 3, characterized in that: The system includes a radar sensor group for collecting information data, which is installed in front of the vehicle and is used to detect information data within a range of at least 180° in front of the vehicle, a data integration unit for processing the information data collected by the radar sensor group, a digital analysis module for analyzing the data integrated by the data integration unit, and an overtaking analysis unit for determining whether overtaking conditions exist based on the digital analysis module.
5. The electric vehicle safety supervision system according to claim 4 is characterized in that: The system further comprises a tag adding unit for adding tags to the plurality of radar sensors of the radar sensor group.
6. The electric vehicle safety supervision system according to claim 5, characterized in that: The data integrated by the data integration unit is sent to the model building unit, and the model building unit is used to build a dynamic digital plane model of the current position of the vehicle according to the information data collected by the radar sensor group.
7. The electric vehicle safety supervision system according to claim 6, characterized in that: The digital analysis module includes a lane positioning unit, a distance analysis unit and a vehicle speed comparison unit; The lane positioning unit is used to analyze and locate the current lane of the vehicle according to the data information collected by the radar sensor group. The distance analysis unit is used to detect the vertical distance between other vehicles according to the detection data of the radar sensor group. The vehicle speed comparison unit is used to compare the vehicle speeds between other vehicles and cooperate with the distance analysis unit to determine the change in the vertical distance between other vehicles.
8. The electric vehicle safety supervision system according to claim 7, characterized in that: The system also includes an acceleration control unit for controlling the acceleration rate of the vehicle when the overtaking analysis unit determines that there is no condition for accelerating to overtake.
Citation Information
Patent Citations
Automatic transmission shifting control method involving driving behavior prediction models
CN109237011A
An overtaking auxiliary early warning system based on multiple radars and a control method
CN109878446A
Automatic driving overtaking control method and system
CN111452789A
New energy automobile emergency self-adjusting driving system
CN113212439A
Vehicle control method
CN114104003A
