New energy automobile safe driving detection method and system

Abstract

The invention discloses a new energy automobile safe driving detection method and system, and relates to the technical field of safe driving detection, and the method comprises the steps: collecting vehicle state data, and carrying out the preprocessing of the vehicle state data; constructing a health state evaluation model, and predicting a vehicle health state score; dynamically adjusting scene detection parameters according to the vehicle health state score; environment data are collected in real time through the adjusted scene detection parameters, and a scene risk score is evaluated based on the environment data; and according to the vehicle health state score and the scene risk score, generating an optimal driving strategy, and executing an active safety linkage mechanism. According to the invention, the health state evaluation model is constructed, the multi-dimensional state data of the vehicle is comprehensively analyzed, and the health state of the vehicle is accurately quantified; the environment detection parameters are dynamically adjusted according to the health state score, the detection sensitivity and frequency are improved when the health state is poor, and the adaptability to complex road conditions and severe weather is enhanced.

Description

Technical Field

[0001] The present invention relates to the technical field of safe driving detection, and in particular to a detection method and system for safe driving of a new energy vehicle. Background Art

[0002] With the rapid development of new energy vehicles, their role in energy conservation, emission reduction and sustainable transportation has become increasingly prominent. However, due to the uniqueness of new energy vehicles in structure and operation characteristics (such as battery system, motor drive and electronic control system), their demand for safe driving is also different from that of traditional internal combustion engine vehicles. In recent years, safe driving detection technology for new energy vehicles has gradually become a research hotspot, including key areas such as vehicle status monitoring, environmental perception and risk assessment. Existing technologies mainly use sensor networks and data analysis technologies to collect and analyze vehicle status (such as battery temperature, voltage, tire pressure, etc.) and environmental status (such as obstacle distance, vehicle speed, road curvature, etc.), assist drivers in making decisions and improve driving safety. For example, some technologies have achieved real-time monitoring of a single vehicle status parameter (such as battery temperature) through on-board sensors and combined with simple environmental data (such as vehicle speed) for risk warning. However, most of these methods use discrete monitoring and single rule evaluation, which cannot achieve comprehensive analysis and dynamic decision-making of vehicle health status and complex driving scenarios, resulting in limited effectiveness in multi-variable and high-dynamic driving scenarios.

[0003] Existing technologies still have certain shortcomings in the detection of safe driving of new energy vehicles. First, existing methods lack a unified comprehensive model for the assessment of vehicle health status, and usually only focus on the monitoring of a single or a small amount of vehicle status data, while ignoring the synergy between multiple key components (such as batteries, brakes, motors and tires, etc.) and their impact on the overall health of the vehicle; this limitation may lead to an incomplete assessment of health status, which in turn affects the accuracy of driving strategies. Secondly, when conducting scenario risk assessments, most existing technologies use static detection parameters (such as a fixed obstacle detection range or refresh frequency), and fail to dynamically adjust environmental perception parameters according to changes in vehicle health status, making it difficult to provide sufficient safety protection when vehicle performance degrades or in complex environments. These technical deficiencies are particularly prominent in high-risk driving scenarios (such as bad weather and complex road conditions), which may lead to an increased risk of accidents or excessive reliance on drivers. Summary of the invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides a detection method for safe driving of new energy vehicles to solve the problems of incomplete vehicle health status assessment and lack of dynamic adjustment of scenario risk assessment.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, the present invention provides a detection method for safe driving of new energy vehicles, which includes collecting vehicle status data and preprocessing the vehicle status data; constructing a health status assessment model to predict a vehicle health status score; dynamically adjusting scene detection parameters according to the vehicle health status score; collecting environmental data in real time through the adjusted scene detection parameters, and evaluating a scene risk score based on the environmental data; generating an optimal driving strategy according to the vehicle health status score and the scene risk score, and executing an active safety linkage mechanism.

[0008] As a preferred solution of the detection method for safe driving of new energy vehicles described in the present invention, the vehicle status data includes battery status data, brake status data, motor status data and tire status data.

[0009] As a preferred solution of the detection method for safe driving of new energy vehicles of the present invention, the vehicle status data is preprocessed, and the specific steps are as follows:

[0010] The battery status data is cleaned and smoothed by outlier filtering and low-pass filtering to remove noise;

[0011] The normalization method is used to process the brake status data;

[0012] Synchronize motor state data through time series alignment;

[0013] The abnormal fluctuation detection method is used to process the abnormal values ​​of tire status data.

[0014] As a preferred solution of the detection method for safe driving of new energy vehicles of the present invention, the steps of constructing a health status assessment model and predicting the vehicle health status score are as follows:

[0015] Based on the preprocessed vehicle status data, a dynamic weight allocation mechanism is formulated to dynamically adjust the impact of each vehicle status data on the vehicle health status score according to the importance and real-time status of different health parameters. The expression is:

[0016]

[0017] Among them, w i is the weight of the i-th vehicle state data, and β is a measure of the degree of deviation of the vehicle state data to w i The weight coefficient of influence, x i is the vehicle status data, μ is the mean of the vehicle status data, N is the total number of vehicle status data, and i is the index variable of the vehicle status data;

[0018] Through nonlinear processing, the impact of vehicle data on health status is magnified, and combined with historical fault data and dynamic driving data, a multi-layer penalty mechanism is formulated to comprehensively evaluate the health status of the vehicle, form a health status assessment model, and predict the vehicle health status score. The expression is:

[0019]

[0020] Where S is the vehicle health score, x i is the value of the i-th vehicle status data, C s is the scene adaptability factor, P i is the comprehensive penalty value of the i-th vehicle status data, N is the total number of vehicle status data, i is the index variable for vehicle status data, and y f The value of the fth historical fault data, z j represents the value of the jth dynamic driving state data, Δz j represents the change rate of the jth dynamic driving parameter, ψ is the layer coefficient of the dynamic change rate, M is the total number of dynamic driving data, j is the epitome variable of the dynamic driving data, and λ is the normalization constant;

[0021] The formulation of a multi-layer penalty mechanism includes the following steps:

[0022] According to the hierarchical characteristics of historical vehicle health status assessment and the breadth of abnormal impact range, the penalty is divided into three levels: single parameter penalty, parameter interaction penalty and scenario adaptability penalty;

[0023] Single parameter penalty is based on the degree of abnormal deviation of a single health parameter;

[0024] Parameter interaction penalty considers the mutual correlation between multiple parameters and imposes penalties;

[0025] The scene adaptability penalty is imposed based on the dynamic environment data of the driving field;

[0026] Combine different levels of penalty mechanisms with the driving environment and adjust the penalty effect in real time.

[0027] As a preferred solution of the detection method for safe driving of new energy vehicles of the present invention, wherein: the scene detection parameters are dynamically adjusted according to the vehicle health status score, and the specific steps are as follows:

[0028] Based on the abnormal statistical analysis of historical vehicle status data, a healthy threshold T1 is defined;

[0029] When S ≥ T1, the vehicle is considered to be in good health;

[0030] When S<T1, the vehicle is considered to be in poor health;

[0031] When the vehicle is in good health, maintain normal detection parameters of environmental data;

[0032] When the vehicle is in poor health, the detection sensitivity and frequency of environmental data are improved.

[0033] As a preferred solution of the detection method for safe driving of new energy vehicles of the present invention, wherein: the environmental data includes obstacle distance, current vehicle speed, road curvature, traffic density and weather conditions;

[0034] The specific steps of evaluating the scenario risk score based on environmental data are as follows:

[0035] By comprehensively analyzing the adjusted scene detection parameters and the real-time collected environmental data, the potential risk level of the driving process in different environments is quantified and the scene risk score is predicted. The expression is:

[0036]

[0037] Where v is the vehicle speed, ρ is the distance between the vehicle and the obstacle, k is the road curvature, η represents the number of vehicles per unit length of road, γ is the weight coefficient of the number of vehicles per unit length of road, ω is the current weather severity, δ is the weight coefficient of the weather severity, and R e The risk score of the scene the vehicle is currently in, t represents the time variable, and e represents the base of the natural logarithm.

[0038] As a preferred solution of the detection method for safe driving of new energy vehicles of the present invention, wherein: the optimal driving strategy is generated according to the vehicle health status score and the scenario risk score, and the active safety linkage mechanism is executed. The specific steps are as follows:

[0039] Based on the vehicle health status score S and the scenario risk score R e , combined in the form of nonlinear weighted coupling to generate a comprehensive driving risk index, expressed as:

[0040]

[0041] Among them, R is the comprehensive driving risk index, a is the weight of controlling the impact of the vehicle health status score S on the comprehensive risk R, and b is the weight of controlling the impact of the vehicle health status score S on the comprehensive driving risk index R;

[0042] Define low security risk threshold R1 and high security risk threshold R2 based on historical data statistics;

[0043] When R<R1, the vehicle's current comprehensive driving risk is low, and the vehicle maintains a normal speed;

[0044] When R1≤R<R2, the vehicle's current comprehensive driving risk is at medium risk, the vehicle speed is reduced, the driver is reminded to pay attention to environmental changes, and the low-speed automatic braking, lane keeping assist and blind spot monitoring in the active safety linkage mechanism are activated;

[0045] When R≥R1, the vehicle's current comprehensive driving risk is at high risk, and active safety intervention is taken to forcibly reduce the vehicle speed and activate the active safety linkage mechanism's emergency automatic braking, active obstacle avoidance, ESC and highly sensitive collision avoidance.

[0046] In the second aspect, the present invention provides a detection system for safe driving of new energy vehicles, including a data acquisition module, a vehicle health scoring module, a detection parameter adjustment module, a risk assessment module and a strategy generation module; the data acquisition module is used to collect vehicle status data and pre-process the vehicle status data; the vehicle health scoring module is used to build a health status assessment model and predict the vehicle health status score; the detection parameter adjustment module is used to dynamically adjust the scene detection parameters according to the vehicle health status score; the risk assessment module is used to collect environmental data in real time through the adjusted scene detection parameters, and evaluate the scene risk score based on the environmental data; the strategy generation module is used to generate the best driving strategy according to the vehicle health status score and the scene risk score, and execute the active safety linkage mechanism.

[0047] In a third aspect, the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, any step of the method for detecting safe driving of new energy vehicles as described in the first aspect of the present invention is implemented.

[0048] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, any step of the method for detecting safe driving of new energy vehicles as described in the first aspect of the present invention is implemented.

[0049] The beneficial effects of the present invention are as follows: by constructing a health status assessment model, comprehensively analyzing the multi-dimensional status data of the vehicle, and accurately quantifying the health status of the vehicle; dynamically adjusting the environmental detection parameters according to the health status score, improving the detection sensitivity and frequency when the health status is poor, and enhancing the adaptability to complex road conditions and bad weather. The present invention realizes the linkage analysis of the vehicle health status and scenario risks, effectively overcoming the shortcomings of the incomplete health assessment and static detection parameters in the prior art, and significantly improving the reliability and adaptability of safe driving of new energy vehicles. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0051] Figure 1 This is a flow chart of the detection method for safe driving of new energy vehicles in Example 1.

[0052] Figure 2 This is a schematic diagram of a detection system for safe driving of new energy vehicles in Example 1. DETAILED DESCRIPTION

[0053] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0054] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0055] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0056] Example 1, reference Figure 1 and Figure 2 , which is the first embodiment of the present invention, and provides a method for detecting safe driving of a new energy vehicle, comprising the following steps:

[0057] S1: Collect vehicle status data and pre-process the vehicle status data.

[0058] S1.1: Vehicle status data includes battery status data, brake status data, motor status data and tire status data.

[0059] Furthermore, the battery status data includes battery temperature, voltage, current and state of charge SOC;

[0060] Braking status data includes brake pad wear, brake fluid pressure and brake response time;

[0061] Motor status data includes motor speed, temperature and current;

[0062] Tire status data includes tire pressure, tire temperature and wear;

[0063] S1.2: Clean and smooth the battery status data through outlier filtering and low-pass filtering denoising;

[0064] For example, the abnormal spike value of the battery voltage caused by short-term electromagnetic interference is filtered out, and the fluctuation trend is smoothed to accurately reflect the real state of the battery.

[0065] S1.3: Use normalization method to process the brake status data;

[0066] For example, the values ​​of brake pad wear can be normalized to a range of 0 to 1 to facilitate comprehensive analysis with other status data.

[0067] S1.4: Synchronize the motor state data by time series alignment;

[0068] For example, aligning the motor speed and motor current on the same time axis ensures that data with different sampling frequencies can be analyzed synchronously.

[0069] S1.5: Use abnormal fluctuation detection method to process abnormal values ​​of tire status data.

[0070] For example, detect and eliminate abnormal data where tire pressure drops to zero instantly due to sensor failure.

[0071] S2: Build a health status assessment model to predict the vehicle health status score.

[0072] S2.1: Based on the pre-processed vehicle status data, a dynamic weight allocation mechanism is formulated to dynamically adjust the impact of each vehicle status data on the vehicle health status score according to the importance and real-time status of different health parameters. The expression is:

[0073]

[0074] Among them, w i is the weight of the i-th vehicle state data, and β is a measure of the degree of deviation of the vehicle state data to w i The weight coefficient of influence, x i is the vehicle state data, μ is the mean of the vehicle state data, N is the total number of vehicle state data, and i is the index variable of the vehicle state data.

[0075] It should be noted that through the dynamic weight allocation mechanism, according to the importance of vehicle status data and the degree of real-time deviation, the impact of different data on the health status score is reasonably adjusted to ensure that the scoring results can fully and accurately reflect the overall health status of the vehicle. Avoid excessive interference of single or low-deviation data on the evaluation results, while highlighting the impact of key abnormal data, thereby improving the accuracy and reliability of health status assessment and providing a scientific basis for the formulation of subsequent driving strategies.

[0076] S2.2: Through nonlinear processing, the impact of vehicle data on health status is amplified, and combined with historical fault data and dynamic driving data, a multi-layer penalty mechanism is formulated to comprehensively evaluate the health status of the vehicle, form a health status assessment model, and predict the vehicle health status score. The expression is:

[0077]

[0078] Where S is the vehicle health score, x i is the value of the i-th vehicle status data, C s is the scene adaptability factor, P i is the comprehensive penalty value of the i-th vehicle status data, N is the total number of vehicle status data, i is the index variable for vehicle status data, and y f The value of the fth historical fault data, z j represents the value of the jth dynamic driving state data, Δz j represents the change rate of the jth dynamic driving parameter, ψ is the layer coefficient of the dynamic change rate, M is the total number of dynamic driving data, j is the epitome variable of the dynamic driving data, and λ is the normalization constant;

[0079] The formulation of a multi-layer penalty mechanism includes the following steps:

[0080] According to the hierarchical characteristics of historical vehicle health status assessment and the breadth of abnormal impact range, the penalty is divided into three levels: single parameter penalty, parameter interaction penalty and scenario adaptability penalty;

[0081] Single parameter penalty is based on the degree of abnormal deviation of a single health parameter;

[0082] Parameter interaction penalty considers the correlation between multiple parameters and imposes penalties;

[0083] The scene adaptability penalty is imposed based on the dynamic environment data of the driving field;

[0084] The penalty mechanism at different levels is combined with the driving environment to adjust the penalty effect in real time. The expression is:

[0085]

[0086] Among them, αi is the penalty weight of the i-th vehicle state data, θ is the nonlinear adjustment coefficient of the vehicle state data deviation, and B is the vehicle state data x i and x l The interaction penalty coefficient of Akin, P i is the comprehensive penalty value of the i-th vehicle status data.

[0087] Historical fault data includes failure information of key components such as battery failure, motor overheating, brake failure, tire abnormality, etc. recorded during the long-term operation of the vehicle.

[0088] It should be noted that through nonlinear processing and multi-layer penalty mechanisms, the impact of key vehicle status data on health status can be magnified, and the vehicle health status can be comprehensively evaluated by combining historical fault data and dynamic driving data, effectively reflecting the hidden dangers and real-time status changes in the long-term operation of the vehicle. This process not only improves the accuracy and adaptability of the health status score, but also reduces the interference of short-term extreme data fluctuations on the evaluation, providing a solid guarantee for accurately monitoring the overall operating performance of the vehicle and formulating reasonable driving strategies.

[0089] S3: Dynamically adjust scene detection parameters based on the vehicle health status score.

[0090] S3.1: Based on the abnormal statistical analysis of historical vehicle status data, define the health threshold T1;

[0091] When S ≥ T1, the vehicle is considered to be in good health;

[0092] When S<T1, the vehicle is considered to be in poor health;

[0093] When the vehicle is in good health, maintain normal detection parameters of environmental data;

[0094] When the vehicle is in poor health, the detection sensitivity and frequency of environmental data are improved.

[0095] For example:

[0096] Increase the detection range of potential obstacles ahead (e.g., expand it to 100 meters) and shorten the refresh cycle;

[0097] Strengthen real-time monitoring of close-range dynamic objects (such as objects within 5-10 meters);

[0098] Improve the recognition accuracy of road signs, lane deviations and dynamic traffic signals;

[0099] Enhance the detection capabilities of weather factors (such as rain, fog, crosswind, etc.) and road conditions (such as slippery, waterlogged, etc.);

[0100] S4: Evaluate the scenario risk score based on the environmental data by adjusting the scenario detection parameters and collecting environmental data in real time.

[0101] S4.1: Environmental data includes obstacle distance, current vehicle speed, road curvature, traffic density, and weather conditions;

[0102] S4.2: Evaluate scenario risk scores based on environmental data. The specific steps are as follows:

[0103] By comprehensively analyzing the environmental data collected in real time after the adjusted scene detection parameters, the potential risk level of the driving process in different environments is quantified, and the scene risk score is predicted. The expression is:

[0104]

[0105] Where v is the vehicle speed, ρ is the distance between the vehicle and the obstacle, k is the road curvature, η represents the number of vehicles per unit length of road, γ is the weight coefficient of the number of vehicles per unit length of road, ω is the current weather severity, δ is the weight coefficient of the weather severity, and R e The risk score of the scene the vehicle is currently in, t represents the time variable, and e represents the base of the natural logarithm.

[0106] It should be noted that "ω is the current weather severity" is obtained through a combination of on-board environmental sensors and external data sources. For example, on-board sensors can detect real-time weather data such as rainfall, humidity, temperature, and wind speed. At the same time, combined with weather condition information (such as rain, snow, haze, strong wind, etc.) provided by external data sources (such as meteorological service platforms), the weather conditions are evaluated through quantitative algorithms and a numerical representation reflecting the severity of the weather is generated.

[0107] It should also be noted that by comprehensively analyzing the environmental data collected in real time after the adjusted scene detection parameters, the potential risk level under different environmental conditions during driving is quantified to generate a scene risk score. By combining key factors such as vehicle speed, obstacle distance, road curvature, traffic density and weather severity, the impact of the environment on driving safety is comprehensively evaluated, and the contribution of each factor in the risk score is dynamically adjusted through weight parameters. This process can accurately reflect the risk status in complex driving scenarios, provide a scientific basis for the formulation of active safety strategies, and significantly improve the safety and adaptability of vehicles in complex road conditions and harsh environments.

[0108] S5: Generate the best driving strategy based on the vehicle health status score and scenario risk score, and execute the active safety linkage mechanism.

[0109] S5.1: Based on the vehicle health status score S and the scenario risk score R e, combined in the form of nonlinear weighted coupling to generate a comprehensive driving risk index, expressed as:

[0110]

[0111] Among them, R is the comprehensive driving risk index, a is the weight of controlling the impact of the vehicle health status score S on the comprehensive driving risk index R, and b is the weight of controlling the impact of the vehicle health status score S on the comprehensive risk R;

[0112] It should be noted that the vehicle health status score and scenario risk score are combined through nonlinear weighted coupling to generate a comprehensive driving risk index, which quantifies the overall driving risk level of the vehicle in the current state and environment. By flexibly adjusting the weight ratio of the health status score and the scenario risk score, the impact of different factors on the comprehensive risk can be highlighted according to actual needs, which not only reflects the long-term impact of the vehicle's own health status on driving safety, but also accurately reflects the real-time risks of the external environment. This method effectively overcomes the limitations of single risk analysis, provides a scientific basis for the dynamic formulation of accurate and reliable driving strategies, and significantly improves driving safety and adaptability in complex scenarios.

[0113] S5.2: Define low security risk threshold R1 and high security risk threshold R2 based on historical data statistics;

[0114] When R<R1, the vehicle's current comprehensive driving risk is low, and the vehicle maintains a normal speed;

[0115] When R1≤R<R2, the vehicle's current comprehensive driving risk is at medium risk, the vehicle speed is reduced, the driver is reminded to pay attention to environmental changes, and the low-speed automatic braking, lane keeping assist and blind spot monitoring in the active safety linkage mechanism are activated;

[0116] When R≥R1, the vehicle's current comprehensive driving risk is at high risk, and active safety intervention is taken to forcibly reduce the vehicle speed and activate the active safety linkage mechanism's emergency automatic braking, active obstacle avoidance, ESC and highly sensitive collision avoidance.

[0117] It should be noted that by defining low and high safety risk thresholds based on historical data statistics, the comprehensive driving risk index is divided into three levels: low risk, medium risk and high risk, and corresponding measures are taken for different levels. When the comprehensive risk is at low risk, the vehicle maintains normal operation; when the risk reaches medium risk, the vehicle automatically reduces the speed, reminds the driver to pay attention to environmental changes, and activates active safety functions such as low-speed automatic braking, lane keeping assist and blind spot monitoring; when the risk rises to high risk, the vehicle implements more stringent safety intervention measures, including forced speed reduction, emergency automatic braking, active obstacle avoidance, electronic stability control (ESC) and highly sensitive anti-collision system to maximize the driving safety of the vehicle and passengers.

[0118] The present embodiment also provides a detection system for safe driving of new energy vehicles, including: a data acquisition module, a vehicle health scoring module, a detection parameter adjustment module, a risk assessment module and a strategy generation module; the data acquisition module is used to collect vehicle status data and pre-process the vehicle status data; the vehicle health scoring module is used to build a health status assessment model and predict the vehicle health status score; the detection parameter adjustment module is used to dynamically adjust the scene detection parameters according to the vehicle health status score; the risk assessment module is used to collect environmental data in real time through the adjusted scene detection parameters, and evaluate the scene risk score based on the environmental data; the strategy generation module is used to generate the best driving strategy according to the vehicle health status score and the scene risk score, and execute the active safety linkage mechanism.

[0119] This embodiment also provides a computer device, which is suitable for the detection method of safe driving of new energy vehicles, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute computer-executable instructions to implement the detection method of safe driving of new energy vehicles proposed in the above embodiment.

[0120] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0121] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the detection method for realizing safe driving of new energy vehicles proposed in the above embodiment is implemented; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, referred to as EPROM), programmable read-only memory (Programmable Red-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0122] In summary, the present invention: constructs a health status assessment model, comprehensively analyzes the multi-dimensional status data of the vehicle, and accurately quantifies the health status of the vehicle; dynamically adjusts the environmental detection parameters according to the health status score, improves the detection sensitivity and frequency when the health status is poor, and enhances the adaptability to complex road conditions and bad weather. The present invention realizes the linkage analysis of vehicle health status and scene risks, effectively overcomes the shortcomings of incomplete health assessment and static detection parameters in the prior art, and significantly improves the reliability and adaptability of safe driving of new energy vehicles. It should be noted that the above embodiments are only used to illustrate the technical solution of the present invention and are not limited. Although the present invention is described in detail with reference to the preferred embodiments, ordinary technicians in the field should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention, which should be included in the scope of the claims of the present invention.

Claims

1. A method for detecting safe driving of new energy vehicles, characterized in that: include, Collect vehicle status data and pre-process the vehicle status data; Build a health status assessment model to predict the vehicle health status score; Dynamically adjust scene detection parameters based on vehicle health status scores; Collect environmental data in real time through adjusted scene detection parameters, and evaluate the scene risk score based on the environmental data; Based on the vehicle health status score and scenario risk score, the optimal driving strategy is generated and an active safety linkage mechanism is implemented.

2. The method for detecting safe driving of a new energy vehicle according to claim 1, characterized in that: The vehicle status data includes battery status data, brake status data, motor status data and tire status data.

3. The method for detecting safe driving of a new energy vehicle as claimed in claim 2, characterized in that: The specific steps of preprocessing the vehicle status data are as follows: The battery status data is cleaned and smoothed by outlier filtering and low-pass filtering to remove noise; The normalization method is used to process the brake status data; Synchronize motor state data through time series alignment; The abnormal fluctuation detection method is used to process the abnormal values ​​of tire status data.

4. The method for detecting safe driving of a new energy vehicle as claimed in claim 3, characterized in that: The specific steps of constructing a health status assessment model and predicting a vehicle health status score are as follows: Based on the preprocessed vehicle status data, a dynamic weight allocation mechanism is formulated to dynamically adjust the impact of each vehicle status data on the vehicle health status score according to the importance and real-time status of different health parameters. The expression is: Among them, w i is the weight of the i-th vehicle state data, and β is a measure of the degree of deviation of the vehicle state data to w i The weight coefficient of influence, x i is the vehicle status data, μ is the mean of the vehicle status data, N is the total number of vehicle status data, and i is the index variable of the vehicle status data; Through nonlinear processing, the impact of vehicle data on health status is magnified, and combined with historical fault data and dynamic driving data, a multi-layer penalty mechanism is formulated to comprehensively evaluate the health status of the vehicle, form a health status assessment model, and predict the vehicle health status score. The expression is: Where S is the vehicle health score, x i is the value of the i-th vehicle status data, C s is the scene adaptability factor, P i is the comprehensive penalty value of the i-th vehicle status data, N is the total number of vehicle status data, i is the index variable for vehicle status data, and y f The value of the fth historical fault data, z j represents the value of the jth dynamic driving state data, Δz j represents the change rate of the jth dynamic driving parameter, ψ is the layer coefficient of the dynamic change rate, M is the total number of dynamic driving data, j is the epitome variable of the dynamic driving data, and λ is the normalization constant; The formulation of a multi-layer penalty mechanism includes the following steps: According to the hierarchical characteristics of historical vehicle health status assessment and the breadth of abnormal impact range, the penalty is divided into three levels: single parameter penalty, parameter interaction penalty and scenario adaptability penalty; Single parameter penalty is based on the degree of abnormal deviation of a single health parameter; Parameter interaction penalty considers the correlation between multiple parameters and imposes penalties; The scene adaptability penalty is imposed based on the dynamic environment data of the driving field; Combine different levels of penalty mechanisms with the driving environment and adjust the penalty effect in real time.

5. The method for detecting safe driving of new energy vehicles as claimed in claim 4, characterized in that: The specific steps of dynamically adjusting scene detection parameters according to the vehicle health status score are as follows: Based on the abnormal statistical analysis of historical vehicle status data, a healthy threshold T1 is defined; When S ≥ T1, the vehicle is considered to be in good health; When S<T1, the vehicle is considered to be in poor health; When the vehicle is in good health, maintain normal detection parameters of environmental data; When the vehicle is in poor health, the detection sensitivity and frequency of environmental data are improved.

6. The method for detecting safe driving of a new energy vehicle as claimed in claim 5, characterized in that: The environmental data includes obstacle distance, current vehicle speed, road curvature, traffic density and weather conditions; The specific steps of evaluating the scenario risk score based on environmental data are as follows: By comprehensively analyzing the adjusted scene detection parameters and the real-time collected environmental data, the potential risk level of the driving process in different environments is quantified and the scene risk score is predicted. The expression is: Where v is the vehicle speed, ρ is the distance between the vehicle and the obstacle, k is the road curvature, η represents the number of vehicles per unit length of road, γ is the weight coefficient of the number of vehicles per unit length of road, ω is the current weather severity, δ is the weight coefficient of the weather severity, and R e The risk score of the scene the vehicle is currently in, t represents the time variable, and e represents the base of the natural logarithm.

7. The method for detecting safe driving of a new energy vehicle as claimed in claim 6, characterized in that: The optimal driving strategy is generated according to the vehicle health status score and the scenario risk score, and the active safety linkage mechanism is executed. The specific steps are as follows: Based on the vehicle health status score S and the scenario risk score R e , combined in the form of nonlinear weighted coupling to generate a comprehensive driving risk index, expressed as: Among them, R is the comprehensive driving risk index, a is the weight of controlling the impact of the vehicle health status score S on the comprehensive risk R, and b is the weight of controlling the impact of the vehicle health status score S on the comprehensive driving risk index R; Define low security risk threshold R1 and high security risk threshold R2 based on historical data statistics; When R<R1, the vehicle's current comprehensive driving risk is low, and the vehicle maintains a normal speed; When R1≤R<R2, the vehicle's current comprehensive driving risk is at medium risk, the vehicle speed is reduced, the driver is reminded to pay attention to environmental changes, and the low-speed automatic braking, lane keeping assist and blind spot monitoring in the active safety linkage mechanism are activated; When R≥R1, the vehicle's current comprehensive driving risk is at high risk, and active safety intervention is taken to forcibly reduce the vehicle speed and activate the active safety linkage mechanism's emergency automatic braking, active obstacle avoidance, ESC and highly sensitive collision avoidance.

8. A new energy vehicle safe driving detection system, based on the new energy vehicle safe driving detection method according to any one of claims 1 to 7, characterized in that: Including data collection module, vehicle health scoring module, detection parameter adjustment module, risk assessment module and strategy generation module; A data acquisition module is used to collect vehicle status data and pre-process the vehicle status data; The vehicle health score module is used to build a health status assessment model and predict the vehicle health status score; The detection parameter adjustment module is used to dynamically adjust the scene detection parameters according to the vehicle health status score; A risk assessment module, which is used to collect environmental data in real time through adjusted scene detection parameters and evaluate the scene risk score based on the environmental data; The strategy generation module is used to generate the best driving strategy based on the vehicle health status score and scenario risk score, and implement the active safety linkage mechanism.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method for detecting safe driving of a new energy vehicle according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for detecting safe driving of a new energy vehicle according to any one of claims 1 to 7 are implemented.

Images