New energy vehicle cooperative control fault processing method and system

Abstract

The invention belongs to the technical field of new energy vehicle control, and discloses a new energy vehicle cooperative control fault processing method and system, and the method comprises the steps: obtaining vehicle operation data, environment perception data, driver operation data and driver attention related data; according to the obtained data, the complexity of the driving scene and the cognitive load of the driver are evaluated; fault information output by the cooperative control system is received; selecting an information presentation strategy from a preset strategy library according to the fault information, the complexity of the driving scene and the cognitive load of the driver; the information presentation strategy comprises an information presentation channel, information content details and presentation opportunity; generating fault information according to the selected information presentation strategy, and controlling the man-machine interface equipment to execute information presentation; according to the driving scene complexity and driver cognitive load, the fault information can be clearly and timely transmitted to the driver in a manner of not interfering driving safety, so that the safety risk or the damage to the driving experience caused by improper information transmission is avoided.

Description

Technical Field

[0001] The present application relates to the field of new energy vehicle control technology, and more specifically, to a method and system for handling collaborative control faults of new energy vehicles. Background Art

[0002] The collaborative control system of new energy vehicles is crucial for safe and stable vehicle operation. It coordinates the operation of multiple core subsystems, including the electric drive system, braking system, and energy management system, to achieve the driver's intent or preset driving goals. During vehicle operation, any subsystem in the collaborative control system may malfunction. To address this, collaborative control systems typically incorporate sophisticated fault diagnosis capabilities. When the system detects abnormal fluctuations in data from a subsystem, it initiates an internal fault diagnosis process, using a series of algorithmic analyses and logical judgments to accurately identify the specific fault type.

[0003] Once a fault is diagnosed, the collaborative control system further assesses the potential impact of the fault on vehicle performance and driving safety. Based on the assessment results, the system immediately implements appropriate fault-handling measures, such as limiting the vehicle's maximum power output, adjusting the torque distribution of other normally operating drive motors, disabling some non-critical functions, and even entering a specific performance-limiting "limp home" mode depending on the severity of the fault, to ensure that the vehicle can continue to drive or park in a relatively safe manner after the fault occurs. While the system implements these fault-handling measures, a crucial step is to promptly and accurately convey the fault information and the resulting changes in vehicle status to the driver. This is an indispensable part of ensuring driving safety.

[0004] However, existing technologies have significant shortcomings in presenting fault information. Traditional fault information presentation methods are often overly simplistic and generic, typically limited to lighting a generic fault indicator light on the instrument panel or displaying a general text warning on the central control screen, such as "Powertrain Fault" or "Please Check Vehicle." This simple, general information presentation method fails to meet the needs of complex driving scenarios. After receiving such vague warnings, drivers often cannot clearly understand the specific nature of the fault (for example, is it a motor fault or a battery fault?), the severity of the fault (for example, is it a minor fault or an emergency requiring immediate stopping?), the specific impact of the fault on vehicle performance (for example, how much has the power dropped? Has braking performance been affected?), and the countermeasures that the system has or will take. This lack of transparency can easily lead to confusion, uncertainty, and even anxiety in drivers.

[0005] Furthermore, if the fault occurs at a critical moment requiring intense concentration and precision, such as when the driver is driving at high speed or preparing to change lanes or overtake, then a sudden, ambiguous system prompt, possibly accompanied by a warning sound, can be a significant distraction. Due to the unclear information received, the driver may become nervous and unable to make optimal decisions. They may even panic and take inappropriate emergency actions, such as sudden and sharp braking or steering, which increases the risk of an accident. Even if the fault handling measures implemented by the cooperative control system are smooth at the vehicle dynamics level, the psychological stress response caused by insufficient information can still significantly affect the driver's perception of the vehicle's status and the accuracy of subsequent actions, thereby reducing the overall driving experience and safety.

[0006] Therefore, in the process of new energy vehicle collaborative control systems failing and taking countermeasures, how to break through the limitations of existing technologies in presenting fault information, especially in complex driving scenarios, through an intelligent and adaptive information presentation and human-computer interaction strategy, can clearly, timely and in a way that does not interfere with driving safety convey fault information, vehicle status changes and system response measures to the driver and passengers, thereby reducing the driver's anxiety and uncertainty, and avoiding safety risks or damage to the driving experience due to improper information transmission. This has become a technical problem that needs to be urgently solved in the field of human-computer interaction design of new energy vehicle collaborative control systems.

[0007] In view of the above problems, the existing technology is in urgent need of improvement. Summary of the Invention

[0008] The purpose of this application is to provide a new energy vehicle collaborative control fault handling method and system, which can convey fault information to the driver in a clear, timely and non-interfering manner according to the complexity of the driving scenario and the driver's cognitive load, thereby reducing the driver's anxiety and uncertainty, and avoiding safety risks or damage to the driving experience due to improper information transmission.

[0009] In a first aspect, the present application provides a method for handling faults in a collaborative control system of a new energy vehicle, which is used to present fault information to the driver when a fault occurs in the collaborative control system of the new energy vehicle during vehicle operation. The method comprises the following steps: A1. Acquire vehicle operation data, environmental perception data, driver operation data, and driver attention data; A2. Assess the complexity of the driving scenario and the driver's cognitive load based on acquired vehicle operation data, environmental perception data, driver operation data, and driver attention data. A3. Receive fault information output by the collaborative control system; fault information includes fault type, fault severity, and vehicle performance impact assessment results; A4. Select an information presentation strategy from a preset strategy library based on the fault information, driving scenario complexity, and driver cognitive load. This strategy includes the presentation channel, information content, and presentation timing. A5. Generate fault information based on the selected information presentation strategy and control the human-machine interface device to perform information presentation.

[0010] Preferably, step A1 includes: A101. Read vehicle operating data through the vehicle bus CAN interface; vehicle operating data includes speed, steering angle, and acceleration; A102. Acquire environmental perception data through radar and cameras. Environmental perception data includes the distance to surrounding vehicles, relative speed, and road curvature. A103. Acquire driver operation data through sensors; driver operation data includes throttle opening, brake pressure, and steering torque; A104. Obtain driver attention-related data through image recognition; driver attention-related data includes eye movement data and head posture; A105. Preprocess vehicle operation data, environmental perception data, driver operation data, and driver attention-related data.

[0011] Preferably, step A2 includes: A201. Evaluate vehicle driving stability based on vehicle operating data and obtain a stability index. A202. Evaluate road congestion based on environmental perception data and road type, and obtain a congestion index. A203. Assess the driver's fatigue and distraction levels based on the driver's operating data and driver attention-related data to obtain fatigue and distraction indicators; A204. Calculate the complexity of the driving scenario and the driver's cognitive load by combining the stability index, congestion index, fatigue index, and distraction index.

[0012] Preferably, step A201 includes: Extract vehicle speed sequence, steering angle sequence and acceleration sequence based on vehicle operation data; Calculate the sequence entropy for the vehicle speed sequence, steering angle sequence and acceleration sequence to obtain the vehicle speed sequence entropy, steering angle sequence entropy and acceleration sequence entropy; According to the entropy of vehicle speed sequence, steering angle sequence and acceleration sequence, a weighted fusion algorithm is used to calculate the stability index.

[0013] Preferably, step A202 includes: Determining the road type of the vehicle based on the real-time location of the vehicle; Based on the environmental perception data, extract the surrounding vehicle distance sequence, relative speed sequence, and road curvature sequence; For the surrounding vehicle distance sequence and relative speed sequence, adopt the dynamic time warping algorithm to calculate the distance congestion factor and speed congestion factor; For the road curvature sequence, calculate the curvature change rate, and according to the road type and the curvature change rate, correct the distance congestion factor and speed congestion factor; According to the corrected distance congestion factor and the corrected speed congestion factor, adopt the weighted fusion algorithm to calculate the road congestion degree index.

[0014] Preferably, the step of calculating the curvature change rate for the road curvature sequence and correcting the distance congestion factor and speed congestion factor according to the road type and the curvature change rate includes: According to the road type of the road where the vehicle is located, determine the reference curvature change rate threshold; the road types include highways, urban roads, and rural roads, and different road types correspond to different reference curvature change rate thresholds; For the road curvature sequence, adopt the sliding window algorithm to calculate the curvature change rate sequence; the length of the sliding window is adaptively adjusted according to the vehicle speed, and the higher the vehicle speed, the longer the window length; For the curvature change rate sequence, count the number of curvature change rates greater than the reference curvature change rate threshold to obtain the number of curvature change rates exceeding the threshold; According to the road type and the number of curvature change rates exceeding the threshold, use a piecewise function to correct the distance congestion factor and speed congestion factor; the correction amplitude of highways is less than that of urban roads and rural roads, and the more the number of curvature change rates exceeding the threshold, the greater the correction amplitude.

[0015] Preferably, step A203 includes: Based on the driver operation data, extract the throttle opening sequence, braking pressure sequence, and steering torque sequence, and calculate the mean and variance of each sequence; Based on the driver attention-related data, extract the blink frequency of the eye movement data and the head shake frequency of the head pose data; For the mean and variance of the throttle opening sequence, the mean and variance of the braking pressure sequence, the mean and variance of the steering torque sequence, the blink frequency, and the nod frequency, adopt the preset fuzzy inference rules to calculate the driver fatigue degree index and the driver distraction degree index.

[0016] Preferably, step A204 includes: Normalize the stability index, congestion degree index, fatigue degree index, and distraction degree index; Perform a weighted fusion operation on the difference between 1 and the normalized stationarity index and the normalized congestion degree index to obtain the complexity of the driving scenario; Perform a weighted fusion operation on the normalized fatigue degree index and the normalized distraction degree index to obtain the driver's cognitive load.

[0017] Preferably, step A4 includes: A401. Evaluate the priority of the fault information according to the fault type, fault severity, and vehicle performance impact assessment results; A402. Evaluate the risk level of the driving scenario according to the complexity of the driving scenario; A403. Determine the urgency of information presentation according to the priority of the fault information and the risk level of the driving scenario; A404. Select an information presentation strategy from the preset strategy library according to the urgency of information presentation and the driver's cognitive load; the information presentation strategy includes the information presentation channel, the detail level of the information content, and the presentation timing.

[0018] In a second aspect, the present application provides a new energy vehicle collaborative control fault handling system, which is used to present fault information to the driver when a fault occurs during the operation of the new energy vehicle collaborative control system. The system includes: A data acquisition module, which is used to acquire vehicle operation data, environment perception data, driver operation data, and driver attention-related data; An evaluation module, which is used to evaluate the complexity of the driving scenario and the driver's cognitive load according to the acquired vehicle operation data, environment perception data, driver operation data, and driver attention-related data; A fault information receiving module, which is used to receive the fault information output by the collaborative control system; the fault information includes the fault type, fault severity, and vehicle performance impact assessment results; A strategy selection module, which is used to select an information presentation strategy from the preset strategy library according to the fault information, the complexity of the driving scenario, and the driver's cognitive load; the information presentation strategy includes the information presentation channel, the detail level of the information content, and the presentation timing; An information presentation module, which is used to generate fault information according to the selected information presentation strategy and control the human-machine interface device to perform information presentation.

[0019] Beneficial effects: A new energy vehicle collaborative control fault handling method and system provided by this application can, by acquiring multi-dimensional data, evaluating the driving scenario and driver state, and combining fault information, intelligently select an appropriate information presentation strategy, thereby solving the problem in the prior art that the fault information presentation method is simple and general and difficult to meet the requirements in complex driving scenarios. It can convey fault information to the driver in a clear, timely and non-interfering manner with driving safety according to the complexity of the driving scenario and the driver's cognitive load, thereby reducing the driver's anxiety and uncertainty and avoiding safety risks or damage to the riding experience caused by improper information transmission. Description of the Drawings

[0020] Figure 1 It is a flowchart of the new energy vehicle collaborative control fault handling method provided by an embodiment of this application.

[0021] Figure 2 It is a schematic structural diagram of the new energy vehicle collaborative control fault handling system provided by an embodiment of this application.

[0022] Label description: 1. Data acquisition module; 2. Evaluation module; 3. Fault information receiving module; 4. Strategy selection module; 5. Information presentation module. Detailed Embodiments

[0023] Next, the technical solutions in this application will be clearly and completely described in conjunction with the drawings in this application. Obviously, the described embodiments are only a part of the embodiments of this application, rather than all the embodiments. Usually, the components of this application described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the drawings is not intended to limit the scope of this application that is required to be protected, but only represents the selected embodiments of this application. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of protection of this application.

[0024] It should be noted that: Similar reference numerals and letters indicate similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. At the same time, in the description of this application, terms such as "first" and "second" are only used for distinguishing descriptions and cannot be understood as indicating or implying relative importance.

[0025] Refer to Figure 1 , this application proposes a new energy vehicle collaborative control fault handling method for presenting fault information to the driver when a fault occurs during the operation of a new energy vehicle collaborative control system. The steps of this method include: A1. Obtain vehicle operation data, environmental perception data, driver operation data, and driver attention-related data; A2. Evaluate the complexity of the driving scenario and the driver's cognitive load based on the obtained vehicle operation data, environmental perception data, driver operation data, and driver attention-related data; A3. Receive the fault information output by the cooperative control system; the fault information includes the fault type, fault severity, and vehicle performance impact assessment result; A4. Select an information presentation strategy from a preset strategy library according to the fault information, driving scenario complexity, and driver cognitive load; the information presentation strategy includes the information presentation channel, information content detail level, and presentation timing; A5. Generate fault information according to the selected information presentation strategy, and control the human-machine interface device to perform information presentation.

[0026] Among them, vehicle operation data refers to the data reflecting the current motion state of the vehicle, which is used to evaluate the driving smoothness of the vehicle. Environmental perception data refers to the data reflecting the state of the vehicle's surrounding environment, which is used to evaluate the road congestion degree. Driver operation data refers to the data reflecting the driver's control operations on the vehicle, which is used to evaluate the driver's fatigue degree and distraction degree. Driver attention-related data refers to the data reflecting the driver's attention state, which is used to evaluate the driver's fatigue degree and distraction degree.

[0027] Among them, the complexity of the driving scenario refers to the degree of occupation of the driver's attention and potential risks in the current driving environment, which is used to determine the urgency of information presentation. The driver's cognitive load refers to the mental burden of the driver in processing information currently, which is used to select the information presentation strategy.

[0028] Among them, fault information refers to the details of the faults diagnosed by the cooperative control system, which is used to evaluate the priority of the fault information.

[0029] Among them, the preset strategy library refers to a collection storing multiple information presentation schemes, which can specifically include different combinations of information presentation channels, information content detail levels, and presentation timings, and is used to select a suitable presentation method according to the situation. The information presentation strategy refers to the specific scheme for determining how to convey the fault information to the driver, which is used to guide the generation and presentation of the fault information. The information presentation channel refers to the medium for transmitting the fault information, which can specifically be implemented by one or more of visual, auditory, tactile, etc. methods, and is used to select the most effective communication channel according to the situation. The information content detail level refers to the degree of detail of the fault information conveyed, which can specifically be implemented by means such as concise prompts or detailed explanations, and is used to adjust the amount of information according to the driver's state and the complexity of the scenario. The presentation timing refers to the time point for displaying or informing the driver of the fault information, which can specifically be implemented by means such as immediate prompts or delayed prompts, and is used to avoid disturbing the driver at critical moments.

[0030] Among them, the human-machine interface device refers to the hardware in a vehicle used for information interaction with the driver. Specifically, it can be implemented by one or more of an instrument panel, a central control screen, a speaker, a steering wheel vibrator, etc., and is used to execute a selected information presentation strategy.

[0031] The core innovation of this application lies in adaptively selecting an information presentation strategy from a preset strategy library according to the fault information, the complexity of the driving scenario, and the driver's cognitive load, including the information presentation channel, the detail level of the information content, and the presentation timing, so as to realize the intelligent and contextual presentation of fault information.

[0032] This method provides a basis for subsequent evaluation and decision-making by obtaining vehicle operation data, environmental perception data, driver operation data, and driver attention-related data. These data reflect the current dynamic state of the vehicle, the external environmental conditions, as well as the real-time behavior and physiological state of the driver.

[0033] Furthermore, based on these multi-dimensional data obtained, the complexity of the current driving scenario and the driver's cognitive load are evaluated. The evaluation of the driving scenario complexity reflects the potential occupation of the driver's attention by the current environment and the difficulty of the driving task; the evaluation of the driver's cognitive load reflects the driver's current information processing ability and state. These evaluation results provide a key basis for judging when and how to present information to the driver, aiming to avoid interference when the driver is not suitable for receiving information.

[0034] At the same time, the fault information output by the cooperative control system is received. This fault information includes the fault type, the fault severity, and the evaluation result of the impact of the fault on the vehicle performance. These detailed fault information are the basis for determining the specific content to be conveyed to the driver and the urgency of this information.

[0035] Therefore, according to the received fault information, the evaluated driving scenario complexity, and the driver's cognitive load, the most suitable information presentation strategy for the current situation is selected from the preset strategy library. This strategy library contains multiple information presentation schemes, and each scheme defines the information presentation channel (such as visual, auditory, tactile), the detail level of the information content, and the information presentation timing. The process of strategy selection is an adaptive decision based on the current situation, aiming to ensure the effectiveness and safety of information transmission.

[0036] Finally, according to the selected information presentation strategy, specific fault information content is generated, and the human-machine interface device is controlled to perform information presentation. The human-machine interface device can include an instrument panel, a central control screen, a speaker, a steering wheel vibrator, etc. By controlling these devices, the generated fault information is presented to the driver in a selected channel, level of detail, and timing, so as to achieve the safe and clear transmission of fault information. The whole process forms a closed loop, enabling the presentation of fault information to dynamically adapt to the vehicle running state, environmental conditions, and driver state.

[0037] Through the above solution, this application solves the problem that when a fault occurs in the new energy vehicle collaborative control system, the existing fault information presentation method is fuzzy and non-adaptive in the prior art, resulting in driver confusion, distraction, and even improper operations, thus affecting driving safety and experience. This solution realizes the adaptive presentation of fault information by comprehensively considering fault characteristics, driving scenarios, and driver states, improving the clarity and effectiveness of information transmission. As a result, the driver can more accurately understand the vehicle state and the impact of faults, reducing uncertainty and anxiety. At the same time, by selecting appropriate presentation channels, levels of detail, and timing, the interference of fault prompts on the driver's attention is reduced, avoiding driving risks caused by improper information transmission, and enhancing driving safety and user experience.

[0038] Specifically, step A1 includes: A101. Read vehicle operation data through the vehicle bus CAN interface; the vehicle operation data includes vehicle speed, steering angle, and acceleration; A102. Obtain environmental perception data through radar and cameras; the environmental perception data includes the distance to surrounding vehicles, relative speed, and road curvature; A103. Obtain driver operation data through sensors; the driver operation data includes throttle opening, braking pressure, and steering torque; A104. Obtain driver attention-related data through image recognition; the driver attention-related data includes eye movement data and head posture; A105. Preprocess the vehicle operation data, environmental perception data, driver operation data, and driver attention-related data.

[0039] Among them, the vehicle operation data includes vehicle speed, steering angle, and acceleration. These data reflect the dynamic state of the vehicle itself and provide input for evaluating the driving smoothness of the vehicle.

[0040] Among them, the environmental perception data includes the distance to surrounding vehicles, relative speed, and road curvature. These data are used to perceive the external environment of the vehicle and provide a basis for evaluating road congestion and road type. For example, radar can provide the distance to and relative speed of surrounding vehicles, and cameras can identify road markings and calculate road curvature.

[0041] Driver operation data includes throttle opening, brake pressure, and steering torque. These data directly reflect the driver's control input to the vehicle and provide input for assessing driver fatigue and distraction. These data can be measured by sensors built into the collaborative control system.

[0042] Driver attention data includes eye movement data and head posture. These data reflect the driver's physiological and behavioral state, providing evidence for assessing driver fatigue and distraction. For example, eye movement data can include blink frequency and gaze direction, while head posture can include the head's pitch and yaw angles relative to the vehicle. This driver attention data can be obtained by capturing images of the driver using the vehicle's in-car camera and then using existing image recognition technology.

[0043] The four types of data acquired are preprocessed. This can include data cleaning, such as removing noise and outliers; data synchronization, such as time-aligning data collected by different sensors; and data format conversion, such as converting raw data to a unified format. This ensures the usability of the data input into the subsequent evaluation module.

[0044] The vehicle operation data, environmental perception data, driver operation data, and driver attention data obtained through the above steps provide the foundation for subsequent assessments of driving scenario complexity and driver cognitive load. Comprehensive data acquisition and preprocessing ensure that the assessment process is based on high-quality data, thereby supporting the selection of subsequent information presentation strategies and addressing issues such as inadequate or unavailable data that may lead to inappropriate information presentation.

[0045] In some embodiments, step A2 comprises: A201. Evaluate vehicle driving stability based on vehicle operating data and obtain a stability index. A202. Evaluate road congestion based on environmental perception data and road type, and obtain a congestion index. A203. Assess the driver's fatigue and distraction levels based on the driver's operating data and driver attention-related data to obtain fatigue and distraction indicators; A204. Calculate the complexity of the driving scenario and the driver's cognitive load by combining the stability index, congestion index, fatigue index, and distraction index.

[0046] Among them, this solution proposes specific evaluation steps for how to evaluate the complexity of driving scenarios and the cognitive load of drivers.

[0047] First, through step A201, the driving smoothness of the vehicle is evaluated based on the vehicle operation data to obtain a smoothness index. The driving smoothness of the vehicle reflects the current driving environment and the state of driving operations. For example, in complex road conditions or during emergency obstacle avoidance, the vehicle will show instability during driving. By evaluating the smoothness, the state of the driving scenario can be reflected.

[0048] Next, through step A202, the road congestion level is evaluated based on the environmental perception data and road type to obtain a congestion level index. The road congestion level is a factor affecting the state of the driving scenario. Congested road conditions require the driver to devote more attention and energy. By evaluating the congestion level, the state of the driving scenario can be directly quantified.

[0049] Then, through step A203, the fatigue level and distraction level of the driver are evaluated based on the driver operation data and driver attention-related data to obtain a fatigue level index and a distraction level index. The fatigue and distraction states of the driver himself determine his current cognitive load level. Fatigue or distraction will reduce the driver's ability to process information and respond to emergencies. By evaluating these indexes, the driver's cognitive load can be reflected.

[0050] Finally, through step A204, by integrating the smoothness index, congestion level index, fatigue level index, and distraction level index obtained in steps A201 to A203, the complexity of the driving scenario and the driver's cognitive load are calculated. This comprehensive evaluation method can consider the factors of the vehicle, environment, and driver, so as to obtain evaluation results of the complexity of the driving scenario and the driver's cognitive load that conform to the actual situation. These evaluation results provide a basis for selecting an information presentation strategy according to these factors in the follow-up, enabling the system to adjust the information presentation method according to the actual situation, avoiding distracting the driver's attention in complex scenarios or high-load states, and improving the effectiveness and safety of the presentation of fault information.

[0051] By applying this evaluation method to the fault information presentation process, the system can dynamically adjust the presentation method, content, and timing of the fault information according to the driver's current cognitive state and the complexity of the driving environment, so as to ensure the effective transmission of information while reducing the interference to the driver's attention, avoiding causing improper operations or safety risks, and solving the problem of inadaptability of information presentation caused by insufficient evaluation in the prior art.

[0052] Preferably, step A201 may include: Based on the vehicle operation data, extract the vehicle speed sequence, steering angle sequence, and acceleration sequence; For the vehicle speed sequence, steering angle sequence, and acceleration sequence, calculate the sequence entropy to obtain the vehicle speed sequence entropy, steering angle sequence entropy, and acceleration sequence entropy; According to the speed sequence entropy, steering angle sequence entropy, and acceleration sequence entropy, a weighted fusion algorithm is used to calculate the ride smoothness index.

[0053] Among them, the speed sequence, steering angle sequence, and acceleration sequence are extracted. The length of the sequence can be set according to actual needs, can be set to a fixed value, or the sequence length can be adaptively adjusted according to the vehicle speed.

[0054] Furthermore, sequence entropy is an index to measure the complexity or uncertainty of a sequence. The Shannon entropy algorithm can be used to calculate the sequence entropy, and this algorithm requires discretization of the sequence data. Discretization can divide the continuous numerical range into several intervals (i.e., "bins"), and then count the frequency of data points appearing in each interval. The number and width of the bins can be preset or dynamically determined according to the distribution characteristics of the sequence data (the Shannon entropy algorithm is a prior art, and its calculation process is not detailed here). The calculated speed sequence entropy, steering angle sequence entropy, and acceleration sequence entropy respectively reflect the ride smoothness of the vehicle in terms of longitudinal speed change, lateral steering operation, and longitudinal acceleration and deceleration. A lower sequence entropy value indicates that the corresponding parameter changes gently and the ride smoothness is better; a higher sequence entropy value indicates that the corresponding parameter changes violently and the ride smoothness is worse.

[0055] Thus, the three sequence entropy values are linearly combined through a weighted fusion algorithm, and each entropy value is assigned a weight. These weights can be fixed values (for example, the weight of the speed sequence entropy can be set to 0.4, the weight of the steering angle sequence entropy can be set to 0.3, and the weight of the acceleration sequence entropy can be set to 0.3), or can be dynamically adjusted according to the current driving state or scenario (for example, when the vehicle is driving straight, the weights of the speed and acceleration can be increased; when the vehicle is turning, the weight of the steering angle can be increased). Through weighted fusion, the ride smoothness information from different dimensions is integrated into a single ride smoothness index. This ride smoothness index is used to evaluate the complexity of the driving scenario and the driver's cognitive load in the subsequent steps. By providing a more comprehensive and multi-dimensional quantification result of ride smoothness, this ride smoothness index provides a more refined input for the subsequent evaluation steps, thus helping to improve the accuracy of the evaluation of the driving scenario and the driver's state.

[0056] Preferably, step A202 may include: Determine the road type of the road where the vehicle is located according to the real-time position of the vehicle; Based on the environmental perception data, extract the surrounding vehicle distance sequence, relative speed sequence, and road curvature sequence; For the surrounding vehicle distance sequence and relative speed sequence, use the dynamic time warping algorithm to calculate the distance congestion factor and speed congestion factor; For the road curvature sequence, calculate the curvature change rate, and correct the distance congestion factor and speed congestion factor according to the road type and the curvature change rate; According to the corrected distance congestion factor and the corrected speed congestion factor, use a weighted fusion algorithm to calculate the road congestion degree index.

[0057] Among them, this solution provides a specific method for evaluating the road congestion degree index, aiming to more comprehensively and accurately reflect the complexity of the actual driving scenario, so as to provide a more reliable basis for the subsequent selection of the fault information presentation strategy.

[0058] First, determine the road type of the road where the vehicle is located according to the real-time position of the vehicle. This can be achieved by combining the vehicle's global positioning system data with the pre-installed digital map database. Different types of road environments have a significant impact on the driver's cognitive load and driving complexity. Distinguishing the road type is the basis for more refined congestion assessment.

[0059] Next, based on the environmental perception data, extract the surrounding vehicle distance sequence, relative speed sequence, and road curvature sequence. These sequence data contain key information reflecting the current traffic conditions (surrounding vehicles) and road geometric features (road curvature), which are the basic inputs required for evaluating the congestion degree. The length of the extracted sequence can be adjusted according to actual needs.

[0060] Then, for the surrounding vehicle distance sequence and relative speed sequence, the dynamic time warping (DWT) algorithm is adopted to calculate the distance congestion factor and speed congestion factor. Using the dynamic time warping algorithm to process sequence data can more effectively capture the dynamic characteristics of the distances and relative speeds of surrounding vehicles over time, such as the distance and speed change patterns during vehicle platooning or following, so as to calculate the distance congestion factor and speed congestion factor that can better reflect the interaction between vehicles and traffic fluency, overcoming the limitations of simple instantaneous value or average value evaluation. The dynamic time warping algorithm calculates the similarity or distance between two time series by finding the optimal matching path between them, even if they are offset or stretched on the time axis, thus more accurately evaluating the congestion dynamics based on vehicle spacing and relative speed. The DTW algorithm can be used to calculate the similarity or distance between the current sequence and a preset reference sequence representing different congestion states (e.g., free flow, congestion), and map this similarity or distance to a congestion factor; for example, for the surrounding vehicle distance sequence and relative speed sequence respectively, using the Euclidean distance as a metric, applying the dynamic time warping algorithm with Sakoe-Chiba window constraints, calculate the DTW distance between the current sequence and multiple preset reference sequences of urban arterial road congestion representing different congestion degrees (reference surrounding vehicle distance sequences or reference relative speed sequences with different congestion degrees), and map these DTW distances to the distance congestion factor or speed congestion factor (for example, taking the sum of the reciprocals of each DTW distance as the distance congestion factor or speed congestion factor).

[0061] Furthermore, for the road curvature sequence, calculate the curvature change rate, and based on the road type and the curvature change rate, correct the distance congestion factor and the speed congestion factor. This step is the key of this solution, which incorporates the geometric complexity of the road itself into the congestion assessment. The road curvature change rate reflects the degree of road curvature and driving difficulty. The curvature change rate can be obtained, for example, by calculating the difference between adjacent points in the curvature sequence or the amplitude of curvature change within a sliding window. By calculating the curvature change rate and combining the previously determined road type, correct the congestion factors calculated only based on vehicle spacing and speed, so that the assessment of congestion degree not only considers traffic flow, but also takes into account the characteristics of the road itself and the driving experience under different road types. For example, on a section with large curvature changes, even if there are not many vehicles, the driving difficulty and "congestion feeling" felt by the driver may increase, and the correction can more accurately reflect this complexity. This correction mechanism enables the congestion degree index to be closer to the actual feelings of the driver in a specific road environment, thus more accurately reflecting the complexity of the driving scenario. This corrected congestion degree index, together with other indexes such as vehicle driving smoothness, driver fatigue degree and distraction degree, is used to comprehensively calculate the complexity of the driving scenario and the driver's cognitive load. This more accurate congestion assessment as input makes the assessment of the overall driving scenario complexity more precise, and then can more effectively guide the selection of subsequent fault information presentation strategies to ensure that the most appropriate information is provided to the driver in driving environments with different levels of complexity.

[0062] Finally, based on the corrected distance congestion factor and the corrected speed congestion factor, use a weighted fusion algorithm to calculate the road congestion degree index. By weighted fusion of the distance and speed congestion information corrected by road type and curvature change rate, comprehensively consider the impacts of traffic flow, road geometric complexity and road type, and finally obtain an index that more comprehensively and accurately reflects the current road congestion degree, providing a more accurate input for subsequent assessment of the driving scenario complexity. The weighted fusion algorithm can combine the two corrected factors according to the preset weights to generate the final congestion degree index.

[0063] Through the above technical solution, this application can more comprehensively evaluate the road congestion degree, taking into account the impacts of the geometric characteristics of the road itself and road type on driving complexity, and overcoming the limitations of evaluating congestion only based on vehicle spacing and speed. Thus, the obtained congestion degree index can more accurately reflect the complexity of the actual driving scenario, providing a more reliable input for subsequent assessment of the driving scenario complexity, and further supporting the system to select more appropriate fault information presentation strategies in complex and changeable driving environments, improving the effectiveness of information presentation and driving safety.

[0064] In some preferred embodiments, the steps of calculating the curvature change rate for the road curvature sequence and correcting the distance congestion factor and the speed congestion factor according to the road type and the curvature change rate include: Determine a reference curvature change rate threshold according to the road type of the road where the vehicle is located; the road types include highways, urban roads, and rural roads, and different road types correspond to different reference curvature change rate thresholds; For the road curvature sequence, use a sliding window algorithm to calculate the curvature change rate sequence; the length of the sliding window is adaptively adjusted according to the vehicle speed, and the higher the vehicle speed, the longer the window length; For the curvature change rate sequence, count the number of curvature change rates greater than the reference curvature change rate threshold to obtain the number of curvature change rates exceeding the threshold; According to the road type and the number of curvature change rates exceeding the threshold, use a piecewise function to correct the distance congestion factor and the speed congestion factor; the correction amplitude for highways is less than that for urban roads and rural roads, and the more the number of curvature change rates exceeding the threshold, the greater the correction amplitude.

[0065] Among them, a reference curvature change rate threshold is set according to the road type determined by the current position of the vehicle. For example, a relatively high threshold can be set for highways, indicating that highways have a higher tolerance for curvature changes; a medium threshold can be set for urban roads; and a lower threshold can be set for rural roads, indicating that the change in the degree of curvature of rural roads is more likely to be perceived as an increase in driving difficulty. These thresholds can be preset based on actual driving data or expert experience and form a query table, and the reference curvature change rate threshold can be obtained by querying this query table according to the actual road type.

[0066] Furthermore, obtain the road curvature sequence within a period of time and use the sliding window algorithm to calculate the curvature change rate sequence. The length of the sliding window is not fixed but is adjusted according to the real-time speed of the vehicle. For example, when the vehicle speed is not greater than the first preset speed V1, the window length is set to L1; when the vehicle speed is greater than the second preset speed V2, the window length is L3; when the vehicle speed is between the first preset speed V1 and the second preset speed V2, the window length is L2; V1 < V2, L1 < L2 < L3, and each preset speed and window length can be set according to actual needs. This adaptive adjustment reflects that when driving at high speed, the driver needs a longer distance to perceive and respond to the road geometry changes ahead, so the curvature changes in a longer section need to be considered. The sliding window moves on the curvature sequence, calculates the change rate of the curvature within the window, and forms a curvature change rate sequence.

[0067] Therefore, for the calculated curvature change rate sequence, count the number of points whose values are greater than the previously determined benchmark curvature change rate threshold. This number is the number of curvature change rates exceeding the threshold, which quantifies the "severity" or "frequency" of the change in the road geometry at the current speed on the current road section. The more the number of points exceeding the threshold, the more significant the curve or curvature change on this road section.

[0068] Finally, using the road type and the statistically obtained number of curvature change rates exceeding the threshold, correct the previously calculated distance congestion factor and speed congestion factor through a piecewise function. The piecewise function can define different correction rules. For example, for highways, regardless of the number of points exceeding the threshold, the correction amplitude is relatively small; for urban roads and rural roads, the correction amplitude is large, and as the number of curvature change rates exceeding the threshold increases, the correction amplitude increases non-linearly (e.g., step-shaped or piecewise linear); the specific piecewise function can be set according to actual needs and is not limited here. This correction method superimposes the additional influence of the road geometry on the driving difficulty and congestion perception onto the congestion factors calculated based on the vehicle spacing and speed, making the congestion assessment result better reflect the actual driving experience.

[0069] Through this correction method that combines road type, speed adaptive window, and quantification of geometric complexity, the accuracy of road congestion degree assessment is improved, providing a more reliable basis for the subsequent calculation of the complexity of driving scenarios.

[0070] Preferably, step A203 may include: Based on the driver operation data, extract the throttle opening sequence, braking pressure sequence, and steering torque sequence, and calculate the mean and variance of each sequence; Based on the driver attention-related data, extract the blink frequency of the eye movement data and the head shake frequency of the head pose data; For the mean and variance of the throttle opening sequence, the mean and variance of the braking pressure sequence, the mean and variance of the steering torque sequence, the blink frequency, and the nod frequency, adopt the preset fuzzy inference rules to calculate the driver fatigue degree index and the driver distraction degree index.

[0071] Among them, this method provides a specific implementation for the link of evaluating the driver fatigue degree and distraction degree.

[0072] First, based on the driver operation data, sequences of throttle opening, braking pressure, and steering torque are extracted. The throttle opening sequence reflects the control input of the driver's intention to accelerate or decelerate the vehicle. The braking pressure sequence reflects the control input of the driver's intention to decelerate or stop the vehicle. The steering torque sequence reflects the driver's input for controlling the vehicle direction. Means and variances are calculated for these sequences. The mean reflects the average level or trend of the operation, such as the average throttle opening or average steering torque. The variance reflects the volatility or smoothness of the operation. For example, the more uneven the operation, the larger the variance. Thus, the original operation data is transformed into quantified statistical features that can characterize the driver's behavior pattern when controlling the vehicle.

[0073] Furthermore, based on the driver attention-related data, the blink frequency of eye movement data and the head shake frequency of head pose data are extracted. The eye movement data and head pose data are obtained through image recognition. The blink frequency is the number of times the driver blinks per unit time, and an abnormal blink pattern is associated with a fatigue state. The head pose data reflects the orientation and movement of the driver's head, and the head shake frequency is the number of times the head shakes per unit time. Frequent or abnormal head movements are associated with a distracted state. Extracting these specific frequency metrics can directly obtain the behavioral characteristics related to the driver's physiological state and attention.

[0074] Specifically, the extracted feature values are used as the input of a fuzzy inference system. The fuzzy inference system contains a preset fuzzy rule base, which is established based on expert knowledge or training data and is used to describe the relationship between the input features and the fatigue level and distraction level. For example, a rule could be "If the blink frequency is high and the variance of the steering torque is large, then the fatigue level is high". Through the processes of fuzzification, fuzzy inference, and defuzzification, these multi-source and potentially uncertain input features are integrated to output quantified driver fatigue level metrics and driver distraction level metrics. This method can handle the complex relationships and uncertainties among the input features and provide a comprehensive evaluation result.

[0075] Through the above technical solution, the present application solves the problems in the prior art that the methods for evaluating driver fatigue and distraction are not clear, and the evaluation results may be inaccurate or unstable. By extracting the means and variances of the throttle opening, braking pressure, and steering torque, as well as the blink frequency and head shaking frequency, etc., which are closely related to the driver's state, from the driver operation data and attention-related data, and using these multi-source heterogeneous features as inputs. Thus, by using fuzzy inference rules to comprehensively analyze and judge these features, it is possible to simulate the fuzzy judgment process of humans for complex situations and handle the uncertainties and non-linear relationships in the data. This method based on multi-feature fusion and fuzzy inference can more comprehensively and robustly evaluate the fatigue level and distraction level of the driver, and obtain more reliable fatigue level indicators and distraction level indicators. The improvement in the accuracy of the evaluation results directly enhances the reliability of the subsequent calculation of the driver's cognitive load, and further supports the system to more accurately select the information presentation strategy. This helps to avoid presenting too much information to increase the burden when the driver is in a poor state, or insufficient information to affect understanding when the state is good, thereby improving the adaptability and effectiveness of the fault information presentation and enhancing the safety and user experience of the human-machine interaction.

[0076] Preferably, step A204 may include: Normalize the smoothness index, congestion degree index, fatigue degree index, and distraction degree index; Perform a weighted fusion operation on the difference between 1 and the normalized smoothness index and the normalized congestion degree index to obtain the driving scenario complexity; Perform a weighted fusion operation on the normalized fatigue degree index and the normalized distraction degree index to obtain the driver's cognitive load.

[0077] Among them, for the problem of how to comprehensively calculate the driving scenario complexity and the driver's cognitive load based on the smoothness index, congestion degree index, fatigue degree index, and distraction degree index, the present solution proposes a specific calculation method.

[0078] First, normalize the smoothness index, congestion degree index, fatigue degree index, and distraction degree index. Normalization is to convert the values of different indicators to a unified scale, for example, map all indicator values to the range of 0 to 1. As a preferred implementation, the min-max normalization method can be used. Subtract the historical minimum value of each indicator from its current value, and then divide by the difference between its historical maximum value and minimum value to obtain the normalized value between 0 and 1. Thus, the differences in the numerical range or dimension of different indicators are eliminated, making the subsequent comprehensive calculation more reasonable.

[0079] Next, when calculating the complexity of the driving scenario, a weighted fusion operation is adopted for the difference between 1 and the normalized smoothness index and the normalized congestion degree index. The smoothness index reflects the stability of vehicle driving. The higher the smoothness index value, the smoother the driving. Using "the difference between 1 and the normalized smoothness index" indicates lower smoothness. The larger this difference, the more unstable the vehicle driving, and the higher the complexity of the driving scenario. The normalized congestion degree index directly reflects the road congestion degree. The higher the congestion degree, the higher the complexity of the driving scenario. By performing weighted fusion on these two, for example, using the method of linear weighted summation, the influence of the vehicle's own driving state (smoothness) and the external traffic environment (congestion degree) on the complexity of the driving scenario can be comprehensively considered. For example, the complexity of the driving scenario can be calculated as W1*(1 - normalized smoothness index) + W2*normalized congestion degree index, where W1 and W2 are weight coefficients, which can be calibrated according to actual driving data or determined through expert experience. Weighted fusion allows different weights to be assigned to the two according to the actual situation, making the calculation result more in line with the reality.

[0080] Finally, when calculating the driver's cognitive load, a weighted fusion operation is adopted for the normalized fatigue degree index and the normalized distraction degree index. The normalized fatigue degree index reflects the driver's physiological fatigue state. The higher the fatigue degree, the higher the cognitive load. The normalized distraction degree index reflects the degree of the driver's attention dispersion. The higher the distraction degree, the higher the cognitive load. By performing weighted fusion on these two, for example, using the method of linear weighted summation, the influence of the driver's current physiological and psychological states on their cognitive ability can be comprehensively evaluated. For example, the driver's cognitive load can be calculated as W3*normalized fatigue degree index + W4*normalized distraction degree index, where W3 and W4 are weight coefficients, which can be calibrated according to actual driving data or determined through expert experience. Weighted fusion also allows different weights to be assigned to the two according to the actual situation, making the calculation result more accurately reflect the driver's current cognitive load level.

[0081] Through the above technical solution, the present application eliminates the differences in dimension and numerical range among different indicators, making the stability indicator, congestion degree indicator, fatigue degree indicator, and distraction degree indicator comparable. By performing weighted fusion on the difference between 1 and the normalized stability indicator and the normalized congestion degree indicator, the influence of the vehicle driving state and the external traffic environment on the complexity of the driving scenario can be comprehensively considered, and an evaluation result reflecting the complexity of the driving scenario can be obtained. By performing weighted fusion on the normalized fatigue degree indicator and the normalized distraction degree indicator, the influence of the driver's physiological and psychological states on the cognitive load can be comprehensively reflected, and an evaluation result reflecting the driver's cognitive load can be obtained. Thus, more accurate and stable evaluation results of the driving scenario complexity and the driver's cognitive load can be obtained compared to directly using the original indicators, providing a reliable basis for the selection of subsequent information presentation strategies.

[0082] In some embodiments, step A4 includes: A401. Evaluate the priority of the fault information according to the fault type, fault severity, and vehicle performance impact evaluation result; A402. Evaluate the risk level of the driving scenario according to the complexity of the driving scenario; A403. Determine the urgency of information presentation according to the priority of the fault information and the risk level of the driving scenario; A404. Select an information presentation strategy from a preset strategy library according to the urgency of information presentation and the driver's cognitive load; the information presentation strategy includes the information presentation channel, the detail level of the information content, and the presentation timing.

[0083] Among them, in step A401, the received fault information is processed to convert the inherent attributes of the fault and its impact on vehicle functions into a priority value. For example, a fault affecting the braking function is usually assigned a higher priority than a fault affecting the air conditioning function. The fault type can include motor faults, battery faults, braking system faults, etc. The fault severity can be divided into levels such as minor, medium, severe, etc. The vehicle performance impact evaluation result can quantify the impact of the fault on aspects such as power output, battery life, braking performance, etc. By comprehensively considering these factors, a priority indicator reflecting the importance of the fault can be obtained. As a preferred embodiment, a look-up table method or a rule-based reasoning method can be used to determine the priority. For example, define a rule set: if the fault type is a braking system fault and the severity is severe, the priority is the highest; if the fault type is a battery fault and the vehicle performance impact evaluation result shows a significant decrease in battery life, the priority is high.

[0084] Further, in step A402, based on the already evaluated driving scenario complexity, this step correlates the complexity with potential driving risks. For example, the driving scenario complexity on a congested urban road section may be very high, but due to the low vehicle speed, its risk level may be lower than that of driving at a high speed on a highway, even if the highway scenario complexity (such as traffic flow) is similar. The risk level can reflect the potential challenges of the current driving environment to the driver's safe operation. The evaluation can be based on a preset risk model that maps different driving scenario complexities to different risk levels. For example, the complexity is divided into low, medium, and high, corresponding to low, medium, and high risk levels. Alternatively, the risk level can be dynamically calculated according to specific environmental perception data (such as the density of surrounding vehicles, relative speed, road curvature change rate) and vehicle operation data (such as vehicle speed). For example, when the vehicle speed is higher than a certain threshold and the density of surrounding vehicles is high, the risk level is evaluated as high.

[0085] Thus, in step A403, the urgency of the fault itself and the danger of the current driving environment are comprehensively considered. A high-priority fault may need to be presented immediately in a low-risk scenario, while in a high-risk scenario, it may need to be delayed or presented in a more cautious manner. Conversely, a low-priority fault may not need to be presented immediately even in a low-risk scenario. The urgency of information presentation reflects the urgency of the system to convey fault information to the driver. The determination of this urgency can be achieved through a two-dimensional look-up table or a decision matrix, where one dimension is the priority of the fault information and the other dimension is the risk level of the driving scenario, and the cells of the table or matrix store the corresponding information presentation urgency values. For example, when the priority of the fault information is high and the risk level of the driving scenario is low, the urgency of information presentation is determined to be the highest; when the priority of the fault information is high and the risk level of the driving scenario is high, the urgency of information presentation may be determined to be medium or low, or it needs to be presented with a delay. In this way, the system can avoid distracting the driver's attention due to information presentation at high-risk moments.

[0086] Specifically, in step A404, according to the urgency of information presentation and the driver's cognitive load, an information presentation strategy is selected from a preset strategy library. After determining the comprehensive urgency of information presentation, in combination with the driver's current cognitive load (which has been evaluated in previous steps), the system selects the most suitable strategy from a preset library containing various information presentation strategies. The strategies in the strategy library can be indexed according to different combinations of the urgency of information presentation and the driver's cognitive load. For example, when the urgency of information presentation is the highest and the driver's cognitive load is low, detailed fault information can be presented simultaneously through multiple channels such as vision, audition, and touch, and presented immediately. When the urgency of information presentation is medium and the driver's cognitive load is high, a brief warning message can be presented only through the visual channel and presented after a delay until the cognitive load decreases. The information presentation channels can include at least one of dashboard display, central control screen display, voice prompt, warning sound, seat vibration, etc. The details of the information content can range from simple warning lights to detailed fault descriptions and recommended operations. The presentation timing can be immediate, delayed for a certain time, or presented under specific conditions (such as when the vehicle speed decreases or the driver's cognitive load decreases). By comprehensively considering the presentation urgency and cognitive load, the system can select a strategy that minimizes interference with the driver's safe operation while ensuring effective information transmission. This step, combined with the steps of evaluating the complexity of the driving scenario and the driver's cognitive load, enables the selection of information presentation strategies to adapt to the dynamically changing driving environment and driver state, so that when a fault occurs, the needs of information transmission and driving safety can be more intelligently balanced.

[0087] Through the above technical solutions, the present application refines the evaluation dimensions of fault information and introduces the priority of fault information; by converting the complexity of the driving scenario into the risk level of the driving scenario, it more directly reflects the impact of the environment on driving safety; by comprehensively considering the priority of fault information and the risk level of the driving scenario, the comprehensive urgency of information presentation is determined, thereby establishing a connection between the urgency of the fault itself and the risk level of the current driving environment; finally, in combination with the driver's cognitive load, the most suitable information presentation strategy is selected from the preset strategy library. Thus, the present application can select information presentation strategies more precisely and intelligently, effectively balancing the timeliness of fault information transmission and the need to avoid interfering with the driver's safe operation, solving the problem of suboptimal strategy selection that may exist in existing solutions, improving the adaptability and effectiveness of fault information presentation, and contributing to ensuring driving safety and enhancing the user experience.

[0088] Refer to Figure 2 , the present application provides a cooperative control fault handling system for a new energy vehicle, which is used to present fault information to the driver when a fault occurs during the operation of the cooperative control system of the new energy vehicle. The system includes: The data acquisition module 1 is used to acquire vehicle operation data, environment perception data, driver operation data, and driver attention-related data (for the specific process, refer to step A1 in the previous text); The evaluation module 2 is used to evaluate the driving scenario complexity and driver cognitive load based on the acquired vehicle operation data, environment perception data, driver operation data, and driver attention-related data (for the specific process, refer to step A2 in the previous text); The fault information receiving module 3 is used to receive the fault information output by the cooperative control system; the fault information includes the fault type, fault severity, and vehicle performance impact evaluation result (for the specific process, refer to step A3 in the previous text); The strategy selection module 4 is used to select an information presentation strategy from a preset strategy library according to the fault information, driving scenario complexity, and driver cognitive load; the information presentation strategy includes the information presentation channel, the detail level of information content, and the presentation timing (for the specific process, refer to step A4 in the previous text); The information presentation module 5 is used to generate fault information according to the selected information presentation strategy and control the human-machine interface device to perform information presentation (for the specific process, refer to step A5 in the previous text).

[0089] The above are only the embodiments of the present application and are not used to limit the protection scope of the present application. For those skilled in the art, various changes and modifications can be made to the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method for handling collaborative control faults in a new energy vehicle, which is used to present fault information to the driver when a fault occurs during the operation of the new energy vehicle collaborative control system. It is characterized in that, The steps of this method include: A1. Obtain vehicle operation data, environment perception data, driver operation data, and driver attention-related data; A2. Evaluate the driving scenario complexity and driver cognitive load based on the obtained vehicle operation data, environment perception data, driver operation data, and driver attention-related data; A3. Receive the fault information output by the cooperative control system; the fault information includes the fault type, fault severity, and vehicle performance impact evaluation result; A4. Select an information presentation strategy from a preset strategy library according to the fault information, driving scenario complexity, and driver cognitive load; the information presentation strategy includes the information presentation channel, the detail level of the information content, and the presentation timing; A5. Generate fault information according to the selected information presentation strategy, and control the human-machine interface device to perform information presentation.

2. The method for handling collaborative control faults of a new energy vehicle according to claim 1, wherein, Step A1 includes: A101. Read vehicle operation data through the vehicle bus CAN interface; the vehicle operation data includes vehicle speed, steering angle, and acceleration; A102. Obtain environment perception data through radar and cameras; the environment perception data includes the distance to surrounding vehicles, relative speed, and road curvature; A103. Obtain driver operation data through sensors; the driver operation data includes throttle opening, braking pressure, and steering torque; A104. Obtain driver attention-related data through image recognition; the driver attention-related data includes eye movement data and head posture; A105. Preprocess the vehicle operation data, environment perception data, driver operation data, and driver attention-related data.

3. The collaborative control fault handling method for a new energy vehicle according to claim 2, wherein, Step A2 includes: A201. Evaluate the vehicle driving smoothness based on the vehicle operation data to obtain a smoothness index; A202. Evaluate the road congestion degree based on the environment perception data and road type to obtain a congestion degree index; A203. Evaluate the driver's fatigue degree and distraction degree based on the driver operation data and driver attention-related data to obtain a fatigue degree index and a distraction degree index; A204. Calculate the driving scenario complexity and driver cognitive load by integrating the smoothness index, congestion degree index, fatigue degree index, and distraction degree index.

4. A new energy vehicle collaborative control fault handling method according to claim 3, characterized in that, Step A201 includes: Based on the vehicle operation data, extract the vehicle speed sequence, steering angle sequence, and acceleration sequence; For the vehicle speed sequence, steering angle sequence, and acceleration sequence, calculate the sequence entropy to obtain the vehicle speed sequence entropy, steering angle sequence entropy, and acceleration sequence entropy; According to the vehicle speed sequence entropy, steering angle sequence entropy, and acceleration sequence entropy, use a weighted fusion algorithm to calculate the smoothness index.

5. The method for processing faults in cooperative control of a new energy vehicle according to claim 3, wherein, Step A202 includes: Determine the road type of the road where the vehicle is located according to the vehicle's real-time position; Based on the environment perception data, extract the surrounding vehicle distance sequence, relative speed sequence, and road curvature sequence; For the surrounding vehicle distance sequence and relative speed sequence, use the dynamic time warping algorithm to calculate the distance congestion factor and speed congestion factor; For the road curvature sequence, calculate the curvature change rate, and correct the distance congestion factor and speed congestion factor according to the road type and curvature change rate. According to the corrected distance congestion factor and the corrected speed congestion factor, a weighted fusion algorithm is used to calculate the road congestion degree index.

6. The method for handling collaborative control faults of a new energy vehicle according to claim 5, wherein, The steps of calculating the curvature change rate for the road curvature sequence and correcting the distance congestion factor and the speed congestion factor according to the road type and the curvature change rate include: Determine the reference curvature change rate threshold according to the road type of the road where the vehicle is located; the road types include highways, urban roads, and rural roads, and different road types correspond to different reference curvature change rate thresholds; For the road curvature sequence, use the sliding window algorithm to calculate the curvature change rate sequence; the length of the sliding window is adaptively adjusted according to the vehicle speed, and the higher the vehicle speed, the longer the window length; For the curvature change rate sequence, count the number of curvature change rates greater than the reference curvature change rate threshold to obtain the number of curvature change rates exceeding the threshold; According to the road type and the number of curvature change rates exceeding the threshold, use a piecewise function to correct the distance congestion factor and the speed congestion factor; the correction amplitude for highways is less than that for urban roads and rural roads, and the more the number of curvature change rates exceeding the threshold, the greater the correction amplitude.

7. A method for processing faults in the collaborative control of a new energy vehicle according to claim 3, characterized in that, Step A203 includes: Based on the driver operation data, extract the throttle opening sequence, the braking pressure sequence, and the steering torque sequence, and calculate the mean and variance of each sequence; Based on the driver attention-related data, extract the blink frequency of the eye movement data and the head movement frequency of the head pose data; For the mean and variance of the throttle opening sequence, the mean and variance of the braking pressure sequence, the mean and variance of the steering torque sequence, the blink frequency, and the nodding frequency, use the preset fuzzy inference rules to calculate the driver fatigue degree index and the driver distraction degree index.

8. The collaborative control fault handling method for a new energy vehicle according to claim 3, wherein, Step A204 includes: Normalize the smoothness index, the congestion degree index, the fatigue degree index, and the distraction degree index; Perform a weighted fusion operation on the difference between 1 and the normalized smoothness index and the normalized congestion degree index to obtain the driving scenario complexity; Perform a weighted fusion operation on the normalized fatigue degree index and the normalized distraction degree index to obtain the driver cognitive load.

9. A method for handling faults in the coordinated control of a new energy vehicle according to claim 1, characterized in that, Step A4 includes: A401. Evaluate the priority of the fault information according to the fault type, the fault severity, and the vehicle performance impact assessment result; A402. Evaluate the driving scenario risk level according to the driving scenario complexity; A403. Determine the urgency of information presentation according to the priority of the fault information and the driving scenario risk level; A404. Select the information presentation strategy from the preset strategy library according to the urgency of information presentation and the driver cognitive load; the information presentation strategy includes the information presentation channel, the detail level of the information content, and the presentation timing.

10. A cooperative control fault handling system for new energy vehicles, which is used to present fault information to the driver when a fault occurs in the cooperative control system of new energy vehicles during vehicle operation, and is characterized in that, The system includes: A data acquisition module for acquiring vehicle operation data, environment perception data, driver operation data, and driver attention-related data; An evaluation module for evaluating the driving scenario complexity and the driver cognitive load according to the acquired vehicle operation data, environment perception data, driver operation data, and driver attention-related data; A fault information receiving module, configured to receive the fault information output by the cooperative control system; the fault information includes the fault type, the fault severity, and the evaluation result of the impact on vehicle performance; A strategy selection module, configured to select an information presentation strategy from a preset strategy library according to the fault information, the complexity of the driving scenario, and the driver's cognitive load; the information presentation strategy includes the information presentation channel, the detail level of the information content, and the presentation timing; An information presentation module, configured to generate fault information according to the selected information presentation strategy, and control the human-machine interface device to perform information presentation.

Images