Driving safety detection method, system and device and medium

Abstract

The invention discloses a driving safety detection method, and the method comprises the steps: obtaining auxiliary data which comprises at least one of battery system data, driving system data, driving posture data and environment detection data; based on the auxiliary data, determining fusion data; acquiring historical operation data; and determining the vehicle driving risk based on the historical operation data and the fusion data. According to the method, the safety of the pure electric commercial vehicle in the driving process is ensured through multi-dimensional detection and intelligent analysis.

Description

Technical Field

[0001] The present invention relates to the field of electric vehicle safety control technology, and in particular to a driving safety detection method and system, device and medium. Background Art

[0002] In recent years, pure electric commercial vehicles have been increasingly used in logistics and transportation. However, due to their special power systems and complex operating environments, they face new safety challenges compared to traditional fuel commercial vehicles. For example, the stability of the battery system directly affects the operation of the vehicle, and once problems such as thermal runaway occur, serious consequences may occur; failures in the electric drive system may cause the vehicle to stall or lose control instantly; furthermore, the electronic control system of pure electric commercial vehicles is more complex, and the compatibility of software and hardware, the reliability of electronic components, etc. are all closely related to driving safety. At present, there is a lack of a comprehensive and efficient safety detection method for pure electric commercial vehicles during driving, which makes it difficult to accurately predict and promptly deal with various safety hazards in advance.

[0003] At present, there is a lack of a comprehensive and efficient safety detection method for pure electric commercial vehicles during driving on the market. The safety hazards that exist during the driving of pure electric commercial vehicles are often independent detection feedback problems of each system. It is impossible to conduct comprehensive multi-dimensional and comprehensive detection of key aspects such as the battery system, electric drive system, vehicle driving posture and environment of pure electric commercial vehicles. It is difficult to accurately predict various safety hazards such as battery thermal runaway, electric drive system failure, vehicle skidding danger, and being too close to obstacles in advance, and it is impossible to deal with these hazards in time, resulting in a lack of reliable guarantee for the safety of pure electric commercial vehicles during driving.

[0004] Therefore, there is an urgent need for a driving safety detection method to ensure the safety of pure electric commercial vehicles during driving through multi-dimensional detection and intelligent analysis. Summary of the invention

[0005] This specification discloses a driving safety detection method, which includes: obtaining auxiliary data, wherein the auxiliary data includes at least one of battery system data, drive system data, driving posture data, and environmental detection data; determining fusion data based on the auxiliary data; obtaining historical operation data; and determining vehicle driving risks based on the historical operation data and the fusion data.

[0006] In some embodiments, the method further includes: in response to the vehicle driving risk meeting a preset risk condition, triggering a safety mechanism.

[0007] In some embodiments, the battery system data includes battery pack temperature data, total voltage of the battery pack, single cell voltage and charge and discharge current, and insulation resistance of the battery system.

[0008] In some embodiments, the drive system data includes motor parameters and electronic control component parameters; the motor parameters include motor speed, torque, and vibration amplitude; the electronic control component parameters include the working status of internal electronic components of the electronic control component, the connection status of the communication line, and the accuracy of the control signal.

[0009] In some embodiments, the driving posture data includes the longitudinal and lateral accelerations of the vehicle and the pitch and roll angles of the vehicle body.

[0010] In some embodiments, the environmental detection data includes target information and identification information; the target information includes the distance, speed, and relative movement direction of the vehicle or obstacle ahead; the identification information includes road markings and traffic signs.

[0011] In some embodiments, determining the vehicle driving risk based on the historical operating data and the fused data includes: determining the vehicle driving risk through a safety risk assessment model based on the historical operating data and the fused data, and the safety risk assessment model is a machine learning model.

[0012] The present invention also discloses a driving safety detection system, including a first acquisition module, a fusion module, a second acquisition module, and a determination module; the first acquisition module is configured to acquire auxiliary data, and the auxiliary data includes at least one of battery system data, drive system data, driving posture data, and environmental detection data; the fusion module is configured to determine fusion data based on the auxiliary data; the second acquisition module is configured to acquire historical operation data; the determination acquisition module is configured to determine the vehicle driving risk based on the historical operation data and the fusion data.

[0013] The present invention also discloses a driving safety detection device, comprising a processor, wherein the processor is used to execute the above-mentioned driving safety detection method.

[0014] The present invention also discloses a computer-readable storage medium, wherein the storage medium stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the driving safety detection method as described above.

[0015] Beneficial effects: Based on the driving safety detection method of the present invention, the following significant effects can be achieved:

[0016] Multi-dimensional comprehensive testing: Testing is carried out from multiple dimensions such as the battery system, electric drive system, vehicle driving posture and environment, comprehensively covering the key safety areas of pure electric commercial vehicles, greatly improving the integrity and systematicness of the testing.

[0017] Accurate monitoring and early warning: In each detection dimension, by installing high-precision sensors in key locations such as the battery pack and key locations of the motor, it is possible to monitor subtle changes in key parameters in real time and accurately. Whether it is battery temperature, voltage, current, insulation resistance, or motor speed, torque, vibration amplitude, etc., once an abnormality occurs, the risk of failure can be quickly and accurately determined, and an early warning signal can be issued in a timely manner, allowing the driver and related systems to be aware of potential dangers and respond in the first place.

[0018] Intelligent and efficient data processing and risk assessment: Using advanced data fusion models, such as Kalman filtering, Bayesian estimation and other algorithms, multi-source data is fused and processed, effectively improving the accuracy and reliability of the data, thereby providing a more solid data foundation for subsequent safety decisions. Based on the fused data, the safety risk assessment model established with the help of artificial intelligence algorithms (neural networks) can quantitatively assess the current safety risks of the vehicle based on the historical operation data and real-time detection data of the vehicle, and obtain an intuitive safety risk index. This intelligent assessment method can judge the safety status of the vehicle more scientifically and reasonably, avoiding the subjectivity and limitations of human judgment.

[0019] Timely and effective safety response: When the safety risk index exceeds the warning value, the system can automatically take corresponding safety measures based on the specific situation of the vehicle, such as surrounding traffic conditions, road conditions, etc., such as reducing the speed, prompting the driver to drive carefully, or directly controlling the vehicle to drive to a safe area. This automated and intelligent response mechanism can intervene in time before danger occurs, effectively preventing the occurrence of various safety accidents, greatly improving the driving safety and reliability of pure electric commercial vehicles, protecting the lives and property of vehicles and personnel, and also helping to reduce traffic congestion and economic losses caused by accidents, and improving the operational efficiency and stability of industries such as logistics and transportation. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] This specification will be further described in the form of exemplary embodiments, which will be described in detail by the accompanying drawings. These embodiments are not restrictive, and in these embodiments, the same number represents the same structure, wherein:

[0021] Figure 1 is a schematic diagram of the module structure of a driving safety detection device according to some embodiments of this specification;

[0022] Figure 2 is an exemplary flow chart of a driving safety detection method according to some embodiments of this specification;

[0023] Figure 3 is an exemplary schematic diagram of a security risk assessment model according to some embodiments of this specification;

[0024] Figure 4 It is an exemplary schematic diagram of the driving safety detection method shown in other embodiments of this specification. DETAILED DESCRIPTION

[0025] In order to more clearly illustrate the technical solutions of the embodiments of this specification, the following is a brief introduction to the drawings required for the description of the embodiments. Obviously, the drawings described below are only some examples or embodiments of this specification. For ordinary technicians in this field, this specification can also be applied to other similar scenarios based on these drawings without creative work. Unless it is obvious from the language environment or otherwise explained, the same reference numerals in the figures represent the same structure or operation.

[0026] It should be understood that the "system", "device", "unit" and / or "module" used herein are a method for distinguishing different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the words can be replaced by other expressions.

[0027] As shown in this specification and claims, unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular and may also include the plural. Generally speaking, the terms "comprise" and "include" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0028] Figure 1 It is a schematic diagram of the module structure of the driving safety detection system 100 shown in some embodiments of this specification.

[0029] like Figure 1 As shown, the driving safety detection system 100 (hereinafter referred to as the system 100 ) includes a first acquisition module 110 , a fusion module 120 , a second acquisition module 130 , and a determination module 140 .

[0030] In some embodiments, the first acquisition module is configured to acquire auxiliary data, and the auxiliary data includes at least one of battery system data, drive system data, driving posture data, and environmental detection data.

[0031] In some embodiments, the battery system data includes battery pack temperature data, total voltage of the battery pack, single cell voltage and charge and discharge current, and insulation resistance of the battery system.

[0032] For example, the first acquisition module includes multiple high-precision temperature sensors evenly distributed in the battery pack to monitor the temperature changes of the battery cells and the whole in real time. For another example, the first acquisition module includes a high-precision voltage sensor and a current sensor to measure the total voltage, cell voltage, and charge and discharge current of the battery pack in real time. For another example, the first acquisition module includes an insulation resistance detection circuit to detect the insulation resistance of the battery system.

[0033] In some embodiments, the drive system data includes motor parameters and electronic control component parameters; the motor parameters include motor speed, torque, and vibration amplitude; the electronic control component parameters include the working status of internal electronic components of the electronic control component, the connection status of the communication line, and the accuracy of the control signal.

[0034] For example, the first acquisition module includes sensors installed at key locations such as the stator winding and rotor shaft of the motor, which can monitor parameters such as the motor's speed, torque, and vibration amplitude. For another example, the first acquisition module includes a processing unit such as a processor that can acquire real-time self-test data of electric control components such as a motor controller and an inverter. By performing real-time self-tests on electric control components such as motor controllers and inverters, the working status of their internal electronic components, the connection status of communication lines, and the accuracy of control signals can be checked.

[0035] In some embodiments, the driving posture data includes the longitudinal and lateral accelerations of the vehicle and the pitch and roll angles of the vehicle body.

[0036] For example, the first acquisition module includes attitude sensors such as acceleration sensors and gyroscopes installed in the vehicle to monitor the longitudinal and lateral accelerations of the vehicle and the pitch and roll angles of the vehicle in real time.

[0037] In some embodiments, the environmental detection data includes target information and identification information; the target information includes the distance, speed, and relative movement direction of the vehicle or obstacle ahead; the identification information includes road markings and traffic signs.

[0038] For example, the first acquisition module includes sensors such as millimeter wave radar, laser radar and camera to perceive the traffic conditions and road environment around the vehicle, detect the distance, speed, relative movement direction and other information of the vehicle or obstacle in front, and also recognize road markings, traffic signs and so on.

[0039] In some embodiments, the fusion module is configured to determine fusion data based on the auxiliary data. For example, the fusion module can fuse the data obtained by the above-mentioned detection systems, and use algorithms such as Kalman filtering and Bayesian estimation to improve the accuracy and reliability of the data. For example, the radar and camera data can be fused to more accurately determine the position and shape of the obstacle ahead.

[0040] In some embodiments, the second acquisition module is configured to acquire historical operation data; the determination acquisition module is configured to determine the vehicle driving risk based on the historical operation data and the fusion data. In some embodiments, the second acquisition module is configured to determine the vehicle driving risk based on the historical operation data and the fusion data through a safety risk assessment model, and the safety risk assessment model is a machine learning model. For a detailed description of the safety risk assessment model, see Figure 3 The corresponding content.

[0041] In some embodiments, the system 100 further includes an early warning module (not shown in the figure). The early warning module is configured to trigger a safety mechanism in response to the vehicle driving risk meeting a preset risk condition.

[0042] For details about the above embodiments, please refer to Figure 2-Figure 4 The following is an embodiment of the system 100:

[0043] In terms of battery system detection, high-precision temperature sensors are evenly arranged in the battery pack. Once the local temperature exceeds 55°C or the temperature difference between adjacent cells is greater than 10°C, an alarm is immediately issued and the cooling system is started. At the same time, voltage and current sensors are used for real-time monitoring. When the cell voltage or charge and discharge current is abnormal, the vehicle power is reduced and the driver is prompted to stop for inspection. The insulation resistance is tested every 10 minutes. If it is lower than 500Ω / V, the circuit is cut off and a leakage risk is warned.

[0044] Then, during the electric drive system inspection, sensors are installed at key parts of the motor to monitor parameters such as speed, torque, and vibration amplitude. If an abnormality occurs, the system enters limp home mode and transmits the fault information to the vehicle monitoring center. The motor controller, inverter and other electronic control components are self-checked in real time. In case of a fault, the backup control circuit is switched or the electric drive system is stopped, allowing the vehicle to glide to a safe area by inertia.

[0045] At the same time, the vehicle's driving posture and environment detection link uses accelerometers, gyroscopes and other posture sensors to monitor the vehicle's longitudinal and lateral acceleration, as well as the pitch and roll angles of the vehicle body, and adjusts power distribution and braking in time when abnormalities occur; uses millimeter-wave radar, lidar, and cameras and other sensors to perceive the surrounding traffic and road environment, activates the pre-collision system when the distance to the obstacle ahead is too close, and reminds the driver to correct when the vehicle deviates from the lane or exceeds the speed limit.

[0046] Finally, at the data fusion and intelligent analysis level, a data fusion model is established, and algorithms such as Kalman filtering are used to fuse various detection data to improve accuracy; based on the fused data, a safety risk assessment model is established using a neural network algorithm. When the safety risk index exceeds 60, corresponding safety measures are taken based on the traffic conditions around the vehicle, and with the help of big data collection and analysis of the Carsmart smart interconnection platform, the danger alarm threshold parameters during detection of each system are optimized. This method can achieve comprehensive, real-time, and accurate detection, effectively prevent accidents, and improve the driving safety and reliability of pure electric commercial vehicles.

[0047] Some embodiments of this specification, based on the system 100 of the present invention, can set detection contents from the key dimensions of battery system, electric drive system, vehicle driving posture and environment, covering temperature, voltage and current, insulation resistance, motor performance, electronic control system, vehicle posture and surrounding environment perception and other aspects of detection, forming a comprehensive and detailed detection architecture.

[0048] It should be noted that the above description of the driving safety detection system and its platform is only for convenience of description and cannot limit this specification to the scope of the embodiments. It is understandable that for those skilled in the art, after understanding the principle of the system, it is possible to arbitrarily combine the various platforms or form a subsystem to connect with other platforms without deviating from this principle. In some embodiments, Figure 1 The first acquisition module 110, the fusion module 120, the second acquisition module 130, and the determination module 140 disclosed in the specification can be different platforms in a system, or one platform can realize the functions of two or more platforms. For example, each platform can share a storage database, or each platform can have its own storage database. Such variations are all within the scope of protection of this specification.

[0049] Figure 2 is an exemplary flow chart of a driving safety detection method according to some embodiments of this specification. Figure 2 As shown, the process 200 includes the following steps 210 to 240. In some embodiments, the process 200 may be executed by the system 100.

[0050] Step 210, obtaining auxiliary data.

[0051] In some embodiments, the auxiliary data includes at least one of battery system data, drive system data, driving posture data, and environmental detection data.

[0052] In some embodiments, the battery system data includes battery pack temperature data, total voltage of the battery pack, single cell voltage and charge and discharge current, and insulation resistance of the battery system.

[0053] In some embodiments, the drive system data includes motor parameters and electronic control component parameters; the motor parameters include motor speed, torque, and vibration amplitude; the electronic control component parameters include the working status of internal electronic components of the electronic control component, the connection status of the communication line, and the accuracy of the control signal.

[0054] In some embodiments, the driving posture data includes the longitudinal and lateral accelerations of the vehicle and the pitch and roll angles of the vehicle body.

[0055] In some embodiments, the environmental detection data includes target information and identification information; the target information includes the distance, speed, and relative movement direction of the vehicle or obstacle ahead; the identification information includes road markings and traffic signs.

[0056] For further information on auxiliary data, see Figure 1 The corresponding content.

[0057] Step 220: Determine fused data based on the auxiliary data.

[0058] In some embodiments, data fusion can be performed based on a fusion model. For example, a data fusion model is established: the data acquired by the above detection systems are fused and processed, and algorithms such as Kalman filtering and Bayesian estimation are used to improve the accuracy and reliability of the data.

[0059] Step 230, obtaining historical operation data.

[0060] The historical operation data may include various historical auxiliary data of the vehicle during its historical operation. For a description of the auxiliary data, please refer to the content of step 210 .

[0061] Step 240: Determine the vehicle driving risk based on the historical operating data and the fused data.

[0062] In some embodiments, the determining of the vehicle driving risk based on the historical operation data and the fused data includes: determining the vehicle driving risk based on the historical operation data and the fused data through a safety risk assessment model, wherein the safety risk assessment model is a machine learning model. For example, based on the fused data, an artificial intelligence algorithm (such as a neural network) is used to establish a vehicle driving safety risk assessment model. Based on the historical operation data and real-time detection data of the vehicle, a quantitative assessment of the current safety risk of the vehicle is performed (such as a safety risk index of 0-100).

[0063] In some embodiments, the method further includes: in response to the vehicle driving risk meeting a preset risk condition, triggering a safety mechanism.

[0064] For example, when the safety risk index exceeds the warning value (such as 60), corresponding safety measures are taken, such as reducing the speed, prompting the driver to drive carefully, or directly controlling the vehicle to a safe area; through the big data collection and analysis of the Carsmart intelligent interconnection platform, the potential manifestations and early phenomena of various driving hazards are summarized, and the danger alarm threshold parameters during detection of each system are continuously optimized.

[0065] In some embodiments, the early warning module may issue an early warning based on a separate judgment of the auxiliary data to detect risks in advance.

[0066] For example, when the local temperature in the battery system data exceeds the set threshold (such as 55°C) or the temperature difference (such as the temperature difference between adjacent cells is greater than 10°C) is too large, an early warning signal is immediately issued and the battery cooling system is started for cooling.

[0067] For example, if the single cell voltage in the battery system data is too high (such as exceeding 4.25V) or too low (such as lower than 2.8V), or the charging and discharging current fluctuates abnormally (such as the instantaneous current change rate exceeds the set value), the battery is judged to be at risk of failure, the vehicle power output is reduced, and the driver is prompted to pull over for inspection.

[0068] For example, if the insulation resistance value in the battery system data is lower than the safety standard (such as 500Ω / V), the battery power supply circuit is cut off and the driver is notified that there is a risk of leakage in the battery system.

[0069] For example, if the drive system data shows that the speed is unstable (such as the fluctuation range exceeds 10% of the rated speed), the torque changes abnormally (such as a sudden drop or increase of more than 20% of the rated torque), or the vibration amplitude exceeds the set value (determined according to the motor model and operating conditions), the motor is judged to be faulty, the vehicle enters limp home mode and the speed is limited, and the fault information is transmitted to the vehicle monitoring center.

[0070] For example, if an electronic control system fault is detected based on the drive system data, such as power module overheating, communication failure, etc., it will immediately switch to the backup control circuit or stop the electric drive system, and rely on the vehicle's inertia to glide to a safe area.

[0071] For example, if the lateral acceleration in the driving posture data exceeds the safety threshold (such as 0.8g), it indicates that the vehicle may be in danger of skidding, and the vehicle power distribution should be adjusted in time and the corresponding wheels should be braked. If the pitch angle of the vehicle changes abnormally (such as exceeding 10 degrees during sudden acceleration or braking), check whether the vehicle suspension system and braking system are working properly.

[0072] For example, when the safety distance to the obstacle ahead is less than the set value (e.g., dynamically adjusted according to vehicle speed, the safety distance is 30 meters at a speed of 60 km / h), the pre-collision system is automatically activated, including issuing an alarm, pre-tightening the seat belt, and partial braking operations. Or, based on the recognized road markings, traffic signs, etc., if the vehicle deviates from the lane or exceeds the speed limit, the driver is promptly reminded to correct the situation.

[0073] It should be noted that the above description of the process 200 is only for example and illustration, and does not limit the scope of application of this specification. For those skilled in the art, various modifications and changes can be made to the process 200 under the guidance of this specification. However, these modifications and changes are still within the scope of this specification.

[0074] Figure 3 It is an exemplary schematic diagram of a security risk assessment model according to some embodiments of this specification.

[0075] In some embodiments, the system 100 may determine the vehicle driving risk 340 based on the historical operation data 310 and the fusion data 320 of the vehicle and based on the safety risk assessment model 330 .

[0076] The safety risk assessment model is a model used to determine the risk of vehicle driving. In some embodiments, the safety risk assessment model can be a machine learning model, such as a recurrent neural network (RNN) model or other trained machine learning models.

[0077] In some embodiments, the input of the safety risk assessment model includes historical operation data 310 and fusion data 320 of the vehicle, and the output includes vehicle driving risk 340 .

[0078] In some embodiments, the security risk assessment model can be obtained by various methods, for example, based on a plurality of labeled training samples, trained and obtained by gradient descent method or other feasible methods.

[0079] In some embodiments, the training sample and its corresponding label can be determined based on historical data. The training sample can be obtained based on historical driving data that matches the sample vehicle. The training sample can include fusion data of historical operating data of the sample vehicle in a first historical period and a second historical period, and the label can be the actual vehicle driving risk of the sample vehicle in a third historical period.

[0080] The first historical period, the second historical period, and the third historical period are all past periods, the first historical period is earlier than the second historical period, and the second historical period is earlier than the third historical period. The actual vehicle driving risk of the sample vehicle in the third historical period can be determined based on whether the sample vehicle has a fault or accident in the third historical period. If a fault or accident occurs, the actual vehicle driving risk is 1, otherwise it is 0.

[0081] As an example only, the training samples can be input into the initial security risk assessment model to obtain the output of the initial security risk assessment model; a loss function can be constructed based on the output of the initial security risk assessment model and the labels corresponding to the training samples; based on the loss function, the parameters of the initial security risk assessment model are iteratively updated; until the iteration end condition is met, the training is completed, and a trained security risk assessment model is obtained. The iteration end condition includes the convergence of the loss function and the number of iterations reaching a threshold.

[0082] In some embodiments of this specification, a machine learning model can be used to more accurately estimate vehicle risks, which is conducive to timely risk control. The method in some embodiments of the present invention can comprehensively, real-timely and accurately detect the safety status of the vehicle during driving, effectively prevent the occurrence of various safety accidents, and improve the driving safety and reliability of pure electric commercial vehicles.

[0083] The following is a further description of the method of the present invention by taking a specific practical application scenario (applied to electric commercial vehicles) as an example:

[0084] like Figure 4 As shown, this solution requires the following operations:

[0085] (I) Battery system testing implementation

[0086] In the battery pack of pure electric commercial vehicles, temperature sensors are installed at a certain interval (such as every 3-5 battery cells), and the sensors are connected to the battery management system (BMS). The microprocessor in the BMS continuously reads temperature data. When a sensor detects a temperature higher than 55°C, the BMS starts the cooling fan or liquid cooling pump to cool it down; if the temperature difference between adjacent cells is greater than 10°C, the battery balancing circuit is adjusted to make the battery cell voltage and temperature tend to be consistent.

[0087] For voltage and current detection, voltage sensors are connected to the positive and negative poles of the battery pack and both ends of each single cell, and current sensors are installed on the main circuit. These sensors transmit data to the BMS. The BMS analyzes the voltage and current data in real time. Once a single cell voltage is abnormal or the current fluctuates, the BMS sends a signal to the vehicle controller through the vehicle communication bus. The vehicle controller reduces the motor output power and displays battery fault information on the vehicle dashboard, prompting the driver to stop the car for inspection.

[0088] The insulation resistance test uses a special insulation monitor connected between the positive and negative poles of the battery and the vehicle body ground. Every 10 minutes, the insulation monitor applies a detection signal of a specific frequency and voltage to the battery system and calculates the insulation resistance value based on the feedback current. If the insulation resistance is lower than 500Ω / V, the insulation monitor triggers the relay to cut off the battery power supply circuit and sends a leakage alarm to the driver.

[0089] (II) Implementation of electric drive system testing

[0090] A current transformer is installed on the motor stator winding to monitor the winding current, and a Hall sensor is installed on the rotor shaft to detect the speed and torque. At the same time, an acceleration sensor is installed on the motor housing to monitor the vibration amplitude. These sensors transmit data to the motor controller. The motor controller has a built-in fault diagnosis algorithm. When the motor speed fluctuation exceeds 10% of the rated speed, the motor controller analyzes the current and torque data to determine whether it is a sudden load change or an internal motor fault; if the torque abnormal change exceeds 20% of the rated torque or the vibration amplitude exceeds the set value, the motor controller determines that the motor is faulty, enters limp mode, limits the maximum speed of the vehicle to 30km / h, and sends the fault information to the vehicle monitoring center through the wireless communication module.

[0091] For electronic control system detection, the motor controller and inverter are internally integrated with self-test circuits. During vehicle operation, the self-test circuit periodically (e.g., every 5 minutes) checks the power module temperature, drive signal, communication interface, etc. If the power module is found to be overheated (e.g., the temperature exceeds 120°C), the cooling fan is started or the power output is reduced; if the communication fails, try to re-establish the connection. If it fails multiple times, switch to the backup control circuit (if any) or stop the electric drive system, and the vehicle relies on inertia to glide to a safe area.

[0092] (III) Implementation of vehicle driving posture and environment testing

[0093] The acceleration sensor and gyroscope are installed at the center of the vehicle chassis, which can accurately measure the longitudinal and lateral acceleration of the vehicle as well as the pitch and roll angles of the vehicle. These data are transmitted to the vehicle controller. When the vehicle controller detects that the lateral acceleration exceeds 0.8g, it determines that the vehicle may skid. According to the vehicle's steering angle, speed and other information, the electronic stability control system (ESC) brakes the corresponding wheels and adjusts the power distribution to restore the vehicle to stable driving; if the pitch angle of the vehicle exceeds 10 degrees during sudden acceleration or braking, the vehicle controller checks whether the damping coefficient of the suspension system, the spring travel and the braking force distribution of the braking system are normal. If abnormal, a prompt message will be displayed on the instrument panel.

[0094] The vehicle's millimeter-wave radar is installed on the front bumper, rear bumper and under the rearview mirrors on both sides of the vehicle, the laser radar is installed on the roof, and the camera is installed above the windshield and at the rear of the vehicle. These sensors work together to perceive the vehicle's surrounding environment in all directions. For example, the millimeter-wave radar and laser radar monitor the distance, speed and relative movement direction of the vehicle or obstacle in front in real time, and the camera identifies road markings and traffic signs. When the distance to the obstacle in front is less than the safe value, the pre-collision system is activated, first issuing an alarm and flashing warning lights. If the driver does not respond in time, when the distance is further reduced to the dangerous value, the pre-collision system automatically partially brakes the vehicle (such as applying 30% braking force) and pre-tightens the seat belt; when the camera recognizes that the vehicle deviates from the lane or exceeds the speed limit, the corresponding warning message is displayed on the dashboard, and the steering wheel vibration can be used to remind the driver according to the vehicle configuration.

[0095] (IV) Data fusion and intelligent analysis implementation

[0096] The data fusion model runs in the vehicle's central processing unit (CPU). For example, for radar and camera data fusion, the CPU first pre-processes the data from the millimeter-wave radar and lidar to extract information such as the location and speed of the target, and processes the camera image to identify the type and shape of the target. Then, the Kalman filter algorithm is used to fuse the radar and camera data to obtain more accurate target information, such as the exact location, speed and type of the vehicle in front.

[0097] The safety risk assessment model uses a neural network algorithm, takes the vehicle's historical driving data (such as battery temperature, motor performance, vehicle posture, etc. in the past 1,000 kilometers) and real-time detection data as input, and outputs a safety risk index. Before the vehicle is operated, a large amount of test data is used to train the neural network to optimize the model's weights and thresholds. During the vehicle's driving, the CPU inputs the fused data into the safety risk assessment model every 1 second to obtain the current safety risk index. When the safety risk index exceeds 60, the CPU takes corresponding safety measures based on the specific conditions of the vehicle, such as surrounding traffic conditions, road conditions, etc., such as reducing the speed, adjusting the vehicle's driving route, or directly controlling the vehicle to drive to a safe area.

[0098] The schemes of some embodiments of the present invention can create a data fusion model, use Kalman filtering, Bayesian estimation and other algorithms to fuse the data obtained by each detection system, and improve the accuracy and reliability of the data; at the same time, based on the fused data, a safety risk assessment model is constructed using artificial intelligence algorithms such as neural networks to achieve a quantitative assessment of the safety risk of vehicle driving. With accurate monitoring and intelligent analysis in various dimensions, various potential safety hazards such as battery failure, motor failure, abnormal vehicle posture, and too close distance to obstacles can be accurately discovered in advance, and early warning signals can be issued in time so that the driver or related systems can quickly know and take countermeasures. When it is detected that the safety risk index exceeds the warning value, corresponding safety measures can be automatically taken according to the actual situation of the vehicle, such as adjusting the vehicle power distribution, braking intervention, reducing the speed, prompting the driver to drive carefully, or directly controlling the vehicle to drive to a safe area, etc., to prevent all kinds of safety accidents in an all-round way and effectively ensure the safety and reliability of pure electric commercial vehicles during driving. Reducing vehicle damage and traffic congestion caused by safety accidents will help pure electric commercial vehicles to be better applied in logistics and transportation and other fields, and improve the overall efficiency and stability of industry operations.

[0099] The basic concepts have been described above. Obviously, for those skilled in the art, the above detailed disclosure is only for example and does not constitute a limitation of this specification. Although not explicitly stated here, those skilled in the art may make various modifications, improvements and corrections to this specification. Such modifications, improvements and corrections are suggested in this specification, so such modifications, improvements and corrections still belong to the spirit and scope of the exemplary embodiments of this specification.

[0100] At the same time, this specification uses specific words to describe the embodiments of this specification. For example, "some embodiments" means a certain feature, structure or characteristic related to at least one embodiment of this specification. Therefore, it should be emphasized and noted that "some embodiments" mentioned twice or more in different places in this specification do not necessarily refer to the same embodiment. In addition, some features, structures or characteristics in one or more embodiments of this specification can be appropriately combined.

[0101] In addition, the order of processing elements and sequences, the use of alphanumeric characters, or the use of other names described in this specification are not intended to limit the order of the processes and methods of this specification. Although the above disclosure discusses some of the invention embodiments currently considered useful through various examples, it should be understood that such details are only for illustrative purposes and are not limited to the disclosed embodiments. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only by software solutions, such as installing the described system on an existing server or mobile device.

[0102] Similarly, it should be noted that in order to simplify the description disclosed in this specification and thus help understand one or more embodiments of the invention, in the above description of the embodiments of this specification, multiple features are sometimes combined into one embodiment, figure or description thereof. In fact, the features of the embodiment are less than all the features of the single embodiment disclosed above.

[0103] In some embodiments, numbers describing the number of components and attributes are used. It should be understood that such numbers used in the description of the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise specified, "about", "approximately" or "substantially" indicate that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification are approximate values, which may change according to the required features of individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining digits. Although the numerical domains and parameters used to confirm the breadth of their range in some embodiments of this specification are approximate values, in specific embodiments, the setting of such numerical values ​​is as accurate as possible within the feasible range.

[0104] Each patent, patent application, patent application publication, and other materials, such as articles, books, specifications, publications, documents, etc., cited in this specification are hereby incorporated by reference in their entirety. Except for application history documents that are inconsistent with or conflicting with the contents of this specification, documents that limit the broadest scope of the claims of this specification (currently or later attached to this specification) are also excluded. It should be noted that if the descriptions, definitions, and / or use of terms in the materials attached to this specification are inconsistent or conflicting with the contents described in this specification, the descriptions, definitions, and / or use of terms in this specification shall prevail.

[0105] Finally, it should be understood that the embodiments described in this specification are only used to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, as an example and not a limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly introduced and described in this specification.

Claims

1. A driving safety detection method, characterized in that: The method comprises: Acquiring auxiliary data, wherein the auxiliary data includes at least one of battery system data, drive system data, driving posture data, and environmental detection data; Determining fused data based on the auxiliary data; Get historical operation data; Based on the historical operation data and the fused data, the vehicle driving risk is determined.

2. The method according to claim 1, characterized in that: The method further comprises: In response to the vehicle driving risk meeting a preset risk condition, a safety mechanism is triggered.

3. The method according to claim 1, characterized in that: The battery system data includes battery pack temperature data, total voltage of the battery pack, single cell voltage and charge and discharge current, and insulation resistance of the battery system.

4. The method according to claim 1, characterized in that: The drive system data includes motor parameters and electronic control component parameters; The motor parameters include the motor's rotational speed, torque, and vibration amplitude; the electronic control component parameters include the working state of the electronic components inside the electronic control component, the connection status of the communication line, and the accuracy of the control signal.

5. The method according to claim 1, characterized in that: The driving posture data includes the longitudinal and lateral accelerations of the vehicle and the pitch and roll angles of the vehicle body.

6. The method according to claim 1, characterized in that: The environmental detection data includes target information and identification information; the target information includes the distance, speed, and relative movement direction of the vehicle or obstacle ahead; the identification information includes road markings and traffic signs.

7. The method according to any one of claims 1 to 6, characterized in that: The determining of the vehicle driving risk based on the historical operation data and the fusion data includes: Based on the historical operation data and the fused data, the vehicle driving risk is determined through a safety risk assessment model, and the safety risk assessment model is a machine learning model.

8. A driving safety detection system, characterized in that: It includes a first acquisition module, a fusion module, a second acquisition module, and a determination module; The first acquisition module is configured to acquire auxiliary data, wherein the auxiliary data includes at least one of battery system data, drive system data, driving posture data, and environment detection data; The fusion module is configured to determine fused data based on the auxiliary data; The second acquisition module is configured to acquire historical operation data; The determination acquisition module is configured to determine the vehicle driving risk based on the historical operation data and the fusion data.

9. A driving safety detection device, comprising a processor, characterized in that: The processor is used to execute the driving safety detection method as described in any one of claims 1-7.

10. A computer-readable storage medium storing computer instructions, characterized in that: After the computer reads the computer instructions in the storage medium, the computer executes the driving safety detection method as described in any one of claims 1 to 7.

Images