Fault detection method and device, electronic equipment and storage medium
By determining the sensor type and setting the corresponding fault detection dimensions and methods, the real-time problem of vehicle sensor fault detection is solved, the accuracy and reliability of detection are improved, and the vehicle driving safety is ensured.
Patent Information
- Application Number
- CN202411277128.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-12
- Publication Date
- 2024-11-12
AI Technical Summary
The prior art cannot detect sensor failures in vehicles in real time, which may not be able to detect sensor failures in time, affecting vehicle driving safety.
By determining the sensor type and setting the corresponding fault detection dimensions and detection methods, real-time fault detection of the sensor is realized, including sensor self-detection and associated detection dimensions, ensuring the accuracy and reliability of the detection results.
Real-time fault detection of vehicle sensors is realized, safety during vehicle driving is improved, and the accuracy and reliability of detection results are ensured.
Smart Images

Figure CN118936928A_ABST
Abstract
Description
Technical Field
[0001] Embodiments of the present invention relate to the technical field of vehicle fault detection, and in particular to a fault detection method, device, electronic device and storage medium. Background Art
[0002] With the popularization of vehicle autonomous driving functions, in order to ensure the safety of the vehicle during driving and the normal operation of software functions, it is necessary to ensure that the sensors in the vehicle can operate normally.
[0003] At present, as more and more sensors are integrated into vehicles, it is inevitable that certain difficulties will arise in sensor fault detection. In practical applications, fault detection of sensors in vehicles mostly requires testing of the sensor hardware itself. However, this method cannot perform fault detection on sensors in vehicles in real time, and there may be a problem of not being able to detect sensor faults in a timely manner.
[0004] In order to solve the above problems, it is necessary to improve the fault detection method of the sensor. Summary of the invention
[0005] The embodiments of the present invention provide a fault detection method, device, electronic device and storage medium to realize the problem that the existing technology needs to rely on hardware detection when performing fault detection on sensors. Since the sensor cannot be detected in real time, it may not be possible to detect the sensor fault in time.
[0006] In a first aspect, an embodiment of the present invention provides a fault detection method, including:
[0007] Determine at least one sensor to be detected in the target vehicle, and determine the sensor type of each sensor to be detected; wherein the sensor type includes a first sensor type with an associated sensor or a second sensor type without an associated sensor;
[0008] For each sensor to be detected, determining a fault detection dimension corresponding to the current sensor to be detected according to the sensor type of the current sensor to be detected;
[0009] Based on the fault detection method corresponding to the fault detection dimension, fault detection is performed on the to-be-detected data of the current to-be-detected sensor to obtain a target fault detection result.
[0010] In a second aspect, an embodiment of the present invention further provides a fault detection device, including:
[0011] A type determination module, used to determine at least one sensor to be detected in the target vehicle, and determine the sensor type of each sensor to be detected; wherein the sensor type includes a first sensor type with an associated sensor or a second sensor type without an associated sensor;
[0012] A detection dimension determination module, used for determining, for each sensor to be detected, a fault detection dimension corresponding to the current sensor to be detected according to the sensor type of the current sensor to be detected;
[0013] The detection result determination module is used to perform fault detection on the to-be-detected data of the current to-be-detected sensor based on the fault detection method corresponding to the fault detection dimension to obtain a target fault detection result.
[0014] In a third aspect, an embodiment of the present invention further provides an electronic device, the electronic device comprising:
[0015] one or more processors;
[0016] A storage device for storing one or more programs;
[0017] When the one or more programs are executed by the one or more processors, the one or more processors implement the fault detection method described in any embodiment of the present invention.
[0018] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the fault detection method described in any embodiment of the present invention.
[0019] In a fifth aspect, an embodiment of the present invention further provides a computer program product, including a computer program, which, when executed by a processor, implements the fault detection method as described in any embodiment of the present invention.
[0020] The embodiment of the present invention provides a fault detection method, device, electronic device and storage medium, which determines at least one sensor to be detected in a target vehicle and determines the sensor type of each sensor to be detected; wherein the sensor type includes a first sensor type with an associated sensor or a second sensor type without an associated sensor; for each sensor to be detected, the fault detection dimension corresponding to the current sensor to be detected is determined according to the sensor type of the current sensor to be detected; based on the fault detection mode corresponding to the fault detection dimension, the data to be detected of the current sensor to be detected is fault detected to obtain the target fault detection result. In this technical solution, the sensors are divided into a first sensor type with an associated sensor and a second sensor type without an associated sensor according to whether the sensor data collected by the sensors in the target vehicle are the same observation quantity. Further, different fault detection dimensions are set for sensors of different sensor types, wherein the fault detection dimension corresponding to the first sensor type includes a sensor self-detection dimension and / or a sensor associated detection dimension, and the fault detection dimension corresponding to the second sensor type is a sensor self-detection dimension. On this basis, according to the fault detection dimension corresponding to the sensor type to which each sensor belongs, the fault detection mode corresponding to each sensor is determined, and the corresponding fault detection result is obtained. The advantage of this arrangement is that by using a progressive fault detection method to detect faults in the sensors in the vehicle, not only can the corresponding sensors be detected in real time based on the sensor data, but also the accuracy and reliability of the sensor fault detection results can be guaranteed. This solves the problem that the existing technology needs to rely on hardware detection when performing fault detection on sensors, and the problem that sensor faults cannot be discovered in time due to the inability to perform real-time detection on the sensors is solved. This achieves real-time fault detection of sensors in the vehicle and guarantees the accuracy and reliability of the detection results, thereby improving the safety of the vehicle during driving. BRIEF DESCRIPTION OF THE DRAWINGS
[0021] Other features, objects and advantages of the present invention will become more apparent by reading the detailed description of non-limiting embodiments made with reference to the following drawings. The drawings are only for the purpose of illustrating preferred embodiments and are not to be considered as limiting the present invention. Also, the same reference symbols are used throughout the drawings to represent the same parts. In the drawings:
[0022] Figure 1 is a flow chart of a fault detection method provided in an embodiment of the present invention;
[0023] Figure 2 is a flow chart of a fault detection method provided in an embodiment of the present invention;
[0024] Figure 3is a schematic diagram of performing fault detection on a sensor based on a sensor self-detection dimension provided in an embodiment of the present invention;
[0025] Figure 4 is a schematic diagram of performing fault detection on a sensor based on a sensor association detection dimension provided in an embodiment of the present invention;
[0026] Figure 5 is a structural schematic diagram of a fault detection device provided in an embodiment of the present invention;
[0027] Figure 6 It is a structural schematic diagram of an electronic device provided in an embodiment of the present invention. DETAILED DESCRIPTION
[0028] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the present invention, rather than to limit the present invention. It should also be noted that, for ease of description, only parts related to the present invention, rather than all structures, are shown in the accompanying drawings.
[0029] Before discussing the exemplary embodiments in more detail, it should be mentioned that some exemplary embodiments are described as processes or methods depicted as flow charts. Although the flow charts describe the operations (or steps) as sequential processes, many of the operations (or steps) therein can be implemented in parallel, concurrently or simultaneously. In addition, the order of the operations can be rearranged. The process can be terminated when its operation is completed, but can also have additional steps not included in the accompanying drawings. The process can correspond to a method, function, procedure, subroutine, subprogram, etc.
[0030] Among them, the acquisition, storage, use and processing of data in the technical solution of this application are in compliance with the relevant provisions of national laws and regulations. It should be noted that in the embodiments of this application, some existing solutions in the industry such as certain software, components or models may be mentioned, which should be considered as exemplary, and their purpose is only to illustrate the feasibility of the implementation of the technical solution of this application, but it does not mean that the applicant has or will necessarily use the solution.
[0031] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein.
[0032] Embodiment 1
[0033] Figure 1This is a flow chart of a fault detection method provided in an embodiment of the present invention. This embodiment can be applied to determine the fault detection dimension corresponding to each sensor according to the sensor type to which the sensor in the vehicle belongs, and perform fault detection on the corresponding sensor based on the pre-set fault detection method corresponding to the fault detection dimension to obtain the fault detection result. The method of this embodiment can be executed by a fault detection device, which can be implemented in hardware and / or software. The device can be configured in a fault detection server. The method specifically includes the following steps:
[0034] S110: Determine at least one sensor to be detected in the target vehicle, and determine the sensor type of each sensor to be detected.
[0035] The target vehicle refers to a vehicle that needs to detect whether there is a sensor fault in real time during driving. The sensor to be detected refers to a sensor in the target vehicle. For example, the sensor to be detected can be an inertial sensor, a wheel speed meter sensor, a positioning sensor, a radar sensor, or a visual semantic sensor, etc., or the sensor to be detected can also be a camera sensor or a point cloud device sensor, etc. The specific type of the sensor is not limited in this technical solution. The sensor type includes a first sensor type with an associated sensor or a second sensor type without an associated sensor.
[0036] In practical applications, in order to ensure the safety of the target vehicle during driving, different sensors collect sensor data to assist the normal operation of the vehicle functions of the target vehicle. If the sensor itself has a fault, the sensor data it collects may be wrong, which in turn affects the driving safety or system stability of the target vehicle when the target vehicle works based on the sensor data. Based on this, it is necessary to perform fault detection on at least one sensor to be detected in the target vehicle during the driving process of the target vehicle to determine whether each sensor to be detected has a fault, and to perform early warning processing in a timely manner when a fault exists.
[0037] Specifically, for each sensor to be detected in the target vehicle, it is necessary to determine the sensor type corresponding to the corresponding sensor to be detected, and then determine the fault detection method corresponding to the sensor to be detected according to the sensor type of the sensor to be detected.
[0038] Optionally, determining the sensor type of each sensor to be detected includes: determining whether the sensor to be detected is a positioning sensor or a wheel speed meter sensor; if so, determining that the sensor to be detected belongs to a first sensor type; if not, determining that the sensor to be detected belongs to a second sensor type.
[0039] In the present technical solution, when determining whether the sensor to be detected is faulty, if the sensor to be detected is a positioning sensor or a wheel speed meter sensor, the sensor to be detected is classified as the first sensor type, and the associated sensors corresponding to the positioning sensor and the wheel speed meter sensor are all inertial sensors. If the sensor to be detected is an inertial sensor, a radar sensor, a visual semantic sensor, or other sensor with sensor data, the sensor to be detected is classified as the second sensor type.
[0040] S120 . For each sensor to be detected, determine a fault detection dimension corresponding to the current sensor to be detected according to the sensor type of the current sensor to be detected.
[0041] Among them, the fault detection dimension includes a sensor self-detection dimension and / or a sensor association detection dimension. The sensor self-detection dimension refers to a detection dimension for performing value detection, acquisition frequency detection or variance detection on sensor data collected by the sensor to be detected. The sensor association detection dimension refers to a detection dimension for performing fault detection on the current sensor to be detected based on sensor data of the current sensor to be detected and at least one associated sensor that has association with the sensor data of the current sensor to be detected.
[0042] Optionally, the fault detection dimension corresponding to the current sensor to be detected is determined according to the sensor type of the current sensor to be detected, including: if the current sensor to be detected belongs to the first sensor type, then determining that the fault detection dimension corresponding to the current sensor to be detected includes a sensor self-detection dimension and / or a sensor associated detection dimension; if the current sensor to be detected belongs to the second sensor type, then determining that the fault detection dimension corresponding to the current sensor to be detected is a sensor self-detection dimension.
[0043] In practical applications, more and more sensors are integrated into the automotive domain controller in the target vehicle. Different sensors collect different sensor data, and the sensor data collected by some sensors can observe the same observation quantity.
[0044] In the present technical solution, sensors that can observe the same observation quantity are regarded as associated sensors, and accordingly, their corresponding sensor types are classified as the first sensor type, and sensors without associated sensors are classified as the second sensor type.
[0045] Exemplarily, if the current sensor to be detected is a positioning sensor, the sensor data collected by the positioning sensor is the position data corresponding to the target vehicle, and the associated sensor corresponding to the positioning sensor is an inertial sensor. The inertial sensor uses inertial sensors such as gyroscopes and accelerometers to measure the attitude, angular velocity and acceleration of the target vehicle, thereby calculating the position, speed and direction of the target vehicle. In other words, the positioning sensor and the inertial sensor can jointly observe the position data corresponding to the target vehicle. If the current sensor to be detected is a positioning sensor, the current sensor to be detected corresponds to the first sensor type, and its corresponding fault detection dimension includes a sensor self-detection dimension and / or a sensor associated detection dimension.
[0046] For example, if the current sensor to be detected is a wheel speed meter sensor, the sensor data collected by the wheel speed meter sensor is the speed data corresponding to the target vehicle, and the associated sensor corresponding to the wheel speed meter sensor is an inertial sensor. The inertial sensor can measure the attitude, angular velocity and acceleration of the target vehicle using inertial sensors such as gyroscopes and accelerometers, thereby inferring the position, speed and direction of the target vehicle. In other words, the wheel speed meter sensor and the inertial sensor can jointly observe the speed data corresponding to the target vehicle. If the current sensor to be detected is a wheel speed meter sensor, the current sensor to be detected corresponds to the first sensor type, and its corresponding fault detection dimension includes a sensor self-detection dimension and / or a sensor associated detection dimension.
[0047] Exemplarily, if the current sensor to be detected is an inertial sensor, a lidar sensor, or a visual semantic sensor, etc., the current sensor to be detected corresponds to the second sensor type, and its corresponding fault detection dimension is determined to be the sensor self-detection dimension.
[0048] S130 . Based on the fault detection method corresponding to the fault detection dimension, perform fault detection on the data to be detected of the current sensor to be detected to obtain a target fault detection result.
[0049] The data to be detected can be understood as the sensor data collected by the current sensor to be detected. In this technical solution, different fault detection dimensions correspond to different fault detection methods, and the same sensor to be detected corresponds to one or more fault dimensions, and the target fault detection result refers to the comprehensive result obtained by comprehensively combining the detection results corresponding to at least one fault detection dimension.
[0050] Exemplarily, taking the current sensor to be detected as a positioning sensor, its corresponding fault detection dimension includes a sensor self-detection dimension and / or a sensor associated detection dimension. Fault detection is performed on the data to be detected based on the fault detection method corresponding to the sensor self-detection dimension to obtain a first fault detection result. Fault detection is performed on the data to be detected based on the fault detection method corresponding to the sensor associated detection dimension to obtain a second fault detection result. The target fault detection result is a comprehensive result obtained based on the first fault detection result and the second fault detection result, which is used to characterize whether the current sensor to be detected has a fault.
[0051] The embodiment of the present invention provides a fault detection method, device, electronic device and storage medium, which determines at least one sensor to be detected in a target vehicle and determines the sensor type of each sensor to be detected; wherein the sensor type includes a first sensor type with an associated sensor or a second sensor type without an associated sensor; for each sensor to be detected, the fault detection dimension corresponding to the current sensor to be detected is determined according to the sensor type of the current sensor to be detected; based on the fault detection mode corresponding to the fault detection dimension, the data to be detected of the current sensor to be detected is fault detected to obtain the target fault detection result. In this technical solution, the sensors are divided into a first sensor type with an associated sensor and a second sensor type without an associated sensor according to whether the sensor data collected by the sensors in the target vehicle are the same observation quantity. Further, different fault detection dimensions are set for sensors of different sensor types, wherein the fault detection dimension corresponding to the first sensor type includes a sensor self-detection dimension and / or a sensor associated detection dimension, and the fault detection dimension corresponding to the second sensor type is a sensor self-detection dimension. On this basis, according to the fault detection dimension corresponding to the sensor type to which each sensor belongs, the fault detection mode corresponding to each sensor is determined, and the corresponding fault detection result is obtained. The advantage of this arrangement is that by using a progressive fault detection method to detect faults in the sensors in the vehicle, not only can the corresponding sensors be detected in real time based on the sensor data, but also the accuracy and reliability of the sensor fault detection results can be guaranteed. This solves the problem that the existing technology needs to rely on hardware detection when performing fault detection on sensors, and the problem that sensor faults cannot be discovered in time due to the inability to perform real-time detection on the sensors is solved. This achieves real-time fault detection of sensors in the vehicle and guarantees the accuracy and reliability of the detection results, thereby improving the safety of the vehicle during driving.
[0052] Embodiment 2
[0053] Figure 2Flow chart of a fault detection method provided in an embodiment of the present invention. The embodiment of the present invention further optimizes the above embodiment on the basis of the above embodiment, and the embodiment of the present invention can be combined with various optional solutions in one or more of the above embodiments. Figure 2 As shown, the fault detection method provided in the embodiment of the present invention may include the following steps:
[0054] S210: Determine at least one sensor to be detected in the target vehicle, and determine the sensor type of each sensor to be detected.
[0055] S220: Determine a fault detection dimension corresponding to the current sensor to be detected according to the sensor type of the current sensor to be detected.
[0056] S230 . Based on the fault detection method corresponding to the fault detection dimension, perform fault detection on the to-be-detected data of the current to-be-detected sensor to obtain a target fault detection result.
[0057] In actual applications, based on the fault detection method corresponding to the fault detection dimension, fault detection is performed on the data to be detected of the current sensor to be detected to obtain a target fault detection result, including: obtaining the data to be detected corresponding to the current sensor to be detected; determining a first fault detection result corresponding to the data to be detected based on the fault detection method corresponding to the numerical detection dimension and / or the frequency detection dimension in the sensor self-detection dimension; if the first fault detection result is a suspected sensor fault, then determining a second fault detection result corresponding to the data to be detected based on the fault detection method corresponding to the variance detection dimension in the sensor self-detection dimension; if the second fault detection result is that the sensor is normal, then determining the target fault detection result corresponding to the current sensor to be detected based on the fault detection method corresponding to the sensor association detection dimension.
[0058] The data to be detected includes sensor numerical data and / or sensor acquisition frequency data. The first fault detection result is that the sensor is normal, the sensor is faulty, or a suspected sensor fault. The second fault detection result is that the sensor is normal or the sensor is faulty.
[0059] In practical applications, when any sensor to be detected in the target vehicle is fault-detected, it is necessary to detect the sensor self-detection dimension. Specifically, the sensor self-detection dimension includes a numerical detection dimension, a frequency detection dimension, and a variance detection dimension. In this technical solution, the fault detection results corresponding to the numerical detection dimension and the frequency detection dimension in the sensor self-detection dimension are used as the first fault detection result, and the fault detection result corresponding to the variance detection dimension is used as the second fault detection result.
[0060] For example, Figure 3As shown, taking the inertial sensor as an example, the acceleration threshold and angular velocity threshold corresponding to the inertial sensor are pre-set, and the preset acquisition frequency corresponding to the inertial sensor (i.e., the timestamp interval between the current frame and the previous frame) is determined. If the inertial sensor data (i.e., the data to be detected) collected by the inertial sensor does not belong to the preset acceleration threshold or angular velocity threshold, then regardless of whether the acquisition frequency of the inertial sensor is normal, the first fault detection result corresponding to the current sensor to be detected is directly determined to be a sensor fault. If the inertial sensor data (i.e., the data to be detected) collected based on the inertial sensor is within the acceleration threshold and the angular velocity threshold, then the detection result of the current sensor to be detected in the numerical detection dimension is determined to be a normal sensor. At the same time, the acquisition frequency of the inertial sensor in two adjacent frames of the inertial sensor is obtained. If the acquisition frequency is within the preset acquisition frequency, then the detection result of the current sensor to be detected in the frequency detection dimension is determined to be a normal sensor. Correspondingly, the first fault detection result corresponding to the current sensor to be detected is a normal sensor. On the contrary, if the value of the inertial sensor data is within the preset acceleration threshold or angular velocity threshold range, but the acquisition frequency of the inertial sensor is not within the preset acquisition frequency, it is determined that the first fault detection result corresponding to the current sensor to be detected is a suspected sensor fault.
[0061] Similarly, if the current sensor to be detected is a wheel speed meter sensor, whether the wheel speed value collected by the wheel speed meter sensor is within the preset wheel speed value range, and whether the collection frequency of the wheel speed meter sensor is within the preset collection frequency range, it can be determined whether the wheel speed meter sensor is normal.
[0062] Similarly, if the current sensor to be detected is a positioning sensor, it can be determined whether the positioning sensor is normal based on the coordinate values obtained by the positioning sensor and whether the confidence given during the use of the positioning sensor is within the corresponding range. At the same time, combined with whether the acquisition frequency of the positioning sensor is within the preset acquisition frequency range.
[0063] Exemplarily, if the current sensor to be detected is a radar sensor or a visual semantic sensor, the point cloud data collected by the current sensor to be detected can be obtained, and the first point cloud number of the point cloud data within the preset coordinate range and the total point cloud number of the point cloud data can be determined, and the proportion of the point cloud to be compared is obtained according to the ratio of the first point cloud number to the total point cloud number. If the proportion of the point cloud to be compared is greater than the preset point cloud proportion, it is determined that the fault detection result of the current sensor to be detected in the numerical detection dimension is that the sensor is normal. At the same time, combined with whether the acquisition frequency of the current sensor to be detected is within the preset acquisition frequency range, the first fault detection result corresponding to the current sensor to be detected can be further determined.
[0064] On this basis, in order to further determine whether the current sensor to be detected is normal, the current sensor to be detected can be further detected based on the variance detection dimension. Specifically, if the first fault detection result is a suspected sensor fault, based on the fault detection method corresponding to the variance detection dimension in the sensor self-detection dimension, the second fault detection result corresponding to the data to be detected is determined, including: determining the actual value and predicted value corresponding to the data to be detected, and determining the first residual corresponding to the actual value and the second residual corresponding to the predicted value; if the residual difference between the first residual and the second residual is less than the preset residual difference, then the second fault detection result corresponding to the data to be detected is determined to be a normal sensor; if the residual difference is greater than the preset residual difference, then the second fault detection result is determined to be a sensor fault.
[0065] On the basis of the above example, taking the current sensor to be detected as an inertial sensor as an example, the Jacobian matrix, the covariance matrix of the system state quantity and the observation noise are constructed according to the inertial sensor data (i.e., the data to be detected) collected by the inertial sensor, and the actual value and predicted value corresponding to the inertial sensor data are obtained based on the Jacobian matrix, the covariance matrix of the system state quantity and the observation noise. Further, based on the residual detection method, the first residual corresponding to the actual value and the second residual corresponding to the predicted value are determined. If the residual difference between the first residual and the second residual is less than the preset residual difference, the second fault detection result corresponding to the data to be detected is determined to be a normal sensor; if the residual difference is greater than the preset residual difference, the second fault detection result is determined to be a sensor fault.
[0066] Optionally, a target fault detection result corresponding to the current sensor to be detected is determined based on a fault detection method corresponding to a sensor-associated detection dimension, including: if the current sensor to be detected belongs to a first sensor type, using the inertial sensor as an associated sensor of the current sensor to be detected; determining first data to be used corresponding to the current sensor to be detected, and second data to be used corresponding to the associated sensor; if a target difference between the first data to be used and the second data to be used is less than or equal to a preset difference, determining that the target fault detection result corresponding to the current sensor to be detected is a normal sensor; if the target difference is greater than a preset difference, determining that the target fault detection result corresponding to the current sensor to be detected is a faulty sensor.
[0067] The first data to be used refers to the difference between the current acquisition time and the nearest historical acquisition time corresponding to the current sensor to be detected, and the second data to be used refers to the integral component of the associated sensor between the current acquisition time and the historical acquisition time;
[0068] Based on the above example, if the current sensor to be detected is a positioning sensor or a wheel speed meter sensor, it is determined that the current sensor to be detected belongs to the first sensor type, and the associated sensors of the positioning sensor and the wheel speed meter sensor are both inertial sensors.
[0069] Optionally, if the current sensor to be detected is a positioning sensor, the integral component is the position component between the current collection time and the historical collection time; if the current sensor to be detected is a tachometer sensor, the integral component is the speed component between the current collection time and the historical collection time.
[0070] Take the current sensor to be detected as a positioning sensor as an example, Figure 4 As shown, the position data corresponding to the target vehicle collected by the positioning sensor is obtained, and when the positioning sensor is not in a locked state (that is, the positioning sensor is in a state where the position data can be collected normally), the first data to be used is obtained according to the difference between the sensor data between the current collection time and the historical collection time. At the same time, the acceleration data of the target vehicle is extracted from the inertial sensor data collected by the inertial sensor, and the velocity component is obtained according to the integration of the acceleration data, and then the velocity component is integrated to obtain the position component between two adjacent collection times (that is, the IMU data integration interval must be the same as the GNSS data interval to ensure the consistency of the integral amount, wherein the IMU data is the inertial sensor data, and the GNSS data is the position data collected based on the positioning sensor), and the position component is used as the second data to be used. If the target difference between the first data to be used and the second data to be used is less than or equal to the preset difference, it is determined that the target fault detection result corresponding to the current sensor to be detected is a normal sensor; if the target difference is greater than the preset difference, it is determined that the target fault detection result corresponding to the current sensor to be detected is a faulty sensor.
[0071] Take the wheel speed sensor as an example, and continue to refer to Figure 4 , obtain the wheel speed information data corresponding to the target vehicle collected by the wheel speed meter sensor, and obtain the first data to be used according to the difference between the sensor data between the current collection time and the historical collection time. At the same time, extract the acceleration data of the target vehicle from the inertial sensor data collected by the inertial sensor, and obtain the speed component according to the acceleration data integration (that is, the imu data integration interval must be the same as the wheel speed, that is, the data interval, to ensure the consistency of the integral amount), and use the speed component as the second data to be used. If the target difference between the first data to be used and the second data to be used is less than or equal to the preset difference, it is determined that the target fault detection result corresponding to the current sensor to be detected is a normal sensor; if the target difference is greater than the preset difference, it is determined that the target fault detection result corresponding to the current sensor to be detected is a faulty sensor.
[0072] The embodiment of the present invention provides a fault detection method, device, electronic device and storage medium, which determines at least one sensor to be detected in a target vehicle and determines the sensor type of each sensor to be detected; wherein the sensor type includes a first sensor type with an associated sensor or a second sensor type without an associated sensor; for each sensor to be detected, the fault detection dimension corresponding to the current sensor to be detected is determined according to the sensor type of the current sensor to be detected; based on the fault detection mode corresponding to the fault detection dimension, the data to be detected of the current sensor to be detected is fault detected to obtain the target fault detection result. In this technical solution, the sensors are divided into a first sensor type with an associated sensor and a second sensor type without an associated sensor according to whether the sensor data collected by the sensors in the target vehicle are the same observation quantity. Further, different fault detection dimensions are set for sensors of different sensor types, wherein the fault detection dimension corresponding to the first sensor type includes a sensor self-detection dimension and / or a sensor associated detection dimension, and the fault detection dimension corresponding to the second sensor type is a sensor self-detection dimension. On this basis, according to the fault detection dimension corresponding to the sensor type to which each sensor belongs, the fault detection mode corresponding to each sensor is determined, and the corresponding fault detection result is obtained. The advantage of this arrangement is that by using a progressive fault detection method to detect faults in the sensors in the vehicle, not only can the corresponding sensors be detected in real time based on the sensor data, but also the accuracy and reliability of the sensor fault detection results can be guaranteed. This solves the problem that the existing technology needs to rely on hardware detection when performing fault detection on sensors, and the problem that sensor faults cannot be discovered in time due to the inability to perform real-time detection on the sensors is solved. This achieves real-time fault detection of sensors in the vehicle and guarantees the accuracy and reliability of the detection results, thereby improving the safety of the vehicle during driving.
[0073] Embodiment 3
[0074] Figure 5 This is a schematic diagram of the structure of a fault detection device provided in an embodiment of the present invention. The technical solution of this embodiment can be applied to determine the fault detection dimension corresponding to each sensor according to the sensor type of the sensor in the vehicle, and perform fault detection on the corresponding sensor based on the pre-set fault detection method corresponding to the fault detection dimension to obtain the fault detection result. The device can be implemented by software and / or hardware, and is generally integrated on any electronic device with network communication function, including but not limited to: servers, computers, personal digital assistants and other devices. Figure 5 As shown, the fault detection device provided in this embodiment may include: a type determination module 310, a detection dimension determination module 320 and a detection result determination module 330.
[0075] The type determination module 310 is used to determine at least one sensor to be detected in the target vehicle and determine the sensor type of each sensor to be detected; wherein the sensor type includes a first sensor type with an associated sensor or a second sensor type without an associated sensor;
[0076] A detection dimension determination module 320 is used to determine, for each sensor to be detected, a fault detection dimension corresponding to the current sensor to be detected according to the sensor type of the current sensor to be detected;
[0077] The detection result determination module 330 is used to perform fault detection on the to-be-detected data of the current to-be-detected sensor based on the fault detection method corresponding to the fault detection dimension to obtain a target fault detection result.
[0078] The embodiment of the present invention provides a fault detection method, device, electronic device and storage medium, which determines at least one sensor to be detected in a target vehicle and determines the sensor type of each sensor to be detected; wherein the sensor type includes a first sensor type with an associated sensor or a second sensor type without an associated sensor; for each sensor to be detected, the fault detection dimension corresponding to the current sensor to be detected is determined according to the sensor type of the current sensor to be detected; based on the fault detection mode corresponding to the fault detection dimension, the data to be detected of the current sensor to be detected is fault detected to obtain the target fault detection result. In this technical solution, the sensors are divided into a first sensor type with an associated sensor and a second sensor type without an associated sensor according to whether the sensor data collected by the sensors in the target vehicle are the same observation quantity. Further, different fault detection dimensions are set for sensors of different sensor types, wherein the fault detection dimension corresponding to the first sensor type includes a sensor self-detection dimension and / or a sensor associated detection dimension, and the fault detection dimension corresponding to the second sensor type is a sensor self-detection dimension. On this basis, according to the fault detection dimension corresponding to the sensor type to which each sensor belongs, the fault detection mode corresponding to each sensor is determined, and the corresponding fault detection result is obtained. The advantage of this arrangement is that by using a progressive fault detection method to detect faults in the sensors in the vehicle, not only can the corresponding sensors be detected in real time based on the sensor data, but also the accuracy and reliability of the sensor fault detection results can be guaranteed. This solves the problem that the existing technology needs to rely on hardware detection when performing fault detection on sensors, and the problem that sensor faults cannot be discovered in time due to the inability to perform real-time detection on the sensors is solved. This achieves real-time fault detection of sensors in the vehicle and guarantees the accuracy and reliability of the detection results, thereby improving the safety of the vehicle during driving.
[0079] On the basis of the above embodiment, optionally, the type determination module includes a sensor determination submodule, which is used to determine whether the sensor to be detected is a positioning sensor or a wheel speed meter sensor;
[0080] A first sensor type determination submodule, configured to determine that the sensor to be detected belongs to the first sensor type;
[0081] The second sensor type determination submodule is used to determine, if not, whether the sensor to be detected belongs to the second sensor type.
[0082] On the basis of the above embodiment, optionally, the detection dimension determination module includes: a first detection dimension determination submodule, which is used to determine that the fault detection dimension corresponding to the current sensor to be detected includes a sensor self-detection dimension and / or a sensor associated detection dimension if the current sensor to be detected belongs to the first sensor type;
[0083] The second detection dimension determination submodule is used to determine that the fault detection dimension corresponding to the current sensor to be detected is a sensor self-detection dimension if the current sensor to be detected belongs to the second sensor type; wherein the sensor self-detection dimension includes at least one of a numerical detection dimension, a frequency detection dimension and a variance detection dimension; wherein the sensor association detection dimension refers to a detection dimension for performing fault detection on the current sensor to be detected based on sensor data of the current sensor to be detected and at least one associated sensor that is associated with the sensor data of the current sensor to be detected.
[0084] On the basis of the above embodiment, optionally, the detection result determination module includes: a data acquisition submodule, used to obtain the data to be detected corresponding to the current sensor to be detected; wherein the data to be detected includes sensor numerical data and / or sensor acquisition frequency data;
[0085] A first fault detection result determination submodule, used to determine a first fault detection result corresponding to the data to be detected based on the fault detection method corresponding to the numerical detection dimension and / or the frequency detection dimension; wherein the first fault detection result is a normal sensor, a sensor fault, or a suspected sensor fault;
[0086] A second fault detection result determination submodule is used to determine a second fault detection result corresponding to the data to be detected based on the fault detection method corresponding to the variance detection dimension if the first fault detection result is a suspected sensor fault; wherein the second fault detection result is a normal sensor or a sensor fault;
[0087] The target fault detection result determination submodule is used to determine the target fault detection result corresponding to the current sensor to be detected based on the fault detection method corresponding to the sensor-associated detection dimension if the second fault detection result is that the sensor is normal.
[0088] On the basis of the above embodiment, optionally, the second fault detection result determination submodule includes: a residual determination unit, used to determine an actual value and a predicted value corresponding to the data to be detected, and to determine a first residual corresponding to the actual value and a second residual corresponding to the predicted value;
[0089] The first unit is configured to determine that the second fault detection result corresponding to the to-be-detected data is that the sensor is normal if the residual difference between the first residual and the second residual is less than a preset residual difference;
[0090] The second unit is configured to determine that the second fault detection result is a sensor fault if the residual difference value is greater than a preset residual difference value.
[0091] On the basis of the above embodiment, optionally, the detection result determination module includes: an associated sensor determination submodule, configured to use the inertial sensor as an associated sensor of the current sensor to be detected if the current sensor to be detected belongs to the first sensor type;
[0092] The submodule for determining the data to be used is used to determine the first data to be used corresponding to the current sensor to be detected, and the second data to be used corresponding to the associated sensor; wherein the first data to be used refers to the difference between the sensor data of the current acquisition time and the nearest historical acquisition time corresponding to the current sensor to be detected, and the second data to be used refers to the integral component of the associated sensor between the current acquisition time and the historical acquisition time;
[0093] A first submodule is configured to determine that a target fault detection result corresponding to the current sensor to be detected is a normal sensor if a target difference between the first data to be used and the second data to be used is less than or equal to a preset difference;
[0094] The second submodule is used to determine that the target fault detection result corresponding to the current sensor to be detected is a faulty sensor if the target difference is greater than a preset difference.
[0095] The fault detection device provided in the embodiment of the present invention can execute the fault detection method provided in any embodiment of the present invention mentioned above, and has the corresponding functions and beneficial effects of executing the fault detection method. For detailed process, please refer to the relevant operations of the fault detection method in the above embodiment.
[0096] Embodiment 4
[0097] Figure 61 is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. The electronic device 10 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.
[0098] like Figure 6 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.
[0099] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.
[0100] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as a fault detection method.
[0101] In some embodiments, the fault detection method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the fault detection method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the fault detection method in any other appropriate manner (e.g., by means of firmware).
[0102] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.
[0103] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.
[0104] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
[0105] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).
[0106] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.
[0107] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.
[0108] Embodiment 5
[0109] An embodiment of the present invention further provides a computer program product, including a computer program, which, when executed by a processor, implements the fault detection method provided in any embodiment of the present application.
[0110] In the process of implementation, the computer program product can be written in one or more programming languages or a combination thereof to perform the computer program code of the present invention, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).
[0111] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.
[0112] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims
1. A fault detection method, characterized in that: The method comprises: Determine at least one sensor to be detected in the target vehicle, and determine the sensor type of each sensor to be detected; wherein the sensor type includes a first sensor type with an associated sensor or a second sensor type without an associated sensor; For each sensor to be detected, determining a fault detection dimension corresponding to the current sensor to be detected according to the sensor type of the current sensor to be detected; Based on the fault detection method corresponding to the fault detection dimension, fault detection is performed on the to-be-detected data of the current to-be-detected sensor to obtain a target fault detection result.
2. The method according to claim 1, characterized in that The step of determining the sensor type of each sensor to be detected includes: Determine whether the sensor to be detected is a positioning sensor or a wheel speed meter sensor; If yes, determining that the sensor to be detected belongs to the first sensor type; If not, it is determined that the sensor to be detected belongs to the second sensor type.
3. The method according to claim 1, characterized in that The determining, according to the sensor type of the current sensor to be detected, a fault detection dimension corresponding to the current sensor to be detected includes: If the current sensor to be detected belongs to the first sensor type, determining that the fault detection dimension corresponding to the current sensor to be detected includes a sensor self-detection dimension and / or a sensor association detection dimension; If the current sensor to be detected belongs to the second sensor type, determining that the fault detection dimension corresponding to the current sensor to be detected is the sensor self-detection dimension; wherein the sensor self-detection dimension includes at least one of a value detection dimension, a frequency detection dimension, and a variance detection dimension; The sensor association detection dimension refers to a detection dimension for performing fault detection on the current sensor to be detected based on sensor data of the current sensor to be detected and at least one associated sensor associated with sensor data of the current sensor to be detected.
4. The method according to claim 3, characterized in that The method of performing fault detection on the to-be-detected data of the current to-be-detected sensor to obtain a target fault detection result based on the fault detection method corresponding to the fault detection dimension includes: Acquire the data to be detected corresponding to the current sensor to be detected; wherein the data to be detected includes sensor numerical data and / or sensor acquisition frequency data; Based on the fault detection mode corresponding to the numerical detection dimension and / or the frequency detection dimension, determine a first fault detection result corresponding to the data to be detected; wherein the first fault detection result is a normal sensor, a sensor fault, or a suspected sensor fault; If the first fault detection result is the suspected sensor fault, determining a second fault detection result corresponding to the data to be detected based on the fault detection method corresponding to the variance detection dimension; wherein the second fault detection result is that the sensor is normal or the sensor is faulty; If the second fault detection result is that the sensor is normal, the target fault detection result corresponding to the current sensor to be detected is determined based on the fault detection method corresponding to the sensor-associated detection dimension.
5. The method according to claim 4, characterized in that The determining, based on the fault detection method corresponding to the variance detection dimension in the sensor self-detection dimension, a second fault detection result corresponding to the data to be detected includes: Determine an actual value and a predicted value corresponding to the data to be detected, and determine a first residual corresponding to the actual value and a second residual corresponding to the predicted value; If the residual difference between the first residual and the second residual is less than a preset residual difference, determining that the second fault detection result corresponding to the data to be detected is that the sensor is normal; If the residual difference is greater than the preset residual difference, it is determined that the second fault detection result is a sensor fault.
6. The method according to claim 2, characterized in that The determining the target fault detection result corresponding to the current sensor to be detected based on the fault detection mode corresponding to the sensor-associated detection dimension includes: If the current sensor to be detected belongs to the first sensor type, using the inertial sensor as an associated sensor of the current sensor to be detected; Determine the first data to be used corresponding to the current sensor to be detected, and the second data to be used corresponding to the associated sensor; wherein the first data to be used refers to the difference between the current acquisition time and the nearest historical acquisition time corresponding to the current sensor to be detected, and the second data to be used refers to the integral component of the associated sensor between the current acquisition time and the historical acquisition time; If the target difference between the first data to be used and the second data to be used is less than or equal to a preset difference, determining that the target fault detection result corresponding to the current sensor to be detected is a normal sensor; If the target difference is greater than the preset difference, it is determined that the target fault detection result corresponding to the current sensor to be detected is a faulty sensor.
7. The method according to claim 6, characterized in that include: If the current sensor to be detected is the positioning sensor, the integral component is the position component between the current acquisition time and the historical acquisition time; If the current sensor to be detected is the wheel speed meter sensor, the integral component is the speed component between the current collection time and the historical collection time.
8. A fault detection device, characterized in that: The device comprises: A type determination module, used to determine at least one sensor to be detected in the target vehicle, and determine the sensor type of each sensor to be detected; wherein the sensor type includes a first sensor type with an associated sensor or a second sensor type without an associated sensor; A detection dimension determination module, used for determining, for each sensor to be detected, a fault detection dimension corresponding to the current sensor to be detected according to the sensor type of the current sensor to be detected; The detection result determination module is used to perform fault detection on the to-be-detected data of the current to-be-detected sensor based on the fault detection method corresponding to the fault detection dimension to obtain a target fault detection result.
9. An electronic device, characterized in that: include: one or more processors; A storage device for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the fault detection method described in any one of claims 1-7.
10. A storage medium containing computer executable instructions, characterized in that: The computer executable instructions are used to perform the fault detection method according to any one of claims 1 to 7 when executed by a computer processor.
