Vehicle fault identification method, device and equipment and storage medium
By combining the fault judgment method of image and audio data, the problem of fault detection difficulties in complex automotive electronic systems is solved, the efficiency and accuracy of fault detection are improved, and the maintenance cost is reduced.
Patent Information
- Application Number
- CN202411031177.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-30
- Publication Date
- 2024-12-06
AI Technical Summary
As automotive electronic systems become more complex, fault detection and diagnosis have become more difficult. The existing intelligent fault diagnosis system still needs to rely on experienced technicians, resulting in high maintenance costs and reduced accuracy.
By establishing a method that can use image data and audio data to determine the fault, it is determined whether the target device belongs to a preset first device set or second device set, and adopts different judgment methods to determine the fault result in combination with image and audio data. Improve fault detection efficiency and improve the accuracy of judgment results.
It realizes improving the efficiency and accuracy of fault detection in vehicle fault detection, reducing the technical level of maintenance personnel, and reducing overall costs.
Smart Images

Figure CN119085830A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of vehicle fault detection, and specifically to a vehicle fault identification method, device, equipment and storage medium. Background Art
[0002] With the increasing complexity of automotive electronic systems, especially the use of a large number of sensors and controllers, fault detection and diagnosis have become more difficult. Complex systems may lead to a decrease in the accuracy of fault diagnosis, and also increase the difficulty for maintenance personnel to accurately judge the fault.
[0003] Although modern automobile fault diagnosis systems are becoming more intelligent, the current level of intelligence still needs to be improved. Currently, it still needs to rely on experienced technicians for auxiliary judgment. Therefore, this also requires maintenance personnel to have a higher level of technology and knowledge reserves, and the overall cost is high, which needs further improvement. Summary of the invention
[0004] The present application provides a vehicle fault identification method, device, equipment and storage medium, which can solve the technical problems existing in the above-mentioned related technologies.
[0005] In a first aspect, an embodiment of the present application provides a vehicle fault identification method, which adopts the following technical solution:
[0006] A vehicle fault identification method, characterized in that the vehicle fault identification method comprises:
[0007] Determining whether the target device belongs to a preset first device set and a second device set; wherein at least some elements of the first device set and the second device set are the same;
[0008] If it only belongs to the first device set, acquiring image data of the target device, and determining a fault result of the target device according to the image data;
[0009] If it only belongs to the second device set, obtaining audio data of the target device, and determining the failure result of the target device according to the audio data;
[0010] If the target device belongs to both the first device set and the second device set, the image data and the audio data of the target device are acquired, and the failure result of the target device is determined in combination with the image data and the audio data.
[0011] In combination with the first aspect, in one implementation, acquiring the image data and the audio data of the target device, and determining the fault result of the target device in combination with the image data and the audio data, comprises the following steps:
[0012] Obtaining an image detection result of the target device according to the image data and a preset image detection model;
[0013] Obtaining an audio detection result of the target device according to the audio data and a preset audio detection model;
[0014] Determining whether the image detection result of the target device is consistent with the audio detection result;
[0015] If they are inconsistent, determining the failure result of the target device according to one of them, or determining the failure result of the target device by a preset second detection method;
[0016] If they are consistent, it is determined that the fault result corresponding to both is the fault result of the target device.
[0017] In combination with the first aspect, in one implementation, determining the failure result of the target device according to one of the two comprises the following steps:
[0018] According to a preset selection priority corresponding to the target device, a fault result of the target device is determined according to the image detection result or the audio detection result.
[0019] In combination with the first aspect, in one implementation, determining the failure result of the target device by using a preset second detection method includes the following steps:
[0020] Obtaining secondary detection data of the target device;
[0021] Obtaining a secondary detection result of the target device according to the secondary detection data and a preset secondary detection model;
[0022] According to the secondary detection result, a failure result of the target device is determined.
[0023] In combination with the first aspect, in one implementation, after determining the fault result of the target device according to the secondary detection result, the following steps are included:
[0024] Determining whether the image detection result and the audio detection result are consistent with the secondary detection result;
[0025] If the image detection result is inconsistent with the secondary detection result, updating the image detection model according to the secondary detection result;
[0026] If the audio detection result is inconsistent with the secondary detection result, the audio detection model is updated according to the secondary detection result.
[0027] In combination with the first aspect, in one implementation, obtaining the image detection result of the target device according to the preset image detection model and the image data includes the following steps:
[0028] According to a preset segmentation model, the image data is segmented into judgment unit images corresponding to each module in the target device;
[0029] Obtaining unit detection results of each module in the target device according to a preset unit image detection model corresponding to the judgment unit image;
[0030] The image detection result is obtained according to the detection results of each unit.
[0031] In a second aspect, the embodiment of the present application provides a vehicle fault identification device, which adopts the following technical solution:
[0032] A vehicle fault identification device, the vehicle fault identification device comprising:
[0033] A determination module configured to determine whether the target device belongs to a preset first device set and a second device set; wherein at least some elements in the first device set and the second device set are the same;
[0034] A processing module is configured to, if the target device belongs only to the first device set, obtain image data of the target device and determine a fault result of the target device based on the image data; if the target device belongs only to the second device set, obtain audio data of the target device and determine a fault result of the target device based on the audio data; if the target device belongs to both the first device set and the second device set, obtain image data and audio data of the target device and determine a fault result of the target device in combination with the image data and the audio data.
[0035] In conjunction with the second aspect, in one implementation, the processing module includes:
[0036] an acquisition unit, configured to acquire image data and / or audio data of the target device;
[0037] an image detection unit, configured to obtain an image detection result of the target device according to the image data and a preset image detection model;
[0038] an audio detection unit, configured to obtain an audio detection result of the target device according to the audio data and a preset audio detection model;
[0039] A fusion detection unit is configured to determine whether the image detection result and the audio detection result of the target device are consistent; if inconsistent, determine the fault result of the target device according to one of them, or determine the fault result of the target device by a preset second detection method; if consistent, determine the fault result corresponding to both as the fault result of the target device.
[0040] In a third aspect, the embodiment of the present application provides a vehicle fault identification device, which adopts the following technical solution:
[0041] A vehicle fault identification device comprises a processor, a memory, and a vehicle fault identification program stored in the memory and executable by the processor, wherein when the vehicle fault identification program is executed by the processor, the steps of the vehicle fault identification method as described above are implemented.
[0042] In a fourth aspect, an embodiment of the present application provides a storage medium, which adopts the following technical solution:
[0043] A storage medium stores a vehicle fault identification program, wherein when the vehicle fault identification program is executed by a processor, the steps of the vehicle fault identification method described above are implemented.
[0044] The beneficial effects brought by the technical solution provided in the embodiments of the present application include:
[0045] By establishing a first device set that can use image data to make fault judgments, and a second device set that can use audio data to make fault judgments, when subsequently judging the fault results of related devices in the vehicle, different judgment methods can be adopted according to whether the target device belongs to the first device set or the second device set or both. This greatly improves the fault detection efficiency, and for the target device that can make fault judgments based on both image data and audio data, the judgment results will be more accurate and reliable. BRIEF DESCRIPTION OF THE DRAWINGS
[0046] Figure 1 This is a flow chart of an embodiment of a vehicle fault identification method of the present application;
[0047] Figure 2 This is a functional module diagram of an embodiment of a vehicle fault identification device of the present application;
[0048] Figure 3 This is a schematic diagram of the hardware structure of the vehicle fault identification device involved in the embodiment of the present application. DETAILED DESCRIPTION
[0049] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0050] In order to make the objectives, technical solutions and advantages of the present application clearer, the implementation methods of the present application will be further described in detail below with reference to the accompanying drawings.
[0051] In a first aspect, an embodiment of the present application provides a vehicle fault identification method.
[0052] In one embodiment, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the vehicle fault identification method of the present application. Figure 1 As shown, the vehicle fault identification method includes:
[0053] S100, determining whether the target device belongs to a preset first device set and a second device set; wherein at least some elements of the first device set and the second device set are the same;
[0054] S200, if it only belongs to the first device set, acquiring image data of the target device, and determining a fault result of the target device according to the image data;
[0055] S300, if it only belongs to the second device set, obtaining audio data of the target device, and determining the fault result of the target device according to the audio data;
[0056] S400: If the target device belongs to both the first device set and the second device set, obtain image data and audio data of the target device, and determine a fault result of the target device in combination with the image data and the audio data.
[0057] In the present embodiment, by establishing a first device set capable of using image data for fault judgment, and a second device set capable of using audio data for fault judgment, when subsequently judging the fault results of related devices in the vehicle, different judgment methods can be adopted according to whether the target device belongs to the first device set or the second device set or both. This greatly improves the fault detection efficiency, and for the target device capable of performing fault judgment based on both image data and audio data, the judgment result will also be more accurate and reliable.
[0058] Specifically, when determining the fault result of the target device according to the image data in step S200, the image detection result is obtained through a pre-trained image detection model, and the fault result of the target device is determined according to the image detection result.
[0059] When determining the fault result of the target device according to the audio data in step S300, an image detection result is obtained through a pre-trained image detection model, and the fault result of the target device is determined according to the image detection result.
[0060] As for step S400, determining the failure result of the target device in combination with the image data and the audio data includes the following steps:
[0061] S410, obtaining an image detection result of the target device according to the image data and a preset image detection model;
[0062] S420, obtaining an audio detection result of the target device according to the audio data and a preset audio detection model;
[0063] S430, determining whether the image detection result of the target device is consistent with the audio detection result;
[0064] S440: If they are inconsistent, determine the failure result of the target device according to one of them, or determine the failure result of the target device by a preset second detection method;
[0065] S450: If they are consistent, determine that the fault result corresponding to both is the fault result of the target device.
[0066] In this way, for a target device that belongs to both the first device set and the second device set, the fault result will be determined by combining the image detection result and the audio detection result. When the image detection result and the audio detection result are inconsistent, the fault result of the target device will be determined by one of them as needed, or the fault result of the target device will be determined by the preset second detection method.
[0067] Specifically, in some embodiments, when the fault result of the target device is determined by the preset second detection method in step S440, the following steps are included:
[0068] S441, obtaining secondary detection data of the target device;
[0069] S442, obtaining a secondary detection result of the target device according to the secondary detection data and a preset secondary detection model;
[0070] S443: Determine a failure result of the target device according to the secondary detection result.
[0071] Furthermore, secondary detection data that is different from image data and audio data is used to further determine the fault result of the target device, thereby avoiding the current image detection model or audio detection model that cannot perform accurate identification from participating in the determination of the fault result. For the secondary detection data, the types and quantities of the secondary detection data may be different in different target devices, for example, pressure data and temperature data of various areas in the target device. Specifically, technical personnel in this field can more accurately determine whether the target device is faulty based on the secondary detection data, and the difficulty of obtaining the secondary detection data may be more difficult than that of image data and audio data.
[0072] In some other embodiments, determining the failure result of the target device according to one of the above mentioned conditions comprises the following steps:
[0073] According to a preset selection priority corresponding to the target device, a fault result of the target device is determined according to the image detection result or the audio detection result.
[0074] With this arrangement, for different target devices, the priorities of the image detection results and the audio detection results are different, that is, for some target devices, the image detection results are more accurate or the audio detection results are more accurate. In this embodiment, by presetting the selection priority of the two results for each target device, when the two results are inconsistent, the result with a higher priority can be selected to determine the fault result of the target device.
[0075] Wherein, obtaining the image detection result of the target device according to the preset image detection model and the image data includes the following steps:
[0076] S411, segmenting the image data into judgment unit images corresponding to each module in the target device according to a preset segmentation model;
[0077] Specifically, the vehicle image sample is segmented into multiple judgment unit images through the segmentation model, so as to screen out the faulty parts in a targeted manner and improve the data processing efficiency;
[0078] S412, obtaining unit detection results of each module in the target device according to a preset unit image detection model corresponding to the judgment unit image;
[0079] Specifically, the unit image detection model in this embodiment adopts a probabilistic neural network (PNN), which is a four-layer feedforward neural network that integrates Bayesian decision theory on the basis of a radial basis neural network. PNN has the characteristics of easy training, fast convergence speed, strong fault tolerance of radial basis nonlinear mapping function, etc. Its structure usually includes the following four levels:
[0080] Input layer: Receives sample features as input, does not perform calculations, and only transmits the received sample features in the form of vectors to the next layer. The number of neurons in the input layer is equal to the dimension of the input features.
[0081] Hidden layer: Also known as the radial base layer, the number of neurons in this layer is equal to the number of training samples. Each neuron has a center. After receiving the input vector from the input layer, the Euclidean distance between the input vector and the neuron center is calculated through the activation function (usually using the Gaussian kernel function) to obtain a scalar value.
[0082] Sum layer: The number of neurons is equal to the number of data categories. The function of this layer is to sum the scalar values of all samples in each category and divide it by the number of samples in that category to obtain the average value of each category of data.
[0083] Output layer: Compare the average values of each category obtained by the summation layer and classify the data into the category with the largest average value.
[0084] Since the selection of smoothing parameters in PNN will directly affect the detection performance of the algorithm, in order to improve the recognition accuracy of fault results, the dung beetle optimizer (DBO) is used to optimize the smoothing parameters of the PNN algorithm. The optimal position of the dung beetle is recorded as the optimal smoothing parameter.
[0085] The formula for updating the dung beetle position is as follows:
[0086] L γ (t+1)=L γ (t)+tan(θ)|L γ (t)-L γ (t-1)| (1)
[0087] Among them, L γ (t-1) represents the position of the γth dung beetle at the t-1th iteration, L γ (t) represents the position of the γth dung beetle at the tth iteration, L γ (t+1) represents the position of the γth dung beetle at the t+1th iteration, and θ represents the rolling direction angle of the dung beetle.
[0088] The fitness function is used to evaluate the fitness value of the iterative calculation position, that is, to evaluate whether the calculation position meets the requirements of the fault result misjudgment rate and missed judgment rate. In the present invention, it is defined as:
[0089] F(L γ )=λ1Q1+λ2Q2 (2)
[0090] Among them, λ1 represents the weight of the false positive rate, λ2 represents the weight of the missed positive rate, Q1 represents the false positive rate, and Q2 represents the missed positive rate. For the whole vehicle system in the present invention, the harm caused by missed positive rate is greater than that caused by false positive rate, so λ2>λ1 and λ1+λ2=1.
[0091] Further:
[0092] The misclassification rate Q1 reflects the model's ability to correctly predict the purity of positive samples and reduce the number of negative samples predicted as positive samples, that is, the proportion of negative samples predicted as positive samples to the total number of negative samples. The smaller the value, the better the performance. The definition is as follows:
[0093]
[0094] The missed detection rate Q2 reflects the model's ability to correctly predict the purity of negative samples and reduce the number of positive samples predicted as negative samples, that is, the proportion of positive samples predicted as negative samples to the total number of positive samples. The smaller the value, the better the performance. The definition is as follows:
[0095]
[0096] Among them, the positive sample P and the negative sample N, the positive sample predicted as a positive sample is Truepositive (TP), the positive sample predicted as a negative sample is Falsenetiv (FN), the negative sample predicted as a positive sample is False positive (FP), and the negative sample predicted as a negative sample is Truenegative (TN).
[0097] When F(L γ ) is the smallest, the position of the dung beetle is optimal, that is, the smoothing parameter λ is optimal.
[0098] S413: Obtain an image detection result according to the detection results of each unit.
[0099] Specifically, after the unit detection results of each judgment unit image are known, the image detection result of the target device can be obtained through further analysis.
[0100] As for the audio detection model, the frequency, amplitude, time domain and frequency domain characteristics of the audio data are extracted through the Mel-frequency cepstral coefficients; then, the features are identified through the recurrent neural network in the audio detection model to obtain the corresponding audio detection results. Among them, the recurrent neural network is a pre-trained recurrent neural network with the corresponding detection results as the target output.
[0101] Further, in one embodiment, after the step S443, according to the secondary detection result, determines the fault result of the target device, the following steps are included:
[0102] S510, determining whether the image detection result and the audio detection result are consistent with the secondary detection result;
[0103] S520: if the image detection result is inconsistent with the secondary detection result, update the image detection model according to the secondary detection result;
[0104] S530: If the audio detection result is inconsistent with the secondary detection result, update the audio detection model according to the secondary detection result.
[0105] In this embodiment, the secondary detection results will be further used to feed back the image detection model and / or audio detection model whose results are inconsistent with them, so that in actual use, the image detection model and audio detection model with reduced detection accuracy can be corrected according to the accurate fault results.
[0106] In a second aspect, an embodiment of the present application also provides a vehicle fault identification device.
[0107] In one embodiment, referring to Figure 2 , Figure 2 This is a functional module diagram of an embodiment of the vehicle fault identification device of the present application. Figure 2 As shown, the vehicle fault identification device includes:
[0108] A determination module configured to determine whether the target device belongs to a preset first device set and a second device set; wherein at least some elements in the first device set and the second device set are the same;
[0109] A processing module is configured to, if the target device belongs only to the first device set, obtain image data of the target device and determine a fault result of the target device based on the image data; if the target device belongs only to the second device set, obtain audio data of the target device and determine a fault result of the target device based on the audio data; if the target device belongs to both the first device set and the second device set, obtain image data and audio data of the target device and determine a fault result of the target device in combination with the image data and the audio data.
[0110] Furthermore, in one embodiment, the processing module includes:
[0111] an acquisition unit, configured to acquire image data and / or audio data of the target device;
[0112] an image detection unit, configured to obtain an image detection result of the target device according to the image data and a preset image detection model;
[0113] an audio detection unit, configured to obtain an audio detection result of the target device according to the audio data and a preset audio detection model;
[0114] A fusion detection unit is configured to determine whether the image detection result and the audio detection result of the target device are consistent; if inconsistent, determine the fault result of the target device according to one of them, or determine the fault result of the target device by a preset second detection method; if consistent, determine the fault result corresponding to both as the fault result of the target device.
[0115] Among them, the functional implementation of each module in the above-mentioned vehicle fault identification device corresponds to the various steps in the above-mentioned vehicle fault identification method embodiment, and its functions and implementation processes will not be repeated here one by one.
[0116] In a third aspect, an embodiment of the present application provides a vehicle fault identification device, which may be a personal computer (PC), a laptop computer, a server, or other device with data processing capabilities.
[0117] Reference Figure 3 , Figure 3 Schematic diagram of the hardware structure of the vehicle fault identification device involved in the embodiment of the present application. In the embodiment of the present application, the vehicle fault identification device may include a processor, a memory, a communication interface and a communication bus.
[0118] The communication bus may be of any type and is used to interconnect the processor, the memory, and the communication interface.
[0119] The communication interface includes input / output (I / O) interface, physical interface and logical interface, etc., which are used to realize the interconnection of devices inside the vehicle fault identification device, and the interface used to realize the interconnection of the vehicle fault identification device with other devices (such as other computing devices or user devices). The physical interface can be an Ethernet interface, a fiber optic interface, an ATM interface, etc.; the user device can be a display, a keyboard, etc.
[0120] The memory can be various types of storage media, such as random access memory (RAM), read-only memory (ROM), non-volatile RAM (NVRAM), flash memory, optical storage, hard disk, programmable ROM (PROM), erasable PROM (EPROM), electrically erasable PROM (EEPROM), etc.
[0121] The processor may be a general-purpose processor, and the general-purpose processor may call the vehicle fault identification program stored in the memory and execute the vehicle fault identification method provided in the embodiment of the present application. For example, the general-purpose processor may be a central processing unit (CPU). The method executed when the vehicle fault identification program is called may refer to the various embodiments of the vehicle fault identification method of the present application, and will not be repeated here.
[0122] Those skilled in the art will understand that Figure 3 The hardware structure shown in the figure does not constitute a limitation on the present application, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.
[0123] In a fourth aspect, an embodiment of the present application also provides a storage medium.
[0124] The storage medium of the present application stores a vehicle fault identification program, wherein when the vehicle fault identification program is executed by a processor, the steps of the vehicle fault identification method as described above are implemented.
[0125] Among them, the method implemented when the vehicle fault identification program is executed can refer to the various embodiments of the vehicle fault identification method of the present application, and will not be repeated here.
[0126] It should be noted that the serial numbers of the above-mentioned embodiments of the present application are only for description and do not represent the advantages or disadvantages of the embodiments.
[0127] The terms "including" and "having" and any variations thereof in the specification and claims of this application and the above-mentioned drawings are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices. The terms "first", "second" and "third" are used to distinguish different objects, etc., and do not represent a sequence, nor do they limit "first", "second" and "third" to different types.
[0128] In the description of the embodiments of the present application, "exemplary", "for example" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary", "for example" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary", "for example" or "for example" is intended to present related concepts in a specific way.
[0129] In the description of the embodiments of the present application, unless otherwise specified, “ / ” means or, for example, A / B can mean A or B; the “and / or” in the text is merely a description of the association relationship of associated objects, indicating that three relationships may exist, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, in the description of the embodiments of the present application, “multiple” refers to two or more than two.
[0130] In some processes described in the embodiments of the present application, multiple operations or steps that appear in a specific order are included, but it should be understood that these operations or steps may not be executed in the order in which they appear in the embodiments of the present application or in parallel, and the sequence number of the operation is only used to distinguish the different operations, and the sequence number itself does not represent any execution order. In addition, these processes may include more or fewer operations, and these operations or steps may be executed in sequence or in parallel, and these operations or steps may be combined.
[0131] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, disk, CD) as described above, and includes a number of instructions for a terminal device to execute the methods described in each embodiment of the present application.
[0132] The above are only preferred embodiments of the present application, and are not intended to limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.
Claims
1. A vehicle fault identification method, It is characterized in that The vehicle fault identification method comprises: Determining whether the target device belongs to a preset first device set and a second device set; wherein at least some elements of the first device set and the second device set are the same; If it only belongs to the first device set, acquiring image data of the target device, and determining a fault result of the target device according to the image data; If it only belongs to the second device set, obtaining audio data of the target device, and determining the failure result of the target device according to the audio data; If the target device belongs to both the first device set and the second device set, the image data and the audio data of the target device are acquired, and the failure result of the target device is determined in combination with the image data and the audio data.
2. The vehicle fault identification method according to claim 1, It is characterized in that The acquiring of the image data and the audio data of the target device, and determining the fault result of the target device in combination with the image data and the audio data, comprises the following steps: Obtaining an image detection result of the target device according to the image data and a preset image detection model; Obtaining an audio detection result of the target device according to the audio data and a preset audio detection model; Determining whether the image detection result of the target device is consistent with the audio detection result; If they are inconsistent, determining the failure result of the target device according to one of them, or determining the failure result of the target device by a preset second detection method; If they are consistent, it is determined that the fault result corresponding to both is the fault result of the target device.
3. The vehicle fault identification method according to claim 2, It is characterized in that Determining the failure result of the target device according to one of the above mentioned steps comprises the following steps: According to a preset selection priority corresponding to the target device, a fault result of the target device is determined according to the image detection result or the audio detection result.
4. The vehicle fault identification method according to claim 2, It is characterized in that Determining the failure result of the target device by using a preset second detection method includes the following steps: Obtaining secondary detection data of the target device; Obtaining a secondary detection result of the target device according to the secondary detection data and a preset secondary detection model; According to the secondary detection result, a failure result of the target device is determined.
5. The vehicle fault identification method according to claim 4, It is characterized in that After determining the fault result of the target device according to the secondary detection result, the following steps are included: Determining whether the image detection result and the audio detection result are consistent with the secondary detection result; If the image detection result is inconsistent with the secondary detection result, updating the image detection model according to the secondary detection result; If the audio detection result is inconsistent with the secondary detection result, the audio detection model is updated according to the secondary detection result.
6. The vehicle fault identification method according to claim 2, It is characterized in that The step of obtaining the image detection result of the target device according to the preset image detection model and the image data comprises the following steps: According to a preset segmentation model, the image data is segmented into judgment unit images corresponding to each module in the target device; Obtaining unit detection results of each module in the target device according to a preset unit image detection model corresponding to the judgment unit image; The image detection result is obtained according to the detection results of each unit.
7. A vehicle fault identification device, It is characterized in that The vehicle fault identification device comprises: A determination module configured to determine whether the target device belongs to a preset first device set and a second device set; wherein at least some elements in the first device set and the second device set are the same; A processing module is configured to, if the target device belongs only to the first device set, obtain image data of the target device and determine a fault result of the target device based on the image data; if the target device belongs only to the second device set, obtain audio data of the target device and determine a fault result of the target device based on the audio data; if the target device belongs to both the first device set and the second device set, obtain image data and audio data of the target device and determine a fault result of the target device in combination with the image data and the audio data.
8. The vehicle fault identification device according to claim 7, It is characterized in that The processing module comprises: an acquisition unit, configured to acquire image data and / or audio data of the target device; an image detection unit, configured to obtain an image detection result of the target device according to the image data and a preset image detection model; an audio detection unit, configured to obtain an audio detection result of the target device according to the audio data and a preset audio detection model; A fusion detection unit is configured to determine whether the image detection result and the audio detection result of the target device are consistent; if inconsistent, determine the fault result of the target device according to one of them, or determine the fault result of the target device by a preset second detection method; if consistent, determine the fault result corresponding to both as the fault result of the target device.
9. A vehicle fault identification device, It is characterized in that The vehicle fault identification device includes a processor, a memory, and a vehicle fault identification program stored in the memory and executable by the processor, wherein when the vehicle fault identification program is executed by the processor, the steps of the vehicle fault identification method as described in any one of claims 1 to 6 are implemented.
10. A storage medium, It is characterized in that The storage medium stores a vehicle fault identification program, wherein when the vehicle fault identification program is executed by the processor, the steps of the vehicle fault identification method according to any one of claims 1 to 6 are implemented.
