Screen fault detection method and device, cabin system and storage medium

Abstract

The invention discloses a screen fault detection method and device, a cabin system and a storage medium, and particularly relates to the technical field of screen detection, and the method comprises the steps: continuously monitoring all parameters of a vehicle-mounted display screen through a data collection module; processing the acquired image, host software, a deserializer, an in-screen chip, a transmission link, temperature and power signal data by using a deep learning algorithm, and identifying fault features of black and white flashover; an intelligent detection algorithm integrated in the module is utilized to accurately identify and position a fault area in real time, and accurate information is provided for subsequent processing; and according to the fault area, a preset fault library and a diagnosis rule are combined, and the fault type and severity are judged. According to the screen fault detection method and device, the cabin system and the storage medium provided by the embodiment of the invention, the problem that a vehicle-mounted screen is difficult to quickly position and repair when faults such as black and white flashes occur is effectively solved, and the display stability, the driving safety and the user experience are improved.

Description

Technical Field

[0001] The present application relates to the field of screen detection technology, and in particular to a screen fault detection method, device, cockpit system and storage medium. Background Art

[0002] With the development of intelligent vehicles, the in-vehicle display screen has become an important part of the smart cockpit, used to display navigation, entertainment, vehicle status and other information. However, in actual use, the system and applications are becoming more and more heavy, and the software updates are iterating faster and faster. The screen may flicker in black and white after long-term operation or under certain conditions, affecting driving safety and user experience. Existing solutions mostly rely on manual inspection and maintenance, which is inefficient and costly. Summary of the invention

[0003] The purpose of the present invention is to provide a screen fault detection method, device, cockpit system and storage medium, which effectively solves the problem that the vehicle screen is difficult to quickly locate and repair when faults such as black and white flickering occur, thereby improving display stability, driving safety and user experience.

[0004] The present invention provides the following scheme:

[0005] According to one aspect of the present invention, a screen fault detection method is provided, the screen fault detection method comprising:

[0006] Through the data acquisition module, various parameters of the vehicle display screen are continuously monitored;

[0007] The deep learning algorithm is used to process the collected images, host software, codec, on-screen chips, transmission links, temperature and power signal data to identify the fault characteristics of black and white flashes.

[0008] Utilize the intelligent detection algorithm integrated in the module to accurately identify and locate the fault area in real time, providing precise information for subsequent processing;

[0009] According to the fault area, combined with the preset fault library and diagnosis rules, the fault type and severity are determined.

[0010] Optionally, a deep learning algorithm is used to process the collected images, host software, codec, on-screen chip, transmission link, temperature and power signal data to identify the fault characteristics of black and white flash, including:

[0011] The convolutional neural network is trained using images annotated with fault feature data, host software, codec, on-screen chips, transmission links, temperature, and power signal data.

[0012] The trained convolutional neural network is used to identify fault features.

[0013] Optionally, a deep learning algorithm is used to process the collected images, host software, codec, on-screen chip, transmission link, temperature and power signal data to identify the fault characteristics of black and white flash, including:

[0014] UMAP was used to reduce the dimension of the collected data;

[0015] Use cascaded LSTM and Transformer to extract features from the reduced-dimensional data;

[0016] BP neural network is used to further extract features from the first extracted features.

[0017] Optionally, the intelligent detection algorithm integrated in the module can accurately identify and locate the fault area in real time, providing precise information for subsequent processing, including:

[0018] The identified fault features are compared with the fault template features marked with the fault area to locate the fault area.

[0019] Optionally, also include:

[0020] Fault information and module diagnostic reports are saved locally by writing to disk, supporting local fault analysis and repair.

[0021] Optionally, also include:

[0022] Upload fault information and module diagnostic reports to the cloud server through the remote communication module.

[0023] Optionally, also include:

[0024] After receiving the fault information, the cloud server conducts further analysis and sends maintenance suggestions to maintenance personnel or remotely guides maintenance operations.

[0025] According to two aspects of the present invention, a screen fault detection device is provided, the screen fault detection device comprising:

[0026] The parameter detection unit is used to continuously monitor various parameters of the vehicle display screen through the data acquisition module;

[0027] The feature recognition unit is used to process the collected images, host software, codec, on-screen chip, transmission link, temperature and power signal data using a deep learning algorithm to identify the fault characteristics of black and white flashes;

[0028] Fault location unit, which uses the intelligent detection algorithm integrated in the module to accurately identify and locate the fault area in real time, providing precise information for subsequent processing;

[0029] The type judgment unit is used to judge the fault type and severity according to the fault area in combination with the preset fault library and diagnosis rules.

[0030] According to three aspects of the present invention, there is provided a cockpit system, comprising: a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus;

[0031] A computer program is stored in the memory, and when the computer program is executed by the processor, the processor executes the steps of the screen failure detection method.

[0032] According to four aspects of the present invention, there is provided a computer-readable storage medium, comprising: a computer program executable by a cockpit system is stored therein, and when the computer program runs on the cockpit system, the cockpit system executes the steps of the screen fault detection method.

[0033] Through the above scheme, the following beneficial technical effects are obtained:

[0034] This method uses intelligent detection algorithms, diagnostic services, and remote support technologies to achieve real-time monitoring, fault recording, and preliminary diagnosis of vehicle display screens. It effectively solves the problem of how difficult it is to quickly locate and repair faults such as black and white flickering on vehicle screens, thereby improving display stability, driving safety, and user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 is a flow chart of a screen fault detection method provided by one or more embodiments of the present invention.

[0036] Figure 2 is a flow chart of a screen fault detection method provided by one or more embodiments of the present invention.

[0037] Figure 3 is a flow chart of a screen fault detection method provided by one or more embodiments of the present invention.

[0038] Figure 4 is a flow chart of feature recognition provided by one or more embodiments of the present invention.

[0039] Figure 5 is a flow chart of feature recognition provided by one or more embodiments of the present invention.

[0040] Figure 6 This is a flowchart of fault location provided by one or more embodiments of the present invention.

[0041] Figure 7 is a flow chart of a screen fault detection method provided by one or more embodiments of the present invention.

[0042] Figure 8 is a structural diagram of a screen fault detection device provided by one or more embodiments of the present invention.

[0043] Fig. 9 It is a schematic diagram of the structure of a cockpit system provided by one or more embodiments of the present invention. DETAILED DESCRIPTION

[0044] The technical solution of the present invention will be described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0045] Figure 1 is a flow chart of a screen fault detection method provided by one or more embodiments of the present invention. Figure 1 , the screen fault detection method includes the following steps:

[0046] S11, through the data acquisition module, continuously monitors various parameters of the vehicle display screen.

[0047] S12 uses deep learning algorithms to process the collected images, host software, codec, on-screen chips, transmission links, temperature and power signal data to identify the fault characteristics of black and white flashes.

[0048] S13, using the intelligent detection algorithm integrated in the module, accurately identifies and locates the fault area in real time, providing precise information for subsequent processing.

[0049] S14, judging the fault type and severity according to the fault area in combination with the preset fault library and diagnosis rules.

[0050] Black and white flicker is a common fault of the vehicle display screen in the cockpit, also known as the central control display screen. When the black and white flicker fault occurs, the vehicle display screen no longer displays a valid image that the user can identify, but instead displays black and white flickering. At this time, the display on a certain pixel on the vehicle display screen flickers between pure black and pure white, and the entire screen looks like there is no valid, recognizable image.

[0051] Black and white flashing is a very common fault on the car display. There may be many reasons for this fault, such as: abnormal link transmission, abnormal host software, or loss of encoder / deserializer lock.

[0052] Table 1 shows various possible causes of black and white flash failure.

[0053] Table 1 Fault Cause Analysis Table

[0054]

[0055] Since there are many possible causes for this type of failure, troubleshooting is a meticulous, tedious and complex process. In order to troubleshoot the cause of the black and white flash failure, technicians often need to spend several weeks or even months.

[0056] In order to facilitate technical personnel to troubleshoot the causes of black and white flash failures and improve their work efficiency, this application proposes a fault detection method that can not only comprehensively consider various possible causes, but also has very accurate troubleshooting conclusions, which can effectively help technical personnel in troubleshooting and improve work efficiency.

[0057] Moreover, it should be emphasized that in the process of troubleshooting the cause of the fault, the process provided by the present application adopts a neural network approach to extract fault features, thereby simplifying the numerous signals originally collected into a set of very simple feature signals, and finally using the simplified feature signals to locate the point where the fault occurs and the severity of the current fault, thereby greatly simplifying the logical process of fault troubleshooting and further improving work efficiency.

[0058] First, the original data signal needs to be collected. In the embodiment of the present application, the types of original signals collected are very many. Due to the wide variety of collected signals, there are many references to be used when troubleshooting the cause of the fault, so the results of troubleshooting and fault location will be relatively accurate.

[0059] Preferably, the original acquisition signal includes: acquired images, host software, codec, on-screen chip, transmission link, temperature and power signal data.

[0060] Here, the captured image is the image actually displayed by the vehicle computer.

[0061] The host software data includes: the type of operating system installed on the host, the version of the operating system, the name of the display card, and the type and version of the display driver.

[0062] The codec data includes: the type of codec and the real-time input and output data of the codec.

[0063] The on-screen chip data includes: the type, name, and real-time input and output data of each on-screen chip.

[0064] The transmission link data includes: transmission protocol name, transmission protocol version, and real-time input and output data of the transmission link.

[0065] Temperature data includes: real-time temperature data collected at various points on the vehicle screen.

[0066] Power supply signal data: Real-time signal data of each power supply.

[0067] As you can see, there are many types of data actually collected. This means that the amount of raw data is relatively large. In particular, the real-time display image data of the car screen is also collected, which means that the volume of data will increase further.

[0068] It is understandable that most of the original large-volume data has little impact on the final fault location result. How to accurately extract data that has a great impact on the final fault location result from the massive original collected data is a problem that the technical solution of this application needs to face.

[0069] In view of the above problems, the present application adopts a method of extracting features and using the features to locate faults. More specifically, a neural network is used to extract features from the original collected data, and the extracted feature data is then used to locate the faults.

[0070] Those skilled in the art should know that neural networks generally need to be trained for specific problems and specific scenarios, and the structure and parameters of the neural network need to be debugged so that the neural network can accurately solve the problem of feature extraction.

[0071] The training of neural networks can be divided into supervised training and unsupervised training. In the technical solution provided in the present application, depending on the type of neural network selected, supervised training or unsupervised training can be used.

[0072] Through the feature extraction operation of the neural network, also known as the deep learning algorithm, feature data with greatly reduced data volume is obtained.

[0073] After obtaining the characteristic data, the intelligent detection algorithm is used to detect the characteristic data and locate the cause of the fault.

[0074] It should be noted that in the embodiments of the present application, the so-called fault location requires not only accurate identification of the fault area, but also accurate location of the fault area.

[0075] After the accurate fault location is completed, accurate information is provided for subsequent processing. Next, the fault type and severity are determined based on the fault area, combined with the preset fault library and diagnosis rules.

[0076] Table 2 Fault List

[0077]

[0078]

[0079] Through the above process, real-time monitoring, fault recording and preliminary diagnosis of the vehicle display screen can be completed, which effectively solves the problem that the vehicle screen is difficult to quickly locate and repair when faults such as black and white flickering occur, and improves display stability, driving safety and user experience.

[0080] Figure 2 is a flow chart of a screen fault detection method provided by one or more embodiments of the present invention. Figure 2 , the screen fault detection method includes the following steps:

[0081] S21, through the data acquisition module, continuously monitors various parameters of the vehicle display screen.

[0082] S22 uses deep learning algorithms to process the collected images, host software, codec, on-screen chips, transmission links, temperature and power signal data to identify the fault characteristics of black and white flashes.

[0083] S23, using the intelligent detection algorithm integrated in the module, accurately identifies and locates the fault area in real time, providing precise information for subsequent processing.

[0084] S24, judging the fault type and severity according to the fault area in combination with the preset fault library and diagnosis rules.

[0085] S25, the fault information and module diagnosis report are saved locally by local disk, supporting local fault analysis and repair.

[0086] S26, uploading the fault information and module diagnosis report to the cloud server through the remote communication module.

[0087] The process provided in this embodiment is different from the aforementioned embodiments of the present application in that a step of storing fault information and module diagnosis reports is added.

[0088] In this embodiment, the storage of fault information and module diagnosis reports is divided into: local storage and remote storage.

[0089] The so-called remote storage is to upload fault information and module diagnostic reports to the cloud server. The cloud server can be a database server or a file server. The database server includes: Sql server or NoSql server.

[0090] Similarly, local storage can also be stored in a database, or directly stored in the form of a file.

[0091] Whether local storage, remote storage, database storage, or file storage is used, since the fault information and module diagnostic reports are reliably saved, subsequent fault analysis and repair are supported.

[0092] Fault analysis is the task of statistically analyzing various factors related to fault occurrence, such as the frequency of faults, fault causes, etc. Through fault analysis, we can clearly know the overall distribution of some statistical factors such as the causes of faults, the frequency of faults, etc. within a period of time.

[0093] In addition, since the module diagnostic report has given the solutions corresponding to different fault causes, the black and white flash can be restored based on the data in the module diagnostic report.

[0094] Figure 3 is a flow chart of a screen fault detection method provided by one or more embodiments of the present invention. Figure 3 , the screen fault detection method includes the following steps:

[0095] S31, through the data acquisition module, continuously monitors various parameters of the vehicle display screen.

[0096] S32 uses deep learning algorithms to process the collected images, host software, codec, on-screen chips, transmission links, temperature and power signal data to identify the fault characteristics of black and white flashes.

[0097] S33, using the intelligent detection algorithm integrated in the module, accurately identifies and locates the fault area in real time, providing precise information for subsequent processing.

[0098] S34, judging the fault type and severity according to the fault area in combination with the preset fault library and diagnosis rules.

[0099] S35, saves fault information and module diagnosis reports locally by local disk, and supports local fault analysis and repair.

[0100] S36, uploading the fault information and module diagnosis report to the cloud server through the remote communication module.

[0101] S37, after receiving the fault information, the cloud server performs further analysis and sends maintenance suggestions to the maintenance personnel or remotely guides maintenance operations.

[0102] The biggest difference between this embodiment and the aforementioned embodiments of the present application is that cloud-based analysis and remote guidance of operation and maintenance are added to the remote storage solution.

[0103] Since the fault information and module diagnostic reports have been uploaded remotely to the cloud server, the cloud server can perform further analysis based on the various fault-related information stored locally, and provide maintenance suggestions or remote guidance on maintenance operations based on the results of the analysis.

[0104] It should be noted that once the remote storage function on the cloud server is turned on, it will usually last for a period of time. This means that the fault information and module diagnostic reports stored on the cloud server are fault information and module diagnostic reports for a continuous period of time. Therefore, the fault information and module diagnostic reports stored remotely on the cloud server can be used to analyze historical fault information, and relevant suggestions can be given based on the analysis of historical fault information.

[0105] That is, the suggestions given may be the result of time statistics of historical information. For example, if temperature-induced faults often occur around 4 p.m., then it may be suggested to concentrate on cooling the relevant equipment in the cabin around 4 p.m.

[0106] For another example, according to the statistical results of historical data, the failure caused by link transmission is usually related to the opening and closing operations of the air conditioning system. Therefore, it can be recommended to avoid using the car display screen when the air conditioning system is turned on or off.

[0107] Of course, statistical analysis of massive amounts of historical data requires a lot of computing resources, so whether and when such suggestions should be given can be planned based on the computing power configuration of the cloud server itself.

[0108] Figure 4 is a flow chart of feature recognition in a screen fault detection method provided by one or more embodiments of the present invention. Figure 4 , using deep learning algorithms to process the collected images, host software, codec, on-screen chips, transmission links, temperature and power signal data to identify the fault characteristics of black and white flashes, including the following steps:

[0109] S41, train the convolutional neural network using images annotated with fault feature data, host software, codec, on-screen chip, transmission link, temperature and power signal data.

[0110] S42, using the trained convolutional neural network to identify fault features.

[0111] Depend on Figure 4 The illustrated embodiment presents a supervised feature recognition process.

[0112] Specifically, in the supervised feature recognition process, convolutional neural networks are used to identify features.

[0113] Convolutional neural networks have their own characteristics in structure. Its main structure includes multiple convolutional layers, which can perform convolution operations on input data. Therefore, they are particularly suitable for processing matrix data such as images and extracting corresponding features from complex matrix data.

[0114] In this embodiment, the feature recognition process using the convolutional neural network is a supervised feature recognition process. That is, in the convolutional neural network training process, the training data used is feature-labeled training data.

[0115] The training data itself can be the original collected data, but it must be marked with the corresponding fault features. In this way, it can be ensured that the trained convolutional neural network can accurately output the fault feature recognition results.

[0116] Specifically, the convolutional neural network can use the YOLO network to complete the recognition of fault features.

[0117] Figure 5 is a flow chart of feature recognition in a screen fault detection method provided by one or more embodiments of the present invention. Figure 5 , using deep learning algorithms to process the collected images, host software, codec, on-screen chips, transmission links, temperature and power signal data to identify the fault characteristics of black and white flashes, including the following steps:

[0118] S51, UMAP is used to reduce the dimension of the collected data.

[0119] S52, use the cascaded LSTM and Transformer to perform feature extraction on the reduced-dimensional data.

[0120] S53, using BP neural network to further extract features from the once extracted features.

[0121] The feature recognition process provided by this embodiment is an unsupervised feature recognition process.

[0122] UMAP, the full name of which is uniform manifold approximation and projection, is built based on the theoretical framework of Riemann sets and algebraic topology. When processing large data sets, UMAP has obvious advantages, such as fast running speed and small memory usage. In this embodiment, the UMAP algorithm is first used to reduce the dimensionality of the original collected data.

[0123] It can be imagined that after dimensionality reduction, the overall data volume of the original collected data is greatly reduced.

[0124] Then, LSTM and Transformer are cascaded to each other for the first feature extraction.

[0125] LSTM can avoid the gradient message and gradient explosion problems in the long sequence training process and better capture the dependencies between sequences.

[0126] Transformer improves the training speed of the model through the attention mechanism and has better parallel performance.

[0127] The two are cascaded with each other and can effectively complete the feature extraction of the reduced-dimensional data.

[0128] After completing a feature extraction, the BP neural network is used to further extract features. The input data of the BP neural network is the features extracted after the first feature extraction, and the output is the features extracted again.

[0129] After the feature extraction is completed, the obtained feature is the recognition result of the fault feature.

[0130] Figure 6 is a flowchart of fault location in a screen fault detection method provided by one or more embodiments of the present invention. Figure 6 , using the intelligent detection algorithm integrated in the module, accurately identify and locate the fault area in real time, providing precise information for subsequent processing, including the following steps:

[0131] S61, comparing the identified fault features with the fault template features marked with the fault area to locate the fault area.

[0132] The system stores fault template features corresponding to different fault areas and fault types. Therefore, after the fault features are identified, the identified features are compared with the fault template features stored in the system one by one, so that the fault area can be located and the actual cause of the current black and white flash can be known.

[0133] The above one-to-one comparison process can be to calculate the similarity of the identified features and each fault template feature stored in the system. In the similarity calculation process, the similarity algorithm used for different fault template features should be the same. For example, in the similarity calculation process, the similarity calculation with the first fault template feature uses cosine similarity, then all similarity calculations should use cosine similarity.

[0134] After the similarity with each fault template feature is calculated, the similarities are sorted, and the fault area corresponding to the fault template feature with the highest similarity is the fault area finally located.

[0135] Figure 7 is a flow chart of a screen fault detection method provided by one or more embodiments of the present invention. Figure 7 , the screen fault detection method includes the following steps:

[0136] S71, the black and white flash fault monitoring and diagnosis service reports the fault information and module diagnosis report to the diagnosis service / system operation monitoring.

[0137] Among them, black and white flash fault monitoring and diagnosis includes three modules: real-time data collection, fault feature recognition and intelligent detection algorithm.

[0138] S72, the diagnostic service / system operation monitoring performs local fault recording of the received fault information and module diagnostic report.

[0139] S73, the diagnostic service / system operation monitoring uploads the fault information and module diagnostic report to the TSP service.

[0140] S74, diagnostic service / system operation monitoring provides engineering display of fault information and module diagnostic reports.

[0141] S75, the TSP service uploads the fault information and module diagnosis report to the remote vehicle management system in the cloud.

[0142] S76, the remote vehicle management system displays statistical data.

[0143] S77, remote vehicle management system provides remote monitoring technical support.

[0144] like Figure 8 As shown, the present invention also provides a screen fault detection device, comprising:

[0145] The parameter detection unit 81 is used to continuously monitor various parameters of the vehicle-mounted display screen through the data acquisition module.

[0146] The feature recognition unit 82 is used to use a deep learning algorithm to process the collected images, host software, codec, on-screen chip, transmission link, temperature and power signal data to identify the fault characteristics of black and white flashes.

[0147] The fault location unit 83 is used to utilize the intelligent detection algorithm integrated in the module to accurately identify and locate the fault area in real time, and provide accurate information for subsequent processing.

[0148] The type determination unit 84 is used to determine the type and severity of the fault according to the fault area in combination with the preset fault library and diagnosis rules.

[0149] It is worth noting that although only some basic functional modules are disclosed in the embodiments of the present invention, it does not mean that the composition of the present system is limited to the above basic functional modules. On the contrary, what the present embodiment wants to express is that on the basis of the above basic functional modules, those skilled in the art can arbitrarily add one or more functional modules in combination with the prior art to form an infinite number of embodiments or technical solutions. In other words, the present system is open rather than closed. Just because the present embodiment only discloses individual basic functional modules, it cannot be considered that the protection scope of the claims of the present invention is limited to the disclosed basic functional modules. At the same time, for the convenience of description, the above devices are described in terms of functions and are described separately in various units and modules. Of course, when implementing the present invention, the functions of each unit and module can be implemented in the same or one or more software and / or hardware.

[0150] like Fig. 9 As shown, the present invention also provides a cockpit system, comprising: a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus; a computer program is stored in the memory, and when the computer program is executed by the processor, the processor executes the steps of the screen fault detection method.

[0151] Fig. 9 FIG. 1 is a schematic diagram of the structure of a cockpit system provided by an embodiment of the present invention. Fig. 9 The cockpit system provided in the embodiment of the present invention includes: one or more processors 910 and a memory 920; the processor 910 in the cockpit system may be one or more, Fig. 9 A processor 910 is taken as an example; the memory 920 is used to store one or more programs; the one or more programs are executed by the one or more processors 910, so that the one or more processors 910 implement the screen fault detection method as described in any one of the embodiments of the present invention.

[0152] The cockpit system may further include: an input device 930 and an output device 940 .

[0153] The processor 910, memory 920, input device 930 and output device 940 in the cockpit system can be connected via a bus or other means. Fig. 9 The example of connecting through bus is taken in the following.

[0154] The memory 920 in the cockpit system is a computer-readable storage medium that can be used to store one or more programs, which can be software programs, computer executable programs, and modules, such as program instructions / modules corresponding to the screen fault detection method provided in the embodiment of the present invention. The processor 910 executes various functional applications and data processing of the cockpit system by running the software programs, instructions, and modules stored in the memory 920, that is, the screen fault detection method in the above method embodiment is implemented.

[0155] The memory 920 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and applications required for at least one function; the data storage area may store data created according to the use of the cockpit system, etc. In addition, the memory 920 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some instances, the memory 920 may further include a memory remotely disposed relative to the processor 910, and these remote memories may be connected to the device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0156] The input device 930 may be used to receive input digital or character information and generate key signal input related to user settings and function control of the cockpit system. The output device 940 may include display devices such as a display screen.

[0157] The present invention also provides a computer-readable storage medium storing a computer program executable by a cockpit system. When the computer program runs on the cockpit system, the cockpit system executes the steps of the screen fault detection method.

[0158] Specifically, the computer storage medium of the embodiment of the present invention can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, 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 above. In the present embodiment, the computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, device or device or used in combination with it.

[0159] The present invention also provides a vehicle, wherein the vehicle is provided with the screen failure detection device as described above.

[0160] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A screen fault detection method, characterized in that: The screen fault detection method comprises: Through the data acquisition module, various parameters of the vehicle display screen are continuously monitored; The deep learning algorithm is used to process the collected images, host software, codec, on-screen chips, transmission links, temperature and power signal data to identify the fault characteristics of black and white flashes. Utilize the intelligent detection algorithm integrated in the module to accurately identify and locate the fault area in real time, providing precise information for subsequent processing; According to the fault area, combined with the preset fault library and diagnosis rules, the fault type and severity are determined.

2. The method according to claim 1, characterized in that The deep learning algorithm is used to process the collected images, host software, codec, on-screen chips, transmission links, temperature and power signal data to identify the fault characteristics of black and white flash, including: The convolutional neural network is trained using images annotated with fault feature data, host software, codec, on-screen chips, transmission links, temperature, and power signal data. The trained convolutional neural network is used to identify fault features.

3. The method according to claim 1, characterized in that The deep learning algorithm is used to process the collected images, host software, codec, on-screen chips, transmission links, temperature and power signal data to identify the fault characteristics of black and white flash, including: UMAP was used to reduce the dimension of the collected data; Use cascaded LSTM and Transformer to extract features from the reduced-dimensional data; BP neural network is used to further extract features from the first extracted features.

4. The method according to claim 1, characterized in that Utilize the intelligent detection algorithm integrated in the module to accurately identify and locate the fault area in real time, providing precise information for subsequent processing, including: The identified fault features are compared with the fault template features marked with the fault area to locate the fault area.

5. The method according to claim 1, characterized in that Also includes: Fault information and module diagnostic reports are saved locally by writing to disk, supporting local fault analysis and repair.

6. The method according to claim 1, characterized in that Also includes: Upload fault information and module diagnostic reports to the cloud server through the remote communication module.

7. The method according to claim 1, characterized in that Also includes: After receiving the fault information, the cloud server conducts further analysis and sends maintenance suggestions to maintenance personnel or remotely guides maintenance operations.

8. A screen fault detection device, characterized in that: The screen fault detection device comprises: The parameter detection unit is used to continuously monitor various parameters of the vehicle display screen through the data acquisition module; The feature recognition unit is used to process the collected images, host software, codec, on-screen chip, transmission link, temperature and power signal data using a deep learning algorithm to identify the fault characteristics of black and white flashes; Fault location unit, which uses the intelligent detection algorithm integrated in the module to accurately identify and locate the fault area in real time, providing precise information for subsequent processing; The type judgment unit is used to judge the fault type and severity according to the fault area in combination with the preset fault library and diagnosis rules.

9. A cockpit system, characterized in that: include: A processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus; a computer program is stored in the memory, and when the computer program is executed by the processor, the processor executes the steps of the method described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer program executable by the cockpit system is stored therein, and when the computer program is run on the cockpit system, the cockpit system executes the steps of the method according to any one of claims 1 to 7.

Images