Rain and snow weather fault identification processing method and device, terminal and medium

Abstract

The application discloses a rain and snow weather fault identification processing method and device, a terminal and a medium. The method comprises the following steps: acquiring an initial identification result of a freight car under rain and snow weather conditions; if the brake beam station identification result in the initial identification result comprises a first error code, determining an interfered camera channel according to a picture name of the first error code, and shielding a brake beam picture corresponding to the interfered camera channel and a fault predicted by a car coupler buffer picture corresponding to the interfered camera channel; if the side frame station identification result in the initial identification result comprises a second error code, acquiring a preset fault shielding list, and deleting a fault corresponding to the preset fault shielding list in the initial identification result to obtain a target identification result. The application aims to realize channel-level fine fault shielding and snow cover directional fault deletion, thereby reducing the false alarm risk in severe weather.

Description

Technical Field

[0001] This application relates to the field of railway freight car operation safety monitoring technology, and in particular to a method, device, terminal and medium for identifying and handling faults in rain and snow weather. Background Technology

[0002] The Dynamic Image Detection System (TFDS) for Freight Car Operation Faults is a core piece of equipment for ensuring the safe operation of railway freight cars. It collects images of freight cars in operation through trackside equipment and uses intelligent recognition models to automatically detect faults in vehicle components. The system employs linear or area array high-speed cameras to automatically capture images of the underside and sides of the vehicles as trains pass, transmitting these images via network to the train inspection center for manual or intelligent judgment models to assess the severity of the faults based on the images.

[0003] However, in practical applications, rain and snow can severely impact the image acquisition quality of TFDS, primarily in two ways: First, during rain or snowfall, camera lenses are easily covered by water or snow, resulting in blurry images. The intelligent recognition model may then output numerous invalid fault predictions based on such images. Second, when the vehicle body or undercarriage is covered in snow, the intelligent recognition model may misinterpret the snow as part deformation, missing parts, or other faults, generating a large number of false alarms. According to field statistics, under rainy or snowy weather conditions, the number of false fault predictions by TFDS per day can be 5 to 10 times higher than under normal weather conditions. Summary of the Invention

[0004] The main purpose of this application is to provide a method, device, terminal and medium for identifying and processing faults in rain and snow weather, which aims to achieve channel-level fine-grained fault shielding and snow cover-based targeted fault deletion, thereby reducing the risk of false alarms in severe weather.

[0005] To achieve the above objectives, this application provides a method for identifying and handling faults in rainy and snowy weather, the method comprising: The initial identification results of the truck under rain and snow weather conditions are obtained and stored in a high-speed cache. The initial identification results are used to characterize the image display status and fault identification status of each component of the truck identified by the truck operation fault dynamic image detection system. Determine whether the brake beam station identification result in the initial identification result includes the first error code. If the brake beam station identification result includes the first error code, then determine the interfered camera channel according to the image name that predicts the first error code, and block the brake beam image and the coupler image corresponding to the interfered camera channel that predict the fault. Determine whether the side frame station identification result in the initial identification result includes the second error code. If the side frame station identification result includes the second error code, obtain the preset fault masking list and delete the faults corresponding to the preset fault masking list in the initial identification result to obtain the target identification result.

[0006] Specifically, storing the initial recognition result in a cache includes: The initial identification results are written to the cache based on the vehicle sequence of the truck, wherein the cache is used to store the initial identification results corresponding to each component with the vehicle sequence as the primary key.

[0007] Specifically, determining whether the brake beam station identification result in the initial identification result includes the first error code includes: Extract the brake beam station identification result from the cache; Iterate through the images of the bottom left camera channel, the bottom middle camera channel, and the bottom right camera channel corresponding to the brake beam station, and determine whether the images of each camera channel report the first error code. The first error code is output by the brake beam station when rain or snow covers the camera and causes the channel images to become blurry.

[0008] Specifically, the step of determining the interfered camera channel based on the image name of the predicted first error code, and blocking the predicted faults of the brake beam image and the coupler / smooth image corresponding to the interfered camera channel, includes: Obtain the image name that predicts the first error code, and determine the corresponding interfered camera channel based on the image name. The interfered camera channel is one of the bottom left camera channel, the bottom middle camera channel, or the bottom right camera channel. According to the preset channel mapping relationship, find all brake beam images corresponding to the interfered camera channel and all coupler images corresponding to the interfered camera channel. The preset channel mapping relationship is used to record the correspondence between each camera channel, brake beam image name and coupler image name. Mark all predicted faults in all brake beam images and all coupler images found as hidden.

[0009] Specifically, determining whether the side frame station identification result in the initial identification result includes a second error code includes: Extract the identification results of the side rack station from the cache; The identification results of the side frame station are traversed to determine whether there is a record corresponding to the second error code, wherein the second error code is output by the side frame station when the vehicle body or undercarriage is covered by snow.

[0010] Specifically, the step of obtaining a preset fault masking list and deleting the faults corresponding to the preset fault masking list from the initial identification result to obtain the target identification result includes: Read the preset fault masking list from the preset configuration database, wherein the preset fault masking list is used to record fault names that are prone to false alarms under snow cover conditions; Traverse the initial identification results corresponding to the current truck, and match the fault names in the initial identification results with the fault names in the preset fault masking list one by one to obtain the successfully matched fault records; The faults corresponding to the successfully matched fault records are deleted from the initial identification results, resulting in unmatched fault records; The target identification result is determined based on the unmatched fault records.

[0011] Specifically, the method further includes: If the brake beam station identification result does not include the first error code, and the side frame station identification result does not include the second error code, then the initial identification result is determined as the target identification result.

[0012] To achieve the above objectives, this application also provides a rain and snow weather fault identification and processing device, the device comprising: The first unit is used to transform the raw data corresponding to the software business components into a business benefit sequence, wherein the business benefit sequence is used to characterize the business benefit index value obtained by the software business components at each time point. The second unit is used to generate intervention variables based on the business benefit sequence, wherein the intervention variables are used to characterize the impact of software business components on the business scenario before, during and after intervention; The third unit is used to calculate the goodness of fit of the preset regression model based on the business benefit sequence and the intervention variables. The fourth unit is used to obtain the target evaluation results corresponding to the software business components based on the business benefit sequence and the goodness of fit.

[0013] To achieve the above objectives, this application also provides a terminal, including a memory storing multiple instructions; the processor loads instructions from the memory to execute the steps in any of the methods provided in this application.

[0014] To achieve the above objectives, this application also provides a medium storing a plurality of instructions adapted for loading by a processor to execute the steps in any of the methods provided in this application.

[0015] This application provides a method, device, terminal, and medium for fault identification and processing in rain and snow weather. It first obtains the initial identification results of a truck under rain and snow conditions. If the brake beam station identification result in the initial identification results includes the first error code, the affected camera channel is determined based on the image name predicting the first error code, and the brake beam image and the coupler / smooth image corresponding to the affected camera channel are blocked, indicating the predicted faults. If the side frame station identification result in the initial identification results includes the second error code, a preset fault blocking list is obtained, and the faults corresponding to the preset fault blocking list are deleted from the initial identification results to obtain the target identification result. This achieves channel-level refined fault blocking and snow-covered targeted fault deletion, thereby reducing the risk of false alarms in severe weather. Attached Figure Description

[0016] Figure 1 A flowchart illustrating the method provided in the embodiments of this application; Figure 2 A flowchart illustrating the logic processing module provided in an embodiment of this application; Figure 3 Vehicle component diagrams provided for embodiments of this application; Figure 4 This is a schematic diagram of the device provided in the embodiments of this application; Figure 5 This is a schematic diagram of the terminal structure provided in an embodiment of this application. Detailed Implementation

[0017] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0018] In practical applications, rain and snow can severely impact the image acquisition quality of TFDS, primarily in two ways: First, during rain or snowfall, camera lenses are easily covered by water or snow, resulting in blurry images. The intelligent recognition model may then output numerous invalid fault predictions based on such images. Second, when the vehicle body or undercarriage is covered in snow, the intelligent recognition model may misinterpret the snow as part deformation, missing parts, or other faults, generating a large number of false alarms. According to field statistics, under rainy or snowy weather conditions, the number of false fault predictions by TFDS on a single day can be 5 to 10 times higher than under normal weather conditions.

[0019] Therefore, this application provides a method, device, terminal, and medium for identifying and handling faults in rainy and snowy weather to solve practical technical problems.

[0020] In some embodiments, the device may be integrated into an electronic device, such as a terminal or server.

[0021] In some embodiments, the server may also be implemented as a terminal.

[0022] The server can be a standalone physical server, a server cluster or distributed system consisting of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms.

[0023] The terminal can be a smartphone, tablet, laptop, desktop computer, smart speaker, smartwatch, etc., but is not limited to these. The terminal and the server can be connected directly or indirectly through wired or wireless communication, which is not limited herein.

[0024] The following sections provide detailed descriptions of each example. It should be noted that the sequence numbers of the following embodiments are not intended to limit the preferred order of the embodiments.

[0025] This application provides a method for identifying and processing faults in rain and snow weather. The method can achieve channel-level fine-grained fault shielding and snow cover-based targeted fault deletion, thereby reducing the risk of false alarms in severe weather.

[0026] like Figure 1 The specific process of the method can be as follows: S110. Obtain the initial identification result of the truck under rain and snow weather conditions, and store the initial identification result in a high-speed cache, wherein the initial identification result is used to characterize the image display status and fault identification status of each component of the truck identified by the truck operation fault dynamic image detection system.

[0027] In some embodiments, storing the initial identification result in a cache includes the following specific implementation process: The initial identification results are written to the cache based on the vehicle sequence of the truck, wherein the cache is used to store the initial identification results corresponding to each component with the vehicle sequence as the primary key.

[0028] In some embodiments, a backend service receives component identification results output by the TFDS intelligent identification module and stores these results in a high-speed cache based on vehicle sequence. The cache is then processed uniformly once all component identification results for the current vehicle are available. The high-speed cache can be a Redis cache. The truck operation fault dynamic image detection system may include the TFDS intelligent identification module.

[0029] Specifically, the TFDS intelligent identification module returns identification results component by component via HTTP requests. The expert experience algorithm service receives the identification result of one component at a time via the HTTP interface and stores it in a Redis cache. The component identification results include information such as vehicle passage time, number of vehicle components, vehicle sequence, fault name, and fault code. For example, the components of a vehicle... Figure 3 As shown, the system includes multiple workstations such as bogies, brake beams, side frames, and couplers / suspensions. The service stores the received component identification results in a Redis cache, organized by vehicle sequence. After writing each component identification result, it checks if all component identification results for the current vehicle have been received. If not, it continues to wait for more results; otherwise, it proceeds to step S2 for unified processing. This vehicle sequence-based caching design ensures that the identification results for all components of a vehicle are completely collected before unified processing, avoiding misjudgments caused by incomplete component identification results.

[0030] S120. Determine whether the brake beam station identification result in the initial identification result includes the first error code. If the brake beam station identification result includes the first error code, determine the interfered camera channel according to the image name that predicts the first error code, and block the brake beam image corresponding to the interfered camera channel and the fault predicted by the coupler and buffer image corresponding to the interfered camera channel.

[0031] In some embodiments, determining whether the brake beam station identification result in the initial identification result includes a first error code includes the following steps A1 to A2: A1. Extract the brake beam station identification result from the cache; A2. Traverse the images of the bottom left camera channel, the bottom middle camera channel, and the bottom right camera channel corresponding to the brake beam station, and determine whether the images of each camera channel report the first error code. The first error code is output by the brake beam station when rain or snow covers the camera and causes the channel images to become blurry.

[0032] Continuing with the above embodiments, when the rain and snow weather function is enabled, the identification result of the brake beam station is obtained from the high-speed cache, and it is determined whether the first error code output by the brake beam station for the lens blur channel has been received.

[0033] The truck operation fault dynamic image detection system provides a status configuration switch for rain and snow weather functions, which can be remotely turned on or off according to actual weather forecasts or on-site conditions. When the rain and snow weather function is on, the truck operation fault dynamic image detection system first retrieves the recognition results of the brake beam station from the Redis cache, traverses the images of the bottom left camera channel, bottom middle camera channel, and bottom right camera channel corresponding to the brake beam station, and determines whether the image of each camera channel predicts the first error code TFDS.0111. The first error code TFDS.0111 is output by the brake beam station for the affected channel images when rain or snow covers the camera and causes the lens to blur. This error code is only predicted for the images corresponding to the bottom left, bottom middle, and bottom right channels, i.e., the corresponding image names are x_2_0.jpg, x_2_1.jpg, and x_2_2.jpg.

[0034] Continuing with the above embodiments, if any camera channel's image reports the first error code TFDS.0111, it is determined that the first error code has been received and channel-level fault masking is performed; if none of the images from all camera channels report the first error code, it is determined that the first error code has not been received and snow cover detection is performed, which is the method flow corresponding to step S130 mentioned later.

[0035] In some embodiments, the step of determining the interfered camera channel based on the image name of the first error code and blocking the faults predicted by the brake beam image and the coupler image corresponding to the interfered camera channel includes the steps B1 to B3 as shown below: B1. Obtain the image name of the image that predicted the first error code, and determine the corresponding interfered camera channel based on the image name. The interfered camera channel is one of the bottom left camera channel, the bottom middle camera channel, or the bottom right camera channel.

[0036] B2. Based on the preset channel mapping relationship, find all brake beam images corresponding to the interfered camera channel and all coupler images corresponding to the interfered camera channel. The preset channel mapping relationship is used to record the correspondence between each camera channel, brake beam image name, and coupler image name.

[0037] B3. Mark all predicted faults in all brake beam images and all coupler images found as hidden.

[0038] Continuing with the above embodiments, if the first error code is received, the interfered camera channel is determined based on the image name that predicted the first error code, and all predicted faults in the brake beam image and coupler image corresponding to the interfered camera channel are blocked.

[0039] Specifically, the image name that predicted the first error code is first obtained, and the corresponding interfered camera channel is determined based on the image name. The interfered camera channel is one of the bottom left camera channel, the bottom middle camera channel, or the bottom right camera channel. For example, when x_2_0.jpg predicts TFDS.0111, it indicates that the bottom left camera channel is interfered with; when x_2_1.jpg predicts TFDS.0111, it indicates that the bottom middle camera channel is interfered with; and when x_2_2.jpg predicts TFDS.0111, it indicates that the bottom right camera channel is interfered with.

[0040] Then, based on the preset channel mapping relationship, all brake beam images and all coupler images corresponding to the interfered camera channel are found. The correspondence between brake beam images and camera channels is shown in Table 1 below:

[0041] Table 1. Schematic diagram of the mapping relationship between brake beam images and camera channels. The correspondence between the coupler images and camera channels is shown in Table 2 below:

[0042] Table 2. Schematic diagram of the mapping relationship between coupler images and camera channels. When the bottom left camera channel is identified as an interfered camera channel (i.e., x_2_0.jpg predicts TFDS.0111), the system looks up all images corresponding to the bottom left camera channel in Tables 1 and 2, including brake beam images x_2_0.jpg, x_2_3.jpg, x_2_6.jpg, x_2_9.jpg, and coupler and buffer images x_4_0.jpg, x_4_1.jpg, x_4_2.jpg, x_4_11.jpg, x_4_12.jpg, and marks all predicted faults in these images as shielded. Similarly, the bottom center camera channel corresponds to x_2_1.jpg, x_2_4.jpg, x_2_7.jpg, x_2_10.jpg and x_4_3.jpg, x_4_4.jpg, x_4_5.jpg, x_4_13.jpg, x_4_14.jpg; the bottom right camera channel corresponds to x_2_2.jpg, x_2_5.jpg, x_2_8.jpg, x_2_11.jpg and x_4_6.jpg, x_4_7.jpg, x_4_8.jpg, x_4_15.jpg, x_4_16.jpg.

[0043] In some embodiments, faults marked as masked are not pushed to the work platform during subsequent push processes, thereby avoiding false alarms caused by lens blur.

[0044] S130. Determine whether the side frame station identification result in the initial identification result includes the second error code. If the side frame station identification result includes the second error code, obtain the preset fault masking list and delete the faults corresponding to the preset fault masking list in the initial identification result to obtain the target identification result.

[0045] In some embodiments, determining whether the side frame station identification result in the initial identification result includes a second error code includes the following steps C1 to C2: C1. Extract the identification results of the side rack station from the cache.

[0046] C2. Traverse the identification results of the side frame station and determine whether there is a record corresponding to the predicted second error code, wherein the second error code is output by the side frame station when snow covers the vehicle body or undercarriage components.

[0047] Continuing with the previous embodiment, the identification result of the side frame station is obtained from the cache, and it is determined whether the second error code output by the side frame station for snow cover is received.

[0048] After completing the brake beam channel fault masking process corresponding to step S120, the truck operation fault dynamic image detection system further extracts the identification results of the side frame workstation from the Redis cache. It iterates through the identification results of the side frame workstation to determine if there is a record predicting the second error code TFDS.0111. The second error code TFDS.0111 is output by the side frame workstation when snow covers the vehicle body or undercarriage components. Although it has the same code as the first error code, its source workstation and triggering conditions are different: the first error code originates from the brake beam workstation and is triggered by lens blur; the second error code originates from the side frame workstation and is triggered by snow cover. By distinguishing the workstation source of the predicted error code, the system achieves separate processing for the impact of two different severe weather conditions. If a record predicting the second error code exists, it is determined that the second error code has been received and the fault list is deleted; if no record predicting the second error code exists, it is determined that the second error code has not been received, and the current initial identification result is directly pushed to the work platform.

[0049] In some embodiments, obtaining a preset fault masking list and deleting the faults corresponding to the preset fault masking list from the initial identification result to obtain the target identification result includes the steps D1 to D4 as shown below: D1. Read the preset fault masking list from the preset configuration database, wherein the preset fault masking list is used to record fault names that are prone to false alarms under snow cover conditions.

[0050] D2. Traverse the initial identification results corresponding to the current truck, and match the fault names in the initial identification results with the fault names in the preset fault masking list one by one to obtain the successfully matched fault records.

[0051] D3. Delete the faults corresponding to the successfully matched fault records from the initial identification results to obtain unmatched fault records.

[0052] D4. Determine the target identification result based on the unmatched fault records.

[0053] Continuing from the above embodiments, if the second error code is received, a preset fault masking list is obtained. Faults in the fault masking list are deleted from the component identification results, and the processed initial identification result, i.e., the target identification result, is pushed to the operation platform. The truck operation fault dynamic image detection system reads the preset fault masking list from the preset configuration database. The preset fault masking list records a set of fault names that are prone to false alarms under snow cover conditions, such as: brake beam safety chain detachment, side frame column wear plate loss, crossbar safety chain slack, etc. This fault masking list can be dynamically updated based on actual operating experience. The identification results of all components of the current vehicle are traversed, and the fault name in each identification result is matched one by one with the fault name in the preset fault masking list. The successfully matched fault records are deleted from the initial identification results, and the unmatched fault records are retained. The retained fault records are used as the processed initial identification result, i.e., the target identification result, and assembled according to the vehicle sequence. The result is pushed to the operation platform via an HTTP interface for review and processing by the inspection personnel.

[0054] In some embodiments, the method further includes the following specific implementation process: If the brake beam station identification result does not include the first error code, and the side frame station identification result does not include the second error code, then the initial identification result is determined as the target identification result.

[0055] Continuing with the above embodiments, when the truck operation fault dynamic image detection system does not receive the first error code and does not receive the second error code, it indicates that the current weather conditions do not significantly interfere with the TFDS identification results. Therefore, the identification results of all components are not masked or deleted and are directly pushed to the operation platform.

[0056] In some embodiments, when only the first error code is received, it indicates that there is lens blur interference but no snow cover. The initial recognition result after the masking process in step S120 is used as the target recognition result and pushed to the operation platform.

[0057] In some embodiments, when only the second error code is received, it indicates that there is snow cover but the lens is not affected. The initial identification result after the deletion process in step S130 is used as the target identification result and pushed to the operation platform.

[0058] In some embodiments, when both the first error code and the second error code are received simultaneously, it indicates that both lens blur and snow cover exist. The processed initial recognition result is then used as the target recognition result and pushed to the work platform. The channel-level masking in step S120 and the fault list deletion in step S130 are executed sequentially, with channel-level masking completed first and then fault list deletion performed to ensure the combined effects of the two processing steps.

[0059] The method will be illustrated below through another specific embodiment: like Figure 2 As shown, the complete workflow of this application embodiment is as follows: Step S201: Obtain the truck component recognition results output by TFDS intelligent recognition through the Spring Boot service and store the component recognition results in a high-speed cache. It should be noted that the high-speed cache can be a Redis cache, used to temporarily store the recognition results of all components of a truck, and then process them uniformly after all component recognition results for a truck have been collected. The TFDS intelligent recognition module returns the recognition results component by component via HTTP requests, and the expert experience algorithm service receives the recognition result of one component at a time and stores it in Redis. The expert experience algorithm service receives the recognition result of one component at a time via HTTP requests. The components of a truck are as follows: Figure 3 As shown, the system includes multiple workstations such as bogies, brake beams, side frames, and couplers / suspensions. The service stores the received component identification results in a Redis cache according to the vehicle sequence, and then processes them uniformly after all component identification results for that vehicle have arrived.

[0060] Step S202: Determine whether all parts of the vehicle have arrived. If not all parts have arrived, return to step S201 and continue waiting; if all parts have arrived, proceed to step S203.

[0061] Step S203: Determine whether the rain / snow weather function is enabled. If not enabled, proceed to step S208 to directly push all component identification results to the work platform; if enabled, proceed to step S204.

[0062] Step S204: Retrieve the identification results of the braking beam station from the Redis cache, and determine whether the images x_2_0.jpg, x_2_1.jpg, and x_2_2.jpg corresponding to each channel predict the first error code TFDS.0111. If predicted, proceed to step S205; otherwise, proceed to step S206.

[0063] Step S205: Based on the image name of the first error code, determine the affected camera channel, find all brake beam images and coupler images corresponding to that channel, and mark all the predicted faults in these images as shielded.

[0064] Step S206: Determine if there is a record for the second error code TFDS.0111 at the side frame station. If not, proceed to step S208; if so, proceed to step S207.

[0065] Step S207: Obtain a preset fault masking list, poll the identification results of all components of the current vehicle, and delete the fault records that match the fault masking list.

[0066] Step S208: Assemble the processed component identification results according to the vehicle sequence and push them to the work platform.

[0067] To verify the technical effectiveness of the embodiments of this application, a comparative experiment was conducted in the TFDS system of a railway bureau. The experiment selected data from 1000 trains passing through under rainy and snowy weather conditions, and statistically analyzed the number of fault predictions and the false alarm rate before and after applying the method of this invention. The results are shown in Table 3 below:

[0068] Table 3 Comparison of Effects of Embodiments in This Application As can be seen from Table 3, after adopting the embodiments of this application, the total number of rainy day fault forecasts decreased by 75.0%, the total number of snowy day fault forecasts decreased by 60.0%, and the workload of manual review decreased by 66.7%, which significantly improved the efficiency of inspection operations under rainy and snowy weather conditions.

[0069] In summary, this application provides a method for identifying and processing faults in rain and snow weather, which can achieve channel-level fine-grained fault masking and targeted fault deletion under snow cover, thereby reducing the risk of false alarms in severe weather.

[0070] To better implement the above methods, this application also provides a rain and snow weather fault identification and processing device. This device can be integrated into an electronic device, such as a terminal or server. The terminal can be a mobile phone, tablet computer, smart Bluetooth device, laptop computer, or personal computer; the server can be a single server or a server cluster composed of multiple servers.

[0071] For example, in this embodiment, the method of this application embodiment will be described in detail by taking the rain and snow weather fault identification and processing device specifically integrated into the terminal as an example.

[0072] For example, such as Figure 4 As shown, the rain and snow weather fault identification and processing device 400 may include a first unit 401, a second unit 402 and a third unit 403; The device includes: The first unit is used to obtain the initial identification results of the truck under rain and snow weather conditions and store the initial identification results in a high-speed cache. The initial identification results are used to characterize the image display status and fault identification status of each component of the truck identified by the truck operation fault dynamic image detection system. The second unit is used to determine whether the brake beam station identification result in the initial identification result includes the first error code. If the brake beam station identification result includes the first error code, the interfered camera channel is determined according to the image name of the first error code, and the brake beam image corresponding to the interfered camera channel and the fault predicted by the coupler image corresponding to the interfered camera channel are blocked. The third unit is used to determine whether the side frame station identification result in the initial identification result includes the second error code. If the side frame station identification result includes the second error code, a preset fault masking list is obtained, and the faults corresponding to the preset fault masking list are deleted in the initial identification result to obtain the target identification result.

[0073] In practice, each of the above units can be implemented as an independent entity or can be arbitrarily combined to be implemented as the same or several entities. For the specific implementation of each of the above units, please refer to the previous method embodiments, which will not be repeated here.

[0074] As can be seen from the above, the embodiments of this application can achieve channel-level fine-grained fault shielding and snow cover-based targeted fault deletion, thereby reducing the risk of false alarms in severe weather.

[0075] This application also provides an electronic device, which can be a terminal, a server, or other similar device. The terminal can be a mobile phone, tablet computer, smart Bluetooth device, laptop computer, personal computer, etc.; the server can be a single server or a server cluster composed of multiple servers, etc.

[0076] In some embodiments, the product processing device may also be integrated into multiple electronic devices, such as multiple servers, with multiple servers implementing the rain and snow weather fault identification and processing method of this application.

[0077] In this embodiment, the electronic device will be described in detail as a terminal, for example, such as... Figure 5 As shown, it illustrates a structural schematic diagram of the terminal 500 involved in an embodiment of this application. Specifically: The terminal 500 may include components such as a processor 501 with one or more processing cores, a memory 502 with one or more media, a power supply 503, an input module 504, and a communication module 505. Those skilled in the art will understand that... Figure 5The terminal 500 structure shown does not constitute a limitation on the terminal 500, and may include more or fewer components than shown, or combine certain components, or have different component arrangements. Wherein: The processor 501 is the control center of the terminal 500. It connects various parts of the terminal 500 via various interfaces and lines. By running or executing software programs and / or modules stored in the memory 502, and by calling data stored in the memory 502, it performs various functions of the terminal 500 and processes data, thereby providing overall monitoring of the terminal 500. In some embodiments, the processor 501 may include one or more processing cores; in some embodiments, the processor 501 may integrate an application processor and a modem processor, wherein the application processor mainly handles the operating system, user interface, and applications, and the modem processor mainly handles wireless communication. It is understood that the modem processor may also not be integrated into the processor 501.

[0078] The memory 502 can be used to store software programs and modules. The processor 501 executes various functional applications and data processing by running the software programs and modules stored in the memory 502. The memory 502 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, application programs required for at least one function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the terminal 500, etc. In addition, the memory 502 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, the memory 502 may also include a memory controller to provide the processor 501 with access to the memory 502.

[0079] The terminal 500 also includes a power supply 503 that supplies power to the various components. In some embodiments, the power supply 503 can be logically connected to the processor 501 through a power management system, thereby enabling functions such as charging, discharging, and power consumption management through the power management system. The power supply 503 may also include one or more DC or AC power supplies, recharging systems, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components.

[0080] The terminal 500 may also include an input module 504, which can be used to receive input digital or character information, and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control.

[0081] The terminal 500 may also include a communication module 505. In some embodiments, the communication module 505 may include a wireless module. The terminal 500 can perform short-range wireless transmission through the wireless module of the communication module 505, thereby providing users with wireless broadband Internet access. For example, the communication module 505 can be used to help users send and receive emails, browse web pages, and access streaming media.

[0082] Although not shown, terminal 500 may also include a display unit, etc., which will not be described in detail here. Specifically, in this embodiment, processor 501 in terminal 500 loads the executable files corresponding to the processes of one or more applications into memory 502 according to the following instructions, and processor 501 runs the applications stored in memory 502 to realize various functions, as follows: The initial identification results of the truck under rain and snow weather conditions are obtained and stored in a high-speed cache. The initial identification results are used to characterize the image display status and fault identification status of each component of the truck identified by the truck operation fault dynamic image detection system. Determine whether the brake beam station identification result in the initial identification result includes the first error code. If the brake beam station identification result includes the first error code, then determine the interfered camera channel according to the image name that predicts the first error code, and block the brake beam image and the coupler image corresponding to the interfered camera channel that predict the fault. Determine whether the side frame station identification result in the initial identification result includes the second error code. If the side frame station identification result includes the second error code, obtain the preset fault masking list and delete the faults corresponding to the preset fault masking list in the initial identification result to obtain the target identification result.

[0083] For details on the implementation of each of the above operations, please refer to the previous examples, which will not be repeated here.

[0084] As can be seen from the above, the embodiments of this application can achieve channel-level fine-grained fault shielding and snow cover-based targeted fault deletion, thereby reducing the risk of false alarms in severe weather.

[0085] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be accomplished by instructions, or by instructions controlling related hardware. These instructions can be stored in a medium and loaded and executed by a processor.

[0086] Therefore, embodiments of this application provide a medium storing multiple instructions that can be loaded by a processor to execute steps in any of the rain and snow weather fault identification and processing methods provided in this application. For example, the instructions can execute the following steps: The initial identification results of the truck under rain and snow weather conditions are obtained and stored in a high-speed cache. The initial identification results are used to characterize the image display status and fault identification status of each component of the truck identified by the truck operation fault dynamic image detection system. Determine whether the brake beam station identification result in the initial identification result includes the first error code. If the brake beam station identification result includes the first error code, then determine the interfered camera channel according to the image name that predicts the first error code, and block the brake beam image and the coupler image corresponding to the interfered camera channel that predict the fault. Determine whether the side frame station identification result in the initial identification result includes the second error code. If the side frame station identification result includes the second error code, obtain the preset fault masking list and delete the faults corresponding to the preset fault masking list in the initial identification result to obtain the target identification result.

[0087] The medium may include: read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0088] According to one aspect of this application, a computer program product or computer program is provided, comprising computer instructions stored in a medium. A processor of a computer device reads the computer instructions from the medium and executes the computer instructions, causing the computer device to perform the methods provided in the various optional implementations of the above embodiments.

[0089] Since the instructions stored in the medium can execute the steps in any of the rain and snow weather fault identification and processing methods provided in the embodiments of this application, the beneficial effects that any of the rain and snow weather fault identification and processing methods provided in the embodiments of this application can achieve can be realized. For details, please refer to the previous embodiments, which will not be repeated here.

[0090] The above provides a detailed description of a rain and snow weather fault identification and processing method, device, terminal, and medium provided in the embodiments of this application. Specific examples have been used to illustrate the principles and implementation methods of this application. The description of the above embodiments is only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method for identifying and handling faults in rainy and snowy weather, characterized in that, The method includes: The initial identification results of the truck under rain and snow weather conditions are obtained and stored in a high-speed cache. The initial identification results are used to characterize the image display status and fault identification status of each component of the truck identified by the truck operation fault dynamic image detection system. Determine whether the brake beam station identification result in the initial identification result includes the first error code. If the brake beam station identification result includes the first error code, then determine the interfered camera channel according to the image name that predicts the first error code, and block the brake beam image and the coupler image corresponding to the interfered camera channel that predict the fault. Determine whether the side frame station identification result in the initial identification result includes the second error code. If the side frame station identification result includes the second error code, obtain the preset fault masking list and delete the faults corresponding to the preset fault masking list in the initial identification result to obtain the target identification result.

2. The method as described in claim 1, characterized in that, The step of storing the initial recognition result in a cache includes: The initial identification results are written to the cache based on the vehicle sequence of the truck, wherein the cache is used to store the initial identification results corresponding to each component with the vehicle sequence as the primary key.

3. The method as described in claim 1, characterized in that, The determination of whether the brake beam station identification result in the initial identification result includes the first error code includes: Extract the brake beam station identification result from the cache; Iterate through the images of the bottom left camera channel, the bottom middle camera channel, and the bottom right camera channel corresponding to the brake beam station, and determine whether the images of each camera channel report the first error code. The first error code is output by the brake beam station when rain or snow covers the camera and causes the channel images to become blurry.

4. The method as described in claim 1, characterized in that, The step of determining the interfered camera channel based on the image name of the first error code and blocking the faults predicted by the brake beam image and the coupler image corresponding to the interfered camera channel includes: Obtain the image name that predicts the first error code, and determine the corresponding interfered camera channel based on the image name. The interfered camera channel is one of the bottom left camera channel, the bottom middle camera channel, or the bottom right camera channel. According to the preset channel mapping relationship, find all brake beam images corresponding to the interfered camera channel and all coupler images corresponding to the interfered camera channel. The preset channel mapping relationship is used to record the correspondence between each camera channel, brake beam image name and coupler image name. Mark all predicted faults in all brake beam images and all coupler images found as hidden.

5. The method as described in claim 1, characterized in that, The determination of whether the side frame station identification result in the initial identification result includes the following: Extract the identification results of the side rack station from the cache; The identification results of the side frame station are traversed to determine whether there is a record corresponding to the second error code, wherein the second error code is output by the side frame station when the vehicle body or undercarriage is covered by snow.

6. The method as described in claim 1, characterized in that, The process of obtaining a preset fault masking list and deleting faults corresponding to the preset fault masking list from the initial identification result to obtain the target identification result includes: Read the preset fault masking list from the preset configuration database, wherein the preset fault masking list is used to record fault names that are prone to false alarms under snow cover conditions; Traverse the initial identification results corresponding to the current truck, and match the fault names in the initial identification results with the fault names in the preset fault masking list one by one to obtain the successfully matched fault records; The faults corresponding to the successfully matched fault records are deleted from the initial identification results, resulting in unmatched fault records; The target identification result is determined based on the unmatched fault records.

7. The method as described in claim 1, characterized in that, The method further includes: If the brake beam station identification result does not include the first error code, and the side frame station identification result does not include the second error code, then the initial identification result is determined as the target identification result.

8. A fault identification and processing device for rain and snow weather, characterized in that, The apparatus for performing the steps of the method as described in any one of claims 1 to 7 comprises: The first unit is used to obtain the initial identification results of the truck under rain and snow weather conditions and store the initial identification results in a high-speed cache. The initial identification results are used to characterize the image display status and fault identification status of each component of the truck identified by the truck operation fault dynamic image detection system. The second unit is used to determine whether the brake beam station identification result in the initial identification result includes the first error code. If the brake beam station identification result includes the first error code, the interfered camera channel is determined according to the image name of the first error code, and the brake beam image corresponding to the interfered camera channel and the fault predicted by the coupler image corresponding to the interfered camera channel are blocked. The third unit is used to determine whether the side frame station identification result in the initial identification result includes the second error code. If the side frame station identification result includes the second error code, a preset fault masking list is obtained, and the faults corresponding to the preset fault masking list are deleted in the initial identification result to obtain the target identification result.

9. A terminal, characterized in that, The method includes a processor and a memory, the memory storing multiple instructions; the processor loads instructions from the memory to perform the steps of the method as described in any one of claims 1 to 7.

10. A medium, characterized in that, The medium stores a plurality of instructions adapted for loading by a processor to execute the steps of the method according to any one of claims 1 to 7.

Images