Brake cylinder fault detection method, system, device and equipment and medium
Through the automated marking and judgment module, the physical parameters and preset conditions of the picture to be detected are used to accurately detect brake cylinder failures, solving the problem of time-consuming and labor-intensive and low accuracy of manual patrols, and improving the train's Safety and detection efficiency.
Patent Information
- Application Number
- CN202411089587.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-09
- Publication Date
- 2024-12-03
AI Technical Summary
In the prior art, fault detection of train brake cylinders relies on manual patrols, which consumes time and effort and has low accuracy, affecting driving safety.
By obtaining the information to be detected by the brake cylinder, including the pictures to be detected and the shooting position, the labeling module is used to generate the labeling box, and the fault type is determined based on the physical parameters of the labeling box and the preset judgment conditions, so as to realize automatic fault detection.
It improves the accuracy and efficiency of brake cylinder fault detection, saves manpower and material resources, and enhances the safety of the train.
Smart Images

Figure CN119067926A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of fault detection, and in particular to a method, system, device, equipment and medium for detecting a fault of a brake cylinder. Background Art
[0002] The brake components of a train, such as the brake cylinder, are important devices in the braking system of a freight train. Their braking performance will directly affect the safety of the vehicle during operation. However, due to factors such as mechanical failure or environmental loss, the brake cylinder may fail, causing safety hazards. Therefore, fault detection of train brake components is extremely important.
[0003] However, current fault detection mainly relies on manual inspection, which is time-consuming and labor-intensive, and the accuracy of fault detection is low, which seriously affects the safety of train operation. Summary of the invention
[0004] The embodiments of the present invention disclose a brake cylinder fault detection method, system, device, equipment and medium. Through the technical solution of the embodiments of the present invention, the accuracy and efficiency of train brake cylinder fault detection can be improved, and the problem that manual fault troubleshooting is time-consuming, labor-intensive and has low accuracy can be solved.
[0005] In a first aspect, an embodiment of the present invention provides a brake cylinder fault detection method, wherein the brake cylinder comprises a first component, a second component and a third component, wherein the second component is physically connected to the first component and the third component, and comprises:
[0006] Acquire at least one piece of information to be detected for the brake cylinder, wherein the information to be detected includes a picture to be detected and a corresponding shooting position, and the picture to be detected includes at least one of the first component, the second component and the third component;
[0007] According to the information to be detected, each component in the image to be detected is marked to generate a marking frame for each component in the image to be detected;
[0008] Determine the target image to be detected according to the physical parameters of the annotation box, wherein the physical parameters include the position parameters and quantity parameters of the annotation box;
[0009] The fault type of the brake cylinder is determined according to the physical parameters of the marked box in the target to be detected picture and the preset judgment conditions, wherein the preset judgment conditions include a preset area condition and a preset distance condition.
[0010] In a second aspect, an embodiment of the present invention provides a fault detection system, comprising: a patrol vehicle, a wireless base station, a data terminal and a server, wherein the server is used for the brake cylinder fault detection method described in any one of the embodiments of the present invention, and the patrol vehicle, the wireless base station, the data terminal and the server are communicatively connected;
[0011] The inspection vehicle is used to obtain the information to be detected of the brake cylinder and send it to the data terminal, wherein the information to be detected includes a picture to be detected and a corresponding shooting position, and the picture to be detected includes at least one of the first component, the second component and the third component;
[0012] The data terminal is used to receive the information to be detected sent by the inspection vehicle and forward it to the wireless base station;
[0013] The wireless base station is used to send the information to be detected to the server.
[0014] In a third aspect, an embodiment of the present invention provides a fault detection device for a brake cylinder, wherein the brake cylinder comprises a first component, a second component and a third component, wherein the second component is physically connected to the first component and the third component, and comprises:
[0015] An acquisition module, used for acquiring at least one piece of information to be detected for the brake cylinder, wherein the information to be detected includes a picture to be detected and a corresponding shooting position, and the picture to be detected includes at least one of the first component, the second component and the third component;
[0016] A labeling module, used to label each component in the image to be detected according to the information to be detected, and generate a labeling frame for each component in the image to be detected;
[0017] A target image to be detected determining module, used to determine the target image to be detected according to the physical parameters of the annotation box, wherein the physical parameters include the position parameters and quantity parameters of the annotation box;
[0018] The judgment module is used to determine the fault type of the brake cylinder according to the physical parameters of the marked box in the target to be detected picture and the preset judgment conditions, wherein the preset judgment conditions include a preset area condition and a preset distance condition.
[0019] In a fourth aspect, an embodiment of the present invention provides an electronic device, the electronic device comprising:
[0020] at least one processor; and,
[0021] a memory communicatively connected to the at least one processor; wherein,
[0022] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the brake cylinder fault detection method described in any one of the embodiments of the present invention.
[0023] In a fifth aspect, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the brake cylinder fault detection method described in any one of the embodiments of the present invention when executed.
[0024] The embodiment of the present invention provides a brake cylinder fault detection method, system, device, equipment and medium, the method comprising: obtaining at least one piece of information to be detected for the brake cylinder, wherein the information to be detected includes a picture to be detected and a corresponding shooting position, and the picture to be detected includes at least one of a first component, a second component and a third component; according to the information to be detected, marking each component in the picture to be detected, and generating a marking frame for each component in the picture to be detected; determining a target picture to be detected according to the physical parameters of the marking frame, wherein the physical parameters include the position parameter and the quantity parameter of the marking frame; determining the fault type of the brake cylinder according to the physical parameters of the marking frame in the target picture to be detected and preset judgment conditions, wherein the preset judgment conditions include preset area conditions and preset distance conditions. Specifically, the fault type of the brake cylinder can be accurately determined by the physical parameters of the marking frame in the target picture to be detected and the preset judgment conditions, wherein the preset judgment conditions include preset area conditions and preset distance conditions. The method of the embodiment of the present invention can improve the accuracy of fault detection of train brake cylinders, save manpower and material resources required for fault detection, and improve the safety of trains. BRIEF DESCRIPTION OF THE DRAWINGS
[0025] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.
[0026] Figure 1 A flow chart of a brake cylinder fault detection method provided in Embodiment 1 of the present invention;
[0027] Figure 2 A flow chart of a brake cylinder fault detection method provided in Embodiment 2 of the present invention;
[0028] Figure 3 A flowchart of a brake cylinder fault detection method provided in Embodiment 3 of the present invention;
[0029] Figure 4 A schematic diagram of a target detection module provided by an embodiment of the present invention;
[0030] Figure 5 A schematic diagram of labeling a picture to be detected provided by an embodiment of the present invention;
[0031] Figure 6 A structural diagram of a fault detection system provided in Embodiment 4 of the present invention;
[0032] Figure 7 A schematic diagram of a data connection terminal provided by an embodiment of the present invention;
[0033] Figure 8 A schematic structural diagram of a brake cylinder fault detection device provided in a fifth embodiment of the present invention;
[0034] Fig. 9 This is a schematic diagram of the structure of an electronic device provided in Embodiment 6 of the present invention. DETAILED DESCRIPTION
[0035] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. 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 should fall within the scope of protection of the present invention.
[0036] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.
[0037] It should be noted that the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved in the technical solution of the present disclosure are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.
[0038] Embodiment 1
[0039] Figure 1 The flowchart of the brake cylinder fault detection method provided in the first embodiment of the present invention is applicable to the field of fault detection, and is applied to the situation of fault detection of the brake cylinder of a train. It can be executed by a brake cylinder fault detection device, which can be implemented by software and / or hardware and configured in a server or computer.
[0040] Specific as Figure 1 As shown, including:
[0041] Step 110: Obtain at least one piece of information to be detected for the brake cylinder, wherein the information to be detected includes a picture to be detected and a corresponding shooting position, and the picture to be detected includes at least one of the first component, the second component and the third component.
[0042] The information to be detected includes the picture to be detected and the corresponding shooting position. The information to be detected can be obtained by a rail vehicle including a camera. The rail vehicle will shoot at different positions on the track to obtain the picture to be detected at the corresponding shooting position.
[0043] Optionally, the first component may be a piston rod lifting lug of a brake cylinder, the second component may be a return nut of the brake cylinder, and the third component may be a cylinder cover of the brake cylinder.
[0044] Specifically, due to the different shooting positions of the rail vehicles, in the pictures to be detected of the same brake cylinder, some components of the brake cylinder may be blocked by the train wheels or other components due to the angle, and the pictures to be detected cannot include all the components of the brake cylinder. Therefore, it is necessary to determine the target picture to be detected from multiple pictures to be detected of the same brake cylinder according to the method of the embodiment of the present invention, and then judge the fault of the brake cylinder based on the target picture to be detected.
[0045] Step 120: annotate each component in the image to be detected according to the information to be detected, and generate an annotation box for each component in the image to be detected.
[0046] The labeling process is the process of determining the area where the component is located in the image to be detected.
[0047] Specifically, it is necessary to perform image recognition on the image to be detected, and then determine the location areas of the first component, the second component and the third component in the image, and mark the components to generate corresponding marking boxes. Subsequently, it can be determined whether the brake cylinder has a fault based on the physical parameters of the marking box.
[0048] Optionally, step 120 includes:
[0049] The contour of each component in the image to be detected is extracted to determine the contour data of each component.
[0050] Among them, different parts of the brake cylinder have different contours in the image to be detected, and the colors or shapes of different parts may also be different. Therefore, the contour of the parts can be extracted according to the color or shape of each part to determine the corresponding contour data. The specific contour extraction method is not limited in this application. Further, the contour data may include the coordinates of the points on the contour, the contour shape, etc.
[0051] The shooting angle of the image to be detected is determined according to the shooting position.
[0052] The shooting angle may be determined by calculation based on the coordinates of the shooting position and the position coordinates of the brake cylinder. The specific calculation method is not limited here.
[0053] According to the shooting angle and the real contours of the components of the brake cylinder, the shooting contours of the components of the brake cylinder at each shooting angle are determined.
[0054] Specifically, due to different shooting angles, the shooting contour of the component in the image to be detected may be different from the real contour of the component, such as stretching, deformation, etc. Therefore, it is necessary to determine the shooting contour of the corresponding component in the image to be detected according to the shooting angle and the real contour of the component, so as to achieve the purpose of more accurately extracting the components of the brake cylinder, thereby improving the accuracy of fault detection.
[0055] Optionally, based on a preset angle shape relationship, the shooting contour of each component can be determined according to the shooting angle and the actual contour of each component of the brake cylinder, wherein the angle shape relationship is used to characterize the mapping relationship between the actual contour of each component of the brake cylinder and the shooting contour in the picture to be detected at different shooting angles.
[0056] Specifically, before fault detection, the actual shooting contours of each component in the image to be detected at different shooting angles can be pre-stored to establish a corresponding mapping relationship. Then, during the fault detection process, the shooting contour corresponding to the component can be determined according to the shooting angle based on the mapping relationship.
[0057] If the contour data of the component in the to-be-detected image is the corresponding photographed contour, a corresponding annotation box is generated according to the contour data of the component.
[0058] Specifically, if the contour data of the component in the image to be detected is the corresponding shooting contour, it means that the contour data is the data of the component corresponding to the shooting contour. Therefore, the corresponding annotation box can be generated according to the contour data to achieve the purpose of annotating the component in the image to be detected.
[0059] Optionally, in an optional embodiment of the present invention, an optimal shooting position can be determined according to the shooting angle, such as the position facing the brake cylinder. In the picture to be detected at the nearest shooting position, all components are in the facing position, and there is no shooting deformation caused by shooting, that is, the actual contour is the same as the shooting contour. Then, the annotation box of the component can be determined according to the picture to be detected at the shooting position. Further, due to the difference in shooting positions, only some components in the picture to be detected may be in the facing position. Therefore, the components in the facing position in multiple pictures to be detected can also be spliced and combined to form a new picture to be detected, so that all components in the picture to be detected are in the facing position. Then, the corresponding annotation box is generated according to the contour data of the component in the new picture to be detected.
[0060] Optionally, generating a corresponding annotation box according to the contour data of the component includes:
[0061] Determining a minimum circumscribed rectangle of the component according to the contour data of the component;
[0062] The minimum circumscribed rectangle is determined as a labeling box of the component.
[0063] Specifically, the corresponding minimum enclosing rectangle can be determined through the contour coordinates in the contour data. The minimum enclosing rectangle can accurately represent the position of the component in the image to be detected, thereby improving the accuracy of subsequent fault judgment.
[0064] Step 130: determining the target image to be detected according to the physical parameters of the annotation box, wherein the physical parameters include the position parameters and quantity parameters of the annotation box.
[0065] Among them, the physical parameters of the annotation box are used to characterize the working status of the corresponding components. For example, the area of the annotation box is used to determine whether the component is deformed, and the distance between the center points of the annotation box is used to characterize whether the components are tightly connected.
[0066] Specifically, since the brake cylinder itself has a complex structure and is composed of multiple parts, it is necessary to comprehensively judge whether the brake cylinder has a fault based on the status of each part of the brake cylinder.
[0067] Optionally, it is necessary to determine whether the image to be detected contains all the components based on the number of marked boxes. Then, among multiple images of the same brake cylinder, determine the target image to be detected that meets the detection requirements, such as whether the number of components in the image to be detected meets the preset requirements.
[0068] Optionally, the target image to be detected may be judged by determining a labeling frame with a preset aspect ratio as the target labeling frame, and then determining whether the number of target labeling frames meets a preset number condition. The preset aspect ratio may be determined according to the aspect ratio of a real component.
[0069] Step 140: Determine the fault type of the brake cylinder according to the physical parameters of the marked box in the target to be detected picture and preset judgment conditions, wherein the preset judgment conditions include preset area conditions and preset distance conditions.
[0070] The preset judgment conditions are used to characterize whether the working state of the component meets the preset requirements, such as whether the connection is tight or whether deformation occurs.
[0071] Specifically, whether the brake cylinder is faulty can be determined by the working status of each component, and the working status of each component can be represented by the physical parameters of the marked box. Therefore, whether the brake cylinder is faulty can be determined by the physical parameters of the marked box.
[0072] The embodiment of the present invention provides a method for fault detection of a brake cylinder. The method comprises: obtaining at least one piece of information to be detected for the brake cylinder, wherein the information to be detected comprises a picture to be detected and a corresponding shooting position, and the picture to be detected comprises at least one of a first component, a second component and a third component; marking each component in the picture to be detected according to the information to be detected, and generating a marking frame for each component in the picture to be detected; determining a target picture to be detected according to the physical parameters of the marking frame, wherein the physical parameters comprise a position parameter and a quantity parameter of the marking frame; determining the fault type of the brake cylinder according to the physical parameters of the marking frame in the target picture to be detected and a preset judgment condition, wherein the preset judgment condition comprises a preset area condition and a preset distance condition. Specifically, the shooting angle of the picture to be detected can be determined by the shooting position of the picture to be detected, and then the shooting contour of each component can be determined by the preset angle shape relationship. Further, if the contour data of the component in the picture to be detected is the corresponding shooting contour, the corresponding marking frame is generated according to the contour data of the component. In this way, the position of the components in the image to be detected can be accurately determined, and the corresponding annotation box can be generated, thereby improving the accuracy of brake cylinder fault judgment and improving the safety of the train. The method of the embodiment of the present invention can also save manpower and material resources required for fault detection.
[0073] Embodiment 2
[0074] Figure 2 This is a flow chart of a brake cylinder fault detection method provided in the second embodiment of the present invention. This embodiment is based on the above embodiments and further defines the implementation methods of some steps of the brake cylinder fault detection method.
[0075] like Figure 2 As shown, including:
[0076] Step 210: Obtain at least one piece of information to be detected for the brake cylinder, wherein the information to be detected includes a picture to be detected and a corresponding shooting position, and the picture to be detected includes at least one of the first component, the second component and the third component.
[0077] Step 220: annotate each component in the image to be detected according to the information to be detected, and generate an annotation box for each component in the image to be detected.
[0078] Step 230: Determine the number of the marked boxes in the image to be detected according to the number parameter of the marked boxes of the image to be detected.
[0079] Step 240: If the number of the marked boxes in the to-be-detected picture meets a preset number condition, the to-be-detected picture is determined as a target to-be-detected picture.
[0080] Specifically, for each component in the picture to be detected, there is a corresponding unique annotation box, so the number of annotation boxes is equal to the number of components in the picture to be detected. Due to different shooting positions, some components may be blocked by other components. Therefore, it is necessary to judge the number of annotation boxes in the picture to be detected to determine whether the picture to be detected contains all the components that need to be detected / all. If the number of annotation boxes meets the preset quantity condition, it means that the picture to be detected contains all the components that need to be detected / all of the brake cylinder, and then the picture to be detected can be determined as the target picture to be detected. Otherwise, it means that there are insufficient components in the picture to be detected, and the picture to be detected with insufficient components cannot perform accurate fault detection, so it needs to be excluded.
[0081] Optionally, the preset quantity condition may be to determine whether the number of annotation boxes in the image to be detected is equal to 3. If it is equal to 3, it means that the preset quantity condition is met.
[0082] Exemplarily, the annotation process of the image to be detected can be implemented by deep learning / neural network algorithms. Optionally, an anchor-based algorithm uses predefined anchor boxes to predict the location and size of the target; a region-based convolutional neural network (R-CNN) uses a selective search algorithm to generate candidate regions, and then uses a convolutional neural network to classify and regress bounding boxes for these regions. The attention mechanism can also be used to focus on key areas in the image to more accurately predict the bounding box.
[0083] Step 250: Determine the center point coordinates and vertex coordinates of the marked box according to the position parameters of the marked box in the target to be detected picture.
[0084] The position parameters of the annotation box are used to characterize the image area or component outline of the corresponding component, and can also be used to characterize the positional relationship between components.
[0085] Step 260: Determine the distance between each component according to the center point coordinates of each marked frame.
[0086] Step 270: Determine the area of each marked box according to the vertex coordinates of each marked box.
[0087] Step 280: If the distance does not meet the preset distance condition, the brake cylinder fault is determined to be a cylinder brake fault.
[0088] Step 290: If the area does not meet the preset area condition, the fault of the brake cylinder is determined to be a deformation fault.
[0089] The center point of the marked box can represent the center point of the component, and the distance between the components can represent the connection status between the components. If the distance is too large, it means that the components may be disconnected. The preset distance condition is used to determine whether the distance between the components meets the safety distance of the brake cylinder components.
[0090] The area of the marked box can represent the surface area of the component. If the area of the marked box is too large, it means that the component may be stretched, and if the area is too small, it may be squeezed. The preset area condition is used to determine whether the component is stretched or squeezed.
[0091] Specifically, if the distance between the components does not meet the preset distance condition, the fault of the brake cylinder is determined to be a cylinder brake fault. If the area of the annotation box does not meet the preset area condition, the fault of the brake cylinder is determined to be a deformation fault. It should be noted that since the deformation of the component may be due to shooting deformation caused by different shooting angles and physical deformation caused by mechanical failure, the preset area condition can also be used to determine the deformation cause of the component corresponding to the annotation box, such as determining whether the component in the image to be detected is shooting deformation and / or physical deformation. Specifically, actual judgment can be made based on the different deformation areas corresponding to different deformation causes. Among them, the deformation caused by physical deformation can be determined as a deformation fault.
[0092] The embodiment of the present invention provides a brake cylinder fault detection method. The method can determine the target image to be detected by the number parameter of the annotation box. The target image to be detected is the image to be detected that successfully captures the complete image of the brake cylinder. Furthermore, the position parameter of the image annotation box can be used to determine whether the various components of the brake cylinder have cylinder brake faults or deformation faults. Through the method of the embodiment of the present invention, the accuracy of brake cylinder fault detection can be improved, and the safety of the train can be improved. The method of the embodiment of the present invention can also save the manpower and material resources required for fault detection.
[0093] Embodiment 3
[0094] Figure 3 This is a flow chart of a brake cylinder fault detection method provided in Embodiment 3 of the present invention. This embodiment is based on the above embodiments and further defines each step. Figure 3 As shown, including:
[0095] Step 310: input the image to be detected into the fault judgment model.
[0096] The fault judgment model can be obtained through pre-training, and the fault judgment model can be used to judge whether a brake cylinder corresponding to the image to be detected has a fault.
[0097] The fault judgment model includes a target detection module and a defect judgment module. Specifically, Figure 4 A schematic diagram of a target detection module provided by an embodiment of the present invention, wherein the input is a picture to be detected and the output is a picture to be detected with a marked box. The backbone network can be a FPN / PAnet network. The main function of FPN is to solve the problem of multi-scale changes in target detection. It is a top-down structure that can pass low-level features downward and combine them with high-level features to obtain features with strong semantic information. PANet is a bottom-up network that strengthens the entire feature hierarchy through accurate low-level positioning signals, thereby shortening the information path between the low and high layers. FPN can fuse feature information of different scales, and the role of PANet is to make up for the lack of positioning information. The Mosaic algorithm and the CutMix algorithm are mainly used in the target detection module. The Mosaic algorithm is used to enhance data features, and the CutMix algorithm is used to splice and combine pictures. The target detection module also includes an attention submodule to help the network focus on the target object to be identified, thereby improving the position accuracy of the marked box.
[0098] Step 320: extract features from the image to be detected and determine the labeling box of each component in the image to be detected.
[0099] Optionally, contour extraction is performed on each component in the image to be detected to determine contour data of each component;
[0100] Determining a shooting angle of the image to be detected according to the shooting position;
[0101] Determining the shooting contours of the components of the brake cylinder at each shooting angle according to the shooting angle and the real contours of the components of the brake cylinder;
[0102] If the contour data of the component in the to-be-detected image is the corresponding photographed contour, a corresponding annotation box is generated according to the contour data of the component.
[0103] Step 330: Determine whether the number of marked boxes is equal to 3.
[0104] Specifically, if the number of the marked boxes is equal to 3, it means that the image to be tested completely displays all the components of the brake cylinder that need to be tested, and the image to be tested can be determined as the target image to be tested. Otherwise, it means that there are insufficient components in the image to be tested, and the image to be tested with insufficient components cannot be accurately detected, so it needs to be excluded. Figure 5 A schematic diagram of labeling a picture to be detected provided in an embodiment of the present invention, wherein #1, #2 and #3 correspond to the first component, the second component and the third component in the embodiment of the present invention respectively.
[0105] Step 340: Determine whether the area of the annotation box meets a preset area condition.
[0106] Specifically, the area of the annotation box can be determined by the length and width of the annotation box.
[0107] Step 350: Determine whether the distance between the center points of the annotation box meets a preset distance condition.
[0108] Step 360: Output the fault type.
[0109] Specifically, if the distance between the center points of the marking box does not meet the preset distance condition, the fault of the brake cylinder is determined to be a cylinder brake fault; if the area of the marking box does not meet the preset area condition, the fault of the brake cylinder is determined to be a deformation fault.
[0110] Optionally, it is also possible to determine whether the brake cylinder has a fault by marking parameters such as the aspect ratio of the frame or the distance between the edges of the frame and comparing them with corresponding preset conditions.
[0111] Step 370, end.
[0112] The brake cylinder fault detection method provided by the embodiment of the present invention can improve the accuracy of brake cylinder fault detection and save manpower and material resources required for fault detection.
[0113] Embodiment 4
[0114] Figure 6 A structural schematic diagram of a fault detection system provided for Embodiment 4 of the present invention comprises: an inspection vehicle 620, a wireless base station 630, a data terminal 640 and a server 610, wherein the server 610 is used to execute any of the brake cylinder fault detection methods in the embodiments of the present invention, and the inspection vehicle, the wireless base station, the data terminal and the server are communicatively connected; the inspection vehicle 620 is used to obtain information to be detected of the brake cylinder and send it to the data terminal, wherein the information to be detected comprises a picture to be detected and a corresponding shooting position, and the picture to be detected comprises at least one of the first component, the second component and the third component; the data terminal 640 is used to receive the information to be detected sent by the inspection vehicle and forward it to the wireless base station; the wireless base station 630 is used to send the information to be detected to the server.
[0115] Optionally, the server 610 is configured to obtain at least one piece of information to be detected for the brake cylinder, wherein the information to be detected includes a picture to be detected and a corresponding shooting position, and the picture to be detected includes at least one of the first component, the second component and the third component;
[0116] According to the information to be detected, each component in the image to be detected is marked to generate a marking frame for each component in the image to be detected;
[0117] Determine the target image to be detected according to the physical parameters of the annotation box, wherein the physical parameters include the position parameters and quantity parameters of the annotation box;
[0118] The fault type of the brake cylinder is determined according to the physical parameters of the marked box in the target to be detected picture and the preset judgment conditions, wherein the preset judgment conditions include a preset area condition and a preset distance condition.
[0119] Optionally, the server 610 is configured to extract contours of each component in the image to be detected, and determine contour data of each component;
[0120] Determining a shooting angle of the image to be detected according to the shooting position;
[0121] Determining the shooting contours of the components of the brake cylinder at each shooting angle according to the shooting angle and the real contours of the components of the brake cylinder;
[0122] If the contour data of the component in the to-be-detected image is the corresponding photographed contour, a corresponding annotation box is generated according to the contour data of the component.
[0123] Optionally, the server 610 is configured to determine the number of the marked boxes in the picture to be detected according to a number parameter of the marked boxes of the picture to be detected;
[0124] If the number of the marked boxes in the to-be-detected picture meets a preset number condition, the to-be-detected picture is determined as a target to-be-detected picture.
[0125] Optionally, the server 610 is used to determine the center point coordinates and vertex coordinates of the marked box according to the position parameters of the marked box in the target to be detected picture;
[0126] Determine the distance between each component according to the coordinates of the center point of each annotation frame;
[0127] Determine the area of each marked box according to the vertex coordinates of each marked box;
[0128] If the distance does not meet a preset distance condition, determining the brake cylinder failure as a cylinder brake failure;
[0129] If the area does not satisfy a preset area condition, the fault of the brake cylinder is determined to be a deformation fault.
[0130] Optionally, the data terminal 640 is connected to the server 610 via the wireless base station 630. Figure 7 A schematic diagram of a data terminal provided for an embodiment of the present invention, wherein the SOC chip adopts a high-performance, low-power, and feature-rich domestic application processor for the industrial Internet of Things market, a quad-core 64-bit Cortex-A55 architecture, a main frequency of up to 2.0GHz, and a built-in NPU. The RAM memory is 16GB LPDDR4x, and the ROM uses 64GB eMMC. The device adopts a dual 5G-R module active-standby redundant design, which supports multiple frequency bands such as B1, B3, N1, N28, N41, N78, and N79, which is different from other single 5G module data terminals, and provides uninterrupted multi-network access capabilities. With its comprehensive security and multi-data link characteristics, it provides a high-speed and stable multimedia data transmission channel. Due to the remote terrain of the railway freight yard, the operator's 4G / 5G network coverage signal is poor. The device has the ability to manage network multi-links and automatically switches according to priority: the first priority 5G-R private network is the highest. When the first priority network is offline, it automatically switches to the second priority operator 4G / 5G network. When the first priority network is restored, it automatically switches back to the first priority network.
[0131] The fault detection system disclosed in the embodiment of the present invention can improve the accuracy of brake cylinder fault detection and save manpower and material resources required for fault detection.
[0132] Embodiment 5
[0133] Figure 8 This is a schematic diagram of the structure of a brake cylinder fault detection device provided in Embodiment 5 of the present invention, wherein the brake cylinder comprises a first component, a second component and a third component, wherein the second component is physically connected to the first component and the third component, and comprises:
[0134] The acquisition module 810 is used to acquire at least one piece of information to be detected for the brake cylinder, wherein the information to be detected includes a picture to be detected and a corresponding shooting position, and the picture to be detected includes at least one of the first component, the second component and the third component;
[0135] A labeling module 820, configured to label each component in the image to be detected according to the information to be detected, and generate a labeling frame for each component in the image to be detected;
[0136] The target image to be detected determining module 830 is used to determine the target image to be detected according to the physical parameters of the annotation box, wherein the physical parameters include the position parameters and quantity parameters of the annotation box;
[0137] The judgment module 840 is used to determine the fault type of the brake cylinder according to the physical parameters of the marked box in the target to be detected picture and the preset judgment conditions, wherein the preset judgment conditions include a preset area condition and a preset distance condition.
[0138] The brake cylinder fault detection device disclosed in the embodiment of the present invention can accurately determine the fault type of the brake cylinder through the physical parameters of the marked box in the target to be detected picture and the preset judgment conditions, wherein the preset judgment conditions include preset area conditions and preset distance conditions. The method of the embodiment of the present invention can improve the accuracy of the fault detection of the train brake cylinder, save the manpower and material resources required for fault detection, and improve the safety of the train.
[0139] Optionally, the marking module 820 includes:
[0140] A contour extraction unit, used to extract the contour of each component in the image to be detected and determine the contour data of each component;
[0141] An angle determination unit, used to determine the shooting angle of the image to be detected according to the shooting position;
[0142] A shooting contour determining unit, used to determine the shooting contours of the components of the brake cylinder at each shooting angle according to the shooting angle and the real contours of the components of the brake cylinder;
[0143] The judging unit is used to generate a corresponding annotation frame according to the contour data of the component if the contour data of the component in the to-be-detected picture is the corresponding shooting contour.
[0144] Furthermore, the shooting contour determination unit is specifically used to determine the shooting contour of each component based on a preset angle shape relationship, according to the shooting angle and the actual contours of each component of the brake cylinder, wherein the angle shape relationship is used to characterize the mapping relationship between the actual contours of each component of the brake cylinder and the shooting contours in the picture to be detected at different shooting angles.
[0145] Optionally, the judgment unit includes a labeling subunit, which is used to determine the minimum circumscribed rectangle of the component according to the contour data of the component; and determine the minimum circumscribed rectangle as the labeling box of the component.
[0146] Optionally, the target to-be-detected picture determination module 830 includes:
[0147] A quantity counting unit, used to determine the number of the marked boxes in the picture to be detected according to the number parameter of the marked boxes of the picture to be detected;
[0148] The judging unit is configured to determine the image to be detected as a target image to be detected if the number of the marked boxes in the image to be detected meets a preset number condition.
[0149] Optionally, the determination module 840 includes:
[0150] A parsing unit, used to determine the center point coordinates and vertex coordinates of the marked box according to the position parameters of the marked box in the target to be detected picture;
[0151] A distance determination unit, used to determine the distance between each component according to the coordinates of the center point of each marked frame;
[0152] An area determination unit, used to determine the area of each annotation box according to the vertex coordinates of each annotation box;
[0153] a distance judgment unit, configured to determine the brake cylinder failure as a cylinder brake failure if the distance does not satisfy a preset distance condition;
[0154] The area judgment unit is used to determine the fault of the brake cylinder as a deformation fault if the area does not meet a preset area condition.
[0155] The brake cylinder fault detection device provided in the embodiment of the present invention can execute the brake cylinder fault detection device method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.
[0156] Embodiment 6
[0157] Fig. 9A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.
[0158] like Fig. 9 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.
[0159] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.
[0160] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as a fault detection device method for a brake cylinder.
[0161] In some embodiments, the brake cylinder fault detection device method can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the brake cylinder fault detection device method described above can be performed. Alternatively, in other embodiments, the processor 11 can be configured to execute the brake cylinder fault detection device method in any other appropriate manner (for example, by means of firmware).
[0162] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.
[0163] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.
[0164] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
[0165] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).
[0166] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.
[0167] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.
[0168] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.
[0169] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims
1. A brake cylinder fault detection method, characterized in that: The brake cylinder comprises a first component, a second component and a third component, wherein the second component is physically connected to the first component and the third component, and comprises: Acquire at least one piece of information to be detected for the brake cylinder, wherein the information to be detected includes a picture to be detected and a corresponding shooting position, and the picture to be detected includes at least one of the first component, the second component and the third component; According to the information to be detected, each component in the image to be detected is marked to generate a marking frame for each component in the image to be detected; Determine the target image to be detected according to the physical parameters of the annotation box, wherein the physical parameters include the position parameters and quantity parameters of the annotation box; The fault type of the brake cylinder is determined according to the physical parameters of the marked box in the target to be detected picture and the preset judgment conditions, wherein the preset judgment conditions include a preset area condition and a preset distance condition.
2. The method according to claim 1, characterized in that The step of labeling each component in the image to be detected according to the information to be detected, and generating a labeling frame for each component in the image to be detected, comprises: Extracting contours of components in the image to be detected to determine contour data of each component; Determining a shooting angle of the image to be detected according to the shooting position; Determining the shooting contours of the components of the brake cylinder at each shooting angle according to the shooting angle and the real contours of the components of the brake cylinder; If the contour data of the component in the to-be-detected image is the corresponding photographed contour, a corresponding annotation box is generated according to the contour data of the component.
3. The method according to claim 2, characterized in that Determining the shooting contours of the components of the brake cylinder at each shooting angle according to the shooting angle and the real contours of the components of the brake cylinder includes: Based on a preset angle shape relationship, the shooting contour of each component is determined according to the shooting angle and the real contour of each component of the brake cylinder, wherein the angle shape relationship is used to characterize the mapping relationship between the real contour of each component of the brake cylinder and the shooting contour in the image to be detected at different shooting angles.
4. The method according to claim 2, characterized in that: Generating a corresponding annotation frame according to the contour data of the component includes: Determining a minimum circumscribed rectangle of the component according to the contour data of the component; The minimum circumscribed rectangle is determined as a labeling box of the component.
5. The method according to claim 1, characterized in that The step of determining the target image to be detected according to the physical parameters of the annotation box includes: Determining the number of the marked boxes in the picture to be detected according to the number parameter of the marked boxes of the picture to be detected; If the number of the marked boxes in the to-be-detected picture meets a preset number condition, the to-be-detected picture is determined as a target to-be-detected picture.
6. The method according to claim 1, characterized in that The step of determining the fault type of the brake cylinder according to the physical parameters of the marked box in the target to be detected picture and the preset judgment conditions includes: Determine the center point coordinates and vertex coordinates of the marked box according to the position parameters of the marked box in the target to be detected picture; Determine the distance between each component according to the coordinates of the center point of each annotation frame; Determine the area of each marked box according to the vertex coordinates of each marked box; If the distance does not meet a preset distance condition, determining the brake cylinder failure as a cylinder brake failure; If the area does not satisfy a preset area condition, the fault of the brake cylinder is determined to be a deformation fault.
7. A fault detection system, characterized in that: include: Inspection vehicle, wireless base station, data terminal and server, wherein the server is used to execute the brake cylinder fault detection method according to any one of claims 1 to 6, and the inspection vehicle, wireless base station, data terminal and server are communicatively connected; The inspection vehicle is used to obtain the information to be detected of the brake cylinder and send it to the data terminal, wherein the information to be detected includes a picture to be detected and a corresponding shooting position, and the picture to be detected includes at least one of the first component, the second component and the third component; The data terminal is used to receive the information to be detected sent by the inspection vehicle and forward it to the wireless base station; The wireless base station is used to send the information to be detected to the server.
8. A brake cylinder fault detection device, characterized in that: The brake cylinder comprises a first component, a second component and a third component, wherein the second component is physically connected to the first component and the third component, and comprises: An acquisition module, used for acquiring at least one piece of information to be detected for the brake cylinder, wherein the information to be detected includes a picture to be detected and a corresponding shooting position, and the picture to be detected includes at least one of the first component, the second component and the third component; A labeling module, used to label each component in the image to be detected according to the information to be detected, and generate a labeling frame for each component in the image to be detected; A target image to be detected determining module, used to determine the target image to be detected according to the physical parameters of the annotation box, wherein the physical parameters include the position parameters and quantity parameters of the annotation box; The judgment module is used to determine the fault type of the brake cylinder according to the physical parameters of the marked box in the target to be detected picture and the preset judgment conditions, wherein the preset judgment conditions include a preset area condition and a preset distance condition.
9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the brake cylinder fault detection method according to any one of claims 1 to 6.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the brake cylinder fault detection method according to any one of claims 1 to 6 when executed.
Citation Information
Patent Citations
Truck brake cylinder fault detection method based on improved Faster Rcnn
CN112102281A
Upper pull rod fault detection method based on deep learning
CN112434695A
Ideal contour generation algorithm and device based on reinforcement learning, and storage medium
CN116452621A
Oil and gas station image processing method and device, electronic equipment and storage medium
CN117253231A
System and method for manufacturing quality control using automated visual inspection
WO2022160040A1
