Freight train set braking state detection method, device and system

Abstract

The invention discloses a freight train set braking state detection method, device and system. The method comprises the following steps: acquiring vehicle information of at least one vehicle of a freight train set from a marshalling station integrated automation system; responding to a propulsion signal sent by the hump automatic control system to the freight train set, and for each section of vehicle, controlling image acquisition equipment to shoot a brake auxiliary device of the vehicle to obtain a to-be-detected image; the brake assisting device comprises a piston and a brake chain; performing target detection on the to-be-detected image to obtain a target detection result; according to the target detection result and the abnormal state threshold value, the braking state of the vehicle is determined; in response to the fact that the braking state of the vehicle is an abnormal state, the braking state of the vehicle is sent to a debugging automation system, so that the debugging automation system carries out stop control on the freight train set; and the train unit reinspection system receives an end signal sent by the hump automatic control system. According to the embodiment of the invention, the automation level and accuracy of freight train braking state detection can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of rail transit control, and particularly to a method, device and system for detecting the braking state of a freight train formation. Background Art

[0002] With the rapid development of rail transit control technology, in order to ensure the operation safety of a freight train formation during the rolling process after hump breakdown, it is necessary to inspect the execution states of brake shoes, brake chains and pistons of each vehicle of the freight train formation to determine the braking state of each vehicle of the freight train formation.

[0003] Currently, a visual inspection is carried out manually during the pushing process of the freight train formation to determine the execution states of the brake shoes, brake chains and pistons of each vehicle.

[0004] However, the method of manual inspection has low efficiency and is prone to problems of missed inspection and misjudgment, that is, the automation level is poor and the accuracy is low. Summary of the Invention

[0005] The present invention provides a method, device and system for detecting the braking state of a freight train formation. Embodiments of the present invention can improve the automation level and accuracy of detecting the braking state of a freight train formation.

[0006] In a first aspect, an embodiment of the present invention provides a method for detecting the braking state of a freight train formation, the method including:

[0007] Obtaining vehicle information of at least one vehicle of the freight train formation from an integrated automation system of a marshalling station;

[0008] In response to a propulsion signal sent by a hump automation control system to the freight train formation, for each vehicle, controlling an image acquisition device to capture the braking auxiliary device of the vehicle to obtain a to-be-detected image; the braking auxiliary device includes a piston and a brake chain;

[0009] Performing target detection on the to-be-detected image to obtain a target detection result;

[0010] Determining the braking state of the vehicle according to the target detection result and an abnormal state threshold;

[0011] In response to the braking state of the vehicle being an abnormal state, sending the braking state of the vehicle to a locomotive automation system so that the locomotive automation system controls the freight train formation to stop;

[0012] A train re-inspection system receives an end signal sent by the hump automation control system.

[0013] In a second aspect, an embodiment of the present invention further provides a device for detecting the braking state of a freight train formation, the device including:

[0014] A vehicle information acquisition module, configured to acquire vehicle information of at least one vehicle of a freight train from a marshalling station integrated automation system;

[0015] An image acquisition module, configured to, in response to a propulsion signal sent by a hump automation control system to the freight train, for each vehicle, control an image acquisition device to capture the braking auxiliary device of the vehicle to obtain a to-be-detected image; the braking auxiliary device includes a piston and a brake chain;

[0016] A target detection module, configured to perform target detection on the to-be-detected image to obtain a target detection result;

[0017] A braking state determination module, configured to determine the braking state of the vehicle according to the target detection result and an abnormal state threshold;

[0018] A stop control module, configured to, in response to the braking state of the vehicle being an abnormal state, send the braking state of the vehicle to a shunting locomotive automation system, so that the shunting locomotive automation system performs stop control on the freight train;

[0019] An end signal receiving module, configured to receive an end signal sent by the hump automation control system by a train re-inspection system.

[0020] Thirdly, an embodiment of the present invention further provides a freight train braking state detection system, where the freight train braking state detection system includes:

[0021] At least one processor; and

[0022] A memory communicatively connected to the at least one processor; wherein,

[0023] 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 freight train braking state detection method of any embodiment of the present invention.

[0024] Fourthly, an embodiment of the present invention further provides a computer-readable storage medium, where the computer-readable storage medium stores computer instructions, and the computer instructions are used to implement the freight train braking state detection method of any embodiment of the present invention when executed by a processor.

[0025] Fifthly, an embodiment of the present invention further provides a freight train control system, including: a freight train braking state detection system, a marshalling station integrated automation system, a hump automation control system, and a shunting locomotive automation system;

[0026] The marshalling station integrated automation system is configured to acquire vehicle information of at least one vehicle of the freight train, and send the vehicle information of at least one vehicle of the freight train to the freight train braking state detection system;

[0027] The hump automatic control system is used to send a propulsion signal to the freight train formation;

[0028] The braking state detection system of the freight train formation is used to respond to the propulsion signal sent by the hump automatic control system to the freight train formation. For each vehicle, it controls the image acquisition device to photograph the braking auxiliary device of the vehicle to obtain the image to be detected; the braking auxiliary device includes a piston rod and a brake chain;

[0029] The braking state detection system of the freight train formation is used to perform target detection on the image to be detected to obtain the target detection result;

[0030] The braking state detection system of the freight train formation is used to determine the braking state of the vehicle according to the target detection result and the abnormal state threshold;

[0031] The braking state detection system of the freight train formation is used to send the braking state of the vehicle to the hump automatic control system and the shunting locomotive automatic control system;

[0032] The shunting locomotive automation is used to control the stop of the freight train formation;

[0033] The hump automatic control system is used to send an end signal to the train re-inspection system.

[0034] The technical solution of the embodiment of the present invention can realize the acquisition of the status information of the freight train formation by obtaining vehicle information when the freight train formation arrives at the starting section of the hump, providing basic data for subsequent detection and control; by photographing the braking auxiliary device for each vehicle, it can realize the local inspection of the auxiliary braking device to ensure that the auxiliary braking device of each vehicle is effectively detected; by performing target detection on the image to be detected, it can realize the automatic identification of the status of the braking device, reduce the need for manual inspection, and improve the efficiency and accuracy of detection; by combining the target detection result with the abnormal state threshold, it can realize the automatic judgment of the braking state of each vehicle, contribute to improving the accuracy of status evaluation, and avoid human errors; by controlling the stop of the freight train formation according to the braking state of the vehicle, it can realize automatic safety control and reduce the accident risk caused by abnormal braking; thus, it can improve the automation level and accuracy of the braking state detection of the freight train formation.

[0035] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present invention, nor is it used to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] To more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0037] Figure 1 Flow chart of a method for detecting the braking state of a freight train formation provided by an embodiment of the present invention Figure 1 ;

[0038] Figure 2 Flow chart of a method for detecting the braking state of a freight train formation provided by an embodiment of the present invention Figure 2 ;

[0039] Figure 3 Schematic structural diagram of a system for detecting the braking state of a freight train formation provided by an embodiment of the present invention;

[0040] Figure 4 Flow chart of a method for detecting the braking state of a freight train formation provided by an embodiment of the present invention;

[0041] Figure 5 Schematic structural diagram of a device for detecting the braking state of a freight train formation provided by an embodiment of the present invention;

[0042] Figure 6 Schematic structural diagram of a system for detecting the braking state of a freight train formation provided by an embodiment of the present invention. Detailed implementation manners

[0043] In order to enable those skilled in the art to better understand the solutions of the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0044] It should be noted that the terms "first", "second", etc. in the description, claims and above-mentioned drawings of the present invention are used to distinguish similar objects, and do not necessarily have to be used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of the present invention described here can be implemented in an order other than those illustrated or described here. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units does not have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0045] In the technical solution of the embodiment of the present invention, the acquisition, storage and application of vehicle information, initial images, images to be detected, etc. all comply with the provisions of relevant laws and regulations and do not violate public order and good customs.

[0046] Figure 1 The figure is a flowchart of a method for detecting the braking state of a freight train formation provided by an embodiment of the present invention. The embodiment of the present invention is applicable to the situation of detecting the braking state of a train formation. This method can be executed by a device for detecting the braking state of a freight train formation, and the device for detecting the braking state of a freight train formation can be implemented in the form of hardware and / or software.

[0047] See Figure 1 The method for detecting the braking state of a freight train formation shown in the figure includes:

[0048] S101. Obtain the vehicle information of at least one vehicle of the freight train formation from the comprehensive automation system of the marshalling station.

[0049] Among them, the vehicle information may refer to the relevant information of each vehicle in the freight train formation. Among them, the relevant information may include the vehicle number and the vehicle type. The vehicle number may refer to the identifier of each vehicle in the entire freight train formation, and the vehicle number is used to represent the serial number of the vehicle in the entire freight train formation. The vehicle type may refer to the specific model of the vehicle.

[0050] Among them, the hump may refer to a specially designed railway track configuration. The function of the hump is to use the natural slope of the track to help automatically divert the freight train formation to different tracks by gravity.

[0051] Specifically, before the freight train formation arrives at the starting section of the hump, the vehicle information of each vehicle in the freight train formation is obtained. Since there are multiple vehicles in a freight train formation and it is necessary to detect the braking state of each vehicle, it is necessary to obtain the vehicle numbers of each vehicle and sequentially traverse and detect the braking states of each vehicle in the train formation.

[0052] S102. In response to the hump automatic control system sending a propulsion signal to a freight train formation, for each vehicle, control an image acquisition device to capture the braking assist device of the vehicle to obtain an image to be detected; the braking assist device includes a piston and a brake chain.

[0053] Among them, the braking assist device may refer to a device that indirectly reflects the braking state of the train formation. The braking assist device may include a piston and a brake chain. It is relatively difficult to directly detect whether the brake shoe in the freight train formation is in contact with the wheel tread. Detecting the states of the piston and the brake chain can also indirectly reflect the braking state of the freight train formation.

[0054] Among them, the piston may refer to a mechanical device used in the train braking system. The piston converts the thrust under pneumatic or hydraulic action into mechanical energy, pushes the braking device to contact the wheel, brake drum, etc., and generates a braking effect. The function of the piston is to push the components of the braking system and control the application and release of the brake. The extended length of the piston is directly related to the working state of the braking system. When the piston extends, it means that the hydraulic or pneumatic device in the braking system has been activated and the brake starts to work. If the piston does not extend enough or does not extend, it indicates that the braking system has not been fully activated.

[0055] Among them, the brake chain may refer to an important component in the train braking system, mainly composed of a series of metal chains or steel cables. The tensioned state or relaxed state of the brake chain can indirectly reflect the working state of the braking system.

[0056] Among them, the image to be detected may refer to an image containing the braking assist device. The image to be detected provides a visual display of the actual working conditions of the piston and the brake chain in the train braking system. The image to be detected is the basic image for target detection of the braking assist device in the image to be detected. In a specific example, multiple high-definition cameras can be installed between the arrival yard and the push line to capture the braking assist devices of each vehicle from different angles and positions to obtain the image to be detected.

[0057] S103. Perform target detection on the image to be detected to obtain a target detection result.

[0058] Among them, object detection can refer to the operation of identifying the area of the auxiliary braking device in the image to be detected. By using machine learning algorithms or computer vision algorithms, the area of the auxiliary braking device in the image to be detected is identified, and the edge positions of the auxiliary braking device area are obtained. In a specific example, the image to be detected can be preprocessed to obtain the preprocessed image to be detected, and then an edge detection algorithm is used on the preprocessed image to be detected for object detection to extract the contour information and position information of the auxiliary braking device; among them, the preprocessing operations can include denoising operations, enhancement operations, grayscale operations, and binarization operations. Among them, median filtering technology and Gaussian filtering technology can be used for denoising operations, and contrast adjustment and sharpening technology can be used for enhancement operations to enhance the image quality.

[0059] Among them, the object detection result can refer to the specific numerical results of the extending length of the piston rod and the curvature of the brake chain. The object detection result is used to compare with the abnormal state threshold. In a specific example, the object detection result can be that the extending length of the piston rod is X and the curvature of the brake chain is Y.

[0060] S104. Determine the braking state of the vehicle according to the object detection result and the abnormal state threshold.

[0061] Among them, the abnormal state threshold can refer to the thresholds of the extending length of the piston rod and the curvature of the brake chain when the current train is in abnormal braking.

[0062] Among them, the braking state can refer to the state where the braking working state of the vehicle is normal or abnormal. Among them, when the vehicle is in braking, it means that the braking state of the vehicle is abnormal, and when the vehicle is in hump yard rolling, it means that the braking state of the vehicle is normal.

[0063] S105. In response to the braking state of the vehicle being an abnormal state, send the braking state of the vehicle to the shunting locomotive automation system so that the shunting locomotive automation system can perform stop control on the freight train formation.

[0064] Among them, the stop control can refer to the control operation of stopping or advancing the shunting locomotive of the freight train formation. During the hump yard rolling process of the freight train formation, it is necessary for the shunting locomotive to push the vehicle to control the train formation to push the hump. According to the different braking states of the vehicle, the shunting locomotive of the freight train formation can be controlled to perform stop control on the entire freight train formation.

[0065] S106. The train re-inspection system receives the end signal sent by the hump yard automation control system.

[0066] It can be seen that in the embodiments of the present application, by obtaining vehicle information when a freight train arrives at the starting section of a hump, the acquisition of the status information of the freight train can be realized, providing basic data for subsequent detection and control; by photographing the braking assist device for each vehicle, local inspection of the assist braking device can be realized to ensure that the assist braking device of each vehicle is effectively detected; by performing object detection on the image to be detected, the status of the braking device can be automatically identified, reducing the need for manual inspection and improving the efficiency and accuracy of detection; by combining the object detection result with the abnormal state threshold, the automatic judgment of the braking state of each vehicle can be realized, which helps to improve the accuracy of status evaluation and avoid human errors; by controlling the stop of the freight train according to the braking state of the vehicle, automatic safety control can be realized, reducing the accident risk caused by abnormal braking; and thus, the automation level and accuracy of the braking state detection of the freight train can be improved.

[0067] In an alternative embodiment, Figure 2 is the flow of a method for detecting the braking state of a freight train provided by an embodiment of the present invention Figure 2 , the refinement of "the image to be detected includes a piston rod image and a brake chain image; object detection is performed on the image to be detected to obtain an object detection result" into "object detection is performed on the piston rod image to obtain a piston rod area; the piston rod extension length is detected in the piston rod area; object detection is performed on the brake chain image to obtain a brake chain area; the brake chain curvature is detected in the brake chain area; the piston rod extension length and the brake chain curvature are determined as the object detection result" to improve the operation of detecting the braking state of the freight train.

[0068] It should be noted that for the parts not detailed in the embodiments of the present invention, reference can be made to the descriptions of other embodiments.

[0069] See Figure 2 The method for detecting the braking state of a freight train shown, includes:

[0070] S201. In response to the arrival of a freight train at the starting section of a hump, obtain the vehicle information of at least one vehicle of the freight train.

[0071] S202. For each vehicle, according to the vehicle information of the vehicle, photograph the braking assist device of the vehicle to obtain an image to be detected; the braking assist device includes a piston rod and a brake chain.

[0072] S203. Perform object detection on the piston rod image to obtain a piston rod area.

[0073] Among them, the piston image can refer to an image of a piston device captured by a high-definition camera. The piston device is part of the train braking system and is usually related to the brake piston and pneumatic system of the train. The piston image includes the piston, the piston, the compression cylinder, and the components in contact with the brake shoe. By performing object detection on the piston image, the braking state of the vehicle can be determined based on whether the piston in the piston area extends. That is, by judging whether the extension length of the piston is greater than zero to determine the state of the braking device of the vehicle, and then infer whether the vehicle is in a braking state.

[0074] Among them, the piston area can refer to the area in the piston image that only includes the piston device. The piston area is used to clarify the area that needs to be focused on in the piston image.

[0075] S204. Detect the extension length of the piston in the piston area.

[0076] Among them, the piston extension length can refer to the specific length that the piston in the piston device extends out of the cylinder. The piston extension length is one of the important parameters for measuring the braking state of the vehicle. The specific extension length of the piston is usually related to whether the braking system of the vehicle is in an activated state. The longer the extension length of the piston, the higher the degree of activation of the braking system of the vehicle.

[0077] S205. Perform object detection on the brake chain image to obtain the brake chain area.

[0078] Among them, the brake chain image can refer to an image of a brake chain device captured by a high-definition camera. The brake chain device is part of the train braking system and is usually related to the operation, force transmission, and braking effect of the braking system. The brake chain image is used to show the morphological characteristics of the brake chain device in the vehicle braking state and can judge whether the brake chain is in a tightened state.

[0079] Among them, the brake chain area can refer to the area in the brake chain image that only includes the brake chain device. The brake chain area is used to clarify the area that needs to be focused on in the brake chain image.

[0080] S206. Detect the curvature of the brake chain in the brake chain area.

[0081] Among them, the brake chain curvature can refer to the degree of bending of the brake chain in the brake chain area. The brake chain curvature can be measured by the shape of the brake chain area in the brake chain image. The size of the brake chain curvature is used to reflect whether the brake chain device is bent or relaxed during actual braking. The closer the curvature is to zero, the higher the degree of the brake chain being in a tightened state.

[0082] S207. Determine the piston extension length and the brake chain curvature as the object detection results.

[0083] S208. Determine the braking state of the vehicle based on the object detection results and the abnormal state threshold.

[0084] S209. In response to the braking state of the vehicle being an abnormal state, send the braking state of the vehicle to the shunting automation system so that the shunting automation system controls the freight train to stop.

[0085] S210. The train re-inspection system receives the end signal sent by the hump automation control system.

[0086] It can be seen that in this embodiment, by performing object detection on the piston image, the piston area can be accurately located, thereby providing an effective area for subsequent measurement of the extended length of the brake chain and piston; by detecting the extended length of the piston in the piston area, the working state of the braking auxiliary device can be accurately obtained, helping to determine whether the current vehicle is in the braking state, thereby improving the accuracy of braking detection; by performing object detection on the brake chain image, the brake chain area can be accurately located, avoiding misidentification of other parts and improving the accuracy of image analysis. By detecting the curvature of the brake chain in the brake chain area, precise data can be provided for analyzing the tension state of the brake chain, helping to determine whether the current vehicle is in the braking state; by using the extended length of the piston and the curvature of the brake chain as the object detection results, specific numerical and status indicators can be provided to ensure accurate evaluation of the braking state.

[0087] In some embodiments, determining the braking state of the vehicle according to the object detection result and the abnormal state threshold includes:

[0088] Compare the extended length of the piston with the abnormal state threshold to determine the piston abnormal detection result;

[0089] Compare the curvature of the brake chain with the abnormal state threshold to determine the brake chain abnormal detection result;

[0090] Determine the braking state of the vehicle according to the piston abnormal detection result and the brake chain abnormal detection result.

[0091] Among them, the piston abnormal detection result may refer to the judgment result of the braking state of the vehicle obtained by comparing the extended length of the piston detected with the preset abnormal state threshold. The judgment result includes normal and abnormal. Among them, abnormal may refer to the working state of the braking system of the current vehicle, and normal may refer to the non-working state of the braking system of the current vehicle. In a specific example, assume that the extended length of the piston is x. If the extended length of the piston for the abnormal state threshold is y (x < y), then by comparing the extended length of the piston with the abnormal state threshold, the piston abnormal detection result is normal.

[0092] Among them, the brake chain anomaly detection result may refer to the judgment result of the braking state of the vehicle obtained by comparing the brake chain curvature with a preset anomaly state threshold. The judgment results include normal and abnormal. In a specific example, assume the brake chain curvature is x. If the brake chain curvature of the anomaly state threshold is y (x > y), then by comparing the brake chain curvature with the anomaly state threshold, the brake chain anomaly detection result is normal.

[0093] Specifically, when the extending length of the piston rod is less than the anomaly state threshold, it is determined that the piston rod anomaly detection result is abnormal and the braking state of the vehicle is braking; when the extending length of the piston rod is greater than or equal to the anomaly state threshold, it is determined that the piston rod anomaly detection result is normal and the braking state of the vehicle is normal. When the brake chain curvature is greater than the anomaly state threshold, it is determined that the brake chain anomaly detection result is normal and the braking state of the vehicle is normal; when the brake chain curvature is less than or equal to the anomaly state threshold corresponding to the vehicle state information, it is determined that the brake chain anomaly detection result is abnormal and the braking state of the vehicle is braking.

[0094] Specifically, when at least one of the piston rod anomaly detection result and the brake chain anomaly detection result is abnormal, it is determined that the braking state of the vehicle is braking; when both the piston rod anomaly detection result and the brake chain anomaly detection result are normal, it is determined that the braking state of the vehicle is normal.

[0095] It can be seen that in this embodiment, by comparing the extending length of the piston rod with the threshold set in the vehicle information, the braking state of the vehicle can be judged accurately in real time; by comparing the brake chain curvature with the anomaly state threshold, the braking state of the vehicle can be judged accurately in real time; by combining the anomaly detection results of the piston rod and the brake chain, the braking state of the vehicle can be comprehensively evaluated to ensure that necessary measures are taken in time when potential problems are found, thus ensuring the safe operation of the train set.

[0096] In some embodiments,

[0097] In response to the braking state of the vehicle being an abnormal state, send the braking state of the vehicle to the shunting automation system so that the shunting automation system controls the stopping of the freight train set, including:

[0098] In response to the braking state of the vehicle being an abnormal state, send the braking state of the vehicle to the shunting automation system, and the shunting automation system controls the stopping of the shunting of the freight train set; among them, the freight train set is pushed by the shunting locomotive to make each vehicle run.

[0099] Specifically, according to the braking states of the vehicles in the freight train set, when the braking state is an abnormal state, the shunting of the freight train set is controlled to stop accordingly. In the scenario of the freight train set pushing the hump, the shunting locomotive realizes the running of each vehicle by pushing.

[0100] It can be seen that in this embodiment, by monitoring the braking state of each vehicle in real time, precise stop control can be performed on the freight train according to the abnormal braking state, thereby improving the safety and efficiency of train stopping; by controlling the behavior of the shunting locomotive according to the braking state of each vehicle, effective pushing or stop control of the freight train can be achieved, thereby ensuring smoother and safer train running under different braking states.

[0101] In some embodiments, for each vehicle, an image acquisition device takes pictures of the braking assist device of the vehicle to obtain a to-be-detected image, including:

[0102] Controlling a plurality of image acquisition devices located at the arrival yard and the pushing line to acquire a plurality of initial images;

[0103] According to the vehicle information of each vehicle, the to-be-detected image corresponding to each vehicle is screened out from the initial images.

[0104] Among them, the initial image may refer to an image collected in real time by a camera device when the freight train reaches the starting section of the hump. The initial image includes the appearance information of each vehicle and its auxiliary braking device in the freight train.

[0105] Specifically, the initial images are captured by a plurality of camera devices at different positions. The entire scene of the freight train may be included in all the initial images, and the initial images may contain multiple vehicles and other background information. By screening out the to-be-detected image corresponding to each vehicle, irrelevant background information can be effectively removed, so as to only focus on the area related to the braking assist device corresponding to each vehicle, which helps to improve the accuracy of subsequent target detection.

[0106] It can be seen that in this embodiment, by simultaneously acquiring initial images by multiple cameras at different locations, the image information of the vehicle can be comprehensively collected from different angles and positions to ensure that no key details are missed; by screening out the to-be-detected image corresponding to each vehicle, unnecessary background information can be reduced, and the accuracy of subsequent target detection can be improved.

[0107] In some embodiments, screening out the to-be-detected image corresponding to each vehicle from the initial images according to the vehicle information of each vehicle includes:

[0108] Determining the vehicle number of each vehicle according to the vehicle information of each vehicle;

[0109] According to the vehicle numbers of each vehicle, the relevant detection images corresponding to each vehicle are screened out from the initial images;

[0110] According to the shooting integrity of the braking assist device in the relevant detection images corresponding to each vehicle, the to-be-detected image corresponding to each vehicle is screened out from the relevant detection images corresponding to each vehicle.

[0111] Among them, the relevant detection images can refer to all initial images including a certain vehicle. For example, if an initial image includes an incomplete image of a certain vehicle and another initial image includes a complete image of the vehicle, these initial images can be used as relevant detection images.

[0112] Among them, the shooting integrity can refer to the degree of completeness of the shooting of the braking assistance device in the relevant detection image.

[0113] It can be seen that in this embodiment, by determining the vehicle through the vehicle number, the unique identification of each vehicle can be achieved, ensuring no confusion during subsequent processing and analysis. Screening relevant images by the vehicle number helps to accurately locate the position of each vehicle in the initial image, ensuring that the collected images are consistent with the detection target, thereby reducing the interference of irrelevant information. By screening images according to the shooting integrity of the braking assistance device, it can be ensured that the selected images to be detected have sufficient clarity and integrity, thereby improving the reliability and accuracy of the detection results.

[0114] In some embodiments, the vehicle braking states of each vehicle include: abnormal state and normal state; among them, the vehicle braking state of at least one vehicle being in an abnormal state is used for the commissioning automation system to stop the control of the commissioning.

[0115] Optionally, when the braking states of each vehicle are all normal, it can be determined that the detection result of the braking state of this train is normal, and the commissioning continues to be executed normally.

[0116] It can be seen that in this embodiment, by monitoring that the braking state of at least one vehicle is braking, the requirement for the freight train to be in a stopped state as a whole can be judged, so as to stop the control of the commissioning; by detecting that the braking states of all vehicles are normal, it can be determined that the detection result of the braking state of this train is normal.

[0117] In an alternative embodiment, Figure 3Schematic structural diagram of a system for a method of detecting the braking state of a freight train formation provided by an embodiment of the present invention. The system includes an image acquisition device, an image processing module, a state detection and warning module, an interface module, and a system platform. Among them, the image acquisition device includes multiple high-definition cameras installed between the arrival yard and the pushing line, which are used to collect images of the pistons and brake chains of railway freight cars from different angles and positions. The cameras are connected to the image processing module through a network interface for real-time transmission of image data. The image processing module preprocesses and performs target detection on the collected images to generate target detection results, and the image processing module transfers the processed images and preliminary results to the state detection and warning module. The state detection and warning module compares the preliminary detection results of the image processing module with the thresholds set by the system to further determine the states of the pistons and brake chains. When an abnormality is found, a warning message is generated and uploaded to the system platform to remind the operator to handle it. The state abnormality detection module transfers the final analysis results and warning messages to the system platform. The interface module communicates with the integrated automation system of the marshalling station, the automated hump control system, and the automated shunting locomotive control system interface to realize intelligent re-inspection operations. The interface module is connected to external systems through a network interface to transfer external information to the system platform. The system platform displays the detection results and warning messages in real time for the operator to view in real time and records the detection data. The system platform is connected to the state detection and warning module to receive and display the detection results.

[0118] In an alternative embodiment, Figure 4 Flowchart of a method for detecting the braking state of a freight train formation provided by an embodiment of the present invention. The specific process is as follows:

[0119] The integrated automation system of the marshalling station is used for planning operation information. The operation information includes information such as the train number of the pushing locomotive and the vehicle type. Assuming the number of pushing trains is N, the automated hump control system sends a propulsion signal, and the shunting locomotive propels each vehicle to the hump. The image acquisition device starts to collect images and obtains the images to be detected corresponding to each vehicle, and detects whether there are abnormalities in the states of the pistons and brake chains of each vehicle. When an abnormality occurs, a stop instruction is sent to the automated shunting locomotive control system, and the relevant operators handle the abnormality. After the abnormality is handled, a propulsion instruction is sent through the shunting handheld device until all N vehicles are traversed. The automated hump control system sends an end signal, and the detection device is turned off, and the process ends.

[0120] Figure 5 Schematic structural diagram of a device for detecting the braking state of a freight train formation provided by an embodiment of the present invention. The embodiment of the present invention is applicable to the situation of detecting the braking state of a train formation. The device can execute the method for detecting the braking state of a freight train formation, and the device can be implemented in the form of hardware and / or software.

[0121] See Figure 5The freight train braking state detection device shown in the figure includes: a vehicle information acquisition module 501, an image acquisition module 502, a target detection module 503, a braking state determination module 504, a stop control module 505, and an end signal reception module 506. Among them,

[0122] The vehicle information acquisition module 501 is used to obtain the vehicle information of at least one vehicle of the freight train from the comprehensive automation system of the marshalling station;

[0123] The image acquisition module 502 is used to, in response to the hump automation control system sending a propulsion signal to the freight train, for each vehicle, control the image acquisition device to take a picture of the braking auxiliary device of the vehicle to obtain an image to be detected; the braking auxiliary device includes a piston and a brake chain;

[0124] The target detection module 503 is used to perform target detection on the image to be detected to obtain a target detection result;

[0125] The braking state determination module 504 is used to determine the braking state of the vehicle according to the target detection result and the abnormal state threshold;

[0126] The stop control module 505 is used to, in response to the braking state of the vehicle being an abnormal state, send the braking state of the vehicle to the shunting locomotive automation system so that the shunting locomotive automation system performs stop control on the freight train;

[0127] The end signal reception module 506 is used for the train re-inspection system to receive the end signal sent by the hump automation control system.

[0128] The technical solution of the embodiment of the present invention can realize the acquisition of the state information of the freight train by obtaining vehicle information when the freight train arrives at the starting section of the hump, providing basic data for subsequent detection and control; by taking pictures of the braking auxiliary device for each vehicle, it can realize the local inspection of the auxiliary braking device to ensure that the auxiliary braking device of each vehicle is effectively detected; by performing target detection on the image to be detected, it can realize the automatic identification of the state of the braking device, reduce the need for manual inspection, and improve the efficiency and accuracy of detection; by combining the target detection result with the abnormal state threshold, it can realize the automatic judgment of the braking state of each vehicle, help improve the accuracy of state evaluation, and avoid human errors; by controlling the stop of the freight train according to the braking state of the vehicle, it can realize automatic safety control and reduce the accident risk caused by abnormal braking; thus, it can improve the automation level and accuracy of the freight train braking state detection.

[0129] In some embodiments, in terms of performing target detection on the image to be detected to obtain a target detection result, the target detection module 503 is specifically used for:

[0130] Perform object detection on the piston image to obtain the piston area;

[0131] Detect the piston extension length in the piston area;

[0132] Perform object detection on the brake chain image to obtain the brake chain area;

[0133] Detect the brake chain curvature in the brake chain area;

[0134] Determine the piston extension length and the brake chain curvature as the object detection results.

[0135] In some embodiments, in determining the braking state of the vehicle according to the object detection results and the abnormal state threshold, the object detection module 503 is specifically configured to:

[0136] Compare the piston extension length with the abnormal state threshold to determine the piston abnormal detection result;

[0137] Compare the brake chain curvature with the abnormal state threshold to determine the brake chain abnormal detection result;

[0138] Determine the braking state of the vehicle according to the piston abnormal detection result and the brake chain abnormal detection result.

[0139] In some embodiments, in response to the braking state of the vehicle being an abnormal state, and sending the braking state of the vehicle to the shunting automation system so that the shunting automation system performs stop control on the freight train formation, the stop control module 505 is specifically configured to:

[0140] In response to the braking state of the vehicle being an abnormal state, send the braking state of the vehicle to the shunting automation system, and the shunting automation system performs stop control on the shunting of the freight train formation; wherein, the freight train formation is pushed by the shunting locomotive to drive each vehicle.

[0141] In some embodiments, for each vehicle, in terms of the image acquisition device photographing the braking assist device of the vehicle to obtain the image to be detected, the image acquisition module 502 is specifically configured to:

[0142] Control multiple image acquisition devices located at the arrival yard and the pushing line to acquire multiple initial images;

[0143] According to the vehicle information of each vehicle, screen out the image to be detected corresponding to each vehicle from each initial image.

[0144] In some embodiments, in terms of screening out the image to be detected corresponding to each vehicle from each initial image according to the vehicle information of each vehicle, the image acquisition module 502 is specifically configured to:

[0145] Determine the vehicle number of each vehicle according to the vehicle information of each vehicle;

[0146] According to the vehicle numbers of each vehicle, relevant detection images corresponding to each vehicle are screened out from each initial image;

[0147] According to the shooting integrity of the braking assist device in the relevant detection images corresponding to each vehicle, the images to be detected corresponding to each vehicle are screened out from the relevant detection images corresponding to each vehicle.

[0148] In some embodiments, the vehicle braking states of each vehicle include: abnormal state and normal state; among them, the vehicle braking state of at least one vehicle is an abnormal state for the machine adjustment automation system to perform stop control on the machine adjustment.

[0149] The freight car train braking state detection device provided by the embodiments of the present invention can execute the freight car train braking state detection method provided by any embodiment of the present invention, and has corresponding functional modules and beneficial effects for executing the freight car train braking state detection method.

[0150] Figure 6 It is a schematic structural diagram of a freight car train braking state detection system provided by an embodiment of the present invention.

[0151] As Figure 6 shown, the freight car train braking state detection system 600 includes at least one processor 601 and a memory communicatively connected to the at least one processor 601, such as a read-only memory (ROM) 602, a random access memory (RAM) 603, etc. Among them, the memory stores a computer program executable by the at least one processor. The processor 601 can execute various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 602 or the computer program loaded from the storage unit 608 into the random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the freight car train braking state detection system 600 can also be stored. The processor 601, the ROM 602, and the RAM 603 are connected to each other through a bus 604. The input / output (I / O) interface 608 is also connected to the bus 604.

[0152] Multiple components in the freight car train braking state detection system 600 are connected to the I / O interface 605, including: an input unit 606, such as a keyboard, a mouse, etc.; an output unit 607, such as various types of displays, speakers, etc.; a storage unit 608, such as a disk, an optical disc, etc.; and a communication unit 609, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 609 allows the freight car train braking state detection system 600 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0153] The processor 601 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the processor 601 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The processor 601 executes the various methods and processes described above, such as the freight train braking state detection method.

[0154] In some embodiments, the freight train braking state detection method can be implemented as a computer program tangibly embodied in a computer-readable storage medium, such as the storage unit 608. In some embodiments, part or all of the computer program can be loaded and / or installed onto the freight train braking state detection system 600 via the ROM 602 and / or the communication unit 609. When the computer program is loaded into the RAM 603 and executed by the processor 601, one or more steps of the freight train braking state detection method described above can be executed. Alternatively, in other embodiments, the processor 601 can be configured to execute the freight train braking state detection method by any other suitable means (e.g., by means of firmware).

[0155] Various embodiments of the systems and techniques described above can be implemented in digital electronic circuitry, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: 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 the data and instructions to the storage system, the at least one input device, and the at least one output device.

[0156] The computer program for implementing the method of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to the processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when the computer program is executed by the processor, the functions / operations specified in the flowchart and / or block diagram are implemented. The computer program can be executed entirely on the machine, partially on the machine, as a stand-alone software package partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0157] In the context of the present invention, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer-readable storage medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, the computer-readable storage medium can be a machine-readable signal medium. More specific examples of the machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0158] To provide interaction with a user, the systems and techniques described herein can be implemented on an operation detection device that includes: 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 a trackball) through which the user can provide input to the freight train braking state detection system. Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0159] The systems and techniques described herein can 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 having a graphical user interface or a web browser through which the user can interact with an implementation 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 can 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.

[0160] A computing system may include a client and a server. The client and the server are generally far from each other and usually interact via a communication network. The client-server relationship is created by computer programs running on respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system, solving the defects of difficult management and weak business scalability existing in traditional physical hosts and VPS (Virtual Private Server) services.

[0161] It should be understood that various forms of the processes shown above can be used, with steps reordered, added, or deleted. For example, the steps recited in the present invention can be executed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved, and no limitation is made herein.

[0162] The above specific embodiments do not constitute a limitation to the protection scope of the present invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A method for detecting the braking state of a freight train formation, characterized in that, Applied to the train re-inspection system, the method includes: Obtain the vehicle information of at least one vehicle of the freight train from the marshalling station integrated automation system; In response to the hump automation control system sending a propulsion signal to the freight train, for each vehicle, control the image acquisition device to take a picture of the braking assist device of the vehicle to obtain a to-be-detected image; the braking assist device includes a piston and a brake chain; Perform object detection on the to-be-detected image to obtain an object detection result; Determine the braking state of the vehicle according to the object detection result and the abnormal state threshold; In response to the braking state of the vehicle being an abnormal state, send the braking state of the vehicle to the shunting locomotive automation system so that the shunting locomotive automation system controls the freight train to stop; The train re-inspection system receives an end signal sent by the hump automation control system.

2. The method according to claim 1, wherein The to-be-detected image includes a piston image and a brake chain image; The performing object detection on the to-be-detected image to obtain an object detection result includes: Perform object detection on the piston image to obtain a piston area; Detect the piston extension length in the piston area; Perform object detection on the brake chain image to obtain a brake chain area; Detect the brake chain curvature in the brake chain area; Determine the piston extension length and the brake chain curvature as the object detection result.

3. The method according to claim 2, wherein The determining the braking state of the vehicle according to the object detection result and the abnormal state threshold includes: Compare the piston extension length with the abnormal state threshold to determine a piston abnormality detection result; Compare the brake chain curvature with the abnormal state threshold to determine a brake chain abnormality detection result; Determine the braking state of the vehicle according to the piston abnormality detection result and the brake chain abnormality detection result.

4. The method according to claim 1, wherein The responding to the braking state of the vehicle being an abnormal state and sending the braking state of the vehicle to the shunting locomotive automation system so that the shunting locomotive automation system controls the freight train to stop includes: In response to the braking state of the vehicle being an abnormal state, send the braking state of the vehicle to the shunting locomotive automation system, and the shunting locomotive automation system controls the shunting locomotive of the freight train to stop; wherein, the freight train is pushed by the shunting locomotive to drive each vehicle.

5. The method according to claim 1, characterized in that The for each vehicle, the image acquisition device takes a picture of the braking assist device of the vehicle to obtain a to-be-detected image includes: Control multiple image acquisition devices located at the arrival yard and the pushing line to collect multiple initial images; According to the vehicle information of each vehicle, screen out the to-be-detected image corresponding to each vehicle from each initial image.

6. The method according to claim 5, characterized in that, The screening out the to-be-detected image corresponding to each vehicle from each initial image according to the vehicle information of each vehicle includes: Determine the vehicle number of each vehicle according to the vehicle information of each vehicle; According to the vehicle number of each vehicle, screen out the relevant detection image corresponding to each vehicle from each initial image; According to the shooting integrity of the braking assist device in the relevant detection images corresponding to each vehicle, the to-be-detected images corresponding to each vehicle are screened out from the relevant detection images corresponding to each vehicle.

7. The method according to claim 1, wherein The vehicle braking states of each vehicle include: abnormal state and normal state; among them, the vehicle braking state of at least one vehicle being in an abnormal state is used for the shunting automation system to control the shunting to stop.

8. A braking state detection device for a freight train formation, characterized in that Including: A vehicle information acquisition module, configured to acquire vehicle information of at least one vehicle of the freight train from the comprehensive automation system of the marshalling station; An image acquisition module, configured to, in response to the hump automation control system sending a propulsion signal to the freight train, for each vehicle, control an image acquisition device to photograph the braking assist device of the vehicle to obtain to-be-detected images; the braking assist device includes a piston and a brake chain; A target detection module, configured to perform target detection on the to-be-detected images to obtain a target detection result; A braking state determination module, configured to determine the braking state of the vehicle according to the target detection result and the abnormal state threshold; A stop control module, configured to, in response to the braking state of the vehicle being in an abnormal state, send the braking state of the vehicle to the shunting automation system, so that the shunting automation system controls the freight train to stop; An end signal receiving module, configured to receive the end signal sent by the hump automation control system by the train re-inspection system.

9. A braking state detection system for a freight train formation, characterized in that, The freight train braking state detection system includes: 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 freight train braking state detection method according to any one of claims 1-7.

10. A freight train control system, characterized in that, Including: The freight train braking state detection system, the comprehensive automation system of the marshalling station, the hump automation control system and the shunting automation system as claimed in claim 9; The comprehensive automation system of the marshalling station is configured to acquire vehicle information of at least one vehicle of the freight train and send the vehicle information of at least one vehicle of the freight train to the freight train braking state detection system; The hump automation control system is configured to send a propulsion signal to the freight train; The freight train braking state detection system is configured to, in response to the hump automation control system sending a propulsion signal to the freight train, for each vehicle, control an image acquisition device to photograph the braking assist device of the vehicle to obtain to-be-detected images; the braking assist device includes a piston and a brake chain; The freight train braking state detection system is configured to perform target detection on the to-be-detected images to obtain a target detection result; The freight train braking state detection system is configured to determine the braking state of the vehicle according to the target detection result and the abnormal state threshold; The freight train braking state detection system is configured to send the braking state of the vehicle to the hump automation control system and the shunting automation system; The locomotive adjustment automation is used to perform stop control on the freight train formation; The hump automation control system is used to send an end signal to the train re-inspection system.

Images