Railway track fastening status detection and tightening apparatus

Abstract

The application provides a railway track fastener state detection and fastening equipment. It comprises a working vehicle, a power system, a fastener cleaning device, a bolt fastening device, a telescopic pressing strip device, a sensor system, a data acquisition and processing device, a control system, a data storage device and the like. The fastener cleaning device is used for cleaning the fastener bolt and the elastic strip. The data acquisition and processing device obtains the fastener state information through machine vision, uses a convolutional neural network model to train and predict the friction coefficient of the friction wheel in the bolt fastening device and the fastener bolt, and obtains the relative position relationship with the fastener. The telescopic pressing strip device reduces the torque required by the fastening bolt by telescoping the elastic strip, and the bolt fastening device controls the fastening torque of the bolt by adjusting the distance between the friction wheel and the rolling wheel. Thus, the detection of the railway track fastener state and the automatic fastening of the fastener are realized. The application greatly reduces the manual labor and on-site operation process required for the detection of the fastener state and the fastening of the fastener.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of railway track fastener detection, fastener tightening and the like, and particularly relates to a railway track fastener state detection and tightening device. BACKGROUND

[0002] In railway transportation operation, the fastener system is an important component of railway rails, which plays a role in maintaining and adjusting the track gauge and track direction, providing longitudinal resistance and preventing rail climbing. Therefore, the fastener system is crucial to railway operation safety. However, with the increase of train speed and density, the phenomenon of bolt loosening in the fastener system is more and more common, especially in heavy haul railways, because of the greater vibration impact of trains, the problem of bolt loosening occurs frequently. If the problems of bolt loosening and overtightening cannot be solved in time, it will cause the failure of the fasteners in the adjacent area, change the geometric parameters of the track, and thus reduce the smoothness of the track and endanger the safety of train operation. In the current railway maintenance and repair operation, the railway fastener tightening is mainly operated by manually pushing the special tightening wrench, which has low automation, slow speed and low efficiency. Therefore, it is necessary to provide a high-efficiency railway track fastener state detection and tightening device. SUMMARY

[0003] Embodiments of the present application provide a railway track fastener state detection and tightening device to solve the problems in the prior art.

[0004] In order to achieve the above-mentioned purpose, the present application adopts the following technical solutions.

[0005] A railway track fastener state detection and tightening device, comprising a work vehicle, and a fastener cleaning device, a bolt tightening device, a telescopic pressing strip device, a sensor system, a data acquisition and processing device, a control system and a data storage device arranged on the work vehicle;

[0006] The fastener cleaning device has a rotatable cleaning disc, which is located on the bottom surface of the work vehicle; the bolt tightening device has a friction wheel and a rolling wheel, which are arranged in pairs at intervals and located on the bottom surface of the work vehicle; the friction wheel is used to drive the bolt of the fastener, and the interval between the friction wheel and the rolling wheel is adjustable;

[0007] The telescopic pressing strip device is located on the bottom surface of the work vehicle and has a telescopic pressing strip, which is used to press the elastic strip of the fastener;

[0008] The data acquisition and processing device has an image acquisition module and a processor; the image acquisition module is used to obtain the apparent information of the fastener; the processor is used to obtain the state of the fastener, the friction coefficient between the bolt of the fastener and the friction wheel, and the relative position between the fastener and the work vehicle through calculation according to the apparent information;

[0009] The sensor system is used to monitor the vibration information of the fastener cleaning device, the bolt fastening device and the telescopic compression strip device, and the temperature information of the data acquisition and processing device, the control system and the data storage device;

[0010] The control system is circuit-connected with the fastener cleaning device, the bolt fastening device, the telescopic compression strip device, the sensor system, the data acquisition and processing device, the control system and the data storage device respectively. The control system is used to: judge whether the railway track fastener state detection and fastening equipment fails according to the vibration information of the fastener cleaning device, the bolt fastening device and the telescopic compression strip device, and the temperature information of the data acquisition and processing device, the control system and the data storage device; and adjust the interval distance between the friction wheel and the rolling wheel according to the friction coefficient of the bolt and the friction wheel obtained by the data acquisition and processing device.

[0011] Preferably, the fastener cleaning device has a fastener cleaning engine, and the fastener cleaning engine is drivingly connected with the cleaning disc.

[0012] Preferably, the bolt fastening device comprises:

[0013] A bolt fastening engine is installed on the working vehicle;

[0014] A driving shaft is detachably connected with the output end of the bolt fastening engine, and the bolt fastening engine is drivingly connected with the friction wheel through the driving shaft;

[0015] An axle system structure comprises a positioning rod, the positioning rod is detachably installed at the bottom of the working vehicle, one end of the positioning rod has a rolling bearing, and the rolling wheel is movably installed at one end of the positioning rod through the rolling bearing;

[0016] A transmission rod-sleeve structure has a pair of sleeve rings connected with each other through a tensioner, the sleeve rings are in contact with the driving shaft and the positioning rod respectively; the tensioner is circuit-connected with the control system, and the interval distance between the friction wheel and the rolling wheel can be adjusted by changing the length of the tensioner.

[0017] Preferably, the bolt fastening device further comprises a friction wheel cleaning device which is detachably installed on the outer side of the friction wheel.

[0018] Preferably, the telescopic compression strip device comprises:

[0019] A pair of first rail clamps are detachably installed on the working vehicle body, and the first rail clamps are used to clamp the rail;

[0020] A telescopic compression strip is detachably connected with the first rail clamp; the first rail clamp has a window, and the telescopic compression strip is located in the area of the window;

[0021] A plurality of rollers are installed on the inner side of the first rail clamp, and the rollers are in contact with the surface of the rail when the first rail clamp clamps the rail;

[0022] The pressing driving motor is installed on the first rail gripper of the working vehicle body; the output end of the pressing driving motor has an eccentric wheel, the position of the eccentric wheel corresponds to the telescopic pressing strip, and the pressing driving motor can drive the eccentric wheel to push the telescopic pressing strip out of the window and press the elastic strip of the fastener;

[0023] A pair of reset springs are connected at both ends of the telescopic pressing strip.

[0024] Preferably, the data acquisition and processing device calculates the relative position between the fastener and the working vehicle through the SURF algorithm, and calculates the state of the fastener and the friction coefficient of the bolt and the friction wheel of the fastener through the convolutional neural network algorithm.

[0025] Preferably, the process of calculating the friction coefficient of the bolt and the friction wheel of the fastener according to the apparent information by the processor includes:

[0026] S1, pre-processing the first image, including normalization, color space conversion, noise removal and first image enhancement; the first image is an image of the mutual contact between the bolt and the friction wheel of the fastener;

[0027] S2, constructing a convolutional network model; the convolutional network model includes an input layer, a convolutional layer, a pooling layer, a full connection layer and an output layer arranged in sequence along the data flow direction; the input layer is used to set the property parameters of the bolt surface features of the pre-processed first image as the size of the input layer; the convolutional layer is multiple, used to extract the local features of the bolt surface in the pre-processed first image; the pooling layer is used to reduce the size of the extracted local features of the bolt surface; the full connection layer is used to map the local features of the bolt surface to the friction coefficient prediction value; the output layer is used to output the predicted friction coefficient value;

[0028] S3, using the ReLU activation function to increase the nonlinear expression ability of the convolutional network model;

[0029] S4, measuring the difference between the predicted value and the actual value of the convolutional network model through the mean absolute error loss function, and updating the parameters of the convolutional network model through the SGD optimizer;

[0030] S5, using the data set to train, test and optimize the convolutional network model;

[0031] S6, using the optimized convolutional network model to predict the friction coefficient of the bolt and the friction wheel of the fastener, so that the control system can adjust the interval distance between the friction wheel and the rolling wheel based on the obtained friction coefficient.

[0032] Preferably, the process of calculating the relative position between the fastener and the working vehicle through the SURF algorithm includes:

[0033] E1 uses the Hessian matrix to detect the key points in the second image, and obtains the positions of the potential key points in the second image by performing extreme value detection on the determinant of the Hessian matrix; the second image is an image of the fastener used to calculate the relative position between the fastener and the service vehicle;

[0034] E2 excludes unstable or mismatched feature points by calculating the distance and angle difference between the feature points in the second image;

[0035] E3 obtains a descriptor by calculation based on the feature points in the second image after step E2 is performed;

[0036] E3 normalizes the descriptor;

[0037] E4 obtains the Euclidean distance of the descriptor by calculation based on the normalized descriptor;

[0038] E5 screens the feature points matched with the random sample consensus algorithm based on the proportion of the calculated Euclidean distance;

[0039] E6 estimates the homography matrix by the random sample consensus algorithm based on the screened feature points;

[0040] E7 calibrates the parameters using the image acquisition module;

[0041] E8 obtains the three-dimensional coordinates of the same feature points in the second images of two adjacent frames by calculation based on the calibrated parameters combined with the corresponding geometric correspondence, and calculates the relative position between the fastener and the service vehicle by comparing the differences in the three-dimensional coordinates of the feature points.

[0042] Preferably, the sensor system includes a temperature sensor, a vibration sensor, and a displacement sensor; the temperature sensor is used to obtain the temperature information of the data acquisition and processing device, the control system, and the data storage device in real time; the vibration sensor is used to obtain the vibration information of the fastener cleaning device, the bolt fastening device, and the telescopic compression strip device in real time; the displacement sensor is used to obtain the position information and the travel distance information of the service vehicle, and the working stroke information of the fastener cleaning device, the bolt fastening device, and the telescopic compression strip device.

[0043] Preferably, it further includes a driving device and a power device installed on the service vehicle, and a walking wheel; the walking wheel is located on the bottom surface of the service vehicle and cooperates with the track; the driving device is drivingly connected with the walking wheel, and is used to drive the service vehicle to move on the track through the walking wheel; the power device is used to provide power for the driving device, the fastener cleaning device, the bolt fastening device, the telescopic compression strip device, the sensor system, the data acquisition and processing device, the control system, and the data storage device.

[0044] The technical scheme provided by the above-mentioned embodiment of the present application can be seen, and the present application provides a railway track fastener state detection and fastening equipment. The equipment comprises a working vehicle, a power system, a fastener cleaning device, a bolt fastening device, a telescopic pressing strip device, a sensor system, a data acquisition and processing device, a control system, a data storage device and the like. The fastener cleaning device is used for cleaning the fastener bolts and the elastic strip. The data acquisition and processing device obtains the fastener state information through machine vision, uses a convolutional neural network model to train and predict the friction coefficient of the friction wheel in the bolt fastening device and the fastener, and obtains the relative position relationship with the fastener. The telescopic pressing strip device reduces the torque required by the fastening bolt by telescoping the elastic strip, and the bolt fastening device controls the fastening torque of the bolt by adjusting the distance between the friction wheel and the rolling wheel. Thus, the detection of the railway track fastener state and the automatic fastening of the fastener are realized. The present application greatly reduces the labor and on-site operation process required for the detection and fastening of the fastener on site, realizes the integration of the railway fastener state detection and the fastening operation of the fastener bolt, greatly improves the detection and maintenance efficiency of the fastener, and provides certain theoretical and technical support for the intelligent detection and automatic maintenance of the railway fastener.

[0045] Additional aspects and advantages of the present application will be described in the following description, which will become apparent from the following description, or will be learned by practice of the present application. BRIEF DESCRIPTION OF DRAWINGS

[0046] In order to more clearly illustrate the technical scheme of the embodiments of the present application, the drawings required in the embodiment description will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0047] Figure 1 A schematic diagram of the upper structure of the railway track fastener state detection and fastening equipment provided by the present application;

[0048] Figure 2 A schematic diagram of the bottom structure of the railway track fastener state detection and fastening equipment provided by the present application;

[0049] Figure 3 A schematic diagram of the walking wheel structure of the railway track fastener state detection and fastening equipment provided by the present application;

[0050] Figure 4 A three-dimensional schematic diagram of the telescopic pressing strip device of the railway track fastener state detection and fastening equipment provided by the present application;

[0051] Figure 5 A telescopic pressing strip initial state schematic diagram of the telescopic pressing strip device of the railway track fastener state detection and fastening equipment provided by the present application;

[0052] Figure 6 A schematic diagram of the pressing state of the telescopic pressing strip device of the railway track fastener state detection and tightening equipment provided by the present application;

[0053] Figure 7 A partial structure schematic diagram of the telescopic pressing strip device of the railway track fastener state detection and tightening equipment provided by the present application, used to show the connection relationship of the pressing driving motor, eccentric wheel, spring and telescopic pressing strip;

[0054] Figure 8 Another view schematic diagram of the partial structure of the telescopic pressing strip device of the railway track fastener state detection and tightening equipment provided by the present application;

[0055] Figure 9 A schematic diagram of the bolt tightening device of the railway track fastener state detection and tightening equipment provided by the present application;

[0056] Figure 10 A schematic diagram of the fastener cleaning device of the railway track fastener state detection and tightening equipment provided by the present application;

[0057] Figure 11 A visual sensor structure schematic diagram of the railway track fastener state detection and tightening equipment provided by the present application.

[0058] In the figure:

[0059] 1. driving device, 2. seat, 3. industrial control computer, 4. positioning system, 5. wind deflector, 6. walking wheel structure, 7. fastener cleaning device, 8. data acquisition and processing device, 9. lighting and alarm device, 10. bolt tightening device, 11. telescopic pressing strip device, 121. walking wheel, 122. second rail hugging device, 13. first rail hugging device, 131. roller, 14. telescopic pressing strip, 15. bolt tightening engine, 16. friction wheel cleaning device, 17. friction wheel, 18. rolling wheel, 191. sleeve ring, 192. stretcher, 20. driving shaft, 21. cleaning disc, 22. fastener cleaning engine, 23. shock absorber, 24. visual sensor, 25. power device, 26. positioning rod, 27. data storage device, 28. pressing driving motor, 29. eccentric wheel, 30. return spring. DETAILED DESCRIPTION

[0060] Embodiments of the present application are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals represent the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the accompanying drawings are exemplary and are only used to explain the present application, and cannot be interpreted as a limitation of the present application.

[0061] Those skilled in the art can understand that the singular forms "a," "an," and "the" used herein include plural references unless expressly stated to the contrary. It should be further understood that the use of the term "includes" in the specification of the application means that there are features, integers, steps, operations, elements, and / or components present, but does not preclude the addition or the presence of one or more other features, integers, steps, operations, elements, components, and / or groups thereof. It should be understood that when we say an element is "connected" or "coupled" to another element, it can be directly connected or coupled to the other element, or there can be intervening elements. In addition, "connected" or "coupled" as used herein can include wireless connections or couplings. The term "and / or" as used herein includes any one and all combinations of one or more associated listed items.

[0062] Those skilled in the art can understand that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the application belongs. It should also be understood that terms such as those defined in a general dictionary should be understood to have meanings consistent with those in the context of the prior art, and should not be interpreted in an idealized or overly formal sense unless defined as such.

[0063] In order to facilitate the understanding of the embodiments of the application, the following will be further explained and described with several specific embodiments as examples in conjunction with the accompanying drawings, and each embodiment does not constitute a limitation on the embodiments of the application.

[0064] Referring to Figures 1 to 11 The present application provides a railway track fastener state detection and tightening device, comprising a working vehicle body, and a fastener cleaning device 7, a bolt tightening device 10, a telescopic pressing strip device 11, a sensor system, a data acquisition and processing device 8, a control system and a data storage device arranged on the working vehicle body.

[0065] The fastener cleaning device 7 has a rotatable cleaning disc 21, which is located on the bottom surface of the working vehicle body. The bolt tightening device has friction wheels 17 and rolling wheels 18, which are arranged in pairs with each other and located on the bottom surface of the working vehicle. Each pair of friction wheels 17 and rolling wheels 18 can rotate in opposite directions. The telescopic pressing strip device 11 is located on the bottom surface of the working vehicle body, and has a telescopic pressing strip 14 for pressing the elastic strip of the fastener.

[0066] The data acquisition and processing device 8 has an image acquisition module and a processor. The image acquisition module is used to obtain the apparent information of the fastener. The processor is used to obtain the state of the fastener, the friction coefficient between the bolt of the fastener and the friction wheel, and the relative position between the fastener and the working vehicle by calculation according to the apparent information.

[0067] The sensor system is used to monitor the vibration information of the fastener cleaning device, the bolt fastening device and the telescopic compression strip device, and the temperature information of the data acquisition and processing device, the control system and the data storage device.

[0068] The control system is electrically connected with the fastener cleaning device, the bolt fastening device, the telescopic compression strip device, the sensor system, the data acquisition and processing device 8, the control system and the data storage device respectively. The control system is used to: according to the vibration information of the fastener cleaning device 7, the bolt fastening device 10 and the telescopic compression strip device 11, the temperature information of the data acquisition and processing device 8, the control system and the data storage device, judge whether the railway track fastener state detection and fastening equipment appears fault; according to the friction coefficient of the bolt and the friction wheel of the fastener calculated by the data acquisition and processing device, adjust the interval distance of the friction wheel and the rolling wheel.

[0069] In the preferred embodiments provided by the present application, the specific settings of each device and system are as follows:

[0070] The driving device 1 is arranged on the working vehicle body. It drives the working vehicle to move along the railway track by using the torque generated by the motor or other power source through a specific mechanical transmission structure and the walking parts (such as rail wheels, etc.) in contact with the steel rail. The power transmission and control mode is designed to enable the working vehicle to run smoothly and flexibly on the track, so as to smoothly reach the fasteners at different positions on the track and prepare for subsequent detection and fastening operations. In actual operation, the speed of the driving device 1 can be adjusted as needed to adapt to different working scenes and requirements.

[0071] The power system 25 is installed at a suitable position of the working vehicle, which mainly consists of a power source (such as an engine, a generator set, etc.) and corresponding power distribution components (such as a distribution box, a hydraulic pump station, etc.). The energy generated by the power source is transmitted through the circuit or hydraulic pipeline to provide sufficient and stable power for each working device.

[0072] As shown in Figure 2 The fastener cleaning device 7 can be installed at a position behind the working vehicle walking wheel structure 6, which can facilitate the operation of the spring strip fastener bolt. It is equipped with a specially designed cleaning disc 21, which can be made of appropriate materials. Figure 10 As shown in

[0073] The bolt fastening device 10 is arranged in front of the rear wheel of the working vehicle, which can ensure that it accurately operates the bolt of the rail fastener. It is driven by electricity or hydraulic power, and the transmission rod-sleeve structure is used to control the fastening torque. When the working vehicle drives to the bolt to be fastened, the bolt information collected by the data acquisition and processing device 8 is analyzed by the industrial control computer 3, and the position of the friction wheel 17 and the rolling wheel 18 is adjusted by the shafting device to apply the required pressure to the bolt, so that the appropriate torque is applied to the bolt to make the connection between the fastener and the rail more stable.

[0074] In some preferred embodiments, as shown in Figure 9 the bolt fastening device comprises:

[0075] The bolt fastening engine 15 is installed on the working vehicle.

[0076] The driving shaft 20 is detachably connected to the output end of the bolt fastening engine 15, and the bolt fastening engine is drivingly connected to the friction wheel 17 through the driving shaft 20.

[0077] The shafting structure comprises a positioning rod 26, which is detachably installed on the bottom of the working vehicle, and one end of the positioning rod 26 is provided with a rolling bearing, and the rolling wheel 18 is movably installed on one end of the positioning rod 26 through the rolling bearing.

[0078] The transmission rod-sleeve structure has a pair of sleeves 191 connected to each other through a tensioner 192, and the sleeves 191 are in contact with the driving shaft 20 and the positioning rod 26, respectively. The tensioner 192 is connected to the control system circuit, and can adjust the interval distance between the friction wheel 17 and the rolling wheel 18 by changing its length. In the embodiments provided in the present application, the tensioner 192 is based on existing technology (commercial products), and is preferably a rod structure, which will not be described here. The tensioner 192 adjusts the interval distance between the friction wheel 17 and the rolling wheel 18 in a small range, which is fine tuning. The initial interval distance between the friction wheel 17 and the rolling wheel 18 is set according to the model of the rail bolt.

[0079] In some improvements, the outer side (the side away from the rolling wheel 18) of the friction wheel 17 is also provided with a friction wheel 17 cleaning device 16, as shown in Figure 9 which can adopt a cover type structure, and the cover has a cleaning body such as sponge or wiping cotton yarn, which can wipe the friction wheel 17 when it rotates to remove dirt.

[0080] The telescopic strip pressing device 11 is installed in the middle of the side bolt fastening device, and the device avoids contacting other parts of the elastic strip by extending the telescopic strip 14 in the appropriate position. When the working vehicle advances under the action of the driving device, the telescopic strip pressing device 11 is pressed to the appropriate position of the elastic strip by mutual frictional contact during operation, thereby reducing the torque required when the bolt is tightened.

[0081] For example, in some preferred embodiments, as shown in Figure 4 、 7 , 8, the telescopic strip pressing device 14 includes:

[0082] A pair of first rail grippers 13 are detachably installed on the working vehicle body, and the first rail grippers 13 provide stable support for the telescopic strip pressing device 14 by clamping the rail.

[0083] The telescopic strip 14 is located in the first rail gripper 13 and is detachably connected with the first rail gripper 13, as shown in Figure 4 、 5 , 6, the first rail gripper 13 has a window, and the telescopic strip 14 is located in the area of the window and can be extended or retracted from the window.

[0084] A plurality of rollers 131 are installed on the inner side of the first rail gripper 13, and the rollers 131 are in contact with the surface of the rail when the first rail gripper 13 clamps the rail.

[0085] A pressing driving motor 28 is installed in the first rail gripper 13 or at the bottom of the working vehicle body, and the output end of the pressing driving motor 28 has an eccentric wheel 29, the position of the eccentric wheel 29 corresponds to the telescopic strip 14, and the pressing driving motor 28 can drive the eccentric wheel 29 to make the convex part of the eccentric wheel 29 approach and push the telescopic strip 14 to extend from the window and press the elastic strip of the buckle.

[0086] A pair of reset springs 30 are connected at both ends of the telescopic strip 14 (the other end of the spring is connected to the inner wall of the first rail gripper 13). When the pressing driving motor 28 drives the eccentric wheel 29 to push the telescopic strip 14 to extend, the reset spring 30 is stretched. When the pressing driving motor 28 drives the eccentric wheel 29 to make the convex part away from the telescopic strip 14, the reset spring 30 can pull the telescopic strip 14 back into the first rail gripper 13 by its pulling force (elastic restoring force).

[0087] As shown in Figure 8 and 9 , when the eccentric wheel 29 is in the current position, the telescopic strip 14 is not extended, and at this time there is some elastic force back to the reset spring 30. When the driving motor drives the eccentric wheel 29 to rotate 180°, the telescopic strip 14 is in the extended state, and at this time the extension amount is maximum. The eccentric wheel 29 continues to rotate, and the telescopic strip 14 will be retracted in real time under the influence of the pulling force of the reset spring 30.

[0088] The pressing drive motor 28 is controlled in real time by the electric signal output by the control system. Since the pressing drive motor 28 mainly overcomes the resistance of the return spring 30, the volume and power of the pressing drive motor 28 can be smaller, but the control accuracy is higher.

[0089] Sensor systems are installed at various necessary locations on the work vehicle, including but not limited to near the drive unit 1, fastener cleaning unit 7, and bolt tightening unit 10. Various sensor types are available, including temperature sensors, vibration sensors, and displacement sensors. Temperature sensors monitor temperature changes in key equipment components in real time to prevent overheating and damage. Vibration sensors detect vibration during operation, analyzing any abnormal vibrations and determining wear or looseness of mechanical components. Displacement sensors monitor the distance traveled by the work vehicle and the operating range of various devices. The data collected by these sensors is transmitted via signal lines to the control system and industrial control computer 3, enabling identification and judgment of the normal operating status of various components of the work vehicle. This enables real-time monitoring of equipment operation and prompt detection of potential faults.

[0090] The data acquisition and processing device 8 is located at a suitable position on the work vehicle, and includes an image acquisition module (such as Figure 11 The visual sensor 24, etc., shock absorber 23, industrial control computer 3, and the algorithms built into them. The image acquisition module can capture the apparent state of the fastener, obtain surface information about the fastener bolts, and train a model using a convolutional neural network algorithm to accurately determine the friction coefficient between the fastener bolts and the friction wheel. The SURF algorithm calculates the distance to the track or other fixed reference points to determine the relative position information between the spring clip fastener and the work vehicle. Furthermore, the visual sensor 24 can identify damaged, missing, or misaligned fasteners, as well as the surface condition of the rail. This collected data is transmitted to the industrial control computer 3 via a data transmission line, providing an important basis for analyzing the fastener bolt condition and ensuring the accurate operation of subsequent equipment. The industrial control computer 3 is installed on the work vehicle and is electrically connected to the sensor system, data acquisition system 8, and control system via data cables. This terminal is equipped with a large-capacity storage device (such as a hard drive, solid-state drive, etc.) and a high-performance processor, and is equipped with a convolutional neural network algorithm and a SURF algorithm. During operation, it receives and stores equipment operating data collected by the sensor system, fastener information and position data acquired by the data acquisition and processing device, and operating parameters and command records of the control system. At the same time, the processing software within the device uses the above-mentioned algorithms to analyze and process these data. These processed data provide a reliable basis for subsequent analysis and decision-making, helping to further optimize operating procedures and equipment performance.

[0091] In the preferred embodiments provided by the application, the process of predicting the friction coefficient by the convolutional neural network algorithm comprises:

[0092] (1) Image preprocessing: The main purpose of image preprocessing is to eliminate irrelevant information in the first image, restore useful real information, enhance the detectability of relevant information, and maximize data simplification, thereby improving the reliability of feature extraction, image segmentation, matching, and recognition.

[0093] The first image is the image of the bolt of the fastener in contact with the friction wheel.

[0094] 1) Image normalization: Linear normalization method is used to linearly scale the pixel values of the first image to a specific range (such as 0 to 1 or -1 to 1) to eliminate differences between different first images due to different pixel value ranges. According to the maximum and minimum values of the image data, the pixel values are mapped to the target range through a linear transformation formula.

[0095] 2) Color space conversion: RGB to grayscale image conversion is used to generate a grayscale image by calculating the weighted sum of the three RGB channels. This simplifies the first image data, reduces computational complexity, and preserves the texture and shape information of the image.

[0096] 3) Image denoising: Linear filtering methods such as mean filtering and Gaussian filtering are used. Noise is removed by calculating the weighted average of the pixels around each pixel in the image.

[0097] 4) Image enhancement:

[0098] ① Sharpening method: including Laplacian operator and high-pass filter, etc. Sharpening effect is achieved by enhancing the high-frequency components in the image. The edge and detail information of the image are clearer, and the resolution of the image is improved.

[0099] ② Contrast enhancement method: including histogram stretching and histogram equalization, etc. The contrast is enhanced by adjusting the brightness distribution of the image, making the brightness difference between different objects in the image more obvious, and improving the clarity of the image.

[0100] 5) Image cropping and scaling: to adapt to the needs of subsequent processing or analysis.

[0101] (2) Construction of convolutional neural network model:

[0102] 1) Select the PyTorch-based deep learning framework for construction and training;

[0103] 2) Design network structure:

[0104] ① Input layer: according to the preprocessed image in the previous step, the properties of the preprocessed bolt surface image are

[0105] The number of layers is set to the size of the input layer;

[0106] ②Convolutional layer: Add multiple convolutional layers to extract local features of the bolt surface in the image. Each convolutional layer can

[0107] Set different convolution kernel size, number and step length to ensure the accurate operation of the model;

[0108] ③Pooling layer: Add a pooling layer after the convolutional layer to reduce the size of the feature map and reduce the amount of calculation. The pooling method can be max pooling and average pooling.

[0109] ④Fully connected layer: Flatten the feature map output by the pooling layer and input it into the fully connected layer. The fully connected layer is responsible for mapping the extracted features to the final friction coefficient prediction value.

[0110] ⑤Output layer: Set the number of neurons in the output layer according to the requirements of the prediction task. In this task, the output layer usually has only one neuron, which is used to output the predicted friction coefficient value.

[0111] 3) Select activation function: Use ReLU activation function after convolutional layer and fully connected layer to increase the non-linear expression ability of the model. Use linear activation function after the output layer to output the predicted friction coefficient value.

[0112] 4) Design loss function and optimizer: Select the mean absolute error (MAE) loss function to measure the difference between the model's predicted value and the actual value. And select the SGD optimizer to update the parameters of the model.

[0113] (3) Model training and evaluation

[0114] 1) Divide the dataset: Divide the dataset in the database built into training set, validation set and test set. The training set is used to train the model, the validation set is used to adjust the hyperparameters of the model and evaluate the performance of the model, and the test set is used to evaluate the generalization ability of the model.

[0115] 2) Train the model: Use the training set data to train the model, and monitor the performance of the model through the validation set data.

[0116] And in the training process, according to the performance on the validation set to adjust the hyperparameters of the model.

[0117] 3) Evaluate the model: Use the test set data to evaluate the performance of the model. Calculate the prediction error of the model on the test set to evaluate the accuracy of the model.

[0118] 4) Model tuning: According to the evaluation results, the model is tuned, the process of training, evaluation and tuning is repeated, until the satisfactory model performance is obtained.

[0119] (4) Model deployment and application:

[0120] Deploy the trained model to the data acquisition and processing system, and make reasonable adjustments according to the actual operation.

[0121] Adjust the spacing of the friction wheel and the rolling wheel according to the predicted friction coefficient to ensure that enough torque is output to the nut.

[0122] In some preferred embodiments, the process of calculating the relative distance by the SURF algorithm includes:

[0123] (1) Feature point extraction:

[0124] a. Construct the Hessian matrix: Use the Hessian matrix to detect key points in the second image. By performing extreme value detection on the determinant of the Hessian matrix, the position of the potential key points in the second image can be determined.

[0125] The second image is the image of the fastener used to calculate the relative position between the fastener and the working vehicle.

[0126] b. Feature point screening: By calculating the distance and angle difference between feature points, those unstable or mis-matched feature points are excluded.

[0127] (2) Feature point description:

[0128] a. Calculate the descriptor

[0129] b. Normalization: To enhance the robustness of the features, the SURF algorithm will normalize the descriptor to ensure that each feature vector has a unit length.

[0130] (3) Feature point matching:

[0131] a. Calculate the Euclidean distance

[0132] b. Matching screening: Matching screening based on distance ratio and outlier rejection based on RANSAC (Random Sample Consensus) algorithm. These methods can further exclude mis-matched feature point pairs.

[0133] (4) Calculate the actual distance

[0134] a. Calculate the geometric transformation relationship: Using the matched feature point pairs, the RANSAC algorithm can be used to estimate the homography matrix, which describes the perspective transformation relationship from one second image to another adjacent frame second image.

[0135] b. Use the camera calibration parameters.

[0136] c. Calculate three-dimensional coordinates and distances: Using the calibration parameters and geometric transformation relationships, the three-dimensional coordinates of corresponding points in the two second images can be calculated. By comparing the differences of these three-dimensional coordinates, the actual object distance can be calculated.

[0137] The lighting and alarm device 9 is installed on the working vehicle. The lighting part uses high-brightness, multi-angle lighting lamps, which are distributed on the working vehicle body, especially near the spring strip fastener. These lamps can produce light of sufficient intensity, effectively improving the visibility of the spring strip fastener, and providing good light conditions for detection and tightening operation whether in insufficient daylight or at night. The alarm function is connected to the sensor system and control system. When the sensor detects a fault in the equipment (such as excessive temperature of a device, abnormal vibration of a key component, etc.), the alarm function will immediately start, prompting the staff to handle through sound and light alarm (such as sounding an alarm and flashing warning lights).

[0138] The control system is located on the working vehicle body. The control system is electrically connected to the bolt fastening device 10, the driving device 1, the data acquisition and processing device 8, and the sensor system through control circuit and control algorithm. It receives various monitoring data from the sensor system, judges the running state of the equipment according to the preset program and algorithm, and sends control instructions to the driving device to adjust the driving speed and direction of the working vehicle; issues instructions such as fastening torque and operation time to the bolt fastening device; controls the acquisition frequency and parameters of the data acquisition and processing device. Through this way of coordinating the work of each device, the automatic detection and fastening process is realized, and the operation efficiency and accuracy are improved.

[0139] The positioning system 4 is installed beside the data storage and processing terminal on the working vehicle. It uses advanced positioning technology (such as GPS, Beidou satellite positioning system, and track mileage marker auxiliary positioning method). The satellite positioning system can provide large-scale position coordinate information, while the track mileage marker auxiliary positioning method can more accurately determine the specific position of the equipment on the railway track. These position information is transmitted to the control system and industrial control computer 3 through data transmission lines, providing accurate position information for the equipment, facilitating accurate positioning and recording of the working position, and ensuring that the equipment can accurately detect and tighten the target fastener.

[0140] As shown in the figure, the driving device and the power device are also installed on the working vehicle, and the walking wheels are also installed. The walking wheels are located on the bottom surface of the working vehicle and cooperate with the track. As shown in the figure, the walking wheels are arranged in pairs, and four pairs of walking wheels are arranged at the bottom of one working vehicle. The interval area of each pair of walking wheels is also provided with a second rail hugging device. The second rail hugging device also adopts a double-arm structure similar to the first rail hugging device, and can provide stable support for the walking wheels. The driving device is drivingly connected with the walking wheels, and is used to drive the working vehicle to move on the track through the walking wheels. The power device is used to provide power for the driving device, the fastener cleaning device, the bolt fastening device, the telescopic pressing strip device, the sensor system, the data acquisition and processing device, the control system and the data storage device.

[0141] In summary, the present application provides a railway track fastener state detection and tightening equipment. It includes a working vehicle, a power system, a fastener cleaning device, a bolt fastening device, a telescopic pressing strip device, a sensor system, a data acquisition and processing device, a control system, a data storage device, etc. The fastener cleaning device is used to clean the fastener bolts and the elastic strips. The data acquisition and processing device obtains the fastener state information through machine vision, and uses a convolutional neural network model to train and predict the friction coefficient of the friction wheel in the bolt fastening device and the relative position relationship with the fastener. The telescopic pressing strip device reduces the torque required for the fastening bolt by telescoping the elastic strip, and the bolt fastening device controls the bolt fastening torque by adjusting the distance between the friction wheel and the rolling wheel. Thus, the detection of the railway track fastener state and the automatic tightening of the fastener are realized. The present application greatly reduces the manual labor and on-site operation procedures required for on-site fastener state detection and fastener tightening, realizes the integration of railway fastener state detection and fastener bolt tightening operation, greatly improves the detection and maintenance efficiency of the fastener, and provides certain theoretical and technical support for intelligent detection and automatic maintenance of the railway fastener.

[0142] Those skilled in the art can understand that the modules or processes in the drawings are not necessarily required for the implementation of the present application.

[0143] From the above description of the embodiments, those skilled in the art can clearly understand that the present application can be implemented by means of software and the necessary general hardware platform. Based on such understanding, the technical solutions of the present application can be embodied in the form of a software product, which can be stored in a storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes a plurality of instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0144] The various embodiments described in this specification are described with reference to a particular sequence or order, but the order of the embodiments described is not necessarily the order in which the embodiments are implemented. Embodiments described in this specification are not necessarily mutually exclusive, as some embodiments can be combined with one or more other embodiments to form new embodiments. The terms used in this specification generally have their ordinary meanings. The terminology used in the description is for the purpose of describing specific embodiments only and is not intended to be limiting. The use of the terms "first", "second", and so on do not imply any particular order but are used for naming purposes only. The use of headings and section or paragraph titles is for convenience only. The use of words like "can", "may", and "will" in this specification is intended to convey a possibility of an event occurring in a specific context and simply indicates that there exists one or more embodiments in which the event occurs, one or more embodiments in which the event does not occur, and that these facts alone can or can not be dependent on each other. The word "comprising", and variations such as "comprise" or "comprises", when used in this specification are not used in a restrictive sense and are used to mean the words "including", "containing", or "characterized by". The word "substantially" does not mean "exactly" or "perfectly" but means "to a high degree" or "essentially". The words "coupled" and "coupling" mean to be directly or indirectly connected, and are not necessarily limited to an optical connection. The words "program" and "software" mean any non-firmware instruction set in any language, code, script, machine code, machine language, or other combination of instructions supported or implemented by a processor or controller. The words "processor" and "controller" mean any hardware component that is capable of executing instructions. The words "memory" and "storage" mean any hardware component that is capable of storing instructions. The words "module" and "unit" mean any hardware component that is capable of performing a function. The words "interface" and "connection" mean any hardware component that is capable of transmitting or receiving signals. The words "signal" and "data" mean any information that is capable of being transmitted or received. The words "transmit" and "receive" mean to send or to get, respectively. The words "include" and "comprise" mean to be inclusive of but not limited to. The words "one" or "the" mean one, but also means more than one. The words "exemplary" and "example" mean serving as an example, instance, or illustration, and are not necessarily limited to the preferred embodiment.

[0145] The above description is only the preferred embodiment of the present application, but the protection scope of the present application is not limited to this. Any person skilled in the art

Claims

1. A railway track fastener condition detection and tightening apparatus, characterized by, It includes a work vehicle, and a fastener cleaning device, a bolt tightening device, a telescopic batten device, a sensor system, a data acquisition and processing device, a control system and a data storage device arranged on the work vehicle; The fastener cleaning device has a rotatable cleaning disc, and the cleaning disc is located on the bottom surface of the work vehicle; The bolt fastening device comprises a friction wheel and a rolling wheel, the friction wheel and the rolling wheel are arranged in pairs with an interval between each other and are located on the bottom surface of the work vehicle; The friction wheel is used to drive the bolt of the fastener, and the interval between the friction wheel and the rolling wheel is adjustable; The retractable pressure strip device is located on the bottom surface of the work vehicle and has a retractable pressure strip, and the pressure strip is used to press the elastic strip of the fastener; The data acquisition and processing device comprises an image acquisition module and a processor; the image acquisition module is used to obtain the appearance information of the fastener; the processor is used to calculate, based on the appearance information: the state of the fastener, the friction coefficient between the fastener bolt and the friction wheel, and the relative position between the fastener and the work vehicle; The sensor system is used to monitor: vibration information of the fastener cleaning device, bolt tightening device and telescopic strip device, and temperature information of the data acquisition and processing device, control system and data storage device; The control system is respectively connected in circuit to the fastener cleaning device, bolt tightening device, telescopic pressure strip device, sensor system, data acquisition and processing device, control system and data storage device; the control system is used to: determine whether the railway track fastener status detection and tightening equipment has a fault based on the vibration information of the fastener cleaning device, bolt tightening device and telescopic pressure strip device, and the temperature information of the data acquisition and processing device, control system and data storage device; and adjust the spacing distance between the friction wheel and the rolling wheel based on the friction coefficient between the fastener bolt and the friction wheel calculated by the data acquisition and processing device.

2. The device according to claim 1, characterized in that The fastener cleaning device includes a fastener cleaning engine drivingly connected to the cleaning disk.

3. The apparatus of claim 1, wherein, The bolt fastening device comprises: Bolt-fastening the engine and installing it on the work vehicle; a drive shaft detachably connected to an output end of the bolt-tightening engine, wherein the bolt-tightening engine is drivingly connected to the friction wheel via the drive shaft; The shaft system structure includes a positioning rod, the positioning rod is detachably mounted on the bottom of the work vehicle, one end of the positioning rod has a rolling bearing, and the rolling wheel is movably mounted on the one end of the positioning rod through the rolling bearing; The transmission rod-sleeve structure has a pair of rings connected to each other through a stretcher, and the rings are respectively in contact with the drive shaft and the positioning rod; the stretcher is connected to the control system circuit and can adjust the distance between the friction wheel and the rolling wheel by changing its own length.

4. The apparatus of claim 3, wherein, The bolt fastening device further comprises a friction wheel cleaning device detachably mounted on the outer side of the friction wheel.

5. The apparatus of claim 1, wherein, The telescopic layering device comprises: a pair of first rail grippers, detachably mounted on the work vehicle body, the first rail grippers being used to clamp the rail; A telescopic pressing strip, detachably connected with the first rail hugging device; the first rail hugging device has a window, and the telescopic pressing strip is located in the area of the window; A plurality of rollers, installed on the inner side of the first rail hugging device, and in contact with the surface of the rail when the first rail hugging device clamps the rail; A pressing driving motor, installed on the first rail hugging device of the working vehicle body; the output end of the pressing driving motor has an eccentric wheel, the position of the eccentric wheel corresponds to the telescopic pressing strip, and the pressing driving motor can push the telescopic pressing strip out of the window and press the elastic strip of the fastener by driving the eccentric wheel; A pair of reset springs, respectively connected at both ends of the telescopic pressing strip.

6. The apparatus of claim 1, wherein, The data acquisition and processing device calculates the relative position between the fastener and the working vehicle through the SURF algorithm, and calculates the state of the fastener and the friction coefficient of the bolt and the friction wheel of the fastener through the convolutional neural network algorithm.

7. The apparatus of claim 6, wherein, The process of calculating the friction coefficient of the bolt and the friction wheel of the fastener according to the apparent information by the processor includes: S1, preprocessing the first image, including normalization, color space conversion, noise removal and first image enhancement; the first image is an image in which the bolt and the friction wheel of the fastener contact each other; S2, constructing a convolutional network model; the convolutional network model includes an input layer, a convolutional layer, a pooling layer, a full connection layer and an output layer arranged in sequence along the data flow direction; the input layer is used to set the property parameters of the bolt surface features of the preprocessed first image as the size of the input layer; the convolutional layer is used to extract the local features of the bolt surface in the preprocessed first image; the pooling layer is used to reduce the size of the extracted local features of the bolt surface; the full connection layer is used to map the local features of the bolt surface to the predicted friction coefficient; and the output layer is used to output the predicted friction coefficient value; S3, using a ReLU activation function to increase the nonlinear expression ability of the convolutional network model; S4, measuring the difference between the predicted value and the actual value of the convolutional network model through an average absolute error loss function, and updating the parameters of the convolutional network model through an SGD optimizer; S5, training, testing and tuning the convolutional network model using a data set; S6, using the tuned convolutional network model to predict the friction coefficient of the bolt and the friction wheel of the fastener, so that the control system can adjust the interval distance between the friction wheel and the rolling wheel based on the obtained friction coefficient.

8. The apparatus of claim 6, wherein, The process of calculating the relative position between the fastener and the working vehicle through the SURF algorithm includes: E1, using a Hessian matrix to detect key points in the second image, and obtaining the positions of potential key points in the second image by performing extreme value detection on the determinant of the Hessian matrix; the second image is an image of the fastener used to calculate the relative position between the fastener and the working vehicle; E2, excluding unstable or mismatched feature points by calculating the distance and angle difference between the feature points in the second image; E3, calculating the descriptor based on the feature points in the second image after step E2 is performed; E3, normalizing the descriptor; E4, based on the descriptors after normalization, obtaining the Euclidean distance of the descriptors by calculation; E5, based on the proportion of the Euclidean distance obtained by calculation, screening the feature points matched with the random sampling consistency algorithm; E6, based on the feature points obtained by screening, estimating the homography matrix by the random sampling consistency algorithm; E7, using the image acquisition module to calibrate the parameters; E8, based on the parameters calibrated in combination with the corresponding geometric correspondence, obtaining the three-dimensional coordinates of the same feature points in the second image of two adjacent frames by calculation, and calculating the relative position between the fastener and the work car by comparing the differences of the three-dimensional coordinates of the feature points.

9. The apparatus of claim 1, wherein, The sensor system includes a temperature sensor, a vibration sensor and a displacement sensor; the temperature sensor is used to obtain the temperature information of the data acquisition and processing device, the control system and the data storage device in real time; the vibration sensor is used to obtain the vibration information of the fastener cleaning device, the bolt fastening device and the telescopic compression strip device in real time; the displacement sensor is used to obtain the position information and the running distance information of the work car, and the working stroke information of the fastener cleaning device, the bolt fastening device and the telescopic compression strip device.

10. The apparatus of claim 1, wherein, It also includes a driving device and a power device installed on the work car, and a walking wheel; the walking wheel is located on the bottom surface of the work car and cooperates with the track; the driving device is drivingly connected with the walking wheel, and is used to drive the work car to move on the track through the walking wheel; the power device is used to provide power for the driving device, the fastener cleaning device, the bolt fastening device, the telescopic compression strip device, the sensor system, the data acquisition and processing device, the control system and the data storage device.

Images