A failure repair system for shear hinge system of track structure

Abstract

The present invention discloses a failure repair system for a shear hinge system of a track structure, comprising a data acquisition module, an image detection module, a control system, a repair structure, and a classification module. The data acquisition module acquires image data of the shear hinge and sends the data to the image detection module. The image detection module receives the image data of the shear hinge acquired from the data acquisition module and pre-processes the acquired image. The feature extraction module extracts features from the acquired image data of the shear hinge, extracts the failure area of ​​the shear hinge, and sends the extracted data of the failure area to the data acquisition module. The data acquisition module uses the data of the adhesion, longitudinal force, and temperature of the shear hinge in the area, and sends the data to the classification module. The classification module uses a clustering algorithm to classify the extracted data and determine the category of the shear hinge failure. The present invention realizes automatic detection and automatic repair of the shear hinge, and has the characteristics of high efficiency and intelligence.

Description

Technical Field

[0001] The invention relates to the technical field of track structure shear hinge repair, and in particular to a track structure shear hinge system failure repair system. Background Art

[0002] The shear hinge system of the track structure is an important supporting structure in the track structure. It determines the safety and stability of the track structure. Based on the importance of the shear hinge system, the shear hinge system needs to be regularly maintained. However, the current maintenance system mostly uses manual maintenance, which is neither efficient nor economical and convenient. In addition, the maintenance system cannot achieve integrated intelligent repair from detection to maintenance, making the entire repair process cumbersome and inefficient. Summary of the invention

[0003] In order to at least solve or partially solve the above problems, a failure repair system for a shear hinge system of a track structure is provided.

[0004] In order to achieve the above object, the present invention provides the following technical solutions:

[0005] The present invention provides a failure repair system for a shear hinge system of a track structure, comprising a data acquisition module, an image detection module, a control system, a repair structure, and a classification module. The data acquisition module acquires image data of the shear hinge and sends the data to the image detection module. The image detection module comprises a preprocessing module and a feature extraction module. The preprocessing module receives the image data of the shear hinge acquired from the data acquisition module, preprocesses the acquired image, and sends the preprocessed image data to the feature extraction module. The feature extraction module extracts features from the preprocessed image data, extracts a failure area of ​​the shear hinge, and sends the data of the extracted failure area to the data acquisition module. The data acquisition module acquires data on the adhesion, longitudinal force, and temperature of the shear hinge in the area, and sends the data to the classification module. The classification module classifies the extracted data using a clustering algorithm, determines the category of shear hinge failure, and sends the failure category and failure area to the control system. The control system controls the repair structure to repair the shear hinge according to the failure category and failure area.

[0006] As a preferred technical solution of the present invention, it also includes a mobile module and a communication module. The mobile module drives the data acquisition module to patrol the shear hinge area, and the data acquisition module and the image detection module exchange data through the communication module.

[0007] As a preferred technical solution of the present invention, the preprocessing module sequentially performs grayscale processing, normalization, contrast-limited adaptive histogram equalization and gamma nonlinear processing on the shear hinge image to obtain a preprocessed image.

[0008] As a preferred technical solution of the present invention, the feature extraction module calculates the feature value by means of the integral image in the HAAR feature; various HAAR features applicable to shear hinge failure are subjected to the AdaBoost algorithm to obtain a strong classifier; the strong classifiers are cascaded to obtain the final cascade classifier, thereby obtaining an image of shear hinge failure, and the Unet model of the convolutional neural network is used for segmentation.

[0009] As a preferred technical solution of the present invention, the convolutional neural network is composed of a network structure in the form of convolution units from convolution to batch normalization to activation of ReLU function.

[0010] As a preferred technical solution of the present invention, the clustering algorithm adopts the kmeans clustering algorithm, which places the data of the attachment force, longitudinal force and temperature of the shear hinge in the area in a database for clustering processing to obtain the category of failure of the shear hinge.

[0011] Compared with the prior art, the present invention has the following beneficial effects:

[0012] The present invention adopts an automated detection system to realize automatic detection and automatic repair of shear hinges, and completes the entire process from collection to repair. It has the characteristics of high efficiency and intelligence, and is suitable for various track structures. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0014] Figure 1 It is a schematic diagram of the overall structure of the present invention;

[0015] In the figure: 1. Data acquisition module; 2. Image detection module; 3. Control system; 4. Repair structure; 5. Classification module; 6. Preprocessing module; 7. Feature extraction module; 8. Mobile module; 9. Communication module. DETAILED DESCRIPTION

[0016] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention. The same reference numerals in the accompanying drawings all refer to the same components.

[0017] Furthermore, if a detailed description of known techniques is not necessary for illustrating the characteristics of the present invention, it will be omitted.

[0018] Example 1

[0019] like Figure 1As shown, the present invention provides a failure repair system for a shear hinge system of a track structure, comprising a data acquisition module 1, an image detection module 2, a control system 3, a repair structure 4, and a classification module 5. The data acquisition module 1 collects image data of the shear hinge and sends the data to the image detection module 2. The image detection module 2 comprises a preprocessing module 6 and a feature extraction module 7. The preprocessing module 6 receives the image data of the shear hinge collected from the data acquisition module 1, preprocesses the collected image, and sends the preprocessed image data to the feature extraction module 7. The feature extraction module 7 extracts features from the preprocessed image data, extracts the failure area of ​​the shear hinge, and sends the data of the extracted failure area to the data acquisition module 1. The data acquisition module 1 collects the data of the adhesion, longitudinal force, and temperature of the shear hinge in the area, and sends the data to the classification module 5. The classification module 5 uses a clustering algorithm to classify the extracted data, determines the category of shear hinge failure, and sends the failure category and failure area to the control system 3. The control system 3 controls the repair structure 4 to repair the shear hinge according to the failure category and failure area.

[0020] In order to further improve the detection range, it also includes a mobile module 8 and a communication module 9. The mobile module 8 drives the data acquisition module 1 to patrol the shear hinge area, thereby realizing large-area image detection. The data acquisition module 1 and the image detection module 2 exchange data through the communication module 9 to realize the remote data interaction function.

[0021] Specifically, in the process of image detection, the preprocessing module 6 performs grayscale processing, normalization, contrast-limited adaptive histogram equalization and gamma nonlinear processing on the shear hinge image in sequence to obtain a preprocessed image, and then performs feature extraction through the feature extraction module 7. The feature extraction module 7 calculates the eigenvalue by the integral image method in the HAAR feature; the various HAAR features applicable to shear hinge failure are subjected to the AdaBoost algorithm to obtain a strong classifier; the strong classifiers are cascaded to obtain a final cascade classifier, thereby obtaining an image of shear hinge failure, and the Unet model of a convolutional neural network composed of a network structure in the form of convolution units from convolution to batch normalization to activation of the Relu function is used for segmentation to obtain a failure image, and the shear hinge data is further detected according to the sensors near the failure image to determine the type of failure, and the kmeans clustering algorithm is used for judgment. The kmeans clustering algorithm places the data of the shear hinge adhesion, longitudinal force, and temperature of the shear hinge in the area in a database for clustering processing to obtain the category of the shear hinge failure.

[0022] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A failure repair system for a shear hinge system of a track structure, characterized in that: The invention comprises a data acquisition module (1), an image detection module (2), a control system (3), a repair structure (4), and a classification module (5). The data acquisition module (1) acquires image data of the shear hinge and sends the data to the image detection module (2). The image detection module (2) comprises a preprocessing module (6) and a feature extraction module (7). The preprocessing module (6) receives the image data of the shear hinge acquired from the data acquisition module (1), preprocesses the acquired image, and sends the preprocessed image data to the feature extraction module (7). The feature extraction module (7) Feature extraction is performed on the preprocessed image data to extract the failure area of ​​the shear hinge, and the data of the extracted failure area is sent to a data acquisition module (1). The data acquisition module (1) collects data on the adhesion force, longitudinal force, and temperature of the shear hinge in the area, and sends the data to a classification module (5). The classification module (5) uses a clustering algorithm to classify the extracted data, determine the category of shear hinge failure, and send the failure category and failure area to a control system (3). The control system (3) controls a repair structure (4) to repair the shear hinge according to the failure category and failure area.

2. A rail structure shear hinge system failure repair system according to claim 1, characterized in that: It also includes a moving module (8) and a communication module (9), wherein the moving module (8) drives the data acquisition module (1) to patrol the shear hinge area, and the data acquisition module (1) and the image detection module (2) perform data exchange via the communication module (9).

3. A rail structure shear hinge system failure repair system according to claim 1, characterized in that: The preprocessing module (6) sequentially performs grayscale processing, normalization, contrast-limited adaptive histogram equalization and gamma nonlinear processing on the shear hinge image to obtain a preprocessed image.

4. A rail structure shear hinge system failure repair system according to claim 1, characterized in that: The feature extraction module (7) calculates the feature value by using the integral image method in the HAAR feature; uses the AdaBoost algorithm to obtain a strong classifier for various HAAR features applicable to shear hinge failure; cascades the strong classifiers to obtain a final cascade classifier, thereby obtaining an image of shear hinge failure, and uses a Unet model of a convolutional neural network for segmentation.

5. A rail structure shear hinge system failure repair system according to claim 4, characterized in that: The convolutional neural network consists of a network structure in the form of convolution units from convolution to batch normalization to activation of ReLU function.

6. A rail structure shear hinge system failure repair system according to claim 1, characterized in that: The clustering algorithm adopts the kmeans clustering algorithm, which places the data of the attachment force, longitudinal force and temperature of the shear hinge in the area into a database for clustering processing to obtain the category of the shear hinge failure.

Images