Method for identifying installation looseness of anti-snaking shock absorber of train

Abstract

The invention relates to a train anti-snaking shock absorber installation loosening identification method, in particular to the field of railway traffic engineering, a camera is installed to obtain train anti-snaking shock absorber image data, and the overall and contrast of the train anti-snaking shock absorber image data are changed by enhancing the brightness difference, scaling the brightness range and stretching the gray level, so that train anti-snaking shock absorber installation loosening identification is achieved. The method comprises the following steps: positioning an object boundary through a gradient violent change region of a pixel gray value in train anti-snaking damper image data, carrying out edge detection, corner detection and spot detection, carrying out classification on each candidate frame through a random forest algorithm, judging detection features, and carrying out feature tracking; a Z-score algorithm is utilized to realize conversion of train anti-snaking damper image data and judgment condition data into standard normal distribution with a zero mean value and a unit standard deviation, the standard normal distribution is selectively stored in a cloud and a local database, and an alarm is sent to a train management worker according to the degree of loosening and abnormal conditions.

Description

Technical Field

[0001] The invention relates to the field of railway traffic engineering, and more specifically to a method for identifying loose installation of a train anti-snaking shock absorber. Background Art

[0002] The train anti-snaking damper is a shock absorbing device fixed to the train, which is mainly used to reduce the vibration and lateral movement of the train when it is running at high speed.

[0003] The current method for identifying loose installation of train anti-snaking shock absorbers has certain errors and missed detections, and cannot meet the needs of high precision and high reliability. In addition, the current method for identifying loose installation of train anti-snaking shock absorbers requires the train to be shut down for maintenance, and real-time monitoring cannot be achieved. The amount of data generated by the identification is huge, and effective data storage cannot be performed. Summary of the invention

[0004] The present invention aims at the technical problems existing in the prior art and provides a method for identifying loose installation of a train anti-snaking shock absorber to solve the problems raised in the above-mentioned background technology.

[0005] The technical solution of the present invention to solve the above technical problem is as follows: A method for identifying loose installation of a train anti-snaking shock absorber comprises the following steps: S101: installing a camera to obtain train anti-snaking shock absorber image data, taking one of the pixel points as the center to remove noise, and changing the overall image data and contrast of the train anti-snaking shock absorber image data by enhancing brightness difference, scaling brightness range, and stretching grayscale levels; S102: locating the object boundary by the region where the gradient of the pixel gray value in the train anti-snaking shock absorber image data changes dramatically to perform edge detection and corner point detection, performing spot detection by using the converted binary image data, classifying and determining the detection features of each candidate frame by using the random forest algorithm, and performing feature tracking; S103: setting a standard value of the misalignment of the clamps at the same end of the upper and lower shock absorbers in the train anti-snaking shock absorber, and comparing the actual values ​​of the misalignment of the clamps at the same end of the upper and lower shock absorbers in the train anti-snaking shock absorber identified and tracked to determine whether there is looseness or abnormality; S104: using a Z-score algorithm to convert the train anti-snaking shock absorber image data and the judgment situation data into a standard normal distribution with a zero mean and a unit standard deviation, and selectively storing them in a cloud and a local database, and creating a corresponding table in the selected database management system to implement data storage management; S105: Use the API interface to connect to the selected database and mark and display the train anti-snaking shock absorber image data of the determined situation through the visual interface, and send an alarm notification to the train management staff according to the degree of looseness and abnormality.

[0006] In a preferred embodiment, in S101, a camera is installed at the position of the train's anti-snaking shock absorber to obtain image data of the train's anti-snaking shock absorber, and the camera is fixed to the train using a camera bracket to ensure that the camera withstands the vibration of the train's operation and to adjust the camera angle and focal length to optimize.

[0007] Furthermore, a pixel point in the train anti-snaking shock absorber image data is taken as the center, and the pixel points around the center pixel point are averaged using a mean filter to remove the noise in the train anti-snaking shock absorber image data. The specific formula is:

[0008] in Indicates the position on the image after mean filtering The new pixel value at represents the size of the filter, represents the position of each pixel in the filter, Representing each position of the filter on the image, the contrast of the train anti-snaking damper image data is enhanced by increasing the brightness difference of different regions in the train anti-snaking damper image data, and the overall contrast of the train anti-snaking damper image data is changed by scaling the brightness range and stretching the grayscale level.

[0009] In a preferred embodiment, in S102, the object boundary is located by the area where the gradient of the pixel grayscale value in the train anti-snaking shock absorber image data changes dramatically, which is used for edge detection and corner detection of the train anti-snaking shock absorber image data, and the train anti-snaking shock absorber image data is converted into binary image data, and the spots in the train anti-snaking shock absorber image data are changed to black and the background is changed to white. The connected domain is defined by a 16-connected method, and the feature information of the area, shape and position of the spots in the binary image data is obtained by the area composed of adjacent pixels with the same pixel value. The features obtained by edge detection, corner detection and spot detection are selected, and redundant features are excluded to retain the most representative feature information.

[0010] Furthermore, selective search is used to generate multiple candidate boxes containing features in the image data, and each candidate box is classified by the random forest algorithm to determine whether it contains the detection feature. If it contains the detection feature, feature tracking is submitted; if it does not contain the detection feature, the candidate box is regenerated for classification and judgment. The specific steps of training the random forest model are: by constructing a tree structure, a decision tree is constructed using internal nodes to represent features and leaf nodes to represent decision results, and multiple decision trees are constructed by randomly selecting features and samples and the results are intersected to determine whether the detection feature is contained.

[0011] Furthermore, feature tracking updates the target area, shape and position through feature matching, and estimates the state information of the feature, which is used to identify and track the actual value of the misalignment of the clamps at the same end of the upper and lower shock absorbers in the train anti-snaking shock absorber.

[0012] In a preferred embodiment, in S103, the standard value of the misalignment of the clamps at the same end of the upper and lower shock absorbers in the train anti-snaking shock absorbers is set to be less than 50 mm, and the actual value of the misalignment of the clamps at the same end of the upper and lower shock absorbers in the train anti-snaking shock absorbers is identified and tracked for comparison to determine whether there is looseness and abnormal conditions. When the actual value is less than or equal to 50 mm, it is determined that the misalignment of the clamps at the same end of the upper and lower shock absorbers in the train anti-snaking shock absorbers is normal. When the actual value is greater than 50 mm, it is determined that the misalignment of the clamps at the same end of the upper and lower shock absorbers in the train anti-snaking shock absorbers is loose. When there are spots in the image data of the train anti-snaking shock absorbers, it is determined that the misalignment of the clamps at the same end of the upper and lower shock absorbers in the train anti-snaking shock absorbers is abnormal.

[0013] In a preferred embodiment, in S104, the train anti-snaking shock absorber image data and the judgment data are scaled so that their value range falls within the range of [-1, 1] centered on 0, and the train anti-snaking shock absorber image data and the judgment data are converted into a standard normal distribution with zero mean and unit standard deviation using a Z-score algorithm, and the specific formula is:

[0014] in represents the standardized value, represents the value before normalization, represents the mean before standardization, It represents the standard deviation before normalization. The train anti-snaking shock absorber image data and judgment data are selectively stored in the cloud and the local database. The cloud storage has redundancy and backup mechanisms. The local database allows complete control of the train anti-snaking shock absorber image data and judgment data, including storage structure, backup strategy and data migration. The database table structure is designed, in which each table corresponds to a data entity and subject. One table is used to store the train anti-snaking shock absorber image data, and the other table is used to store the corresponding judgment data. The corresponding table is created in the selected database management system to realize data storage management.

[0015] In a preferred embodiment, in S105, an API interface is used to connect to a selected database and the train anti-snaking shock absorber image data of the judged situation is marked and displayed through a visual interface, wherein normal conditions are marked in green, loose conditions are marked in yellow, and abnormal conditions are marked in red. An alarm notification is sent to the train management staff according to the degree of the looseness and abnormality, and detailed information on the looseness and abnormality in the selected database is sent together.

[0016] The beneficial effects of the present invention are as follows: by installing a camera, real-time monitoring of the anti-snaking shock absorber of the train can be achieved; a mean filter is used to remove noise in the image to effectively improve the image quality; by enhancing brightness differences, scaling the brightness range, and stretching the grayscale level, the overall image and contrast are changed to make the image more consistent with visual features; edge detection, corner detection, and spot detection help to perform more detailed analysis and recognition of the anti-snaking shock absorber image of the train; random forest decision-making is used to improve the accuracy and robustness of target features; feature tracking helps to accurately identify and track the misalignment in the anti-snaking shock absorber of the train; Z-score standardization helps to unify the scale of stored data; selected storage cloud and local databases are used to ensure data security and reliability, improve data accessibility and operability; the selected database is connected through an API interface; and the image data of the anti-snaking shock absorber of the train is marked and displayed through a visual interface, which can realize real-time monitoring and visual and intuitive display of the train status, and take emergency measures to ensure the safety of the train and passengers. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 is a flow chart of the method of the present invention; DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0019] In the description of this application, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, "plurality" means two or more, unless otherwise clearly and specifically defined.

[0020] In the description of the present application, the term "for example" is used to mean "used as an example, illustration or description". Any embodiment described as "for example" in the present application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any technician in the field to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid unnecessary details to obscure the description of the present invention. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present application.

[0021] This embodiment provides Figure 1 A method for identifying loose installation of a train anti-snaking shock absorber is shown, which specifically includes the following steps: S101: installing a camera to obtain train anti-snaking shock absorber image data, taking one of the pixel points as the center to remove noise, and changing the overall image data and contrast of the train anti-snaking shock absorber image data by enhancing brightness difference, scaling brightness range, and stretching grayscale levels; Furthermore, a camera is installed at the position of the train's anti-snaking shock absorber to obtain image data of the train's anti-snaking shock absorber. The camera is fixed to the train using a camera bracket to ensure that the camera withstands the vibration of the train's operation and to adjust the camera angle and focal length for optimization.

[0022] Furthermore, a pixel point in the train anti-snaking shock absorber image data is taken as the center, and the pixel points around the center pixel point are averaged using a mean filter to remove the noise in the train anti-snaking shock absorber image data. The specific formula is:

[0023] in Indicates the position on the image after mean filtering The new pixel value at represents the size of the filter, represents the position of each pixel in the filter, Representing each position of the filter on the image, the contrast of the train anti-snaking damper image data is enhanced by increasing the brightness difference of different regions in the train anti-snaking damper image data, and the overall contrast of the train anti-snaking damper image data is changed by scaling the brightness range and stretching the grayscale level.

[0024] S102: locating the object boundary by the region where the gradient of the pixel gray value in the train anti-snaking shock absorber image data changes dramatically to perform edge detection and corner point detection, performing spot detection by using the converted binary image data, classifying and determining the detection features of each candidate frame by using the random forest algorithm, and performing feature tracking; Furthermore, the object boundary is located through the area where the gradient of pixel grayscale values ​​in the train anti-snaking shock absorber image data changes drastically, which is used for edge detection and corner detection of the train anti-snaking shock absorber image data. The train anti-snaking shock absorber image data is converted into binary image data, and the spots in the train anti-snaking shock absorber image data are changed to black and the background is changed to white. The connected domain is defined using the 16-connectivity method, and the feature information of the area, shape and position of the spots in the binary image data is obtained by the area composed of adjacent pixels with the same pixel value. The features obtained by edge detection, corner detection and spot detection are selected, and redundant features are excluded to retain the most representative feature information.

[0025] Furthermore, selective search is used to generate multiple candidate boxes containing features in the image data, and each candidate box is classified by the random forest algorithm to determine whether it contains the detection feature. If it contains the detection feature, feature tracking is submitted; if it does not contain the detection feature, the candidate box is regenerated for classification and judgment. The specific steps of training the random forest model are: by constructing a tree structure, a decision tree is constructed using internal nodes to represent features and leaf nodes to represent decision results, and multiple decision trees are constructed by randomly selecting features and samples and the results are intersected to determine whether the detection feature is contained.

[0026] Furthermore, feature tracking updates the target area, shape and position through feature matching, and estimates the state information of the feature, which is used to identify and track the actual value of the misalignment of the clamps at the same end of the upper and lower shock absorbers in the train anti-snaking shock absorber.

[0027] S103: setting a standard value of the misalignment of the clamps at the same end of the upper and lower shock absorbers in the train anti-snaking shock absorber, and comparing the actual values ​​of the misalignment of the clamps at the same end of the upper and lower shock absorbers in the train anti-snaking shock absorber identified and tracked to determine whether there is looseness or abnormality; Furthermore, the standard value of the misalignment of the clamps at the same end of the upper and lower shock absorbers in the train anti-snaking shock absorbers is set to be less than 50mm, and the actual value of the misalignment of the clamps at the same end of the upper and lower shock absorbers in the train anti-snaking shock absorbers is identified and tracked for comparison, so as to determine whether there is looseness and abnormality. When the actual value is less than or equal to 50mm, it is determined that the misalignment of the clamps at the same end of the upper and lower shock absorbers in the train anti-snaking shock absorbers is normal; when the actual value is greater than 50mm, it is determined that the misalignment of the clamps at the same end of the upper and lower shock absorbers in the train anti-snaking shock absorbers is loose; when there are spots in the image data of the train anti-snaking shock absorbers, it is determined that the misalignment of the clamps at the same end of the upper and lower shock absorbers in the train anti-snaking shock absorbers is abnormal.

[0028] S104: using a Z-score algorithm to convert the train anti-snaking shock absorber image data and the judgment situation data into a standard normal distribution with a zero mean and a unit standard deviation, and selectively storing them in a cloud and a local database, and creating a corresponding table in the selected database management system to implement data storage management; Furthermore, the train anti-snaking shock absorber image data and judgment data are scaled so that their value range falls within the range of [-1,1] centered on 0, and the Z-score algorithm is used to convert the train anti-snaking shock absorber image data and judgment data into a standard normal distribution with zero mean and unit standard deviation. The specific formula is:

[0029] in represents the standardized value, represents the value before normalization, represents the mean before standardization, It represents the standard deviation before normalization. The train anti-snaking shock absorber image data and judgment data are selectively stored in the cloud and the local database. The cloud storage has redundancy and backup mechanisms. The local database allows complete control of the train anti-snaking shock absorber image data and judgment data, including storage structure, backup strategy and data migration. The database table structure is designed, in which each table corresponds to a data entity and subject. One table is used to store the train anti-snaking shock absorber image data, and the other table is used to store the corresponding judgment data. The corresponding table is created in the selected database management system to realize data storage management.

[0030] S105: using the API interface to connect to the selected database and marking and displaying the image data of the train anti-snaking shock absorber of the determined situation through the visual interface, and sending an alarm notification to the train management staff according to the degree of looseness and abnormality; Furthermore, the API interface is used to connect to the selected database and mark and display the train anti-snaking shock absorber image data through a visual interface, where normal conditions are marked in green, loose conditions are marked in yellow, and abnormal conditions are marked in red. Alarm notifications are sent to train management staff based on the degree of looseness and abnormality, and detailed information on the looseness and abnormality in the selected database is sent together.

[0031] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0032] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0033] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0034] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0035] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0036] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0037] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A method for identifying loose installation of train anti-snaking shock absorbers, characterized in that: The specific steps include: S101: installing a camera to obtain train anti-snaking shock absorber image data, taking one of the pixel points as the center to remove noise, and changing the overall image data and contrast of the train anti-snaking shock absorber image data by enhancing brightness difference, scaling brightness range, and stretching grayscale levels; S102: locating the object boundary by the region where the gradient of the pixel gray value in the train anti-snaking shock absorber image data changes dramatically to perform edge detection and corner point detection, performing spot detection by using the converted binary image data, classifying and determining the detection features of each candidate frame by using the random forest algorithm, and performing feature tracking; S103: setting a standard value of the misalignment of the clamps at the same end of the upper and lower shock absorbers in the train anti-snaking shock absorber, and comparing the actual values ​​of the misalignment of the clamps at the same end of the upper and lower shock absorbers in the train anti-snaking shock absorber identified and tracked to determine whether there is looseness or abnormality; S104: using a Z-score algorithm to convert the train anti-snaking shock absorber image data and the judgment situation data into a standard normal distribution with a zero mean and a unit standard deviation, and selectively storing them in a cloud and a local database, and creating a corresponding table in the selected database management system to implement data storage management; S105: Use the API interface to connect to the selected database and mark and display the train anti-snaking shock absorber image data of the determined situation through the visual interface, and send an alarm notification to the train management staff according to the degree of looseness and abnormality.

2. A method for identifying loose installation of a train anti-snaking shock absorber according to claim 1, characterized in that: In the S101, a camera is installed at the position of the train anti-snaking shock absorber to obtain the train anti-snaking shock absorber image data, the camera is fixed on the train by a camera bracket to ensure that the camera withstands the vibration of the train operation, the camera angle and focal length are adjusted to be optimized, a pixel point in the train anti-snaking shock absorber image data is taken as the center, and the pixel points around the center pixel point are averaged by a mean filter to remove the noise existing in the train anti-snaking shock absorber image data, the contrast of the train anti-snaking shock absorber image data is enhanced by increasing the brightness difference of different areas in the train anti-snaking shock absorber image data, and the overall and contrast of the train anti-snaking shock absorber image data are changed by scaling the brightness range and stretching the grayscale level.

3. A method for identifying loose installation of a train anti-snaking shock absorber according to claim 2, characterized in that: The specific formula of the mean filter is: ,in Indicates the position on the image after mean filtering The new pixel value at represents the size of the filter, represents the position of each pixel in the filter, represents each position of the filter on the image.

4. A method for identifying loose installation of a train anti-snaking shock absorber according to claim 1, characterized in that: In the S102, the object boundary is located through the area where the gradient of the pixel grayscale value in the train anti-snaking shock absorber image data changes dramatically, which is used for edge detection and corner point detection of the train anti-snaking shock absorber image data, the train anti-snaking shock absorber image data is converted into binary image data, the spots in the train anti-snaking shock absorber image data are changed to black, and the background is changed to white, the connected domain is defined by the 16-connected method, and the feature information of the area, shape and position of the spots is obtained in the area composed of adjacent pixels with the same pixel value in the binary image data, the features obtained by edge detection, corner point detection and spot detection description are selected, and redundant features are excluded, and the most representative feature information is retained, and a plurality of candidate boxes containing features are generated in the image data by selective search, and each candidate box is classified by the random forest algorithm to determine whether it contains the detection feature, and the feature tracking updates the target area, shape and position through feature matching, and estimates the state information of the feature, which is used to identify and track the actual value of the misalignment of the clamp at the same end of the upper and lower shock absorbers in the train anti-snaking shock absorber.

5. A method for identifying loose installation of a train anti-snaking shock absorber according to claim 4, characterized in that: The specific steps of random forest model training are: by constructing a tree structure, using internal nodes to represent features and leaf nodes to represent decision results to construct a decision tree, by randomly selecting features and samples to construct multiple decision trees and intersecting the results, to determine whether the detection feature is included.

6. A method for identifying loose installation of a train anti-snaking shock absorber according to claim 1, characterized in that: In S103, the standard value of the misalignment of the clamps at the same end of the upper and lower shock absorbers in the train anti-snaking shock absorber is set to be less than 50 mm, and the actual value of the misalignment of the clamps at the same end of the upper and lower shock absorbers in the train anti-snaking shock absorber is identified and tracked for comparison to determine whether there is looseness and abnormality.

7. A method for identifying loose installation of a train anti-snaking shock absorber according to claim 6, characterized in that: When the actual value is less than or equal to 50mm, it is judged that the misalignment of the clamps at the same end of the upper and lower shock absorbers in the train anti-snaking shock absorber is normal. When the actual value is greater than 50mm, it is judged that the misalignment of the clamps at the same end of the upper and lower shock absorbers in the train anti-snaking shock absorber is loose. When there are spots in the image data of the train anti-snaking shock absorber, it is judged that the misalignment of the clamps at the same end of the upper and lower shock absorbers in the train anti-snaking shock absorber is abnormal.

8. The method for identifying loose installation of a train anti-snaking shock absorber according to claim 1, characterized in that: In S104, the train anti-snaking shock absorber image data and the judgment data are scaled so that their value range falls within the range of [-1,1] centered on 0, and the train anti-snaking shock absorber image data and the judgment data are converted into a standard normal distribution with zero mean and unit standard deviation using the Z-score algorithm, and the specific formula is: ,in represents the standardized value, represents the value before normalization, represents the mean before standardization, It represents the standard deviation before normalization. The train anti-snaking shock absorber image data and judgment situation data are selectively stored in the cloud and local database.

9. A method for identifying loose installation of a train anti-snaking shock absorber according to claim 8, characterized in that: The cloud storage has redundancy and backup mechanisms, and the local database allows complete control of the train anti-snaking shock absorber image data and judgment situation data, including storage structure, backup strategy and data migration. The database table structure is designed, in which each table corresponds to a data entity and subject, one table is used to store the train anti-snaking shock absorber image data, and another table is used to store the corresponding judgment situation data. The corresponding table is created in the selected database management system to realize data storage management.

10. A method for identifying loose installation of a train anti-snaking shock absorber according to claim 1, characterized in that: In the S105, the API interface is used to connect to the selected database and the train anti-snaking shock absorber image data of the judged situation is marked and displayed through the visual interface, wherein the normal situation is marked with green, the loose situation is marked with yellow, and the abnormal situation is marked with red. According to the degree of the looseness and abnormality, an alarm notification is sent to the train management staff, and the detailed information of the looseness and abnormality in the selected database is sent together.

Images