A method for detecting and identifying key dimensions of a multi-configuration brake lever

Abstract

The present application belongs to the technical field of railway vehicle brake lever maintenance, and particularly relates to a method for detecting and identifying key dimensions of multi-configuration brake levers, comprising the following steps: creating a first-level type template of brake levers; processing collected image data; comparing key dimension data with standard library data to detect the limit of brake lever dimensions and identify the type. The present application designs a three-level brake lever data model, which covers all multi-configuration brake levers. The first-level brake lever data model is divided according to the external contour information of brake levers, the second-level brake lever data model is divided according to the roundness of round holes in the first-level data model, and the third-level brake lever data model is divided according to the number of round holes in the second-level data model. The present application can detect and identify levers of different types and specifications using the same set of devices and algorithms.

Description

Technical Field

[0001] This invention belongs to the field of railway vehicle brake lever maintenance technology, specifically relating to a method for detecting and identifying key dimensions of multi-configuration brake levers. Background Technology

[0002] The brake lever is a crucial component of the railway freight car braking system. Its size and proper installation significantly impact the vehicle's braking force, making it a key part of the basic braking system for railway vehicles. A malfunctioning braking system directly affects the vehicle's braking performance, posing serious safety hazards during operation. Therefore, the stability and reliability of the braking system must be given high priority.

[0003] Currently, the accuracy and consistency of the round pin hole measuring gauge and brake lever hole spacing calibration ruler used in factory and section maintenance depend entirely on the subjective judgment of the maintenance personnel. If maintenance personnel make mistakes in measuring the key assembly dimensions of the brake lever or fail to match the correct brake lever type, resulting in incorrect or misinstalled brake levers, it will directly lead to a change in the braking ratio, thus posing a significant threat to the safety of railway train operations. Summary of the Invention

[0004] In response to the technical problem that the accuracy and consistency of the round pin hole inspection gauge and brake lever hole distance calibration ruler currently used in factory repair and maintenance depend on the subjective judgment of maintenance personnel, this invention provides a method for detecting and identifying key dimensions of multi-configuration brake levers.

[0005] To solve the above-mentioned technical problems, the technical solution adopted by the present invention is as follows:

[0006] A method for detecting and identifying key dimensions of multi-configuration brake levers includes the following steps:

[0007] S1. Create a primary type template for brake levers;

[0008] S2, Process the acquired image data;

[0009] S3. Compare the key dimension data with the standard library data to perform limit detection and type identification of the brake lever dimensions.

[0010] The method for creating a primary type template for a brake lever in S1 includes the following steps:

[0011] S1.1 Obtaining the region of interest based on image correlation: Dividing the region of interest can reduce the amount of computation on image data by the host computer and improve detection and recognition efficiency;

[0012] S1.2 Creating connected regions: Region information processing includes grayscale values, area values, row information, and column information, making the feature points of the processed image more obvious;

[0013] S1.3 Separate Connected Regions: Connected regions include the selection of brake lever feature regions, which need to be separated from the original graphic as separate regions;

[0014] S1.4 Check template parameters: Establish a multi-level pyramid model to adapt to the matching of brake lever levels with multiple angles and sizes;

[0015] S1.5 Create a shape-based brake lever primary type template, and generate and save the template file.

[0016] The formula for calculating the pyramid levels in S1.4 is as follows:

[0017] n=log2{min(M,N)―t,t∈[0,log2{min(M,N)}}

[0018] Where M and N are the original dimensions of the image, and t is the logarithm of the minimum dimension of the tower top image.

[0019] The method for processing the acquired image data in S2 includes the following steps:

[0020] S2.1. Use shape matching operators to perform shape template matching;

[0021] S2.2 Select the circular hole area: Select the circular hole area of ​​the brake lever based on the grayscale area;

[0022] S2.3 Calculate the roundness of the lever bushing hole: Based on the obtained height and width dimensions of the hole, use the height-to-width ratio calculation result as the roundness of the bushing hole, and match the secondary type of the brake lever according to this roundness;

[0023] S2.4 Draw the minimum circumscribed circle of the bushing hole: Drawing the minimum circumscribed circle can provide information on the center position of the bushing hole;

[0024] S2.5 Count the minimum number of circumscribed circles of the bushing hole: Match the three-stage brake lever type according to the number of circumscribed circles;

[0025] S2.6, Call the caliper circle finding program segment: Use an appropriate number and length of calipers to obtain the edge information of the bushing hole within the range of the circumscribed circle, and fit it as the bushing hole contour;

[0026] S2.7 Critical Dimension Measurement: Based on the three types of brake levers and the order of the round holes, measure the diameter and spacing of the required bushing holes.

[0027] The formula for calculating roundness in S2.3 is as follows:

[0028] K = (4 × π × A) / P 2

[0029] Where K is the roundness, A is the area of ​​the hole image, and P is the perimeter of the hole image.

[0030] The method for finding circles using calipers in S2.6 is as follows: calculate the average gray value along the slicing direction for each rectangular ROI of the calipers; perform Gaussian filtering on the average gray value; and extract edge points according to the set parameters.

[0031] The method for limit detection and type identification of the brake lever size in S3 is as follows:

[0032] Combine the key dimensions obtained from the standard database into a row vector. That is, the feature vectors of standard size, and then the key dimensions obtained from the detection results are used to form row vectors. The probability of a match is measured by calculating the angle between two vectors.

[0033]

[0034] By iterating through the standard dimension vectors and sorting the test results, the minimum value of the vector is taken, which indicates that the test result is closest to the standard dimension, thereby obtaining the type and standard dimension of the standard brake lever corresponding to the brake lever under test.

[0035] Based on the standard dimensions obtained above, the absolute value of the difference between the measured value and the standard value is taken and compared with the limit value specified in the relevant regulations. If it is less than the limit value, it means that the lever under test is qualified; if it is greater than the limit value, it means that the lever under test is unqualified.

[0036] Compared with the prior art, the beneficial effects of this invention are:

[0037] This invention designs a three-level brake lever data model, which covers all multi-configuration brake levers. The first-level brake lever data model is divided according to the external contour information of the brake lever; the second-level brake lever data model is divided according to the roundness of the holes within its respective first-level data model; and the third-level brake lever data model is divided according to the number of holes within the second-level data model. This invention uses the same set of devices and algorithms to detect and identify levers of different types and specifications. It solves the problems of poor consistency, low accuracy, and low detection efficiency in the manual inspection of key assembly dimensions of brake levers of different models and types of railway vehicles. Attached Figure Description

[0038] To more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings in the following description are merely exemplary, and those skilled in the art can derive other embodiments based on the provided drawings without creative effort.

[0039] The structures, proportions, sizes, etc. illustrated in this specification are only for the purpose of assisting those skilled in the art in understanding and reading the content disclosed herein, and are not intended to limit the conditions under which the present invention can be implemented. Therefore, they have no substantial technical significance. Any modifications to the structure, changes in the proportions, or adjustments to the size, without affecting the effects and objectives that the present invention can produce, should still fall within the scope of the technical content disclosed in the present invention.

[0040] Figure 1 This is a flowchart of the key dimension detection and identification process for the multi-configuration brake lever of the present invention. Detailed Implementation

[0041] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. These descriptions are only for further illustrating the features and advantages of the present invention, and not for limiting the claims of the present invention. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0042] The specific embodiments of the present invention will be described in further detail below with reference to the accompanying drawings and examples. The following examples are for illustrative purposes only and are not intended to limit the scope of the invention.

[0043] Railway vehicle brake levers mainly consist of movable levers, fixed levers, front levers of the brake cylinder, rear levers of the brake cylinder, tie rods, and control levers, which are collectively referred to as multi-configuration brake levers in this invention. The dimensions and angles of each brake lever vary depending on the vehicle model or bogie.

[0044] Due to the large variety of multi-configuration brake levers, this embodiment designs a three-level brake lever data model, which covers all multi-configuration brake levers. The first-level brake lever data model is divided according to the external contour information of the brake lever; the second-level brake lever data model is divided according to the roundness of the holes within its respective first-level data model; and the third-level brake lever data model is divided according to the number of holes within its second-level data model. For example... Figure 1The diagram illustrates the critical dimension detection and identification process for multi-configuration brake levers. This embodiment includes the following steps:

[0045] Step 1: Create a brake lever type template. The image templates at this level require the following steps to be created:

[0046] Step 1.1: Obtain the region of interest based on image correlation: Dividing the region of interest can reduce the amount of computation required by the host computer for image data and improve detection and recognition efficiency.

[0047] Step 1.2: Create connected regions: Region information processing includes grayscale values, area values, row information, and column information. The processed image feature points are more obvious.

[0048] Step 1.3: Separate connected regions: Connected regions include the selection of brake lever feature regions, which need to be separated from the original graphic as separate regions.

[0049] Step 1.4: Check template parameters: Establish a multi-level pyramid model to accommodate brake levers of various angles and sizes. The formula for calculating the pyramid levels is as follows:

[0050] n=log2{min(M,N)―t,t∈[0,log2{min(M,N)}}

[0051] In the formula, M and N are the original dimensions of the image, and t is the logarithm of the minimum dimension of the tower top image.

[0052] Step 1.5: Create a shape-based brake lever primary type template, and generate and save the template file.

[0053] Step 2: Process the acquired image data. The image data processing at this level involves the following steps:

[0054] Step 2.1: Process the newly acquired image and use the shape matching operator to perform shape template matching.

[0055] Step 2.2: Select the circular hole area: Select the circular hole area of ​​the brake lever based on the grayscale area.

[0056] Step 2.3: Calculate the roundness of the lever bushing hole: Based on the obtained height and width dimensions of the hole, the height-to-width ratio is calculated as the roundness of the bushing hole. Based on this roundness, the secondary type of the brake lever is matched. This step calculates the roundness of the bushing hole because when a multi-configuration lever is photographed from above, the roundness of the hole with the angled portion differs from that of the round hole in the planar portion. The formula for calculating roundness (K) is:

[0057] K = (4 × π × A) / P 2

[0058] Where K is the roundness, A is the area of ​​the hole image, and P is the perimeter of the hole image.

[0059] Step 2.4: Draw the minimum circumscribed circle of the bushing hole: Drawing the minimum circumscribed circle can provide information on the center position of the bushing hole.

[0060] Step 2.5: Count the minimum number of circumscribed circles of the bushing hole: Match the three-level type of brake lever according to the number of circumscribed circles.

[0061] Step 2.6: Call the caliper circle finding program segment: Use an appropriate number and length of calipers to obtain the edge information of the bushing hole within the range of the circumscribed circle, and fit it as the bushing hole contour.

[0062] Step 2.7, Key Dimension Measurement: Based on the three types of brake levers and the order of the round holes, measure the diameter and spacing of the required bushing holes.

[0063] The method for finding circles using calipers is as follows: Calculate the average grayscale value along the slicing direction for each rectangular region of interest (ROI) using the calipers. Apply a Gaussian filter to the average grayscale value. Extract edge points based on the set parameters.

[0064] Step 3: Brake Lever Size Limit Detection and Type Identification. Step 2 involved measuring key dimensions of the acquired visual images. Since the brake lever type is unknown, this step requires comparing this key dimension data with data from a standard library to perform limit detection and type identification of the brake lever size. The algorithm used in this step is as follows:

[0065] Combine the key dimensions obtained from the standard database into a row vector. That is, the feature vectors of standard size, and then the key dimensions obtained from the detection results are used to form row vectors. The probability of a match is measured by calculating the angle between two vectors, as shown below.

[0066]

[0067] By iterating through the standard dimension vectors and sorting the test results, the minimum value of the vector is taken, which indicates that the test result is closest to the standard dimension. This allows us to obtain the type and standard dimension of the standard brake lever corresponding to the brake lever under test.

[0068] Based on the standard dimensions obtained above, the absolute value of the difference between the measured value and the standard value is taken and compared with the limit value specified in the relevant regulations. If it is less than the limit value, it means that the lever under test is qualified; if it is greater than the limit value, it means that the lever under test is unqualified.

[0069] The above description only details the preferred embodiments of the present invention. However, the present invention is not limited to the above embodiments. Within the scope of knowledge possessed by those skilled in the art, various changes can be made without departing from the spirit of the present invention, and all such changes should be included within the protection scope of the present invention.

Claims

1. A method for detecting and identifying key dimensions of multi-configuration brake levers, characterized in that, Includes the following steps: S1. Create a primary type template for brake levers: S1.1 Obtaining the region of interest based on image correlation: Dividing the region of interest can reduce the amount of computation on image data by the host computer and improve detection and recognition efficiency; S1.2 Creating connected regions: Region information processing includes grayscale values, area values, row information, and column information, making the feature points of the processed image more obvious; S1.3 Separate Connected Regions: Connected regions include the selection of brake lever feature regions, which need to be separated from the original graphic as separate regions; S1.4 Check template parameters: Establish a multi-level pyramid model to adapt to the matching of brake lever levels with multiple angles and sizes; S1.5 Create a shape-based brake lever primary type template, and generate and save the template file; S2. Process the acquired image data: S2.

1. Use shape matching operators to perform shape template matching; S2.2 Select the circular hole area: Select the circular hole area of ​​the brake lever based on the grayscale area; S2.3 Calculate the roundness of the lever bushing hole: Based on the obtained height and width dimensions of the hole, use the height-to-width ratio calculation result as the roundness of the bushing hole, and match the secondary type of the brake lever according to this roundness; S2.4 Draw the minimum circumscribed circle of the bushing hole: Drawing the minimum circumscribed circle can provide information on the center position of the bushing hole; S2.5 Count the minimum number of circumscribed circles of the bushing hole: Match the three-stage brake lever type according to the number of circumscribed circles; S2.6, Call the caliper circle finding program segment: Use an appropriate number and length of calipers to obtain the edge information of the bushing hole within the range of the circumscribed circle, and fit it as the bushing hole contour; S2.7 Critical Dimension Measurement: Based on the three types of brake levers and the order of the round holes, measure the diameter and spacing of the required bushing holes; S3. Compare the key dimension data with the standard library data to perform limit detection and type identification on the brake lever dimensions: Combine the key dimensions obtained from the standard database into a row vector. That is, the feature vector of standard size, and then the key dimensions obtained from the detection results are used to form a row vector. The probability of a match is measured by calculating the angle between two vectors. The test results are used to iterate through the angles between standard size vectors and sort them. The minimum value of the vector is taken, which means that the test result is closest to the standard size. In this way, the type and standard size of the standard brake lever corresponding to the brake lever to be tested can be obtained. Based on the standard dimensions obtained above, the absolute value of the difference between the measured value and the standard value is taken and compared with the limit value specified in the relevant regulations. If it is less than the limit value, it means that the lever under test is qualified; if it is greater than the limit value, it means that the lever under test is unqualified.

2. The method for detecting and identifying key dimensions of a multi-configuration brake lever according to claim 1, characterized in that, The formula for calculating the pyramid levels in S1.4 is as follows: Where M and N are the original dimensions of the image, and t is the logarithm of the minimum dimension of the tower top image.

3. The method for detecting and identifying key dimensions of a multi-configuration brake lever according to claim 1, characterized in that, The formula for calculating roundness in S2.3 is as follows: in, Let A be the roundness, A be the area of ​​the hole image, and P be the perimeter of the hole image.

4. The method for detecting and identifying key dimensions of a multi-configuration brake lever according to claim 1, characterized in that, The method for finding circles using calipers in S2.6 is as follows: calculate the average gray value along the slicing direction for each rectangular ROI of the calipers; perform Gaussian filtering on the average gray value; and extract edge points according to the set parameters.

Images