A monorail track defect detection system and method

Abstract

The application discloses a monorail track defect detection system and method, and relates to the track detection technical field.The system comprises a vehicle selection module, a data acquisition module, a data judgment module, a secondary acquisition module and a defect division module.The vehicle selection module is used for acquiring vehicle trial operation data, and comparing the trial operation data with a standard threshold interval to judge whether the vehicle meets the requirements.The technical points are as follows: the vehicle is detected before detection, the benchmark of the detection is used as the benchmark for judging whether defects exist on the monorail track, the subsequent judgment of defects is more accurate, small defects can be identified, the defect position is further acquired and analyzed, the content and grade of the defects are analyzed, the corresponding defect repair plan can be formulated according to the defect grade, the data amount processed in the whole process is small, the defect position can be analyzed in real time, and the system has a good application prospect.

Description

Technical Field

[0001] This invention relates to the field of track inspection technology, specifically to a defect detection system and method for monorail tracks. Background Technology

[0002] A monorail system is a system in which a specially made I-beam is suspended above the tunnel as a track, and various types of suspended vehicles are connected together to form a train set, which is pulled along the track by traction equipment.

[0003] The monorail uses a specially made I-beam suspended above the tunnel as its track.

[0004] Monorail locomotives are a new type of auxiliary transportation equipment in mines. They overcome the shortcomings of overhead electric locomotives and battery locomotives in that they lack the ability to climb slopes, thus enabling long-distance continuous transportation and reducing transportation links. Monorail locomotives also have the advantages of high operating speed and fewer personnel required, which not only improves transportation efficiency but also reduces labor costs, making them widely used in underground mines.

[0005] Underground transportation using monorails is characterized by complex environments, confined spaces, and insufficient lighting. Traditional manually operated monorails face numerous uncertainties, making them a major source of mine transportation accidents. Monorail accidents have a wide range of hazards and require lengthy repair times. Therefore, to reduce the accident rate and minimize property damage, it is necessary to implement technical measures to reduce and curb monorail accidents. The most direct way to do this is to ensure that the monorail track is in normal condition.

[0006] An existing invention patent with publication number CN114740086A, entitled "A Method for Detecting Defects in a Monorail," describes the hardware primarily used, including ultrasonic sensors, RFID modules, Wi-Fi signal transmission modules, and image acquisition modules. The monorail track defect inspection method includes data statistics and periodic inspections, sensor data processing and analysis, cumulative comparison, and defect location. This solution utilizes a monorail crane as its power source to move along the track, carrying ultrasonic sensors, RFID modules, Wi-Fi signal transmission modules, and image acquisition modules. It develops a track parameter identification and detection system capable of detecting track parameters (Y-axis and Z-axis misalignment, straightness) and locating defects. It also designs a host computer interface that can display track video information and detection results in real time, enabling autonomous detection of track misalignment defects and straightness.

[0007] However, based on the above content and existing technology, the central solution of the above-described patent is mainly used to detect the breakage of the monorail track joint and the deformation of the track. In the detection process, it mainly relies on collecting detailed data of the track over a large area, and then performing detailed analysis on the collected data to determine whether there is deformation or breakage at the joint of the entire monorail track.

[0008] However, the above-mentioned solutions have significant drawbacks in practical use. Firstly, the analysis mainly relies on the outer contour to determine whether the monorail track joint is broken and whether the track is deformed. This method is suitable for situations with large deformation and obvious breakage at the joint. It is difficult to detect minor local deformations of the monorail track (track wear and local protrusions) (the wheels of the crane contact the side of the I-beam during operation, and the structure of the I-beam itself provides some obstruction). Therefore, when defects are detected in the monorail track, the condition is often quite serious, requiring a lot of time to handle and posing certain risks. This does not meet the requirements of users. To address this, we have developed a defect detection system and method for monorail tracks. Summary of the Invention

[0009] (a) Technical problems to be solved

[0010] To address the shortcomings of existing technologies, this invention provides a defect detection system and method for monorail tracks. Before inspection, the vehicle is inspected, and the baseline from this inspection is used as the benchmark for subsequent evaluation of the presence of defects on the monorail track. This makes the subsequent defect assessment more accurate, enabling the identification of smaller defects. Further data collection and analysis of the defect location, including the content and severity of the defect, facilitates the development of corresponding defect repair plans based on the defect severity level. The entire process does not require comprehensive analysis of the entire monorail track, resulting in a small amount of data processing. It can analyze defect locations in real time, effectively solving the problem of existing monorail track systems where data collection takes a considerable amount of time to produce results, causing the monorail track to be unusable for a period of time and resulting in low effectiveness. Overall, the system offers good performance and has promising application prospects.

[0011] (II) Technical Solution

[0012] To achieve the above objectives, the present invention provides the following technical solution:

[0013] A defect detection system for monorail tracks includes a vehicle selection module, a data acquisition module, a data judgment module, a secondary acquisition module, and a defect classification module.

[0014] Vehicle selection module: used to acquire vehicle trial run data, compare the trial run data with standard threshold ranges to determine whether the vehicle meets the requirements, select the vehicle for testing if it meets the requirements, and calculate the vehicle's average parameters;

[0015] Data acquisition module: used to acquire in real time the parameters of the inspection vehicle running on the monorail track and the track data captured by the explosion-proof camera on the vehicle.

[0016] Data judgment module: Used to receive data collected by the data acquisition module, analyze the collected data, and determine whether there are major defects or ordinary defects in the monorail track;

[0017] Secondary acquisition module: used to receive the presence of a common defect signal, and to start the common defect data acquisition device to collect data on the defect location when the common defect signal is received;

[0018] Defect Classification Module: This module analyzes the data of defect locations, determines the defect type, calculates the defect level based on the defect type, defect data, and the operating parameters of the vehicle being inspected, obtains the defect location, marks the defect level at the defect location, generates a defect drawing, and activates the warning device at the defect location based on the defect level.

[0019] Furthermore, the vehicle test run data includes the stability index of the vehicle running at a constant speed for 50 meters on a horizontal monorail. The vehicle test run data is collected by vibration sensors installed on the vehicle, with the vibration sensor collection time period set to 0.05 seconds. The average parameters of the vehicle are the vehicle stability index parameters.

[0020] The parameters for testing the vehicle's operation on the monorail are stability indicators generated by the vehicle's uniform motion on the monorail, and the track data captured by the onboard explosion-proof camera are image data captured by the vehicle during operation.

[0021] The location of the defect is sent via a positioning device on the inspection vehicle.

[0022] Further steps to determine whether a vehicle meets the requirements are as follows:

[0023] The stability index of the vehicle during the first 10 meters and the last 10 meters of its operation on the horizontal monorail is removed. The first 10 meters and the last 10 meters involve the acceleration and deceleration of the vehicle, which will cause changes in the vibration data. Therefore, it needs to be removed. After removal, the overall data is more accurate.

[0024] Obtain the maximum value of the stability index of the vehicle during its uniform 30-meter journey on a horizontal monorail track;

[0025] Determine whether the maximum value is within the standard threshold range. If the maximum value is within the standard threshold range, the vehicle meets the inspection requirements. If the maximum value is outside the standard threshold range, the vehicle does not meet the inspection requirements.

[0026] The formula for calculating the vehicle stability index parameters is as follows:

[0027]

[0028] In the formula, These are parameters related to vehicle stability. This refers to the number of stability indicators collected during a 30-meter uniform motion. Let be the i-th stationarity index.

[0029] Further analysis of the track data captured by the vehicle's onboard explosion-proof camera to determine whether there are major defects in the monorail track follows these steps:

[0030] S1 acquires images taken by the vehicle's onboard explosion-proof camera and then crops the images.

[0031] S2 converts the cropped image to grayscale, and then performs Gaussian filtering on the grayscale image;

[0032] S3 calculates the average difference between the gray values ​​of a pixel and its four adjacent pixels (top, bottom, left, and right) in the image after Gaussian filtering.

[0033] S4 marks pixels whose average difference in grayscale values ​​between adjacent pixels lies within a set extraction range, and sets the grayscale values ​​of other pixels to the maximum value.

[0034] S5 selects the bottom left corner of the cropped image as the origin of the coordinate system, linearly fits a linear function, and determines the number of linear functions formed by the marked pixels.

[0035] If the number of linear functions is 2 and the linear functions are uninterrupted, it is determined that the monorail track of the corresponding road section in the photo is defect-free.

[0036] If the linear function is any other quantity, or if the linear function is 2 but interrupted, it is determined that there is a major defect in the monorail track. The defect location is the intersection of the interruption point and the linear function, and the defect type is monorail track breakage. The detection vehicle stops running, and the warning device at the corresponding location is activated to issue a warning.

[0037] Furthermore, the formula for calculating grayscale conversion of the cropped image is as follows:

[0038]

[0039] R represents the grayscale value of the image after grayscale adjustment, and R, G, and B represent the red, green, and blue values ​​of the pixels in the image, respectively.

[0040] Furthermore, the formula for calculating the average difference between the grayscale values ​​of a pixel and its four adjacent pixels (top, bottom, left, and right) in the image after Gaussian filtering is as follows:

[0041]

[0042] In the formula, This is the average difference between the grayscale values ​​of a pixel and its four adjacent pixels (top, bottom, left, and right). The grayscale value of a pixel. , , and These are the grayscale values ​​of the four adjacent pixels, one above, one below, one to the left and one to the right.

[0043] Furthermore, the parameters of the inspection vehicle running on the monorail are analyzed to determine whether there are common defects in the monorail. The stability index of uniform speed operation on the monorail is obtained, and the obtained data is compared with a set standard range (0, ). The stability index is compared with the standard range. If the stability index is within the standard range, the monorail is considered to be normal. If the stability index is outside the standard range, the monorail has a common defect and the defect location is the location of the stability index outside the standard range.

[0044] The formula for calculating the fluctuation value δ is as follows:

[0045]

[0046] in, The constant coefficients, <0.35, It is a natural constant. This is the slope value. and These are the upslope gradient coefficient and the downslope gradient coefficient, respectively. .

[0047] Furthermore, the ordinary defect data acquisition device collects data on the defect location as photographs of the side of the monorail track; the steps for analyzing the defect location data and determining the defect type are as follows:

[0048] The image of the defect location is converted to grayscale, and then Gaussian filtering is applied to the grayscale image.

[0049] The formula for converting an image to grayscale is as follows:

[0050]

[0051] The image processed by Gaussian filtering is compared with a standard image. The absolute value of the difference in grayscale values ​​is calculated, and pixels whose absolute value of the grayscale difference is greater than a set value β are marked. The area of ​​the defect is calculated by the number of marked pixels. , To mark the number of pixels, This represents the ratio of the difference between a pixel and its actual location; it also records the minimum difference in grayscale values. Maximum difference in grayscale values and the average difference of gray values , , It is the difference between the gray value of the i-th marked pixel and the gray value of the corresponding pixel in the standard image;

[0052] Minimum difference of gray values Maximum difference in grayscale values The calculation method is to subtract the gray value of the standard image pixel from the gray value of the pixel at the defect location in the photo;

[0053] The minimum and maximum differences in grayscale values ​​are compared with the set classification intervals to determine the defect type.

[0054] The classification intervals include the deformation indentation interval (-255, -μβ), the wear interval (-μβ, -β), and the deformation protrusion interval (β, 255), where 1 < μ < 3;

[0055] If the minimum difference in grayscale values If the defect is located within the deformation depression region, the defect type is that the track has a depression;

[0056] If the minimum difference in grayscale values If it is located in the wear range, the defect type is track wear;

[0057] If the maximum difference in grayscale values If the defect is located in the deformation protrusion area, the defect type is that there is a protrusion in the track.

[0058] Furthermore, the formula for calculating the defect level is as follows:

[0059]

[0060] In the formula, Defect level, As an indicator of the stability of the defect location, and These are the stability index and the weighting ratio of the photo data, respectively. , .

[0061] Furthermore, a defect detection method for a monorail track includes the following steps:

[0062] Acquire vehicle trial run data and compare the trial run data with the standard threshold range to determine whether the vehicle meets the requirements. If the vehicle meets the requirements, determine the vehicle to be tested and calculate the vehicle's average parameters.

[0063] Real-time acquisition of parameters of the inspection vehicle running on the monorail track and track data captured by the explosion-proof camera on the vehicle;

[0064] It receives data collected by the data acquisition module, analyzes the collected data, and determines whether there are defects in the monorail track;

[0065] Receive a defect signal and, upon receiving the defect signal, activate the defect data acquisition device to collect data on the defect location;

[0066] The data on the defect location is analyzed to determine the defect type. Based on the defect type, defect data, and the operating parameters of the vehicle being inspected, the defect level is calculated, the defect location is obtained, the defect level is marked at the defect location, a defect drawing is generated, and the warning device at the defect location is activated according to the defect level.

[0067] (III) Beneficial Effects

[0068] This invention provides a defect detection system and method for monorail tracks, which has the following advantages:

[0069] 1. This invention describes a defect detection system for monorail tracks. Before inspection, the vehicle is inspected, and the baseline from this inspection is used as the benchmark for subsequent evaluation of the presence of defects on the monorail track. This makes the subsequent judgment of defects more accurate, enabling the identification of smaller defects. The system then collects and analyzes the defect location, analyzing the content and severity of the defects. This facilitates the development of corresponding defect repair plans based on the defect severity level. The entire process does not require comprehensive analysis of the entire monorail track, resulting in a small amount of data processing. It can analyze defect locations in real time, effectively solving the problem of existing monorail track systems where data collection takes a period of time to produce results, causing the monorail track to be unusable for a period of time and resulting in low effectiveness. Overall, the system has good performance and promising application prospects.

[0070] 2. This invention describes a defect detection system for monorail tracks. During operation, it performs multiple defect assessments. Initial assessments are made using track data captured by an explosion-proof camera mounted on the inspection vehicle to determine if a serious defect has occurred due to an accident. If such a defect is found, the inspection is stopped to ensure safety. Then, parameters from the inspection vehicle's movement on the monorail track are used to determine if a defect exists. If a defect is found, further defect data is collected. Combining the defect data with the parameters from the inspection vehicle's movement on the monorail track, the defect type and severity are determined. The entire defect analysis is relatively accurate, has good performance, and shows promising application prospects.

[0071] 3. This invention describes a defect detection system for monorail tracks. When defects are detected, the system further collects and processes the defect data. It can specifically analyze the defect locations along the monorail track where the inspection vehicle has passed, and can analyze whether there is wear, protrusion, or dent on the monorail track. The overall defect detection of the monorail track is more detailed, effectively avoiding the situation where too many defects on the monorail track lead to a sharp decrease in the subsequent lifespan of the monorail track and make subsequent defect repair difficult. The defect detection effect is better and has good application prospects. Attached Figure Description

[0072] Figure 1 This is a flowchart of a defect detection system for a monorail track according to the present invention;

[0073] Figure 2 This is a diagram showing the usage status of a detection vehicle used in a defect detection system for a monorail track according to the present invention.

[0074] Figure 3 This is a diagram showing the acquisition location of the defect data acquisition device in a defect detection system for a monorail track according to the present invention.

[0075] Figure 4 This is a schematic diagram of track interruption and marked pixel points in a defect detection system for a monorail track according to the present invention;

[0076] Figure 5 This is a flowchart of a defect detection method for a monorail track according to the present invention. Detailed Implementation

[0077] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0078] Research Reasons

[0079] Existing intelligent detection systems for monorail tracks typically detect broken track joints and track deformation. The detection process mainly relies on collecting detailed data from a large area of ​​the track, and then performing detailed analysis on the collected data to determine whether the entire monorail track is deformed or has broken joints.

[0080] When using intelligent monitoring, the initial analysis mainly involves judging whether the monorail track joint is broken or whether the track is deformed by judging the outer contour. It is suitable for situations with large deformation and obvious breakage at the joint. However, it is difficult to detect localized micro-deformation of the monorail track (track wear and local bulges) (the wheel contacts the side of the I-beam when the crane is running, and the structure of the I-beam itself can obstruct the view). Therefore, when it detects defects in the monorail track, the condition of the monorail track is often quite serious, requiring a lot of time to deal with, and there is also a certain risk involved.

[0081] For minor inspections of monorail tracks, manual periodic observation is usually sufficient. While this can detect obvious defects, it's easy to miss areas with slight deformation or wear due to the length of the track and the reliance on visual inspection. This lack of thoroughness leads to an increase in defects over time, affecting the track's lifespan and making subsequent repairs more difficult. It may even necessitate replacing sections of the track, resulting in higher costs and failing to meet user requirements.

[0082] Design Concept

[0083] Most existing systems involve comprehensively acquiring images of the monorail track from multiple angles, then inspecting and analyzing the track's outline to determine if the outline is deformed. They also check for breaks in the outline to identify abnormal track joints. However, this process involves a large amount of data and a lengthy analysis time, typically requiring considerable time to determine if the track is defective. Continuing to operate the inspection vehicle before a result is obtained carries a certain risk.

[0084] Therefore, the initial approach during the research and development process was to reduce analysis time. Thus, we carefully analyzed situations such as interruptions, simplified the existing detection scheme, and adopted the explosion-proof camera built into the detection vehicle to collect data. At the same time, the detection scheme was simplified, which not only eliminated the need to add multiple separate camera components, reducing costs, but also significantly shortened the amount of data processing. It can realize real-time detection of the track (the explosion-proof camera captures the section of the track where the detection vehicle is not running on the monorail, detecting in advance and analyzing whether there are defects before the detection vehicle reaches the running position). Based on the defects, we can determine whether to continue detection, and the overall safety is relatively high.

[0085] However, in actual use, it was found that this method can only detect large deformations in the monorail. In reality, large deformations in the monorail are usually caused by small defects that gradually develop, except in cases of sudden events. When the monorail is deformed, it is difficult to repair. Moreover, during the period when small defects turn into large defects, it will affect the operation of the monorail, causing the monorail to sway during movement, reducing overall safety and failing to meet people's usage requirements.

[0086] Therefore, in the middle of the research and development, the approach was changed and a new detection scheme was studied. After research, a step-by-step detection method was adopted, which first detects whether there are defects and then analyzes the degree of defects. This detection method does not require a comprehensive analysis of the entire monorail track, so the amount of data analyzed is not large.

[0087] However, in actual use, it was found that the inspection vehicles themselves also have differences in operation. The operating data of each inspection vehicle is different, and as the inspection vehicle is used, its subsequent operating data will change significantly from the previous data, which will also affect the results of the identification and cause defect identification errors.

[0088] Therefore, in the later stages of research and development, the previous plans were fully integrated, and the test vehicles were tested. The test data of the test vehicles were used as the basis for analysis and judgment of defects, which greatly improved the accuracy of defect analysis and made the product effective.

[0089] Research Plan

[0090] Example 1

[0091] A defect detection system for monorail tracks includes a vehicle selection module, a data acquisition module, a data judgment module, a secondary acquisition module, and a defect classification module.

[0092] Vehicle selection for testing

[0093] Since the operating data of the test vehicles are different, the operating data may cause certain interference to the subsequent tests. Therefore, it is necessary to select test vehicles that meet the requirements. The selection of test vehicles is based on the vehicle selection module.

[0094] like Figure 2 As shown, this is a diagram illustrating the running status of the detection vehicle on the monorail track.

[0095] The vehicle selection module is used to acquire vehicle trial run data, compare the trial run data with the standard threshold range, determine whether the vehicle meets the requirements, select the vehicle for testing if it meets the requirements, and calculate the vehicle's average parameters.

[0096] The parameters for testing the vehicle's operation on the monorail track are the stability indicators generated by the vehicle's uniform motion on the monorail track.

[0097] The vehicle trial run data includes the stability index of the vehicle running at a constant speed for 50 meters on a horizontal monorail. The vehicle trial run data is collected by vibration sensors installed on the vehicle, and the average parameters of the vehicle are the vehicle stability index parameters.

[0098] The steps to determine whether a vehicle meets the requirements are as follows:

[0099] Remove the stability index of the vehicle running on the horizontal monorail track for the first 10 meters and the last 10 meters (the first 10 meters and the last 10 meters are mainly for acceleration or deceleration, and the vibration is large during this process, so the data needs to be removed);

[0100] The maximum value of the stability index is obtained during the process of the vehicle running at a constant speed on a horizontal monorail track for 30 meters (the longer the distance, the more accurate it is, but the longer the distance, the more data is processed, and the shorter the distance, the less data may be collected, so 30 meters is selected);

[0101] Determine whether the maximum value is within the standard threshold range. If the maximum value is within the standard threshold range, the vehicle meets the inspection requirements. If the maximum value is outside the standard threshold range, the vehicle does not meet the inspection requirements.

[0102] The formula for calculating the stationarity index is as follows:

[0103]

[0104] In the formula, As a stability indicator, For vibration acceleration, The frequency is the vibration frequency.

[0105] The standard threshold range is 0-2.5. When the maximum value of the calculated stability index is within the standard threshold range, the vehicle meets the testing requirements.

[0106] The formula for calculating the vehicle stability index parameters is as follows:

[0107]

[0108] In the formula, These are parameters related to vehicle stability. This refers to the number of stability indicators collected during a 30-meter uniform motion. Let be the i-th stationarity index.

[0109] This invention describes a defect detection system for monorail tracks. Before defect detection, the system inspects the vehicle, using the baseline from this initial inspection as the benchmark for subsequent evaluation of the presence of defects on the monorail track. This makes the subsequent defect assessment more accurate, enabling the identification of smaller defects. Further data collection and analysis of the defect location, including the content and severity of the defect, facilitates the development of corresponding defect repair plans based on the defect severity level. The entire process does not require comprehensive analysis of the entire monorail track, resulting in a small data volume and real-time defect location analysis. This effectively solves the problem of existing monorail track systems where data collection takes a considerable amount of time to produce results, causing the monorail track to be unusable for a period of time and resulting in low effectiveness. Overall, the system offers good performance and has promising application prospects.

[0110] Data Acquisition

[0111] Once the inspection vehicle is selected, all data collected by the inspection vehicle on the monorail track is acquired. This process is based on the data acquisition module.

[0112] The data acquisition module is used to acquire in real time the parameters of the inspection vehicle running on the monorail track and the track data captured by the explosion-proof camera on the vehicle.

[0113] The data collected by the data acquisition module is transmitted through wireless devices on the detection vehicle.

[0114] Defect Analysis

[0115] After acquiring the data from the inspection vehicle, it is necessary to analyze and judge the data to determine whether there are any defects on the monorail track. The specific data analysis is based on the data judgment module.

[0116] The data judgment module is used to receive data collected by the data acquisition module, analyze the collected data, and determine whether there are defects in the monorail track.

[0117] Determining whether there are defects in the monorail track includes determining whether there are major defects (track interruption and severe deformation, in which case testing is abandoned for safety reasons) and whether there are ordinary defects (local deformation and wear) on the monorail track.

[0118] The track data captured by the vehicle-mounted explosion-proof camera is image data taken during the operation of the detection vehicle;

[0119] The steps for analyzing track data captured by the vehicle's onboard explosion-proof camera to determine whether there are defects (major defects) in the monorail track are as follows:

[0120] S1 acquires images taken by the vehicle's onboard explosion-proof camera and then crops the images.

[0121] Since the explosion-proof camera uses a fixed focal length, you only need to crop and keep the middle part of the upper half of the photo taken during the shooting.

[0122] S2 converts the cropped image to grayscale, and then performs Gaussian filtering on the grayscale image;

[0123] The formula for converting a cropped image to grayscale is as follows:

[0124]

[0125] R represents the grayscale value of the image after grayscale adjustment, and R, G, and B represent the red, green, and blue values ​​of the pixels in the image, respectively.

[0126] This step involves a simple grayscale conversion of the image. Since this step is mainly to determine whether there are major defects, minor interruptions do not affect normal defect detection (subsequent detections will detect them). By using a simple processing method, this step happens to fail to detect minor interruptions, allowing the inspection vehicle to operate normally even when there are small defects in the monorail track.

[0127] S3 calculates the average difference between the gray values ​​of a pixel and its four adjacent pixels (top, bottom, left, and right) in the image after Gaussian filtering.

[0128] The formula for calculating the average difference between the grayscale value of a pixel and its four adjacent pixels (top, bottom, left, and right) in an image after Gaussian filtering is as follows:

[0129]

[0130] In the formula, This is the average difference between the grayscale values ​​of a pixel and its four adjacent pixels (top, bottom, left, and right). The grayscale value of a pixel. , , and These are the grayscale values ​​of the four adjacent pixels, one above, one below, one to the left and one to the right.

[0131] This step obtains the outline of the track edge. The track is set to be suspended in the air, and the photos taken have no real objects on both sides of the track, so there will be obvious grayscale differences.

[0132] During normal shooting, the gray values ​​of the left and top pixels of the track (left) edge pixels are all above 230, while the gray values ​​of the right and bottom pixels are close to those of the edge pixels. Through the above calculation method, the position of the edge pixels can be clearly calculated.

[0133] The above steps can be used to calculate the pixels at the edge of the track.

[0134] S4 marks pixels whose average difference in grayscale values ​​between adjacent pixels lies within a set extraction range, and sets the grayscale values ​​of other pixels to the maximum value.

[0135] The extraction range is 10-255.

[0136] S5 selects the bottom left corner of the cropped image as the origin of the coordinate system, linearly fits a linear function, and determines the number of linear functions formed by the marked pixels.

[0137] If the number of linear functions is 2 and the linear functions are uninterrupted, it is determined that the monorail track of the corresponding road section in the photo is defect-free.

[0138] If the linear function is any other quantity, or if the linear function is 2 but interrupted, it is determined that there is a major defect in the monorail track. The defect location is the intersection of the interruption point and the linear function, and the defect type is monorail track breakage. The detection vehicle stops running, and the warning device at the corresponding location is activated to issue a warning.

[0139] The number of linear functions displayed by track misalignment has increased significantly and is also severe, which also indicates a single-railway track breakage.

[0140] The detection is performed on the bottom surface of the track. The crane does not contact the bottom surface of the track. When there is obvious deformation on the bottom surface of the track, the overall deformation of the track is greater. Although it is not considered a track break, it is still extremely dangerous (this situation is rare and will not happen except by accident, so it is not classified separately). Moreover, the number of linear functions is not 2 (a new function is generated at the deformation point), so a breakage warning is also issued.

[0141] The location of the defect is sent via a positioning device on the inspection vehicle.

[0142] like Figure 3 As shown, these are three common scenarios of monorail track interruption, with the lines on the right representing marked pixels.

[0143] This system can detect common defects in monorail tracks and repair them in a timely manner, effectively preventing monorail track interruptions.

[0144] To determine whether common defects exist on a monorail track, the parameters of the inspection vehicle running on the monorail track are analyzed. To determine the presence of common defects, the stability index of uniform speed operation on the monorail track is obtained, and the obtained data is compared with a set standard range (0, 1). The stability index is compared with the standard range. If the stability index is within the standard range, the monorail is considered to be normal. If the stability index is outside the standard range, the monorail has a common defect, and the defect location is the location corresponding to the stability index outside the standard range.

[0145] The location of the defect is sent via a positioning device on the inspection vehicle.

[0146] The formula for calculating the fluctuation value δ is as follows:

[0147]

[0148] in, The constant coefficients, <0.35, It is a natural constant. This is the slope value. and These are the upslope gradient coefficient and the downslope gradient coefficient, respectively. .

[0149] The lower the value, the higher the accuracy, and the higher the requirements for the vehicle being inspected.

[0150] During defect detection, the vehicle maintains the same speed. When encountering a downhill slope, it brakes, resulting in increased vibration data. When encountering an uphill slope, the power of the electric mechanism increases, resulting in increased vibration. Therefore, a corresponding standard range is required.

[0151] Defect detection

[0152] If a major defect is detected, the system will stop immediately and terminate the measurement. If a minor defect is detected, further testing is required. If no defects are detected, the system will operate normally.

[0153] Further testing requires more detailed data, which necessitates the acquisition of additional data based on a secondary data acquisition module.

[0154] The secondary acquisition module receives a defect signal and, upon receiving the defect signal, activates the ordinary defect data acquisition device to collect data on the defect location. The ordinary defect data acquisition device collects a photograph of the side of the monorail track (in contact with the crane wheel).

[0155] like Figure 4 As shown, the defect data acquisition device is installed on one side of the crane wheel. When in use, the crane wheel first contacts the defect location. After analysis and judgment, the defect data acquisition device is activated. At this time, the inspection vehicle drives the defect data acquisition device to move near the defect location to take pictures, thus realizing the acquisition of the defect location.

[0156] Analysis of defects

[0157] Once detailed defect data is obtained, further analysis of the acquired data is needed to gain a deeper understanding of the defects. This analysis is based on the defect segmentation module.

[0158] The defect classification module analyzes the data of the defect location, determines the defect type, calculates the defect level based on the defect type, defect data and the operating parameters of the vehicle being inspected, obtains the defect location, marks the defect level at the defect location, generates a defect drawing, and activates the warning device at the defect location according to the defect level.

[0159] The steps for analyzing the data on defect locations and determining the defect type are as follows:

[0160] The image of the defect location is converted to grayscale, and then Gaussian filtering is applied to the grayscale image.

[0161] The formula for converting an image to grayscale is as follows:

[0162]

[0163] The image processed by Gaussian filtering is compared with a standard image. The absolute value of the difference in grayscale values ​​is calculated, and pixels whose absolute value of the grayscale difference is greater than a set value β are marked. β is usually set to 10, and its value is determined based on the defect detection accuracy. The smaller the β, the higher the detection accuracy. The area of ​​the defect is calculated by the number of marked pixels. , To mark the number of pixels, This represents the ratio of the difference between a pixel and its actual location; it also records the minimum difference in grayscale values. Maximum difference in grayscale values and the average difference of gray values , , It is the difference between the gray value of the i-th marked pixel and the gray value of the corresponding pixel in the standard image;

[0164] Minimum difference of gray values Maximum difference in grayscale values The calculation method is to subtract the gray value of the standard image pixel from the gray value of the pixel at the defect location in the photo;

[0165] At regular intervals, select a defect-free location on the monorail track and take a fixed-focus, equidistant photograph. The resulting images are then converted to grayscale and processed with Gaussian filtering to form a standard image.

[0166] The captured image shows the side of the monorail track. Existing monorail cranes are all equipped with cleaning structures, so the grayscale values ​​of the captured image can directly reflect the actual condition of the monorail track.

[0167] The minimum and maximum differences in grayscale values ​​are compared with the set classification intervals to determine the defect type.

[0168] The classification intervals include the deformation indentation interval (-255, -μβ), the wear interval (-μβ, -β), and the deformation protrusion interval (β, 255), where 1 < μ < 3;

[0169] If the minimum difference in grayscale values If the defect is located within the deformation depression region, the defect type is that the track has a depression;

[0170] If the minimum difference in grayscale values If it is located in the wear range, the defect type is track wear;

[0171] If the maximum difference in grayscale values If the defect is located in the deformation protrusion area, the defect type is that there is a protrusion in the track.

[0172] Because defects are repaired promptly after detection, it is normal not for a situation where a bulge and a depression in the track occur simultaneously. A bulge and a depression in the track are actually the same situation, with one end being bulge and the other end being depression. However, this solution uses data collection from only one side, so the results are divided into two categories.

[0173] This invention describes a defect detection system for monorail tracks. When defects are detected, the system further collects and processes the defect data. It can specifically analyze the defect locations along the monorail track as the inspection vehicle passes, and can analyze whether there is wear, protrusions, or depressions on the monorail track. The overall defect detection of the monorail track is more detailed, effectively avoiding situations where too many defects on the monorail track lead to a sharp decrease in subsequent track lifespan and make subsequent defect repair difficult. The system offers better defect detection results and has promising application prospects.

[0174] The defect level calculated based on track wear is lower than that for track protrusions and track depressions. Therefore, when track wear occurs simultaneously with track protrusions and track depressions, the calculation is performed according to the track protrusion and track depression calculations, resulting in a higher defect level (which does not affect repair).

[0175] The formula for calculating the defect level is as follows:

[0176]

[0177] In the formula, Defect level, As an indicator of the stability of the defect location, and These are the stability index and the weighting ratio of the photo data, respectively. , .

[0178] Defect levels help maintenance personnel understand the defect situation. At this point, repair personnel can bring the appropriate tools to the defect location to carry out maintenance based on the defect type and defect level.

[0179] Furthermore, the defect level helps maintenance personnel understand the extent of repairs that the monorail track has undergone (defects are more likely to occur at this location after major repairs), which facilitates the development of separate maintenance and repair plans for this location.

[0180] The defect location is obtained and sent through the positioning device on the inspection vehicle. The defect level is marked at the defect location, a defect drawing is generated, and the warning device at the defect location is activated according to the defect level.

[0181] Activating the warning device at the defect location allows maintenance personnel to quickly determine when they are near the defect.

[0182] The weighting coefficients are determined using the coefficient of variation method, which assigns weights to each indicator based on the degree of variation between the current value and the target value. If the numerical difference of an indicator is large, clearly distinguishing each evaluated object, it indicates that the indicator has rich discriminative information and should therefore be given a larger weight. Conversely, if the numerical difference of each evaluated object on a certain indicator is small, then the indicator's ability to distinguish each evaluated object is weak, and therefore it should be given a smaller weight. This method directly utilizes the information contained in each indicator to calculate the weight of the indicator, thus possessing objectivity.

[0183] This invention describes a defect detection system for monorail tracks. During operation, the system performs multiple defect assessments. Initial assessments are made using track data captured by an explosion-proof camera mounted on a detection vehicle to determine if a serious defect has occurred due to an accident. If such a defect is found, the system stops detection to ensure safety. Then, parameters from the detection vehicle's movement on the monorail track are used to further assess the presence of defects. If a defect is found, further defect data is collected. Combining the defect data with the parameters from the detection vehicle's movement on the monorail track, the system determines the defect type and severity. The entire defect analysis is accurate, effective, and shows promising application prospects.

[0184] Example 2

[0185] like Figure 5 As shown, based on Example 1, this embodiment also provides a method for detecting defects in a monorail track, including the following steps:

[0186] Acquire vehicle trial run data and compare the trial run data with the standard threshold range to determine whether the vehicle meets the requirements. If the vehicle meets the requirements, determine the vehicle to be tested and calculate the vehicle's average parameters.

[0187] Real-time acquisition of parameters of the inspection vehicle running on the monorail track and track data captured by the explosion-proof camera on the vehicle;

[0188] It receives data collected by the data acquisition module, analyzes the collected data, and determines whether there are defects in the monorail track;

[0189] If a major defect is found, stop the inspection, locate the defect, and activate the warning device at the defect location.

[0190] When a common defect exists, a defect signal is received, and upon receiving the defect signal, the defect data acquisition device is activated to collect data on the defect location.

[0191] The data on the defect location is analyzed to determine the defect type. Based on the defect type, defect data, and the operating parameters of the vehicle being inspected, the defect level is calculated, the defect location is obtained, the defect level is marked at the defect location, a defect drawing is generated, and the warning device at the defect location is activated according to the defect level.

[0192] The above formula is a formula derived from software simulation using a large amount of collected data to obtain the most recent real-world situation. The preset parameters in the formula can be set by those skilled in the art according to the actual situation.

[0193] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented in software, the above embodiments can be implemented, in whole or in part, as a computer program product. Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution.

[0194] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0195] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application.

Claims

1. A monorail track defect detection system, characterized by, The application relates to a vehicle detection system and a vehicle detection method. The vehicle detection system comprises a vehicle selection module, a data collection module, a data judgment module and a secondary collection module. The vehicle selection module is used for acquiring vehicle trial operation data and comparing the trial operation data with a standard threshold interval to determine whether the vehicle meets the requirements, and the vehicle is determined as a detection vehicle when the vehicle meets the requirements. The vehicle trial operation data comprises a stability index of the vehicle running at a constant speed for 50 meters on a horizontal monorail track, and the vehicle trial operation data is collected by a vibration sensor installed on the vehicle. The data collection module is used for acquiring parameters of the detection vehicle running on the monorail track and track data photographed by a vehicle-mounted explosion-proof camera of the detection vehicle in real time. The parameters of the detection vehicle running on the monorail track are stability indexes generated by the detection vehicle running at a constant speed on the monorail track, and the track data photographed by the vehicle-mounted explosion-proof camera are picture data photographed by the vehicle-mounted explosion-proof camera when the detection vehicle runs. The parameter for detecting the vehicle running on the monorail track is analyzed to determine whether the monorail track has common defects, to obtain a smoothness index of the monorail track running at a constant speed, and to compare the obtained data with a set standard interval (0, + δ), wherein δ is a fluctuation value, a vehicle smoothness index parameter; if the smoothness index is within the standard interval, it is determined that the monorail track is normal, if the smoothness index is outside the standard interval, the monorail track has common defects, and the defect position is the position corresponding to the smoothness index outside the standard interval. The data judgment module is used for receiving the data collected by the data collection module and analyzing the collected data to determine whether the monorail track has major defects and common defects. The major defects of the monorail track are fractures, and the detection vehicle is stopped immediately and the measurement is ended when it is determined that the monorail track has major defects.

2. A monorail track defect detection system according to claim 1, wherein: The average parameter of the vehicle is a parameter of the vehicle stability index, and the defect position is sent by detecting a positioning device on the vehicle. The calculation formula of the stability index is as follows: In the formula, is the stability index, is the vibration acceleration, is the vibration frequency.

3. A monorail track defect detection system according to claim 2, wherein: The secondary collection module is used for receiving a common defect signal and starting a common defect data collection device to collect data of a defect position, i.e. collecting a photo of a side of the monorail track, when the common defect signal is received. The defect classification module is used for analyzing the data of the defect position, determining the defect type, calculating a defect level according to the defect type, the defect data and the running parameters of the detection vehicle, marking the defect level at the defect position, generating a defect drawing and starting an alarm device at the defect position according to the defect level. The steps of determining whether the vehicle meets the requirements are as follows: The stability indexes of the vehicle running on the monorail track for 10 meters at the front and 10 meters at the back are removed. The formula for calculating the vehicle stability index parameter is as follows: In the formula, is the vehicle stability index parameter, is the number of stability indexes collected in the process of moving at a constant speed for 30 meters, is the i-th stability index.

4. A monorail track defect detection system according to claim 3, wherein: The maximum value of the stability indexes of the vehicle running at a constant speed for 30 meters on the monorail track is acquired. It is determined whether the maximum value is in the standard threshold interval, and the vehicle meets the detection requirements when the maximum value is in the standard threshold interval. The steps of analyzing the track data photographed by the vehicle-mounted explosion-proof camera of the detection vehicle to determine whether the monorail track has major defects are as follows: S1: a picture photographed by the vehicle-mounted explosion-proof camera of the detection vehicle is acquired, and the picture is cropped. S2: the cropped picture is grayed, and the grayed picture is subjected to Gaussian filter processing. S3: the average difference value of pixel points in the picture subjected to the Gaussian filter processing and four adjacent pixel points is calculated. S4: the pixel points with the average difference value of the adjacent pixel points in a set extraction interval are marked, and the gray values of other pixel points are set as maximum values. S5: the lower left corner of the cropped picture is selected as a coordinate origin, a linear function is linearly fitted, and the number of linear functions formed by the marked pixel points is determined. If the number of linear functions is 2 and the linear functions have no interruption, it is determined that the monorail track of the corresponding section in the picture has no defects. If the linear function is other quantity, or the quantity of the linear function is 2, but the linear function is interrupted, it is determined that the monorail track has a large defect, the defect position is the intersection position of the interruption and the linear function, the defect type is monorail track fracture, the detection vehicle stops running, and the warning device at the corresponding position is started to warn.

5. A monorail track defect detection system according to claim 4, wherein: The calculation formula for the gray-scale of the cropped picture is as follows: is the gray value of the picture after the gray-scale processing, R, G and B are respectively the red value, green value and blue value of the pixel point on the picture.

6. A monorail track defect detection system according to claim 5, wherein: The formula for calculating the average difference value of the pixel point in the picture after Gaussian filtering processing and the gray values of the four adjacent pixel points is as follows: In the formula, is the average difference value of the pixel point and the gray values of the four adjacent pixel points, is the gray value of the pixel point, , , and are the gray values of the four adjacent pixel points, respectively.

7. A monorail track defect detection system according to claim 6, wherein: The calculation formula of the fluctuation value δ is as follows: wherein, is a constant coefficient, <0.35, is a natural constant, is a slope value, and are an uphill slope coefficient and a downhill slope coefficient, respectively, .

8. A monorail track defect detection system according to claim 7, wherein: The steps of analyzing the data of the defect position and judging the defect type are as follows: Gray the picture of the defect position, and then perform Gaussian filter processing on the grayed picture; The calculation formula for graying the picture is as follows: The picture after the Gaussian filtering processing is compared with the standard picture, the absolute value of the gray value difference is calculated, and the pixel points with the absolute value of the gray value difference greater than the set value β are marked, and the area of the defect is converted through the number of the marked pixel points , The number of the marked pixel points is The pixel point and the actual point difference ratio are recorded, the minimum gray value difference , the maximum gray value difference and the average gray value difference , , The difference between the gray value of the ith marked pixel point and the gray value of the pixel point at the corresponding position on the standard picture is calculated. Minimum difference of gray scale value Maximum difference of gray scale value The calculation method of the minimum difference of gray scale value and the maximum difference of gray scale value is that the gray scale value of the pixel point of the defect photo is subtracted from the gray scale value of the pixel point of the standard photo. Compare the minimum difference value of the gray value and the maximum difference value of the gray value with the set classification interval to judge the defect type; The classification interval includes a deformation depression interval (-255, -mu), a wear interval (-mu, -beta), and a deformation convex interval (beta, 255), 1 < mu < 3; If the minimum difference of gray values is greater than the threshold value If the minimum difference of gray values is greater than the threshold value If the minimum difference of gray values is greater than the threshold value If the gray value minimum difference is located in the wear interval, the defect type is track wear; If the maximum difference of gray value If the maximum difference of gray value If the maximum difference of gray value If the maximum difference of gray value If the maximum difference of gray value If the maximum difference of 9. A monorail track defect detection system according to claim 8, wherein: The calculation formula of the defect grade is as follows: In the formula, is the defect grade, is the smoothness index of the defect position, and are the smoothness index and the weight proportion corresponding to the photo data respectively, , .

10. A method for detecting defects in a monorail track using the system of any one of claims 1 to 9, characterized by: The steps include: Obtain the vehicle test running data, compare the test running data with the standard threshold interval, judge whether the vehicle meets the requirements, determine the detection vehicle when meeting the requirements, and calculate the average parameters of the vehicle; Real-time acquisition of the parameters of the detection vehicle running on the monorail track and the track data shot by the vehicle-mounted explosion-proof camera of the detection vehicle; Receive the data collected by the data acquisition module, analyze the collected data, and judge whether the monorail track has defects; Receive the defect signal, and start the defect data acquisition device to collect the data of the defect position when the defect signal is received; Analyze the data of the defect position, judge the defect type, calculate the defect level according to the defect type, defect data and detection vehicle running parameters, obtain the defect position, mark the defect level at the defect position, generate the defect drawing, and start the warning device at the defect position according to the defect level.

Images