Heavy-load electric locomotive vibration measurement method and system based on machine vision

Abstract

The invention relates to the technical field of vibration measurement, in particular to a heavy-load electric locomotive vibration measurement method and system based on machine vision, and the method comprises the steps: obtaining a vibration function set and a speed gradient set which are used for simulating vibration, obtaining a vibration combination set based on the vibration function set and the speed gradient set, and obtaining a target detection locomotive, acquiring a vibration detection video stream based on the vibration combination set and a target detection locomotive, acquiring a detection vibration displacement set based on the vibration detection video stream, screening the detection vibration displacement set to obtain a target vibration displacement set, and acquiring a fitting vibration displacement set and a size parameter set, and acquiring a fitting detection model based on the fitting vibration displacement set, the size parameter set and the target vibration displacement set, and sending the fitting detection model to an initiating end of a vibration test instruction by using a vibration feedback unit to realize vibration measurement of the heavy-load electric locomotive. The accuracy and the intelligent degree of vibration measurement of the heavy-load electric locomotive can be improved.

Description

Technical Field

[0001] The present invention relates to the field of vibration measurement technology, and in particular to a machine vision-based vibration measurement method, system, electronic equipment and computer-readable storage medium for a heavy-load electric locomotive. Background Art

[0002] During the operation of heavy-load electric locomotives, vibrations will inevitably occur, and the vibrations will have a significant impact on the locomotive itself and the entire transportation system. The vibrations often lead to a decrease in the passenger experience and may even lead to safety accidents. Therefore, accurate and comprehensive testing of heavy-load electric locomotives is of great significance to ensure their safe and reliable application.

[0003] At present, the vibration measurement method mainly includes contact measurement, that is, the vibration measurement of the object to be measured is achieved by placing a large number of sensors on the surface of the object to be measured.

[0004] Although the above method can realize the vibration measurement of heavy-loaded electric locomotives, it consumes a lot of resources and there is a problem of inaccurate vibration measurement when performing vibration measurement on heavy-loaded electric locomotives. Therefore, the intelligence level and accuracy of vibration measurement on heavy-loaded electric locomotives need to be improved. Summary of the invention

[0005] The present invention provides a heavy-load electric locomotive vibration measurement method based on machine vision and a computer-readable storage medium, the main purpose of which is to improve the accuracy and intelligence of the heavy-load electric locomotive vibration measurement.

[0006] To achieve the above object, the present invention provides a heavy-load electric locomotive vibration measurement method based on machine vision, comprising: Receiving a vibration test instruction, and confirming a vibration test environment for the vibration test based on the vibration test instruction, wherein the vibration test environment includes: a heavy-load electric locomotive, a simulated vibration table and a vibration measurement system, wherein the vibration measurement system includes: a video shooting unit and a vibration feedback unit; Acquire a vibration function set and a velocity gradient set for simulating vibration, wherein the vibration function set includes a plurality of vibration functions, the velocity gradient set includes a plurality of reference speeds, and acquire a vibration combination set based on the vibration function set and the velocity gradient set; A reference coordinate system is constructed, and a target detection locomotive is obtained by using the reference coordinate system and the heavy-load electric locomotive, wherein the target detection locomotive includes a plurality of target detection points; Based on the vibration combination set, the target detection locomotive, the simulated vibration platform and the video shooting unit, a vibration detection video stream is obtained, and based on the vibration detection video stream, a detection vibration displacement set is obtained, wherein the detection vibration displacement set includes multiple detection vibration displacements; Filtering the detected vibration displacement set to obtain a target vibration displacement set; Acquire a fitting vibration displacement set of the target detection locomotive, wherein the fitting vibration displacement set includes a plurality of fitting vibration displacements, and the fitting vibration displacements correspond to the target detection points one by one; A size parameter set of a target detection locomotive is obtained, a fitting detection model is obtained based on the fitting vibration displacement set, the size parameter set and the target vibration displacement set, and a vibration feedback unit is used to send the fitting detection model to an initiator of a vibration test instruction to realize vibration measurement of a heavy-load electric locomotive.

[0007] Optionally, acquiring the vibration combination set based on the vibration function set and the velocity gradient set includes: Extract vibration functions from the vibration function set in sequence, and perform the following operations on the extracted vibration functions: The extracted vibration function is matched with the velocity gradient set to obtain a vibration combination, and the vibration combinations are summarized to obtain a vibration combination set, wherein the vibration combination is as follows: ; in, Indicates the vibration combination set A vibration combination, represents the vibration function set A vibration function, represents the velocity gradient set, They represent the first reference speed, the second reference speed, and the The reference speed and A reference speed, Indicates that the velocity gradient is concentrated A reference speed.

[0008] Optionally, the method of acquiring the target detection locomotive by using a reference coordinate system and a heavy-load electric locomotive includes: Confirming a detection area in the heavy-load electric locomotive, and acquiring a plurality of target detection points based on the reference coordinate system and the detection area; Extract target detection points from the multiple target detection points in sequence, and perform the following operations on the extracted target detection points: Acquire a detection grayscale value based on the extracted target detection point, use the detection grayscale value as the starting point of a pre-constructed region growing algorithm, and use the region growing algorithm to acquire a target growth region, wherein the grayscale values ​​of the pixel points corresponding to the target growth region are all the same; In the detection area corresponding to the target growth area, a target positioning pattern is confirmed based on the detection grayscale value, wherein the target positioning pattern is a square chessboard pattern in which a preset first grayscale value and a preset second grayscale value are alternately arranged, and both the first grayscale value and the second grayscale value are different from the detection grayscale value, and the side length of the square chessboard pattern is preset to be (2q+1), wherein q is an integer greater than or equal to 1; The center of the target positioning pattern is fixed to the target detection point to obtain the target detection locomotive.

[0009] Optionally, the step of obtaining a vibration detection video stream based on the vibration combination set, the target detection locomotive, the simulated vibration table and the video shooting unit includes: Extract vibration combinations from the vibration combination set in sequence, and perform the following operations on the extracted vibration combinations: A plurality of target vibration combinations are obtained based on the extracted vibration combinations, wherein the target vibration combinations are as follows: ; in, Indicates the vibration combination set The vibration combination corresponds to the target vibration combination; Extract target vibration combinations from multiple target vibration combinations in sequence and perform the following operations on the extracted target vibration combinations: The extracted target vibration combination is input into a simulated vibration table to obtain a target vibration table, and a vibration operation is performed on a target detection locomotive using the target vibration table, wherein the duration of the vibration operation is preset, and a video shooting unit is used to shoot the target vibration table in the vibration operation to obtain a vibration detection video stream.

[0010] Optionally, acquiring a detected vibration displacement set based on the vibration detection video stream includes: Based on the target detection locomotive, an initial detection image is obtained, an initial frame number of the vibration detection video stream is obtained, target detection images are sequentially extracted from the vibration detection video stream based on the initial frame number, and the following operations are performed on the extracted target detection images: Extract target positioning patterns from the target detection locomotive in sequence, and perform the following operations on the extracted target positioning patterns: Performing a grayscale operation on the initial detection image to obtain an initial grayscale image, and acquiring an initial detection window based on the initial grayscale image and the extracted target positioning pattern, wherein the initial detection window is a pixel area corresponding to the target positioning pattern in the initial grayscale image; Performing a grayscale operation on the extracted target detection image to obtain a target grayscale image, and using the initial detection window and the target grayscale image to obtain a plurality of different first positioning patterns; Extracting first positioning patterns from the multiple different first positioning patterns in sequence, and performing the following operations on the extracted first positioning patterns: Calculate reference similarity using a pre-constructed similarity evaluation relationship and the extracted first positioning pattern, summarize the reference similarities to obtain a reference similarity set, identify a second positioning pattern using the reference similarity set, wherein the second positioning pattern is the first positioning pattern corresponding to the largest reference similarity in the reference similarity set, and obtain the detected vibration displacement based on the second positioning pattern; The detected vibration displacements are summarized to obtain a detected vibration displacement set.

[0011] Optionally, the similarity evaluation relationship is as follows: ; in, represents the reference similarity, are all preset coefficients. Represents the grayscale value of the pixel corresponding to the target positioning pattern in the initial grayscale image, Represents the mean grayscale value of the pixel points corresponding to the target positioning pattern in the initial grayscale image, represents the gray value of the pixel corresponding to the first positioning pattern, represents the mean value of the grayscale values ​​of the pixels corresponding to the first positioning pattern, Indicates the first positioning pattern corresponding to the Line The pixel point or target positioning pattern of the column corresponds to the first Line Column pixels, Represents the coordinates of the target detection point corresponding to the target positioning pattern in the reference coordinate system, Represents the coordinates of the pre-constructed reference point in the reference coordinate system, The pixel area corresponding to the target positioning pattern in the initial grayscale image is OK The pixel area of ​​the column.

[0012] Optionally, acquiring the detected vibration displacement based on the second positioning pattern includes: The central pixel point is retrieved from the second positioning pattern, and the pixel point is used as the displacement pixel point. The displacement coordinates are calculated using the pre-constructed displacement conversion relationship and the displacement pixel point. The initial detection coordinates are retrieved from the target detection locomotive using the displacement pixel point. The vibration displacement is calculated based on the detection displacement coordinates and the initial detection coordinates. The displacement conversion relationship is as follows: ; in, represents the calibration parameters of the video capture unit, Represents the coordinates of the displaced pixel points, represents the intrinsic parameter matrix of the video capture unit, represents the extrinsic parameter matrix of the video capture unit, Indicates the detected displacement coordinates.

[0013] Optionally, screening the detected vibration displacement set to obtain a target vibration displacement set includes: The screening value is calculated using the detected vibration displacement set and the pre-built screening relationship, where the screening relationship is as follows: ; in, Indicates the detection of vibration displacement concentration The screening value corresponding to the detected vibration displacement, Indicates the detection of vibration displacement concentration A detection vibration displacement, Indicates the detection of vibration displacement concentration A detection vibration displacement, Indicates the total number of detected vibration displacements Detect vibration displacement; Summarizing the screening values ​​to obtain a screening value set, and performing a sorting operation on the screening values ​​in the screening value set in descending order to obtain a screening sequence, wherein the screening values ​​correspond to the detected vibration displacements one by one; The detected vibration displacements corresponding to the screening values ​​are sequentially extracted from the screening sequence, and the following operations are performed on the extracted detected vibration displacements: The extracted detected vibration displacement is eliminated from the detected vibration displacement set to obtain an updated vibration displacement set, and an estimated value is calculated based on the updated vibration displacement set and a pre-constructed estimation relation, wherein the estimation relation is as follows: ; in, Represents an estimated value, represents the coordinates corresponding to the extracted detected vibration displacement, Represents the update of the vibration displacement concentration Update vibration displacement, Indicates the update of vibration displacement concentration Update vibration displacement, Represents the update of the vibration displacement concentration Update the coordinates corresponding to the vibration displacement; Obtaining a first evaluation value using the estimated value and the extracted detection vibration displacement, wherein the first evaluation value is an absolute difference between the estimated value and the extracted detection vibration displacement; comparing the first evaluation value with a preset evaluation threshold; If the first evaluation value is less than or equal to the evaluation threshold, confirming that the detected vibration displacement set is a target vibration displacement set; Otherwise, the extracted detected vibration displacement is eliminated from the detected vibration displacement set to obtain a eliminated detected displacement set, the eliminated detected displacement set is used as the detected vibration displacement set, and the step of calculating the screening value using the detected vibration displacement set and the pre-constructed screening relationship is returned until the first evaluation value is less than or equal to the evaluation threshold, so as to obtain the target vibration displacement set.

[0014] Optionally, acquiring a fitting detection model based on the fitting vibration displacement set, the size parameter set and the target vibration displacement set includes: Building an initial locomotive model based on the size parameter set, and retrieving a plurality of model detection points in the initial locomotive model according to the position of the target detection point in the target detection locomotive, wherein the model detection points correspond one-to-one to the target detection points; According to the position of the target detection point, matching the fitting vibration displacement in the fitting vibration displacement set with the target vibration displacement in the target vibration displacement set to obtain a plurality of matching displacement groups, wherein the matching displacement groups correspond to the target detection points one by one; Extract matching displacement groups from the multiple matching displacement groups in sequence, and perform the following operations on the extracted matching displacement groups: If the target vibration displacement exists in the extracted matching displacement group, the matching displacement group is proposed to be an empty set; Summarize the matching displacement groups that are not empty sets to obtain multiple target displacement groups; Extracting target displacement groups from the plurality of target displacement groups in sequence, and acquiring target vibration values ​​based on the extracted target displacement groups, wherein the target vibration value is a difference between the fitting vibration displacement and the target vibration displacement; The fitting vibration displacement, target vibration displacement and target vibration value corresponding to the target displacement group are used to perform a marking operation on the model detection points corresponding to the target displacement group to obtain a fitting detection model.

[0015] To achieve the above object, the present invention also provides a heavy-load electric locomotive vibration measurement system based on machine vision, comprising: A vibration test environment confirmation module, used for receiving a vibration test instruction, and confirming a vibration test environment for vibration testing based on the vibration test instruction, wherein the vibration test environment includes: a heavy-load electric locomotive, a simulated vibration table and a vibration measurement system, wherein the vibration measurement system includes: a video shooting unit and a vibration feedback unit; A vibration test preparation module, used to obtain a vibration function set and a velocity gradient set for simulating vibration, wherein the vibration function set includes a plurality of vibration functions, the velocity gradient set includes a plurality of reference speeds, and a vibration combination set is obtained based on the vibration function set and the velocity gradient set; A reference coordinate system is constructed, and a target detection locomotive is obtained by using the reference coordinate system and the heavy-load electric locomotive, wherein the target detection locomotive includes a plurality of target detection points; A vibration test module, used for acquiring a vibration detection video stream based on the vibration combination set, the target detection locomotive, the simulated vibration platform and the video shooting unit, and acquiring a detection vibration displacement set based on the vibration detection video stream, wherein the detection vibration displacement set includes a plurality of detection vibration displacements; Filtering the detected vibration displacement set to obtain a target vibration displacement set; A vibration test analysis module, used for obtaining a fitting vibration displacement set of a target detection locomotive, wherein the fitting vibration displacement set includes a plurality of fitting vibration displacements, and the fitting vibration displacements correspond to the target detection points one by one; A size parameter set of a target detection locomotive is obtained, a fitting detection model is obtained based on the fitting vibration displacement set, the size parameter set and the target vibration displacement set, and a vibration feedback unit is used to send the fitting detection model to an initiator of a vibration test instruction to realize vibration measurement of a heavy-load electric locomotive.

[0016] In order to solve the above problem, the present invention further provides an electronic device, the electronic device comprising: a memory storing at least one instruction; and The processor executes the instructions stored in the memory to implement the above-mentioned heavy-load electric locomotive vibration measurement method based on machine vision.

[0017] In order to solve the above problems, the present invention also provides a computer-readable storage medium, in which at least one instruction is stored. The at least one instruction is executed by a processor in an electronic device to implement the above-mentioned machine vision-based heavy-load electric locomotive vibration measurement method.

[0018] The present invention is to solve the problem described in the background technology. The present invention obtains a vibration function set and a velocity gradient set for simulating vibration, wherein the vibration function set includes multiple vibration functions, and the velocity gradient set includes multiple reference speeds. A vibration combination set is obtained based on the vibration function set and the velocity gradient set. It can be seen that the embodiment of the present invention takes into account that different speeds and different vibration conditions will cause different vibrations in heavy-loaded electric locomotives. Therefore, the form of a vibration combination set is adopted to analyze the situation in which different reference speeds cause vibrations of heavy-loaded electric locomotives under the same vibration function, thereby improving the intelligence level of vibration measurement of heavy-loaded electric locomotives. The present invention obtains a vibration detection video stream based on the vibration combination set, the target detection locomotive, the simulated vibration platform and the video shooting unit, and obtains a detection vibration displacement set based on the vibration detection video stream, wherein the detection vibration displacement set includes multiple detection vibration displacements. It can be seen that the present invention not only considers that different vibrations may exist at different target detection points, but also obtains the vibration conditions of the heavy-loaded electric locomotive at different times, different reference speeds, different vibration functions or different target detection points in the form of vibration detection video streams. In addition, when detecting vibration, not only the difference in the color of the heavy-loaded electric locomotive itself is considered, therefore, different target positioning patterns are formulated at different target detection points, and coordinate elements are incorporated when obtaining the second positioning pattern to improve the accuracy of obtaining the second positioning pattern, thereby improving the accuracy of vibration measurement of the heavy-loaded electric locomotive. The present invention screens the detection vibration displacement set to obtain the target vibration displacement set. It can be seen that the embodiment of the present invention not only considers the problem of inaccurate detection vibration displacement due to image recognition on the basis of being able to accurately obtain the second positioning image, but also screens the detection vibration displacement set to obtain the target vibration displacement set to improve the accuracy of vibration measurement of the heavy-loaded electric locomotive. The present invention obtains the size parameter set of the target detection locomotive, obtains the fitting detection model based on the fitting vibration displacement set, the size parameter set and the target vibration displacement set, and uses the vibration feedback unit to send the fitting detection model to the initiator of the vibration test instruction to realize the vibration measurement of the heavy-loaded electric locomotive. It can be seen that the present invention also uses the target vibration displacement set to construct vibration-related parameters for characterizing the heavy-loaded electric locomotive at different target detection points to improve the intelligence level of the vibration measurement of the heavy-loaded electric locomotive. Therefore, the present invention can improve the accuracy and intelligence level of the vibration measurement of the heavy-loaded electric locomotive. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 A schematic flow chart of a method for measuring vibration of a heavy-load electric locomotive based on machine vision provided by one embodiment of the present invention; Figure 2 A functional module diagram of a heavy-load electric locomotive vibration measurement system based on machine vision provided by an embodiment of the present invention; Figure 3A schematic diagram of the structure of an electronic device for implementing the machine vision-based heavy-load electric locomotive vibration measurement method provided in one embodiment of the present invention.

[0020] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0021] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0022] The embodiment of the present application provides a vibration measurement method for a heavy-loaded electric locomotive based on machine vision. The execution subject of the vibration measurement method for a heavy-loaded electric locomotive based on machine vision includes but is not limited to at least one of the electronic devices such as a server and a terminal that can be configured to execute the method provided in the embodiment of the present application. In other words, the vibration measurement method for a heavy-loaded electric locomotive based on machine vision can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc.

[0023] Reference Figure 1 FIG. 1 is a flow chart of a method for measuring vibration of a heavy-load electric locomotive based on machine vision according to an embodiment of the present invention. In this embodiment, the method for measuring vibration of a heavy-load electric locomotive based on machine vision includes: S1. Receive a vibration test instruction, and confirm a vibration test environment for the vibration test based on the vibration test instruction, wherein the vibration test environment includes: a heavy-load electric locomotive, a simulated vibration table and a vibration measurement system, wherein the vibration measurement system includes: a video shooting unit and a vibration feedback unit.

[0024] It should be explained that the vibration test instruction refers to the instruction issued by the heavy-load electric locomotive tester to the heavy-load electric locomotive that is to undergo a vibration test. The vibration test system refers to an APP or software for vibration detection and analysis of a heavy-load electric locomotive, and the vibration measurement system includes: a video shooting unit and a vibration feedback unit. For the application of specific units, please refer to the subsequent embodiments. Optionally, the simulated vibration table is a rolling vibration test table, and other technologies can achieve the same effect, which will not be repeated here.

[0025] For example, in order to test the vibration resistance performance of a certain model of heavy-load electric locomotive at different speeds and in different vibration modes, the tester of the heavy-load electric locomotive issues the vibration test instruction to the heavy-load electric locomotive of this model, and confirms the vibration test environment based on the vibration test instruction.

[0026] S2. Obtain a vibration function set and a velocity gradient set for simulating vibration, wherein the vibration function set includes a plurality of vibration functions, and the velocity gradient set includes a plurality of reference speeds, and obtain a vibration combination set based on the vibration function set and the velocity gradient set.

[0027] It is understandable that the vibration function refers to a function used to simulate the vibration conditions that a heavy-load electric locomotive may encounter in life. The reference speed refers to the speed at which a heavy-load electric locomotive may actually run in life. Optionally, a simple harmonic vibration function is selected as the vibration function, wherein the simple harmonic vibration function is as follows: ; in, represents the simple harmonic oscillation function, represents the amplitude, represents the phase angle, Indicates time, Represents the angular frequency.

[0028] It should be explained that the step of obtaining a vibration combination set based on the vibration function set and the velocity gradient set includes: Extract vibration functions from the vibration function set in sequence, and perform the following operations on the extracted vibration functions: The extracted vibration function is matched with the velocity gradient set to obtain a vibration combination, and the vibration combinations are summarized to obtain a vibration combination set, wherein the vibration combination is as follows: ; in, Indicates the vibration combination set A vibration combination, represents the vibration function set A vibration function, represents the velocity gradient set, They represent the first reference speed, the second reference speed, and the The reference speed and A reference speed, Indicates that the velocity gradient is concentrated A reference speed.

[0029] It should be understood that under the same vibration function, the vibration amount generated by the heavy-load electric locomotive may be different at different reference speeds. Therefore, the vibration function is matched with the speed gradient set to obtain a vibration combination for vibration simulation, and the vibration combination can characterize the influence of different reference speeds on the vibration of the heavy-load electric locomotive under the same vibration function. For the specific characterization method, please refer to the subsequent embodiments.

[0030] S3. Construct a reference coordinate system, and use the reference coordinate system and the heavy-load electric locomotive to obtain a target detection locomotive, wherein the target detection locomotive includes multiple target detection points.

[0031] It is understandable that the target detection point refers to the point where the vibration change of the heavy-load electric locomotive is observed. Optionally, the world coordinate system is selected as the reference coordinate system, and other technologies can achieve the same effect, which will not be repeated here.

[0032] It should be explained that the method of using a reference coordinate system and a heavy-load electric locomotive to obtain a target detection locomotive includes: Confirming a detection area in the heavy-load electric locomotive, and acquiring a plurality of target detection points based on the reference coordinate system and the detection area; Extract target detection points from the multiple target detection points in sequence, and perform the following operations on the extracted target detection points: Acquire a detection grayscale value based on the extracted target detection point, use the detection grayscale value as the starting point of a pre-constructed region growing algorithm, and use the region growing algorithm to acquire a target growth region, wherein the grayscale values ​​of the pixel points corresponding to the target growth region are all the same; In the detection area corresponding to the target growth area, a target positioning pattern is confirmed based on the detection grayscale value, wherein the target positioning pattern is a square chessboard pattern in which a preset first grayscale value and a preset second grayscale value are alternately arranged, and both the first grayscale value and the second grayscale value are different from the detection grayscale value, and the side length of the square chessboard pattern is preset to be (2q+1), wherein q is an integer greater than or equal to 1; The center of the target positioning pattern is fixed to the target detection point to obtain the target detection locomotive.

[0033] It should be noted that the detection area refers to the area used to observe the vibration changes of heavy-loaded electric locomotives, and the selection of the detection area needs to be combined with a specific vibration function. For example: the selected vibration function is used to characterize the vibration of the heavy-loaded electric locomotive in the up and down directions, then the area that cannot characterize the heavy-loaded electric locomotive perpendicular to the up and down directions should not be selected as the detection area. The target detection point refers to the point used to observe the vibration changes of the heavy-loaded electric locomotive. For example: the figure corresponding to the detection area is a 3 by 5 rectangle, and the detection area is divided into 3 equal points and 5 equal points respectively, and the intersection of the division is used as the target detection point, then 24 target detection points are obtained. The detection gray value refers to the gray value of the image corresponding to the target detection point in the heavy-loaded electric locomotive. The purpose of the region growing algorithm in the embodiment of the present invention is to identify the target growth area composed of pixel points with the same detection gray value, and to formulate different target positioning patterns according to different target growth areas, so as to improve the accuracy of positioning the target detection point in the image of vibration changes. The purpose of presetting the first grayscale value and the second grayscale value is to distinguish the difference between the target positioning pattern and the detection area corresponding to the target production area, thereby improving the accuracy of the target positioning pattern being identified at the target detection point, thereby improving the accuracy of the vibration measurement of the heavy-load electric locomotive. The region growing algorithm is a prior art and will not be described in detail here.

[0034] It is understandable that if the grayscale value of the selected target positioning pattern is slightly different from the grayscale value of the target growth area, it may be difficult to identify the target positioning pattern at the target detection point. The side length unit of the square chessboard pattern can be set according to the size of the target growth area, which will not be repeated here.

[0035] For example, before conducting a vibration test on a heavy-load electric locomotive, a tester of the heavy-load electric locomotive selects a surface perpendicular to the vibration test direction in the heavy-load electric locomotive as the detection area, and evenly sets multiple target detection points in the detection area. For ease of understanding, the target positioning pattern is represented in the form of coordinates, wherein the target positioning pattern is a square area surrounded by vertices (0, 0), (0, 5), (5, 0) and (5, 5), wherein the center of the square chessboard image is (3, 3).

[0036] S4. Acquire a vibration detection video stream based on the vibration combination set, the target detection locomotive, the simulated vibration platform and the video shooting unit, and acquire a detected vibration displacement set based on the vibration detection video stream, wherein the detected vibration displacement set includes multiple detected vibration displacements.

[0037] It should be explained that the step of obtaining the vibration detection video stream based on the vibration combination set, the target detection locomotive, the simulated vibration platform and the video shooting unit includes: Extract vibration combinations from the vibration combination set in sequence, and perform the following operations on the extracted vibration combinations: A plurality of target vibration combinations are obtained based on the extracted vibration combinations, wherein the target vibration combinations are as follows: ; in, Indicates the vibration combination set The vibration combination corresponds to the target vibration combination; Extract target vibration combinations from multiple target vibration combinations in sequence and perform the following operations on the extracted target vibration combinations: The extracted target vibration combination is input into a simulated vibration table to obtain a target vibration table, and a vibration operation is performed on a target detection locomotive using the target vibration table, wherein the duration of the vibration operation is preset, and a video shooting unit is used to shoot the target vibration table in the vibration operation to obtain a vibration detection video stream.

[0038] It is understandable that the multiple target vibration combinations obtained in the vibration combination can characterize the impact of different speeds on the heavy-loaded electric locomotive under the same vibration function. Vibration operation refers to the operation of vibrating the heavy-loaded electric locomotive using the vibration that can be generated by the simulated vibration table under the extracted vibration function. Duration refers to the duration of the vibration operation, and the duration should be greater than or equal to the period of the vibration function. So that the vibration of the heavy-loaded electric locomotive can be fully observed throughout the entire cycle. The vibration detection video stream refers to the video of the detection area captured by the video shooting unit during the vibration process. Optionally, a camera is used as the video shooting unit, and other technologies can achieve the same effect, which will not be repeated here.

[0039] Further, the acquiring the detected vibration displacement set based on the vibration detection video stream includes: Based on the target detection locomotive, an initial detection image is obtained, an initial frame number of the vibration detection video stream is obtained, target detection images are sequentially extracted from the vibration detection video stream based on the initial frame number, and the following operations are performed on the extracted target detection images: Extract target positioning patterns from the target detection locomotive in sequence, and perform the following operations on the extracted target positioning patterns: Performing a grayscale operation on the initial detection image to obtain an initial grayscale image, and acquiring an initial detection window based on the initial grayscale image and the extracted target positioning pattern, wherein the initial detection window is a pixel area corresponding to the target positioning pattern in the initial grayscale image; Performing a grayscale operation on the extracted target detection image to obtain a target grayscale image, and using the initial detection window and the target grayscale image to obtain a plurality of different first positioning patterns; Extracting first positioning patterns from the multiple different first positioning patterns in sequence, and performing the following operations on the extracted first positioning patterns: Calculate reference similarity using a pre-constructed similarity evaluation relationship and the extracted first positioning pattern, summarize the reference similarities to obtain a reference similarity set, identify a second positioning pattern using the reference similarity set, wherein the second positioning pattern is the first positioning pattern corresponding to the largest reference similarity in the reference similarity set, and obtain the detected vibration displacement based on the second positioning pattern; The detected vibration displacements are summarized to obtain a detected vibration displacement set.

[0040] It should be explained that the initial detection image refers to the image of the target detection locomotive before the target detection locomotive vibrates. The initial frame number refers to the frame number of the vibration detection video stream. The target detection image refers to the image extracted from the vibration detection video stream using the initial frame number. The grayscale operation refers to the operation of converting a color image into a grayscale image, and the technology of the grayscale operation is a prior art and will not be described in detail here.

[0041] It should be understood that the purpose of obtaining the initial detection window in the initial grayscale image is to retrieve a pixel area in the target grayscale image that is similar to or even identical to the target positioning pattern, so as to obtain the displacement of the pixel points generated by the target detection points corresponding to the target positioning pattern through the target grayscale image and the initial grayscale image, and then convert the displacement into a vibration value.

[0042] It is understandable that the similarity evaluation relationship is as follows: ; in, represents the reference similarity, are all preset coefficients. Represents the grayscale value of the pixel corresponding to the target positioning pattern in the initial grayscale image, Represents the mean grayscale value of the pixel points corresponding to the target positioning pattern in the initial grayscale image, represents the gray value of the pixel corresponding to the first positioning pattern, represents the mean value of the grayscale values ​​of the pixels corresponding to the first positioning pattern, Indicates the first positioning pattern corresponding to the Line The pixel point or target positioning pattern of the column corresponds to the first Line Column pixels, Represents the coordinates of the target detection point corresponding to the target positioning pattern in the reference coordinate system, Represents the coordinates of the pre-constructed reference point in the reference coordinate system, The pixel area corresponding to the target positioning pattern in the initial grayscale image is OK The pixel area of ​​the column.

[0043] It should be explained that if under a certain vibration function, the target vibration table actually generates less vibration on the target detection locomotive or cannot generate vibration on the target detection locomotive, then the reference similarity corresponding to the second positioning pattern is the largest. Optionally, by using a laser generator to monitor the vibrating target detection locomotive in real time, at the same time as the first positioning pattern, the displacement generated by the target detection locomotive during vibration is obtained by using the laser generator, and the coordinates of the reference point in the reference coordinate system are calculated by the displacement. Other technologies can achieve the same effect, which will not be repeated here. For example: the line connecting the laser generator and the reference point is parallel to the vertical axis of the reference coordinate system. When there is no vibration, the distance between the laser generator and the reference point is 50cm, and the coordinates corresponding to the reference point in the reference coordinate system are (10, 20, 100). At a certain moment, the distance between the laser generator and the reference point is detected by the laser generator as 49cm, and the coordinates corresponding to the reference point in the reference coordinate system are (10, 20, 51). Optionally, the laser generator is a fixed laser generator, and other technologies can achieve the same effect, which will not be described here.

[0044] Furthermore, the coordinates of the reference point in the reference coordinate system can only express the vibration displacement of the target detection locomotive as a whole, and cannot express the vibration condition of the target detection locomotive at a certain position. For example, a shock absorber at a certain position of the target detection locomotive fails, resulting in a larger displacement value at that position due to vibration under the same vibration condition.

[0045] It should be understood that, in general, there are a large number of areas with consistent grayscale values ​​in the target detection locomotive, and the target detection image in the vibration detection video stream is easily disturbed by the environment, which may result in inaccurate matching results when the extracted target positioning pattern is used to match the first positioning pattern. For example: because the proposed grayscale values ​​of the target positioning patterns are similar and are affected by the environment, multiple different first positioning patterns can be matched using the extracted target positioning pattern. Therefore, the similarity evaluation relationship formulated by the present invention also takes into account the changes in the overall vibration, so the accuracy of matching the first positioning pattern using the extracted target positioning pattern can be improved.

[0046] Further, acquiring and detecting the vibration displacement based on the second positioning pattern includes: The central pixel point is retrieved from the second positioning pattern, and the pixel point is used as the displacement pixel point. The displacement coordinates are calculated using the pre-constructed displacement conversion relationship and the displacement pixel point. The initial detection coordinates are retrieved from the target detection locomotive using the displacement pixel point. The vibration displacement is calculated based on the detection displacement coordinates and the initial detection coordinates. The displacement conversion relationship is as follows: ; in, represents the calibration parameters of the video capture unit, Represents the coordinates of the displaced pixel points, represents the intrinsic parameter matrix of the video capture unit, represents the extrinsic parameter matrix of the video capture unit, Indicates the detected displacement coordinates.

[0047] It can be understood that, in theory, the pixel point in the center of the second positioning pattern is the pixel point corresponding to the target detection point. Therefore, by converting the displaced pixel point into the detection displacement coordinates, the detection vibration displacement can be calculated by detecting the displacement coordinates and the detection initial coordinates, wherein the detection initial coordinates are the coordinates of the target detection point in the reference coordinate system. Optionally, the distance between the detection initial coordinates and the detection displacement coordinates is calculated using the distance formula between the two points, and the distance is used as the detection vibration displacement.

[0048] S5. Filter the detected vibration displacement set to obtain a target vibration displacement set.

[0049] It is understandable that the screening of the detected vibration displacement set to obtain the target vibration displacement set includes: The screening value is calculated using the detected vibration displacement set and the pre-built screening relationship, where the screening relationship is as follows: ; in, Indicates the detection of vibration displacement concentration The screening value corresponding to the detected vibration displacement, Indicates the detection of vibration displacement concentration A detection vibration displacement, Indicates the detection of vibration displacement concentration A detection vibration displacement, Indicates the total number of detected vibration displacements Detect vibration displacement; Summarizing the screening values ​​to obtain a screening value set, and performing a sorting operation on the screening values ​​in the screening value set in descending order to obtain a screening sequence, wherein the screening values ​​correspond to the detected vibration displacements one by one; The detected vibration displacements corresponding to the screening values ​​are sequentially extracted from the screening sequence, and the following operations are performed on the extracted detected vibration displacements: The extracted detected vibration displacement is eliminated from the detected vibration displacement set to obtain an updated vibration displacement set, and an estimated value is calculated based on the updated vibration displacement set and a pre-constructed estimation relation, wherein the estimation relation is as follows: ; in, Represents an estimated value, represents the coordinates corresponding to the extracted detected vibration displacement, Represents the update of the vibration displacement concentration Update vibration displacement, Indicates the update of vibration displacement concentration Update vibration displacement, Represents the update of the vibration displacement concentration Update the coordinates corresponding to the vibration displacement; Obtaining a first evaluation value using the estimated value and the extracted detection vibration displacement, wherein the first evaluation value is an absolute difference between the estimated value and the extracted detection vibration displacement; comparing the first evaluation value with a preset evaluation threshold; If the first evaluation value is less than or equal to the evaluation threshold, confirming that the detected vibration displacement set is a target vibration displacement set; Otherwise, the extracted detected vibration displacement is eliminated from the detected vibration displacement set to obtain a eliminated detected displacement set, the eliminated detected displacement set is used as the detected vibration displacement set, and the step of calculating the screening value using the detected vibration displacement set and the pre-constructed screening relationship is returned until the first evaluation value is less than or equal to the evaluation threshold, so as to obtain the target vibration displacement set.

[0050] It should be understood that, ideally, the detected vibration displacements in the detected vibration displacement set corresponding to the target detected locomotive should be roughly the same. The screening value in the screening sequence can express the degree of deviation of the detected vibration displacement from the overall situation, and the screening value in the screening sequence corresponds one-to-one to the detected vibration displacement. The estimated value refers to the value of the detected vibration displacement in the updated vibration displacement set that estimates the extracted detected vibration displacement, and when estimating, the distance factor is taken into account. The farther the distance between the detected vibration displacement in the updated vibration displacement set and the extracted detected vibration displacement, the smaller the influence of the detected vibration displacement in the updated vibration displacement set on the extracted detected vibration displacement. When the first evaluation value is less than or equal to the evaluation threshold, it indicates that the extracted detected vibration displacement is equivalent to the estimated detected vibration displacement, indicating that there is no abnormal detected vibration displacement in the detected vibration displacement set, that is, the matched second positioning patterns are all expected second positioning patterns.

[0051] S6. Acquire a fitting vibration displacement set of the target detection locomotive, wherein the fitting vibration displacement set includes a plurality of fitting vibration displacements, and the fitting vibration displacements correspond to the target detection points one by one.

[0052] It should be explained that the fitted vibration displacement set refers to the set of vibration values ​​that can be generated by the target vibration combination under ideal conditions, using the target vibration combination and the time corresponding to the extracted target detection image. For example: under ideal conditions, the vibration value that can be generated by the target vibration combination is the amplitude of the simple harmonic vibration function, then the fitted vibration displacement set includes multiple fitted vibration displacements corresponding to the target detection points one by one, and the value of the fitted vibration displacement is the amplitude.

[0053] S7. Obtain a dimension parameter set of a target detection locomotive, obtain a fitting detection model based on the fitting vibration displacement set, the dimension parameter set and the target vibration displacement set, and use a vibration feedback unit to send the fitting detection model to an initiator of a vibration test instruction to achieve vibration measurement of a heavy-load electric locomotive.

[0054] It is understandable that, in the embodiment of the present invention, the size parameter set refers to the size parameters of the surface of the target detection vehicle, for example, the length, width and height parameters of the target detection vehicle.

[0055] It should be explained that the step of obtaining the fitting detection model based on the fitting vibration displacement set, the size parameter set and the target vibration displacement set includes: Building an initial locomotive model based on the size parameter set, and retrieving a plurality of model detection points in the initial locomotive model according to the position of the target detection point in the target detection locomotive, wherein the model detection points correspond one-to-one to the target detection points; According to the position of the target detection point, matching the fitting vibration displacement in the fitting vibration displacement set with the target vibration displacement in the target vibration displacement set to obtain a plurality of matching displacement groups, wherein the matching displacement groups correspond to the target detection points one by one; Extract matching displacement groups from the multiple matching displacement groups in sequence, and perform the following operations on the extracted matching displacement groups: If the target vibration displacement exists in the extracted matching displacement group, the matching displacement group is proposed to be an empty set; Summarize the matching displacement groups that are not empty sets to obtain multiple target displacement groups; Extracting target displacement groups from the plurality of target displacement groups in sequence, and acquiring target vibration values ​​based on the extracted target displacement groups, wherein the target vibration value is a difference between the fitting vibration displacement and the target vibration displacement; The fitting vibration displacement, target vibration displacement and target vibration value corresponding to the target displacement group are used to perform a marking operation on the model detection points corresponding to the target displacement group to obtain a fitting detection model.

[0056] It should be explained that when the initial locomotive model is constructed using 3D modeling software, the dimensional parameters in the dimensional parameter set will be proportionally enlarged or reduced. Therefore, the point used to characterize the target detection point can be retrieved in the initial locomotive model through the position of the target detection point in the target detection machine. This point is the model detection point. Optionally, the model detection point is retrieved in the initial locomotive model through the coordinates corresponding to the target detection point. Other technologies can achieve the same effect, which will not be repeated here. Optionally, the initial locomotive model is constructed using SolidWorks and the dimensional parameter set. Other technologies can achieve the same effect, which will not be repeated here.

[0057] It should be understood that, because the model detection point corresponds to the target detection point one by one, the model detection point can be matched with the target detection point. Ideally, the matched fitting vibration displacement and the target vibration displacement should correspond to each other one by one, and ideally, the matched fitting vibration displacement and the target vibration displacement constitute the target displacement group. Since the acquired target vibration displacement set does not necessarily have the target vibration displacement at the coordinates corresponding to each target detection point. Therefore, when the target vibration displacement is missing in the matching displacement group, the matching displacement group is meaningless, so the matching displacement group is set to an empty set, and the matching displacement group in which the target vibration displacement and the fitting vibration displacement exist at the same time is taken as the target displacement group. The purpose of performing the marking operation on the model detection point corresponding to the target displacement group by the fitting vibration displacement, the target vibration displacement and the target vibration value corresponding to the target displacement group is to intuitively reflect the vibration situation in the target detection locomotive. For example: the model detection point corresponding to the target displacement group is annotated, wherein the fitting vibration displacement, the target vibration displacement and the target vibration value are annotated, and the marking operation can be realized. The same effect can be achieved by using other technologies, which will not be repeated here.

[0058] The present invention is to solve the problem described in the background technology. The present invention obtains a vibration function set and a velocity gradient set for simulating vibration, wherein the vibration function set includes multiple vibration functions, and the velocity gradient set includes multiple reference speeds. A vibration combination set is obtained based on the vibration function set and the velocity gradient set. It can be seen that the embodiment of the present invention takes into account that different speeds and different vibration conditions will cause different vibrations in heavy-loaded electric locomotives. Therefore, the form of a vibration combination set is adopted to analyze the situation in which different reference speeds cause vibrations of heavy-loaded electric locomotives under the same vibration function, thereby improving the intelligence level of vibration measurement of heavy-loaded electric locomotives. The present invention obtains a vibration detection video stream based on the vibration combination set, the target detection locomotive, the simulated vibration platform and the video shooting unit, and obtains a detection vibration displacement set based on the vibration detection video stream, wherein the detection vibration displacement set includes multiple detection vibration displacements. It can be seen that the present invention not only considers that different vibrations may exist at different target detection points, but also obtains the vibration conditions of the heavy-loaded electric locomotive at different times, different reference speeds, different vibration functions or different target detection points in the form of vibration detection video streams. In addition, when detecting vibration, not only the difference in the color of the heavy-loaded electric locomotive itself is considered, therefore, different target positioning patterns are formulated at different target detection points, and coordinate elements are incorporated when obtaining the second positioning pattern to improve the accuracy of obtaining the second positioning pattern, thereby improving the accuracy of vibration measurement of the heavy-loaded electric locomotive. The present invention screens the detection vibration displacement set to obtain the target vibration displacement set. It can be seen that the embodiment of the present invention not only considers the problem of inaccurate detection vibration displacement due to image recognition on the basis of being able to accurately obtain the second positioning image, but also screens the detection vibration displacement set to obtain the target vibration displacement set to improve the accuracy of vibration measurement of the heavy-loaded electric locomotive. The present invention obtains the size parameter set of the target detection locomotive, obtains the fitting detection model based on the fitting vibration displacement set, the size parameter set and the target vibration displacement set, and uses the vibration feedback unit to send the fitting detection model to the initiator of the vibration test instruction to realize the vibration measurement of the heavy-loaded electric locomotive. It can be seen that the present invention also uses the target vibration displacement set to construct vibration-related parameters for characterizing the heavy-loaded electric locomotive at different target detection points to improve the intelligence level of the vibration measurement of the heavy-loaded electric locomotive. Therefore, the present invention can improve the accuracy and intelligence level of the vibration measurement of the heavy-loaded electric locomotive.

[0059] like Figure 2 , which is a functional module diagram of a heavy-load electric locomotive vibration measurement system based on machine vision provided by one embodiment of the present invention.

[0060] The machine vision-based heavy-duty electric locomotive vibration measurement system 100 of the present invention can be installed in an electronic device. According to the functions to be implemented, the machine vision-based heavy-duty electric locomotive vibration measurement system 100 can include a vibration test environment confirmation module 101, a vibration test preparation module 102, a vibration test module 103 and a vibration test analysis module 104. The module of the present invention can also be called a unit, which refers to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, which are stored in the memory of the electronic device.

[0061] The vibration test environment confirmation module 101 is used to receive a vibration test instruction, and confirm a vibration test environment for vibration testing based on the vibration test instruction, wherein the vibration test environment includes: a heavy-load electric locomotive, a simulated vibration table and a vibration measurement system, wherein the vibration measurement system includes: a video shooting unit and a vibration feedback unit; The vibration test preparation module 102 is used to obtain a vibration function set and a velocity gradient set for simulating vibration, wherein the vibration function set includes a plurality of vibration functions, the velocity gradient set includes a plurality of reference speeds, and a vibration combination set is obtained based on the vibration function set and the velocity gradient set; A reference coordinate system is constructed, and a target detection locomotive is obtained by using the reference coordinate system and the heavy-load electric locomotive, wherein the target detection locomotive includes a plurality of target detection points; The vibration test module 103 is used to obtain a vibration detection video stream based on the vibration combination set, the target detection locomotive, the simulated vibration platform and the video shooting unit, and obtain a detection vibration displacement set based on the vibration detection video stream, wherein the detection vibration displacement set includes multiple detection vibration displacements; Filtering the detected vibration displacement set to obtain a target vibration displacement set; The vibration test analysis module 104 is used to obtain a fitting vibration displacement set of the target detection locomotive, wherein the fitting vibration displacement set includes a plurality of fitting vibration displacements, and the fitting vibration displacements correspond to the target detection points one by one; A size parameter set of a target detection locomotive is obtained, a fitting detection model is obtained based on the fitting vibration displacement set, the size parameter set and the target vibration displacement set, and a vibration feedback unit is used to send the fitting detection model to an initiator of a vibration test instruction to realize vibration measurement of a heavy-load electric locomotive.

[0062] In detail, each module in the machine vision-based heavy-duty electric locomotive vibration measurement system 100 in the embodiment of the present invention is used in the same manner as described above. Figure 1 The same technical means are used as the heavy-load electric locomotive vibration measurement method based on machine vision described in the text, and can produce the same technical effects, so they will not be repeated here.

[0063] like Figure 3 , is a schematic diagram of the structure of an electronic device for implementing a heavy-load electric locomotive vibration measurement method based on machine vision provided by an embodiment of the present invention.

[0064] The electronic device 1 may include a processor 10, a memory 11 and a bus 12, and may also include a computer program stored in the memory 11 and executable on the processor 10, such as a program for a vibration measurement method for a heavy-load electric locomotive based on machine vision.

[0065] The memory 11 includes at least one type of readable storage medium, and the readable storage medium includes a flash memory, a mobile hard disk, a multimedia card, a card-type memory (for example, an SD or DX memory, etc.), a magnetic memory, a disk, an optical disk, etc. In some embodiments, the memory 11 may be an internal storage unit of the electronic device 1, such as a mobile hard disk of the electronic device 1. In other embodiments, the memory 11 may also be an external storage device of the electronic device 1, such as a plug-in mobile hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device 1. Further, the memory 11 also includes an internal storage unit of the electronic device 1 and an external storage device. The memory 11 can not only be used to store application software and various types of data installed in the electronic device 1, such as the code of the program of the vibration measurement method of a heavy-load electric locomotive based on machine vision, but also can be used to temporarily store data that has been output or is to be output.

[0066] The processor 10 may be composed of an integrated circuit in some embodiments, for example, a single packaged integrated circuit, or a plurality of packaged integrated circuits with the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and combinations of various control chips, etc. The processor 10 is the control core (Control Unit) of the electronic device, and uses various interfaces and lines to connect various components of the entire electronic device, and executes or executes programs or modules stored in the memory 11 (such as a program for a vibration measurement method for a heavy-load electric locomotive based on machine vision, etc.), and calls data stored in the memory 11, so as to execute various functions of the electronic device 1 and process data.

[0067] The bus 12 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus 12 may be divided into an address bus, a data bus, a control bus, etc. The bus 12 is configured to realize connection and communication between the memory 11 and at least one processor 10, etc.

[0068] Figure 3 Only an electronic device with components is shown, and those skilled in the art will understand that Figure 3 The structure shown does not constitute a limitation on the electronic device 1, and may include fewer or more components than shown in the figure, or combine certain components, or arrange the components differently.

[0069] For example, although not shown, the electronic device 1 may also include a power source (such as a battery) for supplying power to various components. Preferably, the power source may be logically connected to the at least one processor 10 through a power management device, so that the power management device can realize functions such as charging management, discharging management, and power consumption management. The power source may also include one or more DC or AC power sources, recharging devices, power failure detection circuits, power converters or inverters, power status indicators, and other arbitrary components. The electronic device 1 may also include a variety of sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be repeated here.

[0070] Furthermore, the electronic device 1 may also include a network interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is generally used to establish a communication connection between the electronic device 1 and other electronic devices.

[0071] Optionally, the electronic device 1 may further include a user interface, which may be a display, an input unit (such as a keyboard), or a standard wired interface or a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, and an OLED (Organic Light-Emitting Diode) touch device. The display may also be appropriately referred to as a display screen or a display unit, which is used to display information processed in the electronic device 1 and to display a visual user interface.

[0072] The program of the heavy-load electric locomotive vibration measurement method based on machine vision stored in the memory 11 of the electronic device 1 is a combination of multiple instructions. When running in the processor 10, it can achieve: Receiving a vibration test instruction, and confirming a vibration test environment for the vibration test based on the vibration test instruction, wherein the vibration test environment includes: a heavy-load electric locomotive, a simulated vibration table and a vibration measurement system, wherein the vibration measurement system includes: a video shooting unit and a vibration feedback unit; Acquire a vibration function set and a velocity gradient set for simulating vibration, wherein the vibration function set includes a plurality of vibration functions, the velocity gradient set includes a plurality of reference speeds, and acquire a vibration combination set based on the vibration function set and the velocity gradient set; A reference coordinate system is constructed, and a target detection locomotive is obtained by using the reference coordinate system and the heavy-load electric locomotive, wherein the target detection locomotive includes a plurality of target detection points; Based on the vibration combination set, the target detection locomotive, the simulated vibration platform and the video shooting unit, a vibration detection video stream is obtained, and based on the vibration detection video stream, a detection vibration displacement set is obtained, wherein the detection vibration displacement set includes multiple detection vibration displacements; Filtering the detected vibration displacement set to obtain a target vibration displacement set; Acquire a fitting vibration displacement set of the target detection locomotive, wherein the fitting vibration displacement set includes a plurality of fitting vibration displacements, and the fitting vibration displacements correspond to the target detection points one by one; A size parameter set of a target detection locomotive is obtained, a fitting detection model is obtained based on the fitting vibration displacement set, the size parameter set and the target vibration displacement set, and a vibration feedback unit is used to send the fitting detection model to an initiator of a vibration test instruction to realize vibration measurement of a heavy-load electric locomotive.

[0073] Specifically, the specific implementation method of the processor 10 for the above instructions can refer to Figures 1 to 3 The description of the relevant steps in the corresponding embodiments will not be repeated here.

[0074] Furthermore, if the module / unit integrated in the electronic device 1 is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, and a read-only memory (ROM).

[0075] The present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor of an electronic device, the computer program can implement: Receiving a vibration test instruction, and confirming a vibration test environment for the vibration test based on the vibration test instruction, wherein the vibration test environment includes: a heavy-load electric locomotive, a simulated vibration table and a vibration measurement system, wherein the vibration measurement system includes: a video shooting unit and a vibration feedback unit; Acquire a vibration function set and a velocity gradient set for simulating vibration, wherein the vibration function set includes a plurality of vibration functions, the velocity gradient set includes a plurality of reference speeds, and acquire a vibration combination set based on the vibration function set and the velocity gradient set; A reference coordinate system is constructed, and a target detection locomotive is obtained by using the reference coordinate system and the heavy-load electric locomotive, wherein the target detection locomotive includes a plurality of target detection points; Based on the vibration combination set, the target detection locomotive, the simulated vibration platform and the video shooting unit, a vibration detection video stream is obtained, and based on the vibration detection video stream, a detection vibration displacement set is obtained, wherein the detection vibration displacement set includes multiple detection vibration displacements; Filtering the detected vibration displacement set to obtain a target vibration displacement set; Acquire a fitting vibration displacement set of the target detection locomotive, wherein the fitting vibration displacement set includes a plurality of fitting vibration displacements, and the fitting vibration displacements correspond to the target detection points one by one; A size parameter set of a target detection locomotive is obtained, a fitting detection model is obtained based on the fitting vibration displacement set, the size parameter set and the target vibration displacement set, and a vibration feedback unit is used to send the fitting detection model to an initiator of a vibration test instruction to realize vibration measurement of a heavy-load electric locomotive.

[0076] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, systems and methods can be implemented in other ways. For example, the system embodiments described above are only illustrative, and actual implementation may have other division methods.

[0077] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0078] In addition, each functional module in each embodiment of the present invention may be integrated into one processing unit, each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0079] It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0080] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. A vibration measurement method for heavy-duty electric locomotive based on machine vision, characterized in that: The method comprises: Receiving a vibration test instruction, and confirming a vibration test environment for the vibration test based on the vibration test instruction, wherein the vibration test environment includes: a heavy-load electric locomotive, a simulated vibration table and a vibration measurement system, wherein the vibration measurement system includes: a video shooting unit and a vibration feedback unit; Acquire a vibration function set and a velocity gradient set for simulating vibration, wherein the vibration function set includes a plurality of vibration functions, the velocity gradient set includes a plurality of reference speeds, and acquire a vibration combination set based on the vibration function set and the velocity gradient set; A reference coordinate system is constructed, and a target detection locomotive is obtained by using the reference coordinate system and the heavy-load electric locomotive, wherein the target detection locomotive includes a plurality of target detection points; Based on the vibration combination set, the target detection locomotive, the simulated vibration platform and the video shooting unit, a vibration detection video stream is obtained, and based on the vibration detection video stream, a detection vibration displacement set is obtained, wherein the detection vibration displacement set includes multiple detection vibration displacements; Filtering the detected vibration displacement set to obtain a target vibration displacement set; Acquire a fitting vibration displacement set of the target detection locomotive, wherein the fitting vibration displacement set includes a plurality of fitting vibration displacements, and the fitting vibration displacements correspond to the target detection points one by one; A size parameter set of a target detection locomotive is obtained, a fitting detection model is obtained based on the fitting vibration displacement set, the size parameter set and the target vibration displacement set, and a vibration feedback unit is used to send the fitting detection model to an initiator of a vibration test instruction to realize vibration measurement of a heavy-load electric locomotive.

2. The machine vision-based vibration measurement method for heavy-load electric locomotive according to claim 1, characterized in that: The step of obtaining a vibration combination set based on the vibration function set and the velocity gradient set includes: Extract vibration functions from the vibration function set in sequence, and perform the following operations on the extracted vibration functions: The extracted vibration function is matched with the velocity gradient set to obtain a vibration combination, and the vibration combinations are summarized to obtain a vibration combination set, wherein the vibration combination is as follows: ； in, Indicates the vibration combination set A vibration combination, represents the vibration function set A vibration function, represents the velocity gradient set, They represent the first reference speed, the second reference speed, and the The reference speed and A reference speed, Indicates that the velocity gradient is concentrated A reference speed.

3. The machine vision-based vibration measurement method for heavy-load electric locomotive according to claim 2, characterized in that: The method of acquiring a target detection locomotive by using a reference coordinate system and a heavy-load electric locomotive comprises: Confirming a detection area in the heavy-load electric locomotive, and acquiring a plurality of target detection points based on the reference coordinate system and the detection area; Extract target detection points from the multiple target detection points in sequence, and perform the following operations on the extracted target detection points: Acquire a detection grayscale value based on the extracted target detection point, use the detection grayscale value as the starting point of a pre-constructed region growing algorithm, and use the region growing algorithm to acquire a target growth region, wherein the grayscale values ​​of the pixel points corresponding to the target growth region are all the same; In the detection area corresponding to the target growth area, a target positioning pattern is confirmed based on the detection grayscale value, wherein the target positioning pattern is a square chessboard pattern in which a preset first grayscale value and a preset second grayscale value are alternately arranged, and both the first grayscale value and the second grayscale value are different from the detection grayscale value, and the side length of the square chessboard pattern is preset to be (2q+1), wherein q is an integer greater than or equal to 1; The center of the target positioning pattern is fixed to the target detection point to obtain the target detection locomotive.

4. The machine vision-based vibration measurement method for heavy-load electric locomotive according to claim 3, characterized in that: The step of obtaining a vibration detection video stream based on the vibration combination set, the target detection locomotive, the simulated vibration platform and the video shooting unit includes: Extract vibration combinations from the vibration combination set in sequence, and perform the following operations on the extracted vibration combinations: A plurality of target vibration combinations are obtained based on the extracted vibration combinations, wherein the target vibration combinations are as follows: ； in, Indicates the vibration combination set The vibration combination corresponds to the target vibration combination; Extract target vibration combinations from multiple target vibration combinations in sequence and perform the following operations on the extracted target vibration combinations: The extracted target vibration combination is input into a simulated vibration table to obtain a target vibration table, and a vibration operation is performed on a target detection locomotive using the target vibration table, wherein the duration of the vibration operation is preset, and a video shooting unit is used to shoot the target vibration table in the vibration operation to obtain a vibration detection video stream.

5. The machine vision-based vibration measurement method for heavy-load electric locomotive according to claim 4, characterized in that: The step of acquiring a detected vibration displacement set based on the vibration detection video stream comprises: Based on the target detection locomotive, an initial detection image is obtained, an initial frame number of the vibration detection video stream is obtained, target detection images are sequentially extracted from the vibration detection video stream based on the initial frame number, and the following operations are performed on the extracted target detection images: Extract target positioning patterns from the target detection locomotive in sequence, and perform the following operations on the extracted target positioning patterns: Performing a grayscale operation on the initial detection image to obtain an initial grayscale image, and acquiring an initial detection window based on the initial grayscale image and the extracted target positioning pattern, wherein the initial detection window is a pixel area corresponding to the target positioning pattern in the initial grayscale image; Performing a grayscale operation on the extracted target detection image to obtain a target grayscale image, and using the initial detection window and the target grayscale image to obtain a plurality of different first positioning patterns; Extracting first positioning patterns from the multiple different first positioning patterns in sequence, and performing the following operations on the extracted first positioning patterns: Calculate reference similarity using a pre-constructed similarity evaluation relationship and the extracted first positioning pattern, summarize the reference similarities to obtain a reference similarity set, identify a second positioning pattern using the reference similarity set, wherein the second positioning pattern is the first positioning pattern corresponding to the largest reference similarity in the reference similarity set, and obtain the detected vibration displacement based on the second positioning pattern; The detected vibration displacements are summarized to obtain a detected vibration displacement set.

6. The machine vision-based vibration measurement method for heavy-load electric locomotive according to claim 5, characterized in that: The similarity evaluation relationship is as follows: ； in, represents the reference similarity, are all preset coefficients. Represents the grayscale value of the pixel corresponding to the target positioning pattern in the initial grayscale image, Represents the mean grayscale value of the pixel points corresponding to the target positioning pattern in the initial grayscale image, represents the gray value of the pixel corresponding to the first positioning pattern, represents the mean value of the grayscale values ​​of the pixels corresponding to the first positioning pattern, Indicates the first positioning pattern corresponding to the Line The pixel point or target positioning pattern of the column corresponds to the first Line Column pixels, Represents the coordinates of the target detection point corresponding to the target positioning pattern in the reference coordinate system, Represents the coordinates of the pre-constructed reference point in the reference coordinate system, The pixel area corresponding to the target positioning pattern in the initial grayscale image is OK The pixel area of ​​the column.

7. The machine vision-based vibration measurement method for heavy-load electric locomotive according to claim 6, characterized in that: The acquiring and detecting vibration displacement based on the second positioning pattern includes: The central pixel point is retrieved from the second positioning pattern, and the pixel point is used as the displacement pixel point. The displacement coordinates are calculated using the pre-constructed displacement conversion relationship and the displacement pixel point. The initial detection coordinates are retrieved from the target detection locomotive using the displacement pixel point. The vibration displacement is calculated based on the detection displacement coordinates and the initial detection coordinates. The displacement conversion relationship is as follows: ； in, Represents the calibration parameters of the video capture unit, Represents the coordinates of the displaced pixel points, represents the intrinsic parameter matrix of the video capture unit, represents the extrinsic parameter matrix of the video capture unit, Indicates the detected displacement coordinates.

8. The machine vision-based vibration measurement method for heavy-load electric locomotive according to claim 7, characterized in that: The screening of the detected vibration displacement set to obtain a target vibration displacement set includes: The screening value is calculated using the detected vibration displacement set and the pre-built screening relationship, where the screening relationship is as follows: ； in, Indicates the detection of vibration displacement concentration The screening value corresponding to the detected vibration displacement, Indicates the detection of vibration displacement concentration A detection vibration displacement, Indicates the detection of vibration displacement concentration A detection vibration displacement, Indicates the total number of detected vibration displacements Detect vibration displacement; Summarizing the screening values ​​to obtain a screening value set, and performing a sorting operation on the screening values ​​in the screening value set in descending order to obtain a screening sequence, wherein the screening values ​​correspond to the detected vibration displacements one by one; The detected vibration displacements corresponding to the screening values ​​are sequentially extracted from the screening sequence, and the following operations are performed on the extracted detected vibration displacements: The extracted detected vibration displacement is eliminated from the detected vibration displacement set to obtain an updated vibration displacement set, and an estimated value is calculated based on the updated vibration displacement set and a pre-constructed estimation relation, wherein the estimation relation is as follows: ； in, Represents an estimated value, represents the coordinates corresponding to the extracted detected vibration displacement, Represents the update of the vibration displacement concentration Update vibration displacement, Indicates the update of vibration displacement concentration Update vibration displacement, Represents the update of the vibration displacement concentration Update the coordinates corresponding to the vibration displacement; Obtaining a first evaluation value using the estimated value and the extracted detection vibration displacement, wherein the first evaluation value is an absolute difference between the estimated value and the extracted detection vibration displacement; comparing the first evaluation value with a preset evaluation threshold; If the first evaluation value is less than or equal to the evaluation threshold, confirming that the detected vibration displacement set is a target vibration displacement set; Otherwise, the extracted detected vibration displacement is eliminated from the detected vibration displacement set to obtain a eliminated detected displacement set, the eliminated detected displacement set is used as the detected vibration displacement set, and the step of calculating the screening value using the detected vibration displacement set and the pre-constructed screening relationship is returned until the first evaluation value is less than or equal to the evaluation threshold, so as to obtain the target vibration displacement set.

9. The machine vision-based vibration measurement method for heavy-load electric locomotive according to claim 8, characterized in that: The acquiring of the fitting detection model based on the fitting vibration displacement set, the size parameter set and the target vibration displacement set includes: Building an initial locomotive model based on the size parameter set, and retrieving a plurality of model detection points in the initial locomotive model according to the position of the target detection point in the target detection locomotive, wherein the model detection points correspond one-to-one to the target detection points; According to the position of the target detection point, matching the fitting vibration displacement in the fitting vibration displacement set with the target vibration displacement in the target vibration displacement set to obtain a plurality of matching displacement groups, wherein the matching displacement groups correspond to the target detection points one by one; The matching displacement groups are sequentially extracted from the multiple matching displacement groups, and the following operations are performed on the extracted matching displacement groups: If the target vibration displacement exists in the extracted matching displacement group, the matching displacement group is proposed to be an empty set; Summarize the matching displacement groups that are not empty sets to obtain multiple target displacement groups; Extracting target displacement groups from the plurality of target displacement groups in sequence, and acquiring target vibration values ​​based on the extracted target displacement groups, wherein the target vibration value is a difference between the fitting vibration displacement and the target vibration displacement; The fitting vibration displacement, target vibration displacement and target vibration value corresponding to the target displacement group are used to perform a marking operation on the model detection points corresponding to the target displacement group to obtain a fitting detection model.

10. A heavy-load electric locomotive vibration measurement system based on machine vision, characterized in that: The system comprises: A vibration test environment confirmation module, used for receiving a vibration test instruction, and confirming a vibration test environment for vibration testing based on the vibration test instruction, wherein the vibration test environment includes: a heavy-load electric locomotive, a simulated vibration table and a vibration measurement system, wherein the vibration measurement system includes: a video shooting unit and a vibration feedback unit; A vibration test preparation module, used to obtain a vibration function set and a velocity gradient set for simulating vibration, wherein the vibration function set includes a plurality of vibration functions, the velocity gradient set includes a plurality of reference speeds, and a vibration combination set is obtained based on the vibration function set and the velocity gradient set; A reference coordinate system is constructed, and a target detection locomotive is obtained by using the reference coordinate system and the heavy-load electric locomotive, wherein the target detection locomotive includes a plurality of target detection points; A vibration test module, used for acquiring a vibration detection video stream based on the vibration combination set, the target detection locomotive, the simulated vibration platform and the video shooting unit, and acquiring a detection vibration displacement set based on the vibration detection video stream, wherein the detection vibration displacement set includes a plurality of detection vibration displacements; Filtering the detected vibration displacement set to obtain a target vibration displacement set; A vibration test analysis module, used for obtaining a fitting vibration displacement set of a target detection locomotive, wherein the fitting vibration displacement set includes a plurality of fitting vibration displacements, and the fitting vibration displacements correspond to the target detection points one by one; A size parameter set of a target detection locomotive is obtained, a fitting detection model is obtained based on the fitting vibration displacement set, the size parameter set and the target vibration displacement set, and a vibration feedback unit is used to send the fitting detection model to an initiator of a vibration test instruction to realize vibration measurement of a heavy-load electric locomotive.

Images