Guide wheel seat defect identification and analysis system and method based on machine vision

Abstract

The invention relates to the technical field of image processing and analysis, in particular to a guide wheel seat defect recognition and analysis system and method based on machine vision, and the method comprises the steps: importing an oil duct internal structure image into a guide wheel seat oil duct defect state detection model, and analyzing the defect state of a guide wheel seat oil duct; the characteristic parameter data and the oil transportation flow data of the guide wheel seat oil duct are imported into a guide wheel seat oil duct oil transportation state analysis model, and the oil transportation state of the guide wheel seat oil duct is analyzed; according to the defect state analysis result and the oil transportation state analysis result, the operation state of the guide wheel base oil duct is evaluated; according to the defect state analysis result and the operation evaluation state result, a guide wheel seat oil duct operation state prediction model is constructed and used for predicting the current operation state of the guide wheel seat oil duct; and repairing the defects of the guide wheel seat oil duct according to the running prediction result of the current guide wheel seat oil duct. The overall operation efficiency of the guide wheel seat can be improved, and the risk of guide wheel seat faults is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing and analysis, and particularly to a guide wheel seat defect recognition and analysis system and method based on machine vision. Background Art

[0002] As an important component of a transmission, the guide wheel seat can be specifically divided into an oil inlet guide wheel seat and an oil return guide wheel seat according to its function and position; through the joint cooperation of the oil inlet guide wheel seat and the oil return guide wheel seat, the smooth operation of the transmission can be ensured. Among them, the oil inlet guide wheel seat is located at the front end of the transmission and is used to guide the working oil into the inside of the guide wheel group, so that the transmission can produce a variable pitch effect; the oil return guide wheel seat is located at the rear end of the transmission and is used to guide the working oil back from the guide wheel group to the fuel tank, ensuring the continuous operation of the transmission, and at the same time preventing excessive consumption and waste of the working oil. However, when there are defects in the guide wheel seat, whether it is the oil inlet guide wheel seat or the oil return guide wheel seat, it will affect the performance and operation safety of the transmission. The defects will cause leakage of the working oil, which will not only reduce the operation efficiency of the transmission, but may even cause damage to the components around the guide wheel seat; the defects of the guide wheel seat may not only cause leakage of the working oil inside the transmission, but also cause abnormal internal pressure of the transmission, thereby affecting the accuracy and stability of the transmission ratio, and even to a certain extent, may cause the transmission to fail completely. Therefore, identifying and analyzing the defects of the guide wheel seat and analyzing and warning the possible defect risks of the guide wheel seat can ensure the normal and safe operation of the transmission.

[0003] When analyzing the defects of the guide wheel seat in the prior art, it is often limited to the macroscopic defect detection on the surface of the guide wheel seat, such as obvious defects like cracks and burrs. This detection method does help to evaluate the casting process quality of the guide wheel seat, because surface defects often directly reflect problems in the casting process. However, the prior art does not consider the analysis of subtle defects in the oil channels inside the guide wheel seat. As a key structure inside the guide wheel seat, the oil channels are responsible for the delivery of lubricating oil, and their integrity and efficiency are crucial for the smooth operation of the mechanical system. Some subtle internal defects, such as tiny cracks, roughness on the inner wall of the oil channels, or impurity deposits inside the oil channels, although these internal defects do not have a direct impact on the macroscopic evaluation of the casting process, they may affect the oil delivery efficiency of the oil channels during the long-term operation of the mechanical system, thereby causing a decline in the overall performance of the transmission and a risk of failure; therefore, when identifying and analyzing the defects of the guide wheel seat, the prior art should not ignore the impact of internal defects in the oil channels on the overall operation efficiency of the guide wheel seat.

[0004] To solve these problems, the present application designs a guide wheel seat defect recognition and analysis system and method based on machine vision. Summary of the Invention

[0005] The object of the present invention is to provide a guide wheel seat defect recognition and analysis system and method based on machine vision. By comprehensively considering the defect condition and oil delivery condition of the guide wheel seat oil passage, the operating state of the guide wheel seat oil passage is analyzed, so that it is possible to predict whether the operating state of the guide wheel seat oil passage will be abnormal in the future according to the existing defect condition; help producers to detect unqualified guide wheel seats more timely and reduce the probability of failures during the use of the guide wheel seat.

[0006] The present invention is implemented as follows: In a first aspect, the present invention provides a guide wheel seat defect recognition and analysis method based on machine vision, including the following steps: S1. Obtain the internal structure image of the oil passage of the historical guide wheel seat through an image sensor, and at the same time obtain the characteristic parameter data and oil delivery flow data of the historical guide wheel seat oil passage; S2. Import the internal structure image of the oil passage into the guide wheel seat oil passage defect state detection model to analyze the defect state of the guide wheel seat oil passage; import the characteristic parameter data and oil delivery flow data of the guide wheel seat oil passage into the guide wheel seat oil passage oil delivery state analysis model to analyze the oil delivery state of the guide wheel seat oil passage; S3. Evaluate the operating state of the guide wheel seat oil passage according to the defect state analysis result and the oil delivery state analysis result; S4. Construct a guide wheel seat oil passage operating state prediction model according to the defect state analysis result and the operating evaluation state result for predicting the operating state of the current guide wheel seat oil passage; S5. Repair the defects of the guide wheel seat oil passage according to the operating prediction result of the current guide wheel seat oil passage.

[0007] Preferably, on the basis of the above solution, the step S2 includes the following specific steps: S21. Extract the internal structure image of the oil passage of the historical guide wheel seat; S22. Import the internal structure image of the oil passage of the historical guide wheel seat into the oil passage defect state coefficient calculation formula to calculate the oil passage defect state coefficient of the historical guide wheel seat; the oil passage defect state coefficient calculation formula is: ; Wherein, Cz represents the oil passage defect state coefficient of the historical guide wheel seat, n is the number of internal structure images of the oil passage in the historical guide wheel seat obtained by the image sensor, Ati represents the number of pixel points in the internal structure image of the i-th oil passage, Adi represents the number of pixel points occupied by the defect area in the internal structure image of the i-th oil passage, Udi represents the average pixel value of the defect area in the internal structure image of the i-th oil passage, Uhi represents the average pixel value of the non-defect area in the internal structure image of the i-th oil passage, Umaxi represents the maximum value of the difference between the pixel values of all pixel points in the internal structure image of the i-th oil passage, Si represents the standard deviation of the pixel values of all pixel points in the internal structure image of the i-th oil passage, Ui represents the average value of the pixel values of all pixel points in the internal structure image of the i-th oil passage, and i is any one of 1 to n.

[0008] Preferably, on the basis of the above solution, the step S2 further includes the following specific contents: S23. Extract the characteristic parameter data and oil delivery flow data of the oil passage of the historical guide wheel seat; S24. Substitute the characteristic parameter data and oil delivery flow data of the oil passage of the historical guide wheel seat into the oil passage oil delivery state coefficient calculation formula to calculate the oil passage oil delivery state coefficient of the historical guide wheel seat; the oil passage oil delivery state coefficient calculation formula is: ; Wherein, Sz represents the oil passage oil delivery state coefficient of the historical guide wheel seat, A represents the cross-sectional area of the oil passage of the historical guide wheel seat in the characteristic parameter data, L represents the length of the oil passage of the historical guide wheel seat in the characteristic parameter data, Sin represents the cross-sectional area of the oil inlet of the oil passage of the historical guide wheel seat in the characteristic parameter data, Sout represents the cross-sectional area of the oil outlet of the oil passage of the historical guide wheel seat in the characteristic parameter data; Qin represents the oil inlet volume input from the oil inlet of the oil passage to the oil passage in the oil delivery flow data, and Qout represents the oil outlet volume output from the oil outlet of the oil passage in the oil delivery flow data.

[0009] Preferably, on the basis of the above solution, the step S3 includes the following specific steps: S31. Obtain the oil passage defect state coefficient and oil passage oil delivery state coefficient of the calculated historical guide wheel seat; S32. Substitute the oil passage defect state coefficient and oil passage oil delivery state coefficient of the historical guide wheel seat into the oil passage operation state abnormal coefficient calculation formula to calculate the oil passage operation state abnormal coefficient of the historical guide wheel seat; the oil passage operation state abnormal coefficient calculation formula is: ; Wherein, Yc represents the oil passage operation state abnormal coefficient of the historical guide wheel seat.

[0010] Preferably, on the basis of the above solution, the step S4 includes the following specific steps: S41. Obtain the sample data of the guide wheel seat oil passage for training the prediction model of the operating state of the guide wheel seat oil passage. The sample data of the guide wheel seat oil passage includes the calculated oil passage defect state coefficients and oil passage operating state abnormality coefficients of multiple historical guide wheel seats, and also includes the characteristic parameter data of multiple historical guide wheel seats; S42. Divide the sample data of the guide wheel seat oil passage for training the prediction model of the operating state of the guide wheel seat oil passage into an oil passage sample training set and an oil passage sample test set. Construct a regression network model. Use the oil passage defect state coefficients and characteristic parameter data of the historical guide wheel seats in the oil passage sample training set as the input of the regression network model, and use the oil passage operating state abnormality coefficients of the historical guide wheel seats in the oil passage sample training set as the output of the regression network model. Train the regression network model to obtain an initial regression network model; Use the mean squared error algorithm to evaluate the model effect of the initial regression network model, and select the corresponding initial regression network model greater than or equal to the preset evaluation value as the prediction model of the operating state of the guide wheel seat oil passage; S43. Calculate the oil passage defect state coefficient of the current guide wheel seat, and obtain the characteristic parameter data of the oil passage of the current guide wheel seat. Input the oil passage defect state coefficient and characteristic parameter data of the current guide wheel seat into the prediction model of the operating state of the guide wheel seat oil passage, and output the predicted oil passage operating state abnormality coefficient of the current guide wheel seat.

[0011] Preferably, based on the above solution, the step S5 includes the following specific steps: S51. Obtain the predicted oil passage operating state abnormality coefficient of the current guide wheel seat; S52. Preset an operating state abnormality threshold. When the predicted oil passage operating state abnormality coefficient of the current guide wheel seat is greater than the operating state abnormality threshold, give a warning to the maintenance personnel for repairing the defects of the guide wheel seat oil passage.

[0012] In a second aspect, the present invention provides a guide wheel seat defect identification and analysis system based on machine vision, including: A data acquisition module, configured to obtain the internal structure image of the oil passage of the historical guide wheel seat through an image sensor, and at the same time obtain the characteristic parameter data and oil delivery flow data of the oil passage of the historical guide wheel seat; A guide wheel seat oil passage state analysis module, configured to import the internal structure image of the oil passage into the guide wheel seat oil passage defect state detection model to analyze the defect state of the guide wheel seat oil passage; Import the characteristic parameter data and oil delivery flow data of the guide wheel seat oil passage into the guide wheel seat oil passage oil delivery state analysis model to analyze the oil delivery state of the guide wheel seat oil passage; A guide wheel seat oil passage operating state evaluation module, configured to evaluate the operating state of the guide wheel seat oil passage according to the defect state analysis result and the oil delivery state analysis result; The guide wheel seat oil passage operation status prediction module is used to construct a guide wheel seat oil passage operation status prediction model based on the defect status analysis result and the operation evaluation status result, and is used to predict the operation status of the current guide wheel seat oil passage; The oil passage defect warning module is used to repair the guide wheel seat oil passage defect according to the operation prediction result of the current guide wheel seat oil passage; The control module is used to control the operation of the data acquisition module, the guide wheel seat oil passage status analysis module, the guide wheel seat oil passage operation status evaluation module, the guide wheel seat oil passage operation status prediction module, and the oil passage defect warning module.

[0013] In a third aspect, the present invention provides an electronic device, including: a processor and a memory. Among them, a computer program that can be called by the processor is stored in the memory, and the processor executes the guide wheel seat defect recognition and analysis method based on machine vision by calling the computer program stored in the memory.

[0014] Compared with the prior art, the present invention has the following advantages and beneficial effects: The present invention imports the internal structure image of the oil passage into the guide wheel seat oil passage defect status detection model to analyze the defect status of the guide wheel seat oil passage; imports the characteristic parameter data and oil transmission flow data of the guide wheel seat oil passage into the guide wheel seat oil passage oil transmission status analysis model to analyze the oil transmission status of the guide wheel seat oil passage; evaluates the operation status of the guide wheel seat oil passage according to the defect status analysis result and the oil transmission status analysis result; constructs a guide wheel seat oil passage operation status prediction model based on the defect status analysis result and the operation evaluation status result, and is used to predict the operation status of the current guide wheel seat oil passage; repairs the guide wheel seat oil passage defect according to the operation prediction result of the current guide wheel seat oil passage. It can improve the overall operation efficiency of the guide wheel seat and reduce the risk of guide wheel seat failures. Description of the Drawings

[0015] By reading the detailed description of the non-restrictive embodiments with reference to the following drawings, other features, purposes, and advantages of the present invention will become more obvious: Figure 1 It is a schematic diagram of the overall process of the guide wheel seat defect recognition and analysis method based on machine vision of the present invention; Figure 2 It is a schematic diagram of the structure of the guide wheel seat defect recognition and analysis system based on machine vision of the present invention; Figure 3 It is a schematic diagram of the structure of a guide wheel seat in the guide wheel seat defect recognition and analysis method based on machine vision of the present invention. Detailed Embodiments

[0016] The technical solution of the present invention will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present invention and the specific features in the embodiments are detailed descriptions of the technical solution of the present invention, rather than limitations on the technical solution of the present invention. Without conflict, the technical features in the embodiments of the present invention and the embodiments can be combined with each other.

[0017] Embodiment 1 As Figure 3 shown, this embodiment provides a structural schematic diagram of a guide wheel seat. As an important component in the transmission, the guide wheel seat is mainly responsible for managing the flow of oil between the guide wheel groups in the transmission. Among them, the oil inlet guide wheel seat is responsible for sending oil into the guide wheel group to help the transmission achieve the variable pitch effect; while the oil return guide wheel seat is responsible for recycling the oil from the guide wheel group into the fuel tank, enabling the oil to be recycled and saving the use cost of the oil; during operation, the guide wheel seat controls the flow of oil between the guide wheel groups to ensure that the normal oil pressure can be maintained inside the transmission, thereby ensuring the stable operation of the transmission system; the operating state of the guide wheel seat directly affects the normal operation of the transmission; therefore, this embodiment comprehensively considers the internal defect state of the oil passage of the guide wheel seat and the state of the oil transported inside the oil passage during daily operation, and then analyzes whether the operating state of the guide wheel seat is abnormal; it can improve the production qualification rate of the guide wheel seat and avoid unqualified guide wheel seats from affecting the performance and operating safety of the transmission.

[0018] As Figure 1 shown, this embodiment provides a method for defect recognition and analysis of a guide wheel seat based on machine vision, which specifically includes the following steps: S1. Obtain the internal structure image of the oil passage of the historical guide wheel seat through an image sensor, and simultaneously obtain the characteristic parameter data and oil delivery flow data of the oil passage of the historical guide wheel seat; S2. Import the internal structure image of the oil passage into the defect state detection model of the guide wheel seat oil passage to analyze the defect state of the guide wheel seat oil passage; import the characteristic parameter data and oil delivery flow data of the guide wheel seat oil passage into the oil delivery state analysis model of the guide wheel seat oil passage to analyze the oil delivery state of the guide wheel seat oil passage; S3. Evaluate the operating state of the guide wheel seat oil passage according to the defect state analysis result and the oil delivery state analysis result; S4. Construct an operating state prediction model for the guide wheel seat oil passage according to the defect state analysis result and the operating evaluation state result, and use it to predict the operating state of the current guide wheel seat oil passage; S5. Repair the defects of the guide wheel seat oil passage according to the operating prediction result of the current guide wheel seat oil passage.

[0019] As a preferred technical solution of the present invention, in step S2, by processing the internal structure image of the guide wheel seat oil passage, the pixel values of the pixel points in the defective area and the defect-free area in the image are extracted respectively; the state of the defective area in the oil passage is described through mean difference analysis; by analyzing the differences in the pixel values of all pixel points in the image, the roughness of the inner wall of the guide wheel seat oil passage is quantified; during the oil delivery process of the guide wheel seat, both defects and the roughness of the inner wall surface will affect the flow of the oil. For example, obvious defects and relatively rough inner wall surfaces will both generate resistance to the flow of the oil, and even cause a part of the oil to remain inside the oil passage; further affecting the operating state of the oil passage; therefore, in this embodiment, when evaluating the operating state of the guide wheel seat oil passage, the influence brought by the defect state of the oil passage is fully considered through the specific content of step S2; step S2 includes the following specific steps: S21. Extract the internal structure image of the oil passage of the historical guide wheel seat; S22. Import the internal structure image of the oil passage of the historical guide wheel seat into the oil passage defect state coefficient calculation formula to calculate the oil passage defect state coefficient of the historical guide wheel seat; the oil passage defect state coefficient calculation formula is: ; In the formula, Cz represents the oil passage defect state coefficient of the historical guide wheel seat, n is the number of internal structure images of the oil passage in the historical guide wheel seat obtained through the image sensor, Ati represents the number of pixel points in the i-th internal structure image of the oil passage, Adi represents the number of pixel points occupied by the defective area in the i-th internal structure image of the oil passage, Udi represents the average pixel value of the defective area in the i-th internal structure image of the oil passage, Uhi represents the average pixel value of the defect-free area in the i-th internal structure image of the oil passage, Umaxi represents the maximum value of the differences between the pixel values of all pixel points in the i-th internal structure image of the oil passage, Si represents the standard deviation of the pixel values of all pixel points in the i-th internal structure image of the oil passage, Ui represents the average value of the pixel values of all pixel points in the i-th internal structure image of the oil passage, and i is any one of 1 to n.

[0020] As a preferred technical solution of the present invention, step S2 takes into account the internal defect state of the guide wheel seat oil passage while not ignoring the influence of the oil delivery state of the guide wheel seat during actual operation on its operating state; in this embodiment, step S2 further considers the main influence of the change in the oil volume during the oil delivery process of the guide wheel seat oil passage on the oil delivery state of the guide wheel seat oil passage; of course, the change in the oil volume is also inseparable from the internal structure of the guide wheel seat oil passage, such as the size difference between the oil inlet and the oil outlet of the guide wheel seat. When the oil inlet is large and the oil outlet is small, the outflow of the oil during the flow process is often hindered; at the same time, the internal volume of the oil passage will also inevitably affect the oil delivery state of the guide wheel seat; when the internal volume of the oil passage is much larger than the oil inlet volume of the oil in the guide wheel seat, the flow of the oil in the oil passage often slows down, thereby affecting the oil delivery efficiency of the guide wheel seat oil passage and further affecting the oil delivery state of the guide wheel seat oil passage. Therefore, in order to quantify the oil delivery state of the guide wheel seat, step S2 further includes the following specific contents: S23. Extract the characteristic parameter data and oil delivery flow data of the historical guide wheel seat oil passage; S24. Substitute the characteristic parameter data and oil delivery flow data of the historical guide wheel seat oil passage into the oil passage oil delivery state coefficient calculation formula to calculate the oil passage oil delivery state coefficient of the historical guide wheel seat; the oil passage oil delivery state coefficient calculation formula is: ; In the formula, Sz represents the oil passage oil delivery state coefficient of the historical guide wheel seat, A represents the cross-sectional area of the historical guide wheel seat oil passage in the characteristic parameter data, L represents the length of the historical guide wheel seat oil passage in the characteristic parameter data, Sin represents the cross-sectional area of the oil inlet of the historical guide wheel seat oil passage in the characteristic parameter data, Sout represents the cross-sectional area of the oil outlet of the historical guide wheel seat oil passage in the characteristic parameter data; Qin represents the oil inlet volume input from the oil inlet of the oil passage into the oil passage in the oil delivery flow data, and Qout represents the oil outlet volume output from the oil outlet of the oil passage in the oil delivery flow data.

[0021] As a preferred technical solution of the present invention, step S3 evaluates the operating state of the guide wheel seat oil passage by combining the oil passage defect state coefficient and the oil passage oil delivery state coefficient, where the defect state coefficient is used to reflect the influence of its internal damage on the operating state. Of course, this influence does not exist independently, but jointly affects the operating state of the guide wheel seat oil passage with the actual oil delivery state of the guide wheel seat; in step S3, by adding 1 to the oil passage defect state coefficient, it can be ensured that when there are no defects in the guide wheel seat oil passage, the oil passage oil delivery state can also affect the oil passage operating state; in step S3, by adding 1 to the oil passage oil delivery state coefficient, it is avoided that when the oil passage oil delivery state coefficient appears as an extreme value, the oil passage operating state abnormal coefficient can still accurately reflect whether there is an abnormality in the oil passage operating state of the guide wheel seat. In this embodiment, step S3 includes the following specific steps: S31. Obtain the calculated oil passage defect status coefficient and oil passage oil transmission status coefficient of the historical guide wheel seat; S32. Substitute the oil passage defect status coefficient and oil passage oil transmission status coefficient of the historical guide wheel seat into the calculation formula of the oil passage operation status abnormal coefficient to calculate the oil passage operation status abnormal coefficient of the historical guide wheel seat; the calculation formula of the oil passage operation status abnormal coefficient is: ; In the formula, Yc represents the oil passage operation status abnormal coefficient of the historical guide wheel seat.

[0022] As a preferred technical solution of the present invention, step S4 includes the following specific steps: S41. Obtain the guide wheel seat oil passage sample data for training the guide wheel seat oil passage operation status prediction model. The guide wheel seat oil passage sample data includes the calculated oil passage defect status coefficients and oil passage operation status abnormal coefficients of multiple historical guide wheel seats, and also includes the characteristic parameter data of multiple historical guide wheel seats; S42. Divide the guide wheel seat oil passage sample data for training the guide wheel seat oil passage operation status prediction model into an oil passage sample training set and an oil passage sample test set, construct a regression network model, use the oil passage defect status coefficient and characteristic parameter data of the historical guide wheel seat in the oil passage sample training set as the input of the regression network model, and use the oil passage operation status abnormal coefficient of the historical guide wheel seat in the oil passage sample training set as the output of the regression network model to train the regression network model to obtain an initial regression network model; use the equalization error algorithm to evaluate the model effect of the initial regression network model, and select the corresponding initial regression network model greater than or equal to the preset evaluation value as the guide wheel seat oil passage operation status prediction model; S43. Calculate the oil passage defect status coefficient of the current guide wheel seat, obtain the characteristic parameter data of the current guide wheel seat oil passage, and input the oil passage defect status coefficient and characteristic parameter data of the current guide wheel seat into the guide wheel seat oil passage operation status prediction model to output the predicted oil passage operation status abnormal coefficient of the current guide wheel seat.

[0023] As a preferred technical solution of the present invention, step S5 includes the following specific steps: S51. Obtain the predicted oil passage operation status abnormal coefficient of the current guide wheel seat; S52. A preset abnormal operation state threshold. When the abnormal coefficient of the oil passage operation state of the current guide wheel seat obtained by prediction is greater than the abnormal operation state threshold, a warning for repairing the defect of the oil passage of the guide wheel seat is given to the maintenance personnel. Among them, the value-taking method of the abnormal operation state threshold is as follows: Obtain the internal structure images of the oil passages of multiple guide wheel seats in history and the corresponding characteristic parameter data and oil delivery flow data; Substitute the internal structure images of the oil passages of the guide wheel seats and the corresponding characteristic parameter data and oil delivery flow data into the calculation formula of the abnormal coefficient of the oil passage operation state to calculate the abnormal coefficients of the oil passage operation states of multiple guide wheel seats in history; Obtain the corresponding abnormal operation state judgment results of the oil passages of multiple guide wheel seats in history, and import the abnormal coefficient of the oil passage operation state and the abnormal operation state judgment results into the fitting software to output the value of the corresponding abnormal operation state threshold that meets the highest abnormal operation state judgment accuracy rate.

[0024] Embodiment 2 As Figure 2 shown, this embodiment provides a guide wheel seat defect recognition and analysis system based on machine vision, including: A data acquisition module, configured to acquire the internal structure image of the oil passage of the historical guide wheel seat through an image sensor, and at the same time acquire the characteristic parameter data and oil delivery flow data of the oil passage of the historical guide wheel seat; A guide wheel seat oil passage state analysis module, configured to import the internal structure image of the oil passage into the guide wheel seat oil passage defect state detection model to analyze the defect state of the guide wheel seat oil passage; Import the characteristic parameter data and oil delivery flow data of the guide wheel seat oil passage into the guide wheel seat oil passage oil delivery state analysis model to analyze the oil delivery state of the guide wheel seat oil passage; A guide wheel seat oil passage operation state evaluation module, configured to evaluate the operation state of the guide wheel seat oil passage according to the defect state analysis result and the oil delivery state analysis result; A guide wheel seat oil passage operation state prediction module, configured to construct a guide wheel seat oil passage operation state prediction model according to the defect state analysis result and the operation evaluation state result, and be used to predict the operation state of the current guide wheel seat oil passage; An oil passage defect warning module, configured to repair the defect of the guide wheel seat oil passage according to the operation prediction result of the current guide wheel seat oil passage; A control module, configured to control the operation of the data acquisition module, the guide wheel seat oil passage state analysis module, the guide wheel seat oil passage operation state evaluation module, the guide wheel seat oil passage operation state prediction module, and the oil passage defect warning module.

[0025] For the parameters and the steps of each unit module in the above-mentioned guide wheel seat defect recognition and analysis system based on machine vision of the present invention to implement corresponding functions, reference can be made to the parameters and steps in the embodiments of the guide wheel seat defect recognition and analysis method based on machine vision in the above text, which will not be elaborated here.

[0026] Embodiment 3 An electronic device according to an embodiment of the present invention includes: a processor and a memory. Among them, a computer program that can be called by the processor is stored in the memory. The processor executes a defect recognition and analysis method for a guide wheel seat based on machine vision by calling the computer program stored in the memory. It should be noted that: all computer programs of the defect recognition and analysis method for the guide wheel seat based on machine vision are implemented in the C language. Among them, the data acquisition module, the guide wheel seat oil passage state analysis module, the guide wheel seat oil passage operation state evaluation module, the guide wheel seat oil passage operation state prediction module, the oil passage defect warning module, and the control module are all controlled by a remote server.

[0027] In the description of this specification, the description with reference to terms such as "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in a suitable manner in any one or more embodiments or examples.

[0028] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to the specific embodiments described. Obviously, many modifications and variations can be made according to the content of this specification. These embodiments are selected and specifically described in this specification to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and utilize the present invention well. The present invention is only limited by the claims and their full scope and equivalents.

Claims

1. A guide wheel seat defect recognition and analysis method based on machine vision, characterized in that: The steps include: S1. Obtaining an internal structural image of the oil passage of the historical guide wheel seat through an image sensor, and simultaneously obtaining characteristic parameter data and oil flow data of the oil passage of the historical guide wheel seat; S2, importing the internal structure image of the oil passage into the guide wheel seat oil passage defect state detection model to analyze the defect state of the guide wheel seat oil passage; importing the characteristic parameter data and oil flow data of the guide wheel seat oil passage into the guide wheel seat oil passage oil delivery state analysis model to analyze the oil delivery state of the guide wheel seat oil passage; S3. Evaluate the operating status of the guide wheel seat oil passage based on the defect status analysis results and the oil delivery status analysis results; S4. Constructing a guide wheel seat oil passage operation state prediction model based on the defect state analysis results and the operation evaluation state results, so as to predict the current operation state of the guide wheel seat oil passage; S5. Repair the defects of the guide wheel seat oil passage according to the current operation prediction result of the guide wheel seat oil passage.

2. The guide wheel seat defect recognition and analysis method based on machine vision according to claim 1 is characterized in that: The step S2 comprises the following specific steps: S21, extracting the internal structure image of the oil passage of the historical guide wheel seat; S22, importing the internal structure image of the oil passage of the historical guide wheel seat into the calculation formula of the oil passage defect state coefficient to calculate the oil passage defect state coefficient of the historical guide wheel seat; the calculation formula of the oil passage defect state coefficient is: ； In the formula, Cz represents the oil channel defect state coefficient of the historical guide wheel seat, n is the number of oil channel internal structure images in the historical guide wheel seat obtained by the image sensor, Ati represents the number of pixels in the i-th oil channel internal structure image, Adi represents the number of pixels occupied by the defective area in the i-th oil channel internal structure image, Udi represents the average pixel value of the defective area in the i-th oil channel internal structure image, Uhi represents the average pixel value of the non-defective area in the i-th oil channel internal structure image, Umaxi represents the maximum value of the difference between the pixel values ​​of all pixels in the i-th oil channel internal structure image, Si represents the standard deviation of the pixel values ​​of all pixels in the i-th oil channel internal structure image, Ui represents the average pixel value of all pixels in the i-th oil channel internal structure image, and i is any item from 1 to n.

3. The guide wheel seat defect recognition and analysis method based on machine vision according to claim 2 is characterized in that: The step S2 also includes the following specific contents: S23, extracting characteristic parameter data and oil flow rate data of the historical guide wheel seat oil channel; S24, substituting the characteristic parameter data and oil flow data of the oil passage of the historical guide wheel seat into the oil passage oil delivery state coefficient calculation formula to calculate the oil passage oil delivery state coefficient of the historical guide wheel seat; the oil passage oil delivery state coefficient calculation formula is: ； In the formula, Sz represents the oil delivery state coefficient of the oil channel of the historical guide wheel seat, A represents the cross-sectional area of ​​the historical guide wheel seat oil channel in the characteristic parameter data, L represents the length of the historical guide wheel seat oil channel in the characteristic parameter data, Sin represents the cross-sectional area of ​​the oil inlet of the historical guide wheel seat oil channel in the characteristic parameter data, Sout represents the cross-sectional area of ​​the oil outlet of the historical guide wheel seat oil channel in the characteristic parameter data; Qin represents the oil input into the oil channel from the oil channel inlet in the oil delivery flow data, and Qout represents the oil output from the oil channel outlet in the oil delivery flow data.

4. The guide wheel seat defect recognition and analysis method based on machine vision according to claim 3 is characterized in that: The step S3 comprises the following specific steps: S31, obtaining the calculated oil passage defect state coefficient and oil passage oil delivery state coefficient of the historical guide wheel seat; S32. Substitute the oil passage defect state coefficient and the oil passage oil delivery state coefficient of the historical guide wheel seat into the oil passage operation state abnormality coefficient calculation formula to calculate the oil passage operation state abnormality coefficient of the historical guide wheel seat; the oil passage operation state abnormality coefficient calculation formula is: ； Wherein, Yc represents the abnormal coefficient of the oil channel operation status of the historical guide wheel seat.

5. The guide wheel seat defect recognition and analysis method based on machine vision according to claim 4 is characterized in that: The step S4 comprises the following specific steps: S41, obtaining guide wheel seat oil passage sample data for training a guide wheel seat oil passage operation state prediction model, wherein the guide wheel seat oil passage sample data includes a plurality of calculated historical guide wheel seat oil passage defect state coefficients and oil passage operation state abnormality coefficients, and also includes a plurality of historical guide wheel seat characteristic parameter data; S42, dividing the guide wheel seat oil channel sample data used for training the guide wheel seat oil channel operation state prediction model into an oil channel sample training set and an oil channel sample test set, constructing a regression network model, taking the oil channel defect state coefficient and characteristic parameter data of the historical guide wheel seat in the oil channel sample training set as the input of the regression network model, taking the oil channel operation state abnormality coefficient of the historical guide wheel seat in the oil channel sample training set as the output of the regression network model, training the regression network model to obtain an initial regression network model; using an average error algorithm to evaluate the model effect of the initial regression network model, and selecting the corresponding initial regression network model with a value greater than or equal to a preset evaluation value as the guide wheel seat oil channel operation state prediction model; S43. Calculate the oil passage defect state coefficient of the current guide wheel seat, and obtain the characteristic parameter data of the oil passage of the current guide wheel seat, input the oil passage defect state coefficient and characteristic parameter data of the current guide wheel seat into the guide wheel seat oil passage operation state prediction model, and output the predicted abnormal coefficient of the oil passage operation state of the current guide wheel seat.

6. The guide wheel seat defect recognition and analysis method based on machine vision according to claim 5 is characterized in that: The step S5 comprises the following specific steps: S51, obtaining the predicted abnormal coefficient of the oil channel operation state of the current guide wheel seat; S52. A threshold value for abnormal operating status is preset. When the predicted abnormal operating status coefficient of the oil passage of the current guide wheel seat is greater than the threshold value for abnormal operating status, an early warning for repairing the defect in the oil passage of the guide wheel seat is issued to maintenance personnel.

7. A guide wheel seat defect recognition and analysis system based on machine vision, used to implement the guide wheel seat defect recognition and analysis method based on machine vision as described in any one of claims 1 to 6, characterized in that: The system comprises: A data acquisition module, used to acquire an internal structural image of the oil passage of the historical guide wheel seat through an image sensor, and simultaneously acquire characteristic parameter data and oil flow data of the oil passage of the historical guide wheel seat; The guide wheel seat oil passage state analysis module is used to import the internal structure image of the oil passage into the guide wheel seat oil passage defect state detection model to analyze the defect state of the guide wheel seat oil passage; import the characteristic parameter data and oil flow data of the guide wheel seat oil passage into the guide wheel seat oil passage oil delivery state analysis model to analyze the oil delivery state of the guide wheel seat oil passage; The guide wheel seat oil passage operation status evaluation module is used to evaluate the operation status of the guide wheel seat oil passage according to the defect status analysis results and the oil delivery status analysis results; The guide wheel seat oil passage operation state prediction module is used to construct a guide wheel seat oil passage operation state prediction model based on the defect state analysis results and the operation evaluation state results, so as to predict the current operation state of the guide wheel seat oil passage; The oil channel defect warning module is used to repair the guide wheel seat oil channel defects according to the current guide wheel seat oil channel operation prediction results; A control module is used to control the operation of the data acquisition module, the guide wheel seat oil channel state analysis module, the guide wheel seat oil channel operation state assessment module, the guide wheel seat oil channel operation state prediction module, and the oil channel defect warning module.

8. An electronic device comprising: A processor and a memory, wherein the memory stores a computer program that can be called by the processor; characterized in that the processor executes the guide wheel seat defect identification and analysis method based on machine vision as described in any one of claims 1 to 6 by calling the computer program stored in the memory.

Images