A sliding bearing fault detection method and system based on image processing

Abstract

The present invention relates to the field of fault diagnosis technology, specifically to a sliding bearing fault detection method and system based on image processing. The method comprises establishing a shaft surface defect dataset and training a shaft surface defect detection model to obtain a trained shaft surface defect detection model; then acquiring and processing shaft surface images of the connecting shaft of the sliding bearing to obtain a shaft surface image set, and using the trained model to perform shaft surface defect detection; if the shaft surface defect detection result indicates a defect, acquiring and processing working images of the sliding bearing in a working state to obtain a working image set; acquiring and processing the working image set to obtain vibration amplitude data; and finally, acquiring the vibration amplitude data and combining it with other data to obtain a vibration amplitude index. If the vibration amplitude index is greater than a preset vibration amplitude index threshold, the sliding bearing is faulty. By calculating the vibration amplitude index, the present invention achieves fault detection for sliding bearings in operation, improving detection accuracy.

Description

Technical Field

[0001] The present invention relates to the technical field of fault diagnosis, and in particular to a sliding bearing fault detection method and system based on image processing. Background Art

[0002] A sliding bearing is a mechanical element that uses sliding motion between friction surfaces to support a rotating shaft. It typically consists of a bearing seat and a journal. Compared to rolling bearings, sliding bearings lack rolling elements, and their load-bearing and sliding friction properties rely on the lubricating oil film on the friction surfaces. Sliding bearings are commonly used in applications requiring smooth and silent operation, such as in electric motors, fans, and turbines. Their application scenarios cover a wide range of fields, including heavy industry, power generation equipment, automobiles, and aerospace. They perform particularly well in environments such as low speed and high load, continuous long-term operation, and high temperature and high pressure. They offer advantages such as strong load-bearing capacity, low friction, and long life.

[0003] With the development of artificial intelligence and machine learning, an increasing number of patents and literature are using image processing-based methods for fault detection. These methods first use a camera or other image acquisition device to capture surface images of the sliding bearing. Computer vision and image analysis algorithms are then used to determine whether the bearing exhibits wear, cracks, and other issues. Image-based detection methods offer the advantage of being contactless and capable of real-time monitoring of the bearing's condition.

[0004] Most existing fault detection methods based on image processing collect images of sliding bearings in a stationary state and perform processing and analysis. The accuracy of fault detection for sliding bearings in the working state of the equipment needs to be further improved.

[0005] Therefore, a sliding bearing fault detection method and system based on image processing is proposed. Summary of the Invention

[0006] The object of the present invention is to provide a sliding bearing fault detection method and system based on image processing. First, by establishing a shaft surface defect data set and training a shaft surface defect detection model, shaft surface defect detection of the sliding bearing connecting shaft in a non-operating state is performed. If the shaft surface has no defects, it indicates that the sliding bearing is normal. If there are defects on the shaft surface, further judgment is performed; then, by acquiring multiple images of the sliding bearing in an operating state and processing them, vibration amplitude data is obtained for analyzing the sliding bearing in an operating state; then, combined with other data such as operating time and speed, a vibration amplitude index is obtained to analyze whether the sliding bearing in an operating state has a fault.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] A sliding bearing fault detection method based on image processing, comprising:

[0009] Step S1: Acquire and process historical axial surface data to obtain an axial surface defect data set; train an axial surface defect detection model based on the axial surface defect data set to obtain a trained axial surface defect detection model.

[0010] Furthermore, the axial surface defect data set includes:

[0011] The historical axial surface data includes surface images of the sliding bearing connecting shaft collected at different angles, and the surface images include images of the sliding bearing connecting shaft at different periods during long-term operation;

[0012] Shaft surface defects include: scratches, cracks, pits, wear and corrosion.

[0013] Furthermore, the shaft surface defect detection model includes:

[0014] The structure of the shaft surface defect detection model includes an input layer, a multi-scale convolution layer, a SE module, a feature pyramid layer, a pooling layer, a fully connected layer, a Dropout layer and an output layer; the multi-scale convolution layer adopts 、 and Convolution kernel of size;

[0015] During the training phase, an enhancement strategy based on training loss adjustment is adopted, including: obtaining and processing the training loss to obtain a set of low recognition accuracy samples, performing data enhancement operations on the low recognition accuracy sample set to obtain enhanced low recognition accuracy samples, and training the shaft surface defect detection model based on the enhanced low recognition accuracy samples; the data enhancement includes adding noise, blurring and scaling.

[0016] Step S2: Acquire and process axial surface images of the sliding bearing connecting shaft collected at different angles in a non-working state to obtain an axial surface image set.

[0017] Furthermore, the axial image set includes:

[0018] On the front side of the sliding bearing, a coordinate system is established in the horizontal and vertical directions, and the axial surface images of the sliding bearing connecting shaft are collected from the 0°, 90°, 180° and 270° directions of the sliding bearing connecting shaft, and denoising, correction and image enhancement processing are performed to obtain the axial surface image set.

[0019] Step S3: The trained axial surface defect detection model obtains and processes the data in the axial surface image set to obtain an axial surface defect detection result.

[0020] Furthermore, the shaft surface defect detection results include:

[0021] The trained axial surface defect detection model obtains and processes the axial surface images in the axial surface image set to obtain a first axial surface defect detection result set; obtains and calculates data in the first axial surface defect detection result set to obtain the axial surface defect detection result;

[0022] Furthermore, if the shaft surface defect detection result is that there is no defect, it means that the sliding bearing is operating normally and there is no fault; if the shaft surface defect detection result is that there is a defect, step S4 is performed.

[0023] Step S4: If the shaft surface defect detection result shows that there is a defect, a working image of the sliding bearing in operation is obtained and processed to obtain a working image set; the working image set is obtained and processed to obtain vibration amplitude data.

[0024] Furthermore, the working image includes:

[0025] The image acquisition device is arranged on the front of the sliding bearing to obtain the image of the sliding bearing under the running state. The working images of the sliding bearing are captured and processed to obtain a working image set; the working images include the sliding bearing and the sliding bearing connecting shaft.

[0026] Furthermore, the working image set includes:

[0027] Acquire the working image, smooth the working image using a Gaussian filter, and obtain a first working image; acquire the first working image, detect blur characteristics in the first working image using Fourier transform, and process the image to obtain blur data; perform a deconvolution operation on the first working image based on the blur data to obtain a corrected working image;

[0028] All working images are corrected to obtain the working image set.

[0029] Furthermore, the vibration amplitude data includes:

[0030] Acquiring data from the working image set and processing it using a contour extraction algorithm to obtain a bearing fitting contour;

[0031] Obtaining and processing the bearing fitting profile to obtain a minimum circumscribed circle and a maximum inscribed circle of the bearing fitting profile; calculating the area between the minimum circumscribed circle and the maximum inscribed circle to obtain an offset area;

[0032] Acquire the bearing fitting profile and process it according to the profile fitting algorithm to obtain a fitting circle; acquire the fitting circle and process it to obtain the position of the fitting circle center in the image; process all data in the working image set to obtain a set of fitting circle center positions;

[0033] The data of the set of fitting circle center positions is acquired and processed to obtain the average axis position, the maximum vibration amplitude, the standard deviation of the vibration amplitude, and the mean vibration amplitude.

[0034] Step S5: Acquire the vibration amplitude data and process it to obtain a vibration amplitude index. If the vibration amplitude index is less than or equal to a preset vibration amplitude index threshold, the sliding bearing is not faulty and is normal wear; if the vibration amplitude index is greater than the preset vibration amplitude index threshold, the sliding bearing is faulty.

[0035] Furthermore, the vibration amplitude index includes:

[0036] The vibration amplitude data, rotation speed, operating time and operating temperature are obtained and processed to obtain the vibration amplitude index. The calculation formula of the vibration amplitude index is:

[0037] ;

[0038] in, represents the vibration amplitude index, Indicates the offset area The weight coefficient of Indicates the maximum vibration amplitude The weight coefficient of Indicates the mean vibration amplitude The weight coefficient of Indicates the standard deviation of vibration amplitude The weight coefficient of Indicates the speed The weight coefficient of Indicates the operating time The weight coefficient of Indicates the operating temperature The weight coefficient of .

[0039] A sliding bearing fault detection system based on image processing, comprising:

[0040] A shaft surface defect detection model training module is used to obtain and process historical shaft surface data to obtain a shaft surface defect data set; train a shaft surface defect detection model based on the shaft surface defect data set to obtain a trained shaft surface defect detection model;

[0041] An axial surface image acquisition module is used to acquire and process axial surface images of the sliding bearing connecting shaft acquired at different angles in a non-working state to obtain an axial surface image set;

[0042] An axial surface defect detection module is used for the trained axial surface defect detection model to acquire and process data in the axial surface image set to obtain an axial surface defect detection result;

[0043] a vibration amplitude data acquisition module, configured to acquire and process a working image of the sliding bearing in a working state to obtain a working image set if the shaft surface defect detection result indicates that a defect exists; and acquire and process the working image set to obtain vibration amplitude data;

[0044] The sliding bearing fault detection module is used to obtain and process the vibration amplitude data to obtain a vibration amplitude index. If the vibration amplitude index is less than or equal to a preset vibration amplitude index threshold, the sliding bearing is not faulty and is normal wear; if the vibration amplitude index is greater than the preset vibration amplitude index threshold, the sliding bearing is faulty.

[0045] Compared with the prior art, the present invention has the following beneficial effects:

[0046] 1. When a sliding bearing fails, it will cause damage to the sliding bearing connecting shaft. By establishing a shaft surface defect dataset and training a shaft surface defect detection model, a preliminary inspection of the sliding bearing connecting shaft is first performed. If there are no defects on the shaft surface, it means that the sliding bearing is normal. If there are defects on the shaft surface, further judgment is performed. This indirect judgment method helps to identify whether there is a fault in the invisible part inside the sliding bearing. During the model training process, by identifying and data enhancing samples with low recognition accuracy, and then conducting model training, the model's ability to detect subtle defects can be improved.

[0047] 2. By detecting the blur characteristics in the image and then using the motion blur convolution kernel for deconvolution operations, motion blur can be effectively corrected and image quality can be improved. Even when the sliding bearing and connecting shaft are in operation, high-quality images can still be captured clearly and accurately. By obtaining data such as the offset area and vibration amplitude of the shaft in operation, real-time detection of the sliding bearing is achieved without the need to disassemble or shut down the sliding bearing for inspection, and data support is provided for subsequent judgment of whether the sliding bearing is faulty.

[0048] 3. The calculation formula of the vibration amplitude index includes multiple key variables such as offset area, maximum vibration amplitude, vibration amplitude mean, standard deviation, speed, operating time and operating temperature. By assigning appropriate weights to each variable, the health status of the sliding bearing in operation can be evaluated, and the actual working condition of the sliding bearing can be judged more accurately. By comparing the vibration amplitude index with the preset threshold, it is possible to simply and intuitively determine whether there is an abnormality in the sliding bearing, which helps to reduce misjudgments, especially when the equipment is under normal wear, avoid unnecessary maintenance and downtime operations, and improve the accuracy of fault diagnosis. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1This is a flow chart of a sliding bearing fault detection method based on image processing provided in Example 1 of the present invention;

[0050] Figure 2 A schematic diagram of the structure of the shaft surface defect detection model provided in Example 1 of the present invention;

[0051] Figure 3 This is a structural schematic diagram of a sliding bearing fault detection system based on image processing provided in Example 2 of the present invention. DETAILED DESCRIPTION

[0052] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0053] Example 1

[0054] A certain type of servo motor is equipped with a sliding bearing. In order to detect whether the sliding bearing on the servo motor has failed after long-term use, a machinery company introduced a sliding bearing fault detection method based on image processing provided by the present invention. The method flow is as follows: Figure 1 shown.

[0055] Step S1: Acquire and process historical axial surface data to obtain an axial surface defect data set; train an axial surface defect detection model based on the axial surface defect data set to obtain a trained axial surface defect detection model.

[0056] Furthermore, the axial surface defect data set includes:

[0057] The historical shaft surface data includes surface images of the sliding bearing connecting shaft collected at different angles, specifically images of the journal portion of the sliding bearing connecting shaft in a non-operating state; the surface images include image data of the sliding bearing connecting shaft under different operating conditions and at different time points during long-term operation, and these images reflect the cumulative impact of external factors such as friction and stress on the surface of the shaft;

[0058] Shaft surface defects include but are not limited to the following categories: scratches, cracks, pits, wear, corrosion and other abnormalities. Scratches are shallow surface lines or grooves on the shaft surface caused by friction with the sliding bearing or external force. Cracks are tiny cracks caused by stress concentration on the shaft surface, which may affect the structural strength of the sliding bearing. Pits are local depressions or grooves on the shaft surface caused by long-term use or external impact. Wear is the loss of the shaft surface caused by long-term friction with the sliding bearing. Corrosion is the chemical reaction between the shaft surface and the environment, resulting in oxidation of the shaft surface or the appearance of corrosion spots.

[0059] By collecting and storing historical axial surface image data at different times and angles, a comprehensive and rich axial surface defect dataset is constructed. The axial surface defect detection model is trained using a training dataset containing a rich variety of defect types, providing strong data support for model training.

[0060] Furthermore, the structure of the shaft surface defect detection model is as follows: Figure 2 As shown, it includes: input layer, multi-scale convolution layer, SE module, feature pyramid layer, pooling layer, fully connected layer, Dropout layer and output layer;

[0061] During the training phase, an enhancement strategy based on training loss adjustment is adopted, including: obtaining and processing the training loss to obtain a set of low recognition accuracy samples, performing data enhancement operations on the low recognition accuracy sample set to obtain enhanced low recognition accuracy samples, and training the shaft surface defect detection model based on the enhanced low recognition accuracy samples; the data enhancement includes adding noise, blurring and scaling.

[0062] Furthermore, the input layer is responsible for receiving input data, i.e., the axial images in the dataset. The multi-scale convolution layer has convolution kernels of various sizes, such as 、 and The convolution kernel is used to perform convolution operations on the input image and extract features of different scales in the axial image. Small-sized convolution kernels are used to capture local details, such as tiny scratches and cracks; large-sized convolution kernels are used to identify defects in a wider range, such as wear, pits, and corrosion. Through multi-scale convolution, the model can more comprehensively capture defect features of different sizes. The SE module, also known as the Squeeze-and-Excitation module, weights the features of different channels, selectively emphasizes important features, and suppresses irrelevant or useless features, thereby enhancing the model's ability to detect subtle defects. The feature pyramid layer integrates information from different scales and levels to improve the model's detection effect on various defects. The pooling layer reduces the dimension of the feature map through maximum pooling or average pooling, reduces the amount of calculation, and retains the most important feature information. The fully connected layer maps the extracted features into high-dimensional vectors and further uses this information for classification. The Dropout layer randomly discards some neurons during training to prevent model overfitting and improve the model's generalization ability. The output layer classifies defects based on the features extracted by the previous layers, and ultimately determines whether there are defects on the axial surface and the specific category of the defect.

[0063] Furthermore, during the model training phase, an adjustment and enhancement strategy based on training loss is introduced. After each training iteration, a loss value is calculated for each sample. This loss value reflects the model's prediction error on that sample. A higher loss value indicates that the model's recognition of that sample is inaccurate. Based on the loss value, the training samples are divided into a set of low-accuracy samples and a set of high-accuracy samples. The low-accuracy sample set typically represents samples that are more difficult for the model to identify or contain complex features. Data augmentation is performed on the low-accuracy sample set to generate enhanced samples, which are then retrained, making the model perform better when handling difficult-to-identify defects.

[0064] Table 1 shows the training results of the shaft surface defect detection model. As the number of training rounds increases, the training loss and validation loss of the model gradually decrease, and the accuracy continues to improve.

[0065] Table 1. Training results

[0066]

[0067] The model's axial surface defect detection accuracy is improved by enhancing and retraining samples with low recognition accuracy; the axial surface defect detection model realizes the detection and identification of axial surface defects through a series of operations such as multi-scale feature extraction, adaptive feature enhancement and multi-level information fusion. When dealing with complex axial surface defect detection tasks, it can more efficiently identify potential defects and improve overall detection accuracy and reliability.

[0068] Step S2: Acquire and process axial surface images of the sliding bearing connecting shaft collected at different angles in a non-working state to obtain an axial surface image set.

[0069] Furthermore, the axial image set includes:

[0070] On the front side of the sliding bearing, a coordinate system is established in the horizontal and vertical directions, and the axial surface images of the sliding bearing connecting shaft are collected from the 0°, 90°, 180° and 270° directions of the sliding bearing connecting shaft, and denoising, correction and image enhancement processing are performed to obtain the axial surface image set.

[0071] Furthermore, for the shaft surface in complex scenarios, the sliding bearing connecting shaft can be cleaned first, and then the shaft surface images can be collected from more directions; after the images are collected, the collected images are processed such as denoising, correction and image enhancement to obtain a high-quality shaft surface image set for shaft surface defect detection in subsequent steps.

[0072] Axial surface images are collected from multiple directions and angles to ensure full coverage of the entire axial surface and avoid missing certain areas due to limitations in shooting angles. Images are processed to obtain high-quality images, ensuring data clarity and accuracy, and providing a solid foundation for subsequent axial surface defect detection.

[0073] Step S3: the trained axle surface defect detection model acquires and processes data in the axle surface image set to obtain an axle surface defect detection result;

[0074] Furthermore, the shaft surface defect detection results include:

[0075] The trained axial surface defect detection model obtains and processes the axial surface images in the axial surface image set to obtain a first axial surface defect detection result set; obtains and calculates data in the first axial surface defect detection result set to obtain the axial surface defect detection result;

[0076] Furthermore, the initial defect number is set to 0. In this example, there are 4 axial plane images in the axial plane image set. If the axial plane image has defects, the defect number is incremented by 1. For example, if the data in the first axial plane defect detection result set shows that three axial plane images have defects and one axial plane image does not have defects, the defect number is 3.

[0077] Furthermore, if the number of defects is greater than or equal to 2, it indicates that the axial surface of the sliding bearing connecting shaft has defects, and if the number of defects is less than 2, it indicates that the axial surface of the sliding bearing connecting shaft does not have defects;

[0078] Furthermore, if the shaft surface defect detection result is that there is no defect, it means that the sliding bearing is operating normally and there is no fault; if the shaft surface defect detection result is that there is a defect, step S4 is performed.

[0079] Because internal failures in sliding bearings can cause defects in the axial surface of the connecting shaft, the axial surface integrity of the sliding bearing connecting shaft indirectly reflects whether the sliding bearing is operating normally and helps to identify whether there are failures in invisible parts of the sliding bearing. Detecting axial surface defects through images collected from multiple angles can effectively avoid misjudgments caused by occlusion or limitations of a single angle, thereby improving the accuracy and reliability of the detection results.

[0080] Step S4: If the shaft surface defect detection result is that there is a defect, a working image of the sliding bearing in a working state is obtained and processed to obtain a working image set; the working image set is obtained and processed to obtain vibration amplitude data.

[0081] Furthermore, the working image includes:

[0082] The image acquisition device is set on the front of the sliding bearing to obtain the image of the working state. The working images of the sliding bearing are captured and processed to obtain a working image set; the working images include the sliding bearing and the sliding bearing connecting shaft.

[0083] The image acquisition device is positioned from the front, facilitating a clear view of the sliding bearing and connecting shaft. Combining multiple images from the front provides data support for subsequent comprehensive analysis of whether the sliding bearing is faulty while in operation, helping to reduce misjudgments caused by partial obstruction or viewing angle deviation.

[0084] Furthermore, the working image set includes:

[0085] Acquire the working image and smooth the working image through a Gaussian filter to obtain a first working image; acquire the first working image, detect the blur characteristics in the first working image through Fourier transform and process it to obtain blur data; acquire the blur data and perform a deconvolution operation on the first working image through a motion blur convolution kernel to obtain a corrected working image; the blur data includes a motion direction and a blur length.

[0086] All working images are corrected to obtain a working image set.

[0087] By smoothing the working image, the noise in the image can be effectively reduced, making the image clearer; by analyzing the blur characteristics through Fourier transform and using the motion blur convolution kernel for deconvolution processing, the image quality can be greatly improved, the influence of motion blur can be eliminated, and a clear and accurate working image can be obtained, which helps to improve the accuracy of subsequent bearing status analysis and fault detection.

[0088] Furthermore, the vibration amplitude data includes:

[0089] Acquiring data from the working image set and processing it using a contour extraction algorithm to obtain a bearing fitting contour;

[0090] Furthermore, the contour extraction algorithm can utilize existing technologies such as edge detection algorithms to process the working image, separate the surface contour of the bearing shell in the sliding bearing from the complex background, and obtain the bearing fitting contour.

[0091] Obtain the bearing fitting profile and process it to obtain the minimum circumscribed circle and the maximum inscribed circle of the bearing fitting profile; calculate the area between the minimum circumscribed circle and the maximum inscribed circle to obtain the offset area ;

[0092] Furthermore, the bearing fitting profile is processed using existing technologies such as Hough transform and convex hull algorithm to obtain the minimum circumscribed circle and the maximum inscribed circle; the area between the minimum circumscribed circle and the maximum inscribed circle represents the deformation of the bearing bush of the sliding bearing in operation due to operation, and the offset is used as the displacement. express; for all The above processing is performed on the image to obtain an offset set. The offset area of ​​the bearing shell of the sliding bearing in the operating state is calculated based on the data of the offset set. The calculation formula is:

[0093] ;

[0094] in, represents the offset area, Indicates the number of images, Indicates the The offset calculated in the image.

[0095] Acquire the bearing fitting profile and process it according to the profile fitting algorithm to obtain a fitting circle; acquire the fitting circle and process it to obtain the position of the fitting circle center in the image; process all data in the working image set to obtain a set of fitting circle center positions;

[0096] Furthermore, after obtaining the bearing fitting profile, the profile fitting algorithm can process the bearing fitting profile using existing technology to obtain the fitting circle; further process the fitting circle to obtain the coordinate position of the center of the fitting circle in the image. , process all images and obtain the set of fitting circle center positions.

[0097] The data of the set of fitting circle center positions is acquired and processed to obtain the average axis position, the maximum vibration amplitude, the standard deviation of the vibration amplitude, and the mean vibration amplitude.

[0098] Furthermore, by calculating the mean of the coordinate positions in the set of fitted circle center positions, the average axis position can be obtained. , by calculating the error between the fitting center and the average position, the vibration amplitude can be obtained. The calculation formula is:

[0099] ;

[0100] in, Indicates the The vibration amplitude in the image, Indicates the The position coordinates of the center of the fitted circle in the image, Indicates the distance calculation method.

[0101] Furthermore, the above processing is performed on all images to obtain the vibration amplitude set , maximum vibration amplitude Represents the maximum value in the vibration amplitude set. The calculation formula for the mean vibration amplitude is:

[0102] ;

[0103] in, represents the mean value of the vibration amplitude; the calculation formula for the standard deviation of the vibration amplitude is:

[0104] ;

[0105] in, Indicates the standard deviation of vibration amplitude.

[0106] By extracting the bearing fitting contour and calculating the area between the minimum circumscribed circle and the maximum inscribed circle, the degree of deformation of the sliding bearing's bushing during operation is accurately quantified. The calculation of other vibration amplitude data, such as the maximum vibration amplitude, the mean vibration amplitude, and the standard deviation of the vibration amplitude, provides information on the vibration amplitude changes of the bearing under operation, enabling real-time monitoring of the bearing's health status. Using multiple images for data analysis reduces the impact of single image noise or errors on the overall detection results, thereby improving the reliability of the vibration amplitude data.

[0107] Step S5: Acquire the vibration amplitude data and process it to obtain a vibration amplitude index. If the vibration amplitude index is less than or equal to a preset vibration amplitude index threshold, the sliding bearing is not faulty and is normal wear; if the vibration amplitude index is greater than the preset vibration amplitude index threshold, the sliding bearing is faulty.

[0108] Furthermore, the vibration amplitude index includes:

[0109] The offset area, the vibration amplitude data, the rotational speed, the machine operating time, and the operating temperature are obtained and processed to obtain the vibration amplitude index. The calculation formula of the vibration amplitude index is:

[0110] ;

[0111] in, represents the vibration amplitude index, Indicates the offset area The weight coefficient of Indicates the maximum vibration amplitude The weight coefficient of Indicates the mean vibration amplitude The weight coefficient of Indicates the standard deviation of vibration amplitude The weight coefficient of Indicates the speed The weight coefficient of Indicates the operating time The weight coefficient of Indicates the operating temperature The weight coefficient of .

[0112] Furthermore, in this embodiment, the offset area is 2.403 mm 2 The maximum vibration amplitude is 0.321mm, the mean vibration amplitude is 0.258mm, the standard deviation of the vibration amplitude is 0.103, the speed is 1500, the operating temperature is 86.24℃, and the machine operation time is 302 hours. Finally, after calculation, the vibration amplitude index of the sliding bearing is 188.06, which is greater than the preset vibration amplitude index threshold of 180, indicating that the sliding bearing is faulty.

[0113] The vibration amplitude index calculates a specific value by assigning different weight coefficients to key influencing factors such as offset area, vibration amplitude, temperature and operating time. This effectively quantifies the health status of the sliding bearing, avoids misjudgment caused by relying on only one factor, improves overall decision-making efficiency, and facilitates quick judgment of whether the sliding bearing has abnormalities or faults.

[0114] First, the shaft surface defect detection model is used to detect defects in the sliding bearing connecting shaft, which indirectly reflects whether the sliding bearing is operating normally and helps to identify whether there is a fault in the invisible part inside the sliding bearing. After detecting the defect, the system will enter the vibration data analysis stage of the sliding bearing. By acquiring multiple images of the sliding bearing in operation and analyzing and processing them, vibration amplitude data such as the offset area, maximum vibration amplitude and vibration amplitude standard deviation are obtained, providing a reliable basis for sliding bearing fault detection. Finally, the vibration amplitude data is combined with data such as operating time to calculate the vibration amplitude index, which can quickly and accurately determine whether the sliding bearing has a fault.

[0115] Example 2

[0116] like Figure 3 The figure shows the structure of a sliding bearing fault detection system based on image processing, as provided by the present invention. First, the shaft surface defect detection model training module acquires and processes historical shaft surface data to generate a shaft surface defect dataset. The shaft surface defect detection model is then trained based on this shaft surface defect dataset to generate a trained shaft surface defect detection model.

[0117] After the model training is completed, a sample set is randomly extracted from the test set for testing. The results are shown in Table 2, which shows the recognition accuracy of various types of defects. The overall recognition accuracy is 95.33%.

[0118] Table 2. Defect recognition results

[0119]

[0120] Through technologies such as multi-scale convolution, the shaft surface defect detection model can accurately identify different types of shaft surface defects; in particular, through targeted data enhancement and training, the model can maintain a high recognition accuracy of around 95.33% under complex working conditions, greatly improving the efficiency and accuracy of shaft surface defect detection.

[0121] The axial surface image acquisition module is used to acquire and process the axial surface images of the sliding bearing connecting shaft acquired at different angles in a non-working state to obtain an axial surface image set.

[0122] In the shaft surface defect detection module, the trained shaft surface defect detection model obtains the data in the shaft surface image set and analyzes and processes it to obtain the shaft surface defect detection result. If the shaft surface defect detection result shows that there is a defect, it enters the vibration amplitude data acquisition module.

[0123] If the shaft surface defect detection result shows that there is a defect, the vibration amplitude data acquisition module obtains and processes the working image of the sliding bearing in the working state to obtain a working image set; obtains and processes the working image set to obtain vibration amplitude data.

[0124] Furthermore, the innovation of this embodiment lies in the introduction of new vibration amplitude data and the combination of more features to more accurately measure the operating status of the sliding bearing.

[0125] New vibration amplitude data includes: base vibration frequency, dynamic offset, vibration directionality offset and temperature vibration coupling coefficient.

[0126] First, the vibration spectrum of the sliding bearing in operation is obtained through Fourier transform, and the reference vibration frequency of the sliding bearing is extracted from it. The reference vibration frequency can reflect the vibration data of the sliding bearing under different speeds and loads.

[0127] By detecting the displacement difference of the axis center of the sliding bearing connecting shaft in each working image in the running state, the dynamic offset can be calculated. The calculation formula is:

[0128] ;

[0129] in, Indicates the dynamic offset, Indicates the number of working images, Indicates the The axis position coordinates of the sliding bearing connecting shaft in the working image, Indicates the average axis center position of the plain bearing connection shaft in all working images.

[0130] Vibration directional deviation is used to quantify the deviation direction of the sliding bearing by detecting the main vibration direction of the sliding bearing during operation. The calculation formula is:

[0131] ;

[0132] in, Indicates the main vibration direction of the sliding bearing.

[0133] At high temperatures, bearing materials may undergo slight deformation, resulting in different vibration responses. The temperature-vibration coupling coefficient combines the operating temperature and vibration data of the sliding bearing to evaluate the impact of temperature changes on bearing vibration, which can more comprehensively reflect the actual operating status of the bearing. The calculation formula for the temperature-vibration coupling coefficient is:

[0134] ;

[0135] in, represents the temperature vibration coupling coefficient, Indicates the number of working images, Indicates the The distance between the axis center of the sliding bearing connecting shaft and the average axis center position in the working image, Indicates the Temperature data of the sliding bearing in operation state of the working image, and Indicates the corresponding weight coefficient.

[0136] The sliding bearing fault detection module obtains and processes the vibration amplitude data to obtain a vibration amplitude index. If the vibration amplitude index is less than or equal to a preset vibration amplitude index threshold, the sliding bearing is not faulty and is normal wear; if the vibration amplitude index is greater than the preset vibration amplitude index threshold, the sliding bearing is faulty.

[0137] Furthermore, by combining the above data, a new vibration amplitude index is obtained, and the calculation formula is:

[0138] ;

[0139] in, represents the new vibration amplitude index, Indicates the reference vibration frequency The weight coefficient of Indicates dynamic offset The weight coefficient of Indicates the main vibration direction of the sliding bearing The weight coefficient of Represents the temperature vibration coupling coefficient The weight coefficient of .

[0140] Table 3. Test results

[0141]

[0142] Table 3 shows the fault detection results of a batch of sliding bearings. When the vibration amplitude index is greater than 100, it indicates that the corresponding sliding bearing is faulty. It can be seen that the method proposed in the present invention can quickly and conveniently perform fault detection on sliding bearings, thereby improving detection efficiency and accuracy.

[0143] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A sliding bearing fault detection method based on image processing, characterized in that: include: Step S1: Obtain and process historical axial surface data to obtain an axial surface defect dataset; training an axial surface defect detection model according to the axial surface defect data set to obtain a trained axial surface defect detection model; Step S2: Acquire and process axial surface images of the sliding bearing connecting shaft collected at different angles in a non-working state to obtain an axial surface image set; Step S3: the trained axle surface defect detection model acquires and processes data in the axle surface image set to obtain an axle surface defect detection result; Step S4: If the shaft surface defect detection result is that there is a defect, a working image of the sliding bearing in a working state is obtained and processed to obtain a working image set; data in the working image set is obtained and processed using a contour extraction algorithm to obtain a bearing fitting contour; the bearing fitting contour is obtained and processed to obtain a minimum circumscribed circle and a maximum inscribed circle of the bearing fitting contour; the area between the minimum circumscribed circle and the maximum inscribed circle is calculated to obtain an offset area; the bearing fitting contour is obtained and processed according to a contour fitting algorithm to obtain a fitting circle; the fitting circle is obtained and processed to obtain the position of the fitting circle center in the image; all data in the working image set is processed to obtain a fitting circle center position set; data of the fitting circle center position set is obtained and processed to obtain vibration amplitude data; Step S5: Acquire and process the vibration amplitude data to obtain a vibration amplitude index. If the vibration amplitude index is less than or equal to a preset vibration amplitude index threshold, the sliding bearing is not faulty; if the vibration amplitude index is greater than the preset vibration amplitude index threshold, the sliding bearing is faulty.

2. The sliding bearing fault detection method based on image processing according to claim 1 is characterized in that: The axial surface defect dataset includes: The historical axial surface data includes surface images of the sliding bearing connecting shaft collected at different angles, and the surface images include images of the sliding bearing connecting shaft at different periods during long-term operation; Shaft surface defects include: scratches, cracks, pits, wear and corrosion.

3. The sliding bearing fault detection method based on image processing according to claim 1 is characterized in that: The shaft surface defect detection model includes: The structure of the shaft surface defect detection model includes an input layer, a multi-scale convolution layer, a SE module, a feature pyramid layer, a pooling layer, a fully connected layer, a Dropout layer and an output layer; the multi-scale convolution layer adopts 、 and Convolution kernel of size; During the training phase, an enhancement strategy based on training loss adjustment is adopted, including: obtaining and processing the training loss to obtain a set of low recognition accuracy samples, performing data enhancement operations on the low recognition accuracy sample set to obtain enhanced low recognition accuracy samples, and training the shaft surface defect detection model based on the enhanced low recognition accuracy samples; the data enhancement includes adding noise, blurring and scaling.

4. The sliding bearing fault detection method based on image processing according to claim 1 is characterized in that: The axial image set includes: The axial surface images of the sliding bearing connecting shaft are collected from different directions of the sliding bearing connecting shaft, and denoising, correction and image enhancement processing are performed to obtain the axial surface image set.

5. The sliding bearing fault detection method based on image processing according to claim 1 is characterized in that: The shaft surface defect detection results include: The trained axial surface defect detection model obtains and processes the axial surface images in the axial surface image set to obtain a first axial surface defect detection result set; obtains and processes data in the first axial surface defect detection result set to obtain the axial surface defect detection result; If the shaft surface defect detection result is that there is no defect, it means that the sliding bearing is operating normally and there is no fault; if the shaft surface defect detection result is that there is a defect, step S4 is performed.

6. The sliding bearing fault detection method based on image processing according to claim 1, characterized in that: The working image includes: The image acquisition device is arranged on the front of the sliding bearing to obtain the image of the sliding bearing under the running state. The working images of the sliding bearing are captured and processed to obtain a working image set; the working images include the sliding bearing and the sliding bearing connecting shaft.

7. The sliding bearing fault detection method based on image processing according to claim 1 is characterized in that: The working image set includes: Acquire the working image, smooth the working image using a Gaussian filter, and obtain a first working image; acquire the first working image, detect blur characteristics in the first working image using Fourier transform, and process the image to obtain blur data; perform a deconvolution operation on the first working image based on the blur data to obtain a corrected working image; All working images are corrected to obtain the working image set.

8. The sliding bearing fault detection method based on image processing according to claim 1, characterized in that: The vibration amplitude index includes: The vibration amplitude data, rotation speed, operating time and operating temperature are obtained and processed to obtain the vibration amplitude index. The calculation formula of the vibration amplitude index is: ； in, represents the vibration amplitude index, Indicates the offset area The weight coefficient of Indicates the maximum vibration amplitude The weight coefficient of Indicates the mean vibration amplitude The weight coefficient of Indicates the standard deviation of vibration amplitude The weight coefficient of Indicates the speed The weight coefficient of Indicates the operating time The weight coefficient of Indicates the operating temperature The weight coefficient of .

9. A sliding bearing fault detection system based on image processing, characterized in that: include: A shaft surface defect detection model training module is used to obtain and process historical shaft surface data to obtain a shaft surface defect dataset; training an axial surface defect detection model according to the axial surface defect data set to obtain a trained axial surface defect detection model; An axial surface image acquisition module is used to acquire and process axial surface images of the sliding bearing connecting shaft acquired at different angles in a non-working state to obtain an axial surface image set; An axial surface defect detection module is used for the trained axial surface defect detection model to acquire and process data in the axial surface image set to obtain an axial surface defect detection result; A vibration amplitude data acquisition module is configured to acquire and process a working image of a sliding bearing in a working state to obtain a working image set; acquire data in the working image set and process it using a contour extraction algorithm to obtain a bearing fitting contour; acquire and process the bearing fitting contour to obtain a minimum circumscribed circle and a maximum inscribed circle of the bearing fitting contour; calculate the area between the minimum circumscribed circle and the maximum inscribed circle to obtain an offset area; acquire and process the bearing fitting contour according to a contour fitting algorithm to obtain a fitting circle; acquire and process the fitting circle to obtain the position of the fitting circle center in the image; process all data in the working image set to obtain a fitting circle center position set; acquire and process the data of the fitting circle center position set to obtain vibration amplitude data; The sliding bearing fault detection module is used to obtain and process the vibration amplitude data to obtain a vibration amplitude index. If the vibration amplitude index is less than or equal to a preset vibration amplitude index threshold, the sliding bearing is not faulty and is normal wear; if the vibration amplitude index is greater than the preset vibration amplitude index threshold, the sliding bearing is faulty.

Images