A method and system for intelligent detection of hydraulic equipment

Abstract

The present application discloses a method and system for intelligent detection of hydraulic equipment, which relates to the field of hydraulic equipment testing. The method comprises: obtaining appearance image information and nameplate image information of the hydraulic equipment to be tested; obtaining appearance dimension information based on the appearance image information; obtaining clamping position information, input component position information and output component position information based on the appearance image information; obtaining parameter configuration information based on the nameplate image information; controlling the clamping operation of a universal fixture based on the appearance dimension information, the clamping position information, the input component position information and the output component position information to clamp the hydraulic equipment to be tested; determining test loading parameter information based on the parameter configuration information, wherein the test loading parameter information comprises rotation speed loading information and pressure loading information; and controlling the detection process of the hydraulic equipment to be tested according to the test loading parameter information to obtain test response data of the hydraulic equipment to be tested.

Description

Technical Field

[0001] The present specification relates to the field of hydraulic equipment detection, and more specifically, the present application relates to a hydraulic equipment intelligent detection method and system. Background Art

[0002] Hydraulic equipment is a mechanical system that uses liquid pressure to transfer and control energy. These devices are widely used in a variety of industrial and mobile applications, such as construction machinery, aviation, automobiles, heavy machinery and manufacturing industries. The basic components of a hydraulic system include hydraulic pumps, motors, cylinders, valves, pipes and oil tanks.

[0003] Hydraulic equipment testing is a critical process used to ensure that the performance, safety, and reliability of the equipment meet standard requirements. This process involves a series of tests designed to check and evaluate the various components of the hydraulic system, such as pumps, valves, cylinders, pipes, and hydraulic oil. The goal of hydraulic equipment testing is to identify and solve potential problems, prevent failures, optimize performance, and ensure that the equipment can operate safely under the most demanding working conditions. However, current testing methods are generally based on specific standards, but specific standard testing is no longer suitable for the current testing scenarios of a large number of non-standard equipment. Due to the large variety of non-standard hydraulic equipment, it is difficult to set specific testing procedures for each non-standard equipment, which limits the intelligence and adaptability of hydraulic equipment testing. In order to solve this problem, it is necessary to propose an intelligent detection method and system for hydraulic equipment. Summary of the invention

[0004] A series of simplified concepts are introduced in the Summary of the Invention section, which will be further described in detail in the Detailed Description of the Invention section. The Summary of the Invention section of this application does not mean to attempt to define the key features and essential technical features of the claimed technical solution, nor does it mean to attempt to determine the scope of protection of the claimed technical solution.

[0005] In a first aspect, the present application proposes a hydraulic equipment intelligent detection method, the method comprising:

[0006] Obtaining appearance image information and nameplate image information of the hydraulic equipment to be tested;

[0007] Acquire shape size information based on the shape image information;

[0008] Based on the above appearance image information, obtain clamping position information, input component position information and output component position information;

[0009] Acquire parameter configuration information based on the nameplate image information;

[0010] Based on the above-mentioned shape dimension information, the above-mentioned clamping position information, the above-mentioned input component position information and the above-mentioned output component position information, the clamping operation of the universal clamp is controlled to clamp the above-mentioned hydraulic device to be tested;

[0011] Determine the test loading parameter information based on the parameter configuration information, wherein the test loading parameter information includes rotation speed loading information and pressure loading information;

[0012] The detection process of the hydraulic device to be tested is controlled according to the test loading parameter information to obtain the test response data of the hydraulic device to be tested.

[0013] In a feasible implementation manner, the obtaining of the shape dimension information based on the shape image information includes:

[0014] grayscale processing and noise reduction processing are performed on the above-mentioned appearance image information to obtain processed appearance image information;

[0015] Based on the Canny edge detection algorithm, the above-mentioned shape image information is identified to obtain preliminary contour information of the shape;

[0016] Based on the findContours method, the preliminary contour information of the above-mentioned shape is identified to obtain the precise contour information of the shape;

[0017] The above-mentioned external dimension information is determined based on the above-mentioned precise contour information of the external shape and the image information of the standard reference object, wherein the above-mentioned external dimension information is the maximum external dimension of the above-mentioned hydraulic equipment to be tested.

[0018] In a feasible implementation manner, the above-mentioned obtaining the clamping position information, the input component position information and the output component position information based on the above-mentioned appearance image information includes:

[0019] Adjusting the appearance image information to a standard image size to obtain standard appearance image information and adjustment ratio information, wherein the standard image size is equal to the standard digital model image size in the hydraulic equipment standard digital model library;

[0020] Performing histogram equalization and sharpening processing on the above standard shape image information to obtain an enhanced feature shape image;

[0021] Inputting the enhanced characteristic shape image into the characteristic matching model to match the target digital model image corresponding to the enhanced characteristic shape image in the hydraulic equipment standard digital model library;

[0022] Obtaining target clamping position information, target input component position information and target output component position information corresponding to the target digital-analog image;

[0023] The clamping position information, the input component position information and the output component position information are determined based on the target clamping position information, the target input component position information, the target output component position information and the adjustment ratio information.

[0024] In a feasible implementation, the feature matching model is obtained based on CNN network model training, and the feature matching model includes an input layer, a convolution layer, an activation layer, a pooling layer and a fully connected layer. The convolution layer includes a Prewitt filter, a Gaussian filter and a Laplacian filter. The convolution layer also includes an adaptive weight module, and the adaptive weight module is used to adjust the weight coefficient of each filter.

[0025] In a feasible implementation manner, the above-mentioned control of the clamping operation of the universal clamp based on the above-mentioned shape dimension information, the above-mentioned clamping position information, the above-mentioned input component position information and the above-mentioned output component position information further includes:

[0026] Calculate the moving distance based on the above-mentioned external dimension information and the above-mentioned clamping position information;

[0027] Determine the clamping speed based on the ratio information of the moving distance and the shape dimension information;

[0028] Determine a moving path based on the current position information of the universal fixture, the input component position information, and the output component position information;

[0029] Based on the clamping speed and the moving path, the clamping operation of the universal clamp is controlled.

[0030] In a feasible implementation manner, the determining of the test loading parameter information based on the parameter configuration information includes:

[0031] Based on the matching operation between the parameter configuration information and the historical loading database, the similarity of the parameter configuration information of the hydraulic equipment to be tested and the tested hydraulic equipment is obtained, wherein the historical loading database includes the matching relationship between the parameter configuration information of multiple tested hydraulic equipment and the historical loading information;

[0032] Incorporating the historical loading information of the tested hydraulic equipment whose parameter configuration information similarity is greater than a preset similarity into the test loading parameter candidate data set;

[0033] The test loading parameter information is generated based on the historical loading information in the test loading parameter candidate data set.

[0034] In a feasible implementation manner, the generating the test loading parameter information based on the historical loading information in the test loading parameter candidate data set includes:

[0035] Generate basic test loading parameter information based on the median value of the historical loading information in the test loading parameter candidate data set;

[0036] Obtaining the response analysis results corresponding to the historical loading information in the above-mentioned test loading parameter candidate data set;

[0037] Select the historical loading information with abnormalities in the above response analysis results and cluster them based on the abnormality types to generate N groups of clustered historical loading information, wherein the above abnormality types include one or more of pressure abnormality, flow abnormality, temperature abnormality, noise and vibration abnormality, leakage abnormality, motor start abnormality, and oil quality abnormality;

[0038] Generate enhanced test loading parameter information of the anomaly detection project according to each group of the above clustered historical loading information;

[0039] The above-mentioned basic test loading parameter information and the above-mentioned enhanced test loading parameter information are used as the above-mentioned test loading parameter information.

[0040] In a feasible implementation manner, the test response data includes basic test response data and enhanced test response data.

[0041] The above-mentioned control of the detection process of the above-mentioned hydraulic equipment to be tested according to the above-mentioned test loading parameter information to obtain the test response data of the above-mentioned hydraulic equipment to be tested includes:

[0042] Obtain the number of exceptions corresponding to each type of exception in the above response analysis results;

[0043] Determine the number of basic tests and enhanced tests based on the above abnormal numbers;

[0044] Based on the basic test times and the basic test loading parameter information, the basic detection process of the hydraulic equipment to be tested is controlled to obtain basic test response data of the hydraulic equipment to be tested;

[0045] Based on the enhanced test times and the enhanced test loading parameter information, the enhanced detection process of the hydraulic equipment to be tested is controlled to obtain enhanced test response data of the hydraulic equipment to be tested.

[0046] In a feasible implementation, it also includes:

[0047] Obtain the workplace where the above hydraulic equipment is to be put into use;

[0048] Determine the risk factors corresponding to different types of abnormalities based on the above-mentioned workplaces to be put into use;

[0049] The above-mentioned basic test times and the above-mentioned enhanced test times are determined based on the risk factor corresponding to each abnormality type and the number of abnormalities corresponding to each abnormality type.

[0050] In the second aspect, the present application proposes a hydraulic equipment intelligent detection system, comprising:

[0051] A first acquisition unit is used to acquire the appearance image information and nameplate image information of the hydraulic equipment to be tested;

[0052] A second acquisition unit acquires shape size information based on the shape image information;

[0053] A third acquisition unit is used to acquire clamping position information, input component position information and output component position information based on the above-mentioned appearance image information;

[0054] A fourth acquisition unit, used to acquire parameter configuration information based on the nameplate image information;

[0055] A clamping unit, used for controlling the clamping operation of the universal clamp based on the above-mentioned shape dimension information, the above-mentioned clamping position information, the above-mentioned input component position information and the above-mentioned output component position information, so as to clamp the above-mentioned hydraulic device to be tested;

[0056] A determination unit, configured to determine test loading parameter information based on the parameter configuration information, wherein the test loading parameter information includes rotation speed loading information and pressure loading information;

[0057] The testing unit is used to control the detection process of the hydraulic device to be tested according to the test loading parameter information to obtain the test response data of the hydraulic device to be tested.

[0058] In summary, the intelligent detection method of hydraulic equipment in the embodiment of the present application includes: obtaining the appearance image information and nameplate image information of the hydraulic equipment to be tested; obtaining the appearance size information based on the above appearance image information; obtaining the clamping position information, input component position information and output component position information based on the above appearance image information; obtaining the parameter configuration information based on the above nameplate image information; controlling the clamping operation of the universal fixture based on the above appearance size information, the above clamping position information, the above input component position information and the above output component position information to clamp the above hydraulic equipment to be tested; determining the test loading parameter information based on the above parameter configuration information, wherein the above test loading parameter information includes speed loading information and pressure loading information; controlling the detection process of the above hydraulic equipment to be tested according to the above test loading parameter information to obtain the test response data of the above hydraulic equipment to be tested. The method proposed in the embodiment of the present application utilizes the appearance and nameplate image information to adapt to the specific needs of various non-standard hydraulic equipment. By analyzing the appearance size, clamping position, input and output component position and parameter configuration of the equipment, the detection parameters and process can be automatically adjusted without the need for pre-set standard detection procedures. In the industrial environment where non-standard equipment is becoming more and more common, the adaptability to diversified equipment types is improved. Through precise image analysis technology, the key features of hydraulic equipment can be captured in detail, and the detection parameters can be automatically set according to these features. Not only does it reduce the possibility of human error, but it also improves the efficiency of the detection process. Through the parameter configuration information extracted from the nameplate image, it is possible to intelligently select appropriate test loading parameters, such as pressure and speed. It is also possible to dynamically adjust the test process according to the actual test response data to better adapt to the actual working conditions and performance characteristics of the equipment. By conducting comprehensive performance and response tests on the equipment to be tested, the safety and reliability of the equipment in actual work are ensured. Especially under harsh working conditions, potential equipment failures and operational risks can be prevented through precise testing in advance. Due to its unique design and functional requirements, non-standard hydraulic equipment is difficult to fully cover its detection requirements with conventional detection methods. This solution uses flexible image processing and parameter configuration extraction technology to enable even highly customized equipment to obtain effective detection. The embodiment of the present application provides an efficient, accurate and flexible detection method, which is particularly suitable for meeting the challenges of non-standard hydraulic equipment detection in the current industrial field. It not only improves the intelligence level of detection, but also greatly improves the operating efficiency and safety of the equipment.

[0059] The intelligent detection method for hydraulic equipment proposed in this application, and other advantages, objectives and features of this application will be partially reflected through the following description, and will also be partially understood by technical personnel in this field through research and practice of this application. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present specification. Also, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0061] Figure 1 A schematic diagram of a process flow of a hydraulic equipment intelligent detection method provided in an embodiment of the present application;

[0062] Figure 2 A schematic diagram of the structure of an intelligent detection system for hydraulic equipment provided in an embodiment of the present application. DETAILED DESCRIPTION

[0063] The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices. The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments.

[0064] See also Figure 1 , which is a schematic diagram of a process of intelligent detection method for hydraulic equipment provided in an embodiment of the present application, and may specifically include:

[0065] S110, obtaining appearance image information and nameplate image information of the hydraulic equipment to be tested.

[0066] For example, first, it is necessary to capture the appearance image of the hydraulic equipment to be tested and the nameplate image information of the equipment. The appearance image information provides visual details of the equipment, while the nameplate image information contains the manufacturing details of the equipment, such as model, specifications, etc.

[0067] S120, acquiring shape dimension information based on the shape image information.

[0068] Exemplarily, the shape image information is used to measure and record the shape dimension information of the hydraulic equipment, such as length, width and height, through image processing technology.

[0069] S130. Obtain clamping position information, input component position information, and output component position information based on the above-mentioned appearance image information.

[0070] For example, image processing technology is used to analyze the appearance image information of the hydraulic device to determine the suitable clamping position information on the device and the specific position information of the input component and the output component, so as to correctly install the hydraulic device to be tested and avoid the overlap of the clamping position with the input component position and / or the output component position.

[0071] S140: Acquire parameter configuration information based on the nameplate image information.

[0072] Exemplarily, the nameplate image information is parsed to extract parameter configuration information of the hydraulic equipment to be tested, where the parameter configuration information includes but is not limited to the maximum working pressure, rated speed, etc.

[0073] S150, based on the above-mentioned external dimension information, the above-mentioned clamping position information, the above-mentioned input component position information and the above-mentioned output component position information, the clamping operation of the universal clamp is controlled to clamp the above-mentioned hydraulic equipment to be tested.

[0074] Exemplarily, based on the aforementioned acquired dimensional information, clamping position information, input component position information and output component position information, the system controls the universal fixture to perform a clamping operation to ensure that the hydraulic equipment is safely and correctly fixed on the test bench for accurate testing.

[0075] S160. Determine test loading parameter information based on the parameter configuration information, wherein the test loading parameter information includes rotation speed loading information and pressure loading information.

[0076] Exemplarily, the parameter configuration information obtained from the nameplate image information determines the test loading parameters suitable for the specific device, such as the pressure and rotation speed to be applied.

[0077] S170. Control the detection process of the hydraulic equipment to be tested according to the test loading parameter information to obtain test response data of the hydraulic equipment to be tested.

[0078] Exemplarily, the hydraulic equipment is controlled according to the set test loading parameter information to perform actual test operations. The response data (such as performance data, possible fault information, etc.) collected during the test will be used to evaluate the status and performance of the equipment.

[0079] In summary, the method proposed in the embodiment of the present application utilizes appearance image information and nameplate image information to adapt to the specific needs of various non-standard hydraulic equipment. By analyzing the appearance size information, clamping position information, input component position information, output component position information and parameter configuration of the hydraulic equipment to be tested, the detection parameters and process can be automatically adjusted without the need for pre-set standard detection procedures. In the industrial environment where non-standard equipment is becoming more and more common, the adaptability to diversified equipment types is improved. Through precise image analysis technology, the key features of the hydraulic equipment can be captured in detail, and the detection parameters can be automatically set according to these features. Not only the possibility of human error is reduced, but also the efficiency of the detection process is improved. Through the parameter configuration information extracted from the nameplate image information, the appropriate test loading parameters, such as pressure and speed, can be intelligently selected. The test process can also be dynamically adjusted according to the actual test response data, so as to better adapt to the actual working conditions and performance characteristics of the equipment. By conducting comprehensive performance and response tests on the equipment to be tested, the safety and reliability of the equipment in actual work are ensured. Especially under harsh working conditions, potential equipment failures and operational risks can be prevented through precise testing in advance. Due to its unique design and functional requirements, conventional detection methods are difficult to fully cover the detection requirements of non-standard hydraulic equipment. This solution uses flexible image processing and parameter configuration extraction technology to enable effective detection even for highly customized equipment. The embodiment of this application provides an efficient, accurate and flexible detection method, which is particularly suitable for meeting the challenges of non-standard hydraulic equipment detection in the current industrial field. It not only improves the intelligent level of detection, but also greatly improves the operating efficiency and safety of the equipment.

[0080] In some examples, the obtaining of the shape dimension information based on the shape image information includes:

[0081] grayscale processing and noise reduction processing are performed on the above-mentioned appearance image information to obtain processed appearance image information;

[0082] Based on the Canny edge detection algorithm, the above-mentioned shape image information is identified to obtain preliminary contour information of the shape;

[0083] Based on the findContours method, the preliminary contour information of the above-mentioned shape is identified to obtain the precise contour information of the shape;

[0084] The above-mentioned external dimension information is determined based on the above-mentioned precise contour information of the external shape and the image information of the standard reference object, wherein the above-mentioned external dimension information is the maximum external dimension of the above-mentioned hydraulic equipment to be tested.

[0085] Exemplarily, grayscale processing is to convert a color image into a grayscale image, which simplifies the amount of data and makes subsequent processing more efficient. Grayscale images only contain brightness information, not color information, which is sufficient for tasks such as edge detection. Various noises may be introduced during the image capture process, which will affect the accuracy of image analysis. By using filters (such as Gaussian filtering, median filtering, etc.) to reduce noise, important image features can be clearly extracted.

[0086] Canny edge detection can highly accurately identify low-error edges in images while suppressing noise interference. First, the preliminary contour information of the hydraulic equipment is identified from the processed shape image information through the Canny algorithm. And based on the findContours method, the precise contour information of the shape is further extracted from the preliminary contour information based on the Canny edge detection results. This method can extract contour lines from binary images and organize these contours from the outside to the inside. Through two edge extractions, the precise contour information of the equipment shape can be obtained.

[0087] A standard reference object is an object of standard size whose dimensions are known in the image. By comparing the outline of the hydraulic equipment with the reference object, the actual dimensions of the equipment can be accurately calculated.

[0088] The embodiment of the present application ensures high accuracy of dimension measurement through image processing technology, reduces manual intervention, and improves processing speed and efficiency. The reliability of image analysis is improved through two consecutive edge detection algorithms, making edge detection more accurate.

[0089] In some examples, the obtaining of the clamping position information, the input component position information, and the output component position information based on the appearance image information includes:

[0090] Adjusting the appearance image information to a standard image size to obtain standard appearance image information and adjustment ratio information, wherein the standard image size is equal to the standard digital model image size in the hydraulic equipment standard digital model library;

[0091] Performing histogram equalization and sharpening processing on the above standard shape image information to obtain an enhanced feature shape image;

[0092] Inputting the enhanced characteristic shape image into the characteristic matching model to match the target digital model image corresponding to the enhanced characteristic shape image in the hydraulic equipment standard digital model library;

[0093] Obtaining target clamping position information, target input component position information and target output component position information corresponding to the target digital-analog image;

[0094] The clamping position information, the input component position information and the output component position information are determined based on the target clamping position information, the target input component position information, the target output component position information and the adjustment ratio information.

[0095] For example, the original shape image information is adjusted to the same size as the standard digital model image in the hydraulic equipment standard digital model library, which can ensure consistency with the standard digital model image and facilitate subsequent feature matching and analysis. The adjusted scale information can be used for accurate calculation of size and position in subsequent steps.

[0096] The standard shape image information is subjected to histogram equalization and sharpening processing to obtain an enhanced feature shape image. The contrast of the image is improved by histogram equalization, making the features in the image more obvious and convenient for subsequent processing. The details of the image, especially the edge part, are enhanced by sharpening processing, which is conducive to identifying the precise position.

[0097] The enhanced feature shape image is matched with the standard digital model image in the standard digital model library to determine the corresponding target digital model image. This can be achieved through pattern recognition and machine learning technology to ensure a high degree of consistency between the image and the model in the library.

[0098] Once the target digital model image is determined, the corresponding detailed position information can be extracted from the hydraulic equipment standard digital model library, including target clamping position information, target input component position information and target output component position information.

[0099] By using the target position information obtained from the hydraulic equipment standard digital model library and the scale information of the previous image adjustment, the corresponding position information of the equipment in actual size can be accurately calculated.

[0100] The method provided in this embodiment greatly improves the accuracy and repeatability of position information acquisition by standardizing image size and feature enhancement, as well as efficient feature matching technology. Automated image processing and feature matching reduce the need for manual intervention and improve overall testing and installation efficiency. It can be easily applied to different models of hydraulic equipment, and only the standard digital model library of hydraulic equipment needs to be adjusted to cope with new equipment. By ensuring the precise determination of the clamping position and component position, the potential risks of the equipment during the test process can be reduced and the reliability of the test results can be improved.

[0101] In some examples, the feature matching model is trained based on a CNN network model, and the feature matching model includes an input layer, a convolution layer, an activation layer, a pooling layer, and a fully connected layer. The convolution layer includes a Prewitt filter, a Gaussian filter, and a Laplacian filter. The convolution layer also includes an adaptive weight module, and the adaptive weight module is used to adjust the weight coefficient of each filter.

[0102] Exemplarily, the input layer is the first layer of the CNN model, which is responsible for receiving the original image data. The input layer will receive the enhanced feature shape image after histogram equalization and sharpening.

[0103] The convolution layer is the core of CNN and is used to extract features from images. The convolution layer of the embodiment of the present application uses different types of filters to extract and enhance image features, including:

[0104] Prewitt filter: Mainly used for edge detection, it can identify horizontal and vertical edges in images.

[0105] Gaussian filter: used to smooth images and reduce noise, which helps the model focus more on important image features rather than noise.

[0106] The Laplacian filter is a second-order derivative filter that is used to highlight edge information in an image.

[0107] The activation layer follows the convolutional layer and can use non-linear activation functions (such as ReLU) to introduce non-linear factors, which enables the network to learn and simulate more complex functions.

[0108] Pooling layers (or downsampling layers) are used to reduce the spatial size of the data, thereby reducing the number of parameters and computational complexity. Pooling operations help extract the main features of the image and maintain invariance to rotation and displacement.

[0109] In the feature matching model, the fully connected layer is responsible for converting the learned feature information into the final matching result.

[0110] The adaptive weight module allows the model to automatically adjust the weight coefficients of each filter based on the training data. The model can learn which filters are most effective when processing specific images or features, and adjust their influence accordingly. This adaptive ability makes the model more flexible and accurate.

[0111] The method proposed in the embodiment of the present application combines multiple filters and adaptive weights, so that the model can more accurately identify and match image features, which is conducive to the accurate measurement and detection of hydraulic equipment. The adaptive weight module enables the network to self-optimize according to different data and conditions, enhancing the learning and generalization capabilities of the model. By reducing unnecessary feature calculations and strengthening the processing of key features, image processing and analysis can be performed faster, thereby improving overall efficiency.

[0112] In some examples, the controlling the clamping operation of the universal clamp based on the outer dimension information, the clamping position information, the input component position information, and the output component position information further includes:

[0113] The moving distance is calculated based on the above-mentioned external dimension information and the above-mentioned clamping position information.

[0114] The clamping speed is determined based on the ratio information between the moving distance and the external dimension information.

[0115] Based on the current position information of the universal fixture, the input component position information, and the output component position information, a moving path is determined.

[0116] Based on the clamping speed and the moving path, the clamping operation of the universal clamp is controlled.

[0117] Exemplarily, firstly, based on the specific coordinates of the external dimension information (such as length, width, height) and the clamping position information, the moving distance required for the universal clamp to reach the predetermined clamping position from the current position is calculated.

[0118] The determination of clamping speed takes into account the ratio of travel distance to equipment size. Larger equipment or longer travel distances require different speed settings to optimize overall clamping time and efficiency. Speed ​​settings also need to take into account the safety and accuracy of the operation to avoid equipment damage or inaccurate positioning due to excessive speed.

[0119] The moving path is planned based on the current position of the universal fixture and the position information of the input and output components on the equipment. Path planning ensures that the fixture can avoid important input and output components to prevent damage during movement. This step is critical in the entire clamping operation, ensuring that the fixture moves efficiently and safely along the optimal path.

[0120] The action of the universal clamp is controlled according to the previously calculated and planned clamping speed and moving path. Through the precise control system, the clamp will move to the clamping position along the planned path at the set speed and perform the clamping action.

[0121] The embodiments of the present application significantly improve the accuracy of the clamping operation by calculating the moving distance in detail and carefully planning the clamping speed and path. Reasonable speed and path planning can significantly improve the overall operating efficiency and reduce clamping and setting time. By avoiding contact with key input and output components, the risk of damage to the equipment during the clamping process is reduced. The system can adapt to hydraulic equipment of different sizes and shapes, showing extremely high flexibility and adaptability.

[0122] In some examples, determining the test loading parameter information based on the parameter configuration information includes:

[0123] Based on the matching operation between the parameter configuration information and the historical loading database, the similarity of the parameter configuration information of the hydraulic equipment to be tested and the tested hydraulic equipment is obtained, wherein the historical loading database includes the matching relationship between the parameter configuration information of multiple tested hydraulic equipment and the historical loading information;

[0124] Incorporating the historical loading information of the tested hydraulic equipment whose parameter configuration information similarity is greater than a preset similarity into the test loading parameter candidate data set;

[0125] The test loading parameter information is generated based on the historical loading information in the test loading parameter candidate data set.

[0126] Exemplarily, the parameter configuration information (such as model, rated pressure, maximum flow, etc.) of the hydraulic device to be tested is compared and matched with the historical loading database. The historical loading database contains parameter configuration information of various tested hydraulic devices and their corresponding historical loading information.

[0127] The goal of the matching operation is to find historical records that are similar to the current device parameter configuration information and are higher than a preset threshold. The similarity calculation can be based on the weighted scores of multiple parameters to ensure the accuracy and relevance of the match.

[0128] Once historical loading records with high similarity are found, the loading information of these records (including historical test data of speed and pressure) will be selected and incorporated into a candidate data set, namely the test loading parameter candidate data set. This candidate data set will serve as the basis for generating the final test loading parameters.

[0129] Finally, the information is filtered or integrated from the candidate data sets to form the final test loading parameters. The generated test loading parameters can be ensured to be both safe and able to effectively simulate actual operating conditions through data averaging, optimal range selection, or optimization based on specific algorithms.

[0130] The method proposed in the embodiment of the present application can more accurately predict and set the test conditions of the current device by using historically verified loading information, reducing the uncertainty in the test process. It saves time and resources to design test loading parameters for each device separately, especially when the device parameters are similar. The use of verified loading parameters reduces the risk of device failure that may occur during the test, increases the safety of the test, and can be applied to non-standard devices.

[0131] In some examples, generating the test loading parameter information based on the historical loading information in the test loading parameter candidate data set includes:

[0132] Based on the median value of the historical loading information in the test loading parameter candidate data set, basic test loading parameter information is generated.

[0133] Obtain the response analysis results corresponding to the historical loading information in the above test loading parameter candidate data set.

[0134] The historical loading information with abnormalities in the response analysis results is selected and clustered based on the abnormality types to generate N groups of clustered historical loading information, wherein the abnormality types include one or more of pressure abnormality, flow abnormality, temperature abnormality, noise and vibration abnormality, leakage abnormality, motor start-up abnormality, and oil quality abnormality.

[0135] Generate enhanced test loading parameter information of anomaly detection items based on each group of cluster historical loading information.

[0136] The above-mentioned basic test loading parameter information and the above-mentioned enhanced test loading parameter information are used as the above-mentioned test loading parameter information.

[0137] For example, the median of historical loading information such as speed and pressure is selected from the hydraulic equipment standard digital model library as the basic test loading parameter. Using the median instead of the average can reduce the impact of extreme data on the test parameter setting, thereby providing a more stable test baseline.

[0138] Analyze the response results of each piece of historical loading data, such as the output efficiency of the equipment after operation, any abnormalities that occurred, etc.

[0139] The historical loading information with abnormalities in the response analysis results is selected and clustered based on the types of abnormalities to identify those historical loading data that show various abnormalities in the test (such as pressure abnormalities, flow abnormalities, temperature abnormalities, noise and vibration abnormalities, leakage abnormalities, motor start-up abnormalities, oil quality abnormalities, etc.).

[0140] These data are clustered according to the anomaly types to form several groups, each group containing historical data with similar anomaly types.

[0141] For each type of anomaly, specific enhanced test loading parameter information is generated, which is designed to pay special attention to and test the conditions that may cause similar anomalies during testing. Enhanced test loading parameter information may include higher or lower pressure settings, changes in flow or temperature ranges, to simulate the operating environment that caused the anomaly.

[0142] The basic test loading parameter information and the enhanced test loading parameter information are combined to form the final test plan (ie, the test loading parameter information). This ensures the comprehensiveness of the test and allows for in-depth inspection of known potential problems.

[0143] By combining basic and enhanced test loading parameter information, the embodiments of the present application not only cover normal operating conditions, but also make targeted tests for specific situations where problems have occurred in the past. The use of medians and cluster analysis based on actual abnormal data improves the accuracy and relevance of test parameter settings. Identifying and focusing on testing conditions that may cause equipment failures helps prevent future equipment failures and improve equipment reliability and safety.

[0144] In some examples, the test response data includes basic test response data and enhanced test response data.

[0145] The above-mentioned control of the detection process of the above-mentioned hydraulic equipment to be tested according to the above-mentioned test loading parameter information to obtain the test response data of the above-mentioned hydraulic equipment to be tested includes:

[0146] Get the number of exceptions corresponding to each exception type in the above response analysis results.

[0147] The number of basic tests and enhanced tests is determined based on the above abnormal number.

[0148] Based on the basic test times and the basic test loading parameter information, the basic detection process of the hydraulic equipment to be tested is controlled to obtain basic test response data of the hydraulic equipment to be tested.

[0149] Based on the enhanced test times and the enhanced test loading parameter information, the enhanced detection process of the hydraulic equipment to be tested is controlled to obtain enhanced test response data of the hydraulic equipment to be tested.

[0150] Exemplarily, historical test data is analyzed to count the number of occurrences of various anomalies (such as pressure anomalies, flow anomalies, etc.), thereby determining the basis for the focus and frequency of subsequent tests.

[0151] Adjust the number of basic and enhanced tests based on the number of anomalies counted. If a certain type of anomaly occurs frequently, you may need to increase the number of enhanced tests for that anomaly to more deeply investigate and resolve potential issues.

[0152] Basic testing is performed using the determined basic test times and basic test loading parameter information (usually standard operating conditions for normal equipment operation). Basic testing is designed to evaluate the performance and reliability of hydraulic equipment under normal operating conditions.

[0153] Enhanced testing is performed based on the enhanced test setting times and enhanced test loading parameter information (these parameters are usually adjusted for specific anomalies previously discovered). Enhanced testing focuses on specific test conditions that have historically caused problems, and is designed to trigger potential or known problems of the equipment through extreme or changing operating conditions, so that they can be further analyzed and resolved.

[0154] For example, basic response data is often derived from the performance of hydraulic equipment under standard or normal operating conditions. The goal of basic response data is to evaluate the performance and reliability of the equipment without any enhanced or special conditions. Basic response data can include, but is not limited to:

[0155] Force and stress: reflect the physical bearing capacity of the hydraulic equipment under normal load.

[0156] Torque and work: reflect the energy output and efficiency indicators of the hydraulic equipment under test under standard operating conditions.

[0157] Fluid pressure: reflects the pressure performance of the hydraulic equipment under normal flow conditions.

[0158] Enhanced response data results from applying extreme or special test conditions to a device in order to trigger and identify specific factors that may have caused historical anomalies. Enhanced response data focuses on specific test conditions that have historically caused problems, including but not limited to:

[0159] Mechanical Efficiency: Under stressful test conditions, such as changing load or speed limits, changes in mechanical efficiency can reveal potential problems.

[0160] Fluid pressure (under varying operating conditions): During step-up testing, unusual changes in fluid pressure may indicate flow anomalies, leaks, or other pressure-related problems.

[0161] By customizing the number of tests and parameters based on historical abnormal data, problems can be identified and resolved more effectively, avoiding future equipment failures. Using data to guide test decisions improves the overall efficiency and effectiveness of the test process, ensuring that test activities can target the most likely problem areas. By gaining a deeper understanding of how the equipment performs under different conditions, product design and manufacturing processes can be optimized, improving the quality and reliability of the final product.

[0162] In some examples, this also includes:

[0163] Obtain the workplace where the above hydraulic equipment is to be put into use.

[0164] Based on the above-mentioned workplace to be put into use, the risk factors corresponding to different types of abnormalities are determined.

[0165] The above-mentioned basic test times and the above-mentioned enhanced test times are determined based on the risk factor corresponding to each abnormality type and the number of abnormalities corresponding to each abnormality type.

[0166] For example, determine the specific workplace where the hydraulic equipment will be put into use. Different workplaces to be put into use may have different operating conditions and environmental factors, such as temperature, humidity, dust level, mechanical load, etc., which may affect the performance and failure rate of the equipment.

[0167] According to the environment in which the hydraulic equipment will operate, the risk level of various possible anomalies (such as pressure anomalies, temperature anomalies, etc.) is evaluated, and a risk factor is assigned to each anomaly. These risk factors are based on the potential consequences of equipment failure in these environments, such as operational safety risks, production interruption costs, etc.

[0168] The frequency of each anomaly (number of anomalies) and the risk of each anomaly (risk factor) are combined to adjust the number of basic tests and enhanced tests. If the risk factor of a certain anomaly type is high and the frequency of anomalies in historical data is also high, the number of corresponding enhanced tests will be increased to ensure that these high-risk issues can be thoroughly detected and resolved.

[0169] For example, consider a hydraulic pump as the hydraulic equipment to be tested and assume that it will be put into a working environment in a mining site. In this environment, the equipment may face challenges including high dust levels, extreme temperature fluctuations, and possible mechanical shocks. Determine the type of abnormality and its criticality.

[0170] Since hydraulic pumps are subject to extremely high operating pressures in mining equipment, the risk factor for pressure anomalies is high. The consequences could include equipment failure or more serious mechanical damage. Temperature fluctuations in mining sites can cause equipment to overheat or overcool, affecting performance. Set the risk factor for this anomaly to medium. In high dust environments, dust can clog the pump's filtration system, causing reduced efficiency or damage. Set the risk factor for dust anomalies to medium to high.

[0171] Determine the number of tests based on the risk factor of the anomaly type and the number of anomalies:

[0172] Historical data shows that hydraulic pumps often have abnormal pressure under similar conditions, so the corresponding enhanced test times are set to high (such as 10 tests) to fully detect possible pressure problems. Although temperature problems are not as frequent as pressure problems in historical data, given their potential impact, basic tests are performed 5 times and enhanced tests are performed 3 times. Dust-related tests should also be taken seriously, with basic tests performed 3 times and enhanced tests performed 5 times, with special checks on the filtration system and sealing performance.

[0173] By adjusting the test parameters to suit the environmental conditions of a specific workplace through the method provided in this embodiment, the stability and safety of the equipment in the actual operating environment can be ensured. By adjusting the test frequency based on the risk factor, the test pays more attention to those anomalies that may lead to serious consequences, thereby effectively managing and reducing operational risks. By focusing on key test areas, test resources can be allocated more effectively, avoiding over-investment in low-risk issues, thereby improving overall test efficiency.

[0174] like Figure 2 As shown, the present application proposes a hydraulic equipment intelligent detection system, comprising:

[0175] The first acquisition unit 21 is used to acquire the appearance image information and nameplate image information of the hydraulic equipment to be tested.

[0176] The second acquiring unit 22 acquires the shape size information based on the shape image information.

[0177] The third acquisition unit 23 is used to acquire the clamping position information, the input component position information and the output component position information based on the above-mentioned appearance image information.

[0178] The fourth acquisition unit 24 is used to acquire parameter configuration information based on the nameplate image information.

[0179] The clamping unit 25 is used to control the clamping operation of the universal clamp based on the above-mentioned shape dimension information, the above-mentioned clamping position information, the above-mentioned input component position information and the above-mentioned output component position information, so as to clamp the above-mentioned hydraulic equipment to be tested.

[0180] The determination unit 26 is used to determine the test loading parameter information based on the parameter configuration information, wherein the test loading parameter information includes rotation speed loading information and pressure loading information.

[0181] The testing unit 27 is used to control the detection process of the hydraulic device to be tested according to the test loading parameter information to obtain the test response data of the hydraulic device to be tested.

[0182] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A hydraulic equipment intelligent detection method, characterized in that: include: Obtaining appearance image information and nameplate image information of the hydraulic equipment to be tested; Acquire shape dimension information based on the shape image information; Acquire clamping position information, input component position information, and output component position information based on the appearance image information; Acquiring parameter configuration information based on the nameplate image information; Controlling the clamping operation of the universal clamp based on the outer dimension information, the clamping position information, the input component position information and the output component position information to clamp the hydraulic device to be tested; Determining test loading parameter information based on the parameter configuration information, wherein the test loading parameter information includes rotation speed loading information and pressure loading information; Controlling the detection process of the hydraulic device to be tested according to the test loading parameter information to obtain test response data of the hydraulic device to be tested; The obtaining of the clamping position information, the input component position information and the output component position information based on the appearance image information comprises: Adjusting the appearance image information to a standard image size to obtain standard appearance image information and adjustment ratio information, wherein the standard image size is equal to a standard digital model image size in a standard digital model library of hydraulic equipment; Performing histogram equalization and sharpening processing on the standard shape image information to obtain an enhanced feature shape image; Inputting the enhanced characteristic shape image into a characteristic matching model to match a target digital model image corresponding to the enhanced characteristic shape image in the hydraulic equipment standard digital model library; Obtaining target clamping position information, target input component position information, and target output component position information corresponding to the target digital-analog image; The clamping position information, the input component position information, and the output component position information are determined based on the target clamping position information, the target input component position information, the target output component position information, and the adjustment ratio information.

2. The intelligent detection method for hydraulic equipment according to claim 1, characterized in that: The acquiring of the external dimension information based on the external dimension image information comprises: grayscale processing and noise reduction processing are performed on the shape image information to obtain processed shape image information; Identify the shape image information based on the Canny edge detection algorithm to obtain preliminary contour information of the shape; Identify the preliminary contour information of the shape based on the findContours method to obtain the precise contour information of the shape; The external dimension information is determined based on the external precise contour information and the image information of the standard reference object, wherein the external dimension information is the maximum external dimension of the hydraulic equipment to be tested.

3. The intelligent detection method for hydraulic equipment according to claim 1, characterized in that: The feature matching model is obtained based on CNN network model training. The feature matching model includes an input layer, a convolution layer, an activation layer, a pooling layer and a fully connected layer. The convolution layer includes a Prewitt filter, a Gaussian filter and a Laplacian filter. The convolution layer also includes an adaptive weight module, and the adaptive weight module is used to adjust the weight coefficient of each filter.

4. The intelligent detection method for hydraulic equipment according to claim 1, characterized in that: The method of controlling the clamping operation of the universal clamp based on the outer dimension information, the clamping position information, the input component position information and the output component position information further includes: Calculate the moving distance based on the outer dimension information and the clamping position information; Determining a clamping speed based on ratio information of the moving distance and the outer dimension information; Determining a moving path based on the current position information of the universal fixture, the input component position information, and the output component position information; Based on the clamping speed and the moving path, a clamping operation of the universal clamp is controlled.

5. The intelligent detection method for hydraulic equipment according to claim 1, characterized in that: The determining the test loading parameter information based on the parameter configuration information includes: Based on the matching operation between the parameter configuration information and the historical loading database, the similarity of the parameter configuration information of the hydraulic device to be tested and the tested hydraulic device is obtained, wherein the historical loading database includes the matching relationship between the parameter configuration information of multiple tested hydraulic devices and the historical loading information; Incorporating historical loading information of tested hydraulic equipment whose parameter configuration information similarity is greater than a preset similarity into a test loading parameter candidate data set; The test loading parameter information is generated based on the historical loading information in the test loading parameter candidate data set.

6. The intelligent detection method for hydraulic equipment according to claim 5, characterized in that: The generating the test loading parameter information based on the historical loading information in the test loading parameter candidate data set includes: Generate basic test loading parameter information based on the median value of the historical loading information in the test loading parameter candidate data set; Obtaining a response analysis result corresponding to the historical loading information in the test loading parameter candidate data set; Selecting historical loading information with abnormalities in the response analysis results and clustering them based on the types of abnormalities to generate N groups of clustered historical loading information, wherein the types of abnormalities include one or more of pressure abnormalities, flow abnormalities, temperature abnormalities, noise and vibration abnormalities, leakage abnormalities, motor start-up abnormalities, and oil quality abnormalities; Generate enhanced test loading parameter information of anomaly detection items according to each group of cluster historical loading information; The basic test loading parameter information and the enhanced test loading parameter information are used as the test loading parameter information.

7. The intelligent detection method for hydraulic equipment according to claim 6, characterized in that: The test response data includes basic test response data and enhanced test response data. The step of controlling the detection process of the hydraulic device to be tested according to the test loading parameter information to obtain the test response data of the hydraulic device to be tested includes: Obtain the number of exceptions corresponding to each type of exception in the response analysis result; Determine the number of basic tests and the number of enhanced tests based on the number of abnormalities; Controlling the basic detection process of the hydraulic equipment to be tested based on the basic test number and the basic test loading parameter information to obtain basic test response data of the hydraulic equipment to be tested; The enhanced detection process of the hydraulic equipment to be tested is controlled based on the enhanced test number and the enhanced test loading parameter information to obtain enhanced test response data of the hydraulic equipment to be tested.

8. The intelligent detection method for hydraulic equipment according to claim 7, characterized in that: Also includes: Obtaining a working place where the hydraulic equipment is to be put into use; Determining risk factors corresponding to different types of abnormalities based on the workplace to be put into use; The basic test times and the enhanced test times are determined based on the risk factor corresponding to each abnormality type and the number of abnormalities corresponding to each abnormality type.

9. An intelligent detection system for hydraulic equipment, characterized in that: include: A first acquisition unit is used to acquire the appearance image information and nameplate image information of the hydraulic equipment to be tested; A second acquisition unit, which acquires shape size information based on the shape image information; A third acquisition unit, used for acquiring clamping position information, input component position information and output component position information based on the appearance image information; a fourth acquiring unit, configured to acquire parameter configuration information based on the nameplate image information; A clamping unit, used to control the clamping operation of the universal clamp based on the outer dimension information, the clamping position information, the input component position information and the output component position information, so as to clamp the hydraulic device to be tested; A determination unit, configured to determine test loading parameter information based on the parameter configuration information, wherein the test loading parameter information includes rotation speed loading information and pressure loading information; A testing unit, used for controlling the detection process of the hydraulic device to be tested according to the test loading parameter information, so as to obtain test response data of the hydraulic device to be tested; The obtaining of the clamping position information, the input component position information and the output component position information based on the appearance image information comprises: Adjusting the appearance image information to a standard image size to obtain standard appearance image information and adjustment ratio information, wherein the standard image size is equal to a standard digital model image size in a standard digital model library of hydraulic equipment; Performing histogram equalization and sharpening processing on the standard shape image information to obtain an enhanced feature shape image; Inputting the enhanced characteristic shape image into a characteristic matching model to match a target digital model image corresponding to the enhanced characteristic shape image in the hydraulic equipment standard digital model library; Obtaining target clamping position information, target input component position information, and target output component position information corresponding to the target digital-analog image; The clamping position information, the input component position information, and the output component position information are determined based on the target clamping position information, the target input component position information, the target output component position information, and the adjustment ratio information.

Images