Bearing Detection System and Method for Automotive Generator

Abstract

The present invention discloses a bearing detection system and method for an automotive generator, relating to the technical field of electric machines, including: performing data acquisition through a sensor array to obtain a historical data set of the sensor array monitoring a target bearing within a preset historical window. Traversing the historical data set for data stability analysis to determine a vibration stability factor, a temperature stability factor, and an acoustic emission signal stability factor. Using each stability factor as an index to perform a centralized search in a bearing detection configuration space to determine a target detection step size. Based on the target detection step size, performing bearing status detection on the target bearing according to a preset detection item set to obtain a periodic detection data set, and using a bearing detection identifier to identify the periodic detection data set to obtain a target bearing detection result. The technical problems of low detection efficiency and poor detection accuracy existing in the bearing detection method of an automotive generator in the prior art are solved.

Description

Technical Field

[0001] This application relates to the technical field of motors, and particularly to a bearing detection system and method for automotive generators. Background Art

[0002] Bearings are common key components in mechanical equipment, and their operating status has an important impact on the stability and service life of the equipment. However, due to the influence of factors such as vibration, temperature, and wear during long-term operation, bearings are prone to failure. Most traditional bearing monitoring methods rely on a single data source such as vibration data or temperature data, making it difficult to comprehensively and accurately evaluate the operating status of bearings. In recent years, collecting bearing operation data through a variety of sensor arrays has become a trend. This method combines multi-dimensional data such as vibration, temperature, and acoustic emission signals, and can more comprehensively reflect the operating status of bearings. However, the existing bearing status detection methods based on a variety of sensor arrays still have problems such as low detection efficiency and poor detection accuracy.

[0003] Therefore, in the prior art, the bearing detection method for automotive generators has technical problems of low detection efficiency and poor detection accuracy. Summary of the Invention

[0004] This application provides a bearing detection system and method for automotive generators, which solves the technical problems of low detection efficiency and poor detection accuracy in the bearing detection method for automotive generators in the prior art. By dynamically optimizing the detection step size of sensor data acquisition, the system can obtain data according to the optimal acquisition step size when performing data acquisition, thereby achieving precise detection of the bearing operating status and improving the efficiency and reliability of bearing status detection.

[0005] In the first aspect of the present application, a bearing detection system for an automotive generator is provided. The system includes: a data acquisition module for performing data acquisition of a sensor array to obtain a historical vibration monitoring data set, a historical temperature monitoring data set, and a historical acoustic emission signal monitoring data set of the target bearing monitored by the sensor array within a preset historical window. A stability analysis module for traversing the historical vibration monitoring data set, the historical temperature monitoring data set, and the historical acoustic emission signal monitoring data set for data stability analysis to determine a vibration stability factor, a temperature stability factor, and an acoustic emission signal stability factor. A target detection step acquisition module for performing a centralized search in a bearing detection configuration space using the vibration stability factor, the temperature stability factor, and the acoustic emission signal stability factor as indexes to determine a target detection step. A detection result acquisition module for performing bearing status detection on the target bearing according to a preset detection item set based on the target detection step to obtain a periodic detection data set, and using a bearing detection identifier to identify the periodic detection data set to obtain a target bearing detection result.

[0006] In an implementation manner, the stability analysis module is further configured to: perform data analysis on the historical vibration monitoring data set using the box plot method to obtain a vibration box plot. Count the historical vibration monitoring data located between the upper aggregation boundary and the lower aggregation boundary in the vibration box plot to obtain a cleaned historical vibration data set, where the upper aggregation boundary is a boundary obtained by extending the third quartile by 1.5 times the interquartile range upward, and the lower aggregation boundary is a boundary obtained by extending the first quartile by 1.5 times the interquartile range downward. Calculate the variance of the cleaned historical vibration data set to obtain the vibration stability factor. Perform data stability analysis on the historical temperature monitoring data set and the historical acoustic emission signal monitoring data set to obtain the temperature stability factor and the acoustic emission signal stability factor.

[0007] In an implementation manner, the stability analysis module is further configured to: sort the historical vibration monitoring data set in ascending order, and use the historical vibration monitoring data at the middle position as the median of the box. Calculate the first quartile and the third quartile of the historical vibration monitoring data set. Use the first quartile as the upper boundary and the third quartile as the lower boundary, and combine the median of the box to construct the vibration box plot.

[0008] In the implementation manner, the target detection step acquisition module is further configured to: obtain a plurality of sample vibration stability factors, a plurality of sample temperature stability factors, and a plurality of sample acoustic emission signal stability factors, as well as the corresponding plurality of sample detection steps as construction data. Pre-construct a three-dimensional space, where the origin of coordinates of the three-dimensional space is o, the x-axis is the vibration stability factor, the y-axis is the temperature stability factor, and the z-axis is the acoustic emission signal stability factor. Input the construction data into the three-dimensional space to obtain a plurality of sample space points, and use the plurality of sample detection steps to label the plurality of sample space points to obtain the bearing detection configuration space.

[0009] In the implementation manner, the target detection step acquisition module is further configured to: use the plane passing through the vibration stability factor and parallel to the yoz plane in the bearing detection configuration space as the first plane. Use the plane passing through the temperature stability factor and parallel to the xoz plane in the bearing detection configuration space as the second plane. Use the plane passing through the acoustic emission signal stability factor and parallel to the xoy plane in the bearing detection configuration space as the third plane. Use the space enclosed by the yoz plane, the xoz plane, the xoy plane and the first plane, the second plane, and the third plane as the configuration subspace, where the configuration subspace includes a plurality of configuration sample space points. Conduct a centralized search on the plurality of configuration sample space points to determine the target configuration sample space point, and use the sample detection step corresponding to the target configuration sample space point as the target detection step.

[0010] In the implementation manner, the target detection step acquisition module is further configured to: extract the central configuration sample space point of the configuration subspace, and use the central configuration sample space point as the starting point to construct a central neighborhood according to a preset centralized search bandwidth, where the central neighborhood is a spherical subspace with the central configuration sample space point as the center of the sphere and the preset centralized search bandwidth as the radius. Count the number of configuration sample space points in the central neighborhood, divide the statistical result by the volume of the central neighborhood to obtain the central neighborhood centralized density. Randomly select a configuration sample space point from the edge of the central neighborhood as the first search configuration sample space point, and construct the first search neighborhood centralized density of the first search configuration sample space point. Determine whether the first search neighborhood centralized density is greater than or equal to the central neighborhood centralized density. If so, update the first search configuration sample space point as the starting point and continue the centralized search until the preset centralized search number of times is satisfied, and use the search configuration sample space point obtained in the last search as the target configuration sample space point.

[0011] In the implementation manner, the target detection step size acquisition module is further configured to: if not, update the search update failure times with an initial value of 0 to 1, and randomly extract a configuration sample space point from the edge of the central neighborhood again as the first search configuration sample space point for centralized search analysis. When the search update failure times are greater than the preset maximum search update failure times, use the central configuration sample space point as the target configuration sample space point.

[0012] In the second aspect of the present application, a bearing detection method for an automotive generator is provided. The method includes: performing sensor array data acquisition to obtain a historical vibration monitoring data set, a historical temperature monitoring data set, and a historical acoustic emission signal monitoring data set of the sensor array for monitoring a target bearing within a preset historical window.

[0013] Traverse the historical vibration monitoring data set, the historical temperature monitoring data set, and the historical acoustic emission signal monitoring data set for data stability analysis to determine a vibration stability factor, a temperature stability factor, and an acoustic emission signal stability factor.

[0014] Use the vibration stability factor, the temperature stability factor, and the acoustic emission signal stability factor as indexes to perform centralized search in the bearing detection configuration space to determine the target detection step size.

[0015] Based on the target detection step size, perform bearing status detection on the target bearing according to a preset detection item set to obtain a periodic detection data set, and use a bearing detection identifier to identify the periodic detection data set to obtain a target bearing detection result.

[0016] The bearing detection system and method for an automotive generator proposed in this application perform data acquisition through a sensor array to obtain a historical vibration monitoring data set, a historical temperature monitoring data set, and a historical acoustic emission signal monitoring data set of the target bearing monitored by the sensor array within a preset historical window. Traverse the historical vibration monitoring data set, the historical temperature monitoring data set, and the historical acoustic emission signal monitoring data set for data stability analysis to determine the vibration stability factor, the temperature stability factor, and the acoustic emission signal stability factor. Using the vibration stability factor, the temperature stability factor, and the acoustic emission signal stability factor as indexes, conduct a centralized search in the bearing detection configuration space to determine the target detection step size. Based on the target detection step size, perform bearing status detection on the target bearing according to a preset detection item set to obtain a periodic detection data set, and use a bearing detection identifier to identify the periodic detection data set to obtain the target bearing detection result. This solves the technical problems of low detection efficiency and poor detection accuracy in the existing bearing detection methods for automotive generators. By dynamically optimizing the detection step size of sensor data acquisition, the system can obtain data according to the optimal acquisition step size when performing data acquisition, thereby achieving precise detection of the bearing operating state and improving the efficiency and reliability of bearing status detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings of the embodiments of the present disclosure will be briefly introduced below. Flowcharts are used in this application to illustrate the operations performed by the system according to the embodiments of the application. It should be understood that the operations in the front or below do not necessarily need to be executed precisely in sequence. On the contrary, according to the need, they can be executed in reverse order or simultaneously. At the same time, other operations can also be added to these processes, or one or several operations can be removed from these processes.

[0018] Figure 1 Schematic structural diagram of the bearing detection system for an automotive generator provided by an embodiment of the present application.

[0019] Figure 2 Schematic flowchart of the bearing detection method for an automotive generator provided by an embodiment of the present application.

[0020] Explanation of reference numerals: Data acquisition module 11, stability analysis module 12, target detection step size acquisition module 13, detection result acquisition module 14. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0021] The above description is only an overview of the technical solution of the present application. In order to be able to understand the technical means of the present application more clearly, it can be implemented in accordance with the content of the specification. And in order to make the above and other purposes, features and advantages of the present application more obvious and understandable, the specific embodiments of the present application are specifically given below.

[0022] In order to make the purpose, technical solution and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings. The described embodiments should not be regarded as limitations of the present application. All other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present application.

[0023] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments. However, it can be understood that "some embodiments" can be the same subset or different subsets of all possible embodiments, and can be combined with each other without conflict. The terms "first / second" involved are only used to distinguish similar objects and do not represent a specific order for the objects. The terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or server that includes a series of steps or units does not have to be limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or are inherent to these processes, methods, products or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which the present application belongs. The terms used herein are only for the purpose of describing the embodiments of the present application.

[0024] The embodiments of the present application provide a bearing detection system and method for an automotive generator, as Figure 2 shown, the method includes:

[0025] Perform sensor array data acquisition to obtain a set of historical vibration monitoring data, a set of historical temperature monitoring data, and a set of historical acoustic emission signal monitoring data for the target bearing by the sensor array within a preset historical window. Traverse the set of historical vibration monitoring data, the set of historical temperature monitoring data, and the set of historical acoustic emission signal monitoring data for data stability analysis to determine the vibration stability factor, the temperature stability factor, and the acoustic emission signal stability factor.

[0026] Execute sensor array data acquisition to obtain the monitoring data of the target bearing by the sensor array within a preset historical window, where the preset historical window is a pre-set historical time interval window, such as the acquisition data of the sensor array within the past month. The monitoring data includes: a historical vibration monitoring data set, a historical temperature monitoring data set, and a historical acoustic emission signal monitoring data set. Among them, the vibration monitoring data measures the vibration signal of the bearing through an acceleration sensor and records information such as the vibration amplitude, frequency, and vibration waveform. The temperature monitoring data monitors the change in the surface temperature of the bearing through a temperature sensor, and an increase in temperature may indicate poor lubrication or an impending failure of the bearing. The acoustic emission signal monitoring data captures the high-frequency sound signals generated by the bearing during operation through an acoustic emission sensor. Abnormal acoustic emission signals may indicate cracks, wear, or other failures. Subsequently, the stability analysis module performs data stability analysis by traversing the historical vibration monitoring data set, the historical temperature monitoring data set, and the historical acoustic emission signal monitoring data set to determine the vibration stability factor, the temperature stability factor, and the acoustic emission signal stability factor.

[0027] The method provided by the embodiment of the present application further includes: performing data analysis on the historical vibration monitoring data set by using the box plot method to obtain a vibration box plot. Count the historical vibration monitoring data located between the aggregation upper bound and the aggregation lower bound in the vibration box plot to obtain a cleaned historical vibration data set, where the aggregation upper bound is the boundary obtained by extending 1.5 times the interquartile range upward from the third quartile, and the aggregation lower bound is the boundary obtained by extending 1.5 times the interquartile range downward from the first quartile. Calculate the variance of the cleaned historical vibration data set to obtain the vibration stability factor. Perform data stability analysis on the historical temperature monitoring data set and the historical acoustic emission signal monitoring data set to obtain the temperature stability factor and the acoustic emission signal stability factor.

[0028] The box plot method is used to analyze the historical vibration monitoring data set, and the box plot corresponding to the historical vibration monitoring data set is drawn to obtain a vibration box plot. Among them, the box plot is a graphical tool that displays data distribution through five statistics (minimum value, first quartile, median, third quartile and maximum value). The historical vibration monitoring data between the upper and lower bounds of the aggregation in the vibration box plot are counted, and the outliers outside the upper and lower bounds of the aggregation are eliminated. These outliers are usually data fluctuations caused by sensor failure or external interference, thereby completing the cleaning of the historical vibration data set and obtaining a cleaned historical vibration data set. Among them, the upper bound of the aggregation is the boundary obtained by extending the third quartile upward by 1.5 times the interquartile range, that is, the third quartile plus 1.5 times the interquartile range, and the lower bound of the aggregation is the boundary obtained by extending the first quartile downward by 1.5 times the interquartile range, that is, the first quartile plus 1.5 times the interquartile range. Furthermore, the variance of the cleaning history vibration data set is calculated to obtain the vibration stability factor. When the vibration stability factor is smaller, the corresponding vibration is relatively stable, indicating that the vibration state of the bearing is normal. A larger vibration stability factor may indicate that the vibration fluctuation is large, which may be related to the lubrication or failure of the bearing. Finally, the historical temperature monitoring data set and the historical acoustic emission signal monitoring data set are subjected to data stability analysis using the same processing steps as the vibration stability factor acquisition steps, including drawing box plots and cleaning the data, so as to obtain the temperature stability factor and the acoustic emission signal stability factor.

[0029] The method provided in the embodiment of the present application also includes: sorting the historical vibration monitoring data set in ascending order, and using the historical vibration monitoring data in the middle position as the box center line. Calculating the first quartile and the third quartile of the historical vibration monitoring data set. Using the first quartile as the upper boundary and the third quartile as the lower boundary, combined with the box center line, construct the vibration box plot.

[0030] When drawing a vibration box plot, the historical vibration monitoring data set is arranged in order from small to large, and the historical vibration monitoring data in the middle position is used as the box center line, and the box center line is the median of the data set. Calculate the first quartile and the third quartile of the historical vibration monitoring data set. The first quartile is the value located in the lower 25% position after the data set is sorted from small to large. The third quartile is the value located in the upper 25% position after the data set is sorted from small to large. The first quartile is used as the upper boundary, and the third quartile is used as the lower boundary, combined with the box center line, to construct the vibration box plot.

[0031] Taking the vibration stability factor, temperature stability factor, and acoustic emission signal stability factor as indices, a centralized search is performed in the bearing detection configuration space to determine the target detection step size. Based on the target detection step size, the bearing state of the target bearing is detected according to a preset detection item set, a periodic detection data set is obtained, and the bearing detection identifier is used to identify the periodic detection data set to obtain the target bearing detection result.

[0032] The target detection step size acquisition module takes the vibration stability factor, temperature stability factor, and acoustic emission signal stability factor as index parameters, performs a centralized search in the bearing detection configuration space, and determines the target detection step size. The target detection step size is the acquisition period of sensor array data acquisition. Finally, through the detection result acquisition module, based on the target detection step size, the bearing state of the target bearing is detected according to a preset detection item set to obtain a periodic detection data set. The bearing detection identifier is used to identify the periodic detection data set to obtain the target bearing detection result. The bearing detection identifier is constructed based on a neural network model, where the construction data is a large amount of historical vibration monitoring data, temperature monitoring data, and bearing detection result identification data corresponding to acoustic emission signal monitoring data collected. The bearing detection result identification data includes: a normal identifier, the normal identifier includes a normal state rating, an abnormal identifier, the abnormal identifier includes an abnormal state rating, and specific abnormal categories, such as raceway faults, lubrication problems, ball missing, etc. It solves the technical problems of low detection efficiency and poor detection accuracy in the bearing detection method of automotive generators in the prior art. By dynamically optimizing the detection step size of sensor data acquisition, the system can obtain data according to the optimal acquisition step size when performing data acquisition, thereby realizing precise detection of the bearing operating state and improving the efficiency and reliability of bearing state detection.

[0033] The method provided in the embodiment of the present application further includes: obtaining a plurality of sample vibration stability factors, a plurality of sample temperature stability factors, and a plurality of sample acoustic emission signal stability factors, as well as corresponding plurality of sample detection step sizes as construction data. A three-dimensional space is pre-constructed, where the origin of coordinates of the three-dimensional space is o, the x-axis is the vibration stability factor, the y-axis is the temperature stability factor, and the z-axis is the acoustic emission signal stability factor. The construction data is input into the three-dimensional space to obtain a plurality of sample space points, and the plurality of sample space points are marked using the plurality of sample detection step sizes to obtain the bearing detection configuration space.

[0034] The target detection step acquisition module is further configured to obtain multiple sample vibration stability factors, multiple sample temperature stability factors, and multiple sample acoustic emission signal stability factors, as well as the corresponding multiple sample detection steps as construction data. The sample detection step is the acquisition period of sensor array data acquisition. A three-dimensional space is pre-constructed, where the origin of coordinates of the three-dimensional space is o, the x-axis is the vibration stability factor, the y-axis is the temperature stability factor, and the z-axis is the acoustic emission signal stability factor. The construction data is input into the three-dimensional space to obtain the distribution of the construction data in the three-dimensional space, and multiple sample space points are obtained. And the multiple sample detection steps are used to identify the multiple sample space points, so that the multiple sample space points reflect their corresponding sample detection steps, and the bearing detection configuration space is obtained.

[0035] The method provided by the embodiment of the present application further includes: taking the plane passing through the vibration stability factor and parallel to the yoz plane in the bearing detection configuration space as the first plane. Taking the plane passing through the temperature stability factor and parallel to the xoz plane in the bearing detection configuration space as the second plane. Taking the plane passing through the acoustic emission signal stability factor and parallel to the xoy plane in the bearing detection configuration space as the third plane. Taking the space enclosed by the yoz plane, the xoz plane, the xoy plane and the first plane, the second plane, and the third plane as the configuration subspace, where the configuration subspace includes multiple configuration sample space points. Conduct a centralized search on the multiple configuration sample space points to determine the target configuration sample space point, and take the sample detection step corresponding to the target configuration sample space point as the target detection step.

[0036] Taking the plane passing through the vibration stability factor and parallel to the yoz plane in the bearing detection configuration space as the first plane. Taking the plane passing through the temperature stability factor and parallel to the xoz plane in the bearing detection configuration space as the second plane. Taking the plane passing through the acoustic emission signal stability factor and parallel to the xoy plane in the bearing detection configuration space as the third plane. Taking the space enclosed by the first plane, the second plane, the third plane and the yoz plane, the xoz plane, and the xoy plane as the configuration subspace, and the configuration subspace contains multiple sample points, that is, multiple configuration sample space points.

[0037] Further, conduct a centralized search on the multiple configuration sample space points to determine the target configuration sample space point. The target configuration sample space point is the spatial range with the largest sample point density among the multiple configuration sample space points. And take the sample detection step corresponding to the target configuration sample space point as the target detection step. The sample detection step corresponding to the target configuration sample space point is the step length average of the sample detection steps of each sample point in the target configuration sample space.

[0038] The method provided by the embodiment of the present application further includes: extracting the central configuration sample space point of the configuration subspace, using the central configuration sample space point as the starting point, and constructing a central neighborhood according to a preset centralized search bandwidth, where the central neighborhood is a spherical subspace constructed with the central configuration sample space point as the center of the sphere and the preset centralized search bandwidth as the radius. Count the number of configuration sample space points in the central neighborhood, divide the statistical result by the volume of the central neighborhood to obtain the central neighborhood concentration density. Randomly extract a configuration sample space point from the edge of the central neighborhood as the first search configuration sample space point, and construct the first search neighborhood concentration density of the first search configuration sample space point. Determine whether the first search neighborhood concentration density is greater than or equal to the central neighborhood concentration density. If so, update the first search configuration sample space point as the starting point and continue the centralized search until the preset centralized search times are met, and use the search configuration sample space point obtained in the last search as the target configuration sample space point.

[0039] Extract the central configuration sample space point of the configuration subspace, and the central configuration sample space point is the intersection point of the connection lines of the first plane center, the second plane center, and the third plane center. Using the central configuration sample space point as the starting point, construct a central neighborhood according to the preset centralized search bandwidth, that is, a spherical subspace constructed with the central configuration sample space point as the center of the sphere and the preset centralized search bandwidth as the radius, to obtain the central neighborhood. The search bandwidth is the preset search radius, and this radius can be set based on the actual situation, and the central neighborhood is included in the configuration subspace. Count and obtain the number of configuration sample space points in the central neighborhood, and divide the statistical result by the volume of the central neighborhood to obtain the central neighborhood concentration density.

[0040] Further, randomly extract a configuration sample space point from the edge of the central neighborhood as the first search configuration sample space point, and use the same acquisition method as obtaining the central neighborhood concentration density to construct the first search configuration sample space point and the corresponding first search neighborhood concentration density. Determine whether the first search neighborhood concentration density is greater than or equal to the central neighborhood concentration density. If so, the sample points in the first search neighborhood are relatively rich, then update the first search configuration sample space point as the starting point and continue the centralized search until the preset centralized search times are met, and use the search configuration sample space point obtained in the last search as the target configuration sample space point.

[0041] Determine whether the density in the first search neighborhood set is greater than or equal to the density in the central neighborhood set. If not, update the search update failure count, which is initially 0, to 1, and randomly select a configuration sample space point from the edge of the central neighborhood again as the first search configuration sample space point for centralized search analysis. When the density in the next search neighborhood set is less than the density in the central neighborhood set, increment the updated search failure count by 1. When the search update failure count is greater than the preset maximum search update failure count, use the central configuration sample space point as the target configuration sample space point.

[0042] In the foregoing, reference Figure 2 described in detail the bearing detection method of an automotive generator according to an embodiment of the present invention. Next, reference will be made to Figure 1 describe the bearing detection system of an automotive generator according to an embodiment of the present invention.

[0043] The bearing detection system of an automotive generator according to an embodiment of the present invention solves the technical problems of low detection efficiency and poor detection accuracy in the bearing detection method of an automotive generator in the prior art. By dynamically optimizing the detection step size for sensor data acquisition, the system can obtain data according to the optimal acquisition step size when performing data acquisition, thereby achieving precise detection of the bearing operating state and improving the efficiency and reliability of bearing state detection. The bearing detection system of an automotive generator includes: a data acquisition module 11, a stability analysis module 12, a target detection step size acquisition module 13, and a detection result acquisition module 14.

[0044] The data acquisition module 11 is configured to perform sensor array data acquisition to obtain a historical vibration monitoring data set, a historical temperature monitoring data set, and a historical acoustic emission signal monitoring data set of the target bearing monitored by the sensor array within a preset historical window.

[0045] The stability analysis module 12 is configured to traverse the historical vibration monitoring data set, the historical temperature monitoring data set, and the historical acoustic emission signal monitoring data set for data stability analysis to determine a vibration stability factor, a temperature stability factor, and an acoustic emission signal stability factor.

[0046] The target detection step size acquisition module 13 is configured to perform centralized search in the bearing detection configuration space using the vibration stability factor, the temperature stability factor, and the acoustic emission signal stability factor as indexes to determine the target detection step size.

[0047] The detection result acquisition module 14 is configured to perform bearing state detection on the target bearing according to a preset detection item set based on the target detection step size to obtain a periodic detection data set, and use a bearing detection identifier to identify the periodic detection data set to obtain a target bearing detection result.

[0048] Next, the specific configuration of the stability analysis module 12 will be further described in detail. The stability analysis module 12 further includes: performing data analysis on the historical vibration monitoring data set by using the box plot method to obtain a vibration box plot. Counting the historical vibration monitoring data located between the upper aggregation boundary and the lower aggregation boundary in the vibration box plot to obtain a cleaned historical vibration data set, where the upper aggregation boundary is a boundary obtained by extending the third quartile by 1.5 times the interquartile range, and the lower aggregation boundary is a boundary obtained by extending the first quartile by 1.5 times the interquartile range. Calculating the variance of the cleaned historical vibration data set to obtain the vibration stability factor. Performing data stability analysis on the historical temperature monitoring data set and the historical acoustic emission signal monitoring data set to obtain the temperature stability factor and the acoustic emission signal stability factor.

[0049] Next, the specific configuration of the stability analysis module 12 will be described in detail. The stability analysis module 12 may further include: sorting the historical vibration monitoring data set in ascending order, and using the historical vibration monitoring data at the middle position as the median of the box. Calculating the first quartile and the third quartile of the historical vibration monitoring data set. Using the first quartile as the upper boundary and the third quartile as the lower boundary, and combining the median of the box to construct the vibration box plot.

[0050] Next, the specific configuration of the target detection step size acquisition module 13 will be described in detail. The target detection step size acquisition module 13 further includes: acquiring a plurality of sample vibration stability factors, a plurality of sample temperature stability factors, and a plurality of sample acoustic emission signal stability factors, as well as corresponding plurality of sample detection step sizes as construction data. Pre-constructing a three-dimensional space, where the origin of coordinates of the three-dimensional space is o, the x-axis is the vibration stability factor, the y-axis is the temperature stability factor, and the z-axis is the acoustic emission signal stability factor. Inputting the construction data into the three-dimensional space to obtain a plurality of sample space points, and using the plurality of sample detection step sizes to label the plurality of sample space points to obtain the bearing detection configuration space.

[0051] Next, the specific configuration of the target detection step acquisition module 13 will be further described in detail. The target detection step acquisition module 13 further includes: taking the plane passing through the vibration stability factor and parallel to the yoz plane in the bearing detection configuration space as the first plane. Taking the plane passing through the temperature stability factor and parallel to the xoz plane in the bearing detection configuration space as the second plane. Taking the plane passing through the acoustic emission signal stability factor and parallel to the xoy plane in the bearing detection configuration space as the third plane. Taking the space enclosed by the yoz plane, xoz plane, xoy plane and the first plane, second plane, and third plane as the configuration subspace, where the configuration subspace includes a plurality of configuration sample space points. Conducting a centralized search on the plurality of configuration sample space points to determine the target configuration sample space point, and taking the sample detection step corresponding to the target configuration sample space point as the target detection step.

[0052] Next, the specific configuration of the target detection step acquisition module 13 will be described in detail. The target detection step acquisition module 13 further includes: extracting the central configuration sample space point of the configuration subspace, and taking the central configuration sample space point as the starting point to construct a central neighborhood according to a preset centralized search bandwidth, where the central neighborhood is a spherical subspace with the central configuration sample space point as the center of the sphere and the preset centralized search bandwidth as the radius. Counting the number of configuration sample space points in the central neighborhood, and dividing the statistical result by the volume of the central neighborhood to obtain the central neighborhood centralized density. Randomly extracting a configuration sample space point from the edge of the central neighborhood as the first search configuration sample space point, and constructing the first search neighborhood centralized density of the first search configuration sample space point; judging whether the first search neighborhood centralized density is greater than or equal to the central neighborhood centralized density, if so, updating the first search configuration sample space point as the starting point and continuing the centralized search until the preset centralized search times are met, and taking the search configuration sample space point obtained in the last search as the target configuration sample space point.

[0053] Next, the specific configuration of the correlation index acquisition module 13 will be described in detail. The correlation index acquisition module 13 can further include: if not, updating the search update failure count with an initial value of 0 to 1, and randomly extracting a configuration sample space point from the edge of the central neighborhood again as the first search configuration sample space point for centralized search analysis. When the search update failure count is greater than the preset maximum search update failure count, taking the central configuration sample space point as the target configuration sample space point.

[0054] The bearing detection system of the automotive generator provided by the embodiment of the present invention can execute the bearing detection method of the automotive generator provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing the method.

[0055] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, however, any number of different modules can be used and run on the user terminal and / or the server. The included individual units and modules are only divided according to the functional logic, but are not limited to the above division as long as the corresponding functions can be achieved. In addition, the specific names of the respective functional units are only for the convenience of mutual distinction and do not limit the protection scope of the present invention.

[0056] The above specific implementation manners do not constitute a limitation on the protection scope of the present application. Those skilled in the art should understand that various modifications, combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principle of the present application shall be included within the protection scope of the present application.

Claims

1. Bearing detection system for automobile generator, characterized in that: The system comprises: A data acquisition module, used to perform sensor array data acquisition, and obtain a historical vibration monitoring data set, a historical temperature monitoring data set, and a historical acoustic emission signal monitoring data set of the sensor array monitoring the target bearing within a preset historical window; A stability analysis module, used to traverse the historical vibration monitoring data set, the historical temperature monitoring data set and the historical acoustic emission signal monitoring data set to perform data stability analysis, and determine a vibration stability factor, a temperature stability factor and an acoustic emission signal stability factor; A target detection step length acquisition module is used to perform a centralized search in the bearing detection configuration space using the vibration stability factor, temperature stability factor and acoustic emission signal stability factor as indexes to determine the target detection step length; A detection result acquisition module, used to perform bearing state detection on the target bearing according to a preset detection item set based on the target detection step length, obtain a periodic detection data set, and use a bearing detection identifier to identify the periodic detection data set to obtain a target bearing detection result; The stability analysis module is also used to: Performing data analysis on the historical vibration monitoring data set using a box plot method to obtain a vibration box plot; The historical vibration monitoring data between the upper and lower bounds of the aggregation in the vibration box plot are counted to obtain a cleaning historical vibration data set, wherein the upper bound of the aggregation is a boundary obtained by extending the third quartile upward by 1.5 times the interquartile range, and the lower bound of the aggregation is a boundary obtained by extending the first quartile downward by 1.5 times the interquartile range; Performing variance calculation on the cleaning history vibration data set to obtain the vibration stability factor; Performing data stability analysis on the historical temperature monitoring data set and the historical acoustic emission signal monitoring data set to obtain the temperature stability factor and the acoustic emission signal stability factor; The target detection step length acquisition module is also used for: Acquire multiple sample vibration stability factors, multiple sample temperature stability factors, multiple sample acoustic emission signal stability factors, and corresponding multiple sample detection step lengths as construction data; Pre-constructing a three-dimensional space, wherein the coordinate origin of the three-dimensional space is o, the x-axis is the vibration stability factor, the y-axis is the temperature stability factor, and the z-axis is the acoustic emission signal stability factor; The construction data is input into the three-dimensional space to obtain a plurality of sample space points, and the plurality of sample space points are marked using the plurality of sample detection step lengths to obtain the bearing detection configuration space.

2. The bearing detection system for an automobile generator according to claim 1, characterized in that: The stability analysis module is also used to: Sorting the historical vibration monitoring data set in ascending order, and taking the historical vibration monitoring data in the middle as the box center line; Calculating the first quartile and the third quartile of the historical vibration monitoring data set; The first quartile is used as the upper boundary, and the third quartile is used as the lower boundary, combined with the box center line, to construct the vibration box plot.

3. The bearing detection system for an automobile generator according to claim 1, characterized in that: The target detection step length acquisition module is also used for: Taking a plane in the bearing detection configuration space that passes through the vibration stability factor and is parallel to the yoz plane as a first plane; Taking a plane in the bearing detection configuration space that passes through the temperature stability factor and is parallel to the xoz plane as a second plane; A plane in the bearing detection configuration space that passes through the acoustic emission signal stability factor and is parallel to the xoy plane is used as a third plane; The space enclosed by the yoz plane, the xoz plane, the xoy plane and the first plane, the second plane and the third plane is used as a configuration subspace, wherein the configuration subspace includes a plurality of configuration sample space points; The multiple configuration sample space points are searched intensively to determine a target configuration sample space point, and the sample detection step corresponding to the target configuration sample space point is used as the target detection step.

4. The bearing detection system for an automobile generator according to claim 3, characterized in that: The target detection step length acquisition module is also used for: Extracting a central configuration sample space point of the configuration subspace, taking the central configuration sample space point as a starting point, and constructing a central neighborhood according to a preset centralized search bandwidth, wherein the central neighborhood is a spherical subspace constructed with the central configuration sample space point as a sphere center and the preset centralized search bandwidth as a radius; Counting the number of sample space points configured in the central neighborhood, and dividing the statistical result by the volume of the central neighborhood to obtain the central neighborhood concentration density; Randomly extract a configuration sample space point from the edge of the central neighborhood as a first search configuration sample space point, and construct a first search neighborhood concentration density of the first search configuration sample space point; Determine whether the first search neighborhood concentration density is greater than or equal to the central neighborhood concentration density. If so, update the first search configuration sample space point as the starting point, continue the concentrated search until the preset number of concentrated searches is met, and use the search configuration sample space point obtained in the last search as the target configuration sample space point.

5. The bearing detection system for an automobile generator according to claim 4, characterized in that: The target detection step length acquisition module is also used for: If not, the number of search update failures with an initial value of 0 is updated to 1, and a configuration sample space point is randomly selected from the edge of the central neighborhood as the first search configuration sample space point for centralized search analysis. When the number of search update failures is greater than the preset maximum number of search update failures, the central configuration sample space point is used as the target configuration sample space point.

6. A bearing detection method for an automobile generator, characterized in that: The method is applied to the bearing detection system of the automobile generator according to any one of claims 1 to 5, and the method comprises: Execute sensor array data acquisition to obtain a historical vibration monitoring data set, a historical temperature monitoring data set, and a historical acoustic emission signal monitoring data set of the sensor array monitoring the target bearing within a preset historical window; Traversing the historical vibration monitoring data set, the historical temperature monitoring data set and the historical acoustic emission signal monitoring data set to perform data stability analysis, and determine a vibration stability factor, a temperature stability factor and an acoustic emission signal stability factor; Using the vibration stability factor, temperature stability factor and acoustic emission signal stability factor as indexes, a centralized search is performed in the bearing detection configuration space to determine the target detection step length; Based on the target detection step, the target bearing is subjected to bearing status detection according to a preset detection item set to obtain a periodic detection data set, and the periodic detection data set is identified using a bearing detection identifier to obtain a target bearing detection result.

Images