A kind of asynchronous motor bearing fault intelligent detection method and device

Through the multi-parameter comprehensive fault diagnosis method, the sensing monitoring network and auxiliary component data of the asynchronous motor are used to solve the problem of singularity and low accuracy of bearing fault detection of asynchronous motors, improving detection accuracy and reducing false alarm rate.

CN118758607BActive Publication Date: 2024-11-12DANDONG SHANCHUAN ELECTRICAL ENG
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
CN202411248529.5
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-09-06
Publication Date
2024-11-12
Estimated Expiration
2044-09-06

AI Technical Summary

Technical Problem

The existing asynchronous motor bearing fault detection technology has problems such as strong singularity and low accuracy, which cannot fully reflect the health status of the motor, resulting in high false alarm rates and inaccurate fault diagnosis.

Method used

By receiving control instructions of the asynchronous motor, the pre-arranged sensing monitoring network is used to obtain monitoring data flows of multiple bearings, perform health deviation analysis and fault detection, and combine auxiliary component monitoring data to perform fault association compensation, generate fault detection reports, and realize multiple Comprehensive parameter fault diagnosis.

Benefits of technology

It improves the accuracy of bearing fault detection of asynchronous motors, reduces false alarm rates, and achieves more comprehensive fault diagnosis and more accurate health status reflection.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118758607B_ABST
    Figure CN118758607B_ABST
Patent Text Reader

Abstract

The present application provides an intelligent detection method and device for bearing faults of asynchronous motors, which relates to the field of intelligent fault detection technology, including: receiving control instructions of asynchronous motors; controlling asynchronous motors to obtain N bearing monitoring data streams; extracting the nth bearing monitoring data stream corresponding to the nth bearing; performing health deviation analysis on the nth bearing to obtain the nth bearing health deviation matrix; performing fault detection on the nth bearing to obtain the nth bearing fault detection result; obtaining an auxiliary component monitoring data set of the asynchronous motor, performing fault correlation compensation on the nth bearing fault detection result, and generating the nth bearing fault detection report. The present application can solve the technical problems of strong singularity and low accuracy of bearing fault detection of asynchronous motors in the prior art, achieve the technical goal of multi-parameter comprehensive fault diagnosis, and achieve the technical effect of improving the accuracy of bearing fault detection of asynchronous motors and reducing the false alarm rate.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of intelligent fault detection, and in particular to an intelligent detection method and device for asynchronous motor bearing faults. Background Art

[0002] In modern industrial applications, asynchronous motors are widely used in various machinery and production systems as key power equipment. However, with the continuous development and increasing complexity of production technology, higher requirements are placed on the performance and reliability of asynchronous motors. In order to ensure the normal operation of equipment and improve production efficiency, fault detection and status monitoring of motors are particularly important.

[0003] At present, most of the existing asynchronous motor monitoring and fault detection technologies rely on traditional monitoring methods and single fault diagnosis means, which can identify and prevent faults to a certain extent, but there are still many shortcomings and cannot fully reflect the health status of the motor. Usually, the fault diagnosis of the motor relies on the change of a single parameter, such as temperature, vibration or current fluctuation. However, the change of a single parameter is often interfered by multiple factors, resulting in a high false alarm rate. In addition, there may be complex interrelationships between different fault types, and single parameter analysis is difficult to identify and analyze these relationships, thus limiting the accuracy and comprehensiveness of fault diagnosis.

[0004] In summary, the prior art has the technical problems of high singularity and low accuracy in detecting bearing faults of asynchronous motors. Summary of the invention

[0005] The purpose of this application is to provide an intelligent detection method and device for asynchronous motor bearing faults, so as to solve the technical problems of strong singleness and low accuracy of asynchronous motor bearing fault detection in the prior art.

[0006] In view of the above problems, the present application provides an intelligent detection method and device for asynchronous motor bearing faults.

[0007] In a first aspect, the present application provides an intelligent detection method for bearing faults of asynchronous motors, which is implemented by an intelligent detection device for bearing faults of asynchronous motors, and includes: receiving a control instruction of an asynchronous motor, wherein the control instruction includes a control decision plan; controlling the asynchronous motor according to the control decision plan, and obtaining N bearing monitoring data streams corresponding to N bearings of the asynchronous motor according to a pre-deployed asynchronous motor sensor monitoring network, wherein N is a positive integer greater than 1; extracting an nth bearing monitoring data stream corresponding to an nth bearing according to the N bearing monitoring data streams, wherein n is a positive integer, 1≤n≤N; performing health deviation analysis on the nth bearing according to the control decision plan in combination with the nth bearing monitoring data stream to obtain an nth bearing health deviation matrix; performing fault detection on the nth bearing according to a bearing fault detection channel in combination with the nth bearing health deviation matrix to obtain an nth bearing fault detection result; obtaining an auxiliary component monitoring data set of the asynchronous motor according to the asynchronous motor sensor monitoring network, and performing fault correlation compensation on the nth bearing fault detection result according to the auxiliary component monitoring data set to generate an nth bearing fault detection report.

[0008] In the second aspect, the present application also provides an intelligent detection device for asynchronous motor bearing faults, which is used to execute an intelligent detection method for asynchronous motor bearing faults as described in the first aspect, including: a control instruction receiving module, which is used to receive control instructions of the asynchronous motor, wherein the control instructions include a control decision plan; a bearing monitoring data stream acquisition module, which is used to control the asynchronous motor according to the control decision plan, and obtain N bearing monitoring data streams corresponding to N bearings of the asynchronous motor according to a pre-deployed asynchronous motor sensor monitoring network, wherein N is a positive integer greater than 1; an nth bearing monitoring data stream extraction module, which is used to extract the nth bearing monitoring data stream corresponding to the nth bearing based on the N bearing monitoring data streams, wherein n is a positive integer number, 1≤n≤N; an nth bearing health deviation matrix acquisition module, the nth bearing health deviation matrix acquisition module is used to perform health deviation analysis on the nth bearing according to the control decision scheme in combination with the nth bearing monitoring data stream, and obtain the nth bearing health deviation matrix; an nth bearing fault detection result acquisition module, the nth bearing fault detection result acquisition module is used to perform fault detection on the nth bearing according to the bearing fault detection channel in combination with the nth bearing health deviation matrix, and obtain the nth bearing fault detection result; an nth bearing fault detection report generation module, the nth bearing fault detection report generation module is used to obtain the auxiliary component monitoring data set of the asynchronous motor according to the asynchronous motor sensor monitoring network, and perform fault correlation compensation on the nth bearing fault detection result according to the auxiliary component monitoring data set to generate an nth bearing fault detection report.

[0009] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0010] By receiving a control instruction of an asynchronous motor, wherein the control instruction includes a control decision scheme; controlling the asynchronous motor according to the control decision scheme, and obtaining N bearing monitoring data streams corresponding to N bearings of the asynchronous motor according to a pre-deployed asynchronous motor sensor monitoring network, wherein N is a positive integer greater than 1; extracting an nth bearing monitoring data stream corresponding to an nth bearing according to the N bearing monitoring data streams, wherein n is a positive integer, 1≤n≤N; performing health deviation analysis on the nth bearing according to the control decision scheme in combination with the nth bearing monitoring data stream to obtain an nth bearing health deviation matrix; performing fault detection on the nth bearing according to a bearing fault detection channel in combination with the nth bearing health deviation matrix to obtain an nth bearing fault detection result; obtaining an auxiliary component monitoring data set of the asynchronous motor according to the asynchronous motor sensor monitoring network, performing fault correlation compensation on the nth bearing fault detection result according to the auxiliary component monitoring data set, generating an nth bearing fault detection report, achieving the technical goal of multi-parameter comprehensive fault diagnosis, and achieving the technical effect of improving the bearing fault detection accuracy of the asynchronous motor and reducing the false alarm rate.

[0011] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented according to the contents of the specification, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are specifically cited below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the technical solutions in the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0013] Figure 1 A schematic diagram of a flow chart of an intelligent detection method for bearing fault of an asynchronous motor according to the present application;

[0014] Figure 2 This is a structural schematic diagram of an intelligent detection device for asynchronous motor bearing faults according to the present application.

[0015] Description of reference numerals:

[0016] 11 control instruction receiving module, 12 bearing monitoring data stream acquisition module, 13 nth bearing monitoring data stream extraction module, 14 nth bearing health deviation matrix acquisition module, 15 nth bearing fault detection result acquisition module, 16 nth bearing fault detection report generation module. DETAILED DESCRIPTION

[0017] This application provides an intelligent detection method and device for asynchronous motor bearing faults, which solves the technical problem of strong singularity and low accuracy of asynchronous motor bearing fault detection in the prior art, realizes the technical goal of multi-parameter comprehensive fault diagnosis, and achieves the technical effect of improving the accuracy of asynchronous motor bearing fault detection and reducing the false alarm rate.

[0018] Below, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments of the present application. It should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application. It should also be noted that, for the convenience of description, only the parts related to the present application are shown in the accompanying drawings, rather than all of them.

[0019] For example, please refer to the attached Figure 1 The present application provides an asynchronous motor bearing fault intelligent detection method, which is applied to an asynchronous motor bearing fault intelligent detection device, and specifically includes:

[0020] Step 1: Receive a control instruction of the asynchronous motor, wherein the control instruction includes a control decision plan.

[0021] Specifically, an asynchronous motor is an electric motor used in industry and manufacturing, and different operating tasks such as starting, stopping, and speed regulation are achieved through specific control instructions. A control instruction for the asynchronous motor is received, wherein the control instruction includes a control decision plan. The control decision plan is formulated based on a comprehensive analysis of the current state of the asynchronous motor, the tasks to be performed, and the external environment, and aims to optimize the operating efficiency and stability of the motor through a reasonable control strategy. The control decision plan may include optimized working mode selection, load adjustment strategy, and energy-saving measures to ensure that the motor operates in the optimal state.

[0022] Step 2: Control the asynchronous motor according to the control decision scheme, and obtain N bearing monitoring data streams corresponding to the N bearings of the asynchronous motor according to the pre-deployed asynchronous motor sensor monitoring network, wherein N is a positive integer greater than 1.

[0023] Specifically, after executing the control instruction, the operating state of the asynchronous motor is adjusted according to the control decision scheme, and the pre-arranged sensor monitoring network is used for real-time monitoring. The sensor monitoring network can obtain the status data of each bearing in real time by installing sensors at the N bearing positions of the asynchronous motor. The status data of each bearing forms a monitoring data stream, which provides detailed feedback information for the health status of the motor. Since the bearing of the motor is a key component in its operation process, the monitoring data stream can promptly reflect problems such as bearing wear, abnormal temperature or abnormal vibration. By monitoring the data stream, potential faults can be discovered at an early stage, and necessary preventive or repair measures can be taken to avoid possible serious damage. Since at least two bearings are monitored, N is a positive integer greater than 1.

[0024] Step three: extract the nth bearing monitoring data stream corresponding to the nth bearing based on the N bearing monitoring data streams, where n is a positive integer, 1≤n≤N.

[0025] Specifically, in order to more accurately analyze and process the operating conditions of the asynchronous motor, a bearing monitoring data stream corresponding to a bearing is randomly extracted from the N bearing monitoring data streams as the nth bearing monitoring data stream corresponding to the nth bearing. n represents a random number among the N bearings, ranging from 1 to N. By extracting the nth bearing monitoring data stream of the nth bearing, an in-depth analysis of the nth bearing can be performed, such as evaluating its degree of wear, temperature change trend, and vibration status, which helps to identify the specific problems of a single bearing and provide a basis for formulating a repair plan, which not only improves maintenance efficiency, but also extends the service life of the motor and avoids downtime or larger equipment damage caused by a single bearing failure.

[0026] Step 4: According to the control decision scheme, the health deviation of the nth bearing is analyzed in combination with the nth bearing monitoring data stream to obtain the nth bearing health deviation matrix.

[0027] Specifically, health deviation analysis is to evaluate the difference between the current operating state of the bearing and the ideal health state by analyzing the real-time monitoring data of the nth bearing and combining it with the pre-set control decision plan. It can identify potential abnormal patterns and health deviations through in-depth analysis of the monitoring data stream. The generated health deviation matrix is ​​a multidimensional data structure that quantifies the degree of health deviation of the bearing in different parameter dimensions. This matrix provides important basic data for subsequent fault detection and helps to identify specific abnormal trends and potential problems.

[0028] Step 5: Perform fault detection on the nth bearing according to the bearing fault detection channel and in combination with the nth bearing health deviation matrix to obtain the nth bearing fault detection result.

[0029] Specifically, the fault detection channel is a comprehensive analysis platform that combines the data of the nth bearing health deviation matrix to conduct in-depth fault detection on the nth bearing, and uses multiple analysis models and algorithms to identify the possible fault type and severity of the bearing by comparing the health deviation with the normal operating standard. The test results provide detailed diagnostic information on the health status of the bearing, point out potential fault sources and their impact on the overall performance of the motor, and provide clear directions for maintenance and repair, ensuring that necessary measures are taken in a timely manner.

[0030] Step six: According to the asynchronous motor sensor monitoring network, obtain the auxiliary component monitoring data set of the asynchronous motor, and perform fault correlation compensation on the nth bearing fault detection result according to the auxiliary component monitoring data set to generate an nth bearing fault detection report.

[0031] Specifically, the sensor monitoring network of the asynchronous motor provides real-time data about all auxiliary components, and the data set of the auxiliary components is used to supplement and improve the fault detection analysis of the nth bearing. By analyzing the auxiliary component monitoring data set, auxiliary factors that have a potential impact on the bearing fault detection results can be identified, and fault correlation compensation can be performed to ensure the accuracy and comprehensiveness of the detection results. The final fault detection report is a comprehensive result after multi-level analysis and compensation, which records in detail the health status of the bearing, fault type, influencing factors and recommended treatment measures. The report provides important decision-making basis for the engineering team and helps to formulate and implement effective maintenance strategies.

[0032] The method for intelligently detecting bearing faults of asynchronous motors is applied to an intelligent detection device for bearing faults of asynchronous motors, which can achieve the technical goal of multi-parameter comprehensive fault diagnosis and achieve the technical effect of improving the accuracy of bearing fault detection of asynchronous motors and reducing the false alarm rate.

[0033] Furthermore, the present application also includes:

[0034] Monitoring elements are identified based on the nth bearing monitoring data stream to generate an nth bearing monitoring element set; based on the nth bearing monitoring element set, an nth bearing monitoring element matrix is ​​established; data integration is performed on the nth bearing monitoring data stream based on the nth bearing monitoring element matrix to generate an nth bearing monitoring matrix; health prediction is performed on the nth bearing based on the control decision scheme and the nth bearing monitoring element matrix to obtain an nth bearing health prediction matrix; deviation analysis is performed based on the nth bearing health prediction matrix and the nth bearing monitoring matrix to generate the nth bearing health deviation matrix.

[0035] Specifically, monitoring element identification is an indicator for monitoring the nth bearing monitoring data stream. By identifying the monitoring elements of the nth bearing monitoring data stream, a series of key monitoring elements are identified, including temperature, vibration frequency, lubrication status and rotation speed. The monitoring elements reflect the health status and performance characteristics of the bearing during operation. By identifying the monitoring elements, a monitoring element set can be generated to provide the necessary information basis for subsequent data analysis and status evaluation.

[0036] Then, the monitoring elements in the monitoring element set can be further structured into a monitoring element matrix by mathematical methods. For example, the matrix behavior of the monitoring element matrix is ​​the monitoring element, and the matrix columns are the specific parameters of the monitoring element.

[0037] Then, based on the monitoring element matrix, all relevant data are further integrated to form a more detailed monitoring matrix. The monitoring element matrix combines the data of each monitoring element to form a multidimensional data set that fully reflects the current status of the nth bearing. By integrating the monitoring element set, the operating status of the bearing can be tracked more accurately, and potential anomalies and changing trends can be identified, which not only makes data management more efficient, but also provides a solid foundation for subsequent prediction and analysis.

[0038] Next, health prediction is the process of predictive analysis using historical data and the current monitoring element matrix. Combined with the parameters and methods in the control decision plan, the future state of the nth bearing can be predicted. Through health prediction, the nth bearing health prediction matrix is ​​generated. The health prediction matrix predicts the possible operating state of the bearing in the future, which not only helps to identify possible faults in a timely manner, but also provides forward-looking guidance for maintenance planning and optimization decisions.

[0039] Next, by comparing the nth bearing health prediction matrix with the actual nth bearing monitoring matrix, deviation analysis can be performed to reveal the difference between the prediction and actual data and quantify the difference. The deviation matrix shows the degree of deviation between the actual operating state of the bearing and the expected state, identifying anomalies and taking appropriate corrective measures, so that the control strategy can be adjusted more accurately to ensure the stable operation of the motor.

[0040] By establishing a monitoring element matrix and integrating data, the health status of the bearing can be comprehensively predicted and analyzed. The combination of health prediction and deviation analysis provides data support and decision-making basis for maintenance and optimization, ensuring efficient operation and reliable maintenance of asynchronous motors. Through the monitoring and prediction mechanism, the operating efficiency and reliability of the equipment can be effectively improved, and the risk of failure and maintenance costs can be reduced.

[0041] Furthermore, the present application also includes:

[0042] Obtain characteristic attribute information of the nth bearing, wherein the characteristic attribute information of the nth bearing includes model and specification information of the asynchronous motor, and model and specification parameters and installation position parameters of the nth bearing; associate bearings with the same characteristic attributes according to the characteristic attribute information of the nth bearing, and determine a bearing source with the same characteristic, wherein the bearing source with the same characteristic includes the nth bearing, and multiple bearings with the same characteristic attributes corresponding to the nth bearing; retrieve normal monitoring records according to the bearing source with the same characteristic, and obtain multiple bearing monitoring normal record groups; associate and align the multiple bearing monitoring normal record groups based on the control decision scheme, and obtain a bearing monitoring associated healthy sample set; perform concentrated interval analysis according to the bearing monitoring associated healthy sample set, and obtain multiple bearing monitoring associated healthy intervals; organize the multiple bearing monitoring associated healthy intervals according to the nth bearing monitoring element matrix, and generate the nth bearing health prediction matrix.

[0043] Specifically, in order to accurately analyze and predict the nth bearing, obtain the characteristic attribute information of the nth bearing, including the model and specification parameters of the asynchronous motor, to ensure a comprehensive understanding of the asynchronous motor. For the nth bearing, it is also necessary to clarify its own model, specification parameters, and installation position in the asynchronous motor, which helps to identify the specific function and role of the bearing in the device, thereby providing the necessary background information for subsequent data analysis and health assessment, which not only provides a reference for diagnosis and prediction, but also helps to formulate appropriate control strategies.

[0044] Then, by analyzing the characteristic attribute information of the nth bearing, other bearings with the same or similar characteristics can be found and identified in the database, which may be running in similar devices or have the same specifications and functions. Through association, multiple sources of bearings with the same characteristics can be determined, which include not only the nth bearing, but also other bearings similar to it in parameters and usage environments, which helps to expand the data sample size and provide richer reference data for subsequent analysis and prediction.

[0045] Next, the normal monitoring records of the bearings corresponding to the bearing sources with the same characteristics are retrieved from the historical database. Multiple groups of normal bearing monitoring records refer to the monitoring data without abnormalities or faults, which represent the performance and behavior of the bearings under normal working conditions. By collecting multiple groups of normal bearing monitoring records, the health status of the bearings can be evaluated.

[0046] Then, the control decision-making scheme is used to further analyze and align the multiple normal record groups of bearing monitoring. By combining the monitoring data of different bearings, a bearing monitoring associated health sample set is formed to reflect the standard health status under each monitoring indicator. Through the correlation analysis of the samples, the device can identify the typical behavior patterns of healthy bearings under specific conditions, which not only improves the accuracy of the prediction, but also provides a more reliable basis for anomaly detection.

[0047] Then, by analyzing the data in the healthy sample set, the concentrated intervals of the bearing monitoring parameters can be identified, and multiple bearing monitoring associated health intervals can be obtained. Multiple bearing monitoring associated health intervals reflect the typical range of key parameters of the bearing under normal working conditions, which helps to identify the performance fluctuation range of different bearings under standard conditions, thereby providing clear standards for subsequent abnormality detection. When the actual monitoring data exceeds the bearing monitoring associated health interval, an early warning can be issued in time to indicate possible abnormalities.

[0048] Next, the monitoring element matrix of the nth bearing is combined with the information of the health interval to generate the health prediction matrix of the nth bearing. The health prediction matrix of the nth bearing not only integrates the current monitoring data and historical health standards, but also combines the guidance of the control decision-making plan to provide an accurate prediction of the future state of the bearing. The health prediction matrix helps maintenance personnel identify potential problems in a timely manner and formulate corresponding prevention and maintenance measures to ensure the continued stable operation of the bearing and motor.

[0049] By associating the same characteristic bearings and establishing a healthy sample set, a reliable health standard and prediction basis is formed. Combining the monitoring data with the health interval, a health prediction matrix is ​​generated, which provides important support for the real-time evaluation and decision-making of the bearing status, not only improving the operating efficiency of the motor, but also reducing the risk of failure, ensuring the long-term stability and reliability of the equipment.

[0050] Furthermore, the present application also includes:

[0051] Traverse the multiple bearing monitoring normal record groups, extract the first bearing monitoring normal record group, wherein the first bearing monitoring normal record group includes the first historical asynchronous motor control decision scheme and the first historical bearing monitoring normal data stream; based on the twin neural network, align and identify the control decision scheme and the first historical asynchronous motor control decision scheme to obtain the first asynchronous motor control alignment coefficient; determine whether the first asynchronous motor control alignment coefficient is greater than / equal to the asynchronous motor control alignment threshold; if the first asynchronous motor control alignment coefficient is greater than / equal to the asynchronous motor control alignment threshold, add the first historical bearing monitoring normal data stream to the bearing monitoring associated health sample set; if the first asynchronous motor control alignment coefficient is less than the asynchronous motor control alignment threshold, eliminate the first historical bearing monitoring normal data stream.

[0052] Specifically, multiple normal bearing monitoring record groups are accessed in sequence in order to extract a representative normal record group, namely the first normal bearing monitoring record group. The first normal bearing monitoring record group includes the control decision plan of the asynchronous motor and the corresponding bearing monitoring data stream in a specific historical period, reflecting the operating status and control strategy of the motor and bearing under normal working conditions, and is an important reference basis for comparing and analyzing current monitoring data. By extracting the first normal bearing monitoring record group, a detailed historical background can be provided for subsequent analysis, helping to identify potential deviations in the current device operation.

[0053] Next, the twin neural network is a machine learning model suitable for registration and similarity comparison. The twin neural network model is used to register the current control decision scheme and the first historical asynchronous motor control decision scheme. The purpose of registration and identification is to determine the degree of similarity between the two control schemes under specific conditions. The twin neural network calculates a registration coefficient by comparing the characteristics of the input data, which reflects the similarity between the two schemes in operation strategy and parameter settings, and is used to subsequently determine whether the record group is suitable for inclusion in the healthy sample set.

[0054] Next, the asynchronous motor control registration threshold is a pre-set standard used to determine whether the historical record group has sufficient reference value. Comparing the motor control registration coefficient with the preset asynchronous motor control registration threshold can quickly determine whether the similarity between the current control decision plan and the historical plan meets the standard, ensuring that only highly relevant historical data is included to avoid the impact of irrelevant or misleading data on the healthy sample set.

[0055] Next, when the first asynchronous motor control registration coefficient is greater than or equal to the asynchronous motor control registration threshold, it indicates that the current control decision scheme and the historical scheme have a high degree of similarity in operation strategy. Therefore, the first historical bearing monitoring normal data stream is considered to be representative health data and can be used as a reference standard for the current device operation. Adding the first historical bearing monitoring normal data stream to the bearing monitoring associated health sample set helps to improve the health standard and provide an accurate comparison basis for subsequent monitoring and prediction.

[0056] Next, if the first asynchronous motor control registration coefficient is less than the asynchronous motor control registration threshold, it means that the similarity between the current control decision scheme and the historical scheme is insufficient, and the first historical bearing monitoring normal data stream may not be suitable as a reference for the current analysis. Therefore, the first historical bearing monitoring normal data stream will be eliminated to avoid the interference of irrelevant data on the healthy sample set. The data screening mechanism ensures the high quality and accuracy of the sample set, thereby improving the reliability of the overall device health assessment and prediction.

[0057] By comparing the registration coefficient with the threshold, only valuable data streams are retained and the accuracy of the healthy sample set is ensured, which provides a reliable basis for the health monitoring and prediction of asynchronous motors and bearings, and helps to improve the stability and maintenance efficiency of the device.

[0058] Furthermore, the present application also includes:

[0059] Perform deviation depth evaluation according to the nth bearing health deviation matrix to obtain the nth bearing health deviation depth coefficient; determine whether the nth bearing health deviation depth coefficient is greater than / equal to the bearing health deviation depth threshold; if the nth bearing health deviation depth coefficient is greater than / equal to the bearing health deviation depth threshold, activate the bearing fault detection channel, wherein the bearing fault detection channel includes S bearing fault detection models, wherein S is a positive integer greater than 1; input the nth bearing health deviation matrix into the S bearing fault detection models to obtain S bearing fault detection data; and fuse the S bearing fault detection data to generate the nth bearing fault detection result.

[0060] Specifically, by analyzing the nth bearing health deviation matrix, the degree of difference between the health status of the nth bearing and the normal standard can be identified. Deviation depth evaluation is an accurate method to evaluate the health of the bearing by quantifying the degree of difference. The calculated health deviation depth coefficient reflects the deviation between the nth bearing and the healthy state. The data in the nth health deviation matrix combines multiple parameters monitored by the nth bearing and compares them with the standard health state. The obtained nth bearing health deviation depth coefficient is an indicator that can quantify the health status of the bearing, which not only provides a reliable reference for real-time monitoring, but also can serve as an important basis for predicting potential failures.

[0061] Next, the bearing health deviation depth threshold is a critical point defined during design to determine whether the bearing has deviated from normal operating conditions. The nth bearing health deviation depth coefficient is compared with the preset bearing health deviation depth threshold. When the nth bearing health deviation depth coefficient is greater than or equal to the bearing health deviation depth threshold, it indicates that the health of the nth bearing has significantly deviated from the normal state and further inspection and evaluation are required, which can help identify potential problems and risks in a timely manner so that preventive measures can be taken to reduce the possibility of failures.

[0062] Then, when the nth bearing health deviation depth coefficient is greater than or equal to the bearing health deviation depth threshold, the bearing fault detection channel will be automatically activated. The bearing fault detection channel consists of multiple fault detection models, aiming to perform comprehensive fault analysis on the bearing through multiple detection methods. The bearing fault detection channel includes S bearing fault detection models, each of which may provide multi-level analysis perspectives for different fault types and operating conditions. Since at least two different detection models are included, S is a positive integer greater than 1. The multi-model detection mechanism can improve the accuracy and comprehensiveness of fault detection, thereby providing more reliable fault diagnosis.

[0063] Next, the nth bearing health deviation matrix will be input into each bearing fault detection model. Each bearing fault detection model will process and analyze the input nth bearing health deviation matrix according to its specific algorithm and analysis method, thereby generating corresponding fault detection data as the corresponding fault detection data for each bearing. The bearing fault detection data may include the identification results of different fault modes, the estimation of fault severity, and the analysis of potential fault causes, which can not only help identify the current fault condition, but also provide detailed reference information for formulating repair plans.

[0064] Then, by integrating the analysis results of S models, the bearing fault detection data from different detection models are fused to form a comprehensive n-th bearing fault detection result. The n-th bearing fault detection result not only summarizes the analysis of all models on the fault, but also considers the mutual verification and complementation between the results of different models. Through fusion, the accuracy of fault diagnosis can be improved, the misjudgment that may be caused by a single model can be avoided, and clear guidance can be provided for maintenance personnel to help take effective measures for repair and prevention in a timely manner to ensure the safe and stable operation of the device.

[0065] By deeply evaluating the health deviation matrix and analyzing the deviation depth coefficient, possible fault risks can be identified in a timely manner. When the risk reaches a certain level, the activation of the fault detection channel and multi-model analysis provide comprehensive support for fault diagnosis. The fault detection results obtained through data fusion provide a reliable basis for formulating maintenance and repair measures, effectively improving the operating safety and stability of the device.

[0066] Furthermore, the present application also includes:

[0067] According to the auxiliary component monitoring data set, fault detection is performed on each auxiliary component of the asynchronous motor to obtain multiple auxiliary fault detection results; according to the multiple auxiliary fault detection results, fault correlation compensation is performed on the nth bearing fault detection result to obtain the nth bearing optimized fault detection result; according to a predetermined bearing fault report template, the nth bearing optimized fault detection result is sorted to obtain the nth bearing fault detection report.

[0068] Specifically, the normal operation of asynchronous motors depends not only on the healthy state of the main bearing, but also on the good operation of other auxiliary components. Auxiliary components include cooling devices, lubrication devices, connecting cables, sensors, etc. During the fault detection process, the monitoring data set of the auxiliary components provides information on the operating status of the auxiliary components, and multiple auxiliary fault detection results are obtained. By analyzing the auxiliary components, possible faults or anomalies of each component can be identified. Each auxiliary fault detection result is a detailed diagnosis of a specific component, indicating potential problems and their severity, which helps to ensure the efficient operation of the entire motor device and avoid chain reactions caused by auxiliary component failures.

[0069] Then, the failure of auxiliary components may affect the health status of the bearing. Therefore, when analyzing the bearing fault detection results, the influencing factors of the auxiliary components need to be considered. The fault correlation compensation of the nth bearing fault detection result is performed based on multiple auxiliary fault detection results to obtain the optimized fault detection result of the nth bearing. Fault correlation compensation is to combine multiple auxiliary fault detection results with the nth bearing fault detection result for comprehensive analysis and compensation adjustment. By identifying and correcting possible misjudgments or omissions, the optimized fault detection results can more accurately reflect the true health status of the nth bearing, which not only improves the accuracy of fault detection, but also helps engineers better understand and solve potential problems.

[0070] Then, the optimized fault detection results need to be organized in a standardized way for easy communication and analysis. The bearing fault report template is a pre-designed document format that contains key information for fault detection, such as fault type, severity, possible causes, and recommended repair measures. Organizing and optimizing the detection results according to the template not only makes the information expression clearer and more structured, but also provides clear guidance for subsequent fault handling and maintenance work. The resulting fault detection report can be used as a communication tool to convey information between engineering teams and provide strong support for decision making.

[0071] By detecting the faults of the auxiliary components of the asynchronous motor, multiple auxiliary fault detection results were obtained, which provided background and compensation support for the analysis of bearing faults. Through fault correlation compensation, the fault detection results of the nth bearing were optimized to ensure the accuracy and reliability of the detection. Finally, using a standardized report template, the optimized results were organized into a structured fault detection report, which provided an important reference for maintenance and repair work and improved the fault detection capability and operation and maintenance efficiency of the device.

[0072] Furthermore, the present application also includes:

[0073] Traverse the multiple auxiliary fault detection results and extract the first auxiliary fault detection result; perform fault impact evaluation on the nth bearing according to the first auxiliary fault detection result to obtain a first auxiliary fault impact coefficient; determine whether the first auxiliary fault impact coefficient is greater than / equal to an auxiliary fault impact threshold; if the first auxiliary fault impact coefficient is greater than / equal to the auxiliary fault impact threshold, perform fault interference identification on the nth bearing according to the first auxiliary fault detection result to obtain a bearing fault interference identification result; perform correlation compensation on the nth bearing fault detection result according to the bearing fault interference identification result to generate an optimized fault detection result for the nth bearing.

[0074] Specifically, multiple auxiliary fault detection results are accessed in sequence, and the first auxiliary fault detection result is randomly extracted from them, including the problem of the first auxiliary component at a certain time point or operating condition. Extracting the first auxiliary fault detection result helps to identify which auxiliary components may have an impact on the operation of the bearing and in what aspects the impact may be manifested, providing the necessary basic data for subsequent fault impact analysis.

[0075] Then, by analyzing the first auxiliary fault detection results, the specific impact of the first auxiliary fault detection results on the nth bearing can be evaluated. Impact evaluation usually involves calculating an impact coefficient, which quantifies the degree of interference of the auxiliary fault on the bearing. The calculation of the impact coefficient takes into account multiple factors, such as the severity of the fault, its duration, and the change to the bearing operating environment. The obtained first auxiliary fault impact coefficient provides a quantitative basis for further fault analysis and can help determine whether additional measures are needed for fault intervention or correction.

[0076] Next, the first auxiliary fault impact coefficient is compared with a predetermined auxiliary fault impact threshold. The auxiliary fault impact threshold is a pre-set standard that represents the critical point at which an auxiliary fault has a significant impact on the health of the bearing. If the first auxiliary fault impact coefficient is greater than or equal to the auxiliary fault impact threshold, it means that the auxiliary fault has a significant negative impact on the operation of the bearing, which may lead to a significant decrease in bearing performance or an increase in the risk of failure.

[0077] Then, for the case where the first auxiliary fault influence coefficient is greater than or equal to the auxiliary fault influence threshold, in-depth fault interference identification is performed. By analyzing the first auxiliary fault detection results, the specific fault interference mode and influence mechanism are identified. The identification results may include a detailed analysis of the fault cause, propagation path, and impact on specific bearing functions, which helps to formulate targeted compensation strategies to reduce or eliminate the negative impact of the fault on the bearing.

[0078] Finally, the fault interference identification results are used to perform correlation compensation on the fault detection results of the nth bearing. By taking into account the influence of interference factors, the original fault detection results can be corrected to generate more accurate and reliable optimized fault detection results. The correlation compensation process adjusts the detection data to remove noise and misjudgment introduced by auxiliary faults, ensuring that the fault detection results reflect the true state of the bearing. The optimized detection results not only provide an important basis for maintenance decisions, but also provide detailed guidance for fault prevention and repair.

[0079] By traversing and analyzing the auxiliary fault detection results, the fault factors that have a significant impact on the bearing can be identified. By calculating the influence coefficient and identifying the fault interference, effective fault correlation compensation can be performed, generating more accurate and optimized fault detection results, improving the accuracy and reliability of fault detection, and helping to ensure the stable operation of the asynchronous motor and extend its service life.

[0080] In summary, the intelligent detection method for asynchronous motor bearing fault provided by the present application has the following technical effects:

[0081] By receiving a control instruction of an asynchronous motor, wherein the control instruction includes a control decision scheme; controlling the asynchronous motor according to the control decision scheme, and obtaining N bearing monitoring data streams corresponding to N bearings of the asynchronous motor according to a pre-deployed asynchronous motor sensor monitoring network, wherein N is a positive integer greater than 1; extracting an nth bearing monitoring data stream corresponding to an nth bearing according to the N bearing monitoring data streams, wherein n is a positive integer, 1≤n≤N; performing health deviation analysis on the nth bearing according to the control decision scheme in combination with the nth bearing monitoring data stream to obtain an nth bearing health deviation matrix; performing fault detection on the nth bearing according to a bearing fault detection channel in combination with the nth bearing health deviation matrix to obtain an nth bearing fault detection result; obtaining an auxiliary component monitoring data set of the asynchronous motor according to the asynchronous motor sensor monitoring network, performing fault correlation compensation on the nth bearing fault detection result according to the auxiliary component monitoring data set, generating an nth bearing fault detection report, achieving the technical goal of multi-parameter comprehensive fault diagnosis, and achieving the technical effect of improving the bearing fault detection accuracy of the asynchronous motor and reducing the false alarm rate.

[0082] Embodiment 2: Based on the same invention concept as the method for intelligent detection of bearing faults of asynchronous motors in the above embodiment, the present application also provides an intelligent detection device for bearing faults of asynchronous motors. Figure 2 ,include:

[0083] A control instruction receiving module 11, the control instruction receiving module 11 is used to receive the control instruction of the asynchronous motor, wherein the control instruction includes a control decision scheme; a bearing monitoring data stream obtaining module 12, the bearing monitoring data stream obtaining module 12 is used to control the asynchronous motor according to the control decision scheme, and obtain N bearing monitoring data streams corresponding to N bearings of the asynchronous motor according to a pre-deployed asynchronous motor sensor monitoring network, wherein N is a positive integer greater than 1; an nth bearing monitoring data stream extraction module 13, the nth bearing monitoring data stream extraction module 13 is used to extract the nth bearing monitoring data stream corresponding to the nth bearing according to the N bearing monitoring data streams, wherein n is a positive integer, 1≤n≤N; an nth bearing health deviation matrix obtaining module 14, the nth bearing health deviation matrix obtaining module 15 The healthy deviation matrix acquisition module 14 is used to perform health deviation analysis on the nth bearing according to the control decision scheme in combination with the nth bearing monitoring data stream to obtain the nth bearing health deviation matrix; the nth bearing fault detection result acquisition module 15, the nth bearing fault detection result acquisition module 15 is used to perform fault detection on the nth bearing according to the bearing fault detection channel in combination with the nth bearing health deviation matrix to obtain the nth bearing fault detection result; the nth bearing fault detection report generation module 16, the nth bearing fault detection report generation module 16 is used to obtain the auxiliary component monitoring data set of the asynchronous motor according to the asynchronous motor sensor monitoring network, and perform fault correlation compensation on the nth bearing fault detection result according to the auxiliary component monitoring data set to generate the nth bearing fault detection report.

[0084] Furthermore, the nth bearing health deviation matrix obtaining module 14 in the asynchronous motor bearing fault intelligent detection device is also used for:

[0085] Monitoring elements are identified based on the nth bearing monitoring data stream to generate an nth bearing monitoring element set; based on the nth bearing monitoring element set, an nth bearing monitoring element matrix is ​​established; data integration is performed on the nth bearing monitoring data stream based on the nth bearing monitoring element matrix to generate an nth bearing monitoring matrix; health prediction is performed on the nth bearing based on the control decision scheme and the nth bearing monitoring element matrix to obtain an nth bearing health prediction matrix; deviation analysis is performed based on the nth bearing health prediction matrix and the nth bearing monitoring matrix to generate the nth bearing health deviation matrix.

[0086] Furthermore, the nth bearing health deviation matrix obtaining module 14 in the asynchronous motor bearing fault intelligent detection device is also used for:

[0087] Obtain characteristic attribute information of the nth bearing, wherein the characteristic attribute information of the nth bearing includes model and specification information of the asynchronous motor, and model and specification parameters and installation position parameters of the nth bearing; associate bearings with the same characteristic attributes according to the characteristic attribute information of the nth bearing, and determine a bearing source with the same characteristic, wherein the bearing source with the same characteristic includes the nth bearing, and multiple bearings with the same characteristic attributes corresponding to the nth bearing; retrieve normal monitoring records according to the bearing source with the same characteristic, and obtain multiple bearing monitoring normal record groups; associate and align the multiple bearing monitoring normal record groups based on the control decision scheme, and obtain a bearing monitoring associated healthy sample set; perform concentrated interval analysis according to the bearing monitoring associated healthy sample set, and obtain multiple bearing monitoring associated healthy intervals; organize the multiple bearing monitoring associated healthy intervals according to the nth bearing monitoring element matrix, and generate the nth bearing health prediction matrix.

[0088] Furthermore, the nth bearing health deviation matrix obtaining module 14 in the asynchronous motor bearing fault intelligent detection device is also used for:

[0089] Traverse the multiple bearing monitoring normal record groups, extract the first bearing monitoring normal record group, wherein the first bearing monitoring normal record group includes the first historical asynchronous motor control decision scheme and the first historical bearing monitoring normal data stream; based on the twin neural network, align and identify the control decision scheme and the first historical asynchronous motor control decision scheme to obtain the first asynchronous motor control alignment coefficient; determine whether the first asynchronous motor control alignment coefficient is greater than / equal to the asynchronous motor control alignment threshold; if the first asynchronous motor control alignment coefficient is greater than / equal to the asynchronous motor control alignment threshold, add the first historical bearing monitoring normal data stream to the bearing monitoring associated health sample set; if the first asynchronous motor control alignment coefficient is less than the asynchronous motor control alignment threshold, eliminate the first historical bearing monitoring normal data stream.

[0090] Furthermore, the nth bearing fault detection result obtaining module 15 in the asynchronous motor bearing fault intelligent detection device is also used for:

[0091] Perform deviation depth evaluation according to the nth bearing health deviation matrix to obtain the nth bearing health deviation depth coefficient; determine whether the nth bearing health deviation depth coefficient is greater than / equal to the bearing health deviation depth threshold; if the nth bearing health deviation depth coefficient is greater than / equal to the bearing health deviation depth threshold, activate the bearing fault detection channel, wherein the bearing fault detection channel includes S bearing fault detection models, wherein S is a positive integer greater than 1; input the nth bearing health deviation matrix into the S bearing fault detection models to obtain S bearing fault detection data; and fuse the S bearing fault detection data to generate the nth bearing fault detection result.

[0092] Furthermore, the nth bearing fault detection report generating module 16 in the asynchronous motor bearing fault intelligent detection device is further used for:

[0093] According to the auxiliary component monitoring data set, fault detection is performed on each auxiliary component of the asynchronous motor to obtain multiple auxiliary fault detection results; according to the multiple auxiliary fault detection results, fault correlation compensation is performed on the nth bearing fault detection result to obtain the nth bearing optimized fault detection result; according to a predetermined bearing fault report template, the nth bearing optimized fault detection result is sorted to obtain the nth bearing fault detection report.

[0094] Furthermore, the nth bearing fault detection report generating module 16 in the asynchronous motor bearing fault intelligent detection device is further used for:

[0095] Traverse the multiple auxiliary fault detection results and extract the first auxiliary fault detection result; perform fault impact evaluation on the nth bearing according to the first auxiliary fault detection result to obtain a first auxiliary fault impact coefficient; determine whether the first auxiliary fault impact coefficient is greater than / equal to an auxiliary fault impact threshold; if the first auxiliary fault impact coefficient is greater than / equal to the auxiliary fault impact threshold, perform fault interference identification on the nth bearing according to the first auxiliary fault detection result to obtain a bearing fault interference identification result; perform correlation compensation on the nth bearing fault detection result according to the bearing fault interference identification result to generate an optimized fault detection result for the nth bearing.

[0096] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The intelligent detection method for bearing faults of asynchronous motors and the specific examples in the aforementioned embodiment 1 are also applicable to an intelligent detection device for bearing faults of asynchronous motors in this embodiment. Through the aforementioned detailed description of an intelligent detection method for bearing faults of asynchronous motors, those skilled in the art can clearly understand an intelligent detection device for bearing faults of asynchronous motors in this embodiment, so for the sake of brevity of the specification, it will not be described in detail here. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the description of the method part.

[0097] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

[0098] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application belong to the scope of the present application and its equivalent technology, the present application is also intended to include these modifications and variations.

Claims

1. An intelligent detection method for asynchronous motor bearing fault, characterized in that: The method comprises: Receiving a control instruction of an asynchronous motor, wherein the control instruction includes a control decision scheme, and the control decision scheme includes an optimized working mode selection, a load adjustment strategy, and energy-saving measures to ensure that the motor operates in an optimal state; The asynchronous motor is controlled according to the control decision scheme, and N bearing monitoring data streams corresponding to N bearings of the asynchronous motor are obtained according to a pre-deployed asynchronous motor sensor monitoring network, wherein N is a positive integer greater than 1; Extracting the nth bearing monitoring data stream corresponding to the nth bearing according to the N bearing monitoring data streams, wherein n is a positive integer, 1≤n≤N; According to the control decision scheme, in combination with the monitoring data stream of the nth bearing, health deviation analysis is performed on the nth bearing to obtain a health deviation matrix of the nth bearing, wherein the health deviation analysis refers to evaluating the difference between the current operating state of the bearing and the ideal health state by analyzing the real-time monitoring data of the nth bearing in combination with a pre-set control decision scheme; According to the bearing fault detection channel, in combination with the nth bearing health deviation matrix, fault detection is performed on the nth bearing to obtain an nth bearing fault detection result; According to the asynchronous motor sensor monitoring network, an auxiliary component monitoring data set of the asynchronous motor is obtained, and according to the auxiliary component monitoring data set, fault correlation compensation is performed on the nth bearing fault detection result to generate an nth bearing fault detection report; According to the control decision scheme, the health deviation analysis of the nth bearing is performed in combination with the nth bearing monitoring data stream to obtain the nth bearing health deviation matrix, including: Perform monitoring element identification according to the nth bearing monitoring data stream to generate an nth bearing monitoring element set; Establishing an nth bearing monitoring element matrix according to the nth bearing monitoring element set; Performing data integration on the nth bearing monitoring data stream according to the nth bearing monitoring element matrix to generate an nth bearing monitoring matrix; Performing health prediction on the nth bearing according to the control decision scheme and the nth bearing monitoring element matrix to obtain the nth bearing health prediction matrix, wherein health prediction refers to predicting the future state of the nth bearing by using historical data and the current monitoring element matrix in combination with the control decision scheme; Perform deviation analysis according to the nth bearing health prediction matrix and the nth bearing monitoring matrix to generate the nth bearing health deviation matrix; Among them, performing health prediction on the nth bearing according to the control decision scheme and the nth bearing monitoring element matrix to obtain the nth bearing health prediction matrix includes: Obtaining characteristic attribute information of an nth bearing, wherein the characteristic attribute information of the nth bearing includes model specification information of the asynchronous motor, and model specification parameters and installation position parameters of the nth bearing; Associating bearings with the same characteristic attributes according to the characteristic attribute information of the nth bearing, and determining a bearing source with the same characteristic, wherein the bearing source with the same characteristic includes the nth bearing and a plurality of bearings with the same characteristic attributes corresponding to the nth bearing; Retrieving normal monitoring records according to the bearing sources with the same characteristics to obtain multiple groups of normal bearing monitoring records; Based on the control decision scheme, the plurality of normal bearing monitoring record groups are associated and registered to obtain a bearing monitoring associated healthy sample set; Performing concentrated interval analysis based on the bearing monitoring associated health sample set to obtain multiple bearing monitoring associated health intervals; According to the nth bearing monitoring element matrix, the plurality of bearing monitoring associated health intervals are sorted to generate the nth bearing health prediction matrix.

2. The method according to claim 1, characterized in that Based on the control decision scheme, the plurality of normal bearing monitoring record groups are associated and registered to obtain a bearing monitoring associated healthy sample set, including: Traversing the plurality of normal bearing monitoring record groups, extracting a first normal bearing monitoring record group, wherein the first normal bearing monitoring record group includes a first historical asynchronous motor control decision scheme and a first historical normal bearing monitoring data stream; Based on the twin neural network, the control decision scheme and the first historical asynchronous motor control decision scheme are aligned and identified to obtain a first asynchronous motor control alignment coefficient; Determining whether the first asynchronous motor control registration coefficient is greater than / equal to an asynchronous motor control registration threshold; If the first asynchronous motor control registration coefficient is greater than / equal to the asynchronous motor control registration threshold, adding the first historical bearing monitoring normal data stream to the bearing monitoring associated healthy sample set; If the first asynchronous motor control registration coefficient is less than the asynchronous motor control registration threshold, the first historical bearing monitoring normal data stream is eliminated.

3. The method according to claim 1, characterized in that According to the bearing fault detection channel, in combination with the nth bearing health deviation matrix, fault detection is performed on the nth bearing to obtain the nth bearing fault detection result, including: Perform deviation depth evaluation according to the nth bearing health deviation matrix to obtain the nth bearing health deviation depth coefficient; Determining whether the nth bearing health deviation depth coefficient is greater than / equal to a bearing health deviation depth threshold; If the nth bearing health deviation depth coefficient is greater than / equal to the bearing health deviation depth threshold, activating the bearing fault detection channel, wherein the bearing fault detection channel includes S bearing fault detection models, wherein S is a positive integer greater than 1; Inputting the nth bearing health deviation matrix into the S bearing fault detection models to obtain S bearing fault detection data; The S bearing fault detection data are integrated to generate the nth bearing fault detection result.

4. The method according to claim 1, characterized in that Performing fault correlation compensation on the nth bearing fault detection result according to the auxiliary component monitoring data set to generate an nth bearing fault detection report, including: Performing fault detection on each auxiliary component of the asynchronous motor according to the auxiliary component monitoring data set to obtain a plurality of auxiliary fault detection results; Performing fault association compensation on the nth bearing fault detection result according to the multiple auxiliary fault detection results to obtain an nth bearing optimized fault detection result; According to a predetermined bearing fault report template, the nth bearing optimization fault detection result is sorted to obtain the nth bearing fault detection report.

5. The method according to claim 4, characterized in that Performing fault association compensation on the nth bearing fault detection result according to the multiple auxiliary fault detection results to obtain the nth bearing optimized fault detection result, including: Traversing the plurality of auxiliary fault detection results, and extracting a first auxiliary fault detection result; Performing a fault impact evaluation on the nth bearing according to the first auxiliary fault detection result to obtain a first auxiliary fault impact coefficient; Determining whether the first auxiliary fault impact coefficient is greater than / equal to an auxiliary fault impact threshold; If the first auxiliary fault influence coefficient is greater than / equal to the auxiliary fault influence threshold, performing fault interference identification on the nth bearing according to the first auxiliary fault detection result to obtain a bearing fault interference identification result; The nth bearing fault detection result is associated and compensated according to the bearing fault interference identification result to generate the nth bearing optimized fault detection result.

6. An intelligent detection device for asynchronous motor bearing fault, characterized in that: The steps for implementing the method for intelligent detection of asynchronous motor bearing faults according to any one of claims 1 to 5 include: A control instruction receiving module, the control instruction receiving module is used to receive the control instruction of the asynchronous motor, wherein the control instruction includes a control decision scheme, and the control decision scheme includes an optimized working mode selection, a load adjustment strategy and energy-saving measures to ensure that the motor operates in an optimal state; A bearing monitoring data stream acquisition module, the bearing monitoring data stream acquisition module is used to control the asynchronous motor according to the control decision scheme, and obtain N bearing monitoring data streams corresponding to N bearings of the asynchronous motor according to a pre-arranged asynchronous motor sensor monitoring network, wherein N is a positive integer greater than 1; An nth bearing monitoring data stream extraction module, the nth bearing monitoring data stream extraction module is used to extract an nth bearing monitoring data stream corresponding to the nth bearing according to the N bearing monitoring data streams, wherein n is a positive integer, 1≤n≤N; an nth bearing health deviation matrix obtaining module, the nth bearing health deviation matrix obtaining module is used to perform health deviation analysis on the nth bearing according to the control decision scheme and in combination with the nth bearing monitoring data stream to obtain the nth bearing health deviation matrix, wherein health deviation analysis refers to evaluating the difference between the current operating state of the bearing and the ideal health state by analyzing the real-time monitoring data of the nth bearing and in combination with a pre-set control decision scheme; an nth bearing fault detection result obtaining module, the nth bearing fault detection result obtaining module being used to perform fault detection on the nth bearing according to the bearing fault detection channel in combination with the nth bearing health deviation matrix, and obtain an nth bearing fault detection result; an nth bearing fault detection report generating module, the nth bearing fault detection report generating module being used to obtain an auxiliary component monitoring data set of the asynchronous motor according to the asynchronous motor sensor monitoring network, and to perform fault correlation compensation on the nth bearing fault detection result according to the auxiliary component monitoring data set to generate an nth bearing fault detection report; The nth bearing health deviation matrix obtaining module is also used for: Perform monitoring element identification according to the nth bearing monitoring data stream to generate an nth bearing monitoring element set; Establishing an nth bearing monitoring element matrix according to the nth bearing monitoring element set; Performing data integration on the nth bearing monitoring data stream according to the nth bearing monitoring element matrix to generate an nth bearing monitoring matrix; Performing health prediction on the nth bearing according to the control decision scheme and the nth bearing monitoring element matrix to obtain the nth bearing health prediction matrix, wherein health prediction refers to predicting the future state of the nth bearing by using historical data and the current monitoring element matrix in combination with the control decision scheme; Perform deviation analysis according to the nth bearing health prediction matrix and the nth bearing monitoring matrix to generate the nth bearing health deviation matrix; Obtaining characteristic attribute information of an nth bearing, wherein the characteristic attribute information of the nth bearing includes model specification information of the asynchronous motor, and model specification parameters and installation position parameters of the nth bearing; Associating bearings with the same characteristic attributes according to the characteristic attribute information of the nth bearing, and determining a bearing source with the same characteristic, wherein the bearing source with the same characteristic includes the nth bearing and a plurality of bearings with the same characteristic attributes corresponding to the nth bearing; Retrieve normal monitoring records based on the bearing sources with the same characteristics to obtain multiple groups of normal bearing monitoring records; perform correlation registration on the multiple groups of normal bearing monitoring records based on the control decision scheme to obtain a bearing monitoring correlation health sample set; Performing concentrated interval analysis based on the bearing monitoring associated health sample set to obtain multiple bearing monitoring associated health intervals; According to the nth bearing monitoring element matrix, the plurality of bearing monitoring associated health intervals are sorted to generate the nth bearing health prediction matrix.

Citation Information

Patent Citations

  • Asynchronous motor bearing fault diagnosis method based on multilayer noise reduction technology

    CN110672327A

  • Bearing composite fault diagnosis method based on improved local non-negative matrix factorization

    CN113865866A

  • Rolling bearing fault intelligent diagnosis method

    CN115290326A

  • Asynchronous motor rolling bearing fault detection method

    CN116842364A

  • Fault diagnosis method and system for alternating-current variable-frequency asynchronous motor of petroleum drilling machine

    CN116861183A