Intelligent electromechanical coupling system and fault diagnosis method thereof

By building a diagnostic model and using multiple algorithms to process fault data, combining physical models and system topology, the rapid identification and positioning of fault sources of electromechanical coupled system is achieved, solving the problem of low fault diagnosis efficiency in the existing technology, and improving fault diagnosis accuracy and robustness.

CN119089266AInactive Publication Date: 2024-12-06NANJING XUANHANYU INFORMATION TECHNOLOGY CO LTD
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202411180581.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-27
Publication Date
2024-12-06
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The existing fault diagnosis methods of electromechanical coupling systems cannot quickly determine the fault source, which reduces the working efficiency of fault source identification and positioning.

Method used

A variety of algorithms are used to build diagnostic models, collect and process fault data through sensor data, historical fault data and feature information in the fault database, extract fault characteristics, combine physical models and system topology, analyze fault propagation paths, and use intuitive tools and Visualization technology for troubleshooting and positioning.

Benefits of technology

It effectively improves the identification and positioning efficiency of fault sources in electromechanical coupling systems, improves the accuracy and robustness of fault diagnosis, and can be applied in different working conditions and fault modes.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119089266A_ABST
    Figure CN119089266A_ABST
Patent Text Reader

Abstract

The invention discloses an intelligent electromechanical coupling system and a fault diagnosis method thereof, and belongs to the technical field of electromechanical coupling. The system comprises a mechanical system, an electrical system and a coupling element. The fault diagnosis method comprises the following steps of 1, constructing a diagnosis model by adopting multiple algorithms; step 2, fault data in the electromechanical coupling system are collected and processed by using the diagnosis model, and fault features are extracted; and step 3, determining a fault source of the fault according to the fault characteristics, analyzing a fault propagation path and positioning a fault component or part in combination with a physical model and system topology, and presenting a fault diagnosis result and fault positioning information to maintenance personnel by using a visualization tool and a visualization technology. According to the method, the fault data can be extracted and processed, and the fault features of the fault data are determined according to the feature information in the fault database, so that the fault source can be determined, and the identification and positioning of the fault source in the electromechanical coupling system are effectively improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of electromechanical coupling, and in particular to an intelligent electromechanical coupling system and a fault diagnosis method thereof. Background Art

[0002] As we all know, electromechanical coupling refers to the technology of interaction and cooperation between the two fields of mechanics and electricity. It coordinates the movement of mechanical systems and the control of electricity to achieve more efficient, intelligent and precise work. In an electromechanical coupling system, mechanical energy and electrical energy can be converted into each other. When a mechanical system is subjected to external forces, deformation and movement will occur, which can be converted into electrical energy through appropriate devices. Conversely, when electric current passes through an electromagnetic device, a magnetic field and force are generated, which drive the mechanical system to move or produce mechanical deformation.

[0003] However, the existing electromechanical coupling system fault diagnosis method cannot quickly determine the fault source when diagnosing the electromechanical coupling system, which reduces the efficiency of fault source identification and location in the electromechanical coupling system. Therefore, we propose an intelligent electromechanical coupling system and its fault diagnosis method to solve the above-mentioned problems. Summary of the invention

[0004] The object of the present invention is to provide an intelligent electromechanical coupling system and a fault diagnosis method thereof to solve the problems raised in the above background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] An intelligent electromechanical coupling system includes: a mechanical system, an electrical system and a coupling element, wherein the coupling element includes a motor, a sensor, an actuator and other elements, the mechanical system and the electrical system are connected to each other, and the electrical system and the coupling element are connected to each other.

[0007] Furthermore, a fault diagnosis method for an intelligent electromechanical coupling system comprises the following steps:

[0008] Step 1: Use multiple algorithms to build a diagnostic model that can identify and classify faults;

[0009] Step 2: Use the diagnostic model to collect fault data in the electromechanical coupling system, process the fault data, and extract fault features;

[0010] Step 3: Determine the fault source based on the fault characteristics, analyze the fault propagation path based on the physical model and system topology, locate the faulty component or part, and use intuitive tools and visualization technology to present the fault diagnosis results and fault location information to maintenance personnel.

[0011] Furthermore, in step one, the diagnostic model also includes using sensor data, historical fault data and feature information in the fault database to train and verify the diagnostic model; optimizing the performance of the diagnostic model to improve the accuracy and robustness of fault diagnosis.

[0012] Furthermore, in step one, the multiple algorithms include machine learning methods and deep learning methods.

[0013] Furthermore, in step 2, fault data collection includes using sensor nodes in the wireless sensor network to collect multiple sets of electromechanical fault related data such as vibration, temperature, and current; the wireless sensor network provides high-sensitivity and low-power sensors, which are deployed in hard-to-reach areas to achieve real-time collection of fault signals.

[0014] Furthermore, in step 2, fault data processing includes using data mining, machine learning and multiple algorithms to process the collected fault data and extract fault features; preprocessing the original data through feature engineering to eliminate noise and improve the signal-to-noise ratio of the fault signal.

[0015] Furthermore, the deep learning method for anomaly detection in fault feature extraction includes using a deep learning model to establish a baseline for normal operation of intelligent electromechanical equipment, and then detecting anomalies that deviate from the baseline; through the method, potential faults are identified before signs of faults appear.

[0016] Furthermore, the sensor data, historical fault data and feature information in the fault database are used to train and verify the diagnostic model. The fault classification in the fault database includes classifying the fault types in the electromechanical coupling system based on the fault mechanism, fault mode and fault phenomenon; using fault tree analysis, fault mode and effect analysis and other methods to analyze the causes, effects and propagation paths of the faults; building a fault database to store and manage feature data of different fault types to provide a basis for diagnosis.

[0017] Furthermore, in step one, the evaluation of the diagnostic model includes using cross-validation and leave-one-out validation to evaluate the generalization ability and robustness of the diagnostic model; verifying the effectiveness and practicality of the diagnostic model through actual fault test field tests; and regularly updating and optimizing the diagnostic model to adapt to the evolution of the failure mode of the electromechanical coupling system and the emergence of new fault types.

[0018] Furthermore, the sensor data, historical fault data and feature information in the fault database are used to train and verify the diagnostic model. Through experiments or actual fault cases, the accuracy of the evidence-based reasoning fault diagnosis method is verified. The deviation between the diagnostic results and the actual faults is analyzed, and the model is improved and optimized. The reliability and robustness of fault diagnosis are explored, and the applicability of the diagnostic method under different working conditions and fault modes is improved.

[0019] Compared with the prior art, the present invention has the following beneficial effects:

[0020] The intelligent electromechanical coupling system and the fault diagnosis method thereof collect fault data in the electromechanical coupling system through a diagnostic model, and process the fault data to extract fault characteristics; determine the fault source of the fault according to the fault characteristics, analyze the fault propagation path in combination with the physical model and the system topology, locate the faulty component or part, and present the fault diagnosis results and fault location information to the maintenance personnel by using intuitive tools and visualization technology; can extract and process the fault data, determine the fault characteristics of the fault data according to the characteristic information in the fault database, and thus can determine the fault source, which effectively improves the identification and location of the fault source in the electromechanical coupling system and is relatively convenient. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 It is a structural schematic diagram of the intelligent electromechanical coupling system in the present invention.

[0022] Figure 2 It is a schematic diagram of the flow chart of the fault diagnosis method of the intelligent electromechanical coupling system in the present invention. DETAILED DESCRIPTION

[0023] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0024] like Figure 1 As shown, an intelligent electromechanical coupling system includes: a mechanical system, an electrical system and a coupling element, wherein the coupling element includes a motor, a sensor, an actuator and other components, the mechanical system and the electrical system are interconnected, and the electrical system and the coupling element are interconnected.

[0025] like Figure 2 As shown, a fault diagnosis method for an intelligent electromechanical coupling system comprises the following steps:

[0026] Step 1: Use multiple algorithms to build a diagnostic model that can identify and classify faults;

[0027] Step 2: Use the diagnostic model to collect fault data in the electromechanical coupling system, process the fault data, and extract fault features;

[0028] Step 3: Determine the fault source based on the fault characteristics, analyze the fault propagation path based on the physical model and system topology, locate the faulty component or part, and present the fault diagnosis results and fault location information to the maintenance personnel using intuitive tools and visualization technology;

[0029] The fault data in the electromechanical coupling system is collected through the diagnostic model, and the fault data is processed and the fault characteristics are extracted. The fault source is determined according to the fault characteristics, and the fault propagation path is analyzed in combination with the physical model and system topology, and the faulty components or parts are located. The fault diagnosis results and fault location information are presented to maintenance personnel using intuitive tools and visualization technology. The fault data can be extracted and processed, and the fault characteristics of the fault data can be determined according to the characteristic information in the fault database, so that the fault source can be determined, which effectively improves the identification and location of the fault source in the electromechanical coupling system and is relatively convenient.

[0030] Furthermore, in the step 1, the diagnostic model also includes training and verifying the diagnostic model by using sensor data, historical fault data and feature information in the fault database; optimizing the performance of the diagnostic model to improve the accuracy and robustness of fault diagnosis;

[0031] Furthermore, in step 1, the multiple algorithms include machine learning and deep learning;

[0032] Furthermore, in step 2, fault data collection includes using sensor nodes in a wireless sensor network to collect multiple sets of electromechanical fault related data such as vibration, temperature, and current; the wireless sensor network provides high-sensitivity and low-power sensors, which are deployed in hard-to-reach areas to achieve real-time collection of fault signals; wireless communication technology ensures that data is transmitted from sensor nodes to a data processing center; feature extraction and processing are performed on the acquired data to extract fault-related feature parameters, and a mapping relationship between feature parameters and fault types is established by combining physical models and empirical knowledge.

[0033] Furthermore, in step 2, the fault data processing includes using data mining, machine learning and other algorithms to process the collected fault data and extract fault features; preprocessing the original data through feature engineering to eliminate noise and improve the signal-to-noise ratio of the fault signal;

[0034] Fault signal processing method based on signal-to-noise ratio optimization:

[0035] Time domain signal processing: Use the characteristics of time domain waveforms, such as peak value, root mean square, energy, etc. to identify fault signals. Applicable to low-frequency, periodic faults, such as bearing faults, gear transmission faults, etc.

[0036] Frequency domain signal processing: Convert the signal into frequency domain, analyze the spectrum information, and identify the fault frequency. Applicable to high-frequency, random faults, such as electrical faults, harmonic distortion, etc.

[0037] Time-frequency domain signal processing: Considering both time and frequency information, the fault characteristics are identified through time-frequency analysis diagrams. Applicable to non-stationary and transient faults, such as rotor faults, motor stator faults, etc.

[0038] Signal-to-noise ratio optimization technology:

[0039] Filtering technology: Use digital filters to suppress noise and improve the signal-to-noise ratio. Commonly used filters include low-pass filters, high-pass filters, band-pass filters, etc.

[0040] Noise reduction algorithm: Use digital algorithms to remove noise from signals and enhance fault information. Common noise reduction algorithms include wavelet transform, empirical mode decomposition, etc.

[0041] Adaptive processing technology: Adaptively adjust the signal-to-noise ratio optimization strategy according to signal characteristics to improve fault identification accuracy.

[0042] Furthermore, the anomaly detection in fault feature extraction using the deep learning method includes using a deep learning model to establish a baseline for normal intelligent electromechanical device operation and then detecting anomalies that deviate from the baseline; in this way, potential faults are identified before signs of faults occur;

[0043] Furthermore, the sensor data, historical fault data and characteristic information in the fault database are used to train and verify the diagnostic model. The fault classification in the fault database includes classifying the fault types in the electromechanical coupling system based on the fault mechanism, fault mode and fault phenomenon; using fault tree analysis, fault mode and effect analysis and other methods to analyze the causes, effects and propagation paths of the faults; building a fault database to store and manage characteristic data of different fault types to provide a basis for diagnosis;

[0044] Furthermore, in the step 1, the evaluation of the diagnostic model includes using cross-validation and leave-one-out validation to evaluate the generalization ability and robustness of the diagnostic model; verifying the effectiveness and practicality of the diagnostic model through actual fault test field tests; and regularly updating and optimizing the diagnostic model to adapt to the evolution of the fault mode of the electromechanical coupling system and the emergence of new fault types;

[0045] Furthermore, the sensor data, historical fault data and feature information in the fault database are used to train and verify the diagnostic model. The accuracy of the evidence-based fault diagnosis method is verified through experiments or actual fault cases. The deviation between the diagnostic results and the actual fault is analyzed, and the model is improved and optimized. The reliability and robustness of fault diagnosis are explored to improve the applicability of the diagnostic method under different working conditions and fault modes.

[0046] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. An intelligent electromechanical coupling system, characterized in that: The system comprises: a mechanical system, an electrical system and a coupling element, wherein the coupling element comprises a motor, a sensor, an actuator and other elements, the mechanical system and the electrical system are connected to each other, and the electrical system and the coupling element are connected to each other.

2. According to the intelligent electromechanical coupling system of claim 1, a method for fault diagnosis of the intelligent electromechanical coupling system is characterized in that: The method comprises the following steps: Step 1: Use multiple algorithms to build a diagnostic model that can identify and classify faults; Step 2: Use the diagnostic model to collect fault data in the electromechanical coupling system, process the fault data, and extract fault features; Step 3: Determine the fault source based on the fault characteristics, analyze the fault propagation path based on the physical model and system topology, locate the faulty component or part, and use intuitive tools and visualization technology to present the fault diagnosis results and fault location information to maintenance personnel.

3. The intelligent electromechanical coupling system fault diagnosis method according to claim 2, characterized in that: In the step 1, the construction of the diagnostic model also includes training and verifying the diagnostic model using sensor data, historical fault data and feature information in the fault database, and optimizing the performance of the diagnostic model to improve the accuracy and robustness of fault diagnosis.

4. The intelligent electromechanical coupling system fault diagnosis method according to claim 2, characterized in that: In step one, the multiple algorithms include machine learning methods and deep learning methods.

5. The intelligent electromechanical coupling system fault diagnosis method according to claim 2, characterized in that: In the step 2, the fault data collection includes collecting multiple sets of electromechanical fault related data such as vibration, temperature, and current using sensor nodes in the wireless sensor network; Wireless sensor networks provide highly sensitive and low-power sensors that are deployed in hard-to-reach areas to achieve real-time collection of fault signals.

6. The intelligent electromechanical coupling system fault diagnosis method according to claim 2, characterized in that: In the step 2, the fault data processing includes using data mining, machine learning and multiple algorithms to process the collected fault data and extract fault features; preprocessing the original data through feature engineering to eliminate noise and improve the signal-to-noise ratio of the fault signal.

7. The intelligent electromechanical coupling system fault diagnosis method according to claim 4, characterized in that: The anomaly detection in fault feature extraction using the deep learning method includes using a deep learning model to establish a baseline for normal intelligent electromechanical device operation and then detecting anomalies that deviate from the baseline; By means of the method, potential faults are identified before fault symptoms occur.

8. The intelligent electromechanical coupling system fault diagnosis method according to claim 3, characterized in that: Using sensor data, historical fault data and feature information in the fault database, the diagnostic model is trained and verified. The fault classification in the fault database includes classifying the fault types in the electromechanical coupling system based on the fault mechanism, fault mode and fault phenomenon; Use fault tree analysis, failure mode and effect analysis and other methods to analyze the causes, effects and propagation paths of faults; Build a fault database to store and manage characteristic data of different fault types to provide a basis for diagnosis.

9. The intelligent electromechanical coupling system fault diagnosis method according to claim 2, characterized in that: In the step 1, the evaluation of the diagnostic model includes using cross-validation and leave-one-out validation to evaluate the generalization ability and robustness of the diagnostic model; verifying the effectiveness and practicality of the diagnostic model through actual fault test field tests; and regularly updating and optimizing the diagnostic model to adapt to the evolution of the fault mode of the electromechanical coupling system and the emergence of new fault types.

10. The intelligent electromechanical coupling system fault diagnosis method according to claim 3, characterized in that: Utilize sensor data, historical fault data, and feature information in the fault database to train and validate the diagnostic model. Verify the accuracy of the evidence-based fault diagnosis method through experiments or actual fault cases. Analyze the deviation between the diagnostic results and the actual faults, and improve and optimize the model. Explore the reliability and robustness of fault diagnosis, and improve the applicability of the diagnostic method under different working conditions and fault modes.

Citation Information

Cited By

  • New energy automobile driving motor safety management system and method based on intelligent control

    CN119682544A