Motor fault analysis method and system and medium

Abstract

The invention discloses a motor fault analysis method and system and a medium, and the method comprises the following steps: S1, obtaining a multi-source detection signal of a motor, and extracting fault features from the multi-source detection signal; s2, generating a fault evaluation model through a pre-established fault feature database; and S3, processing fault features according to the fault evaluation model, and obtaining a motor fault analysis result. According to the method, fault analysis is carried out on the motor through the multi-source detection signals, the multi-source detection signals complement each other, the fault type and the fault degree of the motor are diagnosed more accurately, and maintenance personnel are helped to better understand the health condition of the motor.

Description

Technical Field

[0001] This invention relates to the field of fault analysis technology, and in particular to a method, system and medium for analyzing motor faults. Background Technology

[0002] Currently, the methods for analyzing motor faults are relatively limited. For example, they may assess the noise or vibration performance of rotating machinery through sound spectrum analysis, use more complex sound imaging cameras for more detailed diagnosis when sound diagnostic software cannot make a judgment, observe the temperature differences of different parts to diagnose whether there are any abnormalities in the equipment, or detect the insulation status of the motor through various handheld or offline devices. However, the above methods also require maintenance personnel to make analysis and judgment based on their personal experience. Such judgment usually cannot achieve early diagnosis of motor faults and cannot perform qualitative and quantitative analysis. Summary of the Invention

[0003] The technical problem to be solved by the present invention is to address at least one deficiency of the related technologies mentioned in the background: how to overcome the limitation of motor fault analysis and provide a motor fault analysis method, system and medium.

[0004] The technical solution adopted by this invention to solve its technical problem is: to construct a motor fault analysis method, including the following steps: S1: Acquire the multi-source detection signals of the motor and extract fault features from the multi-source detection signals; S2: Generate a fault assessment model using a pre-established fault feature database; S3: Process fault characteristics based on the fault assessment model to obtain motor fault analysis results.

[0005] In some embodiments, the multi-source detection signal includes at least one or more of vibration signal, sound signal, temperature signal, voltage signal, and current signal.

[0006] In some embodiments, the method for establishing a fault feature database includes: S21: Obtain operating data of at least one motor under different operating conditions and different fault modes; S22: Perform fault diagnosis on the operational data from the spatial and temporal dimensions to obtain fault diagnosis data; S23: After processing the fault diagnosis data, store it in the multi-source detection signal fault database.

[0007] In some embodiments, the operating data under different operating conditions and different fault modes include at least one or more of steady-state parameters, transient parameters, time-domain distortions, and harmonic content.

[0008] In some embodiments, fault diagnosis of operating data from a spatial dimension includes: processing the operating data using a second preset algorithm to diagnose faults in the operating data of the motor from a spatial dimension; The second preset algorithm includes at least one of the following: calculating the ratio of the third harmonic content to the fundamental frequency content, and stripping away environmental noise.

[0009] In some embodiments, fault diagnosis of operating data from a time dimension includes: establishing a database partition for the operating data of a single motor, and performing fault diagnosis on the database partition of the single motor from a time dimension.

[0010] In some embodiments, the method further includes: storing the processed fault features into a fault feature database, obtaining an iterated fault feature database, and iterating the fault assessment model using the iterated fault feature database.

[0011] The present invention also provides a motor fault analysis system, comprising: Multiple types of sensors are used to acquire multi-source detection signals from electric motors; Data acquisition card, used to extract fault features from multi-source detection signals; The model generation module is used to generate fault assessment models from a pre-established fault feature database. The processor is used to process fault characteristics according to the fault assessment model and obtain motor fault analysis results.

[0012] In some embodiments, the multiple types of sensors include at least one or more of vibration sensors, sound sensors, temperature sensors, voltage sensors, and current transformers.

[0013] The present invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the motor fault analysis method as described in any of the preceding claims.

[0014] By implementing this invention, the following beneficial effects are achieved: This invention acquires multi-source detection signals from a motor and extracts fault features from these signals. Then, it generates a fault assessment model using a pre-established fault feature database. Finally, it processes the fault features based on the fault assessment model to obtain the motor fault analysis results. This invention uses multi-source detection signals to analyze motor faults; the signals complement each other, leading to a more accurate diagnosis of motor fault types and severity, and helping maintenance personnel better understand the motor's health status. Attached Figure Description

[0015] The present invention will be further described below with reference to the accompanying drawings and embodiments. In the accompanying drawings: Figure 1 A flowchart of one embodiment of the electric motor fault analysis method of the present invention is shown; Figure 2 A flowchart illustrating a method for establishing a fault feature database in one embodiment of the electric motor fault analysis method of the present invention is shown. Detailed Implementation

[0016] To provide a clearer understanding of the technical features, objectives, and effects of the present invention, specific embodiments of the present invention will now be described in detail with reference to the accompanying drawings.

[0017] It should be noted that the flowcharts shown in the accompanying drawings are merely illustrative and do not necessarily include all content and operations / steps, nor do they necessarily have to be performed in the described order. For example, some operations / steps can be broken down, while others can be combined or partially combined; therefore, the actual execution order may change depending on the specific circumstances.

[0018] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0019] like Figure 1 As shown, some embodiments of the present invention disclose a method for analyzing motor faults, including the following steps: S1: Acquire the multi-source detection signals of the motor and extract fault features from the multi-source detection signals; S2: Generate a fault assessment model using a pre-established fault feature database; S3: Process fault characteristics based on the fault assessment model to obtain motor fault analysis results.

[0020] In some embodiments, the multi-source detection signal includes at least one or more of vibration signal, sound signal, temperature signal, voltage signal, and current signal.

[0021] For example, if the fault features extracted from the multi-source detection signals are abnormal vibration signals, sound signals and temperature signals, such as increased vibration of the motor bearing, abnormal noise, and increased temperature at the bearing end cover, then the three signals can be used to help determine that the motor has a bearing misalignment problem. If the fault features extracted from the multi-source detection signals are abnormal temperature and resistance signals, and the measured bearing and stator temperatures of the motor are rising, and the resistance of the motor windings is abnormal, then it is determined that the motor windings have a fault. If the fault features extracted from the multi-source detection signals are abnormalities in current, temperature, and voltage signals, and the abnormal increase in the no-load current of the motor is likely due to an inter-turn short circuit, and the local short circuit is accompanied by a local temperature rise and abnormal voltage signal distribution, then it is determined to be an inter-turn short circuit in the motor.

[0022] This embodiment overcomes the uncertainty of diagnostic results caused by environmental interference, hardware precision limitations, and other factors when using a single signal to complement each other. It improves the stability, reliability, and robustness of the diagnosis, and more accurately diagnoses the type and severity of motor faults. This allows maintenance personnel to better understand the health status of the motor and thus formulate effective maintenance strategies.

[0023] like Figure 2 As shown, in some embodiments, the method for establishing a fault feature database includes: S21: Obtain operating data of at least one motor under different operating conditions and different fault modes; S22: Perform fault diagnosis on the operational data from the spatial and temporal dimensions to obtain fault diagnosis data; S23: After processing the fault diagnosis data, store it in the multi-source detection signal fault database.

[0024] Specifically, the fault feature database includes operating data of multiple motors under different operating conditions and different fault modes, and the operating data is further processed from spatial and temporal dimensions.

[0025] In some embodiments, the operating data under different operating conditions and different fault modes include at least one or more of steady-state parameters, transient parameters, time-domain distortions, and harmonic content.

[0026] In some embodiments, fault diagnosis of operating data from a spatial dimension includes: processing the operating data using a second preset algorithm to diagnose faults in the operating data of the motor from a spatial dimension; The second preset algorithm includes at least one of the following: calculating the ratio of the third harmonic content to the fundamental frequency content, and stripping away environmental noise.

[0027] This embodiment comprehensively evaluates motor operation data from a spatial dimension; that is, the more motors collected at the same time, the higher the accuracy of the data evaluation.

[0028] In some embodiments, fault diagnosis of operating data from a time dimension includes: establishing a database partition for the operating data of a single motor, and performing fault diagnosis on the database partition of the single motor from a time dimension.

[0029] Specifically, a "one machine, one model" architecture is adopted, a dedicated database partition is established for each motor, and unified prior data and fault parameter information for individual motors are updated. Individual motors are evaluated from a time dimension, and the longer the sampling time, the higher the evaluation accuracy.

[0030] This invention is supported by a fault feature database, which stores fault features of multi-source detection signals of motors in both spatial and temporal dimensions. This database can perform fault analysis for faults caused by multiple factors under specific environments, providing rich data support.

[0031] In some embodiments, the method further includes: storing the processed fault features into a fault feature database, obtaining an iterated fault feature database, and iterating the fault assessment model using the iterated fault feature database.

[0032] By combining data fusion technologies such as neural networks and genetic algorithms, the accuracy of fault diagnosis is improved. Through experimental verification, the data in the fault feature database is continuously optimized to ensure the accuracy and reliability of the data. The processed data is stored in the database, and an efficient indexing system is established to enable rapid data retrieval and analysis, providing strong support for subsequent performance evaluation and fault diagnosis of the motor.

[0033] Iterative methods include model learning, transfer learning, and model transfer, enabling iterative capabilities for motor fault analysis methods.

[0034] By combining multi-source detection signal fusion detection with data fusion technology and iterative methods, paint can improve the ability to extract and identify fault features when dealing with complex and nonlinear problems, thereby improving the accuracy of fault analysis.

[0035] In some embodiments, the design of the fault assessment model includes at least methods such as grade point ranking and performance trend statistics.

[0036] Some embodiments of the present invention disclose a motor fault analysis system, comprising: Multiple types of sensors are used to acquire multi-source detection signals from electric motors; Data acquisition card, used to extract fault features from multi-source detection signals; The model generation module is used to generate fault assessment models from a pre-established fault feature database. The processor is used to process fault characteristics according to the fault assessment model and obtain motor fault analysis results.

[0037] In some embodiments, the multiple types of sensors include at least one or more of vibration sensors, sound sensors, temperature sensors, voltage sensors, and current transformers.

[0038] Specifically, a motor fault analysis system is designed according to the physical quantities to be detected, and appropriate sensors are selected. For acquiring the current detection signal of the motor, a current transformer is used, and for measuring motor vibration, a vibration sensor is selected. The vibration sensor, sound sensor, temperature sensor, voltage sensor, and current transformer in this embodiment are merely examples and are not intended to limit the specific scope of the invention; other sensors may also be used.

[0039] Some embodiments of the present invention disclose a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the motor fault analysis method described in any of the above embodiments.

[0040] It is understood that the above embodiments only illustrate some implementation methods of the present invention, and their descriptions are relatively specific and detailed, but they should not be construed as limiting the scope of the present invention. It should be noted that those skilled in the art can freely combine the above embodiments or technical features without departing from the concept of the present invention, and can also make several modifications and improvements, all of which fall within the protection scope of the present invention. That is, the embodiments described "in some embodiments" can be freely combined with any of the preceding and following embodiments. Therefore, all equivalent transformations and modifications made within the scope of the claims of the present invention should be covered by the claims of the present invention.

Claims

1. A method for analyzing motor faults, characterized in that, Includes the following steps: S1: Acquire the multi-source detection signals of the motor and extract fault features from the multi-source detection signals; S2: Generate a fault assessment model using a pre-established fault feature database; S3: Process fault characteristics based on the fault assessment model to obtain motor fault analysis results.

2. The electric motor fault analysis method according to claim 1, characterized in that, The multi-source detection signal includes at least one or more of the following: vibration signal, sound signal, temperature signal, voltage signal, and current signal.

3. The electric motor fault analysis method according to claim 1, characterized in that, Methods for establishing a fault characteristic database include: S21: Obtain operating data of at least one motor under different operating conditions and different fault modes; S22: Perform fault diagnosis on the operational data from the spatial and temporal dimensions to obtain fault diagnosis data; S23: After processing the fault diagnosis data, store it in the multi-source detection signal fault database.

4. The electric motor fault analysis method according to claim 3, characterized in that, Operating data under different operating conditions and different fault modes include at least one or more of the following: steady-state parameters, transient parameters, time-domain distortions, and harmonic content.

5. The electric motor fault analysis method according to claim 3, characterized in that, Fault diagnosis of operating data from a spatial dimension includes: processing the operating data using a second preset algorithm to diagnose faults in the operating data of the motor from a spatial dimension; The second preset algorithm includes at least one of the following: calculating the ratio of the third harmonic content to the fundamental frequency content, and stripping away environmental noise.

6. The electric motor fault analysis method according to claim 3, characterized in that, Fault diagnosis of operational data from a time perspective includes: establishing database partitions for the operational data of individual motors, and performing fault diagnosis on the database partitions of individual motors from a time perspective.

7. The electric motor fault analysis method according to claim 3, characterized in that, The method further includes: storing the processed fault features into a fault feature database, obtaining an iterated fault feature database, and iterating the fault assessment model using the iterated fault feature database.

8. A motor fault analysis system, characterized in that, include: Multiple types of sensors are used to acquire multi-source detection signals from electric motors; Data acquisition card, used to extract fault features from multi-source detection signals; The model generation module is used to generate fault assessment models from a pre-established fault feature database. The processor is used to process fault characteristics according to the fault assessment model and obtain motor fault analysis results.

9. The motor fault analysis system according to claim 8, characterized in that, The various types of sensors include at least one or more of the following: vibration sensors, sound sensors, temperature sensors, voltage sensors, and current transformers.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the motor fault analysis method as described in any one of claims 1-7.

Images