Intelligent fault diagnosis method for electromagnetic valve

Abstract

The invention discloses an intelligent fault diagnosis method for an electromagnetic valve, which comprises the following steps of: hardware fault detection: quickly detecting a circuit signal to judge which working state the electromagnetic valve is in, and judging whether the electromagnetic valve is in a normal fault, an open circuit fault or a short circuit fault; through the setting of the hardware fault detection step, circuit signals can be rapidly detected, which working state, normal, open circuit or short circuit fault of the solenoid valve can be judged, through the setting of the signal processing fault detection step, the running state of the solenoid valve can be known more deeply, the fault detection accuracy is improved, and the fault detection efficiency is improved. Through the setting of the model fault detection step, the operation trend of the electromagnetic valve can be predicted, potential faults can be found in time, through the setting of the intelligent algorithm and the machine learning step, a large amount of data can be processed, the fault mode can be rapidly recognized, the diagnosis efficiency is improved, and therefore the problem that the production period is long is solved.

Description

Technical Field

[0001] The invention relates to the technical field of solenoid valves, and in particular to an intelligent diagnosis method for solenoid valve faults. Background Art

[0002] Solenoid valve is an industrial equipment that uses electromagnetic force to control the flow of fluid. As a basic component of automation, it is widely used in industrial control systems to adjust the direction, flow, speed and other parameters of the medium. The following is a detailed introduction to the solenoid valve. The internal structure of the solenoid valve usually includes components such as electromagnetic coil, valve core, spring and valve seat. When no current passes through the electromagnetic coil, the spring presses the valve core against the valve seat, thereby closing the flow channel. When current passes through the electromagnetic coil, the coil generates electromagnetic force, attracting the valve core and moving it, thereby opening the flow channel. By controlling the current on and off of the electromagnetic coil, precise control of the flow of the fluid can be achieved. According to different working principles, solenoid valves can be divided into many types, such as direct-acting solenoid valves, pilot-operated solenoid valves, etc. When the direct-acting solenoid valve is energized, the electromagnetic force directly acts on the valve core to move it; while the pilot-operated solenoid valve controls the action of the main valve by opening and closing the pilot valve.

[0003] According to the patent announcement number CN112610367B published on the China Patent Network, the present invention relates to a method for diagnosing a charcoal canister solenoid valve fault, which measures the pressure of the desorption pipeline through a pressure sensor on the charcoal canister flushing pump. When the vehicle is in an idle condition and the charcoal canister flushing pump and the charcoal canister solenoid valve are closed, the pressure P0 of the desorption pipeline is measured; the charcoal canister solenoid valve fault is determined by using the pressure change of the desorption pipeline after the charcoal canister flushing pump and the charcoal canister solenoid valve are opened. The method for diagnosing the charcoal canister desorption pipeline of the present invention realizes the fault diagnosis of the normally open or normally closed charcoal canister solenoid valve through the pressure sensor provided by the charcoal canister flushing pump. The fault diagnosis of the charcoal canister solenoid valve can be realized without adding an additional sensor, and the wiring harness arrangement of the sensor is simplified, thereby simplifying the system structure.

[0004] Intelligent fault diagnosis is required when the solenoid valve is working, but most of the solenoid valves on the market have high hardware design requirements for intelligent fault diagnosis and a long production cycle. At the same time, parameters cannot be flexibly modified, which makes intelligent fault diagnosis cumbersome, time-consuming and labor-intensive, and cannot bring convenience to users, affecting the normal operation of the solenoid valve.

[0005] Therefore, it is necessary to design and transform the intelligent diagnosis of solenoid valve faults to effectively prevent the phenomenon of intelligent diagnosis of solenoid valve faults. Summary of the invention

[0006] In order to solve the problems raised in the above background technology, the purpose of the present invention is to provide a solenoid valve fault intelligent diagnosis method, which has the advantage of optimizing the intelligent fault diagnosis and solves the problem of long production cycle and inability to flexibly modify parameters.

[0007] To achieve the above object, the present invention provides the following technical solution: a solenoid valve fault intelligent diagnosis method, comprising the following steps: Hardware fault detection steps: By quickly detecting the circuit signal, it is possible to determine the working state of the solenoid valve, whether it is normal, open circuit or short circuit fault; Signal processing fault detection steps: Through mathematical means, the state parameters of the solenoid valve during movement are analyzed, such as the position of the solenoid valve, current signal, magnetic field signal, etc., combined with signal analysis and processing techniques, such as empirical mode decomposition and fuzzy hierarchical analysis, the classification of normal working state and fault failure state can be realized; Model fault detection steps: By mathematically modeling the solenoid valve control system, starting from the system control process, determine whether the system has a fault. Common mathematical models include observer-based identification methods, parameter-based identification methods, and equivalent space-based methods; Intelligent algorithm and machine learning steps: Applying intelligent algorithm and machine learning technology to solenoid valve fault diagnosis can improve the automation and intelligence level of diagnosis. By collecting the operation data of the solenoid valve and using machine learning algorithms for training and optimization, automatic identification and classification of solenoid valve faults can be achieved; Comprehensive diagnostic steps: Applying the above methods comprehensively to the solenoid valve fault intelligent diagnosis system can realize all-round monitoring and diagnosis of solenoid valve faults. The system can monitor the operating status of the solenoid valve in real time, and through data analysis, model prediction and intelligent algorithms, quickly and accurately identify the fault type and location, providing strong support for maintenance and replacement.

[0008] As a preferred embodiment of the present invention, the hardware fault detection step should ensure that the circuit is in a safe state when performing hardware fault detection to avoid dangerous situations such as electric shock or short circuit. When collecting and analyzing circuit signals, the working characteristics and environmental conditions of the solenoid valve should be fully considered to ensure the accuracy of the diagnostic results.

[0009] As a preferred embodiment of the present invention, the signal processing fault detection step utilizes techniques such as empirical mode decomposition (EMD) to decompose complex signals into a series of intrinsic mode functions (IMFs), thereby making it easier to identify fault signals. At the same time, combined with methods such as fuzzy hierarchical analysis (FHA), a fuzzy comprehensive evaluation is performed on the working state of the solenoid valve to achieve classification of normal working state and fault failure state.

[0010] As a preferred embodiment of the present invention, the model fault detection step can achieve comprehensive monitoring and accurate diagnosis of the solenoid valve control system through a series of steps such as mathematical modeling, model verification and calibration, fault detection algorithm design, real-time fault detection, fault analysis and location, and system optimization and improvement.

[0011] As a preferred embodiment of the present invention, the intelligent algorithm and machine learning steps can realize automatic and intelligent diagnosis of solenoid valve faults through a series of steps such as data collection and processing, feature extraction and selection, machine learning model construction and training, model testing and optimization, fault identification and classification, and diagnostic reporting and decision support.

[0012] As a preferred embodiment of the present invention, the comprehensive diagnosis step, through the comprehensive application of advanced technologies such as data analysis, model prediction and intelligent algorithms, has the advantages of real-time monitoring, rapid and accurate, decision support and continuous optimization, thereby realizing all-round monitoring and diagnosis of solenoid valve faults.

[0013] As a preferred embodiment of the present invention, the comprehensive diagnosis step provides corresponding maintenance suggestions and treatment measures based on the fault diagnosis results, and can provide support documents such as maintenance manuals and drawings so that maintenance personnel can better understand and solve the problem.

[0014] As a preferred embodiment of the present invention, the comprehensive diagnosis step continuously optimizes and improves the diagnosis method and model according to the feedback and effects in actual application, and can introduce new technologies and algorithms to improve the accuracy and efficiency of diagnosis.

[0015] Compared with the prior art, the present invention has the following beneficial effects: 1. The present invention can quickly detect circuit signals and determine the working state of the solenoid valve, whether it is normal, open circuit or short circuit, by setting the hardware fault detection step. By setting the signal processing fault detection step, the operating state of the solenoid valve can be more deeply understood, and the accuracy of fault detection can be improved. By setting the model fault detection step, the operating trend of the solenoid valve can be predicted and potential faults can be discovered in time. By setting the intelligent algorithm and machine learning steps, a large amount of data can be processed, the fault mode can be quickly identified, and the diagnosis efficiency can be improved, thereby solving the problem of long production cycle and inability to flexibly modify parameters, and having the advantage of optimizing the intelligent diagnosis of faults. DETAILED DESCRIPTION

[0016] The following will be combined with the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0017] Embodiment 1: A solenoid valve fault intelligent diagnosis method comprises the following steps: Hardware fault detection steps: By quickly detecting the circuit signal, it is possible to determine the working state of the solenoid valve, whether it is normal, open circuit or short circuit fault; Signal processing fault detection steps: Use mathematical means to analyze the state parameters of the solenoid valve during movement, such as the position of the solenoid valve, current signal, magnetic field signal, etc., combined with signal analysis and processing technology and empirical mode decomposition, to achieve the classification of normal working state and fault failure state; Model fault detection steps: By mathematically modeling the solenoid valve control system, starting from the system control process, determine whether the system has a fault. Common mathematical models include observer-based identification methods and parameter-based identification methods; Intelligent algorithm and machine learning steps: Applying intelligent algorithm and machine learning technology to solenoid valve fault diagnosis can improve the automation and intelligence level of diagnosis. By collecting the operation data of the solenoid valve and using machine learning algorithms for training and optimization, automatic identification and classification of solenoid valve faults can be achieved; Comprehensive diagnostic steps: Applying the above methods in an intelligent diagnostic system for solenoid valve faults can achieve all-round monitoring and diagnosis of solenoid valve faults. The system can monitor the operating status of the solenoid valve in real time, and through data analysis and intelligent algorithms, quickly and accurately identify the fault type and location, providing strong support for maintenance and replacement.

[0018] Embodiment 2: A solenoid valve fault intelligent diagnosis method comprises the following steps: Hardware fault detection steps: By quickly detecting the circuit signal, it is possible to determine the working state of the solenoid valve, whether it is normal, open circuit or short circuit fault; Signal processing fault detection steps: Use mathematical means to analyze the state parameters of the solenoid valve during movement, such as the solenoid valve current signal and magnetic field signal. Combined with signal analysis and processing technology, fuzzy hierarchical analysis can realize the classification of normal working state and fault failure state; Model fault detection steps: By mathematically modeling the solenoid valve control system, starting from the system control process, determine whether the system has a fault. Common mathematical models include observer-based identification methods, parameter-based identification methods, and equivalent space-based methods; Intelligent algorithm and machine learning steps: Applying intelligent algorithm and machine learning technology to solenoid valve fault diagnosis can improve the automation and intelligence level of diagnosis. By collecting the operation data of the solenoid valve and using machine learning algorithms for training and optimization, automatic identification and classification of solenoid valve faults can be achieved; Comprehensive diagnostic steps: Applying the above methods comprehensively to the solenoid valve fault intelligent diagnosis system can realize all-round monitoring and diagnosis of solenoid valve faults. The system can monitor the operating status of the solenoid valve in real time, and through data analysis, model prediction and intelligent algorithms, quickly and accurately identify the fault type and location, providing strong support for maintenance and replacement.

[0019] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0020] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An intelligent diagnosis method for solenoid valve faults, characterized in that: The following steps are involved: Hardware fault detection steps: By quickly detecting the circuit signal, it is possible to determine the working state of the solenoid valve, whether it is normal, open circuit or short circuit fault; Signal processing fault detection steps: Through mathematical means, the state parameters of the solenoid valve during movement are analyzed, such as the position of the solenoid valve, current signal, magnetic field signal, etc., combined with signal analysis and processing techniques, such as empirical mode decomposition and fuzzy hierarchical analysis, the classification of normal working state and fault failure state can be realized; Model fault detection steps: By mathematically modeling the solenoid valve control system, starting from the system control process, determine whether the system has a fault. Common mathematical models include observer-based identification methods, parameter-based identification methods, and equivalent space-based methods; Intelligent algorithm and machine learning steps: Applying intelligent algorithm and machine learning technology to solenoid valve fault diagnosis can improve the automation and intelligence level of diagnosis. By collecting the operation data of the solenoid valve and using machine learning algorithms for training and optimization, automatic identification and classification of solenoid valve faults can be achieved; Comprehensive diagnostic steps: Applying the above methods comprehensively to the solenoid valve fault intelligent diagnosis system can realize all-round monitoring and diagnosis of solenoid valve faults. The system can monitor the operating status of the solenoid valve in real time, and through data analysis, model prediction and intelligent algorithms, quickly and accurately identify the fault type and location, providing strong support for maintenance and replacement.

2. The intelligent diagnosis method for electromagnetic valve fault according to claim 1 is characterized in that: The hardware fault detection step should ensure that the circuit is in a safe state when performing hardware fault detection to avoid dangerous situations such as electric shock or short circuit. When collecting and analyzing circuit signals, the working characteristics and environmental conditions of the solenoid valve should be fully considered to ensure the accuracy of the diagnostic results.

3. The intelligent diagnosis method for solenoid valve fault according to claim 1 is characterized in that: The signal processing fault detection step utilizes techniques such as empirical mode decomposition (EMD) to decompose complex signals into a series of intrinsic mode functions (IMFs), thereby making it easier to identify fault signals. At the same time, combined with methods such as fuzzy hierarchy analysis (FHA), a fuzzy comprehensive evaluation is performed on the working state of the solenoid valve to achieve classification of normal working state and fault failure state.

4. The intelligent diagnosis method for solenoid valve fault according to claim 1 is characterized in that: The model fault detection step can achieve comprehensive monitoring and accurate diagnosis of the solenoid valve control system through a series of steps such as mathematical modeling, model verification and calibration, fault detection algorithm design, real-time fault detection, fault analysis and location, and system optimization and improvement.

5. The solenoid valve fault intelligent diagnosis method according to claim 1 is characterized by: The intelligent algorithm and machine learning steps can realize automatic and intelligent diagnosis of solenoid valve faults through a series of steps such as data collection and processing, feature extraction and selection, machine learning model construction and training, model testing and optimization, fault identification and classification, and diagnostic reporting and decision support.

6. The solenoid valve fault intelligent diagnosis method according to claim 1 is characterized by: The comprehensive diagnosis step, through the comprehensive application of advanced technologies such as data analysis, model prediction and intelligent algorithm, has the advantages of real-time monitoring, rapid and accurate, decision support and continuous optimization, and realizes all-round monitoring and diagnosis of solenoid valve faults.

7. The intelligent diagnosis method for electromagnetic valve fault according to claim 6 is characterized in that: The comprehensive diagnosis step provides corresponding maintenance suggestions and treatment measures based on the fault diagnosis results, and can provide support documents such as maintenance manuals and drawings so that maintenance personnel can better understand and solve the problems.

8. The intelligent diagnosis method for solenoid valve fault according to claim 6 is characterized by: The comprehensive diagnosis steps described above continuously optimize and improve the diagnostic methods and models based on feedback and effects in actual applications, and may introduce new technologies and algorithms to improve the accuracy and efficiency of diagnosis.