A spool valve type hydraulic valve failure diagnosis system and method

Abstract

The application discloses a spool type hydraulic valve fault diagnosis system and method, and relates to the technical field of mechanical fault diagnosis, wherein the system comprises a pressure sensor for collecting real-time pressure in a control cavity; a displacement monitoring module comprising a shell, a synchronous ball, a displacement sensor and a permanent magnet, the permanent magnet being arranged at the end of a valve core, the shell being arranged on the spool close to the permanent magnet, the synchronous ball being located in the shell, the synchronous ball moving synchronously with the valve core inside the shell under the magnetic force of the permanent magnet, and the displacement sensor being used for collecting real-time displacement of the synchronous ball; and a fault diagnosis module for diagnosing faults of the spool according to the real-time pressure and the real-time displacement. The displacement monitoring module is installed on the spool, the displacement of the valve core is reflected by the synchronous ball moving synchronously with the valve core, and thus the displacement of the valve core can be directly measured, and the faults of the valve core of the spool, such as sticking and jamming, can be accurately and timely diagnosed in combination with the displacement and the pressure.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of mechanical fault diagnosis, in particular to a slide valve type hydraulic valve fault diagnosis system and method. BACKGROUND

[0002] Slide valve type hydraulic valves are widely used in aviation, aerospace, shipping and heavy industry fields such as oil. In industrial environments, factors such as pollution, vibration and temperature can easily cause the slide valve spool to jam, and in severe cases, the slide valve can be stuck. Valve spool jamming can cause the performance of the hydraulic system to decline, thereby affecting the performance of the mobile system. If the valve spool is stuck, it will directly cause the equipment to shut down, which can cause major accidents, such as the inability to lower the aircraft landing gear, the stopping of the oil drilling machine, etc. Therefore, accurate hydraulic slide valve fault diagnosis and identification is of great significance to ensure the safe operation of the hydraulic system.

[0003] The sensors commonly used to monitor the hydraulic system are pressure sensors, flow sensors and accelerometers. For example, the prior art Chinese patent CN114818457A discloses a hydraulic valve fault diagnosis method based on a gated recurrent neural network, and the Chinese patent CN119066591A discloses a hydraulic valve fault diagnosis and life prediction method and system. Both of these methods are indirect measurement methods, that is, by analyzing the time-frequency domain of vibration, pressure and flow signals, extracting signal features, and corresponding to existing fault labels to identify hydraulic valve faults. Then, the industrial application environment is harsh, with serious noise pollution and intense mechanical vibration. Using pressure signals, flow signals and vibration signals for indirect slide valve jamming and sticking fault diagnosis can lead to inaccurate slide valve jamming fault identification and untimely sticking fault identification, thereby causing over-maintenance or untimely maintenance of slide valve type hydraulic valves, resulting in low maintenance efficiency. SUMMARY

[0004] The embodiments of the present application provide a slide valve type hydraulic valve fault diagnosis system and method to solve the problem of inaccurate and untimely identification in the prior art using pressure, flow and vibration for indirect fault diagnosis.

[0005] In one aspect, the embodiments of the present application provide a slide valve type hydraulic valve fault diagnosis system, comprising:

[0006] A pressure sensor is arranged on the control chamber of the slide valve, and the pressure sensor is used to collect the real-time pressure in the control chamber.

[0007] A displacement monitoring module includes a housing, a synchronous ball, a displacement sensor and a permanent magnet. The permanent magnet is arranged at the end of the valve core, the housing is arranged on the slide valve near the permanent magnet, the synchronous ball is located in the housing, and the synchronous ball moves synchronously with the valve core inside the housing under the magnetic force of the permanent magnet. The displacement sensor is used to collect the real-time displacement of the synchronous ball.

[0008] The fault diagnosis module is electrically connected with the pressure sensor and the displacement sensor respectively, and the fault diagnosis module diagnoses the fault of the spool according to the real-time pressure and the real-time displacement by using a diagnosis model established based on a neural network.

[0009] In a possible implementation, one end of the pressure sensor is inserted into the control cavity, and a sealing structure is arranged between the pressure sensor and the control cavity.

[0010] In a possible implementation, the pressure sensor is provided with a pressure electrical interface, and the fault diagnosis module is electrically connected with the pressure sensor through the pressure electrical interface.

[0011] In a possible implementation, the shell is provided with a displacement electrical interface, and the fault diagnosis module is electrically connected with the displacement sensor through the displacement electrical interface.

[0012] In a possible implementation, the fault diagnosis module includes a fault diagnosis electrical interface and a solving module, and the solving module is electrically connected with the pressure sensor and the displacement sensor respectively through the fault diagnosis electrical interface.

[0013] In a possible implementation, the neural network adopts one of a convolutional neural network, a recurrent neural network and a long short-term memory network.

[0014] In a possible implementation, the displacement sensor adopts one of a laser displacement sensor, a laser ranging sensor, an eddy current displacement sensor, a capacitive displacement sensor and a fiber-optic displacement sensor.

[0015] In another aspect, the embodiment of the present application also provides a fault diagnosis method for a spool type hydraulic valve, which includes:

[0016] Real-time pressure and real-time displacement collected by a pressure sensor and a displacement sensor respectively are acquired;

[0017] A real-time speed of a valve core is determined according to the real-time displacement;

[0018] Feature information of the real-time pressure and the real-time speed is extracted;

[0019] The feature information is input into a diagnosis model to obtain a fault diagnosis result of the spool.

[0020] In a possible implementation, after the real-time pressure and the real-time displacement are obtained, the real-time pressure and the real-time displacement are further subjected to filtering processing, and one of an inertial filtering algorithm, a mean filtering algorithm and a Kalman filtering algorithm is adopted in the filtering processing.

[0021] In a possible implementation, the real-time displacement is subjected to differential processing to obtain the real-time speed, and one of a forward difference method, a backward difference method and a bilinear transformation method is adopted in the differential processing.

[0022] The valve fault diagnosis system and method of the application has the following advantages:

[0023] The displacement monitoring module is installed on the spool, the displacement of the spool is reflected by the synchronous ball moving synchronously with the spool, and thus the displacement of the spool can be directly measured, and the displacement and pressure can be combined to accurately and timely diagnose the faults such as jamming and locking of the spool of the spool valve, thereby providing an accurate and reliable basis for the maintenance of the spool valve. BRIEF DESCRIPTION OF DRAWINGS

[0024] In order to more clearly illustrate the technical solutions in the embodiments of the application or the prior art, the drawings needed to be used in the embodiments or the prior art description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the application, and other drawings can be obtained by those skilled in the art without creative labor.

[0025] Figure 1 The structure diagram of the sensor installed on the spool in the spool valve hydraulic valve fault diagnosis system provided by the embodiment of the application.

[0026] Figure 2 The flowchart of the spool valve hydraulic valve fault diagnosis method provided by the embodiment of the application.

[0027] The description of reference numerals: 1, spool valve; 2, valve sleeve; 3, spool; 4, pressure sensor; 5, sealing structure; 6, pressure electrical interface; 7, shell; 8, synchronous ball; 9, displacement sensor; 10, displacement electrical interface; 11, permanent magnet; 12, pressure monitoring module; 13, displacement acquisition unit; 14, displacement monitoring module; 15, fault diagnosis electrical interface; 16, solving module; 17, fault diagnosis module. DETAILED DESCRIPTION

[0028] The technical solutions in the embodiments of the application will be described clearly and completely in the following with reference to the drawings in the embodiments of the application. Obviously, the described embodiments are only some of the embodiments of the application, not all the embodiments. Based on the embodiments in the application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the application.

[0029] Figure 1 The connection structure diagram of the spool valve hydraulic valve fault diagnosis system provided by the embodiment of the application and the spool valve. The embodiment of the application provides a spool valve hydraulic valve fault diagnosis system, which comprises:

[0030] The pressure sensor 4 is arranged on the control cavity of the slide valve 1, and is used to collect the real-time pressure in the control cavity.

[0031] The displacement monitoring module 14 includes the shell 7, the synchronous ball 8, the displacement sensor 9 and the permanent magnet 11. The permanent magnet 11 is arranged at the end of the spool 3, the shell 7 is arranged on the slide valve 1 close to the permanent magnet 11, the synchronous ball 8 is located in the shell 7, and the synchronous ball 8 moves synchronously with the spool 3 inside the shell 7 under the magnetic force of the permanent magnet 11. The displacement sensor 9 is used to collect the real-time displacement of the synchronous ball 8.

[0032] The fault diagnosis module 17 is electrically connected with the pressure sensor 4 and the displacement sensor 9 respectively, and is used to diagnose the fault of the slide valve 1 according to the real-time pressure and the real-time displacement by using the diagnosis model based on the neural network.

[0033] Exemplarily, the control cavity is located at both ends of the valve sleeve 2, and the spool 3 is arranged in the valve sleeve 2 and slides. One end of the pressure sensor 4 is inserted into the control cavity, and a sealing structure 5 is arranged between the pressure sensor 4 and the control cavity, which is used to ensure that there is no leakage at the position where the pressure sensor 4 is connected to the slide valve.

[0034] Further, the pressure sensor 4 is provided with a pressure electrical interface 6, and the fault diagnosis module 17 is electrically connected with the pressure sensor 4 through the pressure electrical interface 6. In addition to transmitting the signal of the real-time pressure to the fault diagnosis module 17, the pressure electrical interface 6 also supplies power to the pressure sensor 4 by using the power provided by the fault diagnosis module 17. The pressure sensor 4, the sealing structure 5 and the pressure electrical interface 6 constitute the pressure monitoring module 12.

[0035] Further, the shell 7 is provided with a displacement electrical interface 10, and the fault diagnosis module 17 is electrically connected with the displacement sensor 9 through the displacement electrical interface 10. Similarly to the pressure electrical interface 6, in addition to transmitting the signal of the real-time displacement to the fault diagnosis module 17, the displacement electrical interface 10 also supplies power to the displacement sensor 9 by using the power provided by the fault diagnosis module 17.

[0036] Specifically, the permanent magnet 11 is in a ring structure, and two ring-shaped magnets can be stacked with opposite poles, such as being connected together by using adhesives, to form the permanent magnet 11, so as to enhance the magnetic force. After the permanent magnet 11 is installed at the end of the spool 3, the magnetic field generated by the permanent magnet 11 will propagate to the outside of the slide valve 1, and will generate a magnetic force on the synchronous ball 8. The synchronous ball 8 made of ferromagnetic metal will move synchronously with the permanent magnet 11 under the magnetic force, and since the permanent magnet 11 is installed at the end of the spool 3, the synchronous ball 8 will move synchronously with the spool 3. The displacement of the synchronous ball 8 can be measured to obtain the displacement of the spool 3. The shell 7, the synchronous ball 8, the displacement sensor 9 and the displacement electrical interface 10 constitute the displacement acquisition unit 13.

[0037] The fault diagnosis module 17 comprises a fault diagnosis electrical interface 15 and a solving module 16, which is electrically connected with the pressure sensor 4 and the displacement sensor 9 respectively through the fault diagnosis electrical interface 15.

[0038] Specifically, the solving module 16 can be a computer, and the fault diagnosis electrical interface 15 is used to receive the signals of real-time pressure and real-time displacement, and also to supply power for the pressure sensor 4 and the displacement sensor 9.

[0039] The neural network adopts one of a convolutional neural network, a recurrent neural network and a long short-term memory network.

[0040] The displacement sensor 9 adopts one of a laser displacement sensor, a laser ranging sensor, an eddy current displacement sensor, a capacitive displacement sensor and an optical fiber displacement sensor.

[0041] The embodiment of the present application also provides a fault diagnosis method for the spool type hydraulic valve, as shown in the figure, the method comprises the following steps: Figure 2

[0042] S200, acquiring real-time pressure and real-time displacement collected by the pressure sensor and the displacement sensor respectively;

[0043] S210, determining real-time speed of the valve core 3 according to the real-time displacement;

[0044] S220, extracting feature information of the real-time pressure and the real-time speed;

[0045] S230, inputting the feature information into a diagnosis model to obtain a fault diagnosis result of the spool 1.

[0046] Exemplarily, after the real-time pressure and the real-time displacement are obtained, the real-time pressure and the real-time displacement are also subjected to filtering processing, and one of an inertial filtering algorithm, a mean filtering algorithm and a Kalman filtering algorithm is adopted during the filtering processing.

[0047] The real-time displacement is subjected to differential processing to obtain the real-time speed, and one of a forward difference method, a backward difference method and a bilinear transformation method is adopted during the differential processing.

[0048] ​It should be understood that steps S220 and S230 are both performed in the diagnostic model. Taking a long short-term memory network as an example, the process of the diagnostic model for fault diagnosis according to the real-time pressure and the real-time speed is as follows: (1) normalizing the real-time pressure and the real-time speed; (2) inputting the normalized real-time pressure and the real-time speed into an input gate of the trained long short-term memory network; (3) classifying the output result of the long short-term memory network into: a good slide valve, a low control cavity pressure, a low control cavity pressure, a very low control cavity pressure, a slight valve core jam, a moderate valve core jam, a serious valve core jam, and a valve core jam; (4) the long short-term memory network judges whether the slide valve has a fault and the degree of the fault according to the input real-time pressure and the real-time speed.

[0049] Further, after obtaining the fault diagnosis result, the diagnostic model can classify the fault diagnosis result into one of three categories, four categories, and five categories according to the severity of the fault.

[0050] Although the preferred embodiments of the present application have been described, those skilled in the art can make further changes and modifications to the embodiments once they know the basic inventive concept. Therefore, the appended claims are intended to cover all changes and modifications falling within the scope of the present application.

[0051] Obviously, those skilled in the art can make various modifications and variations 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 fall within the scope of the claims of the present application and their equivalent technologies, the present application also intends to include these modifications and variations.

Claims

1. A fault diagnosis system for spool valves of hydraulic valve type, characterized in that, The pressure sensor (4) is arranged on the control cavity of the spool valve (1), and is used to collect real-time pressure in the control cavity. The displacement monitoring module (14) comprises a shell (7), a synchronous ball (8), a displacement sensor (9) and a permanent magnet (11), the permanent magnet (11) is arranged at the end of the spool (3), the shell (7) is arranged on the spool valve (1) close to the permanent magnet (11), the synchronous ball (8) is located in the shell (7), the synchronous ball (8) moves synchronously with the spool (3) inside the shell (7) under the magnetic force of the permanent magnet (11), and the displacement sensor (9) is used to collect real-time displacement of the synchronous ball (8). The fault diagnosis module (17) is electrically connected with the pressure sensor (4) and the displacement sensor (9) respectively, and the fault diagnosis module (17) diagnoses the fault of the spool valve (1) according to the real-time pressure and the real-time displacement by using a diagnosis model established based on a neural network. One end of the pressure sensor (4) is inserted into the control cavity, and a sealing structure (5) is arranged between the pressure sensor (4) and the control cavity.

2. The fault diagnosis system for a spool valve type hydraulic valve according to claim 1, characterized by A pressure electrical interface (6) is arranged on the pressure sensor (4), and the fault diagnosis module (17) is electrically connected with the pressure sensor (4) through the pressure electrical interface (6).

3. The fault diagnosis system for a spool valve type hydraulic valve according to claim 1, characterized by A displacement electrical interface (10) is arranged on the shell (7), and the fault diagnosis module (17) is electrically connected with the displacement sensor (9) through the displacement electrical interface (10).

4. The fault diagnosis system for a spool valve type hydraulic valve according to claim 1, characterized by The fault diagnosis module (17) comprises a fault diagnosis electrical interface (15) and a solving module (16), and the solving module (16) is electrically connected with the pressure sensor (4) and the displacement sensor (9) respectively through the fault diagnosis electrical interface (15).

5. The fault diagnosis system for a spool valve type hydraulic valve according to claim 1, characterized by The neural network adopts one of a convolutional neural network, a recurrent neural network and a long short-term memory network.

6. The fault diagnosis system for a spool valve type hydraulic valve according to claim 1, characterized by The displacement sensor (9) adopts one of a laser displacement sensor, a laser ranging sensor, an eddy current displacement sensor, a capacitive displacement sensor and a fiber optic displacement sensor.

7. The fault diagnosis system for a spool valve type hydraulic valve according to claim 1, characterized by The real-time pressure collected by the pressure sensor and the real-time displacement collected by the displacement sensor are acquired respectively.

8. A method for diagnosing faults of a hydraulic valve of the spool type, the method being applied to a system for diagnosing faults of a hydraulic valve of the spool type according to any one of claims 1 to 7, characterized in that, The real-time speed of the spool (3) is determined according to the real-time displacement. The feature information of the real-time pressure and the real-time speed is extracted. The feature information is input into the diagnosis model to obtain the fault diagnosis result of the spool valve (1). After the real-time pressure and the real-time displacement are obtained, the real-time pressure and the real-time displacement are further subjected to filtering processing, and one of an inertial filtering algorithm, a mean filtering algorithm and a Kalman filtering algorithm is adopted during filtering processing. The real-time displacement is subjected to differential processing to obtain the real-time speed, and one of a forward difference method, a backward difference method and a bilinear transformation method is adopted during differential processing.

9. The fault diagnosis method of a slide valve type hydraulic valve according to claim 8, characterized by ​ 10. The method of claim 8, wherein the method further comprises: ​

Images