Abnormality detection method for reducing valve of fan hydraulic system, storage medium and electronic equipment

Abstract

The invention provides a fan hydraulic system pressure reducing valve abnormity detection method, a storage medium and electronic equipment, and the method comprises the steps: obtaining the working state data of a to-be-detected pressure reducing valve, the working state data comprising an inlet pressure value, an outlet pressure value, an inlet temperature value and an outlet temperature value; inputting the working state data into a preset fault identification model, and determining whether the to-be-tested pressure reducing valve has a fault according to the output of the fault identification model; the fault identification model is obtained through training according to historical state data of the fan hydraulic system pressure reducing valve in advance, the historical state data takes an inlet pressure value sample, an outlet pressure value sample, an inlet temperature value sample and an outlet temperature value sample as input data, and takes whether the running state of the fan hydraulic system pressure reducing valve has a fault as output data. According to the scheme, the fault of the to-be-tested pressure reducing valve of the fan hydraulic system is automatically recognized through the working state data collected in real time and the model obtained through training, and therefore the operation efficiency and safety of the fan system are improved.

Description

Technical Field

[0001] The present application relates to the technical field of wind power equipment, and in particular to a method for detecting abnormality of a pressure reducing valve in a hydraulic system of a wind turbine, a storage medium, and an electronic device. Background Art

[0002] Fan hydraulic systems are widely used in wind turbines to assist in hydraulic drive tasks such as blade adjustment and yaw control. Pressure reducing valves are crucial components for regulating the hydraulic system's pressure. They regulate and maintain the system's operating pressure, ensuring stable operation. Pressure reducing valves regulate pressure by controlling the pressure difference between the valve inlet and outlet, thereby ensuring the proper functioning of the fan's hydraulic system.

[0003] However, after long-term use, pressure relief valves can malfunction due to factors such as valve core wear, spring fatigue, and internal contamination. If these faults go undetected, they can lead to uncontrolled pressure in the fan hydraulic system and even damage other critical components, resulting in fan shutdown or equipment damage. Currently, fault detection of pressure relief valves in fan hydraulic systems requires manual inspection and regular maintenance, which lacks real-time performance and provides no early warning of faults. Summary of the Invention

[0004] The technical problem to be solved by this application is that the existing technology of pressure reducing valve fault detection in the fan hydraulic system has poor real-time performance and cannot issue advance warnings, and thus provides a method, storage medium and electronic equipment for detecting abnormalities of the pressure reducing valve in the fan hydraulic system.

[0005] In a first aspect, the technical solution of the present application provides a method for detecting abnormality of a pressure reducing valve in a fan hydraulic system, comprising:

[0006] Acquire working state data of the pressure reducing valve to be tested, wherein the working state data includes an inlet pressure value, an outlet pressure value, an inlet temperature value, and an outlet temperature value;

[0007] The working status data is input into a preset fault identification model, and whether the pressure reducing valve to be tested has a fault is determined based on the output of the fault identification model; the fault identification model is pre-trained based on the historical status data of the pressure reducing valve of the fan hydraulic system, and the historical status data uses inlet pressure value samples, outlet pressure value samples, inlet temperature value samples and outlet temperature value samples as input data, and whether there is a fault in the operating status of the pressure reducing valve of the fan hydraulic system is output data.

[0008] Preferably, in some embodiments of the method for detecting abnormality of a pressure reducing valve in a fan hydraulic system, inputting the working status data into a preset fault identification model, and determining whether the pressure reducing valve to be tested has a fault based on an output of the fault identification model, comprises:

[0009] The fault identification model determines whether the inlet pressure value and / or the outlet pressure value exceeds a set pressure threshold, and if so, outputs that the pressure reducing valve to be tested has a fault; and / or,

[0010] The fault identification model determines whether the inlet temperature value and / or the outlet temperature value exceeds a set temperature threshold, and if so, outputs that the pressure reducing valve to be tested has a fault.

[0011] Preferably, in some embodiments of the method for detecting abnormality of a pressure reducing valve in a fan hydraulic system, the operating status data is input into a preset fault identification model, and whether the pressure reducing valve to be tested is faulty is determined based on the output of the fault identification model. The fault identification model is further used to:

[0012] Calculating the outlet pressure fluctuation value of the pressure reducing valve to be tested according to the outlet pressure value detected within a certain period of time;

[0013] Calculating the standard deviation of the outlet pressure fluctuation value according to the outlet pressure fluctuation value;

[0014] If the standard deviation of the outlet pressure fluctuation value is greater than the standard deviation reference value, it is output that the pressure reducing valve to be tested has a fault, and the fault type is confirmed to be reduced accuracy or delayed response.

[0015] Preferably, in some embodiments of the method for detecting abnormality of a pressure reducing valve in a fan hydraulic system, the operating status data is input into a preset fault identification model, and whether the pressure reducing valve to be tested is faulty is determined based on the output of the fault identification model. The fault identification model is further used to:

[0016] Acquire multiple peak values ​​of the outlet pressure values ​​detected within the time period;

[0017] comparing each of the peak values ​​with a reference peak value to determine the number of times the outlet pressure value exceeds the reference peak value;

[0018] If the number of times exceeds the set safety number threshold, it is output that the pressure reducing valve to be tested has a fault, and the fault type is confirmed to be pressure regulation failure.

[0019] Preferably, in some embodiments of the method for detecting abnormality of a pressure reducing valve in a fan hydraulic system, the operating status data is input into a preset fault identification model, and whether the pressure reducing valve to be tested is faulty is determined based on the output of the fault identification model. The fault identification model is further used to:

[0020] Obtaining the fluctuation frequency of the outlet pressure value detected within the time period;

[0021] If the fluctuation frequency exceeds the set safety frequency threshold, it is output that the pressure reducing valve to be tested has a fault, and the fault type is confirmed to be a precursor to pressure regulation failure.

[0022] Preferably, in some embodiments of the method for detecting abnormality of a pressure reducing valve in a fan hydraulic system, the operating status data is input into a preset fault identification model, and whether the pressure reducing valve to be tested is faulty is determined based on the output of the fault identification model. The fault identification model is further used to:

[0023] Calculating the rate of change and / or amplitude of change of the outlet temperature of the pressure reducing valve to be tested according to the outlet temperature values ​​detected within a certain period of time;

[0024] If the change rate exceeds the reference temperature change rate and / or the change amplitude exceeds the reference temperature change amplitude, it is output that the pressure reducing valve to be tested has a fault, and the fault type is confirmed to be a stuck or clogged pressure reducing valve.

[0025] Preferably, the method for detecting abnormality of a pressure reducing valve in a fan hydraulic system described in some solutions further includes:

[0026] Using the working state data of the pressure reducing valve to be tested and the detection result of whether the pressure reducing valve to be tested has a fault as new historical state data;

[0027] The fault identification model is retrained using the new historical state data and the original historical state data according to a set period.

[0028] In a second aspect, the technical solution of the present application provides a device for detecting abnormality of a pressure reducing valve in a hydraulic system of a fan, comprising:

[0029] A pressure sensor is provided at the inlet and outlet of the pressure reducing valve to be tested, and is used to detect the inlet pressure value and the outlet pressure value of the pressure reducing valve to be tested;

[0030] Temperature sensors are provided at the inlet and outlet of the pressure reducing valve to be tested, and are used to detect the inlet temperature value and the outlet temperature value of the pressure reducing valve to be tested;

[0031] a data acquisition module, receiving the detection data sent by the pressure sensor and the temperature sensor, and acquiring the working status data of the pressure reducing valve to be tested, wherein the working status data includes an inlet pressure value, an outlet pressure value, an inlet temperature value, and an outlet temperature value;

[0032] A data analysis module has a built-in fault identification model, which inputs the working status data into the fault identification model, and determines whether the pressure reducing valve to be tested has a fault based on the output of the fault identification model; the fault identification model is pre-trained based on the historical status data of the pressure reducing valve of the fan hydraulic system, and the historical status data uses inlet pressure value samples, outlet pressure value samples, inlet temperature value samples and outlet temperature value samples as input data, and uses whether the operating status of the pressure reducing valve of the fan hydraulic system has a fault as output data.

[0033] In a third aspect, the technical solution of the present application provides a computer-readable storage medium, in which program information is stored. After the computer reads the program information, the computer executes the steps of the abnormality detection method of the pressure reducing valve of the fan hydraulic system described in any technical solution of the first aspect.

[0034] In a fourth aspect, the technical solution of the present application provides an electronic device comprising a memory, a processor and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the method for detecting an abnormality of a pressure reducing valve in a fan hydraulic system as described in any one of the technical solutions of the first aspect.

[0035] Compared with the existing technology, the above technical solution provided by this application has the following technical effects:

[0036] The present application provides a method, storage medium, and electronic device for detecting abnormalities in a pressure reducing valve of a fan hydraulic system. The method acquires the operating status data of the pressure reducing valve to be tested, and processes the operating status data according to a pre-trained fault identification model to determine whether the pressure reducing valve to be tested has a fault. When training the fault identification model, the historical status data of the pressure reducing valve of the fan hydraulic system is used as samples, with inlet pressure value samples, outlet pressure value samples, inlet temperature value samples, and outlet temperature value samples as input data, and the output data is whether the operating status of the pressure reducing valve of the fan hydraulic system has a fault. Therefore, when the pressure reducing valve to be tested is actually tested, the operating status data also includes the inlet pressure value, outlet pressure value, inlet temperature value, and outlet temperature value. By inputting the inlet pressure value, outlet pressure value, inlet temperature value, and outlet temperature value into the fault identification model, it is possible to determine whether the pressure reducing valve to be tested has a fault. The above-mentioned scheme of the present application automatically identifies faults in the pressure reducing valve to be tested in the fan hydraulic system by combining the real-time collected operating status data with the trained model, thereby improving the operating efficiency and safety of the fan system. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 This is a flow chart of a method for detecting abnormality of a pressure reducing valve in a fan hydraulic system according to an embodiment of the present application;

[0038] Figure 2This is a schematic diagram of sample data classification for model training during detection of a pressure reducing valve in a fan hydraulic system according to one embodiment of the present application;

[0039] Figure 3 This is a structural diagram of a device for detecting abnormality of a pressure reducing valve in a fan hydraulic system according to an embodiment of the present application;

[0040] Figure 4 This is a schematic diagram of the hardware connection relationship of an electronic device that executes the method for detecting abnormalities in a pressure reducing valve of a fan hydraulic system according to an embodiment of the present application. DETAILED DESCRIPTION

[0041] The specific implementation of this application is further described below with reference to the accompanying drawings.

[0042] It is easy to understand that according to the technical solution of this application, a variety of structural methods and implementation methods can be replaced with each other by those skilled in the art without changing the essential spirit of this application. Therefore, the following specific embodiments and drawings are only exemplary descriptions of the technical solution of this application and should not be regarded as the entire application or as a limitation or restriction of the technical solution of the application.

[0043] This embodiment provides a method for detecting abnormality of a pressure reducing valve in a fan hydraulic system, and the execution subject thereof may be a controller of the fan hydraulic system, such as Figure 1 As shown, the method includes:

[0044] S100: Acquire working status data of the pressure reducing valve to be tested, wherein the working status data includes an inlet pressure value, an outlet pressure value, an inlet temperature value, and an outlet temperature value.

[0045] In this step, the working status data can be obtained by detecting sensors set in the fan hydraulic system, such as setting a pressure sensor to detect the inlet pressure value and outlet pressure value of the pressure reducing valve to be tested, and setting a temperature sensor to detect the inlet temperature value and outlet temperature value of the pressure reducing valve to be tested. The controller obtains the required working status data by receiving the detection signal of the sensor.

[0046] S200: Inputting the working status data into a preset fault identification model, and determining whether the pressure reducing valve to be tested has a fault according to an output of the fault identification model.

[0047] The fault identification model is pre-trained based on the historical status data of the pressure reducing valve of the fan hydraulic system. The historical status data uses inlet pressure value samples, outlet pressure value samples, inlet temperature value samples and outlet temperature value samples as input data, and whether there is a fault in the operating status of the pressure reducing valve of the fan hydraulic system as output data.

[0048] The fault identification model is an algorithm model based on machine learning and statistical analysis methods. By using known historical status data to train the algorithm model, a fault identification model that can be used for fault detection of the pressure reducing valve in the fan hydraulic system is obtained, and then it is pre-stored in the controller. The above algorithm model is implemented by an existing machine learning algorithm model. In this solution, a machine learning model based on a classification algorithm is preferred. When it is specifically implemented, a machine learning model of a support vector machine is selected. By training a large amount of normal working status data and fault working status data, a classifier is constructed to perform fault judgment on real-time data. Figure 2 The figure shows a sample data classification diagram for model training during the inspection of the pressure reducing valve in the fan hydraulic system (the horizontal axis represents pressure, the vertical axis represents temperature, and the outlet pressure and temperature are used as examples in this figure). The red and yellow point data are both training data, with the red point data corresponding to the normal working state data of the pressure reducing valve, and the yellow point data corresponding to the abnormal working state data of the pressure reducing valve. The blue and green point data are test data, with the blue point data corresponding to the normal data of the pressure reducing valve, and the green point data corresponding to the abnormal working state data of the pressure reducing valve. The machine learning model of the support vector machine is trained with a large amount of training data, and after testing, the decision boundary in the machine learning model of the support vector machine can be determined, that is, the boundary corresponding to the black circle in the figure. In this way, after the actual working state data of the pressure reducing valve to be tested is input, the working state data can be divided according to the decision boundary and classified into normal data or fault data.

[0049] The historical status data is collected by collecting the working status data of the pressure reducing valve in the historical period, and then preprocessing the working status data of the pressure reducing valve to remove noise and abnormal data, and perform data smoothing and normalization to ensure the accuracy and consistency of the input data. The preprocessing process includes:

[0050] Filtering: Use filtering algorithm (mean filtering) to remove noise data in the working status data of the pressure reducing valve to ensure the stability of the working status data of the pressure reducing valve.

[0051] Outlier detection: Identify and eliminate invalid pressure reducing valve working status data to avoid affecting model analysis results.

[0052] Missing value filling: Use interpolation methods (such as linear interpolation or spline interpolation) to fill in missing pressure reducing valve working status data points to avoid the impact of missing data on algorithm performance.

[0053] The scheme in the above embodiment obtains the working status data of the pressure reducing valve to be tested, and processes the working status data according to the pre-trained fault identification model to realize the judgment of whether the pressure reducing valve to be tested has a fault. When training the fault identification model, the historical status data of the pressure reducing valve of the fan hydraulic system is used as a sample, the inlet pressure value sample, the outlet pressure value sample, the inlet temperature value sample and the outlet temperature value sample are used as input data, and the output data is whether the operating status of the pressure reducing valve of the fan hydraulic system has a fault. Therefore, when the pressure reducing valve to be tested is actually tested, the working status data also includes the inlet pressure value, the outlet pressure value, the inlet temperature value and the outlet temperature value. By inputting the inlet pressure value, the outlet pressure value, the inlet temperature value and the outlet temperature value into the fault identification model, it can be determined whether the pressure reducing valve to be tested has a fault. This scheme automatically identifies the fault of the pressure reducing valve to be tested in the fan hydraulic system through the real-time collected working status data and the trained model, thereby improving the operating efficiency and safety of the fan system.

[0054] Furthermore, in the above-mentioned method for detecting abnormalities in a pressure reducing valve in a fan hydraulic system, in step S200, the operating status data is input into a preset fault identification model, and determining whether the pressure reducing valve under test is faulty based on the output of the fault identification model includes: the fault identification model determining whether the inlet pressure value and / or the outlet pressure value exceed a set pressure threshold, and if so, outputting that the pressure reducing valve under test is faulty; and / or the fault identification model determining whether the inlet temperature value and / or the outlet temperature value exceed a set temperature threshold, and if so, outputting that the pressure reducing valve under test is faulty. The core function of a pressure reducing valve is to control the system pressure value within a safe range. Typically, detecting the outlet pressure value is more critical. However, since the inlet and outlet pressure values ​​should have a certain transformation relationship, detecting whether the pressure reducing valve is faulty can also be used to determine whether the pressure reducing valve is faulty. For example, when the pressure reducing valve is clogged, the outlet pressure value will become unstable, but the inlet pressure value will also be affected. In the above-mentioned scheme of the present application, by comparing the operating status data with the set threshold value under normal operating conditions, it is possible to accurately and quickly determine whether the pressure reducing valve under test is faulty.

[0055] Preferably, in some solutions, in step S200, the fault identification model is further used to:

[0056] S201: Calculating the outlet pressure fluctuation value of the pressure reducing valve to be tested according to the outlet pressure value detected within a certain period of time.

[0057] The time period, such as two hours, half a day, etc., can be set according to actual needs. The fluctuation value can be calculated by calculating the difference between the outlet pressure values ​​of adjacent periods, or by calculating the difference between the maximum and minimum values ​​within a certain period (such as one minute).

[0058] S202: Calculating the standard deviation of the outlet pressure fluctuation value according to the outlet pressure fluctuation value.

[0059] According to the standard deviation calculation formula, the degree of deviation of each outlet pressure value from the average value of the outlet pressure values ​​within the time period is calculated to obtain the standard deviation of the outlet pressure fluctuation value.

[0060] S203: If the standard deviation of the outlet pressure fluctuation value is greater than the standard deviation reference value, outputting that the pressure reducing valve to be tested has a fault, and confirming that the fault type is reduced accuracy or delayed response.

[0061] The standard deviation describes the degree to which the outlet pressure data deviates from the mean. Larger values ​​indicate more dramatic fluctuations and greater instability. If the standard deviation is significantly greater than the baseline standard deviation for normal system operation, the pressure reducing valve's adjustment accuracy may be reduced, potentially leading to problems such as jamming and delayed response.

[0062] Furthermore, in step S200, the fault identification model is further used to:

[0063] S204: Acquire multiple peak values ​​of the outlet pressure values ​​detected within the time period.

[0064] S205: Compare the relationship between each peak value and the reference peak value, and determine the number of times the outlet pressure value exceeds the reference peak value.

[0065] S206: If the number exceeds the set safety number threshold, output that the pressure reducing valve to be tested has a fault, and confirm that the fault type is pressure regulation failure.

[0066] The core function of a pressure reducing valve is to control system pressure within a safe range. If the peak value of the outlet pressure frequently exceeds the reference peak value, or even far exceeds the maximum peak value of the reference fluctuation, it indicates that the pressure reducing valve is unable to regulate pressure, and there is a risk of not being able to release pressure in time, which may cause overpressure damage to the system.

[0067] Furthermore, in step S200, the fault identification model is further used to:

[0068] S207: Obtain the fluctuation frequency of the outlet pressure value detected within the time period.

[0069] S208: If the fluctuation frequency exceeds the set safety frequency threshold, outputting that the pressure reducing valve to be tested has a fault, and confirming that the fault type is a precursor to pressure regulation failure.

[0070] Under normal circumstances, the pressure reducing valve will slightly adjust the outlet pressure value according to pressure changes, so the frequency of outlet pressure fluctuations should be stable and low. If the frequency suddenly increases, it means that the pressure is frequently exceeding the adjustment range, and the pressure reducing valve needs to operate repeatedly but cannot stabilize. This may be a precursor to regulation failure caused by valve core wear, insufficient spring elasticity, etc.

[0071] Furthermore, in step S200, the fault identification model is further used to:

[0072] S209: Calculating the rate of change and / or amplitude of change of the outlet temperature of the pressure reducing valve to be tested according to the outlet temperature values ​​detected within a certain period of time.

[0073] S210: If the change rate exceeds the reference temperature change rate and / or the change amplitude exceeds the reference temperature change amplitude, outputting that the pressure reducing valve to be tested has a fault, and confirming the fault type as the pressure reducing valve being stuck or clogged.

[0074] Excessive system oil temperature may be caused by leakage or internal friction of the pressure reducing valve. The rate of change and / or amplitude of the oil temperature change can be used to determine whether the pressure reducing valve is working properly.

[0075] In the above scheme, when the pressure reducing valve to be tested fails, it may be prompted that the pressure reducing valve needs to be readjusted or the pressure reducing valve needs to be replaced.

[0076] Preferably, the method for detecting abnormality of a pressure reducing valve in a fan hydraulic system further includes:

[0077] S300: Using the working status data of the pressure reducing valve to be tested and the detection result of whether the pressure reducing valve to be tested has a fault as new historical status data.

[0078] S400: retraining the fault recognition model using the new historical state data and the original historical state data according to a set period.

[0079] That is, the collected working status data is used as new historical status data and new sample data, and the fault recognition model is updated and learned in a timely manner by continuously expanding the training samples, thereby improving the fault recognition model's ability to recognize new fault types.

[0080] The embodiment of the present application also provides a device for detecting abnormality of a pressure reducing valve of a fan hydraulic system, such as Figure 3 As shown, including:

[0081] The pressure sensor 31 is provided at the inlet and outlet of the pressure reducing valve to be tested, and is used to detect the inlet pressure value and the outlet pressure value of the pressure reducing valve to be tested;

[0082] Temperature sensors 32 are provided at the inlet and outlet of the pressure reducing valve to be tested, and are used to detect the inlet temperature value and the outlet temperature value of the pressure reducing valve to be tested;

[0083] The data acquisition module 33 receives the detection data sent by the pressure sensor and the temperature sensor, and obtains the working status data of the pressure reducing valve to be tested, wherein the working status data includes the inlet pressure value, the outlet pressure value, the inlet temperature value and the outlet temperature value;

[0084] Data analysis module 34 includes a built-in fault identification model. The operating status data is input into the fault identification model, and the output of the fault identification model determines whether the pressure reducing valve under test is faulty. The fault identification model is pre-trained based on historical status data of the pressure reducing valve in the fan hydraulic system. The historical status data uses inlet pressure, outlet pressure, inlet temperature, and outlet temperature samples as input data, and outputs whether the operating status of the pressure reducing valve in the fan hydraulic system is faulty. The fault identification model is an algorithmic model implemented using machine learning and statistical analysis methods. By training the algorithmic model using known historical status data, a fault identification model is obtained that can be used for fault detection of pressure reducing valves in fan hydraulic systems.

[0085] The device in the above embodiment automatically identifies the fault of the pressure reducing valve to be tested in the fan hydraulic system by combining the real-time collected working status data with the trained model, thereby improving the operating efficiency and safety of the fan system.

[0086] Furthermore, in data analysis module 34, the fault identification model determines whether the inlet pressure value and / or the outlet pressure value exceed a set pressure threshold, and if so, outputs a fault in the pressure reducing valve under test. The fault identification model also determines whether the inlet temperature value and / or the outlet temperature value exceed a set temperature threshold, and if so, outputs a fault in the pressure reducing valve under test. This solution accurately and quickly determines whether the pressure reducing valve under test is faulty by comparing the operating status data with the set threshold under normal operating conditions.

[0087] Furthermore, in the data analysis module 34, the fault identification model is also used to:

[0088] According to the outlet pressure value detected within a certain time period, the outlet pressure fluctuation value of the pressure reducing valve to be tested is calculated; according to the outlet pressure fluctuation value, the standard deviation of the outlet pressure fluctuation value is calculated; if the standard deviation of the outlet pressure fluctuation value is greater than the standard deviation reference value, it is output that the pressure reducing valve to be tested has a fault, and the fault type is confirmed to be a decrease in accuracy or a delayed response; multiple peak values ​​of the outlet pressure value detected within the time period are obtained; the relationship between each peak value and the reference peak value is compared to determine the number of times the outlet pressure value exceeds the reference peak value; if the number exceeds a set safety number threshold, it is output that the pressure reducing valve to be tested has a fault, and the fault type is confirmed to be a pressure regulation failure. The fluctuation frequency of the outlet pressure value detected within the time period is obtained; if the fluctuation frequency exceeds a set safety frequency threshold, it is output that the pressure reducing valve to be tested has a fault, and the fault type is confirmed to be a precursor to pressure regulation failure. Based on the outlet temperature values ​​detected within a certain time period, the rate of change and / or amplitude of change of the outlet temperature of the pressure reducing valve under test are calculated. If the rate of change exceeds the rate of change of a reference temperature and / or the amplitude of change exceeds the amplitude of change of the reference temperature, a fault is outputted in the pressure reducing valve under test, and the fault type is confirmed to be a stuck or clogged pressure reducing valve. This solution can automatically identify various pressure reducing valve faults.

[0089] Preferably, the data analysis module 34 is further configured to use the operating status data of the pressure reducing valve under test and the detection result of whether the pressure reducing valve under test is faulty as new historical status data; and to retrain the fault identification model using the new historical status data and the original historical status data at a predetermined period. This solution uses the collected operating status data as new historical status data and new sample data, and timely updates and learns the fault identification model by continuously expanding the training sample, thereby improving the fault identification model's ability to identify new fault types.

[0090] An embodiment of the present application further provides a computer-readable storage medium, wherein program information is stored in the storage medium. After a computer reads the program information, the computer executes the steps of the method for detecting abnormality of a pressure reducing valve in a fan hydraulic system as described in any one of the above method embodiments.

[0091] The present application also provides an electronic device, such as Figure 4As shown, the electronic device includes at least one processor 41 and at least one memory 42. At least one memory 42 stores program information. After reading the program information, the at least one processor 41 executes the method for detecting abnormalities in a pressure reducing valve in a fan hydraulic system as described in any of the above method embodiments. The device may also include an input device 43 and an output device 44. The processor 41, memory 42, input device 43, and output device 44 are communicatively connected. Memory 42, as a non-volatile computer-readable storage medium, can be used to store non-volatile software programs, non-volatile computer-executable programs, and modules. By running the non-volatile software programs, instructions, and modules stored in memory 42, the processor 41 executes various functional applications and processes data, thereby implementing the method for detecting abnormalities in a pressure reducing valve in a fan hydraulic system as described in any of the above method embodiments. Memory 42 may include a program storage area and a data storage area. The program storage area may store an operating system and at least one application required for the function; the data storage area may store data generated by the method for detecting abnormalities in a pressure reducing valve in a fan hydraulic system. In addition, the memory 42 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some embodiments, the memory 42 may optionally include a memory remotely located relative to the processor 41, and these remote memories may be connected to a device for executing the abnormality detection method for the fan hydraulic system pressure reducing valve via a network. Examples of the above-mentioned network include but are not limited to the Internet, corporate intranet, local area network, mobile communication network and a combination thereof. The input device 43 may receive input user clicks and generate signal inputs related to user settings and function controls of the abnormality detection method for the fan hydraulic system pressure reducing valve. The output device 44 may include a display device such as a display screen. When the one or more modules are stored in the memory 42 and are executed by the one or more processors 41, the abnormality detection method for the fan hydraulic system pressure reducing valve in any of the above-mentioned method embodiments is executed.

[0092] As needed, the above technical solutions can be combined to achieve the best technical effect.

[0093] The above are only the principles and preferred embodiments of the present application. It should be noted that, for those skilled in the art, on the basis of the principles of the present application, several other modifications can be made, which should also be considered as the scope of protection of the present application.

Claims

1. A method for detecting abnormality of a pressure reducing valve in a fan hydraulic system, characterized in that: include: Acquire working state data of the pressure reducing valve to be tested, wherein the working state data includes an inlet pressure value, an outlet pressure value, an inlet temperature value, and an outlet temperature value; Inputting the working state data into a preset fault identification model, and determining whether the pressure reducing valve to be tested has a fault according to the output of the fault identification model; The fault identification model is pre-trained based on the historical status data of the pressure reducing valve of the fan hydraulic system. The historical status data uses inlet pressure value samples, outlet pressure value samples, inlet temperature value samples and outlet temperature value samples as input data, and whether there is a fault in the operating status of the pressure reducing valve of the fan hydraulic system as output data.

2. The method for detecting abnormality of a pressure reducing valve in a fan hydraulic system according to claim 1, characterized in that: Inputting the working status data into a preset fault identification model, and determining whether the pressure reducing valve to be tested has a fault according to an output of the fault identification model, includes: The fault identification model determines whether the inlet pressure value and / or the outlet pressure value exceeds a set pressure threshold, and if so, outputs that the pressure reducing valve to be tested has a fault; and / or, The fault identification model determines whether the inlet temperature value and / or the outlet temperature value exceeds a set temperature threshold, and if so, outputs that the pressure reducing valve to be tested has a fault.

3. The method for detecting abnormality of a pressure reducing valve in a fan hydraulic system according to claim 2, characterized in that: The working state data is input into a preset fault identification model, and it is determined whether the pressure reducing valve to be tested is faulty according to the output of the fault identification model. The fault identification model is further used to: Calculating the outlet pressure fluctuation value of the pressure reducing valve to be tested according to the outlet pressure value detected within a certain period of time; Calculating the standard deviation of the outlet pressure fluctuation value according to the outlet pressure fluctuation value; If the standard deviation of the outlet pressure fluctuation value is greater than the standard deviation reference value, it is output that the pressure reducing valve to be tested has a fault, and the fault type is confirmed to be reduced accuracy or delayed response.

4. The method for detecting abnormality of a pressure reducing valve in a fan hydraulic system according to claim 3, characterized in that: The working state data is input into a preset fault identification model, and it is determined whether the pressure reducing valve to be tested is faulty according to the output of the fault identification model. The fault identification model is further used to: Acquire multiple peak values ​​of the outlet pressure values ​​detected within the time period; comparing each of the peak values ​​with a reference peak value to determine the number of times the outlet pressure value exceeds the reference peak value; If the number of times exceeds the set safety number threshold, it is output that the pressure reducing valve to be tested has a fault, and the fault type is confirmed to be pressure regulation failure.

5. The method for detecting abnormality of a pressure reducing valve in a fan hydraulic system according to claim 3, characterized in that: The working state data is input into a preset fault identification model, and it is determined whether the pressure reducing valve to be tested is faulty according to the output of the fault identification model. The fault identification model is further used to: Obtaining the fluctuation frequency of the outlet pressure value detected within the time period; If the fluctuation frequency exceeds the set safety frequency threshold, it is output that the pressure reducing valve to be tested has a fault, and the fault type is confirmed to be a precursor to pressure regulation failure.

6. The method for detecting abnormality of a pressure reducing valve in a fan hydraulic system according to claim 2, characterized in that: The working state data is input into a preset fault identification model, and it is determined whether the pressure reducing valve to be tested is faulty according to the output of the fault identification model. The fault identification model is further used to: Calculating the rate of change and / or amplitude of change of the outlet temperature of the pressure reducing valve to be tested according to the outlet temperature values ​​detected within a certain period of time; If the change rate exceeds the reference temperature change rate and / or the change amplitude exceeds the reference temperature change amplitude, it is output that the pressure reducing valve to be tested has a fault, and the fault type is confirmed to be a stuck or clogged pressure reducing valve.

7. The method for detecting abnormality of a pressure reducing valve in a fan hydraulic system according to any one of claims 1 to 6, characterized in that: Also includes: Using the working state data of the pressure reducing valve to be tested and the detection result of whether the pressure reducing valve to be tested has a fault as new historical state data; The fault identification model is retrained using the new historical state data and the original historical state data according to a set period.

8. A device for detecting abnormality of a pressure reducing valve in a fan hydraulic system, characterized in that: include: A pressure sensor is provided at the inlet and outlet of the pressure reducing valve to be tested, and is used to detect the inlet pressure value and the outlet pressure value of the pressure reducing valve to be tested; Temperature sensors are provided at the inlet and outlet of the pressure reducing valve to be tested, and are used to detect the inlet temperature value and the outlet temperature value of the pressure reducing valve to be tested; a data acquisition module, receiving the detection data sent by the pressure sensor and the temperature sensor, and acquiring the working status data of the pressure reducing valve to be tested, wherein the working status data includes an inlet pressure value, an outlet pressure value, an inlet temperature value, and an outlet temperature value; A data analysis module, having a built-in fault identification model, inputs the working status data into the fault identification model, and determines whether the pressure reducing valve to be tested has a fault according to an output of the fault identification model; The fault identification model is pre-trained based on the historical status data of the pressure reducing valve of the fan hydraulic system. The historical status data uses inlet pressure value samples, outlet pressure value samples, inlet temperature value samples and outlet temperature value samples as input data, and whether there is a fault in the operating status of the pressure reducing valve of the fan hydraulic system as output data.

9. A computer-readable storage medium, characterized in that The storage medium stores program information, and after the computer reads the program information, it executes the steps of the method for detecting abnormality of a pressure reducing valve in a fan hydraulic system according to any one of claims 1 to 7.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory, wherein: The processor executes the computer program to implement the steps of the method for detecting abnormality of a pressure reducing valve in a fan hydraulic system according to any one of claims 1 to 7.

Images