A real-time diagnosis method, equipment, medium and product for sudden faults of electro-hydraulic proportional servo valves

Abstract

The present application discloses a real-time diagnostic method, equipment, medium, and product for sudden faults of an electro-hydraulic proportional servo valve, which relates to the field of hydraulic equipment fault diagnosis. The method includes stabilizing the operating status data acquired in real time, inputting the processed operating status data into an electro-hydraulic proportional servo valve state prediction model, and outputting a state prediction value of the electro-hydraulic proportional servo valve; obtaining a state deviation value based on the state prediction value and the actual state value of the electro-hydraulic proportional servo valve at the current moment, and determining whether the state deviation value exceeds a preset fault threshold; if not, determining that the electro-hydraulic proportional servo valve has not failed at the current moment; if so, determining that the electro-hydraulic proportional servo valve has failed at the current moment, and using a historical fault knowledge base and operating status data to determine the fault type of the electro-hydraulic proportional servo valve at the current moment, and completing fault diagnosis. The present application achieves real-time early warning and accurate diagnosis of faults, thereby improving fault detection efficiency.

Description

Technical Field

[0001] The present application relates to the field of hydraulic equipment fault diagnosis, and in particular to a real-time diagnosis method, equipment, medium and product for sudden faults of an electro-hydraulic proportional servo valve. Background Art

[0002] The electro-hydraulic proportional servo valve is a high-precision hydraulic component that integrates mechanical, electrical, and hydraulic functions. Its internal structure is complex and its cost is high. In most cases, the operating environment of the proportional servo valve is very harsh, making it a high-prone component in electro-hydraulic control systems. Its high precision and high integration make the types of failure complex and varied. Once a failure occurs, it not only seriously affects system operation but can also lead to significant financial losses. Therefore, when an electro-hydraulic proportional servo valve fails, being able to promptly and accurately locate the fault and assess the extent of the damage is crucial to avoid unnecessary full replacement and reduce repair costs.

[0003] Existing hydraulic valve fault detection methods mainly rely on manual subjective experience and oil detection methods. However, for electro-hydraulic proportional servo valves operating under complex and changeable external working conditions, sudden faults such as valve core sticking, control circuit short circuit, and control circuit open circuit are prone to occur. Traditional detection methods are unable to detect and handle such faults in real time, seriously affecting the stability of the hydraulic system and the continuity of operation.

[0004] Therefore, it is particularly urgent to develop a method that can monitor and diagnose sudden faults of electro-hydraulic proportional servo valves in real time. Summary of the Invention

[0005] The purpose of this application is to provide a real-time diagnosis method, equipment, medium and product for sudden faults of electro-hydraulic proportional servo valves, so as to solve the problem of low efficiency in sudden fault detection of electro-hydraulic proportional servo valves.

[0006] To achieve the above objectives, this application provides the following solutions:

[0007] In a first aspect, the present application provides a real-time diagnosis method for sudden faults of an electro-hydraulic proportional servo valve, comprising:

[0008] Obtain the operating status data of the electro-hydraulic proportional servo valve in real time;

[0009] Performing stabilization processing on the operating status data to obtain stabilization-processed operating status data;

[0010] Inputting the stabilized operating state data into an electro-hydraulic proportional servo valve state prediction model to output a state prediction value of the electro-hydraulic proportional servo valve; the electro-hydraulic proportional servo valve state prediction model is obtained by fitting and training a SARIMA model using training samples; the training samples include sample operating state data of the electro-hydraulic proportional servo valve and corresponding sample state values;

[0011] Obtaining a state deviation value of the electro-hydraulic proportional servo valve at the current moment based on a state prediction value of the electro-hydraulic proportional servo valve and a true state value of the electro-hydraulic proportional servo valve at the current moment, and determining whether the state deviation value of the electro-hydraulic proportional servo valve at the current moment exceeds a preset fault threshold;

[0012] If not, it is determined that the electro-hydraulic proportional servo valve has not failed at the current moment;

[0013] If so, it is determined that the electro-hydraulic proportional servo valve is faulty at the current moment, and the fault type of the electro-hydraulic proportional servo valve at the current moment is determined using the historical fault knowledge base and the operating status data to complete the fault diagnosis.

[0014] Optionally, performing stabilization processing on the operating status data to obtain the stabilization-processed operating status data specifically includes:

[0015] performing denoising processing on the operating status data to obtain denoised operating status data;

[0016] The denoised running state data is normalized to obtain stabilized running state data.

[0017] Optionally, a Gaussian filter is used to perform denoising on the operating status data, and the calculation formula is as follows:

[0018]

[0019] Among them, X filtered (t) represents the filtering result at time t; X(τ) represents the value of the operating status data at time τ; G(t-τ,σ) represents the Gaussian function; σ is the standard deviation of the Gaussian function.

[0020] Optionally, after obtaining the stabilized operating status data, the method further includes:

[0021] Using the formula Testing the stability of the running status data after the stabilization process to obtain a test result;

[0022] When the stability of the running status data after the stabilization processing does not meet the preset conditions, performing differential processing on the running status data after the stabilization processing until the running status data after the differential processing meets the preset conditions;

[0023] Where, φ represents the autoregressive coefficient; L represents the lag operator; y t represents time series data; δ represents a constant term; j represents the summation index; N represents the order of the moving average; ε t is the error term.

[0024] Optionally, the fitting training process of the electro-hydraulic proportional servo valve state prediction model specifically includes:

[0025] Performing seasonal analysis on sample operating status data of the electro-hydraulic proportional servo valve to determine a seasonal cycle of the sample operating status data of the electro-hydraulic proportional servo valve;

[0026] Based on the seasonal cycle, seasonally differencing the sample operating state data of the electro-hydraulic proportional servo valve is performed to obtain a seasonal difference order;

[0027] Based on the sample operating state data of the electro-hydraulic proportional servo valve after seasonal difference, the first autocorrelation function graph and the first partial autocorrelation function graph are drawn to determine the seasonal autoregressive order and the seasonal moving average order;

[0028] Based on the sample operating state data of the electro-hydraulic proportional servo valve, a second autocorrelation function graph and a second partial autocorrelation function graph are plotted to determine a non-seasonal autoregressive order and a non-seasonal moving average order;

[0029] Based on the seasonal difference order, the seasonal autoregressive order, the seasonal moving average order, the non-seasonal autoregressive order and the non-seasonal moving average order, the SARIMA model is fitted iteratively until the prediction error is less than a preset threshold, thereby obtaining the electro-hydraulic proportional servo valve state prediction model.

[0030] Optionally, the state prediction model of the electro-hydraulic proportional servo valve is expressed as:

[0031]

[0032] Where p represents the order of non-seasonal autoregression; φ i represents the non-seasonal autoregressive parameter; i represents the lag order of the non-seasonal autoregressive part; L represents the lag operator; s represents the length of the seasonal cycle; Δ represents the difference operator; d represents the non-seasonal difference order; D represents the seasonal difference order; X t represents the operating status data sequence of the electro-hydraulic proportional servo valve; t represents the time; q represents the non-seasonal moving average order; θ j represents the non-seasonal moving average parameter; P represents the seasonal autoregressive order; Q represents the seasonal moving average order; Θ krepresents the seasonal moving average parameter; j and k represent the summation index; ε t represents the error term.

[0033] Optionally, the historical fault knowledge base and the operating status data are used to determine the fault type of the electro-hydraulic proportional servo valve at the current moment, specifically including:

[0034] Performing feature analysis on the operating status data to obtain feature analysis results;

[0035] The characteristic analysis result is matched with characteristic conditions corresponding to different fault modes in a historical fault knowledge base to obtain a matching result, and the fault type of the electro-hydraulic proportional servo valve at the current moment is determined according to the matching result.

[0036] In a second aspect, the present application provides a computer device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the real-time diagnosis method for sudden failure of an electro-hydraulic proportional servo valve as described above.

[0037] In a third aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the real-time diagnosis method for sudden failure of an electro-hydraulic proportional servo valve as described in any one of the above.

[0038] In a fourth aspect, the present application provides a computer program product, comprising a computer program, which, when executed by a processor, implements the steps of the real-time diagnosis method for sudden faults of an electro-hydraulic proportional servo valve as described above.

[0039] According to the specific embodiments provided in this application, this application discloses the following technical effects:

[0040] The present application provides a real-time diagnosis method, equipment, medium and product for sudden faults of electro-hydraulic proportional servo valves. By inputting the real-time operating status data of the electro-hydraulic proportional servo valve into the electro-hydraulic proportional servo valve state prediction model, the operating status of the electro-hydraulic proportional servo valve is predicted. The method can effectively capture the periodic and non-periodic data characteristics in the operation of the electro-hydraulic proportional servo valve, realize real-time early warning and accurate diagnosis of faults, and improve the efficiency of fault detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0042] Figure 1 This is a diagram illustrating an application environment of a method for real-time diagnosis of sudden faults of an electro-hydraulic proportional servo valve according to an embodiment of the present application;

[0043] Figure 2 This is a flow chart of a method for real-time diagnosis of sudden faults of an electro-hydraulic proportional servo valve in one embodiment of the present application;

[0044] Figure 3 A schematic diagram of the valve cavity position structure of an electro-hydraulic proportional servo valve provided in one embodiment of the present application;

[0045] Figure 4 Graphs showing changes in operating condition data collected by various sensors when a circuit breaker fault occurs in the electro-hydraulic proportional servo valve drive circuit in another embodiment of the present application; (a) is a graph showing changes in operating condition data collected by the valve core position sensor; (b) is a graph showing changes in operating condition data collected by the valve drive current sensor; (c) is a graph showing changes in operating condition data collected by the A-port pressure sensor; and (d) is a graph showing changes in operating condition data collected by the B-port pressure sensor.

[0046] Figure 5 This is a schematic diagram of predicting the valve core position of an electro-hydraulic proportional servo valve during a circuit breaker fault in another embodiment of the present application;

[0047] Figure 6 A schematic diagram of a valve core position fault deviation of a circuit breaker fault valve provided by another embodiment of the present application;

[0048] Figure 7 A schematic diagram of the structure of a computer device provided in one embodiment of the present application.

[0049] Explanation of symbols:

[0050] Terminal-102, Server-104. DETAILED DESCRIPTION

[0051] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0052] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0053] The operating data of electro-hydraulic proportional servo valves often exhibit periodicity. Therefore, using the Seasonal Autoregressive Integrated Moving Average model (SARIMA) to process this data can better understand and predict the behavior of the equipment. Once a significant deviation from the model prediction is detected, the fault diagnosis and alarm mechanism can be triggered, enabling real-time diagnosis of sudden faults in the electro-hydraulic proportional servo valve.

[0054] The real-time diagnosis method for sudden faults of electro-hydraulic proportional servo valves provided in the embodiments of the present application can be applied to Figure 1 In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be set up separately, integrated on the server 104, or placed on the cloud or other servers. The terminal 102 can send the acquired operating status data of the electro-hydraulic proportional servo valve to the server 104. After the server 104 receives the acquired operating status data of the electro-hydraulic proportional servo valve, the server 104 acquires the operating status data of the electro-hydraulic proportional servo valve in real time; performs stabilization processing on the operating status data to obtain the operating status data after stabilization processing; inputs the operating status data after stabilization processing into the state prediction model of the electro-hydraulic proportional servo valve, and outputs the state prediction value of the electro-hydraulic proportional servo valve; the state prediction model of the electro-hydraulic proportional servo valve is a SARIMA model trained with training samples. The training samples include sample operating state data and corresponding sample state values ​​of the electro-hydraulic proportional servo valve. Based on the predicted state value of the electro-hydraulic proportional servo valve and the actual state value of the electro-hydraulic proportional servo valve at the current moment, a state deviation value of the electro-hydraulic proportional servo valve at the current moment is obtained, and it is determined whether the state deviation value of the electro-hydraulic proportional servo valve at the current moment exceeds a preset fault threshold. If not, it is determined that the electro-hydraulic proportional servo valve is not faulty at the current moment. If so, it is determined that the electro-hydraulic proportional servo valve is faulty at the current moment, and the fault type of the electro-hydraulic proportional servo valve at the current moment is determined using the historical fault knowledge base and the operating state data to complete fault diagnosis. The server 104 can provide feedback on the fault type of the electro-hydraulic proportional servo valve at the current moment to the terminal 102. In addition, in some embodiments, the real-time diagnosis method of sudden faults of the electro-hydraulic proportional servo valve can also be implemented independently by the server 104 or the terminal 102. For example, the terminal 102 can directly perform fault diagnosis on the obtained operating status data of the electro-hydraulic proportional servo valve, or the server 104 can obtain the operating status data of the electro-hydraulic proportional servo valve from the data storage system and perform fault diagnosis on the obtained operating status data of the electro-hydraulic proportional servo valve.

[0055] Terminal 102 may include, but is not limited to, various desktop computers, laptops, smartphones, tablet computers, IoT devices, and portable wearable devices. IoT devices may include smart speakers, smart TVs, smart air conditioners, and smart car devices. Portable wearable devices may include smart watches, smart bracelets, and head-mounted devices. Server 104 may be implemented as a standalone server or a server cluster consisting of multiple servers, or may be a cloud server.

[0056] In an exemplary embodiment, Figure 2 As shown, a real-time diagnosis method for sudden faults of electro-hydraulic proportional servo valves is provided. The method is executed by a computer device, specifically a computer device such as a terminal or a server, or a terminal and a server. In the embodiment of the present application, the method is applied to Figure 1 The server 104 in the example is used for explanation, and the steps include the following steps S1 to S5.

[0057] in:

[0058] Step S1, real-time acquisition of the operating status data of the electro-hydraulic proportional servo valve; wherein, multiple sensors are used to collect the real-time operating status data of the electro-hydraulic proportional servo valve, including a valve core position sensor, a valve drive current sensor, an A-port pressure sensor, and a B-port pressure sensor. The valve core position sensor is used to collect the linear variable differential transformer (LVDT) position sensor signal of the electro-hydraulic proportional servo valve; the valve drive current sensor is used to collect the proportional solenoid drive current signal of the electro-hydraulic proportional servo valve; the A-port pressure sensor is used to collect the hydraulic oil pressure signal of the slide valve A chamber of the electro-hydraulic proportional servo valve; and the B-port pressure sensor is used to collect the hydraulic oil pressure signal of the slide valve B chamber of the electro-hydraulic proportional servo valve. For a schematic diagram of the valve chamber position structure of the electro-hydraulic proportional servo valve, see Figure 3 , P is the oil inlet port, T is the oil return port.

[0059] Step S2: performing stabilization processing on the operating status data to obtain the stabilization-processed operating status data, so that the stabilization-processed operating status data meets the input requirements of the electro-hydraulic proportional servo valve state prediction model.

[0060] Step S3, input the smoothed operating status data into the electro-hydraulic proportional servo valve state prediction model, and output the state prediction value of the electro-hydraulic proportional servo valve; the electro-hydraulic proportional servo valve state prediction model is obtained by fitting and training the SARIMA model using training samples; the training samples include the sample operating status data of the electro-hydraulic proportional servo valve and the corresponding sample state values.

[0061] Step S4, based on the state prediction value of the electro-hydraulic proportional servo valve and the actual state value of the electro-hydraulic proportional servo valve at the current moment, obtain the state deviation value of the electro-hydraulic proportional servo valve at the current moment, and judge whether the state deviation value of the electro-hydraulic proportional servo valve at the current moment exceeds the preset fault threshold.

[0062] Step S5: If not, it is determined that the electro-hydraulic proportional servo valve is not faulty at the current moment.

[0063] Step S6: If yes, it is determined that the electro-hydraulic proportional servo valve is faulty at the current moment, and the fault type of the electro-hydraulic proportional servo valve at the current moment is determined using the historical fault knowledge base and the operating status data to complete the fault diagnosis.

[0064] As an optional implementation, step S2 specifically includes:

[0065] Step S21, denoising the operating status data to obtain denoised operating status data. A Gaussian filter is used to denoise the operating status data, and the calculation formula is as follows:

[0066]

[0067] Among them, X filtered (t) represents the filtering result at time t; X(τ) represents the value of the operating status data at time τ; G(t-τ,σ) represents the Gaussian function, which is used to determine the weight of each operating status data X(τ) in the filtering process; σ is the standard deviation of the Gaussian function, which determines the width of the Gaussian distribution, that is, the "smoothness" of the filter.

[0068] Step S22 , normalizing the denoised running status data to obtain stabilized running status data.

[0069]

[0070] Among them, X t,minmax Indicates the running status data after stabilization processing; X t represents the time series of real-time running status data, t represents the time point; |X t | max It is the maximum absolute value of the operating status data.

[0071] As an optional implementation, after step S22, the method further includes:

[0072] Using the formula The stability of the running status data after the stabilization process is tested to obtain a test result.

[0073] When the stability of the running status data after the stabilization processing does not meet the preset conditions, differential processing is performed on the running status data after the stabilization processing until the running status data after the differential processing meets the preset conditions.

[0074] Among them, y t represents time series data; φ represents the autoregressive coefficient, which is used to describe the relationship between the value of the time series in different lag periods and its current value; L represents the lag operator; δ is a constant term, which represents the baseline level of the model and is used to adjust the starting point of the model; j represents the summation index, which represents the error term ε in the moving average part. t-j The sum of; N represents the order of moving average; ε t Represents the error term at time point t, that is, the random error at the current time point.

[0075] As an optional implementation, the fitting training process of the electro-hydraulic proportional servo valve state prediction model in step S3 specifically includes:

[0076] (1) Perform seasonal analysis on the sample operating status data of the electro-hydraulic proportional servo valve to determine the seasonal cycle of the sample operating status data of the electro-hydraulic proportional servo valve.

[0077] Specifically, seasonal analysis of sample operating status data for an electro-hydraulic proportional servo valve involves plotting a time series graph to observe whether there are recurring seasonal patterns, using the Ljung-Box Q test to confirm the presence of seasonality, and analyzing the ACF and PACF plots to determine the seasonal cycle. The seasonal cycle S is calculated using the following formula:

[0078]

[0079] Among them, X t+s is the data point after determining the seasonal period S, and n is the number of data points within the seasonal period.

[0080] (2) Based on the seasonal cycle, seasonal differentiation is performed on the sample operating status data of the electro-hydraulic proportional servo valve to obtain a seasonal differentiation order.

[0081] Perform seasonal difference on the sample operating status data of the electro-hydraulic proportional servo valve:

[0082]

[0083] in, represents the seasonal difference operator; D is the seasonal difference order; S is the length of the seasonal cycle. Seasonal difference is used to remove the seasonal component in the time series.

[0084] (3) Draw the first autocorrelation function (ACF) and the first partial autocorrelation function (PACF) of the seasonal differenced data to determine the seasonal autoregressive order P and seasonal moving average order Q of the seasonal part.

[0085] (4) Draw the second ACF diagram and the second PACF diagram of the sample operating status data to determine the non-seasonal autoregressive order p and the non-seasonal moving average order q of the non-seasonal part.

[0086] (5) Based on the seasonal difference order, the seasonal autoregressive order, the seasonal moving average order, the non-seasonal autoregressive order and the non-seasonal moving average order, the SARIMA model is fitted iteratively until the prediction error is less than a preset threshold, thereby obtaining the electro-hydraulic proportional servo valve state prediction model.

[0087] The establishment of the electro-hydraulic proportional servo valve state prediction model includes: the expression of the constructed electro-hydraulic proportional servo valve state prediction model is as follows:

[0088]

[0089] Where p represents the non-seasonal autoregressive order; φ i represents the non-seasonal autoregressive parameter; i represents the lag order of the non-seasonal autoregressive part; L represents the lag operator; s represents the length of the seasonal cycle; Δ represents the difference operator; d represents the non-seasonal difference order; D represents the seasonal difference order; X t represents the operating status data sequence of the electro-hydraulic proportional servo valve; t represents the time; q represents the non-seasonal moving average order; θ j represents the non-seasonal moving average parameter; P represents the seasonal autoregressive order; Q represents the seasonal moving average order; Θ k represents the seasonal moving average parameter; j and k represent the summation index; ε t represents the error term.

[0090] Real-time data integration and prediction: Collect new data points in real time t+1 , the electro-hydraulic proportional servo valve state prediction model is used for prediction: Update the model parameters and constant term to reflect the new data. Where c is the constant term and represents the baseline level of the model.

[0091] As an optional embodiment, in step S4, based on the state prediction value of the electro-hydraulic proportional servo valve and the actual state value of the electro-hydraulic proportional servo valve at the current moment, a state deviation value of the electro-hydraulic proportional servo valve at the current moment is obtained, and it is determined whether the state deviation value of the electro-hydraulic proportional servo valve at the current moment exceeds a preset fault threshold.

[0092] The state deviation value e of the electro-hydraulic proportional servo valve at the current moment t+h The calculation formula is as follows:

[0093]

[0094] Calculate the peak-to-peak value X of historical data p-p , the state deviation value e of the electro-hydraulic proportional servo valve at the current moment t+h Perform standardization to obtain the state deviation value after standardization The calculation formula is as follows:

[0095]

[0096] As an optional implementation, in step S6, the fault type of the electro-hydraulic proportional servo valve at the current moment is determined using the historical fault knowledge base and the operating status data, specifically including:

[0097] Step S61: Perform feature analysis on the operating status data to obtain feature analysis results.

[0098] Step S62 , matching the characteristic analysis result with characteristic conditions corresponding to different fault modes in a historical fault knowledge base to obtain a matching result, and determining the fault type of the electro-hydraulic proportional servo valve at the current moment according to the matching result.

[0099] Specifically, the system analyzes multiple sensor data following an alarm and, based on the fault discrimination logic shown in Table 1, constructs a historical fault knowledge base containing fault characteristics and diagnostic information. A logical judgment algorithm is then used to match real-time operating status data with the fault patterns in the knowledge base. Based on the matching results, the system diagnoses the specific fault type. This involves performing a feature analysis on the features of each sensor data collected in real time to generate a feature analysis result. This feature analysis result is then logically compared with the characteristic values ​​for each predefined fault mode in Table 1. For example, if the knowledge base indicates that a valve core stuck fault is often accompanied by a sudden freeze in the valve core position, the logical matching process will check whether the valve core position sensor reading in the real-time operating status data suddenly freezes. For each fault mode, the system evaluates whether multiple conditions are simultaneously met. These conditions may include thresholds for specific parameters, rates of parameter change, or specific relationships between multiple parameters. If the features of the real-time data match the characteristic conditions corresponding to a particular fault mode, the system diagnoses the specific fault type based on the matching results.

[0100] Table 1 Fault feature knowledge base

[0101]

[0102] Technical effects of this application:

[0103] This application predicts the operating state of the electro-hydraulic proportional servo valve by inputting the real-time operating state data of the electro-hydraulic proportional servo valve into the electro-hydraulic proportional servo valve state prediction model, which can effectively capture the periodic and non-periodic data characteristics in the operation of the electro-hydraulic proportional servo valve, thereby accurately predicting the future state of the valve; by comparing the predicted value with the real-time data, it can monitor in real time whether the equipment state deviates from the normal range. Once it is detected that the deviation exceeds the preset fault threshold, the fault diagnosis process is immediately triggered to achieve real-time warning and accurate diagnosis of the fault; in the fault diagnosis stage, the system uses the historical fault knowledge base to match and analyze abnormal patterns, quickly determine the fault type, and provide guidance for maintenance. This application not only improves the efficiency and accuracy of fault detection, but also reduces equipment downtime, improves maintenance efficiency, and reduces maintenance costs through early fault warning and accurate diagnosis. Overall, this application significantly improves the operating reliability and stability of the electro-hydraulic proportional servo valve through the combined advantages of real-time performance, accuracy, efficiency improvement, and preventive maintenance.

[0104] In another exemplary embodiment of the present application, taking the diagnosis of a sudden circuit breaker fault of an electro-hydraulic proportional servo valve as an example, a real-time diagnosis method for a sudden fault of an electro-hydraulic proportional servo valve includes the following steps:

[0105] S101. Continuously collect real-time data from various sensors of the electro-hydraulic proportional servo valve.

[0106] The valve core position sensor collects the LVDT position sensor signal of the electro-hydraulic proportional servo valve, with the unit being V and the range being [-10, 10] V; the valve drive current sensor collects the proportional solenoid drive current signal of the electro-hydraulic proportional servo valve, with the unit being A and the range being [0, 2.5] A; the A-port pressure sensor collects the hydraulic oil pressure signal of the slide valve A chamber of the electro-hydraulic proportional servo valve, with the unit being bar and the range being [0, 70] bar; the B-port pressure sensor collects the hydraulic oil pressure signal of the slide valve B chamber of the electro-hydraulic proportional servo valve, with the unit being bar and the range being [0, 70] bar. The operating condition data change curve collected by the four sensors of the electro-hydraulic proportional servo valve when a sudden drive circuit failure occurs is shown in the following figure. Figure 4 The blue curve in .

[0107] S102: Stabilize the collected operating status data to make it meet the input requirements of the electro-hydraulic proportional servo valve state prediction model.

[0108] After the operation status data is collected, the operation status data is preprocessed to ensure that the operation status data is suitable for time series analysis, including removing noise in the data and normalizing the data. Finally, the ADF test statistical method is used to test the stationarity of the operation status data collected by each sensor. The test formula is:

[0109]

[0110] Among them, y t is time series data; t is the error term.

[0111] If the ADF test indicates that the data is non-stationary, the operating status data is subjected to differential processing until the stationarity of the operating status data meets the preset conditions. The differential processing formula is as follows:

[0112]

[0113] in, It represents the difference value of the time series at time point t; d represents the difference order.

[0114] S103 , inputting the stabilized operating state data into the electro-hydraulic proportional servo valve state prediction model, and predicting the future state of the electro-hydraulic proportional servo valve to obtain a predicted value of the electro-hydraulic proportional servo valve state.

[0115] Each sensor historical data set M is divided into a training set M train and the test set M test , using the training set M train To estimate the SARIMA model parameters, the obtained electro-hydraulic proportional servo valve state prediction model can be expressed as:

[0116]

[0117] Where φ(L) and θ(L) are the autoregressive and moving average polynomials, Δ is the difference operator, and d and D are the difference orders. Figure 5 As shown, the blue curve is the true value of the valve core position of the circuit breaker fault valve, and the red curve is the valve core position curve of the normal valve predicted by the electro-hydraulic proportional servo valve state prediction model.

[0118] S104 , comparing the predicted value with the real-time operating state data to obtain a state deviation value of the electro-hydraulic proportional servo valve at the current moment, and detecting whether the state deviation value of the electro-hydraulic proportional servo valve at the current moment exceeds a fault threshold.

[0119] Reference Figure 5 ,calculate Figure 5The absolute value of the deviation between the blue curve and the red curve is calculated and the absolute value is normalized to obtain the valve core position fault deviation of the open circuit fault valve. The calculation results are as follows: Figure 6 The blue curve in .

[0120] S105: If not, it is determined that the electro-hydraulic proportional servo valve has not failed at the current moment, and the process continues with S101.

[0121] S106: If yes, determine that the electro-hydraulic proportional servo valve is faulty at the current moment, and use the historical fault knowledge base and the operating status data to determine the fault type of the electro-hydraulic proportional servo valve at the current moment to complete the fault diagnosis.

[0122] Set the fault threshold T1 = 0.21, such as Figure 6 As shown by the red straight line in the middle, when five consecutive prediction points exceed the fault threshold, it can be considered that the valve has a sudden fault, and the process jumps to step S106 for subsequent fault analysis; otherwise, the process jumps to step S101 and repeats the above steps.

[0123] Specifically, analyze the sensor data after the fault alarm, such as Figure 4 As shown. Figure 4 As can be seen from (a) in the figure, after the fault occurs, the valve core position sensor data returns to near zero and then stabilizes. Figure 4 As can be seen from (b) in Figure 1, after a fault occurs, the valve drive current sensor data suddenly drops to zero and then stabilizes. Figure 4 As can be seen from (c) in the figure, after the fault occurs, the pressure sensor data at port A suddenly drops to zero pressure and then stabilizes. Figure 4 As can be seen from (d) in the figure, after the fault occurs, the pressure sensor data at port B suddenly drops to zero pressure and then stabilizes. By matching the changing trends of the four sensor data with the historical fault feature knowledge base in Table 1, it can be diagnosed that the electro-hydraulic proportional servo valve has a sudden drive circuit open fault.

[0124] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Figure 7As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O) and a communication interface. The processor, memory and input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a real-time diagnosis method for sudden failure of an electro-hydraulic proportional servo valve is implemented.

[0125] Those skilled in the art will understand that Figure 7 The structure shown in the figure is merely a block diagram of a portion of the structure related to the solution of the present application and does not constitute a limitation on the computer device to which the solution of the present application is applied. A specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement. In an exemplary embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor implements the steps of the above-mentioned method embodiments when executing the computer program.

[0126] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0127] In an exemplary embodiment, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0128] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0129] Those skilled in the art will understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0130] The databases involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processors involved in the various embodiments provided herein may include, but are not limited to, general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic units, data processing logic units based on quantum computing, and the like.

[0131] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0132] This document uses specific examples to illustrate the principles and implementation methods of this application. The description of the above examples is only intended to help understand the method and core concept of this application. At the same time, for those skilled in the art, based on the concept of this application, there may be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A real-time diagnosis method for sudden faults of electro-hydraulic proportional servo valves, characterized in that: The real-time diagnosis method for sudden faults of the electro-hydraulic proportional servo valve includes: Obtain the operating status data of the electro-hydraulic proportional servo valve in real time; Performing stabilization processing on the operating status data to obtain stabilization-processed operating status data; Inputting the stabilized operating state data into an electro-hydraulic proportional servo valve state prediction model to output a state prediction value of the electro-hydraulic proportional servo valve; the electro-hydraulic proportional servo valve state prediction model is obtained by fitting and training a SARIMA model using training samples; the training samples include sample operating state data of the electro-hydraulic proportional servo valve and corresponding sample state values; Obtaining a state deviation value of the electro-hydraulic proportional servo valve at the current moment based on a state prediction value of the electro-hydraulic proportional servo valve and a true state value of the electro-hydraulic proportional servo valve at the current moment, and determining whether the state deviation value of the electro-hydraulic proportional servo valve at the current moment exceeds a preset fault threshold; If not, it is determined that the electro-hydraulic proportional servo valve has not failed at the current moment; If so, it is determined that the electro-hydraulic proportional servo valve is faulty at the current moment, and the fault type of the electro-hydraulic proportional servo valve at the current moment is determined using the historical fault knowledge base and the operating status data to complete the fault diagnosis; The fitting training process of the electro-hydraulic proportional servo valve state prediction model specifically includes: Performing seasonal analysis on sample operating status data of the electro-hydraulic proportional servo valve to determine a seasonal cycle of the sample operating status data of the electro-hydraulic proportional servo valve; Based on the seasonal cycle, seasonally differencing the sample operating state data of the electro-hydraulic proportional servo valve is performed to obtain a seasonal difference order; Based on the sample operating state data of the electro-hydraulic proportional servo valve after seasonal difference, the first autocorrelation function graph and the first partial autocorrelation function graph are drawn to determine the seasonal autoregressive order and the seasonal moving average order; Based on the sample operating state data of the electro-hydraulic proportional servo valve, a second autocorrelation function graph and a second partial autocorrelation function graph are plotted to determine a non-seasonal autoregressive order and a non-seasonal moving average order; Based on the seasonal difference order, the seasonal autoregressive order, the seasonal moving average order, the non-seasonal autoregressive order and the non-seasonal moving average order, the SARIMA model is fitted iteratively until the prediction error is less than a preset threshold, thereby obtaining the electro-hydraulic proportional servo valve state prediction model; The expression of the state prediction model of the electro-hydraulic proportional servo valve is: ； in, Determine the non-seasonal autoregressive order; represents the non-seasonal autoregressive parameter; i represents the lag order of the non-seasonal autoregressive part; represents the lag operator; s represents the length of the seasonal cycle; represents the difference operator; represents the non-seasonal difference order; represents the seasonal difference order; Represents the operating status data sequence of the electro-hydraulic proportional servo valve; t represents the time; represents the non-seasonal moving average order; represents the non-seasonal moving average parameter; represents the seasonal autoregressive order; represents the seasonal moving average order; represents the seasonal moving average parameter; j and k represent the summation index; represents the error term.

2. The real-time diagnosis method for sudden faults of electro-hydraulic proportional servo valves according to claim 1, characterized in that: Stabilizing the operating status data to obtain the stabilized operating status data specifically includes: performing denoising processing on the operating status data to obtain denoised operating status data; The denoised running state data is normalized to obtain stabilized running state data.

3. The real-time diagnosis method for sudden faults of electro-hydraulic proportional servo valves according to claim 2, characterized in that: A Gaussian filter is used to perform denoising on the operating status data.

4. The real-time diagnosis method for sudden faults of electro-hydraulic proportional servo valves according to claim 2, characterized in that: After obtaining the stabilized operating status data, it also includes: Using the formula Testing the stability of the running status data after the stabilization process to obtain a test result; When the stability of the running status data after the stabilization processing does not meet the preset conditions, performing differential processing on the running status data after the stabilization processing until the running status data after the differential processing meets the preset conditions; in, represents the autoregressive coefficient; represents the lag operator; Represents time series data; represents the constant term; j represents the summation index; N represents the order of the moving average; is the error term.

5. The real-time diagnosis method for sudden faults of electro-hydraulic proportional servo valves according to claim 1, characterized in that: The fault type of the electro-hydraulic proportional servo valve at the current moment is determined by using the historical fault knowledge base and the operating status data, specifically including: Performing feature analysis on the operating status data to obtain feature analysis results; The characteristic analysis result is matched with characteristic conditions corresponding to different fault modes in a historical fault knowledge base to obtain a matching result, and the fault type of the electro-hydraulic proportional servo valve at the current moment is determined according to the matching result.

6. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement a real-time diagnosis method for sudden faults of an electro-hydraulic proportional servo valve according to any one of claims 1 to 5.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, a real-time diagnosis method for sudden faults of an electro-hydraulic proportional servo valve according to any one of claims 1 to 5 is implemented.

8. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, a real-time diagnosis method for sudden faults of an electro-hydraulic proportional servo valve according to any one of claims 1 to 5 is implemented.

Images