Valve performance detection system and method

Abstract

The present invention discloses a valve performance detection system and method, relating to the field of valve detection, for detecting the performance of high-pressure hydrogen valves. The method comprises installing vibration sensors on the valve seat and valve outlets on both sides of the high-pressure hydrogen valve, detecting vibration signals at different opening strokes with and without tapping the valve, performing data processing, and evaluating the degree of hydrogen cavitation based on a physical information fusion LSTM model, thereby obtaining valve material performance detection results. The present invention achieves effective long-term assessment of hydrogen embrittlement in high-pressure hydrogen valves. During the assessment, vibration signal data is enhanced based on the spatial correlation of the vibration spectrum of multiple vibration signals after hammering, effectively improving the accuracy of the assessment results. Furthermore, the assessment of hydrogen cavitation based on the physical information fusion LSTM model addresses the problem that the assessment results of traditional models do not conform to physical laws.

Description

Technical Field

[0001] The present invention relates to the field of valve performance, and in particular to a valve performance detection system and method. Background Art

[0002] High-pressure hydrogen valve testing is a critical step in ensuring the safe and reliable operation of hydrogen energy systems. Due to the flammable and explosive nature of hydrogen and its hydrogen embrittlement effect, the valve's sealing performance and material stability under high-pressure conditions are directly related to the safety of the entire system. The primary causes of failure in high-pressure hydrogen valves are cavitation and erosive wear. Hydrogen embrittlement can occur under the combined effects of complex multi-directional stresses and the high-pressure hydrogen environment, accelerating the degradation of the material's mechanical properties and leading to premature fatigue failure.

[0003] However, the current valve performance testing method in the prior art still adopts a single performance test method, which cannot achieve long-term and effective monitoring of the hydrogen embrittlement effect. Summary of the Invention

[0004] In order to solve the technical problem in the prior art that it is impossible to achieve long-term and effective monitoring of hydrogen embrittlement effects, the present invention provides a valve performance detection system and method.

[0005] The present invention is achieved through the following technical solutions:

[0006] A valve performance testing method for testing high-pressure hydrogen valve performance, comprising:

[0007] A first vibration sensor, a second vibration sensor, and a third vibration sensor are provided on the valve seat and valve outlets on both sides of the high-pressure hydrogen valve;

[0008] Within the valve opening stroke, the valve is closed to fully opened N times in a 1 / N step manner; vibration signals at different opening strokes are detected respectively to obtain a first vibration signal;

[0009] Within the valve opening stroke, the valve is closed to fully open N times in a 1 / N step manner, and a knocking force of a certain frequency and strength is applied to the valve seat to obtain a second vibration signal;

[0010] performing data processing on the first vibration signal and the second vibration signal, including data preprocessing and feature extraction;

[0011] The LSTM model based on physical information fusion is used to evaluate the degree of hydrogen cavitation, thereby obtaining the valve material performance test results.

[0012] Furthermore, the first vibration signal includes a first sub-signal of the first vibration signal, a second sub-signal of the first vibration signal, and a third sub-signal of the first vibration signal corresponding to the first vibration sensor, the second vibration sensor, and the third vibration sensor, respectively; the second vibration signal includes a first sub-signal of the second vibration signal, a second sub-signal of the second vibration signal, and a third sub-signal of the second vibration signal corresponding to the first vibration sensor, the second vibration sensor, and the third vibration sensor, respectively.

[0013] Furthermore, the data preprocessing includes subtracting the first vibration signal from the second vibration signal to obtain a third vibration signal, and the third vibration signal includes three sub-signals.

[0014] Furthermore, the data preprocessing also includes performing data space correlation enhancement processing on the three sub-signals of the third vibration signal based on a graph neural network.

[0015] Furthermore, the data space correlation enhancement processing includes adjusting edge connections based on an edge adjustment module to form a new graph structure. Specifically, a random forest model is embedded to adjust the weight adjustment coefficient of the edge correlation strength in the topological relationship.

[0016] Furthermore, the loss function expression of the LSTM model based on physical information fusion is as follows:

[0017]

[0018] Where N is the number of samples, yi is the observed value, is the predicted value, ρ is the regularization parameter, and Ui is the predicted value based on the physical model of the knocking vibration signal transmitted in the valve.

[0019] Furthermore, the physical model of the knocking vibration signal transmitted through the valve is expressed as follows:

[0020]

[0021] E is the total energy, P in is the input power, determined by the energy applied by the hammer, P dis is the dissipated power, S is the energy flow vector, indicating the outflow of energy, and A is the average cross-sectional area of ​​the energy flow path.

[0022] Furthermore, the energy flow vector expression is as follows:

[0023]

[0024] Where w is the angular frequency, E is the elastic modulus of the material, U is the vibration amplitude, α is the attenuation coefficient, and x is the distance from the tapping point to the measurement point.

[0025] The present invention further provides a valve performance detection system, based on the valve performance detection method described above, comprising:

[0026] The first vibration sensor, the second vibration sensor, and the third vibration sensor are respectively arranged on the valve seat and the valve outlets on both sides of the high-pressure hydrogen valve;

[0027] A valve control module, which is used to control the valve opening;

[0028] A vibration signal acquisition module, which is used to acquire vibration signals from three vibration sensors;

[0029] The vibration signal processing module is used for data preprocessing and feature extraction of vibration signals, including data cleaning and denoising, vibration signal subtraction, and data enhancement.

[0030] The hydrogen cavitation degree assessment and performance test result acquisition module is used to assess the hydrogen cavitation degree based on the LSTM model of physical information fusion, thereby obtaining the valve material performance test results.

[0031] In addition, to achieve the above-mentioned purpose, the present invention also provides a computer-readable storage medium, on which program instructions of the valve performance detection method are stored. The program instructions of the valve performance detection method can be executed by one or more processors to implement the steps of the valve performance detection method as described above.

[0032] Compared with the prior art, the present invention has the following beneficial effects:

[0033] The present invention realizes effective long-term evaluation of the hydrogen embrittlement of high-pressure hydrogen valves based on applying knocking and detecting vibrations. In realizing the evaluation of the hydrogen embrittlement of high-pressure hydrogen valves, data enhancement of the vibration signal is realized based on the spatial correlation of the vibration spectrum of the multi-point vibration signal after the embrittlement of the valve material is manifested in the hammering. The degree of hydrogen cavitation is evaluated based on the LSTM model fused with physical information to solve the problem that the evaluation results of the traditional model do not conform to the physical laws. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0035] Figure 1 It is a flow chart of a valve performance detection method according to an embodiment of the present application. DETAILED DESCRIPTION

[0036] The embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0037] The following describes the embodiments of the present invention through specific examples. Those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that, in the absence of conflict, the following embodiments and features in the embodiments can be combined with each other. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0038] It should also be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present invention. The illustrations only show components related to the present invention and are not drawn according to the number, shape and size of components in actual implementation. In actual implementation, the form, quantity and proportion of each component can be changed at will, and the component layout form may also be more complicated.

[0039] See also Figure 1 A valve performance detection method for high-pressure hydrogen valve detection includes the following steps:

[0040] S1: Install a first vibration sensor, a second vibration sensor, and a third vibration sensor on the valve seat and valve outlets on both sides of the high-pressure hydrogen valve;

[0041] S2: Within the valve opening stroke, the valve is closed to fully opened N times in a 1 / N step manner; vibration signals at different opening strokes are detected respectively to obtain a first vibration signal, which includes a first sub-signal of the first vibration signal, a second sub-signal of the first vibration signal, and a third sub-signal of the first vibration signal corresponding to the first vibration sensor, the second vibration sensor, and the third vibration sensor, respectively;

[0042] S3: Within the valve opening stroke, the valve is closed to fully open N times in a 1 / N step manner, and a knocking force of a certain frequency and intensity is applied to the valve seat to obtain a second vibration signal, which includes a first sub-signal of the second vibration signal, a second sub-signal of the second vibration signal, and a third sub-signal of the second vibration signal corresponding to the first vibration sensor, the second vibration sensor, and the third vibration sensor, respectively;

[0043] Alternatively, the striking force is applied using a pneumatic or electric striking hammer.

[0044] S4: performing data processing on the first vibration signal and the second vibration signal, including data preprocessing and feature extraction;

[0045] Specifically, data preprocessing includes:

[0046] S41: Data cleaning and denoising; optionally, filtering out noise based on an adaptive filtering method and removing outliers through a sliding window.

[0047] S42: The first vibration signal is subtracted from the second vibration signal to obtain a third vibration signal. Specifically, the signals obtained by the first vibration sensor, the second vibration sensor, and the third vibration sensor are subtracted to obtain a first sub-signal of the third vibration signal, a second sub-signal of the third vibration signal, and a third sub-signal of the third vibration signal; the first sub-signal of the third vibration signal is obtained by subtracting the first sub-signal of the first vibration signal and the first sub-signal of the second vibration signal, the second sub-signal of the third vibration signal is obtained by subtracting the second sub-signal of the first vibration signal and the second sub-signal of the second vibration signal, and the third sub-signal of the third vibration signal is obtained by subtracting the third sub-signal of the first vibration signal and the third sub-signal of the second vibration signal.

[0048] The difference between the two signals is used to remove the vibration caused by the gas flow in the valve, and the vibration signal obtained by the hammer is obtained, thereby highlighting the abnormality in the vibration signal caused by the embrittlement of the material due to the hydrogen embrittlement effect of the valve.

[0049] S43: Data enhancement;

[0050] Since the embrittlement of valve materials is manifested in the spatial correlation of the vibration spectra of multi-point vibration signals after being hammered, traditional vibration signal processing methods ignore the multi-scale spatial correlation of vibration signals. To enhance the spatial correlation of vibration signal characteristics caused by valve material embrittlement, the present invention performs data spatial correlation enhancement processing on the three sub-signals of the third vibration signal. Specifically, the sub-signals are regarded as nodes in a graph structure, and the spatial correlation between nodes is modeled using a graph neural network to generate enhanced data that conforms to the topological relationship. Specifically, the following steps are performed:

[0051] a. Get the coordinates of the three sensors' locations;

[0052] b. Build a graph structure: nodes are the feature vectors corresponding to the three sub-signals; edge weights are calculated based on the physical distance between the sub-signals to determine the strength of the association;

[0053] Specifically, assuming that the association strength decays with distance in a Gaussian distribution, the association strength calculation formula is as follows:

[0054]

[0055] σ is the smoothness coefficient of attenuation; d is the distance between the two sensors, is the initial value of the weight adjustment coefficient.

[0056] c. Graph data enhancement:

[0057] Since the corresponding eigenvectors of the vibration signals have different influences on the prediction of valve material embrittlement, the present invention implements graph data enhancement based on dynamic adjustment of the weight adjustment coefficient;

[0058] include:

[0059] Based on the edge adjustment module, the edge connections are adjusted to form a new graph structure. Specifically, the weight adjustment coefficient is adjusted by embedding the random forest model:

[0060] Because vibration spectrum characteristics are particularly effective in distinguishing different material embrittlement conditions in valve hydrogen embrittlement prediction, the present invention uses these characteristics to adjust the weight adjustment coefficient. Specifically, the random forest model inputs the vibration spectrum characteristics and outputs the weight adjustment coefficient. Optionally, the vibration spectrum characteristics include spectrum peaks, harmonic components, frequency band energy percentages, and the rate of change of vibration spectrum entropy.

[0061] When the association strength is less than the set threshold, the edge connection is deleted;

[0062] Traverse all edges in turn and reset the association strength to obtain the updated graph structure.

[0063] Through the above method, the problem of mixing adjacent nodes in the graph network is effectively solved.

[0064] d. Inverse mapping to time domain: convert the enhanced graph node features back to time domain signals.

[0065] Specifically, feature extraction includes time domain features, frequency domain features, and time-frequency domain features;

[0066] The time domain features include root mean square value, peak value, and kurtosis; the frequency domain features include spectrum peak value, harmonic component, and frequency band energy ratio; in order to enhance the change in vibration spectrum entropy of multi-point vibration signals after the valve material is embrittled and hammered, the present invention obtains the Hilbert spectrum of the structural nonlinear vibration signal based on HHT transformation, and further calculates the spectral entropy as the time-frequency domain feature.

[0067] S5: The LSTM model based on physical information fusion evaluates the degree of hydrogen cavitation, thereby obtaining the valve material performance test results, as follows:

[0068] In the prior art, when using the traditional LSTM model for evaluation, there are problems such as slow convergence of the general model, low accuracy, violation of physical laws, etc., and it is impossible to effectively integrate the time-frequency characteristics of the vibration signal in the cavitation detection method of the present invention. Therefore, the present invention uses an LSTM model based on physical information fusion to detect the degree of hydrogen cavitation, and adds the physical constraints of the vibration signal as a regularization term to the loss function to solve the problems of the traditional model. Specifically, the loss function expression is as follows:

[0069]

[0070] Where N is the number of samples, yi is the observed value, is the predicted value, ρ is the regularization parameter, and Ui is the predicted value based on the physical model of the knocking vibration signal transmitted in the valve.

[0071] The physical model takes into account boundary effects, including energy redistribution caused by reflection, transmission, and scattering, such as scattering caused by defects such as cracks and holes. The physical model of the transmission of knock vibration signals in steel pipes is expressed as follows:

[0072]

[0073] E is the total energy, P in is the input power, determined by the energy applied by the hammer, P dis is the dissipated power, S is the energy flow vector, represents the energy outflow, and A is the average cross-sectional area of ​​the energy flow path.

[0074] The energy flow vector is proportional to the square of the vibration amplitude. In the valve system model, the energy flow vector expression is as follows:

[0075] Where w is the angular frequency, E is the elastic modulus of the material, U is the vibration amplitude, α is the attenuation coefficient, and x is the distance from the tapping point to the measurement point.

[0076] The dissipated power is determined according to the valve material.

[0077] The corresponding valve material performance test results are further obtained based on the hydrogen cavitation degree evaluation results.

[0078] The present invention takes physical constraints as prior knowledge and uses the valve vibration physical model to guide the model to maintain reasonable output, while reducing dependence on pure data drive.

[0079] In this embodiment, an effective long-term evaluation of the hydrogen embrittlement of a high-pressure hydrogen valve is achieved based on applying knocking and detecting vibration. In achieving the evaluation of the hydrogen embrittlement of a high-pressure hydrogen valve, data enhancement of the vibration signal is achieved based on the spatial correlation of the vibration spectrum of the multi-point vibration signal after the valve material is hammered, which is manifested in the embrittlement of the valve material. The degree of hydrogen cavitation is evaluated based on the LSTM model of physical information fusion to solve the problem that the evaluation results of the traditional model do not conform to the laws of physics.

[0080] The embodiment of the present invention further provides a valve performance detection system, which is based on the valve performance detection method described above and is used for high-pressure hydrogen valve detection, including:

[0081] The first vibration sensor, the second vibration sensor, and the third vibration sensor are respectively arranged on the valve seat and the valve outlets on both sides of the high-pressure hydrogen valve;

[0082] A valve control module, which is used to control the valve opening;

[0083] A vibration signal acquisition module, which is used to acquire vibration signals from three vibration sensors;

[0084] The vibration signal processing module is used for data preprocessing and feature extraction of vibration signals, including data cleaning and denoising, vibration signal subtraction, and data enhancement.

[0085] The hydrogen cavitation degree assessment and performance test result acquisition module is used to assess the hydrogen cavitation degree based on the LSTM model of physical information fusion, thereby obtaining the valve material performance test results.

[0086] In addition, an embodiment of the present invention further provides a computer-readable storage medium, on which program instructions of a valve performance detection method are stored. The program instructions of the valve performance detection method can be executed by one or more processors to implement the steps of the valve performance detection method as described above.

[0087] The embodiments described above are merely descriptions of preferred implementations of the present invention and are not intended to limit the scope of the present invention. Without departing from the spirit of the present invention, various modifications and improvements made to the technical solutions of the present invention by ordinary technicians in this field should fall within the scope of protection determined by the claims of the present invention.

Claims

1. A valve performance detection method, characterized in that: Used to test the performance of high-pressure hydrogen valves, including: A first vibration sensor, a second vibration sensor, and a third vibration sensor are provided on the valve seat and valve outlets on both sides of the high-pressure hydrogen valve; Within the valve opening stroke, the valve is closed to fully opened N times in a 1 / N step manner; vibration signals at different opening strokes are detected respectively to obtain a first vibration signal; Within the valve opening stroke, the valve is closed to fully open N times in a 1 / N step manner, and a knocking force of a certain frequency and strength is applied to the valve seat to obtain a second vibration signal; performing data processing on the first vibration signal and the second vibration signal, including data preprocessing and feature extraction; the data preprocessing includes subtracting the first vibration signal from the second vibration signal to obtain a third vibration signal, the third vibration signal including three sub-signals, and performing data spatial correlation enhancement processing on the three sub-signals of the third vibration signal based on a graph neural network; The LSTM model based on physical information fusion is used to evaluate the degree of hydrogen cavitation, thereby obtaining the valve material performance test results; The loss function expression of the LSTM model based on physical information fusion is as follows: Where N is the number of samples, yi is the observed value, is the predicted value, ρ is the regularization parameter, and Ui is the predicted value based on the physical model of the knocking vibration signal transmitted in the valve; The physical model of the knock vibration signal transmitted through the valve is expressed as follows: E is the total energy, P in is the input power, determined by the energy applied by the hammer, P dis is the dissipated power, S is the energy flow vector, ∫S·dA represents the energy outflow, and A is the average cross-sectional area of ​​the energy flow path.

2. The valve performance detection method according to claim 1, characterized in that: The first vibration signal includes a first sub-signal of the first vibration signal, a second sub-signal of the first vibration signal, and a third sub-signal of the first vibration signal corresponding to the first vibration sensor, the second vibration sensor, and the third vibration sensor, respectively; the second vibration signal includes a first sub-signal of the second vibration signal, a second sub-signal of the second vibration signal, and a third sub-signal of the second vibration signal corresponding to the first vibration sensor, the second vibration sensor, and the third vibration sensor, respectively.

3. The valve performance detection method according to claim 2, characterized in that: The data space correlation enhancement process includes adjusting edge connections based on an edge adjustment module to form a new graph structure. Specifically, a random forest model is embedded to adjust the weight adjustment coefficient of the edge correlation strength in the topological relationship.

4. The valve performance detection method according to claim 3, characterized in that: The energy flow vector expression is as follows: Where w is the angular frequency, E' is the elastic modulus of the material, U is the vibration amplitude, α is the attenuation coefficient, and x is the distance from the tapping point to the measurement point.

5. A valve performance detection system, using the valve performance detection method according to any one of claims 1 to 4, comprising: The first vibration sensor, the second vibration sensor, and the third vibration sensor are respectively arranged on the valve seat and the valve outlets on both sides of the high-pressure hydrogen valve; A valve control module, which is used to control the valve opening; A vibration signal acquisition module, which is used to acquire vibration signals from three vibration sensors; The vibration signal processing module is used for data preprocessing and feature extraction of vibration signals, including data cleaning and denoising, vibration signal subtraction, and data enhancement. The hydrogen cavitation degree assessment and performance test result acquisition module is used to assess the hydrogen cavitation degree based on the LSTM model of physical information fusion, thereby obtaining the valve material performance test results.

6. A computer-readable storage medium, characterized in that The computer-readable storage medium stores program instructions of the valve performance detection method, and the program instructions of the valve performance detection method can be executed by one or more processors to implement the steps of the valve performance detection method according to any one of claims 1 to 4.

Images