A method and system for detecting the operating status of a hydrogen pipeline flame arrester

Abstract

The present invention provides a method and system for detecting the operating status of a hydrogen pipeline flame arrester. The key points of the technical solution include: obtaining historical normal data and setting threshold parameters corresponding to various detection information; obtaining detection information of various sensors in real time and preprocessing it; performing time-frequency domain analysis on the preprocessed vibration information to obtain multiple IMF components and residuals, extracting vibration characteristics to perform preliminary vibration anomaly judgment; in response to abnormal vibration characteristics, calculating the dynamic vibration threshold corresponding to the current sampling moment; and making an abnormal judgment on the operating status of the flame arrester at the current sampling moment. The present invention can monitor the abnormal information of the flame arrester in real time, accurately judge the current status of the flame arrester, avoid safety hazards caused by flame arrester failure, and at the same time reduce the tedious operations of manual detection and avoid omissions in manual detection.

Description

Technical Field

[0001] The present invention relates to the technical field of flame arrester detection, and in particular to a method and system for detecting the operating status of a hydrogen pipeline flame arrester. Background Art

[0002] As a chemical raw material, hydrogen is widely used in metallurgy, aerospace, electronics, glass, fine chemicals, energy, and other fields. Because hydrogen is flammable and explosive, flame arresters must be installed in hydrogen pipelines to protect the safety of workers and the safety of enterprises in actual production operations within hydrogen applications. This prevents serious accidents caused by flashback, deflagration, or leakage. Furthermore, flame arresters must be routinely inspected to ensure they are in proper working order.

[0003] A flame arrester is a safety device used to prevent the spread of flames from flammable gases and liquid vapors. It's typically installed in pipelines carrying flammable gases or on ventilated tanks to prevent the spread of flames and the resulting deflagration or detonation. A flame arrester primarily consists of a shell and a core. Routine inspection and maintenance of the arrester typically requires disassembly and manual visual inspection to check for defects such as blockage, deformation, and corrosion in the core's flame barrier layer and perforations.

[0004] When a flame arrester has a major abnormal defect, relevant staff are required to promptly discover and repair or replace it to ensure that the flame arrester of the hydrogen pipeline can effectively block fire in a high-risk environment, avoid serious accidents caused by backfire, deflagration or leakage, and avoid safety hazards caused by flame arrester failure. Therefore, it is very important to inspect and monitor the status of the flame arrester. Summary of the Invention

[0005] In order to monitor the operating status of the flame arrester in real time and avoid safety hazards caused by flame arrester failure, while reducing the tedious operations of manual detection and avoiding omissions in manual detection, the present invention provides a method and system for detecting the operating status of a hydrogen pipeline flame arrester.

[0006] In a first aspect, the present invention provides a method for detecting the operating status of a hydrogen pipeline flame arrester, the technical solution of which is as follows:

[0007] A method for detecting the operating status of a hydrogen pipeline flame arrester comprises the following steps: obtaining historical normal data and setting threshold parameters corresponding to various detection information; obtaining detection information from various sensors in real time and performing preprocessing; performing time-frequency domain analysis on the preprocessed vibration information to obtain multiple IMF components and residuals, extracting vibration characteristics to perform preliminary vibration anomaly determination; in response to abnormal vibration characteristics, calculating a dynamic vibration threshold corresponding to a current sampling moment; and determining an abnormality in the operating status of the flame arrester at the current sampling moment.

[0008] Among them, the vibration characteristics include the energy value and the total energy entropy of the current vibration information. The energy of the i-th IMF component at the t-th sampling time is ; The total energy entropy of the vibration information at the tth sampling moment is , the calculation formula is: , where represents the energy proportion of the i-th IMF component at the t-th sampling time, ln represents the natural logarithm, and n represents the number of IMF components;

[0009] The dynamic vibration threshold is , the calculation formula is: , where k is the error correction coefficient, Indicates the theoretical energy value of the i-th IMF component at the current sampling moment.

[0010] Preferably, historical normal data is obtained and threshold parameters corresponding to various detection information are set, including respectively adapting and installing corresponding sensors for detecting vibration, hydrogen flow, temperature, and hydrogen concentration, and setting threshold parameters corresponding to various detection information according to the performance standards of the corresponding flame arrester model and historical normal data;

[0011] Among them, the threshold parameters of temperature and hydrogen concentration can be directly set according to the performance standards of the flame arrester. The dynamic vibration threshold for judging the mechanical state of the flame arrester requires obtaining historical normal data on vibration and hydrogen flow for calculation. If relevant historical normal data is saved, it can be directly imported and referenced. If relevant historical data is not saved, it is necessary to manually detect and confirm that the flame arrester is in a normal state, and then obtain data records under normal operating conditions for a period of time as historical normal data.

[0012] Preferably, the detection information of each sensor is obtained in real time, and the collected vibration information and hydrogen flow information are pre-processed, including synchronously collecting vibration information data and hydrogen flow information data at the same sampling frequency, wherein the initial vibration information data at the t-th sampling moment is , the traffic information data at the tth sampling time is ;

[0013] Preprocess the vibration information, including noise reduction processing to eliminate high-frequency electromagnetic interference in the vibration information; remove trend item processing to eliminate low-frequency drift in the vibration information, such as sensor baseline drift and temperature influence; Among them, the vibration information data at the tth sampling moment After preprocessing, the standard vibration information data at the tth sampling time is obtained ;

[0014] The flow information is pre-processed, including synchronization time stamp alignment, which is used to align the timestamp of the flow information with the timestamp of the vibration information.

[0015] Preferably, the pre-processed vibration information is subjected to time-frequency domain analysis to obtain multiple IMF components and residuals, including parsing the vibration information through the EMD algorithm to obtain the decomposition data of the vibration information, wherein the standard vibration information data pre-processed at the t-th sampling moment is From high frequency to low frequency, it is decomposed into n IMF components and residuals. The expression formula of the decomposition result is:

[0016]

[0017] Where, represents the i-th IMF component of the vibration information at the t-th sampling moment, It represents the residual signal of the vibration information at the t-th sampling moment, and n represents the number of IMF components or the number of decomposition levels.

[0018] Preferably, extracting vibration features to perform preliminary vibration abnormality judgment includes calculating the energy value of each IMF component at the t-th sampling moment , energy ratio and the total energy entropy of the vibration information at the t-th sampling moment ;

[0019] It represents the energy of the i-th IMF component at the t-th sampling time, and the calculation formula is:

[0020]

[0021] Where, represents the mth decomposition data of the i-th IMF component, represents the summation function, M represents the number of vibration information data at the current sampling moment;

[0022] It represents the energy proportion of the i-th IMF component at the t-th sampling time, and the calculation formula is:

[0023]

[0024] Set the threshold F, when ≤F, it is determined that the vibration information at the t-th sampling moment is normal, and the mechanical state of the flame arrester at the t-th sampling moment is normal. >F, it is preliminarily determined that the vibration information at the t-th sampling moment is abnormal, and it is necessary to further combine the flow information at the t-th sampling moment Make abnormal judgment on the mechanical status of the flame arrester.

[0025] Preferably, in response to the abnormal vibration characteristics, a dynamic vibration threshold corresponding to the current sampling moment is calculated, including obtaining a correlation regression coefficient between the vibration energy value and the flow information based on historical normal data, obtaining a decomposition signal of the vibration information in the historical normal data by an EMD algorithm, obtaining n historical IMF components and residuals, and calculating the energy value of each historical IMF component accordingly;

[0026] The historical vibration energy corresponding to each historical IMF component Converted into the form of matrix series and used as the dependent variable of the linear regression model, the i-th historical vibration energy The matrix sequence expression is:

[0027]

[0028] The corresponding historical traffic information data is also converted into the form of a matrix series as an independent variable, and the corresponding historical traffic information data The matrix sequence expression is:

[0029]

[0030] The relationship between historical vibration information characteristics and historical flow information characteristics is established through a linear regression model to obtain the historical vibration energy corresponding to each historical IMF component Compared with historical hydrogen flow The regression coefficient between

[0031] A linear regression model is established for each historical IMF component in the historical normal data, where the i-th historical vibration energy The linear regression model is: , i ranges from 1 to n, and represents the regression coefficient corresponding to the i-th historical IMF component;

[0032] The regression coefficient corresponding to each historical IMF component is obtained using the least squares formula. The specific calculation formula for the regression coefficient corresponding to the i-th historical IMF component is:

[0033]

[0034] Where, represents the i-th historical vibration energy The mth data in the matrix sequence, represents the i-th historical vibration energy The average value of M data in the matrix series, Indicates the corresponding historical traffic information data The mth data in the matrix sequence, Indicates the corresponding historical traffic information The average value of M data in .

[0035] Preferably, in response to the abnormal vibration characteristics, the dynamic vibration threshold corresponding to the current sampling moment is calculated, and the method further includes calculating the theoretical energy value corresponding to each IMF component at the current sampling moment according to the regression coefficient corresponding to each historical IMF component, wherein the theoretical energy value of the i-th IMF component at the t-th sampling moment is The calculation formula is: Where, Represents the flow information data at the tth sampling moment;

[0036] Get the energy average of each IMF component at the current sampling moment as the dynamic vibration threshold at the current sampling moment The comparison object is calculated as follows: , where Represents the average energy of n IMF components at the t-th sampling time.

[0037] Preferably, the abnormality determination is performed on the operating state of the flame arrester at the current sampling moment, including determining the mechanical state of the flame arrester at the current sampling moment. Taking the tth sampling moment as an example, when When , it means that the vibration information at the current sampling moment is within the normal fluctuation range, and the mechanical state of the flame arrester is normal. When , it means that the vibration information at the current sampling moment is abnormal, and the mechanical state of the flame arrester is abnormal, then it is determined that the current state of the flame arrester is abnormal;

[0038] Combined with the detection information of temperature and hydrogen concentration, the temperature and hydrogen concentration information detected at the current sampling moment are compared with the set threshold values. When either the temperature or the hydrogen concentration is judged to be abnormal, the current state of the flame arrester is judged to be abnormal. When the current state of the flame arrester is judged to be abnormal, an abnormal alarm is triggered and the corresponding abnormal information data is recorded.

[0039] In a second aspect, the present invention provides a hydrogen pipeline flame arrester operating status detection system, the technical solution of which is as follows:

[0040] A hydrogen pipeline flame arrester operating status detection system is used to implement the above-mentioned operating status detection method. Its hardware structure includes: a processor for processing data, a data storage device for storing abnormal information data, and a data buffer for caching various sensor information data. The processor is burned with computer program instructions for implementing the above-mentioned detection method. The data buffer is electrically connected to a vibration sensor for capturing high-frequency mechanical vibration information of the flame arrester, a flow meter for real-time measurement of hydrogen flow rate in the pipeline, a temperature sensor for detecting the ambient temperature of the flame arrester accessories, and a hydrogen sensor for detecting the hydrogen concentration of the flame arrester accessories.

[0041] Preferably, the vibration sensor is installed at a vibration sensitive point of the flame arrester housing, and the sampling frequency of the vibration sensor is greater than or equal to 10kHz; the flow meter is installed on the hydrogen pipeline corresponding to the flame arrester, and the sampling frequency of the flow meter is consistent with the sampling frequency of the vibration sensor.

[0042] Compared with the prior art, the present invention has the following beneficial effects:

[0043] 1. This invention provides a method for detecting the operating status of hydrogen pipeline flame arresters. By detecting and analyzing the flame arrester's vibration and hydrogen flow information, it accurately determines the flame arrester's mechanical status. Combined with temperature and hydrogen concentration detection and judgment, this method can effectively detect and determine the flame arrester's current operating status in real time. Furthermore, if the flame arrester's operating status becomes abnormal, it promptly alerts relevant personnel to repair or replace the flame arrester, effectively avoiding safety hazards caused by flame arrester failure.

[0044] 2. This invention provides a hydrogen pipeline flame arrester operating status detection system that uses multiple detection sensors to monitor the flame arrester's operating status in real time and promptly provide feedback on any abnormalities, thereby effectively reducing the tedious manual inspection process and avoiding omissions. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] The above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily understood by reading the following detailed description with reference to the accompanying drawings. In the accompanying drawings, several embodiments of the present invention are shown in an illustrative and non-limiting manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein:

[0046] Figure 1 It is an operation flow chart of the operation status detection method;

[0047] Figure 2 It is the structural block diagram of the operation status detection system;

[0048] In the figure: 1 is a processor; 2 is a data storage device; 3 is a data buffer; 4 is a vibration sensor; 5 is a flow meter; 6 is a temperature sensor; and 7 is a hydrogen sensor. DETAILED DESCRIPTION

[0049] The technical features of the present invention are further described in detail below with reference to the accompanying drawings so that those skilled in the art can understand them.

[0050] In actual hydrogen-related production activities, the installation and application scenarios of flame arresters are as follows: in a nozzle structure using hydrogen as fuel, a flame arrester of corresponding diameter should be installed on the nozzle that transmits hydrogen behind it; when hydrogen is used as fuel for purposes such as welding or flame cutting, a flame arrester should be installed on the branch pipe of each unit or group of hydrogen-using equipment; flame arresters should be installed on the transmission pipeline of the hydrogen station; at the same time, in the production field using hydrogen as a chemical raw material, flame arresters should be installed on the hydrogen transmission pipeline connecting the chemical plant to the production equipment; in summary, the environmental factors that affect the judgment of the flame arrester status in actual application scenarios are often more complex. Therefore, multi-dimensional detection and judgment are required from the aspects of vibration information, hydrogen flow information, temperature information, and hydrogen concentration information.

[0051] Moreover, in the actual application process of detecting and judging the operating status of the flame arrester, it is usually necessary to consider complex conditions such as multiple fault coupling, strong background noise, and dynamic changes in the hydrogen flow rate in the pipeline. The vibration information of the flame arrester can effectively reflect the mechanical state of the flame arrester under complex environmental conditions. Therefore, by detecting and analyzing the vibration information of the flame arrester, and then considering the impact of hydrogen flow changes on the vibration information, the mechanical state of the flame arrester can be judged by extracting relevant features. Combined with temperature and hydrogen concentration detection, the current operating status of the flame arrester can be effectively detected and determined in real time.

[0052] A method for detecting the operating status of a hydrogen pipeline flame arrester, wherein the operating logic of the operating status detection method is as follows: Figure 1 The specific operation steps are as follows:

[0053] Step S1: Obtain historical data under normal working conditions, and set threshold parameters corresponding to various detection information according to the performance standards of the corresponding flame arrester model and historical normal data;

[0054] Specifically, corresponding sensors for detecting vibration, hydrogen flow, temperature, and hydrogen concentration are adapted and installed respectively. The threshold parameters of temperature and hydrogen concentration can be directly set according to the performance standards of the flame arrester, and are used to determine whether the ambient temperature of the flame arrester is safe and whether there is a hydrogen leak.

[0055] In addition, the corresponding threshold parameters for judging the mechanical state of the flame arrester are calculated based on the historical normal data of vibration information and hydrogen flow information. Therefore, it is necessary to obtain historical normal data on vibration and hydrogen flow for calculation. If relevant historical normal data is saved, it can be directly imported and referenced. If relevant historical data is not saved, it is necessary to manually confirm that the flame arrester is in a normal state and then obtain data records under normal operating conditions for a period of time as historical normal data. The sampling time for historical normal data is generally 10 minutes to 24 hours.

[0056] Step S2: Acquire detection information from various sensors in real time and pre-process the collected vibration information and hydrogen flow information;

[0057] Specifically, the vibration sensor is installed at the vibration-sensitive point of the flame arrester housing, and the sampling frequency needs to be ≥10kHz to capture high-frequency mechanical vibrations; the flow meter is installed on the hydrogen pipeline corresponding to the flame arrester, and the sampling frequency needs to be ≥100Hz to measure the hydrogen flow in real time. Generally, since high-frequency mechanical vibration information can effectively feedback the mechanical state of the flame arrester, the vibration sensor requires a higher sampling frequency to obtain sufficient detection information, while hydrogen flow detection does not require an excessively high sampling frequency to obtain the flow change characteristics. However, in the actual application scenario of this detection method, in order to calculate the correlation regression coefficient between the vibration characteristics and the flow information, the data length of the vibration information and the flow information needs to be aligned. Therefore, the sampling frequency of the flow meter needs to be consistent with the sampling frequency of the vibration sensor. When the sampling frequency of the vibration sensor is set to 10kHz, the sampling frequency of the flow meter also needs to be set to 10kHz, and the vibration information segment and flow value are synchronously recorded with a period of 1 second. Each segment of vibration information contains 10,000 sampling data points, and each segment of flow information also contains 10,000 sampling data points.

[0058] The vibration information data and hydrogen flow information data are collected synchronously at the same sampling frequency, where the initial vibration information data at the t-th sampling moment is , the traffic information data at the tth sampling time is ;

[0059] In addition, in order to reduce the impact of environmental factors on vibration information, the collected vibration information needs to be denoised and trend items removed. Preferably, this solution uses adaptive wavelet threshold denoising method for denoising, and the wavelet base selects Sym8 wavelet, with 3 decomposition layers, which can eliminate high-frequency electromagnetic interference in vibration information; preferably, this solution uses least squares fitting to eliminate trend items in vibration information, which can eliminate low-frequency drift in vibration information, such as sensor baseline drift and temperature influence, and avoid trend items interfering with IMF decomposition; wherein, the vibration information data at the t-th sampling moment is After preprocessing, the standard vibration information data at the tth sampling time is obtained ; The flow information preprocessing needs to be synchronized with the time stamp alignment, aligning the timestamp of the flow information with the timestamp of the vibration information;

[0060] In addition, for application scenarios with more complex environmental factors, the vibration information is relatively messy. When the vibration information is decomposed by the EMD algorithm, since the endpoints of the signal cannot be at the maximum or minimum value at the same time, the upper and lower envelopes will diverge at both ends of the data sequence, and this divergence will gradually move inward as the operation proceeds, thereby affecting the entire data sequence. This is the so-called endpoint effect of the EMD method. At this time, preprocessing of the vibration information requires suppressing the endpoint effect. The extreme value extension method or the endpoint mirror method can be used to alleviate the distortion caused by the EMD envelope interpolation at both ends of the vibration information and avoid divergence of the decomposition results at both ends.

[0061] Step S3: Perform time-frequency domain analysis on the pre-processed vibration information to obtain multiple IMF components and residuals, extract vibration features and perform preliminary vibration abnormality judgment;

[0062] Preferably, this solution uses the EMD algorithm to analyze vibration information because vibration information may contain multiple frequency components. For example, different components have different vibration frequencies. The empirical mode decomposition algorithm, that is, the EMD algorithm, can decompose the intrinsic mode function IMF corresponding to each frequency component. After the vibration information is decomposed by EMD, each IMF component may correspond to the vibration mode of one of the components, and then the relevant IMF component features are extracted to analyze the characteristics of each vibration source; therefore, the EMD algorithm can fully and effectively analyze the vibration information to facilitate abnormal diagnosis.

[0063] Specifically, the vibration information is parsed by the EMD algorithm to obtain the decomposition data of the vibration information, including the standard vibration information data preprocessed at the t-th sampling moment From high frequency to low frequency, it is decomposed into n IMF components and residuals. The expression formula of the decomposition result is:

[0064]

[0065] Among them, IMF is the intrinsic mode function, represents the i-th IMF component of the vibration information at the t-th sampling moment, represents the residual signal of the vibration information at the t-th sampling moment, and n represents the number of IMF components or the number of decomposition levels;

[0066] Generally, the vibration information data of a flame arrester requires a 4- to 6-layer decomposition. This solution uses a 4-layer decomposition as an example, decomposing the vibration information data of the flame arrester from high frequency to low frequency into four IMF components and residuals. High-frequency IMF components can reflect mechanical problems such as local loosening, micro-impact noise, structural resonance, periodic wear, and pipeline fluid pulsation coupled vibration. Low-frequency IMF components generally represent factors such as background noise and low-frequency mechanical vibration. Therefore, in practical applications, it is generally only necessary to consider the relevant characteristics of IMF1, IMF2, and IMF3 components to determine the current mechanical status of the flame arrester.

[0067] In addition, for vibration information, the CEEMDAN algorithm, i.e., the adaptive noise-assisted decomposition algorithm, can be used to suppress modal aliasing and optimize the decomposed signal, or the ICA algorithm or PCA algorithm can be used to extract effective features and optimize the decomposed signal. However, in actual applications, the calculation process of these algorithms is too cumbersome and requires a large amount of computing resources and hardware resources for processing data. The cost is too high and is not suitable for popularization and application. Moreover, if the calculation time is too long, it is difficult to ensure the real-time nature of the detection information. Therefore, this scheme uses the EMD algorithm to process and analyze the vibration information, which can take into account both the amount of data calculation and the accuracy of judgment.

[0068] Specifically, the features of each IMF component are extracted, including calculating the energy value of each IMF component at the t-th sampling moment , energy ratio and the total energy entropy of the vibration information at the t-th sampling moment ;

[0069] According to the sampling characteristics of the vibration sensor, the collected vibration information is discrete data. Since each step of the EMD algorithm processes the original signal or its residual, each IMF component decomposed will maintain the same number of data points as the original signal. Therefore, the data length of each IMF component is equal and the same as the original signal length. At the same time, in order to avoid the calculated value being too large, it can be normalized by dividing it by the total number of vibration information data M at the current sampling moment.

[0070] in, It represents the energy of the i-th IMF component at the t-th sampling time, and the calculation formula is:

[0071]

[0072] Where, Represents the summation function, M represents the number of vibration information data at the t-th sampling time, and each IMF component contains M decomposition data. represents the mth decomposition data of the i-th IMF component;

[0073] also, It represents the energy proportion of the i-th IMF component at the t-th sampling time, and the calculation formula is:

[0074]

[0075] also, It represents the total energy entropy of the vibration information at the t-th sampling moment, and the calculation formula is:

[0076]

[0077] Where ln represents the natural logarithm, and n represents the number of IMF components;

[0078] Specifically, the total energy entropy of the current vibration information can be used to quantify the stability of the energy distribution of each IMF component. When the flame arrester is in a normal state, the energy distribution of the vibration information is stable, and the entropy value of the total energy entropy is low. When the flame arrester has a mechanical failure, the energy of the high-frequency component of the vibration information suddenly increases, and the entropy value of the total energy entropy increases. Therefore, the change in the entropy value of the total energy entropy can be used to make a preliminary abnormality judgment on the vibration information at the current sampling moment.

[0079] To make a preliminary judgment on vibration abnormality, it is necessary to set a threshold F. ≤F, it is determined that the vibration information at the current sampling moment is normal, and the mechanical state of the flame arrester at the current sampling moment is normal. >F, it is preliminarily determined that the vibration information at the current sampling moment is abnormal, and it is necessary to further combine the flow information at the current sampling moment to determine the abnormality of the mechanical state of the flame arrester; in relevant experimental tests, the normal value range of total energy entropy is between 1.0 and 1.5. Therefore, in actual detection applications, the threshold F can be set to 1.8;

[0080] In addition, since the vibration of the flame arrester in the pipeline is closely related to the gas flow rate, in general, the vibration intensity usually increases with the increase of flow rate or flow velocity. Therefore, the historical normal data when the hydrogen flow rate is zero or the hydrogen flow rate is small can be selected, and the threshold F can be set by calculating the corresponding energy entropy so that the threshold F can reasonably screen the vibration information; when the total energy entropy is When the value is less than or equal to the threshold F, it indicates that the vibration information at the current sampling moment is similar to the historical normal data. Therefore, it can be determined that the vibration information at the current sampling moment is normal and the mechanical state of the flame arrester at the current sampling moment is normal. As a result, the calculation process related to the flow information at the current sampling moment can be omitted, thereby reducing the amount of calculation and saving computing resources.

[0081] Step S4: In response to the abnormal vibration characteristic, calculating the dynamic vibration threshold corresponding to the current sampling moment;

[0082] when When the value is greater than F, it is preliminarily determined that the vibration information at the current sampling moment is abnormal. Since the change in hydrogen flow rate will affect the detection of vibration information, it is necessary to introduce the flow information at the current sampling moment to further judge the abnormality of the vibration information that is preliminarily determined to be abnormal, eliminate the influence of the flow change at the current sampling moment on the vibration information, avoid false alarm triggering due to flow change, and thus more accurately judge the mechanical state of the flame arrester at the current sampling moment;

[0083] At the same time, since the vibration of the flame arrester is closely related to the hydrogen flow rate in the pipeline, in general, the vibration intensity usually increases with the increase of flow rate or flow velocity. There is a positive correlation between the vibration energy and the vibration intensity, and the vibration intensity is positively correlated with the hydrogen flow rate. Therefore, the relationship between the vibration energy E and the hydrogen flow rate Q can be established through a linear regression model;

[0084] Specifically, in order to judge the abnormality of the mechanical state of the flame arrester in combination with the flow information at the current sampling moment, it is necessary to obtain the correlation regression coefficient between the vibration energy value and the flow information based on the historical normal data, including obtaining the decomposition signal of the vibration information in the historical normal data through the EMD algorithm, obtaining n historical IMF components and residuals, and calculating the historical energy value of each historical IMF component accordingly, and then establishing the relationship between the historical vibration information characteristics and the historical flow information characteristics through the linear regression model, so as to obtain the historical vibration energy corresponding to each historical IMF component. Compared with historical hydrogen flow The regression coefficient between

[0085] According to the calculation formula of the energy value, since the energy value is obtained by normalizing the sum of the squares of M data, the M data corresponding to the energy value can be expanded into the form of a matrix series. At the same time, the flow data also has M data due to the same sampling frequency, and the flow data can be converted into a corresponding matrix series to facilitate the calculation of the regression coefficient.

[0086] The specific calculation process of the regression coefficient is as follows:

[0087] The historical vibration energy corresponding to each historical IMF component Converted into the form of matrix series and used as the dependent variable of the linear regression model, the i-th historical vibration energy The matrix sequence expression is:

[0088]

[0089] The corresponding historical traffic information data is also converted into the form of a matrix series as an independent variable, and the corresponding historical traffic information data The matrix sequence expression is:

[0090]

[0091] The relationship between historical vibration information characteristics and historical flow information characteristics is established through a linear regression model to obtain the historical vibration energy corresponding to each historical IMF component Compared with historical hydrogen flow The regression coefficient between

[0092] A linear regression model is established for each historical IMF component in the historical normal data, where the i-th historical vibration energy The linear regression model is: , i ranges from 1 to n, and represents the regression coefficient corresponding to the i-th historical IMF component;

[0093] The regression coefficient corresponding to each historical IMF component is obtained using the least squares formula. The specific calculation formula for the regression coefficient corresponding to the i-th historical IMF component is:

[0094]

[0095] Where, represents the i-th historical vibration energy The mth data in the matrix sequence, represents the i-th historical vibration energy The average value of M data in the matrix series, Indicates the corresponding historical traffic information data The mth data in the matrix sequence, Indicates the corresponding historical traffic information The average value of M data in .

[0096] In addition, after obtaining the regression coefficient corresponding to each historical IMF component, the theoretical energy value corresponding to each IMF component at the current sampling moment can be calculated based on the regression coefficient corresponding to each historical IMF component, thereby obtaining the dynamic vibration threshold at the current sampling moment;

[0097] The calculation process of the dynamic vibration threshold at the current sampling moment is as follows:

[0098] Based on the obtained regression coefficient, assuming that the current sampling time is the t-th sampling time, the theoretical energy value of each IMF component at the t-th sampling time is calculated using the following formula:

[0099]

[0100] Where, represents the theoretical energy value of the i-th IMF component at the t-th sampling moment, Represents the flow information data at the t-th sampling moment, and represents the regression coefficient corresponding to the i-th IMF component obtained based on historical normal data;

[0101] The dynamic vibration threshold at sampling time t is , the calculation formula is:

[0102]

[0103] Where k is the error correction coefficient. Generally, the value of k ranges from 1.0 to 1.2. The value of k is related to the environment in the actual application scenario. The greater the environmental noise, the larger the value of k. Conversely, the smaller the environmental noise, the closer the value of k is to 1.

[0104] Afterwards, since flow information is positively correlated with vibration information, in order to avoid the logical confusion caused by multiple comparisons and judgments, the average value of the energy values ​​of each IMF component at the tth sampling moment is compared with the corresponding dynamic vibration threshold value in an average processing manner, thereby determining the mechanical state of the flame arrester at the current sampling moment;

[0105] Get the energy average of each IMF component at the current sampling moment as the dynamic vibration threshold at the current sampling moment The comparison object is calculated as follows:

[0106]

[0107] Where, Represents the average energy of n IMF components at the t-th sampling time.

[0108] Step S5: determining whether the flame arrester's operating state at the current sampling moment is abnormal;

[0109] Specifically, the mechanical state of the flame arrester at the current sampling moment is determined. Taking the tth sampling moment as an example, when When , it means that the vibration information at the current sampling moment is within the normal fluctuation range, and the mechanical state of the flame arrester is normal. When , it means that the vibration information at the current sampling moment is abnormal, and the mechanical state of the flame arrester is abnormal, then it is determined that the current state of the flame arrester is abnormal;

[0110] Then, combined with the detection information of temperature and hydrogen concentration, it is judged whether the ambient temperature of the flame arrester is safe and whether there is a hydrogen leak. The temperature and hydrogen concentration information detected at the current sampling moment are compared with the set thresholds. When either the temperature or the hydrogen concentration is judged to be abnormal, the current state of the flame arrester is determined to be abnormal.

[0111] Step S6: When the current state of the flame arrester is determined to be abnormal, an abnormality alarm is triggered and corresponding abnormality information data is recorded;

[0112] Specifically, when the abnormal alarm is triggered S times in a short period of time or continuously, the relevant staff will be reminded to handle it manually. Generally, the value of S is 3. When the abnormal alarm is triggered 3 times or more in a short period of time or continuously, the relevant staff will be reminded that emergency handling is required. The relevant staff will disassemble the flame arrester for manual inspection and confirmation, and then perform repair or replacement operations.

[0113] A hydrogen pipeline flame arrester operating status detection system, such as Figure 2 As shown, the hardware structure for implementing the above-mentioned operation status detection method includes a processor 1 for processing data, a data storage device 2 for storing abnormal information data, and a data buffer 3 for caching various sensor information data. The processor 1 is burned with computer program instructions for implementing the above-mentioned detection method. The data buffer 3 is electrically connected to a vibration sensor 4 for capturing high-frequency mechanical vibration information of the flame arrester, a flow meter 5 for real-time measurement of the hydrogen flow rate in the pipeline, a temperature sensor 6 for detecting the ambient temperature of the flame arrester accessories, and a hydrogen sensor 7 for detecting the hydrogen concentration of the flame arrester accessories.

[0114] Specifically, the vibration sensor 4 is installed at the vibration sensitive point of the flame arrester housing, and the sampling frequency of the vibration sensor 4 is greater than or equal to 10kHz; the flow meter 5 is installed on the hydrogen pipeline corresponding to the flame arrester, and the sampling frequency of the flow meter 5 is consistent with the sampling frequency of the vibration sensor 4.

[0115] The embodiments described in the present invention are merely descriptions of preferred implementations of the present invention and are not limited to the precise structures described above and shown in the accompanying drawings. Various modifications and changes can be made without departing from the scope of protection thereof. Without departing from the design concept of the present invention, various variations and improvements made to the technical solutions of the present invention by engineers and technicians in this field should fall within the scope of protection of the present invention.

Claims

1. A method for detecting the operating status of a hydrogen pipeline flame arrester, characterized in that: Acquire historical normal data and set threshold parameters corresponding to various detection information; obtain detection information from various sensors in real time and perform preprocessing; perform time-frequency domain analysis on the preprocessed vibration information to obtain multiple IMF components and residuals, extract vibration characteristics for preliminary vibration anomaly judgment; in response to abnormal vibration characteristics, calculate the dynamic vibration threshold corresponding to the current sampling time; and make an abnormal judgment on the operating status of the flame arrester at the current sampling time; Among them, the corresponding sensors for detecting vibration, hydrogen flow, temperature, and hydrogen concentration are adapted and installed respectively, and the threshold parameters corresponding to each detection information are set according to the performance standards of the corresponding flame arrester model and historical normal data. Among them, the threshold parameters of temperature and hydrogen concentration can be directly set according to the performance standards of the flame arrester. The dynamic vibration threshold for judging the mechanical state of the flame arrester requires obtaining historical normal data on vibration and hydrogen flow for calculation. If relevant historical normal data is saved, it can be directly imported and referenced. If relevant historical data is not saved, it is necessary to manually check and confirm that the flame arrester is in a normal state, and then obtain data records under normal operating conditions for a period of time as historical normal data. Vibration information data and hydrogen flow information data are synchronously collected at the same sampling frequency, wherein the initial vibration information data at the t-th sampling moment is z(t), and the flow information data at the t-th sampling moment is Q(t); the vibration information is preprocessed, including noise reduction processing for eliminating high-frequency electromagnetic interference in the vibration information; trend removal processing for eliminating low-frequency drift in the vibration information, such as sensor baseline drift and temperature effects; wherein, after preprocessing the vibration information data z(t) at the t-th sampling moment, the standard vibration information data x(t) at the t-th sampling moment is obtained; the flow information is preprocessed, including synchronous time stamp alignment for aligning the timestamp of the flow information with the timestamp of the vibration information; Among them, the vibration characteristics include the energy value and the total energy entropy of the current vibration information. The energy of the i-th IMF component at the t-th sampling time is E t，i ; The total energy entropy of the vibration information at the t-th sampling moment is H t , the calculation formula is: Where, P t，i represents the energy proportion of the i-th IMF component at the t-th sampling moment, ln represents the natural logarithm, and n represents the number of IMF components; the dynamic vibration threshold is Td, and the calculation formula is: Where k is the error correction coefficient, ET i Indicates the theoretical energy value of the i-th IMF component at the current sampling moment.

2. The operating status detection method according to claim 1, characterized in that: The pre-processed vibration information is analyzed in the time-frequency domain to obtain multiple IMF components and residuals, including parsing the vibration information through the EMD algorithm to obtain the decomposition data of the vibration information. The standard vibration information data x(t) pre-processed at the t-th sampling time is decomposed from high frequency to low frequency into n IMF components and residuals. The expression formula of the decomposition result is: Where imf i (m) represents the i-th IMF component of the vibration information at the t-th sampling time, r(t) represents the residual signal of the vibration information at the t-th sampling time, and n represents the number of IMF components or the number of decomposition levels.

3. The operating status detection method according to claim 2, wherein: Extract vibration features to make preliminary vibration anomaly judgment, including calculating the energy value E of each IMF component at the tth sampling time t，i , energy proportion P t，i and total energy entropy H t ;E t，i It represents the energy of the i-th IMF component at the t-th sampling time, and the calculation formula is: Where imf i (m) represents the mth decomposition data of the i-th IMF component, ∑ represents the summation function, and M represents the number of vibration information data at the current sampling moment; P t，i It represents the energy proportion of the i-th IMF component at the t-th sampling time, and the calculation formula is: Set the threshold F, when H t ≤F, it is determined that the vibration information at the t-th sampling moment is normal, and the mechanical state of the flame arrester at the t-th sampling moment is normal. When H t >F, it is preliminarily determined that the vibration information at the t-th sampling moment is abnormal, and it is necessary to further combine the flow information Q(t) at the t-th sampling moment to make an abnormal judgment on the mechanical state of the flame arrester.

4. The operating status detection method according to claim 3, characterized in that: In response to abnormal vibration characteristics, the dynamic vibration threshold corresponding to the current sampling moment is calculated, including obtaining the correlation regression coefficient between the vibration energy value and the flow information based on historical normal data, obtaining the decomposition signal of the vibration information in the historical normal data through the EMD algorithm, obtaining n historical IMF components and residuals, and calculating the energy value of each historical IMF component accordingly; The historical vibration energy EL corresponding to each historical IMF component is converted into the form of a matrix series and used as the dependent variable of the linear regression model. The i-th historical vibration energy EL i The matrix sequence expression is: HE i =[THE i (1),THE i (2),…,THE i (M)] T ; The corresponding historical traffic information data is also converted into a matrix series form as an independent variable. The matrix series expression of the corresponding historical traffic information data QL is: QL=[QL(1),QL(2),…,QL(M)] T ; The relationship between historical vibration information characteristics and historical flow information characteristics is established through a linear regression model, and the regression coefficient between the historical vibration energy EL and the historical hydrogen flow QL corresponding to each historical IMF component is obtained; A linear regression model is established for each historical IMF component in the historical normal data, where the i-th historical vibration energy EL i The linear regression model is: EL i =α i ×QL+β i , i ranges from 1 to n, α i and β i represents the regression coefficient corresponding to the i-th historical IMF component; The regression coefficient corresponding to each historical IMF component is obtained using the least squares formula. The specific calculation formula for the regression coefficient corresponding to the i-th historical IMF component is: Where, EL i (m) represents the i-th historical vibration energy EL i The mth data in the matrix sequence, Represents the i-th historical vibration energy EL i The average value of M data in the matrix series of QL, QL(m) represents the mth data in the matrix series of the corresponding historical traffic information data QL, Represents the average value of M data in the corresponding historical traffic information QL.

5. The operating status detection method according to claim 4, characterized in that: In response to the abnormal vibration characteristics, the dynamic vibration threshold corresponding to the current sampling moment is calculated, and the theoretical energy value corresponding to each IMF component at the current sampling moment is calculated according to the regression coefficient corresponding to each historical IMF component, wherein the theoretical energy value ET of the i-th IMF component at the t-th sampling moment is i The calculation formula is: ET i =α i ×Q(t)+β i , where Q(t) represents the flow information data at the t-th sampling moment; Obtain the energy average of each IMF component at the current sampling moment as the comparison object of the dynamic vibration threshold Td at the current sampling moment. The calculation formula is: Where, Represents the average energy of n IMF components at the t-th sampling time.

6. The operating status detection method according to claim 5, characterized in that: The abnormal operation state of the flame arrester at the current sampling time is judged, including judging the mechanical state of the flame arrester at the current sampling time. Taking the tth sampling time as an example, when When , it means that the vibration information at the current sampling moment is within the normal fluctuation range, and the mechanical state of the flame arrester is normal. When , it means that the vibration information at the current sampling moment is abnormal, and the mechanical state of the flame arrester is abnormal, then it is determined that the current state of the flame arrester is abnormal; Combined with the detection information of temperature and hydrogen concentration, the temperature and hydrogen concentration information detected at the current sampling moment are compared with the set threshold values. When either the temperature or the hydrogen concentration is judged to be abnormal, the current state of the flame arrester is judged to be abnormal. When the current state of the flame arrester is judged to be abnormal, an abnormal alarm is triggered and the corresponding abnormal information data is recorded.

7. A hydrogen pipeline flame arrester operating status detection system, used to implement the operating status detection method according to any one of claims 1 to 6, characterized in that: The invention comprises a processor (1) for processing data, a data memory (2) for storing abnormal information data, and a data buffer (3) for caching various sensor information data. The processor (1) is burned with computer program instructions for implementing the above-mentioned detection method. The data buffer (3) is electrically connected to a vibration sensor (4) for capturing high-frequency mechanical vibration information of the flame arrester, a flow meter (5) for real-time measurement of hydrogen flow in the pipeline, a temperature sensor (6) for detecting the ambient temperature of the flame arrester accessories, and a hydrogen sensor (7) for detecting the hydrogen concentration of the flame arrester accessories.

8. The operating status detection system according to claim 7, characterized in that: The vibration sensor (4) is installed at a vibration sensitive point of the flame arrester housing, and the sampling frequency of the vibration sensor (4) is greater than or equal to 10 kHz; the flow meter (5) is installed on the hydrogen pipeline corresponding to the flame arrester, and the sampling frequency of the flow meter (5) is consistent with the sampling frequency of the vibration sensor (4).

Images