Gas filling intelligent monitoring system based on Internet of Things

Abstract

The invention discloses a fuel gas filling intelligent monitoring system based on the Internet of Things, and particularly relates to the technical field of fuel gas filling intelligent monitoring. Fuel gas flowing pressure pulse information, ion concentration fluctuation information, local temperature gradient change information and pipeline stress fatigue accumulation information in the fuel gas filling process are obtained; based on the gas flow abnormal pressure pulse coefficient, the ion concentration fluctuation coefficient, the local temperature gradient surge coefficient and the stress fatigue accumulation coefficient, a high-pressure backflow precursor hidden danger evaluation model is constructed, a high-pressure backflow precursor hidden danger evaluation index is output, and accurate evaluation of the high-pressure backflow precursor hidden danger is achieved. When a high-pressure backflow precursor hidden danger is detected, the pressure change rate is adjusted in a self-adaptive mode, so that pressure adjustment in the gas filling process is more stable, the possibility of high-pressure backflow is reduced, damage to key equipment such as pipelines and valves due to instantaneous shock waves is effectively reduced, the service life of the equipment is prolonged, and the production cost is reduced. And the long-term operation stability of the gas filling system is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent monitoring of gas filling, and more specifically, to an intelligent monitoring system for gas filling based on the Internet of Things. Background Art

[0002] During the gas filling process, the accuracy of pressure control is crucial. However, when the filling pressure distribution is uneven, the gas may instantly flow back from the high-pressure area to the low-pressure area, forming a strong shock wave, the so-called high-pressure reflux phenomenon. This phenomenon not only causes sharp fluctuations in gas flow rate and pressure, but may also cause irreversible damage to the pipelines, valves and other key equipment in the gas filling system. Existing gas filling monitoring systems often rely on traditional sensor data and static threshold warnings. They can only trigger warning prompts after the high-pressure reflux phenomenon actually occurs, thus missing the opportunity to identify its potential precursors before the accident occurs. It is impossible to accurately perceive its potential precursors before the high-pressure reflux phenomenon occurs. Whenever the high-pressure reflux phenomenon occurs, the instantaneous shock wave generates a huge impact force on the equipment and pipelines, which often causes irreversible damage to the gas filling system, affecting the equipment life and operational safety. Summary of the Invention

[0003] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a gas filling intelligent monitoring system based on the Internet of Things to solve the problems raised in the above-mentioned background technology.

[0004] To achieve the above object, the present invention provides the following technical solutions: The gas filling intelligent monitoring system based on the Internet of Things includes a pressure pulse module, an ion concentration module, a temperature gradient module, a strain fatigue module, a precursor hidden danger assessment module, and an intelligent pressure regulation module; The pressure pulse module is used to obtain the gas flow pressure pulse information during the gas filling process and obtain the gas flow abnormal pressure pulse coefficient based on the gas flow pressure pulse information; The ion concentration module is used to obtain the ion concentration fluctuation information during the gas filling process and obtain the ion concentration fluctuation coefficient based on the ion concentration fluctuation information; The temperature gradient module is used to obtain the local temperature gradient change information during the gas filling process and obtain the local temperature gradient surge coefficient based on the local temperature gradient change information; The strain fatigue module is used to obtain the pipeline stress fatigue accumulation information during the gas filling process and obtain the stress fatigue accumulation coefficient based on the pipeline stress fatigue accumulation information; The precursor hazard assessment module is used to construct a high-pressure backflow precursor hazard assessment model based on the abnormal gas flow pressure pulse coefficient, ion concentration fluctuation coefficient, local temperature gradient surge coefficient, and stress fatigue accumulation coefficient. It outputs a high-pressure backflow precursor hazard assessment index and assesses the probability of the occurrence of the high-pressure backflow precursor hazard. The intelligent pressure regulating module is used to adaptively adjust the pressure change rate when there is a hidden danger of high-pressure backflow.

[0005] In a preferred embodiment, by acquiring gas flow pressure pulse information during the gas filling process, analyzing the pressure fluctuation of the gas flow during the gas filling process, and obtaining the abnormal pressure pulse coefficient of the gas flow, the degree of pressure fluctuation of the gas flow during the gas filling process is measured; The logic for obtaining the abnormal pressure pulse coefficient of gas flow is as follows: High-precision pressure sensors are used to collect instantaneous pressure signals at different time points during the gas flow process and store them in time series: ,in represents the instantaneous pressure value of the i-th sampling point, , is a positive integer; calculate the mean pressure: ,in Indicates the mean pressure; calculate the RMS pressure: ,in Represents the RMS value of pressure; calculate the pressure deflection: ,in Express the pressure skewness; calculate the pressure kurtosis: ,in Represents the pressure kurtosis; the time domain pressure signal is converted to the frequency domain using fast Fourier transform: in Frequency domain pressure signal, represents the time domain pressure signal, represents the fast Fourier transform and calculates the main frequency of pressure: ,in represents the main frequency of pressure, Indicates that the Get the maximum value Value; calculate the abnormal pressure pulse coefficient of gas flow, the expression is as follows: ,in Indicates the abnormal pressure pulse coefficient of gas flow, represents the preset scaling factor, and Both are greater than 0.

[0006] In a preferred embodiment, by obtaining ion concentration fluctuation information during the gas filling process, the dynamic change of ion concentration during the gas filling process is analyzed, and the ion concentration fluctuation coefficient is obtained to measure the degree of dynamic change of ion concentration during the gas filling process; The logic for obtaining the ion concentration fluctuation coefficient is as follows: Install a high-precision concentration sensor in the gas filling pipeline to collect ion concentration signals: ,in represents the ion concentration value at the bth moment, , is a positive integer; for ion concentration signal Construct an m-dimensional vector: ,in , is a positive integer; for any two ion concentration vectors and ,and , calculate the ion concentration similarity distance: ,in Represents the similarity distance of ion concentration, if , it means that the two ion concentration vectors are similar, and the two ion concentration vectors are marked as an ion concentration similarity vector pair, where Represents the similarity threshold; calculate the ion concentration fluctuation coefficient, the expression is as follows: ,in represents the number of similarity vector pairs of ion concentrations when the embedding dimension is m+1, represents the number of similarity vector pairs of ion concentrations when the embedding dimension is m, represents the ion concentration fluctuation coefficient.

[0007] In a preferred embodiment, by obtaining local temperature gradient change information during the gas filling process, analyzing the drastic temperature change in the local area during the gas filling process, and obtaining the local temperature gradient surge coefficient, the drastic degree of the temperature change in the local area during the gas filling process is measured; The logic for obtaining the local temperature gradient surge coefficient is as follows: During the gas filling process, high-precision temperature sensors are placed in key local areas to collect temperature signals in real time and obtain the temperature signal time series. ; Select Daubechies wavelet function to perform continuous wavelet transform on the temperature signal time series and calculate the wavelet coefficients: ,in represents the wavelet coefficients, represents the scale parameter, represents the translation parameter, Represents the complex conjugate of the wavelet function; calculates the local temperature gradient energy: ,in Represents the local temperature gradient energy; divide the local temperature gradient energy into fixed time window lengths, and record each time window as , , is a positive integer; for each time window, the average temperature gradient strength is calculated: ,in represents the average temperature gradient intensity, Indicates the time window The total number of sampling points in the time window; calculate the maximum gradient strength: ,in Indicates the maximum gradient intensity; calculate the local temperature gradient surge coefficient, the expression is as follows: ,in Represents the local temperature gradient surge coefficient.

[0008] In a preferred embodiment, by obtaining pipeline stress fatigue accumulation information during the gas filling process, analyzing the stress fatigue accumulation of the pipeline during the gas filling process, and obtaining a stress fatigue accumulation coefficient, the degree of stress fatigue accumulation of the pipeline during the gas filling process is measured; The logic for obtaining the stress fatigue accumulation coefficient is as follows: During the gas filling process, the cyclic stress of the pipeline is obtained by high-precision stress sensors , calculate the stress intensity factor: ,in represents the stress intensity factor, represents the shape constant, Indicates the crack area of ​​the current pipeline; calculates the crack growth rate: ,in 、 is the material fatigue constant of the pipeline, is the stress intensity factor range, ,in represents the maximum value of the stress intensity factor, Indicates the minimum value of stress intensity factor; calculates the critical fatigue life of the pipeline: ,in represents the critical fatigue life of the pipeline, represents the initial crack area, Indicates the critical crack area at fracture; calculate the stress fatigue accumulation coefficient, the expression is as follows: ,in represents the stress fatigue accumulation coefficient, Indicates the current cyclic stress of the pipeline.

[0009] In a preferred embodiment, a high-pressure backflow precursor hazard assessment model is constructed based on the abnormal pressure pulse coefficient of gas flow, the ion concentration fluctuation coefficient, the local temperature gradient surge coefficient, and the stress fatigue accumulation coefficient, and a high-pressure backflow precursor hazard assessment index is output. The model is based on the following formula , where They represent the abnormal pressure pulse coefficient of gas flow, the ion concentration fluctuation coefficient, the local temperature gradient surge coefficient, and the stress fatigue accumulation coefficient, respectively. They represent the preset proportional coefficients of the abnormal pressure pulse coefficient of gas flow, the ion concentration fluctuation coefficient, the local temperature gradient surge coefficient, and the stress fatigue accumulation coefficient, respectively, and Both are greater than 0.

[0010] In a preferred embodiment, the high-pressure backflow precursor hidden danger assessment index is compared with a preset high-pressure backflow precursor hidden danger assessment index threshold to determine whether a high-pressure backflow precursor hidden danger exists, as follows: If the high-pressure backflow precursor hazard assessment index is greater than the high-pressure backflow precursor hazard assessment index threshold, it means that there is currently a high-pressure backflow precursor hazard; if the high-pressure backflow precursor hazard assessment index is less than or equal to the high-pressure backflow precursor hazard assessment index threshold, it means that there is currently no high-pressure backflow precursor hazard.

[0011] In a preferred embodiment, when there is a high-pressure backflow precursor hidden danger, the pressure change rate is adaptively adjusted as follows: ,in Indicates the adjusted pressure change rate, represents the initial pressure change rate, Indicates the minimum safe pressure change rate, Indicates the high-voltage backflow precursor hidden danger assessment index, Indicates the high-voltage backflow precursor hazard assessment index threshold.

[0012] Technical effects and advantages of the present invention: 1. The present invention acquires information on gas flow pressure pulses, ion concentration fluctuations, local temperature gradient changes, and pipeline stress fatigue accumulation during the gas filling process. Based on the gas flow abnormal pressure pulse coefficient, ion concentration fluctuation coefficient, local temperature gradient surge coefficient, and stress fatigue accumulation coefficient, the model constructs a high-pressure backflow precursor hazard assessment model to output a high-pressure backflow precursor hazard assessment index. This model accurately assesses the high-pressure backflow precursor hazard, enabling timely detection of potential risks before high-pressure backflow occurs, thereby improving the safety and reliability of the gas filling process. When a high-pressure backflow precursor hazard is detected, the intelligent pressure regulation module adaptively adjusts the pressure change rate to ensure smoother pressure regulation during the gas filling process, reducing the likelihood of high-pressure backflow. This effectively reduces damage to key equipment such as pipelines and valves caused by transient shock waves, extends equipment service life, and enhances the long-term operational stability of the gas filling system. The system also possesses the ability to identify precursor hazards and proactively intervenes in the gas filling process through an intelligent pressure regulation strategy to avoid the occurrence of high-pressure backflow, ensuring both equipment safety and the stability of the gas filling process. This innovative technology combines precise monitoring with intelligent regulation, improving the intelligence level of the gas filling system. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] In order to facilitate understanding by those skilled in the art, the present invention will be further described below with reference to the accompanying drawings; Figure 1 Flowchart of the system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0014] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0015] Embodiment: The present invention provides Figure 1 The IoT-based intelligent gas filling monitoring system shown includes a pressure pulse module, an ion concentration module, a temperature gradient module, a strain fatigue module, a precursor hidden danger assessment module, and an intelligent pressure regulation module; The pressure pulse module is used to obtain the gas flow pressure pulse information during the gas filling process and obtain the gas flow abnormal pressure pulse coefficient based on the gas flow pressure pulse information; The ion concentration module is used to obtain the ion concentration fluctuation information during the gas filling process and obtain the ion concentration fluctuation coefficient based on the ion concentration fluctuation information; The temperature gradient module is used to obtain the local temperature gradient change information during the gas filling process and obtain the local temperature gradient surge coefficient based on the local temperature gradient change information; The strain fatigue module is used to obtain the pipeline stress fatigue accumulation information during the gas filling process and obtain the stress fatigue accumulation coefficient based on the pipeline stress fatigue accumulation information; The precursor hazard assessment module is used to construct a high-pressure backflow precursor hazard assessment model based on the abnormal gas flow pressure pulse coefficient, ion concentration fluctuation coefficient, local temperature gradient surge coefficient, and stress fatigue accumulation coefficient. It outputs a high-pressure backflow precursor hazard assessment index and assesses the probability of the occurrence of the high-pressure backflow precursor hazard. Intelligent pressure regulation module, used to adaptively adjust the pressure change rate when there is a hidden danger of high-pressure backflow; The pressure pulse module is used to obtain the gas flow pressure pulse information during the gas filling process and obtain the gas flow abnormal pressure pulse coefficient based on the gas flow pressure pulse information; The abnormal pressure pulse coefficient of gas flow in the present invention is used to measure the severity of pressure fluctuations, sudden changes and abnormal pulse signal characteristics during the gas filling process. The instantaneous pressure change data during the gas filling process is collected by a high-frequency pressure sensor to analyze whether there are abnormal situations with severe fluctuations in a short period of time. By calculating the abnormal pressure pulse coefficient of gas flow, the severity of pressure fluctuations and sudden changes during the gas filling process can be evaluated in real time, thereby identifying and predicting the precursor hidden dangers of high-pressure reflux and achieving accurate risk warning. When the abnormal pressure pulse coefficient of gas flow is large, it indicates that the gas flow has undergone abnormal fluctuations, which may lead to the occurrence of high-pressure reflux. The probability of the precursor hidden danger of high-pressure reflux is calculated based on this coefficient, which can more accurately quantify the severity of the potential risk. In this way, the system can not only perceive the high-pressure reflux hidden danger in advance, but also intelligently trigger the corresponding control mechanism, optimize the pressure regulation strategy before the hidden danger occurs, reduce the risk of damage to the gas filling system caused by high-pressure reflux, and improve the safety, stability and reliability of the filling process.

[0016] Therefore, by obtaining the gas flow pressure pulse information during the gas filling process, analyzing the pressure fluctuation of the gas flow during the gas filling process, and obtaining the abnormal pressure pulse coefficient of the gas flow, the pressure fluctuation degree of the gas flow during the gas filling process is measured; The logic for obtaining the abnormal pressure pulse coefficient of gas flow is as follows: High-precision pressure sensors are used to collect instantaneous pressure signals at different time points during the gas flow process and store them in time series: ,in represents the instantaneous pressure value of the i-th sampling point, , is a positive integer; calculate the mean pressure: ,in Indicates the mean pressure; calculate the RMS pressure: ,in Represents the RMS value of pressure; calculate the pressure deflection: ,in Express the pressure skewness; calculate the pressure kurtosis: ,in Represents the pressure kurtosis; the time domain pressure signal is converted to the frequency domain using fast Fourier transform: in Frequency domain pressure signal, represents the time domain pressure signal, represents the fast Fourier transform and calculates the main frequency of pressure: ,in represents the main frequency of pressure, Indicates that the Get the maximum value Value; calculate the abnormal pressure pulse coefficient of gas flow, the expression is as follows: ,in Indicates the abnormal pressure pulse coefficient of gas flow, represents the preset scaling factor, and All greater than 0; It should be noted that the above formulas are all dimensionless and numerical calculations. Common dimensionless methods include Min-Max normalization and Z-Score normalization, which will not be described here. Set it according to the actual situation. For example, adopt the expert empowerment method, that is, invite experts in related fields to determine the preset proportion coefficients of various indicators through professional opinion surveys and comprehensive evaluations, for example, It can be 0.2, 0.2, 0.3, 0.2, 0.1; During the gas filling process, high-precision pressure sensors collect pressure signals from the gas flow and store these signals in a time series format. The instantaneous pressure values ​​recorded at each sampling point are saved individually for subsequent data processing and analysis. After preliminary data processing, the mean pressure of the collected signals is calculated, a basic indicator of the overall gas flow pressure level. Next, the RMS value of the pressure signal is calculated, which helps assess the intensity and stability of pressure fluctuations.

[0017] Furthermore, the pressure signal's skewness and kurtosis are analyzed. Skewness assesses the symmetry of pressure fluctuations, while kurtosis reveals the extent of extreme values ​​in the pressure signal, which is particularly important for identifying potential pressure pulses. These statistics provide a comprehensive perspective, helping to identify abnormal characteristics in pressure fluctuations.

[0018] To further analyze the frequency characteristics of the pressure signal, a fast Fourier transform (FFT) is used to convert the time-domain pressure signal to the frequency domain. This step identifies the dominant frequency of the signal, which is often associated with specific oscillation modes or resonances in the system and is crucial for understanding the dynamic characteristics of gas flow. By calculating the dominant frequency of the pressure signal, potential abnormal pressure fluctuations can be further identified.

[0019] Ultimately, all statistical quantities and frequency domain analysis results are combined and, using a preset proportional coefficient, the abnormal gas flow pressure pulse coefficient is calculated. This coefficient is a comprehensive indicator that reflects the pressure fluctuation characteristics of the gas flow process. A larger value indicates more severe pressure fluctuations and a higher potential risk. This coefficient not only provides a basis for subsequent fault prediction but also serves as a key parameter for assessing high-pressure backflow precursor hazards, helping to promptly detect and implement measures to ensure the safety and stability of the gas filling process.

[0020] The ion concentration module is used to obtain the ion concentration fluctuation information during the gas filling process and obtain the ion concentration fluctuation coefficient based on the ion concentration fluctuation information; The ion concentration fluctuation coefficient in the present invention is used to measure the degree of temporal fluctuation of the ion concentration in the gas medium during the gas filling process. By analyzing abnormal changes in ion concentration, potential hidden dangers such as gas leakage, high-pressure reflux, and uneven ionization can be identified in advance. It can accurately reflect the dynamic changes in ion concentration during the gas filling process in real time and, by comprehensively quantifying ion concentration fluctuations, provide an early warning of the possible high-pressure reflux risk in the system. It can sensitively capture subtle changes caused by factors such as abnormal gas flow, gas leakage, or uneven ionization. The assessment based on the ion concentration fluctuation coefficient not only improves the monitoring accuracy and early warning capability of the gas filling process, but also realizes dynamic quantitative management of the safety status of the gas system, significantly improving the safety, stability, and reliability of the entire filling system. Therefore, by obtaining the ion concentration fluctuation information during the gas filling process, the dynamic change of ion concentration during the gas filling process is analyzed, and the ion concentration fluctuation coefficient is obtained to measure the dynamic change degree of ion concentration during the gas filling process; The logic for obtaining the ion concentration fluctuation coefficient is as follows: Install a high-precision concentration sensor in the gas filling pipeline to collect ion concentration signals: ,in represents the ion concentration value at the bth moment, , is a positive integer; for ion concentration signal Construct an m-dimensional vector: ,in , is a positive integer; for any two ion concentration vectors and ,and , calculate the ion concentration similarity distance: ,in Represents the similarity distance of ion concentration, if , it means that the two ion concentration vectors are similar, and the two ion concentration vectors are marked as an ion concentration similarity vector pair, where Represents the similarity threshold; calculate the ion concentration fluctuation coefficient, the expression is as follows: ,in represents the number of similarity vector pairs of ion concentrations when the embedding dimension is m+1, represents the number of similarity vector pairs of ion concentrations when the embedding dimension is m, represents the ion concentration fluctuation coefficient; It should be noted that the above formulas are all dimensionless and numerical calculations. Common dimensionless methods include Min-Max normalization and Z-Score normalization, which will not be described here. During the gas filling process, high-precision concentration sensors are installed in the pipeline to collect real-time ion concentration signals as the gas flows. These signals are recorded and stored in a time series format, with each recorded value corresponding to the ion concentration at a specific point in time. The collected data allows for further analysis and processing of the ion concentration.

[0021] During the data processing phase, an m-dimensional vector is constructed to represent the ion concentration changes within a specific time window. This m-dimensional vector contains concentration data for multiple consecutive time points, with each vector effectively describing the concentration trend around a specific moment. Next, the similarity distance between any two ion concentration vectors is calculated to assess the similarity of ion concentration changes at different time points.

[0022] Furthermore, by calculating the change in the number of similar ion concentration vector pairs at different embedding dimensions, we can understand the fluctuation characteristics of ion concentration. In this way, we can accurately identify abnormal fluctuations in concentration changes and assess the risks they may bring.

[0023] Finally, the ion concentration fluctuation coefficient is calculated based on the calculated number of ion concentration similarity vector pairs and the change in embedding dimension. This coefficient reflects the degree of ion concentration fluctuation during the gas filling process. A higher ion concentration fluctuation coefficient indicates more severe concentration fluctuations and greater potential danger. This coefficient provides an important basis for subsequent fault prediction and high-pressure backflow precursor hazard assessment.

[0024] The temperature gradient module is used to obtain the local temperature gradient change information during the gas filling process and obtain the local temperature gradient surge coefficient based on the local temperature gradient change information; The local temperature gradient surge coefficient in the present invention is used to measure the severity of the temperature change in the local area during the gas filling process. Through real-time monitoring and analysis of the temperature gradient, potential hidden dangers before high-pressure reflux can be effectively identified. Calculating this coefficient can help the system quickly capture temperature distribution anomalies when the temperature fluctuates violently, and judge the possible high-pressure reflux risks in the pipeline in advance. Specifically, when the local temperature gradient increases sharply, it can indicate that the abnormal pressure inside the pipeline may cause gas reflux, and sudden pressure fluctuations may occur along with the temperature gradient surge phenomenon, indicating that thermal imbalance caused by factors such as fluid disturbance, local airflow reversal or gas mixing anomalies may occur during the filling process, thereby foreshadowing potential precursors to risks such as high-pressure reflux. Through the calculation and evaluation of this coefficient, it is possible to accurately capture abnormal temperature fluctuations during the gas filling process, and to promptly issue early warnings for abnormal temperature gradients and take corresponding control measures, thereby accurately predicting the risk of high-pressure reflux and taking corresponding control plans, significantly enhancing the safety and stability of the filling process; Therefore, by obtaining the local temperature gradient change information during the gas filling process, the drastic situation of the temperature change in the local area during the gas filling process is analyzed, and the local temperature gradient surge coefficient is obtained to measure the severity of the temperature change in the local area during the gas filling process; The logic for obtaining the local temperature gradient surge coefficient is as follows: During the gas filling process, high-precision temperature sensors are placed in key local areas to collect temperature signals in real time and obtain the temperature signal time series. ; Select Daubechies wavelet function to perform continuous wavelet transform on the temperature signal time series and calculate the wavelet coefficients: ,in represents the wavelet coefficients, represents the scale parameter, represents the translation parameter, Represents the complex conjugate of the wavelet function; calculates the local temperature gradient energy: ,in Represents the local temperature gradient energy; divide the local temperature gradient energy into fixed time window lengths, and record each time window as , , is a positive integer; for each time window, the average temperature gradient strength is calculated: ,in represents the average temperature gradient intensity, Indicates the time window The total number of sampling points in the time window; calculate the maximum gradient strength: ,in Indicates the maximum gradient intensity; calculate the local temperature gradient surge coefficient, the expression is as follows: ,in Represents the local temperature gradient surge coefficient; It should be noted that key local areas include but are not limited to high-pressure gas input ends, narrow or bending points of pipelines, valve and joint areas, and the liquid gas vaporization interface inside storage tanks; It should be noted that the above formulas are all dimensionless and numerical calculations. Common dimensionless methods include Min-Max normalization and Z-Score normalization, which will not be described here. To accurately monitor temperature changes in key areas during the gas filling process, high-precision temperature sensors are deployed in key locations to collect real-time temperature signals. These temperature signals are recorded and stored in a time series format, enabling detailed analysis of temperature changes.

[0025] Next, to extract effective features from the time series, we used the Daubechies wavelet function to perform a continuous wavelet transform on the temperature signal. This wavelet transform allows us to analyze local variations in the signal at different scales and calculate wavelet coefficients. These wavelet coefficients reveal the fluctuation characteristics of the temperature signal across different frequency ranges. Adjusting the scale and wavelet shift parameters allows us to analyze the dynamic changes of the temperature signal from multiple perspectives.

[0026] After the temperature signal undergoes a wavelet transform, the local temperature gradient energy is calculated. This gradient energy reflects the severity of the temperature change, with higher gradient energies indicating more dramatic changes. To better analyze temperature fluctuations, the local temperature gradient energy is segmented into fixed time windows, with each time window representing temperature variation within a specific time period.

[0027] In each time window, the average temperature gradient intensity within the window is calculated, which helps to describe the overall trend of temperature changes during this period. At the same time, by calculating the maximum temperature gradient intensity within the time window, sharp fluctuations and abnormal points in temperature changes can be further identified.

[0028] Finally, combining the average and maximum temperature gradient intensities, the local temperature gradient surge coefficient can be calculated. This coefficient quantifies the severity of temperature changes and effectively identifies sudden anomalies during temperature changes, providing an important basis for assessing the potential for high-pressure backflow during gas filling.

[0029] The strain fatigue module is used to obtain the pipeline stress fatigue accumulation information during the gas filling process and obtain the stress fatigue accumulation coefficient based on the pipeline stress fatigue accumulation information; The stress fatigue accumulation coefficient in the present invention is used to measure the degree of fatigue accumulation of the pipeline during the gas filling process due to long-term repeated stress and high-pressure backflow impact, and to evaluate the risk of high-pressure backflow precursor hidden dangers. This coefficient reflects the local stress distribution and fatigue condition of the pipeline by collecting pipeline strain data in real time. The higher the stress fatigue accumulation coefficient, the more likely the pipeline is to be at risk due to fatigue accumulation. Once the preset safety threshold is exceeded, the system can issue an early warning and trigger intelligent control measures (such as adjusting the filling pressure and initiating active pressure relief), thereby effectively reducing the risk of irreversible damage to the pipeline caused by high-pressure backflow, and realizing dynamic monitoring and precise management of the gas filling safety status. This method of evaluating high-pressure backflow precursor hidden dangers based on stress fatigue accumulation can not only capture tiny fatigue evolution processes, but also identify in advance the risk of local fatigue failure of the pipeline caused by repeated filling operations and high-pressure impacts, thereby triggering early warning and active control measures before the hidden danger is formed, effectively preventing the high-pressure backflow phenomenon from causing irreversible damage to the pipeline and system, and ensuring the safe, stable and efficient operation of the entire gas filling process. Therefore, by obtaining the pipeline stress fatigue accumulation information during the gas filling process, the stress fatigue accumulation of the pipeline during the gas filling process is analyzed, and the stress fatigue accumulation coefficient is obtained to measure the degree of stress fatigue accumulation of the pipeline during the gas filling process; The logic for obtaining the stress fatigue accumulation coefficient is as follows: During the gas filling process, the cyclic stress of the pipeline is obtained by high-precision stress sensors , calculate the stress intensity factor: ,in represents the stress intensity factor, represents the shape constant, Indicates the crack area of ​​the current pipeline; calculates the crack growth rate: ,in 、 is the material fatigue constant of the pipeline, is the stress intensity factor range, ,in represents the maximum value of the stress intensity factor, Indicates the minimum value of stress intensity factor; calculates the critical fatigue life of the pipeline: ,in represents the critical fatigue life of the pipeline, represents the initial crack area, Indicates the critical crack area at fracture; calculate the stress fatigue accumulation coefficient, the expression is as follows: ,in represents the stress fatigue accumulation coefficient, Indicates the current cyclic stress of the pipeline; It should be noted that the above formulas are all dimensionless and numerical calculations. Common dimensionless methods include Min-Max normalization and Z-Score normalization, which will not be described here. To monitor pipeline fatigue during the gas filling process, high-precision stress sensors are required to collect real-time cyclic stress data. These stress signals can be used for further analysis to understand the stress fluctuations experienced by the pipeline during operation and assess the degree of pipeline fatigue.

[0030] First, the stress intensity factor (SIF), a key parameter for assessing crack growth, is calculated based on the collected cyclic stress signals. The SIF is closely related to the shape and area of ​​the crack in the pipeline and is typically calculated based on the pipeline geometry and crack characteristics. In practice, the shape constant and crack area vary over time and with usage, necessitating dynamic updates based on actual measurement data.

[0031] Next, the crack growth rate is calculated. This depends on the range of the stress intensity factor (SIF) and the fatigue constants of the pipe material. These constants are typically determined experimentally and reveal the fatigue properties of the material under specific operating conditions. By calculating the maximum and minimum SIF values, the range of the SIF is determined, allowing the crack growth rate to be estimated.

[0032] Next, the critical fatigue life of the pipeline is calculated. This is the time it takes for a crack to grow to a critical size before the pipeline fractures. Based on the initial crack area and the critical area at fracture, the pipeline fatigue life can be estimated. This critical fatigue life provides an important safety assessment basis for pipelines, helping to predict whether the pipeline will fracture under specific operating conditions.

[0033] Finally, the stress fatigue accumulation coefficient is calculated by combining the current cyclic stress with the pipeline's fatigue life. This coefficient reflects the degree of stress accumulation in the pipeline during the gas filling process, providing a quantitative basis for assessing the pipeline's health. A larger stress fatigue accumulation coefficient indicates higher fatigue stress on the pipeline and a greater risk of fatigue failure. Real-time monitoring of this coefficient can provide early warning of potential pipeline failures and help implement appropriate safety measures.

[0034] The precursor hazard assessment module is used to construct a high-pressure backflow precursor hazard assessment model based on the abnormal gas flow pressure pulse coefficient, ion concentration fluctuation coefficient, local temperature gradient surge coefficient, and stress fatigue accumulation coefficient. It outputs a high-pressure backflow precursor hazard assessment index and assesses the probability of the occurrence of the high-pressure backflow precursor hazard. A high-pressure backflow precursor hazard assessment model is constructed based on the abnormal pressure pulse coefficient of gas flow, ion concentration fluctuation coefficient, local temperature gradient surge coefficient, and stress fatigue accumulation coefficient, and a high-pressure backflow precursor hazard assessment index is output. The model is based on the following formula , where They represent the abnormal pressure pulse coefficient of gas flow, the ion concentration fluctuation coefficient, the local temperature gradient surge coefficient, and the stress fatigue accumulation coefficient, respectively. They represent the preset proportional coefficients of the abnormal pressure pulse coefficient of gas flow, the ion concentration fluctuation coefficient, the local temperature gradient surge coefficient, and the stress fatigue accumulation coefficient, respectively, and All greater than 0; It should be noted that the above formulas are all dimensionless and numerical calculations. Common dimensionless methods include Min-Max normalization and Z-Score normalization, which will not be described here. Set it according to the actual situation. For example, adopt the expert empowerment method, that is, invite experts in related fields to determine the preset proportion coefficients of various indicators through professional opinion surveys and comprehensive evaluations, for example, It can be 0.3, 0.2, 0.3, 0.2; From the above calculation expression, it can be seen that the larger the abnormal pressure pulse coefficient of gas flow, the larger the ion concentration fluctuation coefficient, the larger the local temperature gradient surge coefficient, and the larger the stress fatigue accumulation coefficient, the larger the high-pressure backflow precursor hidden danger assessment index, indicating that the probability of the high-pressure backflow precursor hidden danger is more serious. Conversely, the smaller the abnormal pressure pulse coefficient of gas flow, the smaller the ion concentration fluctuation coefficient, the smaller the local temperature gradient surge coefficient, and the smaller the stress fatigue accumulation coefficient, the larger the high-pressure backflow precursor hidden danger assessment index, indicating that the probability of the high-pressure backflow precursor hidden danger is less serious. The high-voltage backflow precursor hazard assessment index is compared with the preset high-voltage backflow precursor hazard assessment index threshold to determine whether there is a high-voltage backflow precursor hazard, as follows: If the high-pressure backflow precursor hidden danger assessment index is greater than the high-pressure backflow precursor hidden danger assessment index threshold, it means that a high-pressure backflow precursor hidden danger currently exists; if the high-pressure backflow precursor hidden danger assessment index is less than or equal to the high-pressure backflow precursor hidden danger assessment index threshold, it means that no high-pressure backflow precursor hidden danger currently exists; The intelligent pressure regulating module is used to adaptively adjust the pressure change rate when there is a hidden danger of high-pressure backflow, as follows: ,in Indicates the adjusted pressure change rate, represents the initial pressure change rate, Indicates the minimum safe pressure change rate, Indicates the high-voltage backflow precursor hidden danger assessment index, Indicates the threshold value of the high-voltage backflow precursor hidden danger assessment index; It should be noted that the above formulas are all dimensionless and numerical calculations. Common dimensionless methods include Min-Max normalization and Z-Score normalization, which will not be described here. The present invention obtains gas flow pressure pulse information, ion concentration fluctuation information, local temperature gradient change information, and pipeline stress fatigue accumulation information during the gas filling process, and constructs a high-pressure backflow precursor hazard assessment model based on the gas flow abnormal pressure pulse coefficient, ion concentration fluctuation coefficient, local temperature gradient surge coefficient, and stress fatigue accumulation coefficient. The model outputs a high-pressure backflow precursor hazard assessment index to achieve accurate assessment of high-pressure backflow precursor hazards, thereby enabling timely perception of potential risks before high-pressure backflow occurs, thereby improving the safety and reliability of the gas filling process. When a high-pressure backflow precursor hazard is detected, the intelligent pressure regulation module can adaptively adjust the pressure change rate to make pressure regulation during the gas filling process more stable, reduce the possibility of high-pressure backflow, and effectively reduce damage to key equipment such as pipelines and valves due to transient shock waves, extend the service life of the equipment, and improve the long-term operational stability of the gas filling system. The system has the ability to identify precursor hazards and actively intervene in the gas filling process through an intelligent pressure regulation strategy to avoid the occurrence of high-pressure backflow, ensure equipment safety and the stability of the gas filling process, achieve technical innovation combining precise monitoring and intelligent regulation, and improve the intelligence level of the gas filling system.

[0035] The above formulas are all dimensionless and numerical calculations. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters in the formulas are set by technicians in this field according to actual conditions.

[0036] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center via wired or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0037] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0038] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0039] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. The gas filling intelligent monitoring system based on the Internet of Things is characterized by: Including pressure pulse module, ion concentration module, temperature gradient module, strain fatigue module, precursor hidden danger assessment module, and intelligent pressure regulation module; The pressure pulse module is used to obtain the gas flow pressure pulse information during the gas filling process and obtain the gas flow abnormal pressure pulse coefficient based on the gas flow pressure pulse information; The ion concentration module is used to obtain the ion concentration fluctuation information during the gas filling process and obtain the ion concentration fluctuation coefficient based on the ion concentration fluctuation information; The temperature gradient module is used to obtain the local temperature gradient change information during the gas filling process and obtain the local temperature gradient surge coefficient based on the local temperature gradient change information; The strain fatigue module is used to obtain the pipeline stress fatigue accumulation information during the gas filling process and obtain the stress fatigue accumulation coefficient based on the pipeline stress fatigue accumulation information; The precursor hazard assessment module is used to construct a high-pressure backflow precursor hazard assessment model based on the abnormal gas flow pressure pulse coefficient, ion concentration fluctuation coefficient, local temperature gradient surge coefficient, and stress fatigue accumulation coefficient. It outputs a high-pressure backflow precursor hazard assessment index and assesses the probability of the occurrence of the high-pressure backflow precursor hazard. The intelligent pressure regulating module is used to adaptively adjust the pressure change rate when there is a hidden danger of high-pressure backflow.

2. The IoT-based intelligent gas filling monitoring system according to claim 1 is characterized by: By acquiring the gas flow pressure pulse information during the gas filling process, analyzing the pressure fluctuation of the gas flow during the gas filling process, and obtaining the abnormal pressure pulse coefficient of the gas flow, the pressure fluctuation degree of the gas flow during the gas filling process is measured; The logic for obtaining the abnormal pressure pulse coefficient of gas flow is as follows: High-precision pressure sensors are used to collect instantaneous pressure signals at different time points during the gas flow process and store them in time series: ,in represents the instantaneous pressure value of the i-th sampling point, , is a positive integer; calculate the mean pressure: ,in represents mean pressure; Calculate the RMS pressure: ,in Represents the RMS value of pressure; calculate the pressure deflection: ,in Indicates pressure deflection; Calculate pressure kurtosis: ,in Represents the pressure kurtosis; the time domain pressure signal is converted to the frequency domain using fast Fourier transform: in Frequency domain pressure signal, represents the time domain pressure signal, represents the fast Fourier transform and calculates the main frequency of pressure: ,in represents the main frequency of pressure, Indicates that the Get the maximum value Value; calculate the abnormal pressure pulse coefficient of gas flow, the expression is as follows: ,in Indicates the abnormal pressure pulse coefficient of gas flow, represents the preset scaling factor, and Both are greater than 0.

3. The gas filling intelligent monitoring system based on the Internet of Things according to claim 1 is characterized by: By obtaining the ion concentration fluctuation information during the gas filling process, the dynamic change of ion concentration during the gas filling process is analyzed, and the ion concentration fluctuation coefficient is obtained to measure the degree of dynamic change of ion concentration during the gas filling process; The logic for obtaining the ion concentration fluctuation coefficient is as follows: Install a high-precision concentration sensor in the gas filling pipeline to collect ion concentration signals: ,in represents the ion concentration value at the bth moment, , is a positive integer; for ion concentration signal Construct an m-dimensional vector: ,in , is a positive integer; for any two ion concentration vectors and ,and , calculate the ion concentration similarity distance: ,in Represents the similarity distance of ion concentration, if , it means that the two ion concentration vectors are similar, and the two ion concentration vectors are marked as an ion concentration similarity vector pair, where represents the similarity threshold; Calculate the ion concentration fluctuation coefficient, the expression is as follows: ,in represents the number of similarity vector pairs of ion concentrations when the embedding dimension is m+1, represents the number of similarity vector pairs of ion concentrations when the embedding dimension is m, represents the ion concentration fluctuation coefficient.

4. The gas filling intelligent monitoring system based on the Internet of Things according to claim 1 is characterized by: By obtaining the local temperature gradient change information during the gas filling process, the drastic situation of the temperature change in the local area during the gas filling process is analyzed, and the local temperature gradient surge coefficient is obtained to measure the severity of the temperature change in the local area during the gas filling process; The logic for obtaining the local temperature gradient surge coefficient is as follows: During the gas filling process, high-precision temperature sensors are placed in key local areas to collect temperature signals in real time and obtain the temperature signal time series. ; Select Daubechies wavelet function to perform continuous wavelet transform on the temperature signal time series and calculate the wavelet coefficients: ,in represents the wavelet coefficients, represents the scale parameter, represents the translation parameter, Represents the complex conjugate of the wavelet function; calculates the local temperature gradient energy: ,in Represents the local temperature gradient energy; divide the local temperature gradient energy into fixed time window lengths, and record each time window as , , is a positive integer; for each time window, the average temperature gradient strength is calculated: ,in represents the average temperature gradient intensity, Indicates the time window The total number of sampling points in a time window; Calculate the maximum gradient magnitude: ,in represents the maximum gradient strength; Calculate the local temperature gradient surge coefficient, the expression is as follows: ,in Represents the local temperature gradient surge coefficient.

5. The gas filling intelligent monitoring system based on the Internet of Things according to claim 1 is characterized by: By obtaining the pipeline stress fatigue accumulation information during the gas filling process, the stress fatigue accumulation of the pipeline during the gas filling process is analyzed, and the stress fatigue accumulation coefficient is obtained to measure the degree of stress fatigue accumulation of the pipeline during the gas filling process; The logic for obtaining the stress fatigue accumulation coefficient is as follows: During the gas filling process, the cyclic stress of the pipeline is obtained by high-precision stress sensors , calculate the stress intensity factor: ,in represents the stress intensity factor, represents the shape constant, Indicates the crack area of ​​the current pipeline; calculates the crack growth rate: ,in 、 is the material fatigue constant of the pipeline, is the stress intensity factor range, ,in represents the maximum value of the stress intensity factor, Indicates the minimum value of stress intensity factor; Calculate the critical fatigue life of the pipeline: ,in represents the critical fatigue life of the pipeline, represents the initial crack area, Indicates the critical crack area at fracture; Calculate the stress fatigue accumulation coefficient, the expression is as follows: ,in represents the stress fatigue accumulation coefficient, Indicates the current cyclic stress of the pipeline.

6. The gas filling intelligent monitoring system based on the Internet of Things according to claim 1 is characterized by: A high-pressure backflow precursor hazard assessment model is constructed based on the abnormal pressure pulse coefficient of gas flow, ion concentration fluctuation coefficient, local temperature gradient surge coefficient, and stress fatigue accumulation coefficient, and a high-pressure backflow precursor hazard assessment index is output. The model is based on the following formula , where They represent the abnormal pressure pulse coefficient of gas flow, the ion concentration fluctuation coefficient, the local temperature gradient surge coefficient, and the stress fatigue accumulation coefficient, respectively. They represent the preset proportional coefficients of the abnormal pressure pulse coefficient of gas flow, the ion concentration fluctuation coefficient, the local temperature gradient surge coefficient, and the stress fatigue accumulation coefficient, respectively, and Both are greater than 0.

7. The gas filling intelligent monitoring system based on the Internet of Things according to claim 6 is characterized by: The high-voltage backflow precursor hazard assessment index is compared with the preset high-voltage backflow precursor hazard assessment index threshold to determine whether there is a high-voltage backflow precursor hazard, as follows: If the high-pressure backflow precursor hazard assessment index is greater than the high-pressure backflow precursor hazard assessment index threshold, it means that there is currently a high-pressure backflow precursor hazard; if the high-pressure backflow precursor hazard assessment index is less than or equal to the high-pressure backflow precursor hazard assessment index threshold, it means that there is currently no high-pressure backflow precursor hazard.

8. The gas filling intelligent monitoring system based on the Internet of Things according to claim 7 is characterized in that: When there is a hidden danger of high-pressure backflow, the pressure change rate is adaptively adjusted as follows: ,in Indicates the adjusted pressure change rate, represents the initial pressure change rate, Indicates the minimum safe pressure change rate, Indicates the high-voltage backflow precursor hidden danger assessment index, Indicates the high-voltage backflow precursor hazard assessment index threshold.

Images