Safety monitoring system and monitoring method for hydrogen storage device

Abstract

The invention discloses a safety monitoring system and monitoring method for a hydrogen storage device, and relates to the technical field of hydrogen storage, and the system comprises an energy supply module which supplies power to a data collection device through an intelligent power management system; the data acquisition module is used for collecting real-time operation data from a sensor of the hydrogen storage device; the intelligent analysis module is used for performing real-time analysis on the collected data based on a machine learning algorithm, establishing a safety risk assessment model and obtaining a risk development trend; the early warning control module is used for judging whether abnormity occurs or not based on the risk development trend; and the remote monitoring module communicates with the subsystems through a network and provides remote data monitoring. According to the method, key data of the hydrogen storage device are collected in real time, intelligent analysis is conducted through machine learning, environment changes are monitored in real time, safety risks are recognized in advance, leakage and pressure anomalies are recognized through deep learning and an anomaly detection algorithm, the risk development trend is predicted, and safe operation of equipment is guaranteed.

Description

TECHNICAL FIELD

[0001] The application relates to the hydrogen storage technology field, and particularly relates to a hydrogen storage device safety monitoring system and a monitoring method. BACKGROUND

[0002] With the rapid development of hydrogen energy, hydrogen storage technology is increasingly widely applied in energy storage and use. Hydrogen gas is a clean energy, and its storage and transportation process involves special conditions such as high pressure and low temperature, which makes the hydrogen storage device face high safety risks. In particular, in the case of hydrogen leakage, pressure abnormality and equipment failure, a major accident may occur. Therefore, developing an efficient and safe hydrogen storage device safety monitoring system has become an important research topic to be solved at present.

[0003] The existing hydrogen storage device monitoring technology mainly relies on manual inspection and a simple sensor alarm system. However, such a system has the disadvantages of slow response speed, poor early warning accuracy and inability to perform intelligent analysis. In particular, when the equipment is abnormal, the traditional monitoring system is difficult to predict in real time and automatically take effective emergency response measures. Therefore, how to establish an intelligent, automatic and real-time hydrogen storage device safety monitoring system has become an important research direction in the hydrogen energy industry. SUMMARY

[0004] To solve the above technical problems, a hydrogen storage device safety monitoring system and a monitoring method are provided, which solve the above problems.

[0005] To achieve the above purposes, the technical scheme adopted by the application is as follows: A hydrogen storage device safety monitoring system comprises: An energy supply module provides power for a data acquisition device through an intelligent power management system and dynamically adjusts power distribution according to different environmental conditions and equipment load requirements. A data acquisition module collects real-time operation data from sensors of the hydrogen storage device, including temperature, pressure, flow and valve state information. An intelligent analysis module performs real-time analysis on the collected data based on a machine learning algorithm, establishes a safety risk assessment model, and obtains a risk development trend based on the output of the model. A warning control module determines whether an abnormality occurs based on the risk development trend, automatically triggers a warning signal when an abnormality occurs, and executes emergency handling measures according to a preset scheme. A remote monitoring module communicates with the subsystem through a network, provides remote data monitoring, equipment state management and emergency response operation interfaces.

[0006] Preferably, the data acquisition module comprises: The sensor signal acquisition unit: monitors the temperature change of the hydrogen storage device, transmits the temperature data to the data acquisition module, monitors the gas pressure inside and outside the hydrogen storage device based on the pressure sensor, monitors the hydrogen flow based on the flow sensor, including the flow of hydrogen in and out of the hydrogen storage device, and monitors the opening and closing state of the valve in the hydrogen storage device based on the valve state sensor; The data acquisition unit: acquires the analog signals output by the sensors and converts them into digital signals, formats the collected data, including denoising, calibration and filtering; The data synchronization and timestamp unit: timestamps the collected data and detects abnormal values in the collected data in real time.

[0007] Preferably, the intelligent analysis module includes: An anomaly detection model based on machine learning, which identifies the characteristics of specific safety events such as hydrogen leakage and pressure anomalies through training on historical fault data; Wherein, the anomaly detection model formula is: f(x)=sign(w T x+b) In the formula, w is the weight vector, b is the bias, and x is the input feature. When f(x) = 1, it indicates that an anomaly is detected; The data pattern establishment unit models the normal operation data as a Gaussian distribution, builds and optimizes the normal operation mode, compares the real-time data, and identifies the deviation from the normal operation mode; Wherein, the normal mode model formula is: In the formula, μ and σ are the mean and standard deviation of the normal data, x is the real-time collected data, p(x) is the probability density function, and exp represents the exponential function; The fault diagnosis unit uses a time series prediction model to predict the risk development trend in the future period of time, predicts the evolution of the device state through the model, judges whether the potential risk is aggravated, and provides a basis for taking preventive measures in advance, uses the trained model to predict the real-time data in real time, identifies the abnormal pattern in the data, and predicts the potential risk development.

[0008] Preferably, the use of a time series prediction model to predict the risk development trend in the future period of time specifically includes: Wherein, the time series prediction model formula is: In the formula, Y t is the time series value, and θ j are model parameters, and ∈ t is an error term, represents the influence of the observation value at the past p time points on the current observation value, represents the influence of the error term at the past q time points on the current observation value.

[0009] Preferably, the early warning control module comprises: An early warning triggering unit determines whether to trigger an early warning signal based on the output of the intelligent analysis module, and automatically sends an early warning signal when the monitoring data exceeds the normal range; An emergency response unit automatically starts emergency measures, including closing valves near the leakage point, starting the ventilation system, and enabling backup equipment; A data feedback unit transmits real-time data and abnormal information to the remote monitoring platform, so that remote personnel can make timely judgments and decisions.

[0010] Preferably, the remote monitoring module comprises: A real-time data display unit displays real-time running data and state information of each key device for monitoring personnel to view; An early warning information pushing unit timely delivers abnormalities and early warning signals to workers and provides specific processing suggestions; A decision support unit provides risk assessment reports to management personnel based on the data collected by the system and the intelligent analysis results, assisting decision-making; A video monitoring module transmits images to the remote platform through the on-site video monitoring system, supporting personnel to make real-time judgments on the on-site situation.

[0011] A safety monitoring method for a hydrogen storage device, comprising: Real-time collection of data of each key device in the hydrogen storage device, including temperature, pressure, flow rate, and valve state; Based on machine learning algorithms, the collected data is analyzed to identify abnormal risks in the data and predict abnormal risks; when the data deviates from the normal range, an early warning signal is automatically triggered, and pre-set emergency response measures are executed; Abnormal data and early warning information are transmitted to the operator through the remote monitoring platform to support them to take further safety measures.

[0012] Preferably, the data analysis step comprises: Using a deep learning model to analyze historical data, building a normal operation mode, and comparing real-time data with the mode to detect potential safety risks; Using an anomaly detection algorithm to identify the characteristic pattern of key safety events such as hydrogen leakage and pressure abnormalities; Based on the prediction model, trend analysis is performed on the monitoring data to predict possible safety events and give early risk warnings.

[0013] Preferably, the early warning response step includes: When the monitoring data exceeds the set threshold, an early warning is automatically triggered and an emergency response procedure is initiated, including closing the valve of the leakage point and starting the ventilation device; Through the remote monitoring platform, field data and images are transmitted to remote monitoring personnel for real-time analysis and instructions to field operators to take measures.

[0014] Preferably, the data transmission step includes: Through wireless communication technology, data is uploaded to the remote monitoring platform in real time, ensuring that monitoring personnel can obtain real-time operation information of field devices; Combined with an intelligent decision support system, a safety early warning report is generated and sent to the operator for processing.

[0015] Compared with the prior art, the beneficial effects of the present application are: The present application proposes to collect key data of hydrogen storage devices in real time and use machine learning for intelligent analysis, monitor environmental changes in real time, identify safety risks in advance, identify leaks and pressure abnormalities through deep learning and anomaly detection algorithms, and predict risk development trends. The system automatically triggers early warning and emergency response measures such as closing valves and starting ventilation, and the remote monitoring module provides data feedback and decision support to ensure timely response to potential safety incidents. At the same time, wireless data transmission and real-time alarm are supported, which optimizes emergency handling efficiency and ensures safe operation of the device. BRIEF DESCRIPTION OF DRAWINGS

[0016] Figure 1 The system framework diagram of the present application is shown in the figure; Figure 2 The step flow framework diagram of the present application is shown in the figure. DETAILED DESCRIPTION

[0017] The following description is used to disclose the present application so that those skilled in the art can implement the present application. The preferred embodiments in the following description are only as examples, and other obvious modifications can be made by those skilled in the art.

[0018] Referring to Figure 1 A safety monitoring system for hydrogen storage devices is shown in the figure, which includes: An energy supply module provides power for the data acquisition device through an intelligent power management system, and dynamically adjusts power distribution according to different environmental conditions and device load requirements; A data acquisition module collects real-time operation data from sensors of the hydrogen storage device, including temperature, pressure, flow rate and valve status information; An intelligent analysis module performs real-time analysis on the collected data based on machine learning algorithms, establishes a safety risk assessment model, and obtains risk development trends based on the output of the model; Early warning control module, based on the risk development trend, judge whether an abnormality occurs, automatically trigger an early warning signal when an abnormality occurs, and execute emergency handling measures according to a preset scheme; Remote monitoring module, communicates with the subsystem through the network, provides remote data monitoring, device state management and emergency response operation interface.

[0019] The data acquisition module includes: The sensor signal acquisition unit monitors the temperature change of the hydrogen storage device, transmits the temperature data to the data acquisition module, monitors the gas pressure inside and outside the hydrogen storage device based on the pressure sensor, monitors the hydrogen flow based on the flow sensor, including the flow of hydrogen in and out of the hydrogen storage device, and monitors the opening and closing state of the valve in the hydrogen storage device based on the valve state sensor; The data acquisition unit acquires the analog signals output by the sensor and converts them into digital signals, and formats the collected data, including denoising, calibration and filtering; The data synchronization and timestamp unit timestamps the collected data and detects abnormal values in the collected data in real time; The data acquisition module combines multiple sensors for comprehensive monitoring, and includes data synchronization and timestamp functions to ensure the accuracy and timeliness of the collected data, which helps to more accurately capture abnormal data.

[0020] The intelligent analysis module includes: The anomaly detection model based on machine learning identifies the characteristics of specific safety events such as hydrogen leakage and pressure abnormalities through training on historical fault data; Wherein, the anomaly detection model formula is: f(x)=sign(w T x+b) In the formula, w is the weight vector, b is the bias, and x is the input feature. When f(x)=1, it indicates that an anomaly is detected; The data pattern establishment unit models the normally operating data as a Gaussian distribution, builds and optimizes the normal operation mode, compares the real-time data, and identifies the deviation from the normal operation mode; Wherein, the normal mode model formula is: In the formula, μ and σ are the mean and standard deviation of the normal data, x is the real-time collected data, p(x) is the probability density function, and exp represents the exponential function; The fault diagnosis unit uses a time series prediction model to predict the risk development trend in the future period, judges whether the potential risk is aggravated by predicting the evolution of the device state through the model, and provides the basis for taking preventive measures in advance, uses the trained model to make real-time prediction on real-time data, identifies the abnormal pattern in the data, and predicts the potential risk development; By adopting machine learning algorithm and combining historical data to train the anomaly detection model, the hydrogen leakage and pressure anomaly and other key safety events can be identified in real time, and the intelligent level of monitoring is improved. In addition, by Gaussian distribution modeling, the system can more accurately identify the deviation from the normal mode, and the accuracy of risk assessment is improved.

[0021] The time series prediction model is used to predict the risk development trend in the future period, which specifically includes: The formula of the time series prediction model is: In the formula, Y t is the time series value, and θ j are model parameters, and ∈ t is an error term, represents the influence of the observation value at the past p time points on the current observation value, represents the influence of the error term at the past q time points on the current observation value; The time series prediction model is used to predict the risk development trend. The model can dynamically adjust the prediction parameters based on the past data points, improve the accuracy of future risk prediction, and enable the system to identify potential risks and respond in advance.

[0022] The early warning control module includes: The early warning triggering unit judges whether to trigger the early warning signal based on the output of the intelligent analysis module, and automatically sends the early warning signal when the monitoring data exceeds the normal range; The emergency response unit automatically starts emergency measures, including closing the valve near the leakage point, starting the ventilation system, and enabling the standby device; The data feedback unit transmits real-time data and abnormal information to the remote monitoring platform, so that remote personnel can make judgments and decisions in a timely manner; The early warning control module not only can automatically judge and trigger the early warning signal, but also can automatically execute the emergency measures, greatly improving the emergency response efficiency and reducing the error and response time of human intervention.

[0023] The remote monitoring module includes: The real-time data display unit displays the real-time running data and state information of each key device for monitoring personnel to view; The early warning information pushing unit timely delivers the abnormality and early warning signal to the staff and provides specific processing suggestions; A decision support unit provides risk assessment reports to management personnel based on system-collected data and intelligent analysis results to assist decision-making. A video monitoring module transmits images to a remote platform through a live video monitoring system, supporting personnel to judge live conditions in real time. The remote monitoring module integrates functions such as real-time data display, early warning push, decision support, and video monitoring, enabling operating personnel to remotely monitor equipment operation status, timely obtain early warning information and take emergency response measures, and enhancing the safety of the equipment.

[0024] Referring to Figure 2 A safety monitoring method for a hydrogen storage device, comprising: Real-time collection of data from key equipment in the hydrogen storage device, including temperature, pressure, flow rate, and valve status; Based on machine learning algorithms, analyze the collected data, identify abnormal risks in the data, and predict abnormal risks. When data deviates from the normal range, automatically trigger an early warning signal and execute pre-set emergency response measures; Through a remote monitoring platform, transmit abnormal data and early warning information to operating personnel to support them in taking further safety measures.

[0025] The data analysis step includes: Use deep learning models to analyze historical data, build normal operation patterns, and compare real-time data with the patterns to detect potential safety risks; Use anomaly detection algorithms to identify characteristic patterns of key safety events such as hydrogen leaks and pressure abnormalities; Based on prediction models, analyze trends in monitoring data, predict possible safety events, and provide early risk warnings.

[0026] The early warning response step includes: When monitoring data exceeds the set threshold, automatically trigger an early warning and start an emergency response program, including closing the valve at the leak point and starting the ventilation device; Through a remote monitoring platform, transmit live data and images to remote monitoring personnel for real-time analysis and instruct on-site operating personnel to take measures.

[0027] The data transmission step includes: Through wireless communication technology, upload data to a remote monitoring platform in real time to ensure that monitoring personnel can timely obtain live equipment operation information; In combination with an intelligent decision support system, generate a safety warning report and notify operating personnel to handle it through a push method; Real-time data transmission is realized through wireless communication technology, so that monitoring personnel can access on-site data at any time and anywhere, and generate a safety warning report in combination with an intelligent decision support system and push a notification, thereby improving the timeliness and accuracy of early warning response.

[0028] In summary, the advantages of the present application are: The data acquisition module collects real-time data of key parameters of the hydrogen storage device, and the intelligent analysis module analyzes the data by means of machine learning algorithms, which enables the system to establish a safety risk assessment model based on historical data and real-time data, monitor the changes in the hydrogen storage environment in real time, and identify potential safety risks in advance; The intelligent analysis module can accurately identify key safety events such as hydrogen leakage and pressure anomalies through deep learning and anomaly detection algorithms, and predict the risk development trend in the future period of time through a time series prediction model, so that the system can not only identify immediate abnormalities, but also predict potential risks, effectively improving the advance of early warning; When an anomaly is detected, the system automatically triggers an early warning signal and executes emergency response measures according to the pre-set emergency response plan, such as automatically closing the valve at the leakage point, starting the ventilation system, and enabling the backup equipment, which can greatly reduce human negligence and response time, improve emergency handling efficiency, and ensure the safe operation of the equipment; Through the remote monitoring module, the monitoring personnel can view the running data, equipment status and early warning information of the hydrogen storage device in real time, which provides comprehensive decision support for the management personnel, and through video monitoring, real-time data feedback and early warning push, ensures that the operating personnel can take correct handling measures in time to ensure safety; The system integrates an intelligent decision support unit, which provides safety risk assessment reports for management personnel through analysis of real-time data to assist them in making decisions and avoiding accidents, and through combination of intelligent analysis results, the system can effectively optimize decisions and reduce human decision errors; The system supports real-time uploading of data to a remote monitoring platform through wireless communication technology, ensuring that monitoring personnel can understand the real-time situation on site at any time and make emergency decisions in time, and in addition, the system can generate a safety warning report and notify the operating personnel to handle it through a push method, enhancing the timeliness and accuracy of emergency response.

[0029] The above shows and describes the basic principles, main features and advantages of the present application. Those skilled in the art should understand that the present application is not limited to the above embodiments, and the above embodiments and descriptions in the specification are only the principles of the present application. Without departing from the spirit and scope of the present application, various changes and improvements can be made to the present application, and these changes and improvements all fall within the scope of the claimed present application. The scope of protection claimed by the present application is defined by the appended claims and their equivalents.

Claims

1. A safety monitoring system for a hydrogen storage device, characterized in that, include: The energy supply module provides power to the data acquisition device through an intelligent power management system, and dynamically adjusts the power distribution according to different environmental conditions and equipment load requirements. The data acquisition module collects real-time operating data from the sensors in the hydrogen storage device, including temperature, pressure, flow rate, and valve status information; The intelligent analysis module uses machine learning algorithms to analyze the collected data in real time, establish a security risk assessment model, and obtain risk development trends based on the model's output. The early warning and control module determines whether an anomaly has occurred based on the risk development trend. If an anomaly occurs, it automatically triggers an early warning signal and executes emergency response measures according to the preset plan. The remote monitoring module communicates with the subsystems via the network, providing interfaces for remote data monitoring, equipment status management, and emergency response.

2. The safety monitoring system for a hydrogen storage device according to claim 1, characterized in that, The data acquisition module includes: Sensor signal acquisition unit: monitors the temperature change of the hydrogen storage device, transmits temperature data to the data acquisition module, monitors the gas pressure inside and outside the hydrogen storage device based on the pressure sensor, monitors the hydrogen flow rate based on the flow sensor, including the flow rate of hydrogen entering and leaving the hydrogen storage device, and monitors the opening and closing status of the valves in the hydrogen storage device based on the valve status sensor. Data acquisition unit: Acquires analog signals output by sensors, converts them into digital signals, and performs formatting processing on the acquired data, including noise reduction, calibration, and filtering; Data synchronization and timestamp unit: timestamps the collected data and detects outliers in the collected data in real time.

3. The safety monitoring system for a hydrogen storage device according to claim 2, characterized in that, The intelligent analysis module includes: An anomaly detection model based on machine learning identifies the characteristics of specific safety events such as hydrogen leaks and pressure anomalies by training on historical fault data. The formula for the anomaly detection model is as follows: f(x)=sign(w T x+b) In the formula, w is the weight vector, b is the bias, and x is the input feature. When f(x) = 1, it indicates that an anomaly has been detected. The data pattern building unit models the data under normal operation as a Gaussian distribution, constructs and optimizes the normal operation pattern, compares it with the real-time data, and identifies the deviation from the normal operation pattern. The formula for the normal mode model is as follows: In the formula, μ and σ are the mean and standard deviation of normal data, respectively, x is the data collected in real time, p(x) is the probability density function, and exp represents the exponential function; The fault diagnosis unit uses a time series prediction model to predict the risk development trend in the future. By predicting the evolution of equipment status through the model, it can determine whether potential risks will intensify and provide a basis for taking preventive measures in advance. It uses a trained model to make real-time predictions on real-time data, identify abnormal patterns in the data, and predict the development of potential risks.

4. The safety monitoring system for a hydrogen storage device according to claim 3, characterized in that, The specific use of time series forecasting models to predict risk development trends over a future period of time is as follows. include: The formula for the time series prediction model is as follows: In the formula, Y t These are time series values. and θ j These are model parameters, ∈ t It is an error term. This represents the influence of observations from the past p time points on the current observation. This represents the impact of the error term from the past q time points on the current observation.

5. The safety monitoring system for a hydrogen storage device according to claim 4, characterized in that, The early warning control module includes: The early warning triggering unit, based on the output of the intelligent analysis module, determines whether to trigger an early warning signal. When the monitored data exceeds the normal range, it automatically issues an early warning signal. The emergency response unit automatically initiates emergency measures, including closing valves near the leak point, activating the ventilation system, and activating backup equipment. The data feedback unit transmits real-time data and abnormal information to the remote monitoring platform, enabling remote personnel to make timely judgments and decisions.

6. The safety monitoring system for a hydrogen storage device according to claim 5, characterized in that, The remote monitoring module includes: The real-time data display unit shows the real-time operating data and status information of each key device for monitoring personnel to view; The early warning information push unit promptly transmits abnormalities and early warning signals to staff and provides specific handling suggestions; The decision support unit provides risk assessment reports to managers based on data collected by the system and intelligent analysis results to assist in decision-making; The video surveillance module transmits images from the on-site video surveillance system to a remote platform, enabling personnel to assess the situation in real time.

7. A safety monitoring method for a hydrogen storage device, characterized in that, include: Real-time data collection of key equipment in the hydrogen storage device, including temperature, pressure, flow rate, and valve status; The collected data is analyzed using machine learning algorithms to identify and predict abnormal risks in the data. When data deviates from the normal range, an early warning signal is automatically triggered, and preset emergency response measures are executed. Abnormal data and early warning information are transmitted to operators through a remote monitoring platform to support them in taking further safety measures.

8. The safety monitoring method for a hydrogen storage device according to claim 7, characterized in that, The data analysis steps include: using a deep learning model to analyze historical data, constructing a normal operation mode, and comparing real-time data with the mode to detect potential security risks; Anomaly detection algorithms are used to identify characteristic patterns of critical safety events such as hydrogen leaks and pressure anomalies. Based on predictive models, trend analysis is performed on monitoring data to predict potential security incidents and provide early risk warnings.

9. The safety monitoring method for a hydrogen storage device according to claim 7, characterized in that, The early warning response steps include: when the monitoring data exceeds the set threshold, an early warning is automatically triggered and an emergency response procedure is initiated, including closing the valve at the leak point and starting the ventilation device; The remote monitoring platform transmits on-site data and images, providing them to remote monitoring personnel for real-time analysis and instructing on-site operators to take appropriate measures.

10. The safety monitoring method for a hydrogen storage device according to claim 7, characterized in that, The data transmission steps include: uploading data to the remote monitoring platform in real time via wireless communication technology to ensure that monitoring personnel can obtain the operating information of on-site equipment in a timely manner; By integrating with an intelligent decision support system, a safety warning report is generated and notified to operators via push notification for handling.

Images