Intelligent identification method, device, equipment and product for risk factors of injection-production system of underground hydrogen storage

Abstract

The embodiment of the application provides a kind of underground hydrogen storage library injection-production system risk factor intelligent identification method, device, equipment and product.The method is by obtaining the operation parameter of underground hydrogen storage library, operation risk factor and structure causal model, structure causal model is used to indicate the correlation of multiple operation risk factors of underground hydrogen storage library.According to structure causal model, determine the accident hazard type matched with operation parameter and operation risk factor, and the benchmark risk value of accident hazard type.According to benchmark risk value, determine the influence proportion of each risk factor on accident hazard type, and influence proportion is used to represent the processing priority of risk factor.The method can comprehensively monitor, accurately analyze and scientifically control the risk factors of underground hydrogen storage library, can identify potential risk in advance, so that risk control is targeted.

Description

Technical Field

[0001] This application relates to the field of risk assessment technology, and in particular to a method, device, equipment and product for intelligent identification of risk factors in underground hydrogen storage injection and production systems. Background Technology

[0002] Underground hydrogen storage facilities are key infrastructure for large-scale hydrogen storage, and their injection and extraction systems play a crucial role in the energy supply chain, fulfilling core functions of hydrogen storage, peak shaving, and distribution. In actual operation, the hydrogen storage facility's injection and extraction system involves complex processes, including multiple stages such as hydrogen injection, compression, storage, and extraction, with high coupling between these stages.

[0003] Meanwhile, the system needs to address multiple risks, including uncertainties in the geological environment, operational risks of equipment, and human error. Because hydrogen is flammable and explosive, leaks or overpressure accidents could lead to serious consequences such as fires, explosions, equipment damage, and personal injury.

[0004] However, existing underground hydrogen storage facilities lack a dynamic identification and quantitative assessment system for risks throughout the entire lifecycle of the injection and production system, making it difficult for risk management measures to accurately match actual needs. Summary of the Invention

[0005] The intelligent identification method, device, equipment, and product for risk factors in underground hydrogen storage injection and extraction systems provided in this application are used to capture the dynamic interaction risks of control behavior defects and equipment failures during the injection and extraction process in real time. Through counterfactual reasoning mechanism, the contribution of each risk factor to the accident is quantified, the priority of key risks is clarified, and a scientific basis for resource allocation is provided.

[0006] In a first aspect, embodiments of this application provide a method for intelligent identification of risk factors in underground hydrogen storage injection and production systems, including:

[0007] The operational parameters, operational risk factors, and structural causal model of the underground hydrogen storage injection and production system are obtained. The structural causal model is used to indicate the correlation between multiple risk factors of the underground hydrogen storage injection and production system.

[0008] Based on the structural causal model, determine the accident hazard type that matches the operation parameters and the operation risk factors, and the baseline risk value of the accident hazard type;

[0009] Based on the baseline risk value, the weight of each risk factor in relation to the type of accident hazard is determined. The risk factor is at least one of the operational risk factors, and the weight of the risk factor is used to characterize the processing priority of the risk factor.

[0010] In one possible implementation, the method further includes:

[0011] The safety risk characteristics of the underground hydrogen storage injection and production system are used as the outcome variable; the safety risk characteristics are used to characterize the potential safety accidents and safety hazards of the underground hydrogen storage injection and production system.

[0012] Risk factor characteristics are used as basic and exogenous variables; the risk factor characteristics are risk factors and inducing factors of each defective action in the control actions used to achieve safety objectives, which are determined based on safety risk characteristics.

[0013] The structural causal model is constructed based on the outcome variable, the basic variable, and the exogenous variable.

[0014] In one possible implementation, the method further includes:

[0015] Based on the process flow data and equipment association data of the underground hydrogen storage injection and production system, at least one safety constraint is determined, and based on the safety constraint, the safety risk characteristics of the underground hydrogen storage injection and production system are identified.

[0016] Based on the safety constraints and the safety risk characteristics, the safety feedback characteristics of the underground hydrogen storage injection and production system are determined. The safety feedback characteristics are used to characterize the control actions and feedback paths required to achieve the safety objectives when the underground hydrogen storage injection and production system encounters a safety risk.

[0017] Based on the safety feedback characteristics, the risk factor characteristics are determined.

[0018] In one possible implementation, determining the risk factor characteristics based on the safety feedback characteristics includes:

[0019] Based on the control actions and the feedback path, a safety control loop diagram of the underground hydrogen storage injection and production system is constructed.

[0020] Based on the safety control loop diagram, identify the control action sequence of the underground hydrogen storage injection and production system;

[0021] Identify the risk factors and triggering factors for each defective action in the control action sequence.

[0022] In one possible implementation, constructing the structural causal model based on the outcome variable, the basic variable, and the exogenous variable includes:

[0023] A structural causal model is obtained by constructing causal relationships between the outcome variable, the basic variable, and the exogenous variable using logic gates, wherein the logic gates include AND gates, OR gates, and voting gates.

[0024] In one possible implementation, determining the type of accident hazard matching the operational parameters and the baseline risk value of the accident hazard type based on the structural causal model includes:

[0025] Based on the aforementioned operational parameters, the target exogenous variables are determined;

[0026] Obtain the prior probability of the target exogenous variable;

[0027] Based on the structural causal model and the target exogenous variable, determine the type of accident hazard that matches the operating parameters;

[0028] Based on the basic variables of the accident hazard type and the prior probabilities of the target exogenous variables, the baseline risk value of the accident hazard type is determined.

[0029] In one possible implementation, determining the weight of each risk factor on the type of accident hazard based on the benchmark risk value includes:

[0030] For any given risk factor, counterfactual intervention is performed to ensure that the risk factor is in a state of certainty.

[0031] Based on the operational parameters and the structural causal model, the conditional probability of the risk factor is determined;

[0032] Based on the conditional probability and the baseline risk value, the influence ratio of the risk factor on the accident hazard type is generated.

[0033] Secondly, embodiments of this application provide an intelligent identification device for risk factors in an underground hydrogen storage injection and production system, comprising:

[0034] The acquisition module is used to acquire the operating parameters, operational risk factors, and structural causal model of the underground hydrogen storage injection and production system. The structural causal model is used to indicate the correlation between multiple risk factors of the underground hydrogen storage injection and production system.

[0035] The determination module is used to determine, based on the structural causal model, the accident hazard type that matches the operation parameters and the operation risk factors, and the baseline risk value of the accident hazard type;

[0036] The determination module is used to determine the weight of each risk factor on the type of accident hazard based on the benchmark risk value. The risk factor is at least one of the operational risk factors, and the weight of the risk factor is used to characterize the processing priority of the risk factor.

[0037] Thirdly, embodiments of this application provide an electronic device, including: a memory and a processor;

[0038] The memory stores computer-executed instructions;

[0039] The processor executes computer execution instructions stored in the memory, causing the processor to perform the first aspect and / or various possible implementations of the first aspect as described above.

[0040] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the first aspect and / or various possible implementations of the first aspect.

[0041] Fifthly, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the first aspect and / or various possible implementations of the first aspect.

[0042] The intelligent identification method, device, equipment, and product for risk factors in underground hydrogen storage injection and production systems provided in this application acquire on-site monitoring data and actual operating parameters of the underground hydrogen storage facility. Based on the process flow, a structural causal model is trained and constructed. This model can determine the matching accident hazard type and baseline risk value according to the operating parameters, and simultaneously clarify the influence weight of each risk factor on that accident hazard type. Finally, the processing priority of the risk factors is determined based on the influence weight. This process achieves comprehensive monitoring, precise analysis, and scientific management of risk factors in underground hydrogen storage injection and production systems, enabling early identification of potential risks. Furthermore, quantifying the influence weight of each risk factor makes risk prevention and control more targeted and efficient, effectively reducing the probability of accidents and ensuring the safe and stable operation of underground hydrogen storage facilities. Attached Figure Description

[0043] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0044] Figure 1 A flowchart illustrating the intelligent identification method for risk factors in underground hydrogen storage injection and production systems provided in this application. Figure 1 ;

[0045] Figure 2 A flowchart illustrating the intelligent identification method for risk factors in underground hydrogen storage injection and production systems provided in this application. Figure 2 ;

[0046] Figure 3 A flowchart illustrating the intelligent identification method for risk factors in underground hydrogen storage injection and production systems provided in this application. Figure 3 ;

[0047] Figure 4A structural schematic diagram of the structural causal model provided in this application;

[0048] Figure 5 A flowchart illustrating the intelligent identification method for risk factors in underground hydrogen storage injection and production systems provided in this application. Figure 4 ;

[0049] Figure 6 A flowchart illustrating the intelligent identification method for risk factors in underground hydrogen storage injection and production systems provided in this application. Figure 5 ;

[0050] Figure 7 A schematic diagram of the intelligent risk factor identification device for the underground hydrogen storage injection and production system provided in this application;

[0051] Figure 8 A schematic diagram of the structure of the electronic device provided in this application.

[0052] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0053] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0054] As a core infrastructure for large-scale hydrogen energy storage, underground hydrogen storage facilities are crucial to the stability and reliability of the hydrogen energy industry chain, and the safe operation of their injection and extraction systems is directly related to this. Against the backdrop of the rapid development of the hydrogen energy industry, underground hydrogen storage facilities utilize processes such as high-pressure gas injection, geological sealing, and low-pressure gas extraction to achieve seasonal peak shaving and emergency reserve functions for hydrogen.

[0055] However, the injection and production system is extremely complex: the injection and production process involves multi-level control logic (such as the collaboration between the station control system and the operator), multi-device interaction (such as compressors, valves, sensors, safety valves, etc.), multi-condition coupling (such as pressure fluctuations, changes in hydrogen purity, equipment aging, etc.), and there are a large number of dynamic risk sources (such as human error, equipment failure, environmental interference, etc.).

[0056] Currently, risk assessment of underground hydrogen storage injection and production systems mainly relies on traditional industrial safety analysis methods, such as Probabilistic Risk Assessment (PRA), Hazard and Operability Analysis (HAZOP), Failure Mode and Effects Analysis (FMEA), and Fault Tree Analysis (FTA). These methods identify system risk factors through qualitative or semi-quantitative means and construct risk models based on event tree or fault tree logic.

[0057] However, existing methods are mostly based on fixed scenarios or assumptions, and cannot dynamically respond to changes in the system's operating status, making it difficult to capture real-time interactive risks during the injection and extraction process. At the same time, they lack the ability to model complex causal relationships between risk factors, especially in identifying "multi-factor common cause failure" or "chain reactions triggered by control behavior deviations".

[0058] To address the aforementioned issues, this application proposes an intelligent identification method for risk factors in underground hydrogen storage injection and production systems. By integrating System-Theoretic Process Analysis (STPA) and Structural Causal Model (SCM), a dynamic causal network is constructed and a counterfactual reasoning mechanism is introduced. The operational parameters of the underground hydrogen storage injection and production system, collected in real time, are used as exogenous variables to deduce potential accident hazards and the risk factors that lead to these hazards. This enables intelligent identification and quantitative assessment of risk factors in underground hydrogen storage injection and production systems.

[0059] This application applies to the full lifecycle safety management of underground hydrogen storage injection and production systems, including key operational phases such as gas injection, gas production, and equipment maintenance. The risk factor identification system in this application comprises a data acquisition layer (sensors, station control system, operation logs), an analysis layer (STPA and SCM model construction), and a decision-making layer (risk factor sensitivity analysis and safety measure generation). The risk factor identification system requires real-time access to multi-source data such as injection and production pressure, flow rate, equipment status, and operation records. It simulates risk evolution paths through dynamic causal networks and ultimately outputs risk priority ranking and targeted control strategies.

[0060] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0061] Figure 1 A flowchart illustrating the intelligent identification method for risk factors in underground hydrogen storage injection and production systems provided in this application. Figure 1 ,like Figure 1 As shown, the method includes:

[0062] S101. Obtain the operational parameters, operational risk factors, and structural causal model of the underground hydrogen storage injection and production system.

[0063] Understandably, in the safety management of underground hydrogen storage injection and extraction systems, obtaining accurate operational parameters, identifying operational risk factors, and constructing a reasonable structural causal model are fundamental to ensuring the safe and efficient operation of the system. Operational parameters can include environmental data detected on-site and actual system operating status parameters; these parameters can be used to comprehensively understand the operational status of the underground hydrogen storage injection and extraction system. Operational risk factors refer to all potential risk factors that may arise during the operation of the underground hydrogen storage injection and extraction system.

[0064] Environmental data can be acquired through various sensor devices. For example, pressure sensors can be installed at key locations in the underground hydrogen storage injection and extraction system to monitor pressure changes within the storage facility in real time, as pressure data reflects the stability of the storage facility. Temperature sensors can also be used to obtain the temperature within the storage facility, since hydrogen gas can be affected by temperature fluctuations, thus impacting the efficiency and safety of hydrogen storage.

[0065] Actual system operating status parameters may include equipment running time, operating efficiency, and equipment on / off status. This data can be obtained through the equipment's own control system or dedicated monitoring software. For example, recording the compressor's running time can determine the equipment's start-up and shutdown status.

[0066] Structural causal models are used to indicate the relationships between multiple operational risk factors in an underground hydrogen storage injection and production system. They can present the causal connections between various operational risk factors, helping the risk factor identification system determine how a change in one risk factor will affect other risk factors, and thus impact the safe operation of the entire underground hydrogen storage injection and production system. Structural causal models can be trained in advance based on the process flow of the underground hydrogen storage injection and production system. They can help the risk factor identification system predict and identify potential risks in advance, providing a basis for taking effective risk control measures.

[0067] S102. Based on the structural causal model, determine the types of accident hazards that match the operational parameters and operational risk factors, as well as the baseline risk value for each type of accident hazard.

[0068] Understandably, structural causal models can provide a clear framework for risk systems. By inputting real-time operational parameters into the model, it can infer and analyze the causal relationships between various operational risk factors. For example, if on-site monitoring data indicates a continuous increase in pressure within the hydrogen storage facility, while actual operating parameters show an abnormal increase in compressor operating frequency, a structural causal model can infer a potential safety hazard: pressure vessel overload. This is because the pressure increase could be due to excessive compressor operation leading to excessive hydrogen injection. The model can comprehensively consider these factors, combining historical accident data and pre-defined rules, to output the most probable type of safety hazard.

[0069] The baseline risk value refers to the basic probability of a potential accident occurring, determined solely by the operational procedures of the underground hydrogen storage injection and production system, assuming no abnormalities in any risk factors. It is a relatively stable reference value that reflects the potential risk level of the accident under ideal conditions. The baseline risk value provides a fundamental reference for the risk system to assess the actual risk level of the potential accident under current operational parameters. By comparing the actual risk with the baseline risk, the current safety status can be determined, and whether corresponding measures need to be taken to reduce the risk.

[0070] S103. Based on the benchmark risk value, determine the weight of each risk factor in the type of accident hazard.

[0071] Understandably, the weighting of risk factors reflects their relative importance in the process of causing potential accidents, and it can provide a basis for developing risk control strategies for the risk system. A risk factor is at least one of the operational risk factors; that is, multiple risk factors related to the type of potential accident are selected from a pool of operational risk factors.

[0072] For example, the impact weight of each risk factor can be determined through a comprehensive assessment based on historical data and expert experience. By collecting extensive historical operational data from underground hydrogen storage injection and production systems, the correlation between various risk factors and potential accidents under different conditions can be analyzed to determine the frequency and severity of accidents caused by each risk factor. Simultaneously, the impact of each risk factor is assessed based on the professional knowledge and practical experience of experts in relevant fields. Finally, the results of historical data analysis and expert assessment are combined to derive the impact weight of each risk factor on the type of potential accident.

[0073] The magnitude of an impact factor determines its priority in handling. A risk factor with a greater impact factor means it has a greater influence on the occurrence of potential accidents, and therefore should be addressed first. For example, if analysis reveals that abnormal pressure is a significant risk factor for a hydrogen storage facility leak, then when developing risk control measures, the focus should be on pressure monitoring and control. This includes strengthening the maintenance and calibration of pressure sensors to ensure timely detection of abnormal pressure and the implementation of appropriate adjustments, such as activating pressure relief devices.

[0074] For risk factors with a smaller impact, they can be considered after the risk factors with a larger impact have been addressed. By rationally determining the priority of risk factors, the risk management system can utilize resources more efficiently, take targeted measures to reduce the probability of accidents, and ensure the safe operation of the underground hydrogen storage injection and production system.

[0075] The intelligent identification method for risk factors in underground hydrogen storage injection and production systems provided in this application acquires the system's operational parameters, operational risk factors, and a structural causal model. The structural causal model indicates the correlation between multiple operational risk factors in the underground hydrogen storage injection and production system. Based on the structural causal model, it determines the types of accident hazards matching the operational parameters and the baseline risk value for each type of accident hazard. Based on the baseline risk value, it determines the weight of each risk factor's influence on the accident hazard type, and this weight characterizes the priority of handling the risk factor. This method can comprehensively monitor, accurately analyze, and scientifically manage risk factors in underground hydrogen storage injection and production systems, enabling early identification of potential risks and making risk management more targeted.

[0076] Figure 2 A flowchart illustrating the intelligent identification method for risk factors in underground hydrogen storage injection and production systems provided in this application. Figure 2 ,like Figure 2 As shown, this embodiment provides a detailed explanation of the safety risk characteristics and risk factor determination process required for constructing a structural causal model, specifically including:

[0077] S201. Based on the process flow data and equipment correlation data of the underground hydrogen storage injection and production system, determine at least one safety constraint, and based on the safety constraint, identify the safety risk characteristics of the underground hydrogen storage injection and production system.

[0078] Understandably, underground hydrogen storage injection and extraction systems involve numerous complex processes, from hydrogen injection and storage to extraction, each with its own specific operating parameters and requirements.

[0079] As an example, the following will describe the gas injection operation of the underground hydrogen storage injection and production system. It should be noted that the gas injection operation steps described below are only examples. The actual gas injection operation may vary depending on the underground hydrogen storage injection and production system. This application does not limit the gas injection operation steps, and the gas injection operation steps do not affect the identification of the safety risk characteristics shown in this application.

[0080] The hydrogen injection operation steps include: Before injection, operators can assess the current state of the hydrogen storage facility, confirming its inventory, pressure level, and the integrity of the geological structure to ensure there is no risk of leakage. Simultaneously, surface facilities can undergo comprehensive inspection and commissioning. The core equipment, the hydrogen compressor, must undergo a no-load test. Its auxiliary cooling and lubrication systems, as well as the pipes, valves, and flanges connected to the wellhead, must be ensured to be intact and sealed. Flow and pressure gauges used for measurement must also be accurately calibrated. If the hydrogen source contains impurities, a purification and drying system must be activated to treat it. The integrity of the injection well itself and the functionality of downhole safety valves must also be confirmed.

[0081] Once preparations are complete, the gas injection phase begins. Operators can slowly open the wellhead valves and start the compressor, initiating gas injection at a low displacement and pressure to achieve a smooth pressurization and avoid pressure shocks to the wellbore and reservoir. After the pressure stabilizes, the injection parameters are gradually increased to the design values. Monitoring is crucial during this steady-state injection process. Key parameters such as injection pressure, flow rate, wellhead temperature, and compressor operating status must be closely monitored in real time. Hydrogen purity is monitored through periodic gas sampling. The entire injection process typically requires flexible displacement adjustments based on the dynamic response of the reservoir pressure.

[0082] After the planned gas injection volume is completed or the preset pressure is reached, the gas injection operation enters the final stage. At this time, an orderly shutdown procedure must be performed, gradually reducing the compressor load until it stops, and the wellhead valves are closed in sequence. The storage pressure is then observed for a period of time to ensure stability. Finally, a comprehensive equipment inspection and data recording and archiving are carried out to provide a basis for subsequent gas production or the next round of gas injection operations.

[0083] Through in-depth analysis of the above process, the risk system can identify a series of safety constraints. For example, it sets the maximum pressure value within the hydrogen storage facility and specifies the temperature range for hydrogen storage. These safety constraints are fundamental to ensuring the safe operation of the underground hydrogen storage injection and extraction system. Breaching these constraints may trigger various safety risks. Based on these constraints, the potential safety risk characteristics of the hydrogen storage facility can be identified. These safety risk characteristics are used to characterize potential safety accidents and hazards in the underground hydrogen storage injection and extraction system.

[0084] S202. Based on safety constraints and safety risk characteristics, determine the safety feedback characteristics of the underground hydrogen storage injection and production system.

[0085] Understandably, safety constraints and safety risk characteristics are interrelated. Safety feedback characteristics are used to characterize the control actions and feedback paths required to achieve safety objectives when safety risks occur in the underground hydrogen storage injection and production system.

[0086] For example, when the pressure inside the hydrogen storage tank is detected to be approaching the set maximum pressure value, the safety feedback system can trigger an alarm device to remind operators to take control actions, such as activating the pressure relief valve to reduce the pressure. Simultaneously, the operator's actions can also be transmitted back to the safety feedback system via the feedback path, allowing the system to determine whether the pressure has decreased to a safe range and whether further action is needed.

[0087] Furthermore, safety feedback characteristics can also include feedback relationships between various devices. For example, when a compressor malfunctions, the control system can stop the compressor's operation and activate backup equipment to ensure normal hydrogen injection and storage. By clearly defining safety feedback characteristics, a complete safety control system can be constructed, improving the safety and reliability of underground hydrogen storage injection and extraction systems.

[0088] S203. Based on control actions and feedback paths, construct a safety control loop diagram for the underground hydrogen storage injection and extraction system.

[0089] Understandably, a safety control loop diagram can graphically represent the relationship between control actions and feedback paths. Constructing a safety control loop diagram helps identify the key equipment and parameters in the underground hydrogen storage injection and production system, as well as their connections and data transmission directions. Then, based on the previously determined control actions and feedback paths, these elements are integrated into the loop diagram. For example, in the loop diagram, arrows represent the direction of data transmission and the sequence of control actions, and different symbols represent various devices and sensors.

[0090] By constructing a safety control loop diagram, the safety control process of the underground hydrogen storage injection and extraction system can be clearly displayed, which is convenient for operators to understand and operate, and also provides strong support for safety management and fault diagnosis.

[0091] S204. Based on the safety control loop diagram, identify the control action sequence of the underground hydrogen storage injection and extraction system.

[0092] Understandably, a safety control loop diagram provides a clear framework for identifying the sequence of control actions in an underground hydrogen storage injection and production system. A sequence of control actions refers to a series of actions executed sequentially during the operation of an underground hydrogen storage injection and production system to address various safety risks and ensure normal system operation. Based on the safety control loop diagram, the risk system can identify each control action and its execution sequence according to the order of data transmission and control logic.

[0093] By identifying the sequence of control actions, the function and timing of each action can be clearly defined, ensuring the safe and stable operation of the underground hydrogen storage injection and production system under various operating conditions. This also provides a foundation for subsequent analysis of control action defects and risk factors.

[0094] S205. Identify the risk factors and triggering factors for each defective action in the control action sequence.

[0095] Understandably, in the actual operation of underground hydrogen storage injection and production systems, certain actions in the control sequence may malfunction, potentially leading to safety risks. To effectively prevent and control these risks, it is necessary to identify the risk factors and triggering factors for each malfunctioning action. Risk factors refer to the causes that lead to malfunctioning actions and may trigger safety risks, such as the inability of control actions to complete normally. Triggering factors refer to external environmental factors that may trigger malfunctioning actions, such as operator error and ambient temperature.

[0096] When determining the risk factors and triggering factors of a control action sequence, the control action sequence can be divided into multiple categories. According to the category type, the control action sequence can be analyzed and identified using the STPA model.

[0097] Control action sequences can be categorized into four types: never providing a control action, incorrect or unsafe control action, control action occurring prematurely / delayedly, and control action ending too early / lasting too long. The specific unsafe control actions, resulting risks, and corresponding safety constraints for each category are as follows:

[0098] Category 1: No control behavior provided;

[0099] 1. Unsafe control behavior may be that the operator / station control system did not perform hydrogen leak detection on key connection points such as compressors and valves before gas injection. This may result in the initial leak being difficult to detect in time, and the leak may expand after gas injection begins, forming an explosive gas cloud. The corresponding safety constraint is that the hydrogen concentration in the work area must be controlled below the lower explosive limit.

[0100] 2. Unsafe control behavior may be that the operator / station control system did not check the calibration status of pressure relief devices such as safety valves and rupture discs before gas injection. This may cause the last safety barrier to fail when the system is over-pressurized, which may lead to physical rupture of equipment or pipelines. The corresponding safety constraint is that the gas injection pressure must always be maintained within the design safety pressure range of the equipment and storage tank.

[0101] 3. Unsafe control behavior may be that the station control system does not continuously monitor the injection pressure of the storage tank during operation, which may result in the inability to grasp the most critical operating parameters in real time, and the risk of overpressure is extremely high. The corresponding safety constraint is that the injection pressure must always be maintained within the safe range.

[0102] 4. Unsafe control behavior may be that the station control system does not continuously monitor the purity of the injected hydrogen during operation, which may result in the injection of unqualified hydrogen (containing impurities such as O2) into the storage tank, which may contaminate the reservoir or trigger a chemical reaction. The corresponding safety constraint is that the purity of the hydrogen injected into the storage tank must always meet the design standards.

[0103] Category Two: Controlled Behavior Errors or Insecurity;

[0104] 1. Unsafe control behavior may be caused by the station control system setting an incorrect target pressure that exceeds the pressure bearing capacity of the pipeline / storage. This may directly lead the system to an overpressure state, resulting in equipment damage or leakage. The corresponding safety constraint is that the injection pressure must always be maintained within the safe range.

[0105] 2. Unsafe control behavior may be caused by operators misoperating valves, resulting in the high-pressure system impacting the low-pressure system (water hammer), which may damage pipelines, equipment or instruments and cause hydrogen leakage. The corresponding safety constraint is to ensure equipment integrity and prevent leakage.

[0106] 3. Unsafe control behaviors may include the purification device failing to automatically start or switch when it detects excessive purity, or operators mistakenly bypassing it, which may result in a large amount of substandard gas being injected into the storage, causing irreversible pollution and economic losses. The corresponding safety constraint is that the purity of hydrogen injected into the storage must always meet the design standards.

[0107] Category 3: Control behaviors occur prematurely or delayed;

[0108] 1. Unsafe control behavior may be due to the station control system's automatic pressure regulation duration being too short, prematurely exiting automatic mode before the pressure has stabilized, which may cause the pressure to fluctuate out of control again. The corresponding safety constraint is that the injection pressure must always be maintained within the safe range.

[0109] 2. Unsafe control behaviors may include setting the regeneration time of the purification device too short, or the operator stopping the regeneration process too early. This may result in the molecular sieve and other adsorbent materials not being fully regenerated, leading to a decrease in purification efficiency in the next cycle and causing purity to run out of control. The corresponding safety constraint is that the purity of the hydrogen injected into the storage must always meet the design standards.

[0110] 3. Unsafe control behavior may be that management or technical personnel provide the operator with an incorrect maximum injection pressure value for the storage tank, which may cause the operator or system to operate under unsafe high pressure, posing a huge risk. The corresponding safety constraint is that the injection pressure must always be maintained within the safe range.

[0111] Category 4: Control behavior ends too early / lasts too long;

[0112] Unsafe control behavior may involve taking temporary monitoring measures for too long after a minor leak is discovered, failing to carry out fundamental repairs in a timely manner, which may develop into a catastrophic leak and escalate the risk over time. The corresponding safety constraint is that the hydrogen concentration in the work area must be controlled below the lower explosive limit.

[0113] The intelligent risk factor identification method for underground hydrogen storage injection and extraction systems provided in this application determines safety constraints by deeply analyzing the process flow and equipment correlation data of the underground hydrogen storage injection and extraction system, identifies safety risk characteristics based on this, clarifies safety feedback characteristics, constructs a safety control loop diagram based on the safety feedback characteristics, accurately identifies the control action sequence, and deeply analyzes the risks and inducing factors of defective actions. This process can accurately identify potential safety hazards in advance, provide a scientific basis for taking targeted control measures, and effectively reduce the probability of safety risks occurring.

[0114] Figure 3 A flowchart illustrating the intelligent identification method for risk factors in underground hydrogen storage injection and production systems provided in this application. Figure 3 ,like Figure 3 As shown in this embodiment, the process of constructing a structural causal model based on safety risk characteristics and risk factors is explained in detail, including:

[0115] S301. The safety risk characteristics of the underground hydrogen storage injection and extraction system are used as the outcome variable.

[0116] Among them, safety risk characteristics are used to characterize potential safety accidents and safety hazards in underground hydrogen storage injection and extraction systems.

[0117] Understandably, underground hydrogen storage injection and production systems are subject to numerous factors that could lead to safety accidents and hazards during operation, such as hydrogen leakage and storage medium failure. These factors, once triggering an accident, could cause severe casualties, property damage, and large-scale environmental destruction. By treating safety risk characteristics as outcome variables, they can be placed at the core of the research. This results-oriented approach allows for in-depth analysis of the various factors affecting the safety of underground hydrogen storage injection and production systems, providing clear goals and directions for developing safety precautions.

[0118] S302. Use risk factor characteristics as basic and exogenous variables.

[0119] Risk factor characteristics are the risk factors and triggering factors of each defective action in the control actions used to achieve safety objectives, determined based on safety risk characteristics.

[0120] Understandably, the basic variables, or risk factors that cause accidents, are determined based on the process flow of the injection and production system. For example, during hydrogen injection, if the injection rate is too fast, it may cause a sharp increase in internal pressure of the storage equipment, leading to safety accidents such as equipment rupture. An excessively fast injection rate is a risk factor, or a basic variable.

[0121] Exogenous variables are inducing factors, encompassing human error, external environment, and other related factors. Operator negligence and violations of regulations can both contribute to safety accidents. Changes in temperature can also trigger accidents. Clearly defining the concepts and scope of basic and exogenous variables lays the foundation for constructing a scientifically sound structural causal model.

[0122] S303. By constructing causal relationships between outcome variables, basic variables, and exogenous variables through logic gates, a structural causal model is obtained.

[0123] Logic gates include AND gates, OR gates, and voting gates.

[0124] Understandably, logic gates can describe the relationships between variables in an intuitive and precise way. OR gates can be used to represent situations where a single factor can lead to an accident. In the actual operation of underground hydrogen storage injection and extraction systems, certain risk factors, once they occur, can directly trigger safety accidents. For example, if storage equipment is severely aged, even if other conditions are normal, the equipment may rupture, leading to a hydrogen leak. In this case, by using an OR gate to link the basic variable of severe equipment aging with the outcome variable of safety risk characteristics, the impact of a single factor on the accident can be clearly shown.

[0125] An AND gate is used to emphasize that an accident can only occur when multiple factors happen simultaneously. The safe operation of an underground hydrogen storage injection and extraction system relies on the coordinated work of multiple stages. If problems occur in multiple critical stages simultaneously, it can lead to serious safety accidents. For example, in the hydrogen extraction process, two basic variables may simultaneously exist: extraction valve malfunction and pipeline blockage. Only when both factors are present can hydrogen extraction fail normally, leading to safety issues such as abnormal pressure. In this case, an AND gate is needed to establish the causal relationship between them.

[0126] The voting gates can comprehensively consider multiple factors, and an accident will only occur when a certain number of factors are met. In the actual operation of underground hydrogen storage injection and extraction systems, there are multiple potential risk factors. When a certain number of key factors are present simultaneously, the probability of an accident increases. By using these logic gates, the relationships between outcome variables, basic variables, and exogenous variables can be accurately represented in the form of functions, constructing a scientifically sound structural causal model. This model can help risk systems deeply understand the generation mechanism of safety risks in underground hydrogen storage injection and extraction systems, and provide support for risk assessment, prediction, and prevention.

[0127] The corresponding basic formula is as follows:

[0128]

[0129]

[0130]

[0131] Where M represents the intermediate node, that is, the control defect action, and Xi represents all the risk factors and triggering factors of M.

[0132] Figure 4 A structural schematic diagram of the structural causal model provided in this application is shown below. Figure 4 As shown, the accident node Y is the outcome variable, which can represent, for example, hydrogen leakage. X1-X14 can be the basic variables in the risk factor characteristics, such as control algorithm error, slow operator response, pressure sensor reading distortion, gas detector failure, compressor abnormal shutdown, valve actuator failure, safety valve calibration expired, failure to perform leak detection, incorrect valve operation, use of non-explosion-proof tools, purification unit failure, failure to confirm safety conditions, improper maintenance, and communication system delay.

[0133] U1-U14 can represent exogenous variables in the structural causal model, whose prior probabilities determine the probability of risk factors occurring. Intermediate nodes M1-M4 can represent control defects in the control process, which can be discovered through collected operational parameters. For example, they can represent system pressure control failure, undetected early leaks, compromised equipment integrity, and failure of safety barriers, respectively. For simplicity, the exogenous variables of intermediate nodes are omitted.

[0134] The intelligent identification method for risk factors in underground hydrogen storage injection and production systems provided in this application sets the safety risk characteristics of the underground hydrogen storage injection and production system as outcome variables to characterize potential accident hazards. Basic variables and exogenous variables are used as risk factor characteristics, and logical gates such as OR gates, AND gates, and voting gates are used to construct the causal relationships between them, resulting in a structural causal model. This process can clearly present the complex causal relationships between variables, intuitively demonstrating how single or multiple factors can trigger safety accidents, and providing strong support for a deeper understanding of the safety risk generation mechanism of underground hydrogen storage injection and production systems.

[0135] Figure 5 A flowchart illustrating the intelligent identification method for risk factors in underground hydrogen storage injection and production systems provided in this application. Figure 4 ,like Figure 5 As shown in the figure, this embodiment provides a detailed explanation of the process of determining the type of accident hazard and the baseline risk value based on operational parameters, specifically including:

[0136] S401: Determine the target exogenous variables based on the operation parameters.

[0137] Understandably, underground hydrogen storage injection and extraction systems generate numerous real-time operational parameters during operation. These parameters cover various aspects, such as hydrogen injection flow rate, pressure, and temperature. Exogenous variables are factors that are not directly affected by other internal system variables but still influence system operation; they can also be understood as system disturbances or boundary condition variables. Based on real-time operational parameters, the target exogenous variables affecting system operation can be clearly identified, laying the foundation for subsequent risk assessment and hazard identification.

[0138] S402: Obtain the prior probability of the target exogenous variable.

[0139] Understandably, prior probability refers to the probability derived from past experience and analysis. It reflects an initial judgment on the likelihood of different states of a target exogenous variable occurring before any new monitoring data is available. Based on the actual operating status and simulation analysis results of the hydrogen storage reservoir injection and production system, combined with on-site monitoring data and the experience of domain experts, the probabilities of each exogenous variable in the structural causal model of the hydrogen storage reservoir—that is, the prior probabilities of various risk factors—can be assigned values. By assigning prior probabilities to exogenous variables, the risk system can represent the state distribution of these latent variables in a quantitative way, providing important data support for subsequent analysis based on the structural causal model.

[0140] For example, with Figure 4 Taking exogenous variables as an example, Table 1 is the prior probability table of exogenous variables provided in this application.

[0141] Table 1

[0142]

[0143] S403: Based on the structural causal model and the prior probability of the target exogenous variable, determine the type of accident hazard that matches the operation parameters.

[0144] Understandably, structural causal models can clearly describe the causal relationships between exogenous variables, endogenous variables, and outcome variables. Exogenous variables are factors external to the system that affect it. Endogenous variables are various influencing factors existing within the injection and extraction system during its operation. The type of accident hazard is an outcome variable in the structural causal model, reflecting the potential safety risks to the system.

[0145] Based on structural causal models, the causal chains between various variables can be clearly defined. For example, under high-temperature conditions (exogenous variable), the metal materials (such as storage tanks and pipelines) of underground hydrogen storage injection and extraction systems will deform due to thermal expansion. This deformation may lead to insufficient compression of the sealing gaskets at the connection between the storage tank and the pipeline (endogenous variable), thereby reducing sealing performance. If the sealing performance continues to deteriorate, hydrogen may leak into the surrounding strata through tiny gaps, ultimately causing safety hazards such as hydrogen accumulation, explosion, or environmental pollution (outcome variable).

[0146] By inputting the target exogenous variables into the structural causal model, and through model calculations combined with the possible states of endogenous variables, the type of accident hazard matching the operational parameters under the current state of the exogenous variables can be determined. This helps the risk system identify potential safety risks to the injection and production system in advance, providing a basis for taking corresponding preventive measures.

[0147] S404: Determine the baseline risk value for each type of accident hazard based on the basic variables of the accident hazard type and the prior probabilities of the target exogenous variables.

[0148] Understandably, the baseline risk value reflects the probability of an accident occurring in the injection and production system without any intervention from risk factors. The basic variables for accident hazard types refer to various factors directly related to that hazard. The target exogenous variables are the external factors that have been identified and whose prior probabilities have been obtained.

[0149] After obtaining the prior probabilities of the target exogenous variables, this probabilistic information can be input into the structural causal model. Through model calculation and simulation, the probability of the injection-production system experiencing an accident hazard of the specified type under the influence of no risk factors can be obtained; this is the baseline risk value. This baseline risk value can provide a reference for assessing the safety risk level of the injection-production system.

[0150] The intelligent risk factor identification method for underground hydrogen storage injection and production systems provided in this application determines target exogenous variables based on real-time operating parameters of the underground hydrogen storage injection and production system, obtains their prior probabilities, then uses a structural causal model combined with the prior probabilities to identify accident hazard types matching the operating parameters, and finally calculates the baseline risk value of the accident hazard type based on the basic variables of the accident hazard and the target exogenous variables. This process can identify potential safety risks in the system and quantify the baseline risk value to provide a benchmark for subsequent determination of major risk factors.

[0151] Figure 6 A flowchart illustrating the intelligent identification method for risk factors in underground hydrogen storage injection and production systems provided in this application. Figure 5 ,like Figure 6 As shown in the example, this embodiment provides a detailed explanation of the process for determining the weight of risk factors, specifically including:

[0152] S501: For any risk factor, counterfactual intervention is performed to make the risk factor appear certain.

[0153] Understandably, counterfactual intervention is a common method in the field of causal inference. In the context of risk assessment, there are often many uncertainties. These risk factors may or may not occur, and their occurrence and extent are difficult to predict accurately. Through counterfactual intervention, a hypothetical scenario can be artificially set up, making it certain that a specific risk factor will occur (do(Xi=1)).

[0154] For example, in an underground hydrogen storage injection and production system, there may be multiple risk factors, such as unconfirmed safety conditions, operator error, and improper maintenance. To study the impact of operator error on the occurrence of an accident, counterfactual intervention can be used. This involves assuming all other risk factors remain unchanged—that is, disregarding whether safety conditions are confirmed or maintenance is correct—and forcing operator error to a certain state, such as incorrect valve operation. Through this counterfactual intervention, the impact of operator error on the system when it is determined to occur can be observed in isolation, laying the foundation for a more in-depth analysis of its relationship with potential accidents. This approach eliminates interference from other factors, allowing for a clearer focus on the role of a specific risk factor and a more accurate assessment of its impact on the overall risk.

[0155] S502: Determine the conditional probability of risk factors based on operational parameters and structural causal models.

[0156] Understandably, structural causal models are models that can clearly describe the causal relationships between various risk factors. In underground hydrogen storage injection and production systems, various risk factors are interconnected and mutually influential. Structural causal models can clearly demonstrate the relationships between risk factors and their pathways of action.

[0157] Operational parameters are data obtained through actual measurement related to various risk factors. These data are crucial for objectively reflecting the state of risk factors. When determining the conditional probability of risk factors, the actual measured operational parameters can be combined with a structural causal model. Based on the actual data and the causal relationship between factors, the conditional probability of risk factors (P(Y=1|do(Xi=1))) can be calculated scientifically and reasonably, providing strong support for accurate risk assessment.

[0158] S503: Based on conditional probability and baseline risk value, generate the weight of risk factors on the type of accident hazard.

[0159] Understandably, the baseline risk value represents the fundamental risk level inherent in the system itself, without considering the impact of risk factors. It serves as an initial measure of the overall risk status of the system. Conditional probability reflects the probability of a potential accident occurring in the system given that a specific risk factor is certain to occur. After determining the conditional probability and the baseline risk value, certain calculation methods can be used to generate the weight of each risk factor in relation to the type of potential accident.

[0160] The formula for calculating the specific gravity (Si) is as follows:

[0161]

[0162] This calculation method clearly identifies the relative importance of each risk factor to different accident hazard types. Specifically, the impact ratio quantifies the extent to which the certainty of a specific risk factor's occurrence will increase the probability of an accident under existing unfavorable conditions. A positive value indicates that the factor will exacerbate the risk, and its magnitude directly reflects the relative importance of the factor in a given accident scenario. This provides a solid theoretical basis and quantitative support for determining the priority of risk management and implementing precise and effective safety interventions.

[0163] by Figure 4 Taking the risk factors (X1-X14) shown as an example, the risk factors determined by the current operational data include (X4, X9, X12, X13, X14). Table 2 shows the analysis results of the influence ratio of these risk factors.

[0164] Table 2

[0165]

[0166] According to the impact weight analysis, the erroneous operation of valve (X9) resulted in an 89.32% reduction in risk, making it the most critical risk factor. This highlights the decisive role of human factors in the safety of hydrogen storage facilities. Operator errors not only directly compromise equipment integrity but can also lead to the failure of safety isolation barriers, creating a dual safety hazard.

[0167] In contrast, unverified safety conditions (X12) and improper maintenance (X13) tied for second place with an impact of approximately 20%, indicating that the standardized execution of work procedures is equally crucial. Meanwhile, the impact of gas detector failure (X4) and communication system delays (X14) was relatively limited, reflecting that under the existing safety system, a single equipment failure or communication problem can be compensated for by other protective layers.

[0168] The intelligent risk factor identification method for underground hydrogen storage injection and production systems provided in this application uses counterfactual intervention to ensure that risk factors are in a deterministic state, eliminating interference from other factors to determine the role of specific risk factors. It determines the conditional probability of each risk factor by combining operational parameters and a structural causal model. Then, based on the conditional probability and a benchmark risk value, it generates the weight of each risk factor in relation to the type of accident hazard, identifying the relative importance of each risk factor. This achieves a comprehensive, in-depth, and accurate analysis of risk factors, providing a reliable basis for developing targeted risk prevention and control strategies.

[0169] Figure 7 This is a schematic diagram of the intelligent risk factor identification device for the underground hydrogen storage injection and production system provided in this application, as shown below. Figure 7 As shown, the intelligent risk factor identification device 70 for the underground hydrogen storage injection and production system provided in this embodiment includes:

[0170] The acquisition module 701 is used to acquire the operating parameters, operating risk factors, and structural causal model of the underground hydrogen storage injection and production system. The structural causal model is used to indicate the correlation between multiple risk factors of the underground hydrogen storage injection and production system.

[0171] The determination module 702 is used to determine the accident hazard type that matches the operation parameters and operation risk factors, as well as the baseline risk value of the accident hazard type, based on the structural causal model.

[0172] The determination module 702 is used to determine the weight of each risk factor on the type of accident hazard based on the baseline risk value. The risk factor is at least one of the operational risk factors, and the weight of the risk factor is used to characterize the processing priority of the risk factor.

[0173] In one possible implementation, the device further includes: a construction module 703;

[0174] The determination module 702 is also used to use the safety risk characteristics of the underground hydrogen storage injection and production system as the result variable; the safety risk characteristics are used to characterize the potential safety accidents and safety hazards of the underground hydrogen storage injection and production system.

[0175] The determination module 702 is also used to use risk factor characteristics as basic variables and exogenous variables; the risk factor characteristics are risk factors and inducing factors of each defective action in the control actions to achieve the safety objectives, which are determined based on safety risk characteristics.

[0176] Module 703 is used to build structural causal models based on outcome variables, basic variables, and exogenous variables.

[0177] In one possible implementation, the determining module 702 is further configured to determine at least one safety constraint based on the process flow data and equipment association data of the underground hydrogen storage injection and production system, and to identify the safety risk characteristics of the underground hydrogen storage injection and production system based on the safety constraint.

[0178] The determination module 702 is also used to determine the safety feedback characteristics of the underground hydrogen storage injection and production system based on safety constraints and safety risk characteristics. The safety feedback characteristics are used to characterize the control actions and feedback paths required to achieve the safety objectives when safety risks occur in the underground hydrogen storage injection and production system.

[0179] The determination module 702 is also used to determine the risk factor characteristics based on the safety feedback characteristics.

[0180] In one possible implementation, the construction module 703 is specifically used to construct a safety control loop diagram of the underground hydrogen storage injection and extraction system based on control actions and feedback paths.

[0181] The determination module 702 is specifically used to identify the control action sequence of the underground hydrogen storage injection and extraction system based on the safety control loop diagram;

[0182] The determination module 702 is specifically used to determine the risk factors and triggering factors of each defective action in the control action sequence.

[0183] In one possible implementation, the construction module 703 is specifically used to construct the causal relationship between the result variable, the basic variable and the exogenous variable through logic gates to obtain a structural causal model, wherein the logic gates include AND gates, OR gates and voting gates.

[0184] In one possible implementation, the determining module 702 is specifically used to determine the target exogenous variable based on the operation parameters; obtain the prior probability of the target exogenous variable; and determine the type of accident hazard that matches the operation parameters based on the structural causal model and the target exogenous variable.

[0185] The determination module 702 is specifically used to determine the baseline risk value of the accident hazard type based on the basic variables of the accident hazard type and the prior probability of the target exogenous variables.

[0186] In one possible implementation, the determining module 702 is specifically used to perform counterfactual intervention processing on any risk factor to make the risk factor in a deterministic occurrence state.

[0187] The determination module 702 is specifically used to determine the conditional probability of risk factors based on operational parameters and structural causal models;

[0188] The determination module 702 is specifically used to generate the weight of risk factors on the type of accident hazard based on conditional probability and benchmark risk value.

[0189] The intelligent risk factor identification device for the underground hydrogen storage injection and production system provided in this embodiment can execute the method provided in the above-mentioned method embodiment. Its implementation principle and technical effect are similar, and will not be described in detail here.

[0190] Figure 8 A schematic diagram of the structure of the electronic device provided in this application. Figure 8 As shown, the electronic device 80 provided in this embodiment includes at least one processor 801 and a memory 802. Optionally, the device 80 further includes a communication component 803. The processor 801, memory 802, and communication component 803 are connected via a bus 804.

[0191] In a specific implementation, at least one processor 801 executes computer execution instructions stored in memory 802, causing at least one processor 801 to perform the above-described method.

[0192] The specific implementation process of processor 801 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0193] In the above embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0194] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0195] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0196] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0197] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the above-described method.

[0198] The aforementioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0199] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in the device.

[0200] The division of units is merely a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0201] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0202] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0203] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0204] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0205] Finally, it should be noted that other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein, and is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

Claims

1. A method for intelligent identification of risk factors in an underground hydrogen storage injection and production system, characterized in that, include: The operational parameters, operational risk factors, and structural causal model of the underground hydrogen storage injection and production system are obtained. The structural causal model is used to indicate the correlation between multiple risk factors of the underground hydrogen storage injection and production system. Based on the structural causal model, determine the accident hazard type that matches the operation parameters and the operation risk factors, and the baseline risk value of the accident hazard type; Based on the baseline risk value, the weight of each risk factor in relation to the type of accident hazard is determined. The risk factor is at least one of the operational risk factors, and the weight of the risk factor is used to characterize the processing priority of the risk factor.

2. The method according to claim 1, characterized in that, The method further includes: The safety risk characteristics of the underground hydrogen storage injection and production system are used as the outcome variable; the safety risk characteristics are used to characterize the potential safety accidents and safety hazards of the underground hydrogen storage injection and production system. Risk factor characteristics are used as basic and exogenous variables; the risk factor characteristics are risk factors and inducing factors of each defective action in the control actions used to achieve safety objectives, which are determined based on safety risk characteristics. The structural causal model is constructed based on the outcome variable, the basic variable, and the exogenous variable.

3. The method according to claim 2, characterized in that, The method further includes: Based on the process flow data and equipment association data of the underground hydrogen storage injection and production system, at least one safety constraint is determined, and based on the safety constraint, the safety risk characteristics of the underground hydrogen storage injection and production system are identified. Based on the safety constraints and the safety risk characteristics, the safety feedback characteristics of the underground hydrogen storage injection and production system are determined. The safety feedback characteristics are used to characterize the control actions and feedback paths required to achieve the safety objectives when the underground hydrogen storage injection and production system encounters a safety risk. Based on the safety feedback characteristics, the risk factor characteristics are determined.

4. The method according to claim 3, characterized in that, The step of determining the risk factor characteristics based on the safety feedback characteristics includes: Based on the control actions and the feedback path, a safety control loop diagram of the underground hydrogen storage injection and production system is constructed. Based on the safety control loop diagram, identify the control action sequence of the underground hydrogen storage injection and production system; Identify the risk factors and triggering factors for each defective action in the control action sequence.

5. The method according to claim 4, characterized in that, The construction of the structural causal model based on the outcome variable, the basic variable, and the exogenous variable includes: A structural causal model is obtained by constructing causal relationships between the outcome variable, the basic variable, and the exogenous variable using logic gates, wherein the logic gates include AND gates, OR gates, and voting gates.

6. The method according to any one of claims 2-5, characterized in that, The step of determining the accident hazard type matching the operational parameters and the baseline risk value of the accident hazard type based on the structural causal model includes: Based on the aforementioned operational parameters, the target exogenous variables are determined; Obtain the prior probability of the target exogenous variable; Based on the structural causal model and the target exogenous variable, determine the type of accident hazard that matches the operating parameters; Based on the basic variables of the accident hazard type and the prior probabilities of the target exogenous variables, the baseline risk value of the accident hazard type is determined.

7. The method according to claim 6, characterized in that, The step of determining the weight of each risk factor in relation to the type of accident hazard based on the benchmark risk value includes: For any given risk factor, counterfactual intervention is performed to ensure that the risk factor is in a state of certainty. Based on the operational parameters and the structural causal model, the conditional probability of the risk factor is determined; Based on the conditional probability and the baseline risk value, the influence ratio of the risk factor on the accident hazard type is generated.

8. A smart identification device for risk factors in an underground hydrogen storage injection and extraction system, characterized in that, include: The acquisition module is used to acquire the operating parameters, operational risk factors, and structural causal model of the underground hydrogen storage injection and production system. The structural causal model is used to indicate the correlation between multiple risk factors of the underground hydrogen storage injection and production system. The determination module is used to determine, based on the structural causal model, the accident hazard type that matches the operation parameters and the operation risk factors, and the baseline risk value of the accident hazard type; The determination module is used to determine the weight of each risk factor on the type of accident hazard based on the benchmark risk value. The risk factor is at least one of the operational risk factors, and the weight of the risk factor is used to characterize the processing priority of the risk factor.

9. An electronic device, characterized in that, include: Memory, processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory, causing the processor to perform the method as described in any one of claims 1-7.

10. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method described in any one of claims 1-7.

Images