An accident prevention and control strategy, method, device, and storage medium

Abstract

This application discloses an accident prevention and control strategy method, apparatus, and storage medium, relating to the field of accident risk analysis technology. It can improve the accuracy of early warning for LNG storage tank accidents, thereby improving the safety of LNG storage tank operation and reducing the occurrence of potential LNG storage tank accidents. The accident prevention and control strategy method includes: using a computing device to arbitrarily combine multiple risk factors that trigger LNG storage tank accidents to obtain at least one set of risk factors; evaluating the correlation between risk factors in each risk factor set within the at least one set of risk factors to obtain correlation evaluation parameters for each risk factor set; determining the probability of key risk factors and the correlation between risk factors based on the correlation evaluation parameters of each risk factor set; and determining an accident prevention and control strategy based on the probability of key risk factors and the correlation between risk factors.

Description

Technical Field

[0001] This application relates to the field of accident risk analysis technology, and in particular to an accident prevention and control strategy, method, device and storage medium. Background Technology

[0002] As a critical facility for storing liquefied natural gas (LNG), LNG storage tanks face significant safety risks while ensuring the supply of natural gas energy. To summarize and analyze accidents involving LNG storage tanks, accident modeling methods can be used to construct analytical models of historical accidents involving LNG storage tanks.

[0003] However, most LNG storage tank accident models built using accident modeling methods focus on the correlation between specific factors and the safety risks of LNG storage tanks, such as material properties and structural design, while neglecting the complex and variable environmental factors and operating conditions faced by LNG storage tanks in actual operation. This limitation makes it impossible to comprehensively and accurately assess the safety status of LNG storage tanks, thus hindering the provision of effective support for the safety risk management of LNG storage tanks. Summary of the Invention

[0004] The purpose of this application is to provide an accident prevention strategy, method, device, and storage medium that can improve the accuracy of early warning of LNG storage tank accidents, thereby improving the safety of LNG storage tank operation and reducing the occurrence of potential LNG storage tank accidents.

[0005] To achieve the above objectives, this application adopts the following technical solution:

[0006] In a first aspect, this application provides an accident prevention and control strategy method, comprising: arbitrarily combining multiple risk factors that trigger liquefied natural gas storage tank accidents to obtain at least one set of risk factors; assessing the correlation between risk factors in each risk factor set within the at least one set of risk factors to obtain correlation assessment parameters for each risk factor set; the correlation assessment parameters include at least one of the following: support, confidence, dissimilarity, lift, or leverage ratio; determining the probability of the occurrence of correlations between key risk factors and risk factors based on the correlation assessment parameters of each risk factor set; and determining an accident prevention and control strategy based on the probability of the occurrence of correlations between key risk factors and risk factors.

[0007] The risk prevention and control strategy method provided in this application combines multiple risk factors that trigger LNG storage tank accidents to obtain multiple risk factor sets. It then deeply evaluates the internal correlations between the risk factors in these risk factor sets to obtain correlation assessment parameters for each risk factor set. Using these correlation assessment parameters, it accurately identifies key risk factors and their inter-factor correlation probabilities, and determines the LNG storage tank accident prevention and control strategy based on these key risk factors and their inter-factor correlation probabilities. The accident prevention and control strategy method provided in this application improves the accuracy of LNG storage tank accident early warning, enhances the safety of LNG storage tank operation, and thus reduces the potential occurrence of LNG storage tank accidents.

[0008] In one possible implementation, the probability of a correlation between key risk factors and risk factors is determined based on the correlation assessment parameters of each risk factor set, including: determining a first risk factor set from at least one risk factor set whose probability of triggering an accident is greater than a first threshold based on the correlation assessment parameters; constructing a risk factor correlation network based on the risk factors in the first risk factor set and the correlation assessment parameters of the first risk factor set; and determining the probability of a correlation between key risk factors and risk factors by analyzing the risk factor correlation network.

[0009] In one possible implementation, based on the associated assessment parameters, a first set of risk factors is determined from at least one set of risk factors, wherein the probability of triggering an accident is greater than a first threshold. This includes: determining the first set of risk factors from at least one set of risk factors where the support is greater than a second threshold, and / or the confidence is greater than a third threshold, and / or the difference is greater than a fourth threshold, and / or the lift is greater than or equal to 1, and / or the leverage is greater than 0.

[0010] In one possible implementation, the degree of difference satisfies the following formula:

[0011]

[0012] Where I(X→Y) represents the degree of difference in the occurrence of risk factor X and risk factor Y, C(X→Y) represents the confidence level in the occurrence of risk factor X and risk factor Y, and S(Y) represents the support level of risk factor Y.

[0013] In one possible implementation, the leverage ratio satisfies the following formula:

[0014] Leverage(X→Y)=P(X∩Y)-P(X)×P(Y)

[0015] Where Leverage(X→Y) represents the leverage ratio at which the occurrence of risk factor X triggers the occurrence of risk factor Y, P(X) represents the probability that risk factor X triggers an LNG storage tank accident, and P(Y) represents the probability that the occurrence of risk factor Y triggers an LNG storage tank accident.

[0016] In one possible implementation, key risk factors are identified by analyzing the risk factor association network, including: calculating the node degree value, clustering coefficient, and betweenness number of each risk factor in the risk factor association network; performing a weighted summation of the node degree value, clustering coefficient, and betweenness number of each risk factor to obtain the importance of each risk factor; and identifying risk factors with an importance greater than a fifth threshold as key risk factors.

[0017] In one possible implementation, the probability of associations between risk factors is determined by analyzing the risk factor association network, including: determining the shortest length of each path in the risk factor association network based on the lift between every two risk factors; and averaging the shortest lengths of each path to obtain the average shortest length of the risk factor association network.

[0018] In one possible implementation, the length of the average shortest path in the risk factor association network satisfies the following formula:

[0019]

[0020] Where L represents the average shortest length of the risk factor association network, and d ij Let represent the shortest path length between risk factor i and risk factor j in the risk factor association network, and n represent the number of risk factors in the risk factor association network; n is a positive integer and n is greater than or equal to 1.

[0021] Secondly, this application provides an accident prevention and control strategy device, including a processing unit:

[0022] The processing unit is used to instruct the arbitrary combination of multiple risk factors that trigger liquefied natural gas storage tank accidents to obtain at least one set of risk factors; the processing unit is also used to instruct the assessment of the association between risk factors in each risk factor set in the at least one set of risk factors to obtain association assessment parameters for each risk factor set; the association assessment parameters include at least one of the following: support, confidence, dissimilarity, lift, or leverage ratio; the processing unit is also used to instruct the determination of the probability of the occurrence of association between key risk factors and risk factors based on the association assessment parameters of each risk factor set; the processing unit is also used to instruct the determination of accident prevention and control strategies based on the probability of the occurrence of association between key risk factors and risk factors.

[0023] In one possible implementation, the processing unit is further configured to instruct, based on association evaluation parameters, to determine, from at least one set of risk factors, a first set of risk factors whose probability of triggering an accident is greater than a first threshold; the processing unit is further configured to instruct, based on the risk factors in the first set of risk factors and the association evaluation parameters of the first set of risk factors, to construct a risk factor association network; the processing unit is further configured to instruct, by analyzing the risk factor association network, to determine the probability of key risk factors and the association between risk factors occurring.

[0024] In one possible implementation, the processing unit is further configured to instruct the determination of a first risk factor set from at least one set of risk factors that has a support greater than a second threshold, and / or a confidence level greater than a third threshold, and / or a difference greater than a fourth threshold, and / or an elevation greater than or equal to 1, and / or a leverage ratio greater than 0.

[0025] In one possible implementation, the degree of difference satisfies the following formula:

[0026]

[0027] Where I(X→Y) represents the degree of difference in the occurrence of risk factor X and risk factor Y, C(X→Y) represents the confidence level in the occurrence of risk factor X and risk factor Y, and S(Y) represents the support level of risk factor Y.

[0028] In one possible implementation, the leverage ratio satisfies the following formula:

[0029] Leverage(X→Y)=P(X∩Y)-P(X)×P(Y)

[0030] Where Leverage(X→Y) represents the leverage ratio at which the occurrence of risk factor X triggers the occurrence of risk factor Y, P(X) represents the probability that risk factor X triggers an LNG storage tank accident, and P(Y) represents the probability that the occurrence of risk factor Y triggers an LNG storage tank accident.

[0031] In one possible implementation, the processing unit is further configured to instruct the calculation of the node degree value, clustering coefficient, and betweenness number of each risk factor in the risk factor association network; the processing unit is further configured to instruct the weighted summation of the node degree value, clustering coefficient, and betweenness number of each risk factor to obtain the importance corresponding to each risk factor; the processing unit is further configured to instruct the identification of risk factors with an importance greater than a fifth threshold as key risk factors.

[0032] In one possible implementation, the processing unit is further configured to instruct the determination of the shortest length of each path in the risk factor association network based on the lift between every two risk factors in the risk factor association network; the processing unit is further configured to instruct the mean operation of the shortest length of each path to obtain the average shortest length of the risk factor association network.

[0033] In one possible implementation, the length of the average shortest path in the risk factor association network satisfies the following formula:

[0034]

[0035] Where L represents the average shortest length of the risk factor association network, and d ij Let represent the shortest path length between risk factor i and risk factor j in the risk factor association network, and n represent the number of risk factors in the risk factor association network; n is a positive integer and n is greater than or equal to 1.

[0036] Thirdly, this application provides an accident prevention strategy device, which includes: a processor and a communication interface; the communication interface and the processor are coupled, and the processor is used to run computer programs or instructions to implement the accident prevention strategy method as described in the first aspect and any possible implementation of the first aspect.

[0037] Fourthly, this application provides a computer-readable storage medium storing instructions that, when executed on a terminal, cause the terminal to perform the accident prevention strategy method as described in the first aspect and any possible implementation thereof.

[0038] Fifthly, this application provides a computer program product containing instructions that, when run on an accident prevention strategy device, causes the accident prevention strategy device to execute the accident prevention strategy method as described in the first aspect and any possible implementation thereof.

[0039] In a sixth aspect, this application provides a chip including a processor and a communication interface, the communication interface being coupled to the processor, the processor being used to run computer programs or instructions to implement the accident prevention strategy method as described in the first aspect and any possible implementation of the first aspect.

[0040] Specifically, the chip provided in this application also includes a memory for storing computer programs or instructions. Attached Figure Description

[0041] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0042] Figure 1 This is a schematic diagram of the structure of an accident prevention and control strategy system provided in an embodiment of this application;

[0043] Figure 2 This is a schematic diagram of the structure of an accident prevention and control strategy device provided in an embodiment of this application;

[0044] Figure 3 A flowchart illustrating an accident prevention and control strategy method provided in this application embodiment;

[0045] Figure 4 A flowchart illustrating another accident prevention strategy method provided in this application embodiment;

[0046] Figure 5 An example diagram illustrating the process of using the classic Apriori algorithm to screen a first set of risk factors, provided in an embodiment of this application;

[0047] Figure 6 A flowchart illustrating another accident prevention strategy method provided in this application embodiment;

[0048] Figure 7 A flowchart illustrating another accident prevention strategy method provided in this application embodiment;

[0049] Figure 8 A flowchart illustrating another accident prevention strategy method provided in this application embodiment;

[0050] Figure 9 This is a schematic diagram of another accident prevention strategy device provided in an embodiment of this application. Detailed Implementation

[0051] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0052] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this application, unless otherwise stated, "a plurality of" means two or more.

[0053] In embodiments of this application, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, article, or apparatus that includes that element.

[0054] In the embodiments of this application, the terms "exemplary" or "for example" are used to indicate that something is an example, illustration, or description. Any embodiment or design that is described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design. Specifically, the use of the terms "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0055] In the description of this specification, specific features, structures, materials, or characteristics may be combined in any suitable manner in one or more embodiments or examples.

[0056] LNG receiving terminals, as crucial transit points for receiving imported LNG resources, play a vital role in ensuring the security of natural gas supply. Through these terminals, LNG transported by sea can be converted into gaseous or liquefied natural gas and delivered to inland natural gas pipeline networks, thereby meeting users' natural gas demands. LNG storage tanks are the core components of LNG receiving terminals, primarily used to store LNG transported from various locations.

[0057] Due to an inadequate hazard identification system and insufficient risk management measures, LNG storage tanks, as key facilities for storing liquefied natural gas, face significant safety risks while ensuring natural gas energy supply. This leads to frequent accidents related to LNG storage tanks, particularly fires and explosions caused by tank leaks, which pose serious safety hazards. To summarize and analyze LNG storage tank accidents and implement preventative measures against potential accident risks, accident modeling methods can be used to construct an analytical model of historical LNG storage tank accidents.

[0058] For the oil and gas storage and transportation industry, such as LNG receiving terminals, accident models are categorized into traditional and modern models based on the characteristics of their respective eras. Traditional models mainly include sequence models and epidemiological models, such as fault trees, event trees, and REASON models. Modern models mainly include system models, formal models, and dynamic sequence models, such as system theory accident models and process models, probabilistic accident models, and dynamic risk assessment methods. Both traditional and modern models are important tools for analyzing and understanding system failures, accident causes, and risk management.

[0059] Among various traditional models, fault tree analysis (FTA) is a graphical risk assessment method that identifies the causes and events leading to a specific accident by constructing a fault tree. FTA starts from the top event and analyzes downwards step by step, helping to identify various failure modes and potential causes. In contrast, event tree analysis (ASTA) begins with the initial event and derives possible consequences. ASTA can assess different paths and their consequences after an accident occurs, thus helping to develop effective emergency response plans. The REASON model, on the other hand, emphasizes the role of human factors in accidents and uses a "human-machine-environment" model to analyze the accident's mechanism. Through systematic analysis of accidents, the REASON model can reveal potential system defects and human error, thereby improving system safety.

[0060] Among various modern accident models, systems theory accident models, based on a systems theory perspective, view accidents as the result of a complex system. Systems theory accident models emphasize the interrelationships between elements within the system and stress reducing the probability of accidents through an understanding of the system as a whole. Probabilistic accident models, based on probability theory, analyze and manage accidents and adverse events. They quantify uncertainty and assess the likelihood of different events occurring. Probabilistic accident models typically employ methods such as Monte Carlo simulations to improve the accuracy of predicting the probability of accidents. Dynamic risk assessment methods consider the impact of time factors on accident risk, using dynamic models to assess risk in real time, enabling more effective responses to rapidly changing environments and conditions.

[0061] However, most of the aforementioned traditional and modern accident models focus on the correlation between specific factors and the safety risks of LNG storage tanks, such as material properties and structural design, while neglecting the complex and ever-changing environmental factors and operating conditions faced by LNG storage tanks in actual operation. Accident analysis methods for LNG storage tanks that focus on individual accident models cannot be combined with analytical techniques from other fields, nor can they broaden the analysis of accident causation. This reduces the likelihood of accurately predicting and controlling LNG storage tank accidents, ultimately failing to improve the safety of LNG receiving terminals.

[0062] In view of this, embodiments of this application provide a risk prevention and control strategy method. This method combines multiple risk factors that trigger LNG storage tank accidents to obtain multiple risk factor sets, and deeply evaluates the internal correlations between the risk factors in these risk factor sets to obtain correlation assessment parameters for each risk factor set. Then, using the correlation assessment parameters corresponding to each risk factor set, key risk factors and their inter-factor correlation probabilities are accurately identified. Based on the key risk factors and their inter-factor correlation probabilities, an accident prevention and control strategy for LNG storage tanks is determined. The accident prevention and control strategy method provided in this application improves the accuracy of LNG storage tank accident early warning, enhances the safety of LNG storage tank operation, and thereby reduces the potential occurrence of LNG storage tank accident risks.

[0063] For example, Figure 1 The diagram shows a schematic of an accident prevention and control strategy system 10 provided in an embodiment of this application. The accident prevention and control strategy system 10 may include at least one computing device 101 and at least one data acquisition device 102, and the computing device 101 may be communicatively connected to the data acquisition device 102. Figure 1 Only one computing device 101 and one data acquisition device 102 are shown in the illustration. This application embodiment does not impose any limitation on the number of computing devices 101 and data acquisition devices 102.

[0064] In one possible implementation, computing device 101 is used to arbitrarily combine multiple risk factors that trigger an accident in a liquefied natural gas storage tank to obtain at least one set of risk factors; evaluate the correlation between risk factors in each risk factor set within the at least one set of risk factors to obtain correlation evaluation parameters for each risk factor set; the correlation evaluation parameters include at least one of the following: support, confidence, dissimilarity, lift, or leverage; based on the correlation evaluation parameters for each risk factor set, determine the probability of the occurrence of correlations between key risk factors and risk factors; and determine accident prevention and control strategies based on the probability of the occurrence of correlations between key risk factors and risk factors.

[0065] Optionally, the computing device 101 can be an electronic device with computing capabilities, such as a smartphone, tablet, or laptop. The computing device 101 can be deployed indoors or outdoors, handheld or vehicle-mounted. It can also be deployed on water (such as on a ship) or in the air (such as on an airplane, balloon, or satellite). Figure 1 The example shown is a laptop computer, with computing device 101 as an example.

[0066] In one possible implementation, data acquisition device 102 is used to collect historical accident data of the LNG storage tank and send the collected historical accident data of the LNG storage tank to computing device 101. Data acquisition device 102 can be a server with data acquisition and processing functions, or it can be an electronic device with storage functions, such as a smartphone, tablet, or other device. Figure 1 The example shown is a data acquisition device 102 serving as a server.

[0067] It should be noted that, Figure 1 This is just an example framework diagram. Figure 1 The number of nodes included and the names of the devices are unlimited, except for... Figure 1 In addition to the functional nodes shown, the accident prevention and control strategy system 10 may also include other nodes, and this application does not impose any restrictions on this.

[0068] The application scenarios of the embodiments in this application are not limited. The system architecture and business scenarios described in the embodiments of this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided by the embodiments of this application. As those skilled in the art will know, with the evolution of network architecture and the emergence of new business scenarios, the technical solutions provided by the embodiments of this application are also applicable to similar technical problems.

[0069] In practical implementation, Figure 1 All the equipment in the middle can be adopted Figure 2 The shown composition structure, or including Figure 2 The components shown. Figure 2 This is a schematic diagram of the structure of an accident prevention strategy device 20 provided in an embodiment of this application. The accident prevention strategy device 20 can be a computing device 101 or a chip or system-on-a-chip within the computing device 101. Alternatively, the accident prevention strategy device 20 can be a data acquisition device 102 or a chip or system-on-a-chip within the data acquisition device 102. Figure 2 As shown, the accident prevention and control strategy device 20 may include a processor 201 and a communication line 202.

[0070] Furthermore, the accident prevention and control strategy device 20 may also include a communication interface 203 and a memory 204. The processor 201, the memory 204, and the communication interface 203 can be connected via a communication line 202.

[0071] The processor 201 can be a central processing unit (CPU), a general-purpose processor, a network processor (NP), a digital signal processor (DSP), a microprocessor, a microcontroller, a programmable logic device (PLD), or any combination thereof. The processor 201 can also be other devices with processing capabilities, such as circuits, devices, or software modules, without limitation.

[0072] Communication line 202 is used to transmit information between the various components included in the accident prevention and control strategy device 20.

[0073] Communication interface 203 is used to communicate with other devices or other communication networks. These other communication networks can be Ethernet, radio access network (RAN), wireless local area networks (WLAN), etc. Communication interface 203 can be a module, circuit, communication interface, or any device capable of enabling communication.

[0074] Memory 204 is used to store instructions. These instructions can be computer programs.

[0075] The memory 204 can be a read-only memory (ROM) or other type of static storage device that can store static information and / or instructions; it can also be a random access memory (RAM) or other type of dynamic storage device that can store information and / or instructions; it can also be an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, etc., without limitation.

[0076] It should be noted that the memory 204 can exist independently of the processor 201 or can be integrated with the processor 201. The memory 204 can be used to store instructions, program code, or some data, etc. The memory 204 can be located inside or outside the accident prevention strategy device 20, without limitation. The processor 201 is used to execute the instructions stored in the memory 204 to implement the accident prevention strategy method provided in the following embodiments of this application.

[0077] In one example, processor 201 may include one or more CPUs, such as CPU0 and CPU1 (not shown in the figure).

[0078] As an optional implementation, the accident prevention strategy device 20 includes multiple processors.

[0079] As an optional implementation, the accident prevention strategy device 20 also includes output devices and input devices. For example, input devices are devices such as keyboards, mice, microphones, or joysticks, and output devices are devices such as displays and speakers.

[0080] It should be noted that the accident prevention and control strategy device 20 can be a desktop computer, laptop computer, network server, mobile phone, tablet computer, wireless terminal, embedded device, chip system, or other device. Figure 2 Equipment with a similar structure. Furthermore... Figure 2 The composition shown does not constitute a basis for this. Figure 1 as well as Figure 2 The limitations of each device in the process, except Figure 2 In addition to the components shown, Figure 1 as well as Figure 2 The various devices may include more or fewer components than illustrated, or combine certain components, or have different component arrangements.

[0081] In this embodiment of the application, the chip system may be composed of chips or may include chips and other discrete devices.

[0082] Furthermore, the actions, terms, etc., involved in the various embodiments of this application can be referenced interchangeably without limitation. The message names or parameter names in the messages exchanged between the various devices in the embodiments of this application are merely examples, and other names may be used in specific implementations without limitation.

[0083] The accident prevention strategy and method provided in the embodiments of this application are described below with reference to the accompanying drawings. The actions, terminology, etc., involved in the various embodiments of this application can be referred to mutually without limitation. The message names or parameter names in the messages exchanged between various devices in the embodiments of this application are merely examples; other names may be used in specific implementations without limitation. The actions involved in the various embodiments of this application are merely examples; other names may be used in specific implementations, such as replacing "included in" with "carried on" or "carried in," etc.

[0084] To address the problems existing in the prior art, this application proposes an accident prevention strategy method that can improve the accuracy of LNG storage tank accident early warning, thereby improving the safety of LNG storage tank operation and reducing the occurrence of potential LNG storage tank accidents. Figure 3 As shown, the method includes:

[0085] S301. The computing device arbitrarily combines multiple risk factors that trigger liquefied natural gas storage tank accidents to obtain at least one set of risk factors.

[0086] Optionally, taking multiple risk factors including N risk factors as an example, the implementation process of S301 above can be as follows: The computing device treats each of the N risk factors as a risk factor set, resulting in N risk factor sets with a quantity of 1. The computing device then arbitrarily combines any two risk factors from the N risk factors to obtain... A set of N risk factors, each with two elements. The computing device arbitrarily combines any three risk factors from these N risk factors to obtain... A set of risk factors with 3 elements, ..., and so on, the computing device takes N risk factors as a single risk factor set, and obtains a risk factor set with N elements.

[0087] In this implementation, the aforementioned at least one set of risk factors includes: a set of N risk factors, each with a value of 1. A set of risk factors with 2 elements, ..., and a set of risk factors with N elements.

[0088] For example, risk factors may include at least one of the following: equipment aging, improper operation, or environmental factors. The above is merely an exemplary description of risk factors, and the risk factors described in the embodiments of this application may also include other factors, such as natural disasters, which are not limited in this application.

[0089] Alternatively, the aforementioned risk factors triggering LNG storage tank accidents can be sent from the data acquisition device to the computing device. The computing device can also directly acquire information about triggering LNG storage tank accidents and analyze the multiple risk factors based on these accidents; this application does not impose any limitations on this.

[0090] S302. The computing device evaluates the association between risk factors in each risk factor set in at least one risk factor set, and obtains the association evaluation parameters for each risk factor set.

[0091] The relevant assessment parameters include at least one of the following: support, confidence, difference, improvement, or leverage ratio.

[0092] Optionally, the association between risk factors in each of the above risk factor sets can represent the probability or confidence level of the occurrence of another risk factor when one risk factor occurs.

[0093] In some possible implementations, the support corresponding to the set of risk factors satisfies the following formula 1:

[0094]

[0095] Where S(X→Y) represents the support of risk factor X triggering risk factor Y in the risk set, P(X∩Y) represents the probability of LNG storage tank accidents being triggered by both risk factor X and risk factor Y, count(X∩Y) represents the number of LNG storage tank accidents being triggered by both risk factor X and risk factor Y, and N represents the number of LNG storage tank accidents obtained by the computing device.

[0096] The confidence level corresponding to the set of risk factors satisfies the following formula 2:

[0097]

[0098] Where C(X→Y) represents the confidence level that the occurrence of risk factor X triggers the occurrence of risk factor Y, P(Y|X) represents the probability that risk factor Y will occur given that risk factor X has occurred, and count(X) represents the number of LNG storage tank accidents triggered by risk factor X.

[0099] The degree of difference corresponding to the set of risk factors satisfies the following formula 3:

[0100]

[0101] Where I(X→Y) represents the degree of difference between the occurrence of risk factor X and the occurrence of risk factor Y, S(Y) represents the support for the occurrence of risk factor Y, and max[C(X→Y), S(Y)] represents the larger value between C(X→Y) and S(Y).

[0102] The lift corresponding to the set of risk factors satisfies the following formula 4:

[0103]

[0104] Here, Lift(X→Y) represents the degree to which the occurrence of risk factor X triggers the occurrence of risk factor Y.

[0105] The leverage ratio corresponding to the set of risk factors satisfies the following formula 5:

[0106] Leverage(X→Y)=P(X∩Y)-P(X)×P(Y) Formula 5

[0107] Where Leverage(X→Y) represents the leverage ratio at which the occurrence of risk factor X triggers the occurrence of risk factor Y, P(X) represents the probability that risk factor X triggers an LNG storage tank accident, and P(Y) represents the probability that the occurrence of risk factor Y triggers an LNG storage tank accident. Leverage(X→Y) is used to measure the difference between the probability of an LNG storage tank accident being triggered by both risk factors X and Y simultaneously and the expected probability of such an accident.

[0108] For example, the accidents occurring in an LNG storage tank obtained by the computing device include accident 1, accident 2, and accident 3. The risk factors that trigger accident 1 include risk factor 1 and risk factor 2. The risk factors that trigger accident 2 include risk factor 2, risk factor 3, and risk factor 4. The risk factors that trigger accident 3 include risk factor 1 and risk factor 4. For example, if accident factor X is accident factor 1 and accident factor Y is accident factor 2, then the LNG storage tank accident triggered by accident X includes accident 1 and accident 3. The LNG storage tank accident triggered by accident Y includes accident 1 and accident 2. The LNG storage tank accident triggered by both accident X and accident Y includes accident 1.

[0109] In addition, optionally, the names of support, confidence, difference, elevation and leverage ratio recorded in the embodiments of this application may be other names. For example, difference may also be called difference in interest in ideas. This application does not limit this.

[0110] S303. The computing device determines the probability of the occurrence of associations between key risk factors and risk factors based on the association assessment parameters of each risk factor set.

[0111] Optionally, the implementation process of S303 above can be as follows: The computing device compares each of the multiple correlation assessment parameters in each risk factor set with its corresponding threshold to obtain a comparison result for each correlation assessment parameter. Based on the comparison result of each correlation assessment parameter, the computing device filters at least one risk factor set to determine a target risk factor set, wherein the risk factors included in the target risk factor set are target risk factors, and the target risk factors include key risk factors and risk factors that are strongly correlated with the key risk factors.

[0112] The computing device determines the probability of a correlation between key risk factors and target risk factors other than key risk factors based on correlation assessment parameters.

[0113] S304. The computing device determines the accident prevention and control strategy based on the probability of occurrence of key risk factors and the correlation between risk factors.

[0114] For example, taking LNG storage tank equipment aging as a key risk factor, and including environmental factors and improper operation, the implementation process of S304 above is illustrated as follows: The computing device determines that the probability of the risk factor association between environmental factors and LNG storage tank equipment aging is greater than a preset probability threshold, and also determines that the probability of the risk factor association between LNG storage tank equipment aging and improper operation is greater than a preset probability threshold. The computing device establishes a regular maintenance and upkeep strategy for the LNG storage tank equipment, and formulates training and supervision strategies for operators and strategies to optimize the operating environment of the LNG storage tank equipment.

[0115] The risk prevention and control strategy method described in this application combines multiple risk factors that trigger LNG storage tank accidents to obtain multiple risk factor sets, and deeply evaluates the internal correlations between the risk factors in these risk factor sets to obtain correlation assessment parameters for each risk factor set. Then, using the correlation assessment parameters corresponding to each risk factor set, key risk factors and their inter-factor correlation probabilities are accurately identified, and an LNG storage tank accident prevention and control strategy is determined based on the key risk factors and their inter-factor correlation probabilities. The accident prevention and control strategy method provided in this application improves the accuracy of LNG storage tank accident early warning, enhances the safety of LNG storage tank operation, and thus reduces the potential occurrence of LNG storage tank accident risks.

[0116] As described in the aforementioned S303, it is necessary to determine the probability of associations occurring between key risk factors and other risk factors based on the association assessment parameters of each risk factor set. However, determining the probability of associations occurring between key risk factors and other risk factors depends on the risk factor association network, and the construction of the risk factor association network depends on the first risk factor set. Therefore, as... Figure 4 As shown, S303 described in the embodiments of this application can also be implemented through the following steps S401 to S403.

[0117] S401. The computing device determines a first set of risk factors from at least one set of risk factors whose probability of triggering an accident is greater than a first threshold, based on the associated evaluation parameters.

[0118] Optionally, the implementation process of S401 above can be as follows: the computing device filters at least one set of risk factors based on the improved Apriori algorithm, and determines the set of risk factors whose probability of triggering an accident is greater than a first threshold as the first set of risk factors, wherein the first threshold includes a preset threshold set by the computing device for multiple associated evaluation parameters corresponding to a set of risk factors.

[0119] In this implementation, the computing device, based on an improved Apriori algorithm, calculates the lift, leverage, and variance for each risk factor set in at least one risk factor set, and sets preset thresholds for the lift, leverage, and variance. The computing device compares the lift, leverage, and variance for each risk factor set with the corresponding preset thresholds. If the confidence, support, lift, leverage, and variance of a risk factor set are all greater than the corresponding preset thresholds, then that risk factor set is determined as the first risk factor set.

[0120] Alternatively, if the two sets of risk factors have the same lift, the computing device will determine the set of risk factors with the higher leverage as the first set of risk factors.

[0121] In one example, taking at least one risk factor set as including risk factor set 1 and risk factor set 2, and risk factor set 1 including risk factor A and risk factor B, and risk factor set 2 including risk factor C and risk factor D as an example, the process by which the computing device determines the risk factor set with higher leverage as the first risk factor set when the lift corresponding to the two risk factor sets is the same can be as follows: if the lift of risk factor A triggering risk factor B is equal to the lift of risk factor C triggering risk factor D, and the leverage of risk factor A triggering risk factor B is greater than the leverage of risk factor C triggering risk factor D, then the computing device will take risk factor set 1 as the first risk factor set.

[0122] For example, Figure 5 A sample diagram illustrating the process of using the classic Apriori algorithm to select the first set of risk factors is shown. Figure 5 As shown, the computing device scans multiple risk factors that could trigger an LNG storage tank accident and obtains at least one set of risk factors. The computing device calculates the support for each risk factor set within the at least one set of risk factors and determines whether the support for a risk factor set is greater than a support threshold. If the support for a risk factor set is greater than the support threshold, the computing device identifies that risk factor set as a candidate risk factor set. If the support for a risk factor set is less than or equal to the support threshold, the computing device determines that the risk factor set does not meet the conditions to become the first risk factor set and terminates the screening process.

[0123] Furthermore, the computing device calculates the confidence level corresponding to the candidate risk factor set and determines whether the confidence level is greater than a confidence threshold. If the confidence level of the risk factor set is greater than the confidence threshold, the computing device identifies the candidate risk factor set as the first risk factor set. If the confidence level of the risk factor set is less than or equal to the confidence threshold, the computing device determines that the candidate risk factor set does not meet the conditions to become the first risk factor set and ends the screening process. This process is repeated iteratively for each risk factor set until the computing device has completed the screening of at least one risk factor set.

[0124] S402. The computing device constructs a risk factor association network based on the risk factors in the first risk factor set and the association evaluation parameters of the first risk factor set.

[0125] Optionally, the above-mentioned S402 implementation process can be as follows: the computing device uses each risk factor in each first set of risk factors as a node in the risk factor association network, and uses the association relationship of the risk factors in each first set of risk factors as an edge in the risk factor association network to construct the risk factor association network.

[0126] For example, referring to the example described in S401 above, the implementation process of S402 is explained by way of example: When the computing device uses risk factor set 1 as the first risk factor set, the computing device uses risk factor A as node 1 of the risk factor association network and risk factor B as node 2 of the risk factor association network. The computing device forms a directed connection from node 1 to node 2 and uses this directed connection as an edge of the risk factor association network.

[0127] S403. The computing device determines the probability of key risk factors and the associations between risk factors by analyzing the risk factor association network.

[0128] Optionally, the aforementioned computing device can determine the realization process of key risk factors by analyzing the risk factor association network as follows: In the risk factor association network, different risk factors may be directly or indirectly connected, that is, different risk factors have direct or indirect relationships. The computing device uses graph theory and complex network analysis methods to analyze the topology of the risk factor association network, identify the risk factors occupying the core position of the risk factor association network, and determine these risk factors as key risk factors.

[0129] Optionally, the computing device constructs an adjacency matrix corresponding to the risk factor association network based on the risk factor association network. The definition of the adjacency matrix corresponding to the risk factor association network satisfies the following formula:

[0130] Equation 6. The adjacency matrix corresponding to the risk factor association network satisfies the following formula 7.

[0131]

[0132] Where i∈n, j∈n, n is the number of risk factors included in the first risk factor set, n is a positive integer and n is greater than or equal to 1, a ij Let be the elements in the adjacency matrix A, where all elements on the diagonal of adjacency matrix A are 0.

[0133] As described above regarding S401, the computing device determines a first set of risk factors from at least one set of risk factors, based on correlation assessment parameters, whose probability of triggering an accident is greater than a first threshold. Since each set of risk factors has multiple corresponding correlation assessment parameters, the computing device determines the first set of risk factors based on these multiple correlation assessment parameters and the preset thresholds corresponding to them. Therefore, as... Figure 6 As shown, S401 described in the embodiments of this application can also be implemented through the following step S501.

[0134] S501. The computing device determines the set of risk factors in at least one risk factor set that has a support greater than a second threshold, and / or a confidence level greater than a third threshold, and / or a difference greater than a fourth threshold, and / or an elevation greater than or equal to 1, and / or a leverage ratio greater than 0 as the first risk factor set.

[0135] Understandably, in combination Figure 5 The description of the classic Apriori algorithm shown illustrates that the computing device not only filters at least one risk factor set based on the support and confidence of each risk factor set, but also filters at least one risk factor set based on the difference, lift, and leverage ratio. This effectively reduces the number of invalid first risk factor sets generated by the classic Apriori algorithm, thereby improving the accuracy of the LNG storage tank accident prevention strategy formulated by the computing device based on the risk factor association network constructed by the first risk set.

[0136] In addition, the computing device may optionally set a second threshold, a third threshold, and a fourth threshold based on specific needs. This application does not limit the specific values ​​corresponding to the second threshold, the third threshold, and the fourth threshold.

[0137] As described above regarding S403, the computing device identifies key risk factors by analyzing the risk factor association network. In other words, the computing device determines key risk factors based on the importance of each risk factor in the risk factor association network. Therefore, if... Figure 7 As shown, the determination of key risk factors by the computing device in S403 of the embodiments of this application can also be achieved through the following steps S601 to S603.

[0138] S601, The computing device calculates the node degree value, clustering coefficient, and betweenness number of each risk factor in the risk factor association network.

[0139] Optionally, the nodal degree values ​​of the above risk factors satisfy the following formula 8.

[0140]

[0141] Where ki represents the node degree value of risk factor i in the risk factor association network. This represents the in-degree value of risk factor i in the risk factor association network. This represents the out-degree value of risk factor i in the risk factor association network. The in-degree value of a risk factor represents the number of edges pointing to that risk factor in its association network, while the out-degree value of a risk factor represents the number of edges pointed to by that risk factor in its association network.

[0142] The clustering coefficients of the above risk factors satisfy the following formula 9.

[0143]

[0144] Among them, c i E represents the clustering coefficient of risk factor i in the risk factor association network. i k represents the number of edges connected to risk factor i in the risk factor association network. i (k i -1) represents the maximum number of edges that can exist between risk node i and its adjacent risk nodes in the risk factor association network.

[0145] The betweenness coefficients of the above risk factors satisfy the following formula 10.

[0146]

[0147] Among them, B i n represents the betweenness number of risk factor i in the risk factor association network. ij n represents the number of edges included in the risk factor association network. ij (i) represents the number of edges passing through risk factor i in the risk factor association network.

[0148] S602. The computing device performs a weighted summation of the node degree value, clustering coefficient, and betweenness number of each risk factor to obtain the importance of each risk factor.

[0149] As one possible implementation, the above-mentioned S602 implementation process can be as follows: The computing device uses node degree value, clustering coefficient, and betweenness number as three evaluation indicators for risk factors. Based on the number of risk factors included in the risk factor association network and the three evaluation indicators, the computing device constructs an original data matrix and standardizes the elements included in the original data matrix. The computing device calculates the proportion of the node degree value of each risk factor to the sum of the node degree values ​​of all risk factors, the proportion of the clustering coefficient of each risk factor to the sum of the clustering coefficients of all risk factors, and the proportion of the betweenness number of each risk factor to the sum of the betweenness numbers of all risk factors.

[0150] The computing device determines the information entropy values ​​corresponding to the node degree, clustering coefficient, and betweenness for each risk factor based on the weights of their respective node degree values, clustering coefficients, and betweenness values. It then determines the weights of these weights for each risk factor. Finally, the computing device performs a weighted sum of these weights to determine the importance of each risk factor.

[0151] Optionally, the above computing device constructs the original data matrix as shown in Formula 11.

[0152] X = (x ij ) n×m Formula 11

[0153] Where X represents the original data matrix, 1≤i≤n, 1≤j≤m, x ij Let n represent the original data of the j-th evaluation indicator of the i-th risk factor, n represent the number of risk factors included in the risk factor association network, and m represent the number of evaluation indicators.

[0154] Optionally, the above-mentioned computing device can perform standardization processing on the elements included in the original data matrix using the following formula 12.

[0155]

[0156] Among them, y ij Represents the standardized x ij .

[0157] Optionally, the calculation of the proportion of the node degree value of each risk factor to the sum of the node degree values ​​of all risk factors, the proportion of the clustering coefficient of each risk factor to the sum of the clustering coefficients of all risk factors, and the proportion of the betweenness of each risk factor to the sum of the betweennesses of all risk factors can all be achieved by the following formula 13.

[0158]

[0159] Where, p ij This represents the proportion of the i-th risk factor under the j-th evaluation indicator.

[0160] Optionally, the process by which the above-mentioned computing device determines the information entropy value corresponding to the node degree value, the information entropy value corresponding to the clustering coefficient, and the information entropy value corresponding to the proportion of the betweenness of each risk factor based on the weight of the node degree value, the weight of the clustering coefficient, and the weight of the betweenness of each risk factor can be implemented by the following formula 14.

[0161]

[0162] Among them, e j Let y represent the information entropy of the j-th evaluation indicator. ij When the value is 0, its information entropy is 0.

[0163] Optionally, the process of calculating the weight of the node degree value, the weight of the clustering coefficient, and the weight of the betweenness of each risk factor using the above-mentioned computing device can be implemented by the following formula 15.

[0164]

[0165] Among them, w j This represents the weight of the j-th evaluation index.

[0166] S603, The computing device identifies risk factors with an importance greater than the fifth threshold as critical risk factors.

[0167] Optionally, the process of setting the fifth threshold by the computing device can be as follows: the computing device sorts the risk factors included in the risk factor association network based on the importance of each risk factor, obtaining an importance ranking table. The higher the importance value of a risk factor in the ranking table, the higher its position in the ranking table. If the computing device identifies a risk factor in the ranking table whose importance is significantly greater than the importance of the risk factors ranked after it, then the computing device determines that importance value as the fifth threshold. The above is merely an exemplary description of the computing device setting the fifth threshold; the computing device can also set the fifth threshold according to specific needs, and this application does not impose any limitations on this.

[0168] As described above regarding S403, the computing device determines the probability of associations occurring between risk factors by analyzing the risk factor association network. In other words, the computing device determines the probability of associations occurring between risk factors based on the weights of the edges between each pair of risk factors in the risk factor association network. Therefore, as... Figure 8 As shown, in S403 of the embodiments of this application, the probability of the association between risk factors being determined by the computing device can be achieved through the following steps S701 to S702.

[0169] S701, The computing device determines the shortest length of each path in the risk factor association network based on the lift between every two risk factors in the risk factor association network.

[0170] Optionally, the implementation process of S701 above can be as follows: The computing device assigns weights to the edges connected by each edge in the risk factor association network based on the lift degree between the two risk factors connected by each edge, thus obtaining the weight of each edge in the risk factor association network. The computing device determines the length of each edge based on its weight. The computing device identifies all edges between each pair of risk factors as transmission paths between them, thus obtaining multiple transmission paths between each pair of risk factors. The computing device determines the length of each transmission path based on the length of the edges included in each of these multiple transmission paths. The computing device compares the lengths of the multiple transmission paths and determines the shortest transmission path between each pair of risk factors.

[0171] As one possible implementation, the aforementioned computing device can input the weights of each edge in the risk factor association network into MATLAB software to obtain the length of each edge.

[0172] Understandably, computing devices determine the probability of associations between risk factors based on the shortest path length between each pair of risk factors in the risk factor association network. They can quantitatively analyze the degree of influence between each pair of risk factors based on path length, and thus determine the risk propagation speed between them. When computing devices formulate corresponding accident prevention strategies for LNG storage tanks, they can develop corresponding prevention strategies for risk factors with shorter path lengths to key risk factors, further improving the accuracy of the accident prevention strategies formulated by the computing devices.

[0173] S702. The computing device performs an average calculation on the shortest length of each path to obtain the average shortest length of the risk factor association network.

[0174] Alternatively, the above-mentioned S802 implementation process can be implemented by the following formula 16.

[0175]

[0176] Where L represents the average shortest length in the risk factor association network, and d ij represents the shortest path length between risk factor i and risk factor j in the risk factor association network, and n represents the number of risk factors in the risk factor association network; n is a positive integer and n is greater than or equal to 1.

[0177] Alternatively, the computing device may determine the maximum value among the shortest lengths of each path as the diameter of the risk factor association network, so as to quantify the risk transmission speed of the risk factor association network by means of the diameter of the risk factor association network.

[0178] As one possible implementation, the implementation process of S801 described above satisfies the following formula 17.

[0179] D = max 1≤i≤j≤n d ij Formula 17

[0180] Where D represents the diameter of the risk factor association network, which is used to measure the degree of influence between risk factors in the network.

[0181] It is understood that the above-mentioned accident prevention and control strategy method can be implemented by an accident prevention and control strategy device. To achieve the above functions, the accident prevention and control strategy device includes hardware structures and / or software modules corresponding to the execution of each function. Those skilled in the art should readily recognize that, in conjunction with the modules and algorithm steps of the various examples described in the embodiments disclosed herein, the embodiments disclosed in this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the embodiments disclosed in this application.

[0182] The embodiments disclosed in this application can divide the accident prevention strategy device generated by the above method examples into functional modules. For example, each function can be divided into its own functional module, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware or as a software functional module. It should be noted that the module division in the embodiments disclosed in this application is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods.

[0183] Figure 9 This is a schematic diagram of another accident prevention strategy device provided in an embodiment of this application. Figure 9 As shown, the accident prevention and control strategy device 90 can be used to execute... Figures 3-4 ,as well as Figures 6-8 The accident prevention and control strategy method is shown. The accident prevention and control strategy device 90 includes a processing unit 902. Optionally, the accident prevention and control strategy device 90 may further include a communication unit 901.

[0184] Processing unit 902 is configured to instruct the arbitrary combination of multiple risk factors that trigger an LNG storage tank accident to obtain at least one set of risk factors; processing unit 902 is further configured to instruct the evaluation of the association between risk factors in each risk factor set within the at least one set of risk factors to obtain association evaluation parameters for each risk factor set; the association evaluation parameters include at least one of the following: support, confidence, dissimilarity, lift, or leverage ratio; processing unit 902 is further configured to instruct the determination of the probability of the occurrence of association between key risk factors and risk factors based on the association evaluation parameters of each risk factor set; processing unit 902 is further configured to instruct the determination of accident prevention and control strategies based on the probability of the occurrence of association between key risk factors and risk factors.

[0185] In one possible implementation, the processing unit 902 is further configured to instruct, based on the association evaluation parameters, to determine, from at least one set of risk factors, a first set of risk factors whose probability of triggering an accident is greater than a first threshold; the processing unit 902 is further configured to instruct, based on the risk factors in the first set of risk factors and the association evaluation parameters of the first set of risk factors, to construct a risk factor association network; the processing unit 902 is further configured to instruct, by analyzing the risk factor association network, to determine the probability of the occurrence of associations between key risk factors and risk factors.

[0186] In one possible implementation, the processing unit 902 is further configured to instruct the determination of a first risk factor set from at least one risk factor set that has a support greater than a second threshold, and / or a confidence level greater than a third threshold, and / or a difference greater than a fourth threshold, and / or an elevation greater than or equal to 1, and / or a leverage ratio greater than 0.

[0187] In one possible implementation, the degree of difference satisfies the following formula:

[0188]

[0189] Where I(X→Y) represents the degree of difference in the occurrence of risk factor X and risk factor Y, C(X→Y) represents the confidence level in the occurrence of risk factor X and risk factor Y, and S(Y) represents the support level of risk factor Y.

[0190] In one possible implementation, the leverage ratio satisfies the following formula:

[0191] Leverage(X→Y)=P(X∩Y)-P(X)×P(Y)

[0192] Where Leverage(X→Y) represents the leverage ratio at which the occurrence of risk factor X triggers the occurrence of risk factor Y, P(X) represents the probability that risk factor X triggers an LNG storage tank accident, and P(Y) represents the probability that the occurrence of risk factor Y triggers an LNG storage tank accident.

[0193] In one possible implementation, the processing unit 902 is further configured to instruct the calculation of the node degree value, clustering coefficient, and betweenness number of each risk factor in the risk factor association network; the processing unit 902 is further configured to instruct the weighted summation of the node degree value, clustering coefficient, and betweenness number of each risk factor to obtain the importance corresponding to each risk factor; the processing unit 902 is further configured to instruct the identification of risk factors with an importance greater than a fifth threshold as key risk factors.

[0194] In one possible implementation, the processing unit 902 is further configured to instruct the determination of the shortest length of each path in the risk factor association network based on the lift between every two risk factors in the risk factor association network; the processing unit 902 is further configured to instruct the mean operation of the shortest length of each path to obtain the average shortest length of the risk factor association network.

[0195] In one possible implementation, the length of the average shortest path in the risk factor association network satisfies the following formula:

[0196]

[0197] Where L represents the average shortest length of the risk factor association network, and d ij Let represent the shortest path length between risk factor i and risk factor j in the risk factor association network, and n represent the number of risk factors in the risk factor association network; n is a positive integer and n is greater than or equal to 1.

[0198] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. An accident prevention and control strategy method, characterized in that, include: By arbitrarily combining multiple risk factors that trigger liquefied natural gas storage tank accidents, at least one set of risk factors can be obtained; The association between risk factors in each risk factor set within the at least one risk factor set is evaluated to obtain association evaluation parameters for each risk factor set; the association evaluation parameters include at least one of the following: support, confidence, dissimilarity, lift, or leverage. Based on the correlation assessment parameters of each set of risk factors, determine the probability of the occurrence of the correlation between the key risk factors and the risk factors. Accident prevention and control strategies are determined based on the probability of occurrence of the key risk factors and the correlation between them.

2. The method according to claim 1, characterized in that, The determination of the probability of a correlation between a key risk factor and the risk factor based on the correlation assessment parameters of each risk factor set includes: Based on the correlation assessment parameters, a first set of risk factors with a probability of triggering an accident greater than a first threshold is determined from the at least one set of risk factors. A risk factor association network is constructed based on the risk factors in the first risk factor set and the association evaluation parameters of the first risk factor set; By analyzing the risk factor association network, the probability of the occurrence of the association between the key risk factors and the risk factors is determined.

3. The method according to claim 2, characterized in that, The step of determining a first set of risk factors with a probability of triggering an accident greater than a first threshold from the at least one set of risk factors based on the correlation assessment parameters includes: The set of risk factors in the at least one risk factor set that has the following characteristics: the support is greater than a second threshold, and / or the confidence is greater than a third threshold, and / or the difference is greater than a fourth threshold, and / or the lift is greater than or equal to 1, and / or the leverage is greater than 0, is determined as the first risk factor set.

4. The method according to claim 3, characterized in that, The degree of difference satisfies the following formula: Wherein, I(X→Y) represents the degree of difference in the occurrence of risk factor X in relation to risk factor Y, C(X→Y) represents the confidence level of the occurrence of risk factor X in relation to risk factor Y, and S(Y) represents the support level of risk factor Y.

5. The method according to claim 3, characterized in that, The leverage ratio satisfies the following formula: Leverage(X→Y)=P(X∩Y)-P(X)×P(Y) Wherein, Leverage(X→Y) represents the leverage ratio at which the occurrence of risk factor X triggers the occurrence of risk factor Y, P(X) represents the probability that risk factor X triggers the liquefied natural gas storage tank accident, and P(Y) represents the probability that the occurrence of risk factor Y triggers the liquefied natural gas storage tank accident.

6. The method according to claim 2, characterized in that, The process of identifying the key risk factors by analyzing the risk factor association network includes: Calculate the node degree, clustering coefficient, and betweenness number for each risk factor in the risk factor association network; The node degree value, clustering coefficient, and betweenness number of each risk factor are weighted and summed to obtain the importance of each risk factor. Risk factors with an importance greater than the fifth threshold are identified as key risk factors.

7. The method according to claim 2, characterized in that, The step of determining the probability of associations between risk factors by analyzing the risk factor association network includes: The shortest length of each path in the risk factor association network is determined based on the lift between every two risk factors in the risk factor association network. The average shortest length of the risk factor association network is obtained by averaging the shortest length of each path.

8. The method according to claim 7, characterized in that, The length of the average shortest path in the risk factor association network satisfies the following formula: Where L represents the average shortest length of the risk factor association network, and d ij The path length between risk factor i and risk factor j in the risk factor association network is represented by n, where n represents the number of risk factors in the risk factor association network; n is a positive integer and is greater than or equal to 1.

9. An accident prevention and control strategy device, characterized in that, include: A processor and a communication interface; the communication interface is coupled to the processor, the processor being used to run computer programs or instructions to implement the accident prevention and control strategy method as described in any one of claims 1-8.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed on a computer, cause the computer to perform the incident prevention strategy method as described in any one of claims 1-8.

Images