A ship SOFC system safety analysis method, a computing device and a storage medium

Abstract

This invention discloses a safety analysis method for ship SOFC systems, belonging to the field of risk prevention and control technology. It includes: identifying the causative factors of the ship SOFC system; constructing a failure fault tree and event tree model; constructing a Bow-Tie model based on the failure fault tree and event tree model; quantitatively analyzing potential causative factors to identify key factors affecting the SOFC system; combining the analyzed ship SOFC system accident causation data and collected ship fuel cell standard and specification data to form a data system and construct a ship SOFC system accident risk prevention knowledge graph; and conducting SOFC system safety analysis based on the ship SOFC system accident risk prevention knowledge graph. This invention clarifies the criticality, hierarchical relationship, and action path of each causative factor; constructs the causative factors into a complex accident causation network; and, combining the semantic information of the knowledge graph and the capabilities of complex network analysis, deeply reveals the accident causation propagation mechanism, providing a comprehensive perspective for understanding the occurrence and development of accidents.

Description

Technical Field

[0001] This invention relates to the field of risk control technology, specifically to a method, computing device, and storage medium for analyzing the safety of a ship's SOFC system. Background Technology

[0002] In related technologies, the literature "Research on the Construction of Accident Cause Knowledge Graph Based on Chemical Cases" has found a suitable method for constructing a knowledge graph of chemical accident causes: model layer construction, data layer construction, and model layer improvement. It also specifically studied the implementation methods and possible problems of each step in the process. Then, the knowledge in the knowledge graph was imported into the Neo4j database for storage. Finally, the practicality of the knowledge graph was verified based on knowledge question answering. Subsequently, based on the DEMATEL impact analysis method and the correlation between causal factors, the importance of causal factors in the system was quantitatively calculated. Then, according to the cause classification, the key elements in each category were analyzed and targeted suggestions were made. However, this is only applicable to the chemical industry, and the risk identification initially lacked a targeted method.

[0003] Other related patents only address fault diagnosis of SOFC system components, failing to conduct risk analysis from the perspectives of people, machines, environment, and management. Traditional risk analysis methods (such as Fault Tree Analysis (FTA) and Event Tree Analysis (ETA), while capable of tracing accident logic paths, often focus on qualitative or semi-quantitative analysis, struggling to quantify the complex relationships and combined effects of risk factors. They also lack the ability to effectively integrate multi-source data (accident causative factors, relevant standards and specifications, etc.) and deeply explore potential preventative measures. Therefore, in-depth research on risk identification and accident prevention in marine SOFC systems, and the construction of scientific and systematic risk identification methods and accident prevention systems, are crucial for improving the safety and reliability of marine SOFC systems and promoting the widespread application of fuel cell technology in the marine field. Related technological development is urgently needed. Summary of the Invention

[0004] This invention provides a method, computing device, and storage medium for safety analysis of ship SOFC systems. It addresses the problem in the prior art that it is difficult to quantify the complex influence relationships between risk factors and the intensity of their combined effects, as well as the lack of effective integration of multi-source data.

[0005] To solve the above-mentioned technical problems, the present invention adopts the following technical solution:

[0006] This invention provides a method for safety analysis of a ship's SOFC system, characterized by comprising:

[0007] S1. Determine the causative factors of the ship's SOFC system, construct the failure fault tree and event tree model, and construct the Bow-Tie model based on the failure fault tree and event tree model.

[0008] S2. Quantitatively analyze potential causative factors using the Bow-Tie model to identify key factors affecting the SOFC system;

[0009] S3. Combining the analyzed data on the causes of accidents in ship SOFC systems with the collected data on ship fuel cell standards and specifications, a data system is formed to construct a knowledge graph for the prevention of ship SOFC system accidents.

[0010] S4. Conduct a safety analysis of the SOFC system based on the knowledge graph of accident risk prevention for ship SOFC systems.

[0011] Based on this, the present invention can be further improved as follows:

[0012] In step S2, the method for quantitative analysis of potential causative factors includes:

[0013] S21. Based on the evaluation level table based on expert experience and relationships, construct the direct influence matrix B between elements, B = [β]. ij n×n:

[0014]

[0015] Where, β ij Indicates risk factor α i For α j The degree of direct impact;

[0016] S22. Normalize the original direct influence matrix B to construct a normalized direct influence matrix C, C = [cij]n×n, cij∈[0,1]:

[0017]

[0018] S22. Based on the normalized direct influence matrix C, construct the basic influence matrix D (D = [d]). ij ]n×n):

[0019]

[0020] Where C×C represents the increased indirect impact, that is, the matrix product reflects the transmission relationship of indirect impact between elements, and I is the identity matrix;

[0021] S23. Based on the basic influence matrix D, calculate the influence degree and the degree of being influenced of each element;

[0022] S24. Calculate the centrality and causality of each element based on its influence and affectedness.

[0023] Based on this, the present invention can be further improved as follows:

[0024] In step S23, the methods for calculating the influence and affected degree of each element include:

[0025] Let f be the influence degree of the i-th risk factor αi. i The degree of influence is e i i = 1, 2, ..., n;

[0026] f i The sum of the elements in the i-th row of the comprehensive influence matrix D, i.e.

[0027]

[0028] ei is the sum of the elements in the i-th column of the comprehensive influence matrix D, i.e.

[0029]

[0030] Based on this, the present invention can be further improved as follows:

[0031] In step S24, the methods for calculating the centrality and causality of each element include:

[0032] Let the i-th risk factor be α i The centrality is m i , i==1,2,…,n, that is

[0033] m i =f i +e i ;

[0034] Let the i-th risk factor be α i The degree of cause is n i , i==1,2,…,n, that is

[0035] n i =f i -e i .

[0036] Based on this, the present invention can be further improved as follows:

[0037] In step S3, the specific method for constructing a knowledge graph for accident risk prevention of ship SOFC systems is as follows:

[0038] S31. Perform knowledge extraction to extract topics, causes, and rules from structured, semi-structured, and unstructured data;

[0039] S32. Standardize the collected data, and then establish an entity database and an entity relationship database based on the collected data. The entity database includes topics, primary causes, secondary causes, and standard specifications. The entity relationship database includes the relationship between topics and primary causes, the relationship between primary causes and secondary causes, and the relationship between secondary causes and regulations.

[0040] S33. Perform batch import of data. After importing all node and relationship data into the graph database, the knowledge graph construction is completed.

[0041] Based on this, the present invention can be further improved as follows:

[0042] In step S3, when constructing the knowledge graph for accident risk prevention of the ship SOFC system, Neo4j is selected as the storage platform.

[0043] The present invention also proposes a computer device, including a memory, a processor, and a computer program stored in the memory, characterized in that the processor executes the computer program to implement the steps of the above-described method.

[0044] The present invention also proposes a computer-readable storage medium having a computer program stored thereon, characterized in that the computer program, when executed by a processor, implements the steps of the method described above.

[0045] The beneficial effects provided by this invention are:

[0046] This invention focuses on the risk identification system of ship SOFC systems, comprehensively utilizing various theoretical and technical methods to conduct in-depth research on causal analysis and prevention. Using Bow-tie analysis, it comprehensively identifies potential causal factors from four dimensions: human, machine, environment, and management, systematically identifying various possible causes of accidents. Employing a comprehensive analysis method based on DEMATEL-ISM and complex network models, it clarifies the criticality, hierarchical relationships, and action paths of each causal factor. By constructing a complex accident causal network from the causal factors, and combining knowledge graph semantic information and complex network analysis capabilities, it deeply reveals the accident causal propagation mechanism, clearly presenting the inherent laws of accident occurrence, and providing a comprehensive perspective for understanding the occurrence and development of accidents.

[0047] Advantages of additional aspects of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. Attached Figure Description

[0048] Figure 1 A schematic diagram of the safety analysis method for a ship SOFC system provided in an embodiment of the present invention;

[0049] Figure 2This is a schematic diagram of the knowledge graph data extraction process provided in an embodiment of the present invention; Detailed Implementation

[0050] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the protection scope of the present invention.

[0051] like Figure 1 As shown,

[0052] This invention provides claim 1, which constructs a knowledge graph for preventing leaks and explosions of ship hydrogen fuel cells based on the BT-DEMATEL model and knowledge graph association analysis, according to relevant regulations and documents. By closely linking the causes of accidents with the knowledge graph, it fully explores the prevention strategies within. Utilizing the reasoning and query functions of the knowledge graph, it provides a visualized decision support path for accident prevention, helping decision-makers quickly identify key information and accurately formulate preventive measures for high-risk areas. This greatly enhances the ability to prevent leaks and explosions of ship hydrogen fuel cells, effectively safeguarding the safe operation of hydrogen fuel cell ships. Through comprehensive causal analysis and scientific construction of the prevention knowledge graph, it contributes significant theoretical and practical results to the field of hydrogen fuel cell ship safety, effectively improving the ability to respond to such accidents, specifically including:

[0053] S1. Determine the causative factors of the ship's SOFC system, construct the failure fault tree and event tree model, and construct the Bow-Tie model based on the failure fault tree and event tree model.

[0054] In step S1, referencing a case study of a shipboard SOFC system accident (taking a leak and explosion accident as an example using hydrogen as fuel gas), the causal factors were summarized from four aspects: personnel, management, environment, and equipment. An analytical framework containing 24 core causal factors was constructed through system causal identification. Based on accident causation theory, the causal system was divided into four categories, including 4 personnel factors, 3 environmental factors, 4 management factors, and 13 equipment factors. A Bow-Tie analysis model for the causal factors of a shipboard fuel cell system leak and explosion accident was constructed using the Bow-Tie model, which intuitively presents the logical relationships between the various elements.

[0055] S2. Quantitatively analyze potential causative factors using the Bow-Tie model to identify key factors affecting the SOFC system;

[0056] For example, in step S2, a table of 24 causal factors in the accident is obtained based on the analysis in step S1, as shown in Table 1.

[0057] Table 1.

[0058] Causative factors serial number Causative factors serial number Operational error <![CDATA[α1]]> Compressor malfunction <![CDATA[α 13 ]]> Improper maintenance <![CDATA[α2]]> fuel cell stack failure <![CDATA[α 14 ]]> Insufficient training <![CDATA[α3]]> Sensor failure <![CDATA[α 15 ]]> Weak safety awareness <![CDATA[α4]]> Control system failure <![CDATA[α 16 ]]> Physical environmental hazards <![CDATA[α5]]> Circulatory system failure <![CDATA[α 17 ]]> Chemical environmental hazards <![CDATA[α6]]> Gas supply system failure <![CDATA[α 18 ]]> Natural disasters <![CDATA[α7]]> Humidification system malfunction <![CDATA[α 19 ]]> Welding failure <![CDATA[α8]]> Electrical system failure <![CDATA[α 20 ]]> Pipeline failure <![CDATA[α9]]> Institutional deficiencies <![CDATA[α 21 ]]> Seal failure <![CDATA[α 10 ]]> Ineffective supervision and enforcement <![CDATA[α 22 ]]> Hydrogen storage equipment malfunction <![CDATA[α 11 ]]> Emergency management vulnerabilities <![CDATA[α 23 ]]> Valve malfunction <![CDATA[α 12 ]]> Insufficient communication and record keeping <![CDATA[α 24 ]]> ;

[0059] S3. Combining the analyzed data on the causes of accidents in ship SOFC systems with the collected data on ship fuel cell standards and specifications, a data system is formed to construct a knowledge graph for the prevention of ship SOFC system accidents.

[0060] S4. Conduct a safety analysis of the SOFC system based on the knowledge graph of accident risk prevention for ship SOFC systems.

[0061] The solution provided by this invention has the following effects:

[0062] This invention focuses on the risk identification system of ship SOFC systems, comprehensively utilizing various theoretical and technical methods to conduct in-depth research on causal analysis and prevention. Using Bow-tie analysis, it comprehensively identifies potential causal factors from four dimensions: human, machine, environment, and management, systematically identifying various possible causes of accidents. Employing a comprehensive analysis method based on DEMATEL-ISM and complex network models, it clarifies the criticality, hierarchical relationships, and action paths of each causal factor. By constructing a complex accident causal network from the causal factors, and combining knowledge graph semantic information and complex network analysis capabilities, it deeply reveals the accident causal propagation mechanism, clearly presenting the inherent laws of accident occurrence, and providing a comprehensive perspective for understanding the occurrence and development of accidents.

[0063] Optionally, in some possible implementations, the method for quantitatively analyzing potential causative factors in step S2 includes:

[0064] S21. Based on the evaluation level table based on expert experience and relationships, the influence relationships among the 24 factors are quantified using expert scoring methods, and a direct influence matrix B among the factors is constructed, B = [βij]n×n:

[0065]

[0066] Where, β ij Indicates risk factor α i For α j The degree of direct impact;

[0067] S22. Normalize the original direct influence matrix B to construct a normalized direct influence matrix C, C = [cij]n×n, cij∈[0,1]:

[0068]

[0069] S22. Based on the normalized direct influence matrix C, construct the basic influence matrix D (D = [d]). ij ]n×n):

[0070]

[0071] Where C×C represents the increased indirect impact, that is, the matrix product reflects the transmission relationship of indirect impact between elements, and I is the identity matrix;

[0072] S23. Based on the basic influence matrix D, calculate the influence degree and the degree of being influenced of each element;

[0073] S24. Based on the influence and affectedness of each element, calculate the centrality and causation degree of each element, and finally obtain the causal factor element table as shown in Table 2.

[0074] Table 2

[0075]

[0076] Optionally, in some possible implementations, the method for calculating the influence and affected degree of each element in step S23 includes:

[0077] Let the i-th risk factor be α i The degree of influence is f i The degree of influence is e i i = 1, 2, ..., n;

[0078] f i The sum of the elements in the i-th row of the comprehensive influence matrix D, i.e.

[0079]

[0080] ei is the sum of the elements in the i-th column of the comprehensive influence matrix D, i.e.

[0081]

[0082] Optionally, in some possible implementations, the method for calculating the centrality and causality of each element in step S24 includes:

[0083] Let the i-th risk factor be α i The centrality is m i , i==1,2,…,n, that is

[0084] m i =f i +e i ;

[0085] Where, m i The larger the value, the greater the α value. iThe greater the impact on the system, i.e., α i The higher the importance

[0086] Let the i-th risk factor be α i The degree of cause is n i , i==1,2,…,n, that is

[0087] n i =f i -e i ;

[0088] When the causality ni is positive, it indicates that αi has a significant impact on other risk factors and is defined as a causal risk factor; when ni is negative, it indicates that αi is easily affected by other factors and is classified as an outcome risk factor.

[0089] The centrality is expressed as the sum of the influence degree and the degree of influence of a factor in the system, representing its importance.

[0090] The causal degree is calculated by subtracting the degree of influence from the degree of being influenced, representing the degree of causal logical relationship between the factor and other risk factors in the system.

[0091] Optionally, in some possible implementations, the specific method for constructing the knowledge graph of accident risk prevention for ship SOFC systems in step S3 is as follows:

[0092] S31. Perform knowledge extraction, extracting entities such as topics, causes, and rules from structured, semi-structured, and unstructured data. Knowledge extraction, as a core step in building a knowledge graph, encompasses entity extraction and relation extraction. See the appendix for the specific process. Figure 2 ;

[0093] S32. Standardize the collected data, and then establish an entity database and an entity relationship database based on the collected data. The entity database includes topics (topic number and topic name), primary causes (primary cause number and primary cause name), secondary causes (secondary cause number, secondary cause name, and definition), and standard specifications (clause name, clause type, implementation date, clause number, and clause content). The entity relationship database includes the relationship between topics and primary causes, the relationship between primary causes and secondary causes, and the relationship between secondary causes and regulations. To facilitate data import into Neo4j, Chinese pinyin abbreviations are used to replace attribute names in each table during the specific operation.

[0094] S33. Use the LOAD CSV command to import the data in batches. After importing all node and relationship data into the graph database, the knowledge graph construction is completed.

[0095] Optionally, in some possible implementations, in step S3, when constructing the knowledge graph for the prevention of SOFC system accidents, Neo4j is selected as the storage platform. This invention chooses Neo4j as the storage platform to address the complex relationship modeling requirements of the knowledge graph for the prevention of leaks and explosions in hydrogen fuel cell ships. This database is built based on an attribute graph model, supporting each node and relationship to carry any number of key-value pairs, which highly matches the multi-dimensional attribute data such as equipment parameters and accident characteristics in the field of hydrogen fuel cell ships. Neo4j uses Cypher as its native query language, and its declarative syntax supports concise graph operations. Through basic commands such as CREATE / MATCH / SET, the addition, deletion, modification, and querying of nodes and relationships can be efficiently realized, making it particularly suitable for traversing and analyzing complex graph structures.

[0096] The present invention also proposes a computer device, including a memory, a processor, and a computer program stored in the memory, characterized in that the processor executes the computer program to implement the steps of the above-described method.

[0097] The present invention also proposes a computer-readable storage medium having a computer program stored thereon, characterized in that the computer program, when executed by a processor, implements the steps of the method described above.

[0098] Optionally, some possible implementations may include all or part of the above-described implementations.

[0099] It should be understood that in the description of this specification, references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples" refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of the present invention. In this description, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate different embodiments or examples described in this specification, as well as some features of different embodiments or examples.

[0100] Of course, those skilled in the art can make various corresponding changes and modifications based on the present invention without departing from its spirit and essence, but such changes and modifications should all fall within the protection scope of the claims of the present invention.

Claims

1. A method for safety analysis of a ship's SOFC system, characterized in that, include: S1. Determine the causative factors of the ship's SOFC system, construct the failure fault tree and event tree model, and construct the Bow-Tie model based on the failure fault tree and event tree model. S2. Quantitatively analyze potential causative factors using the Bow-Tie model to identify key factors affecting the SOFC system; S3. Combining the analyzed data on the causes of accidents in ship SOFC systems with the collected data on ship fuel cell standards and specifications, a data system is formed to construct a knowledge graph for the prevention of ship SOFC system accidents. S4. Conduct a safety analysis of the SOFC system based on the knowledge graph of accident risk prevention for ship SOFC systems.

2. The safety analysis method for ship SOFC systems according to claim 1, characterized in that, In step S2, the method for quantitative analysis of potential causative factors includes: S21. Based on the evaluation level table based on expert experience and relationships, construct the direct influence matrix B between elements, B = [β]. ij n×n: Where, β ij Indicates risk factor α i For α j The degree of direct impact; S22. Normalize the original direct influence matrix B to construct a normalized direct influence matrix C, C = [cij]n×n, cij∈[0,1]: S22. Based on the normalized direct influence matrix C, construct the basic influence matrix D (D = [d]). ij ]n×n): Where C×C represents the increased indirect impact, that is, the matrix product reflects the transmission relationship of indirect impact between elements, and I is the identity matrix; S23. Based on the basic influence matrix D, calculate the influence degree and the degree of being influenced of each element; S24. Calculate the centrality and causality of each element based on its influence and the degree to which it is affected.

3. The safety analysis method for ship SOFC systems according to claim 2, characterized in that, In step S23, the methods for calculating the influence and affected degree of each element include: Let f be the influence degree of the i-th risk factor αi. i The degree of influence is e i i = 1, 2, ..., n; f i The sum of the elements in the i-th row of the comprehensive influence matrix D, i.e. ei is the sum of the elements in the i-th column of the comprehensive influence matrix D, i.e.

4. The safety analysis method for ship SOFC systems according to claim 2, characterized in that, In step S24, the methods for calculating the centrality and causality of each element include: Let the i-th risk factor be α i The centrality is m i , i==1,2,…,n, that is m i =f i +e i ; Let the i-th risk factor be α i The degree of cause is n i , i==1,2,…,n, that is n i =f i -e i 。 5. The method for safety analysis of a ship SOFC system according to claim 1, characterized in that, In step S3, the specific method for constructing a knowledge graph for accident risk prevention of ship SOFC systems is as follows: S31. Perform knowledge extraction to extract topics, causes, and rules from structured, semi-structured, and unstructured data; S32. Standardize the collected data, and then establish an entity database and an entity relationship database based on the collected data. The entity database includes topics, primary causes, secondary causes, and standard specifications. The entity relationship database includes the relationship between topics and primary causes, the relationship between primary causes and secondary causes, and the relationship between secondary causes and regulations. S33. Perform batch import of data. After importing all node and relationship data into the graph database, the knowledge graph construction is completed.

6. The method for safety analysis of a ship SOFC system according to claim 1 or 5, characterized in that, In step S3, when constructing the knowledge graph for accident risk prevention of the ship SOFC system, Neo4j is selected as the storage platform.

7. A computer device comprising a memory, a processor, and a computer program stored in the memory, characterized in that, The processor executes the computer program to implement the steps of the method according to any one of claims 1-6.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1-6.

Images