Risk assessment method and system for disassembly and assembly practical training task of ship complex power equipment

Abstract

The invention relates to a risk assessment method and system for a ship complex power equipment disassembly and assembly practical training task, and the method comprises the steps: decomposing basic operation links of a ship complex power equipment disassembly and assembly practical training scene through employing a hierarchical task analysis method; identifying risk factors of different operation links by using a work decomposition structure-risk decomposition structure method, and constructing a basic operation incidence matrix and a risk factor coupling matrix; establishing a double-layer complex network model by taking the basic operations and the risk factors as double-layer network nodes, and identifying key basic operations and important risk factors in the disassembly and assembly practical training process of the ship complex power equipment; and mapping the double-layer complex network to form a dynamic Bayesian network model, and evaluating and predicting risk levels and change trends of different task links for dismounting and mounting the ship complex power equipment. Scientific basis and technical support can be provided for practical training teaching of disassembly and assembly of complex power equipment of the ship, and the safety of the practical training teaching process of the ship can be guaranteed.

Description

Technical Field

[0001] This invention relates to the field of shipbuilding and marine engineering technology, and more specifically, to a risk assessment method and system for training tasks involving the disassembly and assembly of complex ship propulsion equipment. This method is particularly suitable for dynamic safety management of multiple tasks and risks coupled in training scenarios involving the disassembly and assembly of complex ship propulsion equipment. Background Technology

[0002] Marine power equipment disassembly and assembly training is a core practical course for students majoring in navigation. Through disassembly and assembly training, students can become familiar with the structure and working principle of marine power equipment, master fault diagnosis and troubleshooting methods, and lay a solid foundation for actual ship operations.

[0003] However, the disassembly and assembly of complex power equipment such as large marine diesel engines involves multi-task, multi-step collaborative operations. For undergraduate students majoring in navigation who lack practical experience, the large number of participants and improper operation can easily lead to electrical shocks, mechanical damage, personal injuries, or even safety accidents. Currently, relying on on-site observation by instructors presents the following problems: first, it is difficult to comprehensively cover all operational steps, easily overlooking hidden risks; second, it is impossible to quantify the coupling relationships between risks, allowing only qualitative judgments; and third, it lacks dynamic assessment capabilities, making it impossible to predict risk changes based on operational progress, resulting in delayed early warnings.

[0004] Therefore, there is an urgent need to invent a risk assessment method and system for the disassembly and assembly training process of complex ship propulsion equipment to ensure the safety of ship training. Summary of the Invention

[0005] To address the aforementioned technical problems, this paper provides a risk assessment method and system for training tasks involving the disassembly and assembly of complex marine power equipment. It resolves the issues of incomplete coverage, difficulty in quantifying coupling, and lack of dynamic assessment in existing risk management systems for marine power equipment disassembly and assembly training. The system offers a risk assessment scheme that allows for layered disassembly operations, systematic risk identification, construction of a coupling network, and dynamic early warning. This effectively assesses and predicts the risk levels at different stages of the training process for disassembling and assembling complex marine power equipment, providing safety assurance for marine training.

[0006] The technical means employed in this invention are as follows: A risk assessment method for training tasks involving the disassembly and assembly of complex marine power equipment includes the following steps: S1. Based on hierarchical task analysis, the training scenario of disassembling and assembling complex ship power equipment is decomposed into layers to obtain the basic operational steps that can be executed. S2. Combining the work breakdown structure and risk breakdown structure, identify the risk factors of each basic operation link, and construct a basic operation correlation matrix that characterizes the correlation between operation links and a risk factor coupling matrix that characterizes the coupling between risk and operation. S3. Construct a two-layer coupling network of basic operation and risk factor, with basic operation correlation matrix as the upper-level node and risk factor coupling matrix as the lower-level node; S4. Based on the topological characteristics of the two-layer coupled network, key basic operation links and important risk factors are identified by quantifying the connection strength, influence range and association depth of nodes. S5. The constructed two-layer coupled network is transformed into a dynamic probabilistic network model that includes the time dimension. The risk level and trend of each task stage are calculated and predicted by combining real-time training data, and a graded early warning is achieved based on the preset risk threshold.

[0007] Furthermore, the layered decomposition in S1 includes: S11. Based on the experimental teaching curriculum, select specific ship disassembly and assembly training scenarios. Based on the ship training curriculum, select specific ship complex power equipment disassembly and assembly training scenarios; S12. For specific scenarios, based on the disassembly and assembly guidelines for ship power equipment, equipment manuals and operating procedures, the training tasks are broken down into the target layer, task layer and operation layer, and each layer contains verifiable operating standards.

[0008] Furthermore, the construction of the basic operation correlation matrix in S2 specifically involves: using the basic operation steps as the rows / columns of the matrix, and by analyzing the sequential dependency relationship of the operation process or combining the expert consensus method, quantifying and assigning values ​​to the correlation strength of any two operation steps to form the basic operation correlation matrix.

[0009] Furthermore, the construction of the risk factor coupling matrix in S2 specifically involves: identifying risk factors from at least five dimensions, including human error, mechanical failure, electrical hazards, environmental interference, and management deficiencies; using basic operational steps as matrix rows and risk factors as matrix columns; and quantifying the degree of coupling between risk factors and operational steps using a Likert scale to form the risk factor coupling matrix.

[0010] Furthermore, step S3 specifically includes the following steps: S31. Using the basic operation links of the decomposition as upper-level network nodes, and the obtained basic operation association matrix as the adjacency matrix of the upper-level network nodes, construct a complex network of basic operation links. S32. Using the identified risk factors as lower-level network nodes, and the obtained risk factor coupling matrix as the adjacency matrix of the upper and lower-level network nodes, a cross-layer connection of the network is established to form a two-layer coupled network of basic operation and risk factors. In the upper-layer network, any two basic operation nodes establish a connection through the assignment in the basic operation association matrix, and there is no connection when the assignment is 0; in the lower-layer network, each risk factor node establishes a cross-layer connection with the corresponding basic operation node through the assignment in the risk factor coupling matrix, and there is no connection when the assignment is 0.

[0011] Furthermore, the identification of key basic operation links in S4 specifically includes: calculating the number of connections of each basic operation node, the frequency of being a necessary path for other nodes, and the association strength with high-importance nodes; obtaining the node importance through weighted summation; and after ranking the importance, selecting the nodes with the highest preset importance index as key basic operation links.

[0012] Furthermore, the identification of important risk factors in S4 specifically includes: calculating the number of connections for each risk factor node, the severity level of the possible consequences, and the frequency with which students encounter the risk during practical training; obtaining the node hazard degree through product normalization; and after ranking the hazard degrees, selecting the nodes with the highest preset hazard degree as important risk factors.

[0013] Furthermore, the dynamic probabilistic network model in S5 specifically includes: taking key basic operation links as parent nodes, important risk factors as root nodes, task layers as intermediate dynamic nodes, and target layers as target nodes, and constructing a dynamic Bayesian network structure based on the hierarchical relationship between nodes; The intermediate dynamic nodes are divided into time slices according to the training progress. The initial probability, conditional probability, and state transition probability across time slices of each node are determined by historical data or expert experience. The risk probability is updated in combination with the real-time observed operation status. When the probability falls into the preset range, the corresponding warning is triggered.

[0014] This invention also discloses a risk assessment system for training tasks involving the disassembly and assembly of complex marine power equipment, comprising: Basic Operation Decomposition Module: This module is used to decompose the training scenario of disassembling and assembling complex ship power equipment into layers using the hierarchical task analysis method, and output the basic operation steps and hierarchical relationships. Risk Matrix Module: Used to identify risk factors in different operational stages of the disassembly and assembly of complex marine power equipment by combining the work breakdown structure-risk decomposition structure method, and outputs a basic operation correlation matrix and a risk factor coupling matrix; Network building module: used to construct a two-layer coupled network of basic operations and risk factors based on the outputs of the basic operation decomposition module and the risk matrix module; Key Operations and Important Risk Factors Identification Module: Based on the output of the network-based module, it calculates the importance and hazard of nodes and outputs the key basic operation steps and important risk factors for the disassembly and assembly of complex ship power equipment; Dynamic assessment and early warning module: It is used to transform the two-layer coupled network into a dynamic probabilistic network model, and outputs risk level and graded early warning signals after inputting real-time training data.

[0015] Compared with the prior art, the present invention has the following advantages: This invention employs the Hierarchical Task Analysis (HTA) method to break down the complex process of disassembling and assembling ship power equipment into multiple basic operational steps, ensuring that each operational step is analyzed in detail.

[0016] This invention combines the Work Breakdown Structure-Risk Breakdown Structure (WBS-RBS) method to comprehensively identify potential risk factors in each operational step, ensuring the comprehensiveness and systematic nature of risk assessment. It solves the problem of incomplete coverage in existing technologies. Compared to risks that may be missed by manual observation, this method can systematically capture risks through operational decomposition and risk matrices.

[0017] This invention, by constructing a basic operational correlation matrix and a risk factor coupling matrix, can assess the risks of the disassembly and assembly training process of complex ship propulsion equipment from multiple dimensions. It considers not only the impact of individual risk factors but also the interactions between them, providing a more comprehensive risk assessment result. By transforming implicit relationships such as operational dependencies and risk linkages into calculable numerical values, it solves the problem of difficulty in quantifying coupling in existing technologies, providing a basis for risk transmission analysis.

[0018] This invention utilizes a node importance algorithm to identify key operations in the disassembly and assembly training of complex ship propulsion equipment; furthermore, by utilizing a node hazard algorithm, this invention can identify important risk factors in different operational stages of the disassembly and assembly training process of complex ship propulsion equipment, providing key directions for risk prevention and control in the disassembly and assembly training process.

[0019] This invention constructs a Dynamic Bayesian Network (DBN) that can update risk probabilities in real time, reflecting dynamic changes during the training process. Compared with manual observation, the Dynamic Bayesian Network can better adapt to complex and ever-changing training environments and promptly identify potential risks.

[0020] This invention defines detailed risk threshold ranges, classifies risk probabilities into different levels, and issues real-time warning signals based on the risk level. Instructors can receive timely warning information and take appropriate intervention measures to effectively reduce the risk of accidents.

[0021] This invention also provides a modular risk assessment system. Through structured steps and intelligent algorithms, the system can automatically assess and provide early warnings of the risk levels at different stages of the training process for disassembling and assembling complex ship propulsion equipment, thereby reducing errors from human intervention and observation.

[0022] The method and system of this invention are applicable to various training scenarios for disassembly and assembly of marine power equipment, and have wide applicability and scalability. They can be adjusted and expanded according to different training needs and types of marine power equipment to ensure that the method and system of this invention always meet the actual application requirements and provide safety assurance for marine training and teaching. Attached Figure Description

[0023] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1 This is a schematic diagram of the risk assessment method for training tasks involving the disassembly and assembly of complex ship power equipment provided by this invention.

[0025] Figure 2 This is a schematic diagram of the module structure of the risk assessment system for training tasks involving the disassembly and assembly of complex ship power equipment provided by this invention. Detailed Implementation

[0026] It should be noted that, unless otherwise specified, the embodiments and features described in the present invention can be combined with each other. The present invention will now be described in detail with reference to the accompanying drawings and embodiments.

[0027] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, 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. The following description of at least one exemplary embodiment is merely illustrative and is in no way intended to limit the present invention or its application or use. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0028] It should be noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the scope of exemplary embodiments according to the invention. As used herein, the singular form is intended to include the plural form as well, unless the context clearly indicates otherwise. Furthermore, it should be understood that when the terms "comprising" and / or "including" are used in this specification, they indicate the presence of features, steps, operations, devices, components, and / or combinations thereof.

[0029] Unless otherwise specifically stated, the relative arrangement, numerical expressions, and values ​​of the components and steps described in these embodiments do not limit the scope of the invention. It should also be understood that, for ease of description, the dimensions of the various parts shown in the drawings are not drawn to actual scale. Techniques, methods, and devices known to those skilled in the art may not be discussed in detail, but where appropriate, such techniques, methods, and devices should be considered part of the specification. In all examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not as limitations. Therefore, other examples of exemplary embodiments may have different values. It should be noted that similar reference numerals and letters in the following figures denote similar items; therefore, once an item is defined in one figure, it need not be further discussed in subsequent figures.

[0030] In the description of this invention, it should be understood that the orientation or positional relationship indicated by directional terms such as "front, back, up, down, left, right", "horizontal, vertical, horizontal" and "top, bottom" is generally based on the orientation or positional relationship shown in the accompanying drawings, and is only for the convenience of describing this invention and simplifying the description. Unless otherwise stated, these directional terms do not indicate or imply that the device or element referred to must have a specific orientation or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation on the scope of protection of this invention. The directional terms "inner" and "outer" refer to the inner and outer contours relative to the outline of each component itself.

[0031] For ease of description, spatial relative terms such as "above," "over," "on the upper surface of," "above," etc., are used herein to describe the spatial positional relationship of a device or feature as shown in the figures to other devices or features. It should be understood that spatial relative terms are intended to encompass different orientations in use or operation besides the orientation of the device as described in the figures. For example, if the device in the figures is inverted, a device described as "above" or "above" other devices or structures would subsequently be positioned as "below" or "under" other devices or structures. Thus, the exemplary term "above" can include both "above" and "below." The device may also be positioned in other different ways (rotated 90 degrees or in other orientations), and the spatial relative descriptions used herein will be interpreted accordingly.

[0032] Furthermore, it should be noted that the use of terms such as "first" and "second" to define components is merely for the purpose of distinguishing the corresponding components. Unless otherwise stated, the above terms have no special meaning and therefore should not be construed as limiting the scope of protection of this invention.

[0033] like Figure 1As shown in the figure, this invention discloses a risk assessment method for training tasks involving the disassembly and assembly of complex ship propulsion equipment, comprising the following steps: S1. Based on hierarchical task analysis (HTA), the training scenario of disassembling and assembling complex ship power equipment is decomposed into layers to obtain the basic operational steps that can be executed. Specifically, the layered decomposition in S1 includes: S11. Based on the experimental teaching curriculum, select specific ship disassembly and assembly training scenarios. Based on the ship training curriculum, select specific ship complex power equipment disassembly and assembly training scenarios; S12. For specific scenarios, based on the disassembly and assembly instructions, equipment manuals and operating procedures of ship power equipment, the training tasks are broken down into the target layer (overall training objective), the task layer (core tasks to achieve the objective), and the operation layer (specific steps to complete the task), and each layer contains verifiable operating standards.

[0034] S2. Combining the Work Breakdown Structure (WBS) and Risk Breakdown Structure (RBS), identify the risk factors of each basic operational step, and construct a basic operational correlation matrix that characterizes the correlation between operational steps and a risk factor coupling matrix that characterizes the coupling between risk and operation. Specifically, the construction of the basic operation correlation matrix in S2 is as follows: taking the basic operation steps as the matrix rows / columns, and by analyzing the sequential dependency relationship of the operation process or combining expert consensus (Delphi method), the correlation strength of any two operation steps is quantified and assigned to form the basic operation correlation matrix.

[0035] Specifically, the construction of the risk factor coupling matrix in S2 involves identifying risk factors from at least five dimensions, including human error, mechanical failure, electrical hazards, environmental interference, and management deficiencies. The basic operational steps are used as the matrix rows, and the risk factors are used as the matrix columns. The degree of coupling between the risk factors and the operational steps is quantified using a Likert scale to form the risk factor coupling matrix.

[0036] S3. Construct a two-layer coupling network of basic operation and risk factor, with basic operation correlation matrix as the upper-level node and risk factor coupling matrix as the lower-level node; Specifically, S3 includes the following steps: S31. Using the basic operation links of the decomposition as upper-level network nodes, and the obtained basic operation association matrix as the adjacency matrix of the upper-level network nodes, construct a complex network of basic operation links. S32. Using the identified risk factors as lower-level network nodes, and the obtained risk factor coupling matrix as the adjacency matrix of the upper and lower-level network nodes, a cross-layer connection of the network is established to form a two-layer coupled network of basic operation and risk factors. In the upper-layer network, any two basic operation nodes establish a connection through the assignment in the basic operation association matrix, and there is no connection when the assignment is 0; in the lower-layer network, each risk factor node establishes a cross-layer connection with the corresponding basic operation node through the assignment in the risk factor coupling matrix, and there is no connection when the assignment is 0.

[0037] S4. Based on the topological characteristics of the two-layer coupled network, key basic operation links and important risk factors are identified by quantifying the connection strength, influence range and association depth of nodes. The identification of key basic operation links in S4 specifically includes: calculating the number of connections (degree centrality), the frequency of being a necessary path for other nodes (betweenness centrality), and the association strength with high-importance nodes (eigenvector centrality) of each basic operation node; obtaining the node importance by weighted summation (weights set based on the training security target); and after ranking the importance, selecting the nodes with the highest preset importance indicators as key basic operation links.

[0038] The identification of important risk factors in S4 specifically includes: calculating the number of connections (degree centrality) of each risk factor node, the severity level of the possible consequences, and the frequency of students' exposure to the risk during training (times / training cycle). The node hazard degree is obtained by product normalization. After ranking the hazard degrees, the nodes with the highest preset indicators are taken as important risk factors.

[0039] More specifically, the following node importance formula is used to identify important basic operational task nodes that are highly correlated with risk factors.

[0040]

[0041] in, For nodes Importance For nodes Degree centrality, For nodes betweenness centrality, For nodes eigenvector centrality.

[0042] in, , and These are the weights of the network topology indicators degree centrality, betweenness centrality, and eigenvector centrality, respectively, satisfying the condition... ; The following node hazard formula is used to identify key risk factors in different basic operational tasks.

[0043]

[0044] In the formula, For nodes The degree of harm, For normalized nodes The degree of harm; For nodes Degree centrality; For nodes The possible risk consequences can be classified into minor, moderate, and severe levels by assigning values. For nodes The corresponding student exposure frequency, measured in times per training cycle, can be obtained through historical data or real-time monitoring.

[0045] S5. The constructed two-layer coupled network is transformed into a dynamic probabilistic network model containing the time dimension. The risk level and changing trend of each task stage are calculated and predicted by combining real-time training data. Based on the preset risk threshold, a graded early warning is realized. Specifically, by mapping it to a dynamic Bayesian network, the risk level of different task stages of disassembling and assembling complex power equipment on ships is evaluated.

[0046] The dynamic probabilistic network model in S5 specifically includes: determining the Bayesian network structure: taking key basic operation links as parent nodes, important risk factors as root nodes, task layers as intermediate dynamic nodes, and target layers as target nodes, and constructing a dynamic Bayesian network structure based on the hierarchical relationship between nodes. In the constructed dynamic Bayesian network, the status of task-type nodes can be divided into "success" and "failure", and the status of risk factor-type nodes can be divided into "occurred" and "not occurred".

[0047] Prior probabilities are determined. For the constructed dynamic Bayesian network, the prior probabilities of risk factor class nodes, which serve as root nodes, need to be determined. In this invention, the prior probabilities can be determined using expert experience or statistical analysis of historical data. Conditional probability calculation. For the constructed dynamic Bayesian network, the conditional probability of the task-class node as the parent node needs to be determined. In this invention, the conditional probability can be determined by expert experience or data-driven methods (maximum likelihood estimation, Bayesian estimation, etc.). Transition probabilities are determined. For the constructed dynamic Bayesian network, intermediate task layer nodes are set as dynamic nodes, and time slices are divided according to the number of intermediate tasks. The state transition probabilities of dynamic nodes are calculated using expert experience or Markov models to complete the construction of the dynamic Bayesian network model. Risk assessment. Based on the constructed dynamic Bayesian network model and combined with real-time observation data as update evidence, the risk probability of different operations during the training process of complex ship propulsion equipment is calculated using the following Bayesian joint probability formula containing time slices.

[0048] in, Let R be the probability that risk factor R occurs during operation T at time t+1. Let T be the Markov transition probability of operation T; Let R be the conditional probability of the risk factor R. Risk Warning. A risk threshold range is defined, and the risk probability output by the Bayesian network model is divided into different risk levels to achieve real-time risk warning during the training process of complex ship propulsion equipment. In this invention, a risk probability of [0, 0.1) indicates low risk, meaning normal operation with no direct safety hazards; a risk probability of [0.1, 0.4) indicates potential risk, requiring attention to operational procedures; a risk probability of [0.4, 0.7) indicates medium risk, with foreseeable danger requiring immediate intervention; a risk probability of [0.7, 0.9) indicates high risk, potentially leading to equipment damage or personnel injury, requiring immediate cessation of training; and a risk probability of [0.9, 1.0] indicates critical risk, potentially leading to serious accidents, requiring immediate emergency evacuation and rescue.

[0049] like Figure 2 As shown, this invention also discloses a risk assessment system for training tasks involving the disassembly and assembly of complex marine power equipment, comprising: Basic Operation Decomposition Module: This module is used to decompose the training scenario of disassembling and assembling complex ship power equipment into layers using the hierarchical task analysis method, and output the basic operation steps and hierarchical relationships. Risk Matrix Module: Used to identify risk factors in different operational stages of the disassembly and assembly of complex marine power equipment by combining the work breakdown structure-risk decomposition structure method, and outputs a basic operation correlation matrix and a risk factor coupling matrix; Network building module: used to construct a two-layer coupled network of basic operations and risk factors based on the outputs of the basic operation decomposition module and the risk matrix module; Key Operations and Important Risk Factors Identification Module: Based on the output of the network-based module, it calculates the importance and hazard of nodes and outputs the key basic operation steps and important risk factors for the disassembly and assembly of complex ship power equipment; Dynamic assessment and early warning module: It is used to transform the two-layer coupled network into a dynamic probabilistic network model, and outputs risk level and graded early warning signals after inputting real-time training data.

[0050] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A risk assessment method for training tasks involving the disassembly and assembly of complex marine power equipment, characterized in that, Includes the following steps: S1. Based on hierarchical task analysis, the training scenario of disassembling and assembling complex ship power equipment is decomposed into layers to obtain the basic operational steps that can be executed. S2. Combining the work breakdown structure and risk breakdown structure, identify the risk factors of each basic operation link, and construct a basic operation correlation matrix that characterizes the correlation between operation links and a risk factor coupling matrix that characterizes the coupling between risk and operation. S3. Construct a two-layer coupling network of basic operation and risk factor, with basic operation correlation matrix as the upper-level node and risk factor coupling matrix as the lower-level node; S4. Based on the topological characteristics of the two-layer coupled network, key basic operation links and important risk factors are identified by quantifying the connection strength, influence range and association depth of nodes. S5. The constructed two-layer coupled network is transformed into a dynamic probabilistic network model that includes the time dimension. The risk level and trend of each task stage are calculated and predicted by combining real-time training data, and a graded early warning is achieved based on the preset risk threshold.

2. The risk assessment method according to claim 1, characterized in that, The layered decomposition in S1 includes: S11. Based on the ship training course, select specific training scenarios for disassembling and assembling complex ship power equipment; S12. For specific scenarios, based on the disassembly and assembly guidelines for ship power equipment, equipment manuals and operating procedures, the training tasks are broken down into the target layer, task layer and operation layer, and each layer contains verifiable operating standards.

3. The risk assessment method according to claim 1, characterized in that, The construction of the basic operation correlation matrix in S2 is specifically as follows: taking the basic operation steps as the matrix rows / columns, and by analyzing the sequential dependency relationship of the operation process or combining the expert consensus method, the correlation strength of any two operation steps is quantified and assigned a value to form the basic operation correlation matrix.

4. The risk assessment method according to claim 1, characterized in that, The construction of the risk factor coupling matrix in S2 specifically involves identifying risk factors from at least five dimensions, including human error, mechanical failure, electrical hazards, environmental interference, and management deficiencies. The basic operational steps are used as the matrix rows, and the risk factors are used as the matrix columns. The degree of coupling between the risk factors and the operational steps is quantified using a Likert scale to form the risk factor coupling matrix.

5. The risk assessment method according to claim 1, characterized in that, S3 specifically includes the following steps: S31. Using the basic operation links of the decomposition as upper-level network nodes, and the obtained basic operation association matrix as the adjacency matrix of the upper-level network nodes, construct a complex network of basic operation links. S32. Using the identified risk factors as lower-level network nodes, and the obtained risk factor coupling matrix as the adjacency matrix of the upper and lower-level network nodes, a cross-layer connection of the network is established to form a two-layer coupled network of basic operation and risk factors. In the upper-layer network, any two basic operation nodes establish a connection through the assignment in the basic operation association matrix, and there is no connection when the assignment is 0; in the lower-layer network, each risk factor node establishes a cross-layer connection with the corresponding basic operation node through the assignment in the risk factor coupling matrix, and there is no connection when the assignment is 0.

6. The risk assessment method according to claim 1, characterized in that, The identification of key basic operation links in S4 specifically includes: calculating the number of connections of each basic operation node, the frequency of being a necessary path for other nodes, and the association strength with high-importance nodes; obtaining the node importance through weighted summation; and after ranking the importance, selecting the nodes with the highest preset importance indicators as key basic operation links.

7. The risk assessment method according to claim 1, characterized in that, The identification of important risk factors in S4 specifically includes: calculating the number of connections for each risk factor node, the severity level of the possible consequences, and the frequency with which students encounter the risk during practical training; obtaining the node hazard degree through product normalization; and after ranking the hazard degrees, selecting the nodes with the highest preset hazard degree as important risk factors.

8. The risk assessment method according to claim 1, characterized in that, The dynamic probabilistic network model in S5 specifically includes: taking key basic operation links as parent nodes, important risk factors as root nodes, task layers as intermediate dynamic nodes, and target layers as target nodes, and constructing a dynamic Bayesian network structure based on the hierarchical relationship between nodes. The intermediate dynamic nodes are divided into time slices according to the training progress. The initial probability, conditional probability, and state transition probability across time slices of each node are determined by historical data or expert experience. The risk probability is updated in combination with the real-time observed operation status. When the probability falls into the preset range, the corresponding warning is triggered.

9. A system for a risk assessment method according to any one of claims 1 to 8, characterized in that, include: Basic Operation Decomposition Module: This module is used to decompose the training scenario of disassembling and assembling complex ship power equipment into layers using the hierarchical task analysis method, and output the basic operation steps and hierarchical relationships. Risk Matrix Module: Used to identify risk factors in different operational stages of the disassembly and assembly of complex marine power equipment by combining the work breakdown structure-risk decomposition structure method, and outputs a basic operation correlation matrix and a risk factor coupling matrix; Network building module: used to construct a two-layer coupled network of basic operations and risk factors based on the outputs of the basic operation decomposition module and the risk matrix module; Key Operations and Important Risk Factors Identification Module: Based on the output of the network-based module, it calculates the importance and hazard of nodes and outputs the key basic operation steps and important risk factors for the disassembly and assembly of complex ship power equipment; Dynamic assessment and early warning module: It is used to transform the two-layer coupled network into a dynamic probabilistic network model, and outputs risk level and graded early warning signals after inputting real-time training data.

Images