Railway safety risk transmission analysis method, device, equipment and medium

Abstract

The invention relates to the technical field of railway transportation safety, and discloses a railway safety risk transmission analysis method, device and equipment and a medium, and the method comprises the steps: obtaining a railway safety risk set which comprises a plurality of safety risk items; analyzing the railway safety risk set based on the railway historical operation data set to obtain a risk transfer relationship between safety risk items; constructing a railway safety risk transfer network based on the risk transfer relationship among the safety risk items; and carrying out probability analysis on the railway safety risk transmission network to obtain a key safety risk item and a key transmission path in the railway safety risk transmission network. The method solves the problem that existing railway safety risk evaluation lacks a quantitative analysis method.

Description

Technical Field

[0001] The present invention relates to the field of railway transportation safety technology, and in particular to an analysis method, device, equipment and medium for railway safety risk transmission. Background Art

[0002] Risk transfer theory is a research field that has gradually attracted attention in recent years. This concept was first proposed in the financial field. With the deepening of research, risk transfer theory has begun to penetrate into other industries, including power supply, food, offshore energy, and railways. Especially in the railway field, with the rapid development of transportation and the increasing safety needs, it is particularly important to conduct a comprehensive and systematic assessment and management of railway safety risks.

[0003] At present, most railway safety risk assessment work remains at the level of qualitative analysis. Although it can provide some directional guidance, it is obviously insufficient in accuracy and depth. The locally developed semi-quantitative analysis technology has also failed to fully solve the problem of quantitative analysis. Specifically, the existing technology lacks a unified standard for describing safety risks, which makes it difficult to compare and analyze the evaluation results; traditional risk analysis methods are highly subjective and rely on expert experience, with limited accuracy and efficiency; quantitative analysis methods are insufficient and cannot accurately estimate risk probability and transmission mechanism, making it difficult to identify and control key safety risks in a targeted manner. Summary of the invention

[0004] In view of this, the embodiments of the present invention provide an analysis method, device, equipment and medium for railway safety risk transmission to solve the problem that the existing railway safety risk assessment lacks a quantitative analysis method.

[0005] In a first aspect, an embodiment of the present invention provides a method for analyzing railway safety risk transmission, the method comprising:

[0006] Acquire a railway safety risk set, wherein the railway safety risk set includes multiple safety risk items;

[0007] Analyze the railway safety risk set based on the railway historical operation data set to obtain the risk transfer relationship between the safety risk items;

[0008] Constructing a railway safety risk transfer network based on the risk transfer relationship between each of the safety risk items;

[0009] A probability analysis is performed on the railway safety risk transfer network to obtain key safety risk items and key transfer paths in the railway safety risk transfer network.

[0010] In an optional implementation manner of the present application, the analyzing the railway safety risk set based on the railway historical operation data set to obtain the risk transfer relationship between the safety risk items includes:

[0011] Acquire historical railway operation data, and map the historical railway operation data into a corresponding Boolean matrix;

[0012] Based on the Boolean matrix, the occurrence frequency of the safety risk item in the historical railway operation data is counted, and a target risk set is constructed using the target safety risk item with an occurrence frequency higher than a preset frequency;

[0013] The target security risk items in the target risk set are subjected to correlation analysis according to preset correlation rules to obtain the risk transfer relationship.

[0014] In an optional implementation manner of the present application, performing correlation analysis on the target security risk items in the target risk set according to a preset correlation rule to obtain the risk transfer relationship includes:

[0015] Calculating the support between every two target security risk items;

[0016] Comparing the support with a preset support, and constructing a risk item group from two target security risk items whose support is greater than or equal to the preset support;

[0017] Calculating the confidence and improvement between the target security risk items in each of the risk item groups;

[0018] The risk item group whose confidence level is higher than a preset confidence level and whose improvement level is higher than a preset improvement level is determined as a target risk item group, and a risk transfer relationship between target security risk items in the target risk item group is constructed.

[0019] In an optional implementation manner of the present application, the construction of a railway safety risk transfer network based on the risk transfer relationship between the safety risk items includes:

[0020] Dividing the risk transfer relationship into a causal transfer relationship and a coupling transfer relationship;

[0021] Taking each target safety risk item in the railway safety risk set as a node, the nodes are connected by a first connection method according to the causal transmission relationship and by a second connection method according to the coupling transmission relationship to construct a corresponding railway safety risk transmission network.

[0022] In an optional implementation manner of the present application, the probabilistic analysis of the railway safety risk transfer network to obtain key safety risk items and key transfer paths in the railway safety risk transfer network includes:

[0023] Using the Bayesian network for forward reasoning, the occurrence probability of the target safety risk item in the railway safety risk transfer network is obtained;

[0024] Using the Bayesian network to perform reverse reasoning, the posterior probability of the target safety risk item in the railway safety risk transfer network is obtained;

[0025] Based on the occurrence probability and the posterior probability, key safety risk items and transfer paths in the railway safety risk transfer network are determined.

[0026] In an optional implementation manner of the present application, the determining the key safety risk items and the key transfer paths in the railway safety risk transfer network based on the occurrence probability and the posterior probability includes:

[0027] Determining the sensitivity of each of the security risks according to the posterior probability;

[0028] Identifying key safety risk items in the railway safety risk transfer network based on the sensitivity;

[0029] The key security risk items are used to track associated transfer links, and a key transfer path for risk transfer is determined based on the transfer links.

[0030] In an optional embodiment of the present application, the method further includes:

[0031] Prioritizing the key security risk items to obtain a target risk list;

[0032] Generating corresponding risk control measures for key safety risk items in the target risk list;

[0033] Based on the key transfer path, the key links in the risk control measures are configured and optimized to obtain optimized risk control measures.

[0034] In a second aspect, an embodiment of the present invention provides a railway safety risk transmission analysis device, the device comprising:

[0035] An acquisition module, used to acquire a railway safety risk set, wherein the railway safety risk set includes multiple safety risk items;

[0036] A first analysis module is used to analyze the railway safety risk set based on the railway historical operation data set to obtain the risk transfer relationship between the safety risk items;

[0037] A construction module, used to construct a railway safety risk transfer network based on the risk transfer relationship between each of the safety risk items;

[0038] The second analysis module is used to perform a probability analysis on the railway safety risk transfer network to obtain key safety risk items and key transfer paths in the railway safety risk transfer network.

[0039] In a third aspect, an embodiment of the present invention provides a computer device, comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, computer instructions being stored in the memory, and the processor executing the method for analyzing railway safety risk transmission of the first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0040] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the analysis method for railway safety risk transfer of the above-mentioned first aspect or any corresponding embodiment thereof.

[0041] The method provided in the embodiment of the present application has the following beneficial effects:

[0042] The method provided in the embodiment of the present application obtains a railway safety risk set, which covers various safety risk items that may be encountered in railway operations, and provides comprehensive basic data for railway safety risk management. Obtaining a railway safety risk set can systematically understand and grasp the risks that may be faced in railway operations, and provide strong support for subsequent risk identification, assessment and control.

[0043] The method provided in the embodiment of the present application reveals the risk transfer relationship between safety risk items by deeply analyzing the historical railway operation data set. By mapping the Boolean matrix, counting the frequency of occurrence and performing correlation analysis, the inherent connection between risks is accurately excavated, so that the mutual influence and transmission mechanism between risks can be more clearly understood, providing a scientific basis for building an effective risk management strategy.

[0044] The method provided in the embodiment of the present application constructs a railway safety risk transfer network based on the risk transfer relationship. By subdividing the risk transfer relationship into causal and coupling relationships and presenting them in the network in different connection methods, the clarity and accuracy of the safety risk network is ensured, and an intuitive and systematic risk management tool is provided, which helps to quickly identify the source of risk and the transmission path, so as to make targeted prevention and control measures.

[0045] The method provided in the embodiment of the present application uses probability analysis to determine the key safety risk items and key transmission paths in the railway safety risk transmission network. By using the Bayesian network for forward and reverse reasoning, as well as comprehensive analysis based on the probability of occurrence and posterior probability, accurate identification of key safety risks and transmission paths is achieved, the accuracy and efficiency of risk management are improved, and resources can be concentrated to deal with the most critical risk points and risk transmission paths, thereby effectively improving the safety and stability of railway operations. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0047] Figure 1 is a flow chart of a method for analyzing railway safety risk transfer according to some embodiments of the present invention;

[0048] Figure 2 is a railway safety risk set diagram according to an embodiment of the present invention;

[0049] Figure 3 is a security risk transfer relationship diagram according to an embodiment of the present invention;

[0050] Figure 4 is a security risk transfer network diagram according to an embodiment of the present invention;

[0051] Figure 5 is a risk transfer network diagram of a foreign body intrusion event according to an embodiment of the present invention;

[0052] Figure 6 is a graph showing the probability of a foreign body intrusion event occurring according to an embodiment of the present invention;

[0053] Figure 7 is a result diagram of the causal relationship reasoning of the safety risk of a foreign object intrusion event according to an embodiment of the present invention;

[0054] Figure 8 is another safety risk causal relationship reasoning result diagram of a foreign object intrusion event according to an embodiment of the present invention;

[0055] Fig. 9 is a diagram showing the inference result of the safety risk coupling relationship of a foreign object intrusion event according to an embodiment of the present invention;

[0056] Fig.10 is a structural block diagram of a railway safety risk transfer analysis device according to an embodiment of the present invention;

[0057] Fig.11 It is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0058] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0059] According to an embodiment of the present invention, a method, device, equipment and medium for analyzing railway safety risk transmission are provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0060] In this embodiment, a railway safety risk transfer analysis method is provided. Figure 1 is a flow chart of a method for analyzing railway safety risk transfer according to an embodiment of the present invention. Figure 1 As shown, the process includes the following steps:

[0061] Step S11, obtaining a railway safety risk set, wherein the railway safety risk set includes multiple safety risk items.

[0062] In the embodiments of the present application, the construction of the safety risk set follows the principles of scientific classification and systematicity. First, from the perspective of personnel, unsafe behaviors are mainly classified with reference to some standard documents in the field, which helps to accurately identify and classify various potential risks related to personnel operations. Secondly, the unsafe state of the equipment is classified based on the full life cycle of the equipment and facilities, so that the risks that may exist in each link of the equipment from design, manufacturing to use, maintenance and scrapping can be fully covered. Thirdly, environmental unsafe factors are classified according to railway practical experience to ensure that there is sufficient understanding and preparation for various adverse conditions that may be encountered in the railway operating environment. Finally, management deficiencies are also classified with reference to some standard documents in the field to ensure that risks at the management level are also taken into consideration.

[0063] As an example, through this comprehensive classification method, a set of 35 security risks can be constructed, such as Figure 2As shown in the figure, there are 14 personnel risks, 7 equipment risks, 4 environmental risks and 10 management risks. This safety risk set provides a solid foundation for subsequent risk analysis and management, and helps the railway bureau group company to more comprehensively understand and grasp the safety risk status in railway operations, so as to formulate more effective risk management strategies and measures.

[0064] Step S12, analyzing the railway safety risk set based on the railway historical operation data set to obtain the risk transfer relationship between the safety risk items.

[0065] In the embodiment of the present application, step S12 includes the following steps A1-A3:

[0066] Step A1, obtaining historical railway operation data, and mapping the historical railway operation data into a corresponding Boolean matrix.

[0067] In an embodiment of the present application, first, obtaining railway historical operation data refers to collecting and organizing various historical data in the railway operation process. These data may include accident records, equipment failure reports, environmental monitoring data, personnel operation records, etc., reflecting various situations and events in railway operations. Secondly, the historical operation data is mapped into a Boolean matrix. Among them, a Boolean matrix is ​​a matrix containing only "0" and "1", which is used to indicate whether a certain risk item appears in a certain data record. Specifically, if a certain risk item appears in a specific data record, the corresponding position in the Boolean matrix is ​​marked as "1"; if it does not appear, it is marked as "0". In this process, the rows of the matrix represent different risk items, and the columns represent different data records. In this way, the complex railway historical operation data is simplified into a mathematical structure that is easier to analyze and process.

[0068] Specifically, the railway historical operation data is mapped into a Boolean matrix B containing only "0" and "1" elements. m×n , where m is the number of risk items, n is the total number of data in the database, B i×j =1 means risk i appears in data j, B i×j =0 means risk i does not appear in data j.

[0069] Step A2, based on the Boolean matrix, statistics the occurrence frequency of safety risk items in the historical railway operation data, and use the target safety risk items with an occurrence frequency higher than the preset frequency to construct a target risk set.

[0070] In an embodiment of the present application, the number of occurrences of "1" in each safety risk item (i.e., each row of the Boolean matrix) is counted, and this number represents the frequency of occurrence of the risk item in the historical operating data. In order to screen out important safety risk items, it is necessary to set a preset frequency, wherein the preset frequency is set based on the analysis of historical data and actual operating conditions, and is intended to exclude those risk items with low occurrence frequencies that may have little impact on the overall risk analysis. By comparing the frequency of occurrence of each safety risk item with the preset frequency, risk items with a frequency higher than the preset frequency can be screened out, and the initial risk items may have a greater impact on the safety risk of the entire railway system.

[0071] Specifically, first, count the number of occurrences S of the element "1" in the jth column of the Boolean matrix B j , and verify whether it meets the preset frequency requirements, and perform pruning operations, that is, if S j ≤n×a, then delete the column and generate a new Boolean matrix , and generate frequent L-1 item sets (L represents the length of the item set). Secondly, for the new Boolean matrix The influencing factor columns are logically "AND" operated, self-connected to generate a new Boolean matrix, and candidate frequent C-2 item sets are generated. The number of "1" elements in each column is compared with m×a. If it does not meet the preset frequency requirement, the column is deleted to generate frequent L-2 item sets. Finally, the pruning operation is repeated until a frequent Lk item set is generated (k represents the association between k influencing factors).

[0072] Step A3: performing correlation analysis on the target security risk items in the target risk set according to preset correlation rules to obtain the risk transfer relationship.

[0073] It should be noted that \={i1,i2,...,i m} is used to represent the railway safety risk set, and T = {t1, t2, ..., t n} represents the railway operation database, T consists of multiple historical data, each of which contains one or more items in the risk set I, satisfying t j ∈I. A risk transfer relationship can be expressed as The expression of and Among them, X is called the antecedent of the risk transfer relationship, and Y is called the posterior of the risk transfer relationship. When describing the strength of the risk transfer relationship, the three indicators of support, confidence and lift are mainly used for measurement.

[0074] In the embodiment of the present application, step A3 includes the following steps A31-A34:

[0075] Step A31, calculating the support between every two target security risk items.

[0076] It should be noted that for each pair of risk items (denoted as X and Y) in the target safety risk item set, their support needs to be calculated. Support is used to measure the importance of risk transfer relationships, reflecting the frequent co-occurrence of each risk item in the railway operation data set or the persuasiveness of a specific risk in the overall data set. Indicates that the calculation formula of support is as follows:

[0077]

[0078] Among them, σ(X∪Y) is the number of risks X and Y that exist simultaneously, in units of pieces; |T| is the total number of railway operation data, in units of pieces.

[0079] In the embodiment of the present application, the railway operation database is traversed, and each record is checked to see whether it contains two specific risk items, namely X and Y. Whenever two risk items appear in a record at the same time, the counter is incremented by one. After the traversal is completed, the count result is divided by the total number of records to obtain the support of the two risk items. The support indicates the frequency of the two risk items appearing at the same time, and a high support indicates that the two are associated. This indicator is crucial for the subsequent judgment of the causal relationship or parallel relationship between risk items.

[0080] Step A32: Compare the support with the preset support, and construct a risk item group from two target security risk items whose support is greater than or equal to the preset support.

[0081] In an embodiment of the present application, in order to improve mining efficiency and eliminate accidental associations, it is necessary to set a support threshold, namely, a preset support a. The preset support is set according to specific application scenarios and data analysis requirements, and is used to screen out those pairs of security risk items that appear frequently enough. The support of each pair of security risk items is compared with the preset support a. Only when the support is greater than or equal to the preset support a, is it considered that the pair of risk items co-occurs frequently and there may be some kind of association relationship. For pairs of security risk items whose support is greater than or equal to the preset support a, a risk item group is constructed. These risk item groups are the basis for subsequent analysis of association rules, causal relationships or coupling relationships between risks.

[0082] Step A33, calculating the confidence and lift between the target security risk items in each risk item group.

[0083] In an embodiment of the present application, after screening out risk item groups whose support is greater than or equal to the preset support a, the confidence and lift between each security risk item in these risk item groups are further calculated. Confidence is an indicator for measuring the reliability of risk transfer relationships, reflecting the probability that another risk item (consequent item) will also appear under the condition that one risk item (precursor item) appears. Lift is an indicator for measuring the correlation of risk transfer relationships, reflecting whether there is a positive correlation, negative correlation, or no correlation between risk items.

[0084] Specifically, for the target security risk items X and Y in each risk item group, the confidence is expressed as The calculation formula is as follows:

[0085]

[0086] Among them, Sup(X) represents the support of risk X, that is, the frequency of risk X appearing in the database; ρ(X) is the number of times risk X appears in the database, in units of pieces.

[0087] Specifically, for the target security risk items X and Y in each risk item group, the lift degree (Lift) is calculated using The calculation formula is as follows:

[0088]

[0089] Among them, Sup(Y) represents the support of risk Y, that is, the frequency of risk Y appearing in the database.

[0090] Step A34, determining the risk item group whose confidence level is higher than the preset confidence level and whose improvement level is higher than the preset improvement level as the target risk item group, and constructing the risk transfer relationship between the target security risk items in the target risk item group.

[0091] In an embodiment of the present application, first, a preset confidence threshold b and a preset lift threshold c are set. These two thresholds are set based on domain knowledge and actual needs to ensure that the screened risk transfer relationship is both reliable and relevant. Secondly, the calculated confidence and lift of each risk item group are compared with the two thresholds. Only when the confidence of a certain risk item group is higher than the preset confidence threshold b, and the lift is higher than the preset lift threshold c, will the risk item group be determined as the target risk item group. Finally, for the screened target risk item group, a risk transfer relationship between the target security risk items is constructed. This usually involves determining the direction of risk transfer (i.e. which risk item is the former and which is the latter) and the type of relationship (causal relationship or coupling relationship).

[0092] Specifically, in association rule mining, the antecedent of the rule is usually regarded as a condition, and the consequent is regarded as a result. Therefore, when constructing risk transfer relationships, this directionality can be followed, and the risk item as a condition in the confidence and lift calculations is set as the antecedent, and the risk item as a result is set as the consequent. Combined with the actual situation of railway operations and domain knowledge, it can be further determined whether these risk transfer relationships are causal or coupled.

[0093] Step S13, constructing a railway safety risk transfer network based on the risk transfer relationship between various safety risk items.

[0094] In the embodiment of the present application, step S13 includes the following steps B1-B2:

[0095] Step B1, divide the risk transfer relationship into causal transfer relationship and coupling transfer relationship.

[0096] In an embodiment of the present application, the risk transfer relationship between various security risk items is divided into a causal transfer relationship (referred to as "causal relationship") and a coupled transfer relationship (referred to as "coupling relationship"), among which the causal relationship belongs to a serial transfer relationship with an obvious transfer direction; the coupling relationship belongs to a parallel transfer relationship, indicating that risks occur simultaneously.

[0097] Step B2, taking each target safety risk item in the railway safety risk set as a node, connecting the nodes using a first connection method according to a causal transmission relationship, and connecting them using a second connection method according to a coupling transmission relationship, to construct a corresponding railway safety risk transmission network.

[0098] In the embodiment of the present application, first, each target safety risk item in the railway safety risk set is regarded as a node. These nodes represent various safety risks that may be encountered during railway operation. Secondly, according to the risk transfer relationship obtained by the previous analysis, connections are established between the nodes. There are two types of connections here:

[0099] Connection of causal transmission relationship: If there is a causal relationship between two risk items, that is, the occurrence of one risk will directly lead to the occurrence of another risk, then the two nodes are connected by a solid arrow (the first connection method), indicating the serial transmission of risks and a clear transmission direction.

[0100] Connection of coupled transfer relationship: If there is a coupling relationship between two risk items, that is, they may occur at the same time but do not constitute a direct causal relationship, then the two nodes are connected by a virtual arrow (the second connection method) to indicate the parallel transmission of risks.

[0101] By integrating all the nodes and connections in the above way, a complete railway safety risk transmission network is formed. This network not only shows the relationship between various safety risk items, but also clearly depicts how risks are transmitted in the railway system.

[0102] As an example, we select the foreign body intrusion risk event E as a case for analysis and identify the main factors that lead to the risk event, including human unsafe behavior H. i , Unsafe state of equipment E qi 、Environmental unsafe factors E ni and management deficiencies i (i=1,2,...,n, n is the total number of various risks). After clarifying these risk factors, we further assume that there is a certain transmission relationship between these risks, such as Figure 3 As shown, the transitive relationship includes: M i →H i 、M i →E qi , H i →E, E qi →E, H i →E qi 、E ni →E qi 、E ni →H i Based on these transmission relationships, a safety risk transmission network can be constructed to intuitively show how risks flow and accumulate between various factors, which may eventually lead to the occurrence of foreign body intrusion risk events. The constructed safety risk transmission network, such as Figure 4 As shown in Figure 1, the complete path from a single risk source to the final risk event is depicted. In this network, the path from a specific risk to the final foreign body intrusion risk event is defined as the "risk transmission path". Figure 2 The transmission relationship shown in the figure can clearly trace each risk transmission path, and accordingly construct a detailed risk transmission network for foreign body intrusion risk events, such as Figure 5 shown.

[0103] Step S14, performing a probability analysis on the railway safety risk transfer network to obtain key safety risk items and key transfer paths in the railway safety risk transfer network.

[0104] In the embodiment of the present application, step S14 includes the following steps C1-C3:

[0105] Step C1, using the Bayesian network to perform forward reasoning, obtain the probability of occurrence of the target safety risk item in the railway safety risk transfer network.

[0106] In the embodiment of the present application, first, the forward reasoning function of the Bayesian network (BN) is used to perform probability calculation. Specifically, Figure 4 In the risk transfer network shown, when the risk item is transmitted through the network and eventually leads to the occurrence of a risk event, the total probability formula can be used to accurately calculate the probability of this risk event causing a railway traffic accident. The accident status here can be a specific accident level, such as the classification of railway traffic accident levels, or a description of the severity of the accident. Secondly, in the calculation process, the following probability values ​​are used: the probability of a risk occurring, which is called a priori probability; the probability of another risk occurring under the condition that a certain risk has occurred, that is, the conditional probability; and the probability of multiple risks occurring at the same time, that is, the joint probability. Finally, by integrating these probability values, the total probability of a risk event causing an accident in the network is obtained. This series of calculation processes all rely on the forward inference rule of the Bayesian network, which enables the accurate quantification of the impact of each risk in the risk transfer network on the final accident.

[0107] Specifically, the probability P (E = p|H) that a risk event E causes an accident p to occur in the network i ,E qi ,E ni ), the calculation formula is as follows:

[0108]

[0109] Among them, P(M i ) is the risk M i Probability of occurrence (prior probability); P(E ni ) is the risk E ni Probability of occurrence (prior probability); P(H i |M i ) is in M i Risk H under the occurrence condition i Probability of occurrence (conditional probability); P(E qi |M i ,H i ) is in H i and M i Risk E under the occurrence condition qi Probability of occurrence (conditional probability); P(E=p,E ni ,E qi ,M i ,H i ) is the risk event E causing the accident p and the risk M i , E ni , E qi , H i The probability of occurring simultaneously (joint probability).

[0110] Specifically, in the risk network, assume that there is a pair of coupled risks, and the two risks occur at the same time. The probability of the risk event occurring under this specific state is evaluated through forward reasoning. The specific calculation formula takes into account multiple probability values: including the probability that the risk event leads to an accident when the coupled risks occur at the same time; the probability that the risk event and a certain risk occur at the same time; and the probability that two coupled risks occur at the same time. The probability of a risk event occurring P (E = p|H i =1,E ni =1), the calculation formula is as follows:

[0111]

[0112] Where P(E=p|H i =1,E ni =1) is the probability that the risk event E leads to the accident p when the risks and the accidents occur simultaneously; P(E=p,H i =1,E ni =1) is the risk event E causing the accident p and the risk E ni , H i The probability of simultaneous occurrence; P(H i =1,E ni =1) is the risk E ni , H i The probability of simultaneous occurrence.

[0113] Step C2, using the Bayesian network to perform reverse reasoning, to obtain the posterior probability of the target safety risk item in the railway safety risk transfer network.

[0114] In the embodiment of the present application, the Bayesian network is used for reverse reasoning, the purpose of which is to obtain the posterior probability of the target safety risk item in the railway safety risk transfer network. Specifically, assuming that a certain risk in the network is bound to occur, that is, the probability of its occurrence is 1, through forward reasoning, the possibility of other safety risks and risk events occurring under this specific state can be evaluated. When it is assumed that the risk event has led to an accident, reverse reasoning can evaluate the probability of each risk occurring under this state, which is the so-called posterior probability. The calculation formula of the posterior probability involves two key probability values: one is the prior probability of the risk occurring, and the other is the conditional probability of the risk event causing the accident under the condition that a certain risk has occurred. Through the calculation of these two probability values, the posterior probability of the risk can be obtained, which reflects the possibility of a certain risk occurring when it is known that an accident has occurred.

[0115] Specifically, the posterior probability P(A i |E=p), the calculation formula is as follows:

[0116]

[0117] Among them, P(A i ) is the probability of risk occurrence (prior probability); P(E=p|A i ) is in A i The probability that risk event E will lead to accident p under certain conditions (conditional probability).

[0118] Step C3, determining the key safety risk items and transmission paths in the railway safety risk transmission network based on the occurrence probability and the posterior probability.

[0119] In the embodiment of the present application, step C3 includes the following steps C31-C33:

[0120] Step C31, determining the sensitivity of each security risk according to the posterior probability.

[0121] In an embodiment of the present application, by calculating the updated posterior probability, the key risk items in the railway safety risk transfer network can be further identified. In order to quantify the criticality of the risk, it is necessary to introduce the indicator of sensitivity (ROV). In the calculation process of sensitivity (ROV), the size of the ROV value directly reflects the contribution of the risk to the occurrence of risk events. Specifically, the larger the ROV value, the greater the contribution of the risk item to the occurrence of risk events, that is, the higher the criticality of the risk item in the network. In this way, the key risks in the network can be more accurately identified and managed.

[0122] Specifically, the calculation formula of sensitivity (ROV) is as follows:

[0123]

[0124] Among them, ROV (A i ) is risk A i sensitivity.

[0125] Step C32, identifying key safety risk items in the railway safety risk transfer network based on sensitivity.

[0126] As an example, the key safety risk items in the railway safety risk transfer network are identified based on sensitivity. Here, the foreign object intrusion event is used as an example. Assume that the probability reasoning result of the foreign object intrusion event is as follows: Figure 6 As shown in the figure, the causal relationship reasoning results of the safety risk of foreign body intrusion incident are as follows: Figure 7 and Figure 8 As shown in the figure, the inference results of the safety risk coupling relationship of foreign body intrusion events are as follows: Fig. 9As shown in Figure 2, by combining these analysis results with the results of reverse reasoning, the sensitivity (ROV) of each risk can be further calculated. According to the ranking of ROV, the top five risks can be obtained as E q6 , E n4 , H7, H3, E q5 This means that in the event of foreign body intrusion, these five risks (E q6 , E n4 , H7, H3, E q5 ) is a key safety risk that leads to serious consequences.

[0127] Step C33, using the key security risk items to track the associated transfer links, and determining the key transfer path of risk transfer based on the transfer links.

[0128] In the embodiment of the present application, after identifying the key safety risk items in the railway safety risk transmission network, the key safety risk items are used to track the associated transmission links, and the key transmission paths of risk transmission are determined based on the transmission links. The purpose is to further track how these key risk items are transmitted in the network. By tracing the transmission links of these key safety risk items upward step by step, the main transmission paths of risks in the network can be determined.

[0129] As an example, the five key risks (E q6 , E n4 , H7, H3, E q5 ), by transferring the key safety risks upward step by step, we can get the key path of risk transfer, for example: E q6 →E n2 、M5→M8→M7→E n4 →E n2 、M5→H2→E n4 →E n2 wait.

[0130] In an embodiment of the present application, the method also includes: prioritizing key security risk items to obtain a target risk list; generating corresponding risk control measures for key security risk items in the target risk list; and optimizing the configuration of key links in the risk control measures based on critical transfer paths to obtain optimized risk control measures.

[0131] In the embodiment of the present application, the key risk items in the railway safety risk network are first identified through sensitivity analysis, and are prioritized according to factors such as their contribution to risk events to form a target risk list. Then, corresponding risk control measures are formulated for each key risk item in the list, such as strengthening training, equipment maintenance, and optimized management. Finally, using the analysis results of the critical transfer path, the key links in the risk control measures are finely configured and optimized to more effectively block risk transmission.

[0132] In this embodiment, a railway safety risk transmission analysis device is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" can implement a combination of software and / or hardware of a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0133] This embodiment provides a railway safety risk transfer analysis device, such as Fig.10 As shown, including:

[0134] An acquisition module 101 is used to acquire a railway safety risk set, wherein the railway safety risk set includes multiple safety risk items;

[0135] The first analysis module 102 is used to analyze the railway safety risk set based on the railway historical operation data set to obtain the risk transfer relationship between the safety risk items;

[0136] A construction module 103 is used to construct a railway safety risk transfer network based on the risk transfer relationship between each safety risk item;

[0137] The second analysis module 104 is used to perform a probability analysis on the railway safety risk transmission network to obtain key safety risk items and key transmission paths in the railway safety risk transmission network.

[0138] In an optional implementation of the present application, the first analysis module 102 is used to obtain historical railway operation data and map the historical railway operation data into a corresponding Boolean matrix; based on the Boolean matrix, the frequency of occurrence of safety risk items in the historical railway operation data is counted, and a target risk set is constructed using target safety risk items whose occurrence frequency is higher than a preset frequency; and a correlation analysis is performed on the target safety risk items in the target risk set according to preset association rules to obtain a risk transfer relationship.

[0139] In an optional implementation of the present application, the first analysis module 102 is used to calculate the support between every two target security risk items; compare the support with the preset support, and construct a risk item group with two target security risk items whose support is greater than or equal to the preset support; calculate the confidence and lift between the target security risk items in each risk item group; determine the risk item group whose confidence is higher than the preset confidence and whose lift is higher than the preset lift as the target risk item group, and construct a risk transfer relationship between the target security risk items in the target risk item group.

[0140] In an optional embodiment of the present application, a construction module 103 is used to divide the risk transfer relationship into a causal transfer relationship and a coupled transfer relationship; each target safety risk item in the railway safety risk set is taken as a node, and the nodes are connected by a first connection method according to the causal transfer relationship and by a second connection method according to the coupled transfer relationship, so as to construct a corresponding railway safety risk transfer network.

[0141] In an optional embodiment of the present application, the second analysis module 104 is used to perform forward reasoning using a Bayesian network to obtain the probability of occurrence of a target safety risk item in the railway safety risk transfer network; perform reverse reasoning using a Bayesian network to obtain the posterior probability of the target safety risk item in the railway safety risk transfer network; and determine the key safety risk items and transfer paths in the railway safety risk transfer network based on the probability of occurrence and the posterior probability.

[0142] In an optional embodiment of the present application, the second analysis module 104 is used to determine the sensitivity of each safety risk based on the posterior probability; identify the key safety risk items in the railway safety risk transmission network based on the sensitivity; use the key safety risk items to track the associated transmission links, and determine the key transmission path of risk transmission based on the transmission links.

[0143] In an optional embodiment of the present application, the device also includes: an optimization module, which is used to prioritize key security risk items to obtain a target risk list; generate corresponding risk control measures for key security risk items in the target risk list; and optimize the configuration of key links in the risk control measures based on critical transfer paths to obtain optimized risk control measures.

[0144] See also Fig.11 , Fig.11 is a schematic diagram of the structure of a computer device provided by an optional embodiment of the present invention, such as Fig.11As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system).

[0145] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0146] The memory 20 stores instructions executable by at least one processor 10, so that at least one processor 10 executes the method shown in the above embodiment.

[0147] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created by the use of a computer device based on the presentation of a small program landing page, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0148] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0149] The computer device further comprises a communication interface 30 for the computer device to communicate with other devices or a communication network.

[0150] The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0151] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A railway safety risk transfer analysis method, characterized in that: The method comprises: Acquire a railway safety risk set, wherein the railway safety risk set includes multiple safety risk items; Analyze the railway safety risk set based on the railway historical operation data set to obtain the risk transfer relationship between the safety risk items; Constructing a railway safety risk transfer network based on the risk transfer relationship between each of the safety risk items; A probability analysis is performed on the railway safety risk transfer network to obtain key safety risk items and key transfer paths in the railway safety risk transfer network.

2. The method according to claim 1, characterized in that The analyzing the railway safety risk set based on the railway historical operation data set to obtain the risk transfer relationship between the safety risk items includes: Acquire historical railway operation data, and map the historical railway operation data into a corresponding Boolean matrix; Based on the Boolean matrix, the occurrence frequency of the safety risk item in the historical railway operation data is counted, and a target risk set is constructed using the target safety risk item with an occurrence frequency higher than a preset frequency; The target security risk items in the target risk set are subjected to correlation analysis according to preset correlation rules to obtain the risk transfer relationship.

3. The method according to claim 2, characterized in that The performing correlation analysis on the target security risk items in the target risk set according to the preset correlation rule to obtain the risk transfer relationship includes: Calculating the support between every two target security risk items; Comparing the support with a preset support, and constructing a risk item group from two target security risk items whose support is greater than or equal to the preset support; Calculating the confidence and improvement between the target security risk items in each of the risk item groups; The risk item group whose confidence level is higher than a preset confidence level and whose improvement level is higher than a preset improvement level is determined as a target risk item group, and a risk transfer relationship between target security risk items in the target risk item group is constructed.

4. The method according to claim 1, characterized in that The step of constructing a railway safety risk transfer network based on the risk transfer relationship between each of the safety risk items includes: Dividing the risk transfer relationship into a causal transfer relationship and a coupling transfer relationship; Taking each target safety risk item in the railway safety risk set as a node, the nodes are connected by a first connection method according to the causal transmission relationship and by a second connection method according to the coupling transmission relationship to construct a corresponding railway safety risk transmission network.

5. The method according to claim 4, characterized in that The probabilistic analysis of the railway safety risk transfer network to obtain key safety risk items and key transfer paths in the railway safety risk transfer network includes: Using the Bayesian network for forward reasoning, the occurrence probability of the target safety risk item in the railway safety risk transfer network is obtained; Using the Bayesian network to perform reverse reasoning, the posterior probability of the target safety risk item in the railway safety risk transfer network is obtained; Based on the occurrence probability and the posterior probability, key safety risk items and transfer paths in the railway safety risk transfer network are determined.

6. The method according to claim 5, characterized in that The determining of the key safety risk items and the key transfer paths in the railway safety risk transfer network based on the occurrence probability and the posterior probability includes: Determining the sensitivity of each of the security risks according to the posterior probability; Identifying key safety risk items in the railway safety risk transfer network based on the sensitivity; The key security risk items are used to track associated transfer links, and a key transfer path for risk transfer is determined based on the transfer links.

7. The method according to claim 1, characterized in that The method further comprises: Prioritizing the key security risk items to obtain a target risk list; Generate corresponding risk control measures for key safety risk items in the target risk list; Based on the key transfer path, the key links in the risk control measures are configured and optimized to obtain optimized risk control measures.

8. A railway safety risk transfer analysis device, characterized in that: The device comprises: An acquisition module, used to acquire a railway safety risk set, wherein the railway safety risk set includes multiple safety risk items; A first analysis module is used to analyze the railway safety risk set based on the railway historical operation data set to obtain the risk transfer relationship between the safety risk items; A construction module, used to construct a railway safety risk transfer network based on the risk transfer relationship between each of the safety risk items; The second analysis module is used to perform a probability analysis on the railway safety risk transfer network to obtain key safety risk items and key transfer paths in the railway safety risk transfer network.

9. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the method according to any one of claims 1 to 7 by executing the computer instructions.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the method according to any one of claims 1 to 7.

Images