CN112465304A - Railway turnout area train derailment accident assessment method based on Bayesian network - Google Patents
Railway turnout area train derailment accident assessment method based on Bayesian network Download PDFInfo
- Publication number
- CN112465304A CN112465304A CN202011234659.5A CN202011234659A CN112465304A CN 112465304 A CN112465304 A CN 112465304A CN 202011234659 A CN202011234659 A CN 202011234659A CN 112465304 A CN112465304 A CN 112465304A
- Authority
- CN
- China
- Prior art keywords
- bayesian network
- node
- nodes
- derailment accident
- train derailment
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 19
- 206010012411 Derailment Diseases 0.000 claims abstract description 65
- 238000010206 sensitivity analysis Methods 0.000 claims abstract description 7
- 238000012163 sequencing technique Methods 0.000 claims abstract description 7
- 238000012502 risk assessment Methods 0.000 claims abstract description 6
- 238000010801 machine learning Methods 0.000 claims description 6
- 229910000831 Steel Inorganic materials 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 4
- 230000001364 causal effect Effects 0.000 claims description 4
- 239000010959 steel Substances 0.000 claims description 4
- 238000005299 abrasion Methods 0.000 claims description 3
- 230000006378 damage Effects 0.000 claims description 3
- 230000007717 exclusion Effects 0.000 claims description 3
- 230000007613 environmental effect Effects 0.000 claims description 2
- 238000011156 evaluation Methods 0.000 claims description 2
- 230000009467 reduction Effects 0.000 claims description 2
- 230000009471 action Effects 0.000 abstract description 4
- 230000008569 process Effects 0.000 description 5
- 238000011160 research Methods 0.000 description 5
- 230000035945 sensitivity Effects 0.000 description 4
- 230000008859 change Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 238000011002 quantification Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N7/00—Computing arrangements based on specific mathematical models
- G06N7/01—Probabilistic graphical models, e.g. probabilistic networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/40—Business processes related to the transportation industry
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Evolutionary Computation (AREA)
- Entrepreneurship & Innovation (AREA)
- Software Systems (AREA)
- Marketing (AREA)
- Educational Administration (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Development Economics (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Quality & Reliability (AREA)
- Medical Informatics (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Analysis (AREA)
- Computational Mathematics (AREA)
- Algebra (AREA)
- Probability & Statistics with Applications (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to a method for evaluating train derailment accidents in a railway turnout area based on a Bayesian network, which comprises the following steps: acquiring train derailment accident data, establishing a derailment accident database, analyzing and judging to select sensitive and easily-acquired key factors, defining the mutual relation between key factor variables, and converting the key factor variables into each node of a Bayesian network; defining variables to determine the sequencing of the nodes of the Bayesian network and establishing a topological relation of the Bayesian network; and (4) learning to obtain probability distribution of each node of the grid and carrying out sensitivity analysis, thereby realizing train derailment risk assessment in the railway turnout area. The invention has the advantages that: the derailment accident risk under the multi-factor action of the system can be comprehensively evaluated and considered, and the running reliability of the rail vehicle can be guided to be improved.
Description
Technical Field
The invention relates to the technical field of railway transportation safety monitoring, in particular to a method for evaluating train derailment accidents in a railway turnout area based on a Bayesian network.
Background
The prevention of train derailment is one of the important subjects of rail transit research, and although a large amount of scientific research work is carried out in the field at present, the technical level at present cannot completely ensure that a train does not have derailment accidents, so how to predict and evaluate the probability of the train derailment accidents can predict the probability of the train derailment accidents in advance, and thus the occurrence of the train derailment can be prevented in advance.
In the prior art, a vehicle-track/turnout dynamic model is mostly adopted to evaluate the safety of a train passing through a turnout, and the driving safety of the train is mainly researched by adopting a wheel derailment coefficient and a wheel weight load shedding rate; however, the prior art has the following disadvantages: the derailment accident in the turnout area has higher complexity, and the randomness cannot effectively evaluate the derailment risk of the train under the action of complex factors based on vehicle track dynamics simulation calculation; many times, even if the train derailment coefficient and the wheel load shedding rate exceed the limit, the derailment does not occur, and the estimation result has errors due to the estimation through the derailment coefficient and the wheel load shedding rate.
Disclosure of Invention
The invention aims to overcome the defects of the prior art, provides a method for evaluating train derailment accidents in a railway turnout area based on a Bayesian network, and overcomes the defects of the conventional method for predicting train derailment accidents.
The purpose of the invention is realized by the following technical scheme: a train derailment accident assessment method based on a Bayesian network railway turnout zone comprises the following steps:
acquiring train derailment accident data, establishing a derailment accident database, analyzing and judging to select sensitive and easily-acquired key factors, defining the mutual relation between key factor variables, and converting the key factor variables into each node of a Bayesian network;
defining variables to determine the sequencing of the nodes of the Bayesian network and establishing a topological relation of the Bayesian network;
and (4) learning to obtain probability distribution of each node of the grid and carrying out sensitivity analysis, thereby realizing train derailment risk assessment in the railway turnout area.
Further, the converting into the respective nodes of the bayesian network comprises: dividing the derailment accident data into a basic event, a middle event and a top event; and converting the basic event into a root node of the Bayesian network, converting the intermediate event into an intermediate node of the Bayesian network, and converting the top event into a leaf node of the Bayesian network.
Further, the defining the interrelationship between the key factor variables comprises: defining the root factor which directly influences whether the train derailment accident happens or not and causes the train derailment accident as the basic event; defining factors affecting the occurrence of the basic event as the intermediate event; the result of all intermediate events acting together is defined as the top event.
Further, the defining variables determine the ordering of the nodes of the bayesian network, and establishing the topological relation of the bayesian network includes: sequencing and grading each node, and defining variable nodes with a limited set of mutual exclusion states as identification root nodes or intermediate nodes to represent identified dangers; and developing fault logic through conditional probability distribution, and establishing a Bayesian network topology to describe conditional independence relations of the definition variables.
Further, the learning to obtain probability distribution of each node of the grid and carrying out sensitivity analysis, and the implementation of train derailment risk assessment in the railway turnout area comprises the following steps:
compiling a machine learning language based on the data sample, and performing parameter learning and structure learning on the Bayesian network according to the sample and the prior information;
the network nodes are connected with each other according to the causal association relationship to form a directed acyclic graph, and the dependency association relationship between the given Bayesian network structure nodes is quantified;
and inputting the prior information of each node into a Bayesian model, carrying out inference calculation on the conditional probability distribution of any node variable in the network node, and endowing the obtained conditional probability table to the determined Bayesian network topology structure.
Further, the intermediate events comprise natural environment factors, poor wheel-rail relation, structural failure and human factors; basic events affecting the natural environmental factors include rainstorms, debris flows, strong winds, and earthquakes; basic events affecting the wheel rail badness comprise point rail reduction value, wheel rail abrasion, steel rail joint, wheel diameter difference and geometric configuration badness; the basic events affecting the structural failure include poor geometry, rail break, axle fatigue, fastener failure, and electrical service switching device failure; the basic events that affect the human factors include electrical service switching device failure, human damage, and improper driver handling.
The invention has the following advantages: a train derailment accident assessment method based on a Bayesian network railway turnout area can comprehensively assess and consider the derailment accident risk under the multi-factor action of a system, and can guide the improvement of the running reliability of a railway vehicle.
Drawings
FIG. 1 is a schematic flow diagram of the present invention;
FIG. 2 is a diagram of a key influencing factor of a derailment accident in a railway turnout zone;
in the figure: k1-rainstorm, K2-debris flow, K3-strong wind, K4-earthquake, K5-reduction value, K6-wheel rail abrasion, K7-steel rail joint, K8-wheel diameter difference, K9-poor geometric form and position, K10-steel rail fracture, K11-wheel shaft fatigue, K12-fastener failure, K13-electric power conversion device failure, K14-artificial destruction, K15-improper driver operation, M1-natural environment factor, M2-wheel rail relation failure, M3-structural failure, M4-artificial factor and D-railway turnout area derailment accident.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all the embodiments. The components of the embodiments of the present application, generally described and illustrated in the figures herein, can be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present application, as presented in the figures, is not intended to limit the scope of the claimed application, but is merely representative of selected embodiments of the application. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the present application without making any creative effort, shall fall within the protection scope of the present application. The invention is further described below with reference to the accompanying drawings.
As shown in figure 1, the invention relates to a train derailment accident assessment method based on a Bayesian network railway switch area, which comprises the steps of respectively converting a basic event, a middle event and a top event of a derailment accident into a root node, a middle node and a leaf node of the Bayesian network, connecting the root node, the middle node and the leaf node through directed arcs, establishing the Bayesian network of the derailment accident of the railway switch area, and finally achieving assessment and prediction of the derailment accident of the railway switch area; it mainly comprises the following contents:
firstly, defining a problem; collecting data and derailment factors about train derailment accidents in the last 30 years through documents, data, reports, news and other channels, analyzing and judging the derailment accident data, then determining the value of a variable, discretizing the variable, defining the mutual relation among key factors, and then using the key factors as each node of the Bayesian network; such as K1-K15 (basic event), M1-M4 (intermediate event).
As shown in fig. 2, a derailment in a railroad switch area is taken as an overhead event; derailment accidents are the result of combined actions of natural disasters, poor wheel-rail relationships, structural failures and human factors, which are intermediate events; the K1-K15 accident cause is a basic event, and is a time when the cause does not need to be ascertained. And constructing a fault tree model of the derailment accident of the railway turnout area.
Furthermore, the analysis and evaluation of the related data of the derailment accident mainly refers to searching the existing database of the derailment accident of the related railway turnout area; judging data to select relatively sensitive and easily-obtained influence factors; according to the derailment accident database investigation, key influence factors of poor wheel-rail relation, natural disasters, structural failure and human factors on the derailment accidents of the railway turnout area are found; the selection of effective key factors is very key to the risk assessment of the derailment accident, if all the factors are considered for research, the research process becomes quite difficult and tedious, and the prediction result is difficult to achieve high accuracy.
Furthermore, the mutual relation mainly refers to the causal relation among all variables in the model; the derailment accident is divided into three levels, and the impact is carried out layer by layer; M1-M4 directly influence whether a train derail accident occurs or not and are the basic factors causing the train derail accident; K1-K15 will influence the occurrence of M1-M4. After the relationship among the factors is defined, a complete Bayesian network model is established for the later time to be laid down.
Secondly, constructing a Bayesian network model; after factor variables and correlation of the model are determined, all nodes are sequenced and graded, variable nodes with limited sets of mutual exclusion states are defined as identification root nodes or intermediate nodes to represent identified dangers, fault logic is developed through conditional probability distribution, and a Bayesian network topology is established to describe conditional independence relations of the defined variables; wherein, the finite group represents the influence factors of K1-K15, and the relation between the influence factors is not considered, namely, each factor is independent.
Furthermore, expert knowledge and machine learning are combined to perform sequencing and grading, a Bayesian network model is built according to information such as prior knowledge, experience skills and the like of field experts, and expert knowledge is added in the machine learning process to jointly complete the building of the Bayesian network model, so that the efficiency of the Bayesian network in the machine learning process can be accelerated, and error conditions generated in the modeling process can be reduced.
Finally, estimating the probability of derailment accidents; based on the data samples, a machine learning language is written. Parameter learning and structure learning are carried out on the Bayesian network by means of samples and priori knowledge; and (3) structure learning: connecting network nodes with each other according to a causal association relationship to form a directed acyclic graph; parameter learning: and carrying out a quantification process on the dependency incidence relation among the nodes of the given Bayesian network structure. After a complete Bayesian model is established, prior information of each node is input, and sensitivity inference analysis calculation is carried out on conditional probability distribution of any node variable in the network node. And assigning the obtained conditional probability table to the determined Bayesian network topology. And after the probability distribution of the variable of each node of the network is obtained, the establishment of the complete railway turnout area derailment accident risk Bayesian network element is completed.
Furthermore, according to the Bayesian network structure of the established train derailment accident prediction model in the railway turnout area, variable values of the nodes are parameter prior distribution (the probability obtained according to past data or empirical analysis is marked as P (xi)), parameter learning is carried out by using MATLAB software (the parameter learning is to quantize the dependency association relationship between the given Bayesian network nodes), and then the probability distribution of the network node variables can be obtained; the inference analysis is implemented based on conditional probability transmission between network nodes, and the Bayesian theorem is the specific inference basis.
Furthermore, sensitivity analysis of the Bayesian network is to research and predict the change of an output value of the system caused by the change of attributes, and is used for measuring the degree of influence of the cause node on the result node; in the train operation safety management, based on the sensitivity coefficient of each factor, the factor with larger influence on the result can be quickly found out to pay attention to, and meanwhile, the factor with smaller sensitivity can be eliminated, so that the system complexity is reduced; for example, the sensitivity of the above-mentioned natural environment factors, poor wheel-rail relationship, structural failure factors and human factors can be obtained through sensitivity analysis, namely, the greatest influence is exerted on the occurrence of train derailment accidents in the railway turnout area.
The foregoing is illustrative of the preferred embodiments of this invention, and it is to be understood that the invention is not limited to the precise form disclosed herein and that various other combinations, modifications, and environments may be resorted to, falling within the scope of the concept as disclosed herein, either as described above or as apparent to those skilled in the relevant art. And that modifications and variations may be effected by those skilled in the art without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (6)
1. A train derailment accident assessment method based on a Bayesian network railway turnout area is characterized by comprising the following steps: the evaluation method comprises the following steps:
acquiring train derailment accident data, establishing a derailment accident database, analyzing and judging to select sensitive and easily-acquired key factors, defining the mutual relation between key factor variables, and converting the key factor variables into each node of a Bayesian network;
defining variables to determine the sequencing of the nodes of the Bayesian network and establishing a topological relation of the Bayesian network;
and (4) learning to obtain probability distribution of each node of the grid and carrying out sensitivity analysis, thereby realizing train derailment risk assessment in the railway turnout area.
2. The Bayesian network-based train derailment accident assessment method for the railway turnout zone, according to claim 1, is characterized in that: the nodes for converting the nodes into the Bayesian network comprise: dividing the derailment accident data into a basic event, a middle event and a top event; and converting the basic event into a root node of the Bayesian network, converting the intermediate event into an intermediate node of the Bayesian network, and converting the top event into a leaf node of the Bayesian network.
3. The Bayesian network-based train derailment accident assessment method for the railway turnout zone, according to claim 2, wherein: the defining interrelations between the key factor variables includes: defining the root factor which directly influences whether the train derailment accident happens or not and causes the train derailment accident as the basic event; defining factors affecting the occurrence of the basic event as the intermediate event; the result of all intermediate events acting together is defined as the top event.
4. The Bayesian network-based train derailment accident assessment method for the railway turnout zone, according to claim 1, is characterized in that: the defining variables determine the sequencing of the nodes of the Bayesian network, and the establishing of the topological relation of the Bayesian network comprises the following steps: sequencing and grading each node, and defining variable nodes with a limited set of mutual exclusion states as identification root nodes or intermediate nodes to represent identified dangers; and developing fault logic through conditional probability distribution, and establishing a Bayesian network topology to describe conditional independence relations of the definition variables.
5. The Bayesian network-based train derailment accident assessment method for the railway turnout zone, according to claim 1, is characterized in that: the learning to obtain probability distribution of each node of the grid and carry out sensitivity analysis, and the implementation of train derailment risk assessment in the railway turnout area comprises the following steps:
compiling a machine learning language based on the data sample, and performing parameter learning and structure learning on the Bayesian network according to the sample and the prior information;
the network nodes are connected with each other according to the causal association relationship to form a directed acyclic graph, and the dependency association relationship between the given Bayesian network structure nodes is quantified;
and inputting the prior information of each node into a Bayesian model, carrying out inference calculation on the conditional probability distribution of any node variable in the network node, and endowing the obtained conditional probability table to the determined Bayesian network topology structure.
6. The Bayesian network-based train derailment accident assessment method for the railway turnout zone, according to claim 3, wherein: the intermediate events comprise natural environment factors, poor wheel-rail relation, structural failure and human factors; basic events affecting the natural environmental factors include rainstorms, debris flows, strong winds, and earthquakes; basic events affecting the wheel rail badness comprise point rail reduction value, wheel rail abrasion, steel rail joint, wheel diameter difference and geometric configuration badness; the basic events affecting the structural failure include poor geometry, rail break, axle fatigue, fastener failure, and electrical service switching device failure; the basic events that affect the human factors include electrical service switching device failure, human damage, and improper driver handling.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011234659.5A CN112465304A (en) | 2020-11-07 | 2020-11-07 | Railway turnout area train derailment accident assessment method based on Bayesian network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011234659.5A CN112465304A (en) | 2020-11-07 | 2020-11-07 | Railway turnout area train derailment accident assessment method based on Bayesian network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112465304A true CN112465304A (en) | 2021-03-09 |
Family
ID=74825955
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011234659.5A Pending CN112465304A (en) | 2020-11-07 | 2020-11-07 | Railway turnout area train derailment accident assessment method based on Bayesian network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112465304A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113793241A (en) * | 2021-08-20 | 2021-12-14 | 北京交通大学 | Deep learning-based railway emergency situation deduction method |
| CN113968262A (en) * | 2021-07-15 | 2022-01-25 | 中国铁道科学研究院集团有限公司铁道建筑研究所 | Online testing and evaluating method for track unit state |
| CN114889678A (en) * | 2022-02-23 | 2022-08-12 | 北京交通大学 | Railway station lane safety collaborative early warning method based on dynamic Bayes |
| CN116739345A (en) * | 2023-06-08 | 2023-09-12 | 南京工业大学 | Real-time evaluation method for possibility of dangerous chemical road transportation accident |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105045975A (en) * | 2015-06-30 | 2015-11-11 | 北京师范大学 | Bayesian network model based risk evaluation method for road transportation accident |
| CN109657880A (en) * | 2019-01-09 | 2019-04-19 | 中交信息技术国家工程实验室有限公司 | A kind of Collision Accidents of Ships grade prediction technique and system based on Bayesian network |
| CN110059963A (en) * | 2019-04-20 | 2019-07-26 | 北京交通大学 | A kind of tunnel risk evaluating method based on fuzzy polymorphism Bayesian network |
| CN110991855A (en) * | 2019-11-28 | 2020-04-10 | 西南交通大学 | Bayesian network-based high-speed railway risk assessment method |
-
2020
- 2020-11-07 CN CN202011234659.5A patent/CN112465304A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105045975A (en) * | 2015-06-30 | 2015-11-11 | 北京师范大学 | Bayesian network model based risk evaluation method for road transportation accident |
| CN109657880A (en) * | 2019-01-09 | 2019-04-19 | 中交信息技术国家工程实验室有限公司 | A kind of Collision Accidents of Ships grade prediction technique and system based on Bayesian network |
| CN110059963A (en) * | 2019-04-20 | 2019-07-26 | 北京交通大学 | A kind of tunnel risk evaluating method based on fuzzy polymorphism Bayesian network |
| CN110991855A (en) * | 2019-11-28 | 2020-04-10 | 西南交通大学 | Bayesian network-based high-speed railway risk assessment method |
Non-Patent Citations (1)
| Title |
|---|
| 安贺路: "铁路站内脱轨事故分析与预警关键技术研究", 《中国优秀硕士学位论文全文数据库-工程科技Ⅱ辑》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113968262A (en) * | 2021-07-15 | 2022-01-25 | 中国铁道科学研究院集团有限公司铁道建筑研究所 | Online testing and evaluating method for track unit state |
| CN113793241A (en) * | 2021-08-20 | 2021-12-14 | 北京交通大学 | Deep learning-based railway emergency situation deduction method |
| CN113793241B (en) * | 2021-08-20 | 2024-02-09 | 北京交通大学 | Railway emergency situation deduction method based on deep learning |
| CN114889678A (en) * | 2022-02-23 | 2022-08-12 | 北京交通大学 | Railway station lane safety collaborative early warning method based on dynamic Bayes |
| CN114889678B (en) * | 2022-02-23 | 2023-08-11 | 北京交通大学 | Railway station line safety cooperative early warning method based on dynamic Bayesian |
| CN116739345A (en) * | 2023-06-08 | 2023-09-12 | 南京工业大学 | Real-time evaluation method for possibility of dangerous chemical road transportation accident |
| CN116739345B (en) * | 2023-06-08 | 2024-03-22 | 南京工业大学 | Real-time evaluation method for possibility of dangerous chemical road transportation accident |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112465304A (en) | Railway turnout area train derailment accident assessment method based on Bayesian network | |
| Zhou et al. | A slim integrated with empirical study and network analysis for human error assessment in the railway driving process | |
| CN104298881A (en) | Bayesian network model based public transit environment dynamic change forecasting method | |
| Liang et al. | Risk analysis on level crossings using a causal Bayesian network based approach | |
| Wang et al. | Modelling confidence in railway safety case | |
| Fourie et al. | A modelling framework for railway infrastructure reliability analysis | |
| Cao et al. | A study of risk relevance reasoning based on a context ontology of railway accidents | |
| Dowd et al. | A decision-making framework for maintenance and modernization of transportation infrastructure | |
| Liang et al. | A risk assessment study on accidents at French level crossings using Bayesian belief networks | |
| CN115938124A (en) | Urban rail transit emergency influence prediction method, system and product | |
| Moghayedi et al. | Predicting the impact size of uncertainty events on construction cost and time of highway projects using ANFIS technique | |
| Rangra et al. | Human reliability assessment under uncertainty–towards a formal method | |
| Grandhi et al. | An estimation framework to quantify railway disruption parameters | |
| Awad et al. | Predicting urban rail transit safety via artificial neural networks | |
| Di Graziano et al. | A risk-based decision support system in local railways management | |
| Rangra et al. | On the study of human reliability in transportation systems of systems | |
| Dunea et al. | Fuzzy inference systems for estimation of air quality index | |
| Zhu | A system-of-systems framework for assessment of resilience in complex construction projects | |
| Vagnoli et al. | A fuzzy-based Bayesian Belief Network approach for railway bridge condition monitoring and fault detection | |
| Hamdan et al. | A knowledge-based Approach for the Assessment of Damages to Constructions | |
| CN115600695A (en) | Fault diagnosis method of metering equipment | |
| KR20230149438A (en) | System for supporting decision for railway safety | |
| Zhu et al. | Reliability analysis of metro vehicles bogie system based on fuzzy fault tree | |
| Bouillaut et al. | Optimal metro-rail maintenance strategy using multi-nets modeling | |
| Bouillaut et al. | Dynamic Bayesian networks modelling maintenance strategies: prevention of broken rails |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210309 |