CN115438867A - Coal mine roof accident risk prediction method - Google Patents
Coal mine roof accident risk prediction method Download PDFInfo
- Publication number
- CN115438867A CN115438867A CN202211114738.1A CN202211114738A CN115438867A CN 115438867 A CN115438867 A CN 115438867A CN 202211114738 A CN202211114738 A CN 202211114738A CN 115438867 A CN115438867 A CN 115438867A
- Authority
- CN
- China
- Prior art keywords
- fuzzy
- fault
- probability
- root node
- node
- 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 55
- 239000003245 coal Substances 0.000 title claims abstract description 35
- 230000002776 aggregation Effects 0.000 claims abstract description 10
- 238000004220 aggregation Methods 0.000 claims abstract description 10
- 238000012545 processing Methods 0.000 claims abstract description 6
- 239000011435 rock Substances 0.000 claims description 23
- 238000010276 construction Methods 0.000 claims description 10
- 238000010206 sensitivity analysis Methods 0.000 claims description 9
- 230000008569 process Effects 0.000 claims description 8
- 238000010586 diagram Methods 0.000 claims description 7
- 238000013461 design Methods 0.000 claims description 5
- 238000004873 anchoring Methods 0.000 claims description 4
- 238000004590 computer program Methods 0.000 claims description 4
- 230000008030 elimination Effects 0.000 claims description 4
- 238000003379 elimination reaction Methods 0.000 claims description 4
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 4
- 238000009933 burial Methods 0.000 claims description 3
- 125000004122 cyclic group Chemical group 0.000 claims description 3
- 238000009826 distribution Methods 0.000 claims description 3
- 239000000463 material Substances 0.000 claims description 3
- 238000005065 mining Methods 0.000 claims description 3
- 230000003313 weakening effect Effects 0.000 claims description 3
- 238000003860 storage Methods 0.000 claims description 2
- 230000010415 tropism Effects 0.000 claims description 2
- 238000011156 evaluation Methods 0.000 abstract description 5
- 230000007547 defect Effects 0.000 abstract description 4
- 238000004364 calculation method Methods 0.000 abstract description 3
- 238000004458 analytical method Methods 0.000 abstract description 2
- 208000010392 Bone Fractures Diseases 0.000 description 2
- 206010017076 Fracture Diseases 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000001131 transforming effect Effects 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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/901—Indexing; Data structures therefor; Storage structures
- G06F16/9027—Trees
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/04—Inference or reasoning models
- G06N5/042—Backward inferencing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/04—Inference or reasoning models
- G06N5/046—Forward inferencing; Production systems
-
- 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
- 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
- G06Q50/02—Agriculture; Fishing; Forestry; Mining
-
- 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
- G06Q50/10—Services
- G06Q50/26—Government or public services
- G06Q50/265—Personal security, identity or safety
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)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Software Systems (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Health & Medical Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Educational Administration (AREA)
- Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Primary Health Care (AREA)
- Animal Husbandry (AREA)
- Agronomy & Crop Science (AREA)
- Marine Sciences & Fisheries (AREA)
- Mining & Mineral Resources (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Security & Cryptography (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a coal mine roof accident risk prediction method, which comprises the following steps of S1, constructing a T-S fuzzy fault tree model with multiple factors; s2, converting the existing T-S fuzzy fault tree into a Bayesian network model with an annular graph; s3, carrying out consistency processing on the semantic values of all the root nodes by a similarity aggregation method; s4, carrying out forward inference on accident risks through a Bayesian network model; and S5, reasoning to obtain the fault probability of the root node and main influence factors S6 influencing the fault of the leaf nodes, and carrying out comprehensive analysis and evaluation on the coal mine roof accident risk according to the fuzzy membership degree of the root node and the fault probability of the leaf nodes. The invention combines the T-S fuzzy fault tree method and the Bayesian network method, and makes up the defect that the T-S fuzzy fault tree method can only calculate the probability of the intermediate event and the top event layer by using the simple logic calculation function of the Bayesian network, thereby reducing the workload of a complex system.
Description
Technical Field
The invention belongs to the field of coal mine safety, coal mine roof accident risk evaluation and artificial intelligence, and particularly relates to a coal mine roof accident risk prediction method based on a T-S fuzzy fault tree and a Bayesian network.
Background
Due to complex changes of geological conditions and extreme uncertainty of surrounding environment, coal mining faces a plurality of safety problems, and coal and gas outburst, rock burst, flood, fire, roof and the like are common. The number of accidents and the number of death people of the coal mine roof are far higher than accidents such as gas, water inrush and fire disasters from the statistical data. The current situation of frequent coal mine accidents not only poses great threat to the life and property safety of practitioners, but also has obvious influence on the energy safety of China. Therefore, the method for predicting the coal mine roadway roof accident risk has very important practical significance for guiding coal mine safety production.
The T-S fuzzy fault tree is used as an effective tool for researching the stability and the reliability of a large complex system, can effectively express the relation between accidents, and can comprehensively consider the influence of different fault states on the system by introducing a fuzzy theory. However, the T-S fuzzy fault tree can only calculate layer by layer when calculating the probability of the intermediate event and the top event, and has large workload for a complicated system, and in addition, the T-S fuzzy fault tree does not have a reverse reasoning function, thereby being not beneficial to the practical application of engineering. In contrast, the bayesian network has certain advantages in terms of the logicality and simplicity of calculation. How to make full use of the advantages of the two methods to organically combine the two methods is explored for realizing the coal mine roof accident risk prediction.
Disclosure of Invention
The method can overcome the defects of the prior art and provide an evaluation method for risk evaluation and prediction of the coal mine roof accidents. The method combines the T-S fuzzy fault tree method and the Bayesian network method for use, overcomes the defects of two single methods, and realizes real-time dynamic risk prediction of coal mine roof accidents.
The invention discloses a coal mine roof accident risk prediction method, which comprises the following basic steps:
s1, starting from disaster factors of coal mine roof accidents, constructing a T-S fuzzy fault tree model with various factors;
s2, converting the existing T-S fuzzy fault tree into a Bayesian network model with an annular diagram;
s3, carrying out consistency processing on the semantic values of the root nodes by a similarity aggregation method to calculate the fault probability of the root nodes, and converting the obtained fuzzy number set into fuzzy failure rate;
s4, carrying out forward inference on the accident risk through a Bayesian network model, namely inferring the fault probability of the leaf nodes according to the obtained root node fuzzy failure rate;
s5, sensitivity analysis is carried out by calculating the fuzzy importance of the root node under the fault state of the leaf node, namely the risk occurrence probability of the root node, and the fault probability of the root node and main influence factors influencing the fault occurrence of the leaf node are obtained through reverse reasoning;
and S6, comprehensively analyzing and evaluating the accident risk of the coal mine roof according to the fuzzy membership of the root node and the probability of the failure of the leaf node.
Further, in the step S1, the disaster causing factors of the coal mine roof accident include three factors of environment, management and support, and the construction process of the T-S fuzzy fault tree model specifically includes the following steps:
s11, disaster factors influencing the roof accident of the coal mine are summarized into three factors of environment, management and support, wherein the environment factors comprise three intermediate events of surrounding rock strength, dynamic pressure disturbance, surrounding rock stress and the like, the management factors have no intermediate event, and the intermediate events of the support factors comprise unreasonable support design, low support construction level, weakening of an anchoring body and the like.
S12, basic events are basically searched according to the middle events, the basic events of the surrounding rock strength are rock properties and surrounding rock structures, the basic events of dynamic pressure disturbance are impact tendency and mining disturbance of a working face, the basic events of the surrounding rock stress include roadway burial depth and geological structure, the basic events of management factors are that safety management measures are not executed in place, personnel are not trained in place, the basic events with unreasonable support design are that support materials are selected improperly, support parameters are selected unreasonably, the basic events with low support construction level are that other construction quality is not up to standard, anchor prestress is insufficient, support is not timely, and the basic events with weakened anchor bodies are that anchor rods and anchor cables break, the surrounding rock develops cracks and the surrounding rock contains water.
And constructing the T-S fuzzy fault tree according to the T-S gate logic rules of the top event, the middle event and the basic event.
Further, in the step S2, converting the existing T-S fuzzy fault tree into a bayesian network model with a cyclic graph specifically includes the following steps:
s21, according to a basic model of a traditional Bayesian network, leaf nodes, intermediate nodes and root nodes of the Bayesian network correspond to top events, intermediate events and bottom events of a T-S fuzzy fault tree respectively, if a plurality of identical events exist in the T-S fuzzy fault tree, only one node needs to be established in the Bayesian network, and finally the logical property of the T-S fuzzy fault tree is ensured to be consistent with the tropism of the Bayesian network;
and S22, carrying out conditional probability assignment on all intermediate nodes of the Bayesian network in the S11 and the S12 to obtain a conditional probability table of the intermediate nodes.
Further, in step S3, an expert opinion method is used for calculating the root node fault probability, and in order to reduce the influence of the personal subjectivity of experts, consistency fuzzification processing is performed on expert evaluation opinions by a similarity aggregation method, which specifically includes the following steps:
s31, each expert gives a corresponding semantic value to an event to be evaluated, and converts the semantic value into a labeled triangular fuzzy number;
s32, calculating the similarity of any two expert opinions;
s33, measuring the average consistency of experts;
s34, calculating the relative consistency of each expert;
s35, calculating a consistency coefficient of an expert;
s36, calculating an aggregation result of the fuzzy opinions;
s37, converting the fuzzy number into a fuzzy possibility score;
and S38, converting the Fuzzy Possibility Score (FPS) into Fuzzy Failure Rate (FFR).
Further, in step S4, the leaf node fault probability is inferred according to the obtained root node fuzzy failure rate, and forward inference of accident risk is performed, specifically including the following steps:
s41, according to the fault probability of the root node or the current fault state, combining Bayes joint probability distribution and a forward reasoning formula, and obtaining the fault probability of the leaf node by using a barrel elimination method;
s42, calculating the probability importance (key importance) of the leaf node corresponding to the root node in a certain fault state, and carrying out sensitivity analysis according to the probability importance;
s43, according to the probability importance (key importance) of the leaf node corresponding to the root node in a certain fault state, the probability importance (key importance) of the leaf node corresponding to the root node in all different fault states can be calculated, and therefore the influence of the root node event on the leaf node event is analyzed.
Further, in step S5, sensitivity analysis is performed by calculating the fuzzy importance of the root node in the leaf node failure state, that is, the risk occurrence probability of the root node, and reverse reasoning is performed to obtain the failure probability of the root node and the main influence factors influencing the failure of the leaf node, which mainly includes the following steps:
s51, knowing the fault state of the leaf node, and applying a Bayes formula to obtain the posterior probability of the root node at the moment;
s52, analyzing the fault probability of the root node through the fault probability of the leaf node to obtain main influence factors influencing the fault of the leaf node.
According to another aspect of the present invention, there is provided a computer readable storage medium having stored thereon a computer program which, when executed by a processor, carries out the steps in the coal mine roof accident risk prediction method of the present invention.
According to a further aspect of the present invention there is provided a computer apparatus comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor when executing the program implementing the steps in the coal mine roof accident risk prediction method of the present invention.
The invention has the beneficial effects that:
(1) The T-S fuzzy fault tree method and the Bayesian network method are combined, the defect that the T-S fuzzy fault tree method can only calculate the probability of the intermediate event and the top event layer by layer is made up by using the simple logic calculation function of the Bayesian network, and the workload of a complex system is reduced.
(2) In the process of acquiring the Bayesian root node fault probability, in order to avoid the difference of different experts in the aspects of professional knowledge, personal experience, subjective preference and the like, the expert opinions are fuzzified by a similarity aggregation method, so that the consistency of the expert opinions is ensured.
(3) The two-way reasoning and sensitivity analysis advantages of Bayes are fully utilized, and the occurrence probability of the roof accident is calculated through forward reasoning; obtaining main factors influencing the roof accident through sensitivity analysis; and system diagnosis is carried out when the top plate is in fault through reverse reasoning.
Drawings
FIG. 1 is a schematic flow diagram of the present invention;
FIG. 2 is a schematic diagram of a T-S fuzzy fault tree model constructed according to disaster-causing factors and specific disaster-causing factors of a coal mine roof accident;
FIG. 3 is a schematic diagram of a specific method for converting an existing T-S fuzzy fault tree into a Bayesian network model with a directed graph according to the present invention;
FIG. 4 is a diagram illustrating the final transformation result of the present invention transforming the existing T-S fuzzy fault tree into the Bayesian network model with a cyclic graph.
Detailed Description
The embodiments of the present invention are explained in detail with reference to the drawings, and further explained by way of examples, which are implemented on the premise of the technical solution of the present invention, and the detailed embodiments and specific operation procedures are given, but the protection scope of the present invention is not limited to the following examples.
The invention discloses a coal mine roof accident risk prediction method based on a T-S fuzzy fault tree and a Bayesian network, which specifically comprises the following steps as shown in FIG. 1:
s1: starting from disaster factors of coal mine roof accidents, a T-S fuzzy fault tree model covering multiple factors is constructed, and the specific process is as follows:
s11, follow-up analysis is carried out by taking the coal mine roof accident as a top event, and an intermediate event influencing the coal mine roof accident is found, wherein the intermediate event found in the embodiment comprises the following steps: the method comprises the following steps of (1) environmental factors (y 1), management factors (y 2), support factors (y 3), surrounding rock strength (y 4), dynamic pressure disturbance (y 5), surrounding rock stress (y 6), unreasonable support design (y 7), low support construction level (y 8) and weakening of an anchoring body (y 9);
s12, further finding a basic event for the intermediate event, where the basic event found in this embodiment includes: rock properties (x 1), surrounding rock structures (x 2), impact tendentiousness (x 3), working face disturbance (x 4), roadway burial depth (x 5), geological structures (x 6), safety management measures (x 7), personnel training (x 8), support material type selection (x 9), support parameter selection (x 10), other construction quality (x 11), anchoring prestress (x 12), support untimely (x 13), anchor rod or anchor cable fracture (x 14), surrounding rock fracture development (x 15) and surrounding rock water content (x 16);
s13, according to the logic rule of the T-S fuzzy fault tree, a model is constructed as shown in figure 2.
S2, converting the established T-S fuzzy fault tree model into a Bayesian network model with an annular diagram, wherein the specific process comprises the following steps:
s21, respectively converting a top event, an intermediate event and a basic event in the young T-S fuzzy fault tree model with a leaf node, an intermediate node and a root node of a corresponding Bayesian network model, wherein the conversion process is as shown in FIG. 3, and the obtained model is as shown in FIG. 4;
and S22, carrying out conditional probability assignment on the intermediate node, wherein the fault state of the intermediate node is divided into three states of no fault, light fault and complete fault, and the three states are carried out by adopting a method of giving weight by an expert. Taking the intermediate node y9 as an example, the root node of the intermediate node y9 includes x14, x15, and x16, and when all three root nodes are fault-free, the conditional probability that the intermediate node y9 is fault-free is 1, and the probabilities of a light fault and a complete fault are 0, and so on. In the same way, the conditional probabilities of all intermediate nodes in different fault states can be obtained.
S3, through a similarity aggregation method, carrying out consistency processing on semantic values of all root nodes by experts to calculate the fault probability of the root nodes, and converting the obtained fuzzy number set into fuzzy failure rate, wherein the specific process is as follows:
s31, each expert Ek (k =1,2, …, M) gives a semantic value to the event to be evaluated and converts it into an annotated triangular blur number. The semantic value given by the expert and the corresponding triangular fuzzy number are defined as follows: the risk level is extremely low- (0,0,0.1), very low- (0,0.1,0.2), very low- (0.1,0.2,0.3), low- (0.2,0.3,0.4), low- (0.3,0.4,0.5), medium- (0.4,0.5,0.6), high- (0.5,0.6,0.7), high- (0.6,0.7,0.8), very high- (0.7,0.8,0.9), very high- (0.8,0.9,1), extremely high- (0.9,1,1);
s32, calculating the similarity of the comments Ru = (Ru 1, ru2, ru 3) and Ru = (rv 1, rv2, rv 3) of any two experts Eu (u =1,2, …, M) and Ev (v =1,2, …, M)
S33, measuring the average consistency of experts
S34, calculating the phase of each expertFor consistency
S35, calculating a consistency coefficient CC (Eu) = beta.w (Eu) + (1-beta). RA (Eu) of an expert;
s36, calculating the aggregation result of the fuzzy opinions
S37, converting the fuzzy number into a fuzzy possibility score
S38, converting the Fuzzy Possibility Score (FPS) into Fuzzy Failure Rate (FFR),
wherein
S4, forward reasoning is carried out through the Bayesian network, namely the fault probability of the leaf nodes is deduced according to the fuzzy failure rate of the root nodes, and the specific flow is as follows:
s41, if the fault probability P (xi) of the fault state of the root node is known ai ) Combining Bayes joint probability distribution and a forward reasoning formula, the fault probability of T = Tq can be obtained by using a barrel elimination method,
wherein λ (T) and λ (yj) are the father node sets of leaf node T and intermediate node yj, respectively;
s42, if the current fault state of the root node xi is xi '= (x 1', x2', …, xn'), obtaining the occurrence probability when T = Tq by using the barrel elimination method in the same way
Wherein the content of the first and second substances,
and the membership degree of the fault state of the root node of the conditional probability table of the Bayesian network when the root node xi is in the current fault state xi' is shown. When xi = xi ai When, the key importance for T = Tq is
Sensitivity analysis was performed in this manner.
S43, comprehensively considering the importance of all fault states of the root node xi, and obtaining the key importance of the root node xi to the leaf node T as
S5, carrying out reverse reasoning by calculating the fuzzy importance of the root node in the leaf node fault state, wherein the specific process comprises the following steps:
s51, under the condition that the fault state of the known leaf node T is Tq, the root node T = Tq can be obtained by applying a Bayesian formula
A posteriori probability of
Wherein the content of the first and second substances,
xi = xi when T = Tq ai The posterior probability fuzzy subset of (1); and the occurrence probability when P (T = Tq) is T = Tq.
And step 52, analyzing main factors influencing the failure of the leaf nodes according to the reverse reasoning result.
The above-mentioned embodiment is only a preferred embodiment of the present invention, but it is not intended to limit the present invention. Various changes and modifications may be made by those skilled in the relevant art and researchers without departing from the spirit and scope of the invention. Therefore, all technical solutions obtained by means of equivalent replacement or equivalent transformation fall within the protection scope of the present invention.
Claims (8)
1. A coal mine roof accident risk prediction method is characterized by comprising the following steps:
s1, starting from disaster factors of coal mine roof accidents, constructing a T-S fuzzy fault tree model with multiple factors;
s2, converting the existing T-S fuzzy fault tree into a Bayesian network model with an annular diagram;
s3, carrying out consistency processing on the semantic values of all root nodes by a similarity aggregation method to calculate the fault probability of the root nodes, and converting the obtained fuzzy number set into fuzzy failure rate;
s4, carrying out forward inference on the accident risk through a Bayesian network model, namely inferring the fault probability of the leaf nodes according to the obtained root node fuzzy failure rate;
s5, sensitivity analysis is carried out by calculating the fuzzy importance of the root node under the fault state of the leaf node, namely the risk occurrence probability of the root node, and the fault probability of the root node and main influence factors influencing the fault occurrence of the leaf node are obtained through reverse reasoning;
and S6, comprehensively analyzing and evaluating the accident risk of the coal mine roof according to the fuzzy membership of the root node and the probability of the failure of the leaf node.
2. The method according to claim 1, wherein in step S1, the disaster causing factors of the coal mine roof accident include three factors of environment, management and support, and the construction process of the T-S fuzzy fault tree model specifically includes the following steps:
s11, summarizing disaster factors influencing a roof accident coal mine roof accident into three factors of environment, management and support, wherein the environment factors comprise three intermediate events of surrounding rock strength, dynamic pressure disturbance, surrounding rock stress and the like, the management factors have no intermediate event, and the intermediate events of the support factors comprise unreasonable support design, low support construction level and weakening of an anchoring body;
s12, basic events are basically searched according to the middle events, the basic events of the surrounding rock strength are rock properties and surrounding rock structures, the basic events of dynamic pressure disturbance are impact tendency and mining disturbance of a working face, the basic events of the surrounding rock stress comprise roadway burial depth and geological structure, the basic events of management factors are that safety management measures are not executed in place, personnel are not trained in place, the basic events with unreasonable support design are that support materials are not selected properly and support parameters are selected unreasonably, the basic events with low support construction level are that other construction quality is not up to standard, anchor prestress is insufficient and support is not timely, and the basic events with weakened anchor bodies are that anchor rods and anchor cables are broken, the cracks of the surrounding rocks develop and the surrounding rocks contain water; and constructing the T-S fuzzy fault tree according to the T-S gate logic rules of the top event, the middle event and the basic event.
3. The method according to claim 2, wherein in the step S2, the step of converting the existing T-S fuzzy fault tree into the bayesian network model with a cyclic graph specifically comprises the steps of:
s21, according to a basic model of a traditional Bayesian network, leaf nodes, intermediate nodes and root nodes of the Bayesian network correspond to top events, intermediate events and bottom events of a T-S fuzzy fault tree respectively, if a plurality of identical events exist in the T-S fuzzy fault tree, only one node needs to be established in the Bayesian network, and finally the logical property of the T-S fuzzy fault tree is ensured to be consistent with the tropism of the Bayesian network;
and S22, carrying out conditional probability assignment on all intermediate nodes of the Bayesian network in the S11 and the S12 to obtain a conditional probability table of the intermediate nodes.
4. The method according to claim 1, wherein in step S3, the root node failure probability is calculated by using an expert opinion method, and in order to reduce the influence of personal subjectivity of experts, the expert opinion is subjected to consistency fuzzification processing by using a similarity aggregation method, which specifically includes the following steps:
s31, each expert gives a corresponding semantic value to an event to be evaluated, and converts the semantic value into an annotated triangular fuzzy number;
s32, calculating the similarity of any two expert opinions;
s33, measuring the average consistency of experts;
s34, calculating the relative consistency of each expert;
s35, calculating a consistency coefficient of an expert;
s36, calculating an aggregation result of the fuzzy opinions;
s37, converting the fuzzy number into a fuzzy possibility score;
and S38, converting the fuzzy possibility score into fuzzy failure rate.
5. The method according to claim 1, wherein in step S4, the leaf node fault probability is inferred according to the obtained root node fuzzy failure rate, and the accident risk forward inference is performed, specifically including the following steps:
s41, according to the fault probability of the root node or the current fault state, combining Bayes joint probability distribution and a forward reasoning formula, and obtaining the fault probability of the leaf node by using a barrel elimination method;
s42, calculating the probability importance of the leaf node corresponding to the root node in a certain fault state, and carrying out sensitivity analysis according to the probability importance;
s43, calculating the probability importance of leaf nodes corresponding to the root node in different fault states according to the probability importance of the leaf nodes corresponding to the root node in a certain fault state, and analyzing the influence of the root node event on the leaf node event.
6. The method according to claim 1, wherein in step S5, sensitivity analysis is performed by calculating fuzzy importance of the root node in the leaf node failure state, i.e. risk occurrence probability thereof, and backward reasoning is performed to obtain failure probability of the root node and main influence factors influencing the failure of the leaf node, including the following steps:
s51, knowing the fault state of the leaf node, and applying a Bayes formula to obtain the posterior probability of the root node at the moment;
s52, analyzing the fault probability of the root node through the fault probability of the leaf node to obtain main influence factors influencing the fault of the leaf node.
7. A computer-readable storage medium having stored thereon a computer program, characterized in that: the program when executed by a processor performs the steps in a coal mine roof accident risk prediction method of any one of claims 1 to 6.
8. A computer apparatus comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executing the program performs the steps in the coal mine roof accident risk prediction method of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211114738.1A CN115438867A (en) | 2022-09-14 | 2022-09-14 | Coal mine roof accident risk prediction method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211114738.1A CN115438867A (en) | 2022-09-14 | 2022-09-14 | Coal mine roof accident risk prediction method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115438867A true CN115438867A (en) | 2022-12-06 |
Family
ID=84247661
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211114738.1A Pending CN115438867A (en) | 2022-09-14 | 2022-09-14 | Coal mine roof accident risk prediction method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115438867A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117196350A (en) * | 2023-11-06 | 2023-12-08 | 天津市地质研究和海洋地质中心 | Mine geological environment characteristic monitoring and recovery treatment method and system |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107045584A (en) * | 2017-05-11 | 2017-08-15 | 河海大学 | A kind of power frequency vibration abnormal failure diagnostic method suitable for water pump rotor system |
| CN109214625A (en) * | 2017-07-03 | 2019-01-15 | 中国石油化工股份有限公司 | A kind of oil tank evaluation method for failure and device |
| 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 |
| CN114036857A (en) * | 2021-11-26 | 2022-02-11 | 天津大学 | Flexible riser risk evaluation method based on quantitative analysis and probabilistic reasoning |
| CN114372405A (en) * | 2021-11-29 | 2022-04-19 | 海洋石油工程股份有限公司 | Method for reliability evaluation and fault prediction of underwater manifold |
| CN114429252A (en) * | 2020-09-09 | 2022-05-03 | 中国石油化工股份有限公司 | Method and equipment for evaluating dynamic risk of underground facility of gas storage reservoir |
| CN114564881A (en) * | 2022-01-26 | 2022-05-31 | 天津大学 | Drilling riser fracture failure risk evaluation method based on fuzzy Bayesian network |
| CN114580150A (en) * | 2022-01-27 | 2022-06-03 | 天津大学 | Submarine pipeline reliability evaluation method based on mesopic fuzzy Bayesian network |
| CN115018334A (en) * | 2022-06-15 | 2022-09-06 | 湖南科技大学 | Fuzzy Bayesian network-based gas explosion risk assessment method |
-
2022
- 2022-09-14 CN CN202211114738.1A patent/CN115438867A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107045584A (en) * | 2017-05-11 | 2017-08-15 | 河海大学 | A kind of power frequency vibration abnormal failure diagnostic method suitable for water pump rotor system |
| CN109214625A (en) * | 2017-07-03 | 2019-01-15 | 中国石油化工股份有限公司 | A kind of oil tank evaluation method for failure and device |
| 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 |
| CN114429252A (en) * | 2020-09-09 | 2022-05-03 | 中国石油化工股份有限公司 | Method and equipment for evaluating dynamic risk of underground facility of gas storage reservoir |
| CN114036857A (en) * | 2021-11-26 | 2022-02-11 | 天津大学 | Flexible riser risk evaluation method based on quantitative analysis and probabilistic reasoning |
| CN114372405A (en) * | 2021-11-29 | 2022-04-19 | 海洋石油工程股份有限公司 | Method for reliability evaluation and fault prediction of underwater manifold |
| CN114564881A (en) * | 2022-01-26 | 2022-05-31 | 天津大学 | Drilling riser fracture failure risk evaluation method based on fuzzy Bayesian network |
| CN114580150A (en) * | 2022-01-27 | 2022-06-03 | 天津大学 | Submarine pipeline reliability evaluation method based on mesopic fuzzy Bayesian network |
| CN115018334A (en) * | 2022-06-15 | 2022-09-06 | 湖南科技大学 | Fuzzy Bayesian network-based gas explosion risk assessment method |
Non-Patent Citations (2)
| Title |
|---|
| 刘文生等: "贝叶斯网络在煤矿生产系统安全评价中的应用", 《工矿自动化》 * |
| 李海丽: "矿山顶板事故的FTA-Fuzzy-venism分析方法探究", 《安全与环境工程》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117196350A (en) * | 2023-11-06 | 2023-12-08 | 天津市地质研究和海洋地质中心 | Mine geological environment characteristic monitoring and recovery treatment method and system |
| CN117196350B (en) * | 2023-11-06 | 2024-01-05 | 天津市地质研究和海洋地质中心 | Mine geological environment characteristic monitoring and recovery treatment method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Xing et al. | Ontology for safety risk identification in metro construction | |
| Xie et al. | A novel risk evaluation method for fire and explosion accidents in oil depots using bow-tie analysis and risk matrix analysis method based on cloud model theory | |
| CN102521710B (en) | A kind of online risk evaluating system of Construction Quality safety | |
| CN106481344A (en) | A kind of balancing earth-pressure shielding machine tunnel piercing parameter intelligent control method | |
| Şen | Supervised fuzzy logic modeling for building earthquake hazard assessment | |
| CN115438867A (en) | Coal mine roof accident risk prediction method | |
| Zhang et al. | Resilience assessment approach of mechanical structure combining finite element models and dynamic Bayesian networks | |
| Li et al. | Fuzzy risk prediction of roof fall and rib spalling: based on FFTA–DFCE and risk matrix methods | |
| Feng et al. | Reliability evaluation of gantry cranes based on fault tree analysis and Bayesian network | |
| CN115018334A (en) | Fuzzy Bayesian network-based gas explosion risk assessment method | |
| CN114036857A (en) | Flexible riser risk evaluation method based on quantitative analysis and probabilistic reasoning | |
| Cai et al. | Quantitative risk assessment methodology of installation process for deepwater oil and gas equipment | |
| CN114881396A (en) | Tunnel collapse risk assessment method based on AHP and TOPSIS | |
| CN114564881A (en) | Drilling riser fracture failure risk evaluation method based on fuzzy Bayesian network | |
| CN117196296A (en) | Railway weather disaster risk prevention and control method and system | |
| Li et al. | A dynamic combination algorithm based scenario construction theory for mine water-inrush accident multi-objective optimization | |
| Wang et al. | Risk assessment of coal mine safety production management activities based on FMEA-BN | |
| Song et al. | Quality Risk Management Algorithm for Cold Storage Construction Based on Bayesian Networks | |
| Garcia et al. | Dams Safety Index (DSI): A reassessment of the parameters of analysis | |
| Meng et al. | A failure probability evaluation method for the collapse of drill-blast tunnels based on a multistate cloud Bayesian network | |
| CN112464576A (en) | Dam risk assessment method and equipment based on Bayesian network | |
| Zhu et al. | A methodology for quantitative analysis of non-determinacy relationships using fuzzy logic in Bayesian networks | |
| Mahmood et al. | Optimizing natural gas pipeline risk assessment using hybrid fuzzy bayesian networks and expert elicitation for effective decision-making strategies | |
| Harirchian | Improved rapid assessment of earthquake hazard safety of existing buildings using a hierarchical type-2 fuzzy logic model | |
| Zhen et al. | Hazard identification and risk decision-making system of tailings storage facilities based on complex networks |
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 |
Application publication date: 20221206 |
|
| RJ01 | Rejection of invention patent application after publication |