CN116167620A - Multi-dimensional risk dynamic evaluation method and system for large-scale vehicle exhibition fire disaster - Google Patents
Multi-dimensional risk dynamic evaluation method and system for large-scale vehicle exhibition fire disaster Download PDFInfo
- Publication number
- CN116167620A CN116167620A CN202310172973.2A CN202310172973A CN116167620A CN 116167620 A CN116167620 A CN 116167620A CN 202310172973 A CN202310172973 A CN 202310172973A CN 116167620 A CN116167620 A CN 116167620A
- Authority
- CN
- China
- Prior art keywords
- fire
- vehicle
- risk
- determining
- dynamic
- 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
- 238000011156 evaluation Methods 0.000 title description 8
- 206010000369 Accident Diseases 0.000 claims abstract description 79
- 238000000034 method Methods 0.000 claims abstract description 55
- 239000008186 active pharmaceutical agent Substances 0.000 claims abstract description 19
- 238000005094 computer simulation Methods 0.000 claims abstract description 17
- 230000004927 fusion Effects 0.000 claims abstract description 16
- 230000007704 transition Effects 0.000 claims abstract description 10
- 238000005516 engineering process Methods 0.000 claims abstract description 9
- 230000009467 reduction Effects 0.000 claims description 20
- 238000004590 computer program Methods 0.000 claims description 16
- 238000002485 combustion reaction Methods 0.000 claims description 14
- 238000003860 storage Methods 0.000 claims description 12
- 230000007613 environmental effect Effects 0.000 claims description 9
- 238000013461 design Methods 0.000 claims description 7
- 238000012423 maintenance Methods 0.000 claims description 7
- 238000005192 partition Methods 0.000 claims description 7
- 230000002265 prevention Effects 0.000 claims description 7
- 239000000779 smoke Substances 0.000 claims description 7
- 238000010276 construction Methods 0.000 claims description 4
- 230000035772 mutation Effects 0.000 claims description 4
- 230000004931 aggregating effect Effects 0.000 claims description 3
- 238000012502 risk assessment Methods 0.000 abstract description 13
- 230000035945 sensitivity Effects 0.000 abstract description 3
- 238000004422 calculation algorithm Methods 0.000 description 12
- 238000010586 diagram Methods 0.000 description 12
- 230000006870 function Effects 0.000 description 12
- 238000012545 processing Methods 0.000 description 10
- 238000004891 communication Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 7
- 230000008859 change Effects 0.000 description 5
- 238000011835 investigation Methods 0.000 description 5
- 238000004088 simulation Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 4
- 238000011160 research Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 3
- 238000011002 quantification Methods 0.000 description 3
- 238000010206 sensitivity analysis Methods 0.000 description 3
- 230000003068 static effect Effects 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000010295 mobile communication Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 230000002441 reversible effect Effects 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 230000002457 bidirectional effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000000670 limiting effect Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000005055 memory storage Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000005312 nonlinear dynamic Methods 0.000 description 1
- 238000011022 operating instruction Methods 0.000 description 1
- 238000011176 pooling Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000001681 protective effect Effects 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 230000002829 reductive effect Effects 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 238000003786 synthesis reaction 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/04—Inference or reasoning models
- G06N5/041—Abduction
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Artificial Intelligence (AREA)
- Operations Research (AREA)
- Computer Security & Cryptography (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Quality & Reliability (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a multi-dimensional risk dynamic assessment method and system for a large-scale vehicle-mounted fire disaster. The method comprises the following steps: the method comprises the steps of identifying a vehicle-mounted fire risk in multiple dimensions, determining risk factors related to vehicle-mounted fire accidents, determining risk factor related information, and establishing a dynamic Bayesian topological structure of the vehicle-mounted fire accidents; based on the state Bayesian topological structure, carrying out data fusion on expert experience weights through DS theory, determining the prior probability of a basic event, constructing a conditional probability table, and determining the occurrence probability of a vehicle-spread fire accident by utilizing the forward reasoning technology of a dynamic Bayesian network; determining the probability of occurrence of a vehicle-mounted fire accident based on the prior probability of the basic event, deeply researching the sensitivity of the Bayesian network, and determining a sensitive event; and entering a unit event accident state through the unit event initial normal working state, completing dynamic mode transition, generating a dynamic simulation model, and predicting the accident occurrence trend according to the dynamic simulation model. The invention can realize multi-dimensional, full-scale and dynamic risk assessment.
Description
Technical Field
The invention relates to the field of large-scale activity fire risk assessment, in particular to a multi-dimensional dynamic risk assessment method and system for a large-scale vehicle-mounted fire.
Background
The exhibition is taken as a green industry with high-speed development, has the characteristics of large influence, high industrial relevance and the like, not only pulls the development of regional economy, but also brings great social benefit. According to the statistical data of the statistical report of the data of the Chinese exhibition in 2021, the following steps are shown: in the industrial exhibits, the number of large-sized automobile exhibits taking passenger vehicles as the subject is the largest, reaches 569, and accounts for 15.85% of the total number of the industrial exhibits. The large-scale exhibition of a vehicle activity has the characteristics of large number of participants, high density, open places, complex conditions and the like, and the safety accidents are very easy to occur. The large-scale vehicle-mounted fire accident has the advantages of high occurrence probability, complex risk types and outstanding dynamic factors, and once the occurrence happens, secondary disasters such as crowded trampling and the like are extremely easy to cause, so that the accident consequences are serious.
At present, students at home and abroad mostly study the security risk of the exhibition industry, and the research is mainly focused on using a traditional risk analysis method; the research on the special research subject of the large-scale vehicle exhibition risk is less at the present stage, and the risk factor identification from the subjective angle is mainly focused; single type risk analysis; static semi-quantitative risk assessment. The above-mentioned disadvantages are: the risk factor identification dimension is single; the related constraint research between factors is deficient; the nonlinear dynamic problem is to be solved.
Disclosure of Invention
The invention aims to provide a multi-dimensional risk dynamic assessment method and system for a large-scale vehicle-mounted fire disaster, which are used for solving the problem that risk factors are single in identification dimension and cannot be subjected to multi-dimensional, comprehensive and dynamic risk assessment.
In order to achieve the above object, the present invention provides the following solutions:
a multi-dimensional risk dynamic assessment method for a large-scale vehicle exhibition fire disaster comprises the following steps:
completing multidimensional identification of the vehicle-mounted fire risk based on the vehicle-mounted field information, the field risk factor identification information and the historical accident risk factor summary information, and determining the related risk factors of the vehicle-mounted fire accident;
determining risk factor related information according to the fire accident related risk factors, and establishing a dynamic Bayesian topological structure of the vehicle-mounted fire accident;
based on the dynamic Bayesian topological structure, carrying out data fusion on expert experience weights through DS theory, determining the prior probability of a basic event and constructing a conditional probability table;
determining the occurrence probability of the vehicle-mounted fire accident by utilizing a forward reasoning technology of a dynamic Bayesian network according to the prior probability of the basic event and the conditional probability table;
determining a risk reduction value, an importance measure and a variation ratio according to the prior probability of the basic event and the occurrence probability of the train-show fire accident;
And entering a unit event accident state through a unit event initial normal working state based on the risk reduction value, the importance measure and the variation ratio, completing dynamic mode transition, generating a dynamic simulation model, and predicting the accident occurrence trend according to the dynamic simulation model.
Optionally, risk factor related information is determined according to the risk factors related to the fire accident, and a dynamic bayesian topological structure of the vehicle-mounted fire accident is established, which specifically comprises:
determining risk factor association information according to the fire accident related risk factors, and establishing a dynamic Bayesian initial topological structure of the vehicle-mounted fire accident;
determining content effectiveness ratio according to expert opinion and determining content effectiveness index according to expert number;
optimizing the dynamic Bayesian initial topological structure according to the content effectiveness ratio and the content effectiveness index to determine a dynamic Bayesian topological structure; the father node of the dynamic Bayesian topological structure is a car-spread fire accident, and the child node of the dynamic Bayesian topological structure comprises inflammables, ignition sources, fire spread, people, objects, environments, management, vehicle exhibit failure combustion, electrical equipment failure combustion, other inflammables, artificial ignition, environmental factors, exceeding personnel load, on-site personnel quality spread, personnel characteristic structure, hand-held fire extinguisher failure, automatic fire extinguishing system failure, fire alarm device failure, smoke prevention and exhaust system failure, lower fire resistance level of a building, insufficient fire partition design, lower fire load, fire station influence, maintenance personnel number standard rate, security personnel number standard rate, fire personnel number standard rate and management work standard failure.
Optionally, based on the dynamic bayesian topological structure, data fusion is performed on expert experience weights through a DS theory, and a basic event prior probability is determined and a conditional probability table is constructed, which specifically includes:
evaluating each node in the dynamic Bayesian topological structure, and aggregating the independent trust structures to form a final trust structure; one of the nodes is a trust structure;
determining the evidence credibility of the final trust structure based on DS theory of a weighted average method;
collecting a group of heterogeneous expert opinions, and calculating a fuzzy possible set by using a linear opinion pool method;
and determining the prior probability of the basic event according to the fuzzy possible set and constructing a conditional probability table according to expert opinion.
Optionally, the risk reduction value is:
wherein RRW (component j) is a risk reduction value;the system operation probability is;the running probability is the running probability of the system in a normal state; />Is the running state of the system; i fu is the initial state component; fu is a component; s is S j,i fu Is the component j in state i; />Is the number of states; p (S) j,i fu =1) is component j in state i; p (xj=1) is the failure probability of component j; x is x j Indicating the failure status of component j, x, as a boolean variable j =1 indicates failure, x j =0 indicates normal operation.
Optionally, the importance measure is:
wherein BIM (component j) is a measure of importance;the running probability in the system failure state.
Optionally, the mutation ratio is:
wherein the ROV (BE i ) Is a variation ratio; pi (BE) i ) For the posterior probability of BEi, θ (BE i ) A priori probability of BEi; BEi is the i-th basic event.
A multi-dimensional risk dynamic assessment system for a large-scale vehicle-mounted fire, comprising:
the vehicle-spread fire accident related risk factor determining module is used for completing multi-dimensional identification of vehicle-spread fire risks based on vehicle-spread site location information, site risk factor identification information and historical accident risk factor summary information and determining vehicle-spread fire accident related risk factors;
the dynamic Bayesian topological structure establishing module is used for determining risk factor association information according to the fire accident related risk factors and establishing a dynamic Bayesian topological structure of the vehicle-mounted fire accident;
the basic event prior probability and conditional probability table construction module is used for carrying out data fusion on expert experience weights through DS theory based on the dynamic Bayesian topological structure, determining basic event prior probability and constructing a conditional probability table;
The vehicle-spread fire accident occurrence probability determining module is used for determining the vehicle-spread fire accident occurrence probability by utilizing a forward reasoning technology of a dynamic Bayesian network according to the basic event prior probability and the conditional probability table;
the parameter determining module is used for determining a risk reduction value, an importance measure and a variation ratio according to the prior probability of the basic event and the occurrence probability of the train-show fire accident;
and the prediction module is used for entering a unit event accident state through a unit event initial normal working state based on the risk reduction value, the importance measure and the variation ratio, completing dynamic mode transition, generating a dynamic simulation model and predicting the accident occurrence trend according to the dynamic simulation model.
Optionally, the dynamic bayesian topological structure establishment module specifically includes:
the dynamic Bayesian initial topological structure establishing unit is used for determining risk factor association information according to the fire accident related risk factors and establishing a dynamic Bayesian initial topological structure of the vehicle-mounted fire accident;
the content effectiveness index determining unit is used for determining a content effectiveness ratio according to expert opinion and determining a content effectiveness index according to expert quantity;
The dynamic Bayesian topological structure determining unit is used for optimizing the dynamic Bayesian initial topological structure according to the content effectiveness ratio and the content effectiveness index to determine a dynamic Bayesian topological structure; the father node of the dynamic Bayesian topological structure is a car-spread fire accident, and the child node of the dynamic Bayesian topological structure comprises inflammables, ignition sources, fire spread, people, objects, environments, management, vehicle exhibit failure combustion, electrical equipment failure combustion, other inflammables, artificial ignition, environmental factors, exceeding personnel load, on-site personnel quality spread, personnel characteristic structure, hand-held fire extinguisher failure, automatic fire extinguishing system failure, fire alarm device failure, smoke prevention and exhaust system failure, lower fire resistance level of a building, insufficient fire partition design, lower fire load, fire station influence, maintenance personnel number standard rate, security personnel number standard rate, fire personnel number standard rate and management work standard failure.
An electronic device comprising a memory and a processor, the memory being configured to store a computer program, the processor being configured to run the computer program to cause the electronic device to perform the above-described method for dynamically assessing multi-dimensional risk of a large vehicle-show fire.
A computer readable storage medium storing a computer program which when executed by a processor implements the above-described large-scale vehicle-spread fire multi-dimensional risk dynamic assessment method.
According to the specific embodiment provided by the invention, the invention discloses the following technical effects: the invention provides a multi-dimensional risk dynamic evaluation method and a system for large-scale vehicle-mounted fire disaster, which are characterized in that risk factor identification is multi-dimensionally identified to construct a dynamic Bayesian topological structure, and objective evaluation is carried out through a DS algorithm to improve the accuracy of a predicted risk result; and further outputting a sensitive risk factor interval based on the risk reduction value, the importance measure and the mutation ratio, realizing hidden trouble investigation and rectification and change of the working direction, generating a dynamic simulation model through dynamic mode transition, predicting the accident occurrence trend, and realizing multidimensional, comprehensive and dynamic risk assessment.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions of the prior art, the drawings that are needed in the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a multi-dimensional risk dynamic assessment method for large-scale vehicle-mounted fire disaster;
FIG. 2 is a frame diagram of a multi-dimensional risk dynamic assessment method for large-scale vehicle-mounted fire disaster provided by the invention;
FIG. 3 is a dynamic Bayesian initial topology structure diagram of a large-scale vehicle-mounted fire accident;
FIG. 4 is a schematic representation of the results of sensitivity analysis using BIM and RRW metrics;
FIG. 5 is a schematic diagram of simulation results of the probability of occurrence of an accident in 24 time slices for a large-scale vehicle display system;
fig. 6 is a frame diagram of a multi-dimensional risk dynamic assessment system for large-scale vehicle-mounted fire disaster.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The invention aims to provide a multi-dimensional risk dynamic assessment method and system for a large-scale vehicle-mounted fire disaster, which can realize multi-dimensional, comprehensive and dynamic risk assessment.
In order that the above-recited objects, features and advantages of the present invention will become more readily apparent, a more particular description of the invention will be rendered by reference to the appended drawings and appended detailed description.
1-2, the invention provides a multi-dimensional dynamic risk assessment method for a large-scale vehicle-mounted fire disaster, which comprises the following steps:
step 101: and completing multidimensional identification of the vehicle-mounted fire risk based on the vehicle-mounted field information, the field risk factor identification information and the historical accident risk factor summary information, and determining the related risk factors of the vehicle-mounted fire accident.
In practical applications, the two dimensional identification analysis of the risk of "fire occurrence" and "fire intervention", including the occurrence of fire includes: inflammables (vehicle exhibit factors, electrical factors, other factors), ignition sources (human factors, physical factors, environmental factors); the fire intervention includes: fire spread (human factors, physical factors, environmental factors, management factors).
The risk factors affecting the fire accident of the large-scale vehicle show can be determined by two dimensions of fire occurrence and fire intervention according to the modes of historical accident data, field investigation, literature investigation and the like, and the table 1 is a multi-dimensional index system table of the fire accident risk of the large-scale vehicle show.
TABLE 1
Step 102: and determining risk factor related information according to the fire accident related risk factors, and establishing a dynamic Bayesian topological structure of the vehicle-mounted fire accident.
In practical applications, step 102 specifically includes: determining risk factor association information according to the fire accident related risk factors, and establishing a dynamic Bayesian initial topological structure of the vehicle-mounted fire accident; determining content effectiveness ratio according to expert opinion and determining content effectiveness index according to expert number; optimizing the dynamic Bayesian initial topological structure according to the content effectiveness ratio and the content effectiveness index to determine a dynamic Bayesian topological structure; the father node of the dynamic Bayesian topological structure is a car-spread fire accident, and the child node of the dynamic Bayesian topological structure comprises inflammables, ignition sources, fire spread, people, objects, environments, management, vehicle exhibit failure combustion, electrical equipment failure combustion, other inflammables, artificial ignition, environmental factors, exceeding personnel load, on-site personnel quality spread, personnel characteristic structure, hand-held fire extinguisher failure, automatic fire extinguishing system failure, fire alarm device failure, smoke prevention and exhaust system failure, lower fire resistance level of a building, insufficient fire partition design, lower fire load, fire station influence, maintenance personnel number standard rate, security personnel number standard rate, fire personnel number standard rate and management work standard failure.
The large-scale vehicle-spread fire accident dynamic Bayesian topological structure comprises a large-scale vehicle-spread fire accident as a father node in a Bayesian dynamic network model, wherein the large-scale vehicle-spread fire accident father node comprises the following child nodes (inflammable matters, ignition sources, fire spread, people, objects, environments, management, vehicle exhibit invalid combustion, electric equipment invalid combustion, other inflammable matters, artificial ignition, environmental factors, excess personnel load, on-site personnel quality spread, personnel characteristic structure, hand-held fire extinguisher invalid, automatic fire extinguishing system invalid, fire alarm device invalid, smoke prevention and exhaust system invalid, lower building fire resistance level, insufficient fireproof partition design, lower fire load, fire station influence, maintenance personnel quantity standard rate, safety management personnel quantity standard rate, and management work standard rate; the algorithm for optimizing the initial topological structure of the dynamic Bayesian network is specifically as follows:
n E is the number of specialists selecting the necessary options; n is the total number of experts.
The implementation standard of the initial topological structure algorithm of the optimized Bayesian optimization dynamic Bayesian network is as follows:
the content effectiveness ratio (Content Validity Ratio, CVR) calculates the effectiveness of the unit event, classifies and quantifies expert opinion languages through a 3-point Likert scale, and assigns 'unnecessary', 'necessary' to '1', '2', and '3', respectively; the content validity index (Content Validity Index, CVI) measures the relation among event units, and the relation is classified and quantified through a 4-point Likest table, wherein 'uncorrelation', 'smaller correlation', 'larger correlation', 'correlation' are respectively assigned with '1', '2', '3', and '4'. The invention specifies that CVI is represented by an expert population ratio of "3" to "4" choices: the index is smaller than 0.7, rejecting the initial structure; the index is between 0.7 and 0.79, and the initial structure is subjected to review modification; the index is greater than 0.79, accepting the initial structure.
The invention optimizes the dynamic Bayes initial topological structure by using CVR and CVI, determines the output dynamic Bayes topological structure, and takes the table 2 as a unit event name table.
TABLE 2
The uncertainty in the initial structure of the topological graph is solved, and the experts in each field are invited to form six groups to solicit expert opinions by adopting a brainstorming method; and the final CVI of the output result is more than 0.79, and the CVR is more than 0.81, so that the dynamic Bayesian initial topological structure of the large-scale vehicle-mounted fire accident is determined, and the dynamic Bayesian initial topological structure is shown in figure 3.
Step 103: based on the dynamic Bayesian topological structure, data fusion is carried out on expert experience weights through DS theory, the prior probability of the basic event is determined, and a conditional probability table is constructed.
In practical applications, step 103 specifically includes: evaluating each node in the dynamic Bayesian topological structure, and aggregating the independent trust structures to form a final trust structure; one of the nodes is a trust structure; determining the evidence credibility of the final trust structure based on DS theory of a weighted average method; collecting a group of heterogeneous expert opinions, and calculating a fuzzy possible set by using a linear opinion pool method; and determining the prior probability of the basic event according to the fuzzy possible set and constructing a conditional probability table according to expert opinion.
DS theory is uncertain reasoning theory, has the capability of processing uncertain problems, can directly endow probability to a multi-object set, expresses uncertain and inaccurate information, and has a synthesis rule ofFrom m 1 ,m 2 ,…,m n The final trust structure formed by the aggregation of the independent trust structures is as follows:
the DS theory improvement algorithm based on the weighted average method is characterized in that the weight is determined, and the evidence credibility (namely the weight) is as follows:
wherein d t The common exhaustive event set is taken as the Euclidean distance of the object, and the distance between each evidence and the average evidence is represented; s is(s) t =1-d t Is evidence m t Is a plausibility representation of (1); c t Evidence m t Is a weight of (2).
Collecting a group of heterogeneous expert opinions, and calculating a fuzzy possible set by using a linear opinion pooling method:
wherein Z is i As basic eventsConsistent fuzzy numbers; w (w) j The weight of expert j; f (f) ij The fuzzy number of the basic event i is judged by an expert; n is the total number of experts; m is the total number of basic events.
An important step of decision making in a fuzzy environment is defuzzification, and the invention adopts a region Center (Center OperationsArea, coA) defuzzification method:
wherein X is the output of the deblurring; mu (mu) i (x) Is an aggregated membership function; x is the output variable. Membership functions μ -A (x) can be expressed as:
The trapezoidal fuzzy number is used as followsAnd carrying out blurring processing by adopting an area center method, and converting the possibility into probability. />
Wherein FP is the probability of each elementary event occurring; FPS is the likelihood value resulting from defuzzification; k is an intermediate variable of the Fps function.
Based on the established dynamic Bayesian topological structure of the vehicle-mounted fire accident, carrying out data fusion on expert experience weights through DS theory, and then quantifying fuzzy numbers to determine the prior probability of the basic event; and obtaining a conditional probability table through expert knowledge construction.
Specifically, a heterogeneous set of experts (4-bit) is invited to evaluate each node. Each node represents 1 trust structure and table 3 is a node evaluation result table, as shown in table 3.
TABLE 3 Table 3
And calculating the weight factor of each trust structure according to the combined algorithm to obtain the final fusion result of the weights of all nodes. And according to the evidence fusion result and the fuzzy evaluation value, the prior probability is obtained through algorithm quantization, and the event probability table is shown in the table 4.
TABLE 4 Table 4
Step 104: and determining the occurrence probability of the vehicle-mounted fire accident by utilizing a forward reasoning technology of a dynamic Bayesian network according to the prior probability of the basic event and the conditional probability table.
In practical application, the prior probability of the root node and the conditional probability of other nodes except the root node are utilized to carry out probability reasoning by utilizing GENIE software to obtain the probability distribution of each node variable, and further the probability of occurrence of large-scale vehicle-mounted fire accidents is obtained.
The large-scale vehicle exhibition fire probability is calculated according to a Bayes basic formula to be 1.9x10 -3 The probability of failure in extinguishing fire after the large-scale vehicle is unfolded is 1.8X10 -3 The fire accident probability of the large-scale vehicle is 8.2 multiplied by 10 -4 。
Step 105: and determining a risk reduction value, an importance measure and a variation ratio according to the prior probability of the basic event and the occurrence probability of the train exhibition fire accident.
The risk reduction value is:
wherein RRW (component j) is a risk reduction value;the system operation probability is;the system is in a normal state, wherein 0 is in a normal operation mode, 1 is in a fault mode, and the score represents a conditional probability; />Is the running state of the system; i fu is the initial state component; fu is a component; s is S j,i fu Is the component j in state i; />Is the number of states; p (S) j,i fu =1) is component j in state i; p (xj=1) is the failure probability of component j; x is x j Indicating the failure status of component j, x, as a boolean variable j =1 indicates failure, x j =0 indicates normal operation.
The importance measure is as follows:
wherein BIM (component j) is a measure of importance;the running probability in the system failure state.
The mutation ratio is as follows:
wherein the ROV (BE i ) Is a variation ratio; pi (BE) i ) For the posterior probability of BEi, θ (BE i ) A priori probability of BEi; BEi is the i-th basic event.
The node 'large-scale vehicle exhibition fire accident' is set as an evidence node, the probability is 1, and the posterior probability is obtained through reverse reasoning. FIG. 4 shows the results of sensitivity analysis using BIM and RRW measurements. BIM and RRW showing BE2, BE19 and BE20 events are highest among all items. Table 4 shows the following rate of change of probability of occurrence of an accident (ROV), showing that BIM and RRW are the same, and the BE2, BE19 and BE20 events are determined as sensitive events.
In addition, the degree of influence of the uncontrolled measure and the implementation of the controlled measure on the occurrence of the accident was measured, and table 5 is an accident occurrence influence table, as shown in table 5.
TABLE 5
Step 106: and entering a unit event accident state through a unit event initial normal working state based on the risk reduction value, the importance measure and the variation ratio, completing dynamic mode transition, generating a dynamic simulation model, and predicting the accident occurrence trend according to the dynamic simulation model.
In practical application, the state transition selection Deltat is 24 time slices, and the system outputs a simulation result of the occurrence probability of the fire accident of the large-scale vehicle display system obtained by prediction.
And (3) entering a unit event accident state (FS) through the initial normal working state (NS) of the unit event, completing the conversion from the NS state to the FS state with lambda probability, and forming the dynamic accident parameter evolution.
The invention selects 24 time slices and calculates the initial probability of accident occurrence as 1.9X10 -3 . The simulation result of the accident occurrence probability of the large-scale vehicle display system in 24 time slices is predicted and obtained, as shown in fig. 5.
1. The invention breaks through the fire risk identification direction mainly based on the intervention level of the traditional fire risk identification through multi-dimensional risk factor collection.
2. According to the invention, a Bayesian network topological graph is constructed, CVI and CVR indexes are adopted to optimize the topological graph structure, so that the influence of artificial subjective factors is reduced, the objectivity of a dynamic Bayesian model is improved, and the rationality of a large-scale vehicle-span multidimensional risk evolution path model is output by a system module.
3. According to the invention, based on the improved DS evidence theory and fuzzy set calculation weight fusion and node probability, information interval fusion is implemented on the evidence body, expert knowledge is optimized, and accuracy of risk results is effectively improved.
4. According to the invention, through outputting the risk reduction value, the importance measure and the variation ratio, the defect that modeling of the fuzzy algorithm is not reversible is overcome, and compared with the traditional algorithm, the fuzzy algorithm is further used for outputting a sensitive risk factor interval, so that hidden danger investigation and rectification change of the working direction are realized.
5. According to the invention, through the conversion from the NS state to the FS state, the transition of the dynamic mode is completed, the dynamic simulation model is output, and the accident occurrence trend is predicted.
Aiming at the defects of incomplete risk identification, more subjective factor influence, unobtrusive dynamic prediction and more complex assessment results of the traditional risk assessment, the invention subjects the risk factor identification to multidimensional identification, the assessment process to objectification by algorithm introduction, the prediction result to be dynamically outputted by simulation, and the assessment result to be implemented by important risk determination.
The method can be widely applied to the fire risk assessment of large-scale exhibitions, and has great value.
Example two
In order to execute the method corresponding to the embodiment to realize the corresponding functions and technical effects, a multi-dimensional risk dynamic evaluation system for large-scale vehicle-mounted fire disaster is provided below.
A multi-dimensional risk dynamic assessment system for a large-scale vehicle-mounted fire, comprising:
the vehicle-spread fire accident related risk factor determining module is used for completing multi-dimensional identification of vehicle-spread fire risks based on vehicle-spread site location information, site risk factor identification information and historical accident risk factor summary information and determining vehicle-spread fire accident related risk factors.
And the dynamic Bayesian topological structure establishing module is used for determining risk factor association information according to the fire accident related risk factors and establishing a dynamic Bayesian topological structure of the vehicle-mounted fire accident.
In practical application, the dynamic bayesian topological structure establishment module specifically comprises: the dynamic Bayesian initial topological structure establishing unit is used for determining risk factor association information according to the fire accident related risk factors and establishing a dynamic Bayesian initial topological structure of the vehicle-mounted fire accident; the content effectiveness index determining unit is used for determining a content effectiveness ratio according to expert opinion and determining a content effectiveness index according to expert quantity; the dynamic Bayesian topological structure determining unit is used for optimizing the dynamic Bayesian initial topological structure according to the content effectiveness ratio and the content effectiveness index to determine a dynamic Bayesian topological structure; the father node of the dynamic Bayesian topological structure is a car-spread fire accident, and the child node of the dynamic Bayesian topological structure comprises inflammables, ignition sources, fire spread, people, objects, environments, management, vehicle exhibit failure combustion, electrical equipment failure combustion, other inflammables, artificial ignition, environmental factors, exceeding personnel load, on-site personnel quality spread, personnel characteristic structure, hand-held fire extinguisher failure, automatic fire extinguishing system failure, fire alarm device failure, smoke prevention and exhaust system failure, lower fire resistance level of a building, insufficient fire partition design, lower fire load, fire station influence, maintenance personnel number standard rate, security personnel number standard rate, fire personnel number standard rate and management work standard failure.
The basic event prior probability and conditional probability table construction module is used for carrying out data fusion on expert experience weights through DS theory based on the dynamic Bayesian topological structure, determining basic event prior probability and constructing a conditional probability table.
And the vehicle-spread fire accident occurrence probability determining module is used for determining the vehicle-spread fire accident occurrence probability by utilizing a forward reasoning technology of a dynamic Bayesian network according to the basic event prior probability and the conditional probability table.
And the parameter determining module is used for determining a risk reduction value, an importance measure and a variation ratio according to the prior probability of the basic event and the probability of occurrence of the train exhibition fire accident.
And the prediction module is used for entering a unit event accident state through a unit event initial normal working state based on the risk reduction value, the importance measure and the variation ratio, completing dynamic mode transition, generating a dynamic simulation model and predicting the accident occurrence trend according to the dynamic simulation model.
Fig. 6 is a frame diagram of a multi-dimensional risk dynamic assessment system for large-scale vehicle-mounted fire disaster, which is provided by the invention, and the invention further comprises the following modules:
and the large-scale vehicle display map module is used for displaying basic plane diagram information of the large-scale vehicle display and other information (such as evacuation channel information, fire-fighting system structure information and the like). The large-scale vehicle display map module also comprises a large-scale vehicle display map display unit and other structural units.
The risk acquisition index module is used for constructing a risk index system according to dimensions, specifically displaying the unit information of each dimension, and facilitating the reading and writing of system information. The risk acquisition index module further comprises a one-dimensional index unit, a two-dimensional index unit, a three-dimensional index unit and a four-dimensional index unit.
The risk evolution module is used for visualizing the correlation of the risk factors and the risk evolution path of the large-scale vehicle exhibition fire disaster. The risk evolution module further comprises a large-scale vehicle-span fire accident dynamic Bayesian network structure unit and a large-scale vehicle-span multidimensional risk evolution path model unit.
And a risk data dynamic quantification module. The system is used for digitizing and dynamically converting the risk factors of the large-scale vehicle-mounted fire disaster so as to accurately output and predict the risk state of the system. The risk data dynamic quantification module further comprises a fire accident probability unit, a sensitivity unit and a dynamic simulation unit.
The hidden danger checking and rectifying module is used for directly obtaining a unit module of the sensitive event, and the unit module displays the sensitive event and the accident occurrence probability result change after rectifying. The hidden danger checking and modifying module also comprises a sensitive event unit and a modifying result unit.
If the traditional dimension of intervention is adopted independently and multi-dimensional large-scale vehicle exhibition fire risk factor identification is not performed, the identification result cannot be comprehensively obtained; if a Bayesian topological graph is formed based on an index system alone without carrying out algorithm optimization on the model, a dynamic Bayesian model can be constructed, but the effectiveness of unit events and the influence of the relation between event units on human supervisor are large, and a scientific and reasonable Bayesian model cannot be obtained; if fuzzy set theory is adopted alone and the DS evidence data fusion is not passed, although the fuzzy set theory is a modeling algorithm, the objectivity is lower, the fuzzy set theory is often built by expert knowledge, and the analysis of an objective angle cannot be carried out; if static Bayesian forward analysis is independently performed without sensitivity analysis and dynamic reasoning, a sensitive event cannot be directly and accurately obtained so as to obtain a rectifying object, and the dynamic prediction cannot be performed in accordance with risk dynamics.
In summary, the invention provides a multi-dimensional dynamic risk assessment method and system for a large-scale vehicle-show fire disaster, aiming at the complex situation of the large-scale vehicle-show risk factors, the risk factors of the large-scale vehicle-show fire disaster are identified in a multi-dimensional angle, and a dimension index system is output by the system; based on CVR and CVI, optimizing and perfecting the dynamic Bayesian topological graph, and outputting a large-scale vehicle-spread fire accident dynamic Bayesian network structure and a large-scale vehicle-spread multidimensional risk evolution path model by the system; on the premise of insufficient data and incomplete knowledge, weight fusion and node probability are calculated by using DS evidence theory and fuzzy set, a sensitive event is obtained by model bidirectional reasoning and sensitivity calculation, a simulation model is obtained by predicting accident risk probabilities of 24 time slices in a dynamic evolution process, and a system output risk data dynamic quantification module and a hidden danger investigation and correction module are provided.
The invention evaluates the risk factors of large-scale vehicle-mounted fire accident by diagnosis, can put forward related protective measures for the sensitive event of the system in advance, pre-controls the potential risk factors, dynamically displays the occurrence probability of the system accident, and monitors the whole monitoring system at any time. The invention is easy to implement and has advancement and practicability.
Example III
The embodiment of the invention provides electronic equipment which comprises a memory and a processor, wherein the memory is used for storing a computer program, and the processor runs the computer program to enable the electronic equipment to execute the multi-dimensional risk dynamic assessment method for the fire disaster of the large-scale vehicle exhibition.
In practical applications, the electronic device may be a server.
In practical applications, the electronic device includes: at least one processor (processor), memory (memory), bus, and communication interface (Communications Interface).
Wherein: the processor, communication interface, and memory communicate with each other via a communication bus.
And the communication interface is used for communicating with other devices.
And a processor, configured to execute a program, and specifically may execute the method described in the foregoing embodiment.
In particular, the program may include program code including computer-operating instructions.
The processor may be a central processing unit, CPU, or specific integrated circuit ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement embodiments of the present invention. The one or more processors included in the electronic device may be the same type of processor, such as one or more CPUs; but may also be different types of processors such as one or more CPUs and one or more ASICs.
And the memory is used for storing programs. The memory may comprise high-speed RAM memory or may further comprise non-volatile memory, such as at least one disk memory.
Based on the description of the above embodiments, the embodiments of the present application provide a storage medium having stored thereon computer program instructions executable by a processor to implement the method of any of the embodiments
The multi-dimensional risk dynamic evaluation system for large-scale vehicle-mounted fire disaster provided by the embodiment of the application exists in various forms, including but not limited to:
(1) A mobile communication device: such devices are characterized by mobile communication capabilities and are primarily aimed at providing voice, data communications. Such terminals include: smart phones (e.g., iPhone), multimedia phones, functional phones, and low-end phones, etc.
(2) Ultra mobile personal computer device: such devices are in the category of personal computers, having computing and processing functions, and generally having mobile internet access capabilities. Such terminals include: PDA, MID, and UMPC devices, etc., such as iPad.
(3) Portable entertainment device: such devices may display and play multimedia content. The device comprises: audio, video players (e.g., iPod), palm game consoles, electronic books, and smart toys and portable car navigation devices.
(4) Other electronic devices with data interaction functions.
Thus, particular embodiments of the present subject matter have been described. Other embodiments are within the scope of the following claims. In some cases, the actions recited in the claims can be performed in a different order and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may be advantageous.
The system, apparatus, module or unit set forth in the above embodiments may be implemented in particular by a computer chip or entity, or by a product having a certain function. One typical implementation is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.
For convenience of description, the above devices are described as being functionally divided into various units, respectively. Of course, the functions of each element may be implemented in one or more software and/or hardware elements when implemented in the present application. It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In one typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of computer-readable media.
Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of a storage medium for a computer include, but are not limited to, a phase change memory (PRAM), a Static Random Access Memory (SRAM), a Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), a Read Only Memory (ROM), an Electrically Erasable Programmable Read Only Memory (EEPROM), a flash memory or other memory technology, a compact disc read only memory (CD-ROM), a compact disc Read Only Memory (ROM),
Digital Versatile Disk (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices
Or any other non-transmission medium, may be used to store information that may be accessed by a computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises the element.
The application may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular transactions or implement particular abstract data types. The application may also be practiced in distributed computing environments where transactions are performed by remote processing devices that are connected through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.
In the present specification, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different point from other embodiments, and identical and similar parts between the embodiments are all enough to refer to each other. For the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant points refer to the description of the method section.
The principles and embodiments of the present invention have been described herein with reference to specific examples, the description of which is intended only to assist in understanding the methods of the present invention and the core ideas thereof; also, it is within the scope of the present invention to be modified by those of ordinary skill in the art in light of the present teachings. In view of the foregoing, this description should not be construed as limiting the invention.
Claims (10)
1. A multi-dimensional risk dynamic assessment method for a large-scale vehicle exhibition fire disaster is characterized by comprising the following steps:
completing multidimensional identification of the vehicle-mounted fire risk based on the vehicle-mounted field information, the field risk factor identification information and the historical accident risk factor summary information, and determining the related risk factors of the vehicle-mounted fire accident;
determining risk factor related information according to the fire accident related risk factors, and establishing a dynamic Bayesian topological structure of the vehicle-mounted fire accident;
Based on the dynamic Bayesian topological structure, carrying out data fusion on expert experience weights through DS theory, determining the prior probability of a basic event and constructing a conditional probability table;
determining the occurrence probability of the vehicle-mounted fire accident by utilizing a forward reasoning technology of a dynamic Bayesian network according to the prior probability of the basic event and the conditional probability table;
determining a risk reduction value, an importance measure and a variation ratio according to the prior probability of the basic event and the occurrence probability of the train-show fire accident;
and entering a unit event accident state through a unit event initial normal working state based on the risk reduction value, the importance measure and the variation ratio, completing dynamic mode transition, generating a dynamic simulation model, and predicting the accident occurrence trend according to the dynamic simulation model.
2. The method for dynamically evaluating multidimensional risk of a large-scale vehicle-mounted fire according to claim 1, wherein the method for dynamically evaluating the risk factor related information is determined according to the risk factor related to the fire accident, and a dynamic bayesian topological structure of the vehicle-mounted fire accident is established, and specifically comprises the following steps:
determining risk factor association information according to the fire accident related risk factors, and establishing a dynamic Bayesian initial topological structure of the vehicle-mounted fire accident;
Determining content effectiveness ratio according to expert opinion and determining content effectiveness index according to expert number;
optimizing the dynamic Bayesian initial topological structure according to the content effectiveness ratio and the content effectiveness index to determine a dynamic Bayesian topological structure; the father node of the dynamic Bayesian topological structure is a car-spread fire accident, and the child node of the dynamic Bayesian topological structure comprises inflammables, ignition sources, fire spread, people, objects, environments, management, vehicle exhibit failure combustion, electrical equipment failure combustion, other inflammables, artificial ignition, environmental factors, exceeding personnel load, on-site personnel quality spread, personnel characteristic structure, hand-held fire extinguisher failure, automatic fire extinguishing system failure, fire alarm device failure, smoke prevention and exhaust system failure, lower fire resistance level of a building, insufficient fire partition design, lower fire load, fire station influence, maintenance personnel number standard rate, security personnel number standard rate, fire personnel number standard rate and management work standard failure.
3. The method for dynamically evaluating multidimensional risk of large-scale vehicle-mounted fire according to claim 1, wherein based on the dynamic bayesian topological structure, expert experience weights are subjected to data fusion by a DS theory, basic event prior probabilities are determined, and a conditional probability table is constructed, specifically comprising:
Evaluating each node in the dynamic Bayesian topological structure, and aggregating the independent trust structures to form a final trust structure; one of the nodes is a trust structure;
determining the evidence credibility of the final trust structure based on DS theory of a weighted average method;
collecting a group of heterogeneous expert opinions, and calculating a fuzzy possible set by using a linear opinion pool method;
and determining the prior probability of the basic event according to the fuzzy possible set and constructing a conditional probability table according to expert opinion.
4. The method for dynamically evaluating the multidimensional risk of a large-scale vehicle-mounted fire according to claim 1, wherein the risk reduction value is:
wherein RRW (componet j) is a risk reduction value;probability of operation for a system;/>Is the number of states;the running probability is the running probability of the system in a normal state; />Is the running state of the system; i fu is the initial state component; fu is a component; s is S j,i fu Is the component j in state i; p (S) j,i fu =1) is component j in state i; x is x j Indicating the failure status of component j, x, as a boolean variable j =1 indicates failure, x j =0 indicates normal operation.
6. The method for dynamically evaluating the multidimensional risk of a large-scale vehicle-mounted fire according to claim 4, wherein the mutation ratio is as follows:
wherein the ROV (BE i ) Is a variation ratio; pi (BE) i ) The posterior probability of BEi, θ #BE i ) A priori probability of BEi; BEi is the i-th basic event.
7. A multi-dimensional risk dynamic assessment system for a large-scale vehicle-mounted fire disaster, comprising:
the vehicle-spread fire accident related risk factor determining module is used for completing multi-dimensional identification of vehicle-spread fire risks by using vehicle-spread site location information, site risk factor identification information and historical accident risk factor summary information and determining vehicle-spread fire accident related risk factors;
the dynamic Bayesian topological structure establishing module is used for determining risk factor association information according to the fire accident related risk factors and establishing a dynamic Bayesian topological structure of the vehicle-mounted fire accident;
the basic event prior probability and conditional probability table construction module is used for carrying out data fusion on expert experience weights through DS theory based on the dynamic Bayesian topological structure, determining basic event prior probability and constructing a conditional probability table;
The vehicle-spread fire accident occurrence probability determining module is used for determining the vehicle-spread fire accident occurrence probability by utilizing a forward reasoning technology of a dynamic Bayesian network according to the basic event prior probability and the conditional probability table;
the parameter determining module is used for determining a risk reduction value, an importance measure and a variation ratio according to the prior probability of the basic event and the occurrence probability of the train-show fire accident;
and the prediction module is used for entering a unit event accident state through a unit event initial normal working state based on the risk reduction value, the importance measure and the variation ratio, completing dynamic mode transition, generating a dynamic simulation model and predicting the accident occurrence trend according to the dynamic simulation model.
8. The system for dynamically assessing the multidimensional risk of a large-scale vehicle-mounted fire according to claim 7, wherein the dynamic bayesian topological structure establishment module specifically comprises:
the dynamic Bayesian initial topological structure establishing unit is used for determining risk factor association information according to the fire accident related risk factors and establishing a dynamic Bayesian initial topological structure of the vehicle-mounted fire accident;
the content effectiveness index determining unit is used for determining a content effectiveness ratio according to expert opinion and determining a content effectiveness index according to expert quantity;
The dynamic Bayesian topological structure determining unit is used for optimizing the dynamic Bayesian initial topological structure according to the content effectiveness ratio and the content effectiveness index to determine a dynamic Bayesian topological structure; the father node of the dynamic Bayesian topological structure is a car-spread fire accident, and the child node of the dynamic Bayesian topological structure comprises inflammables, ignition sources, fire spread, people, objects, environments, management, vehicle exhibit failure combustion, electrical equipment failure combustion, other inflammables, artificial ignition, environmental factors, exceeding personnel load, on-site personnel quality spread, personnel characteristic structure, hand-held fire extinguisher failure, automatic fire extinguishing system failure, fire alarm device failure, smoke prevention and exhaust system failure, lower fire resistance level of a building, insufficient fire partition design, lower fire load, fire station influence, maintenance personnel number standard rate, security personnel number standard rate, fire personnel number standard rate and management work standard failure.
9. An electronic device comprising a memory for storing a computer program and a processor that runs the computer program to cause the electronic device to perform the multi-dimensional risk dynamic assessment method of a large vehicle show fire according to any one of claims 1-6.
10. A computer-readable storage medium, characterized in that it stores a computer program which, when executed by a processor, implements the method for dynamically assessing multi-dimensional risk of fire in a large vehicle according to any one of claims 1 to 6.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310172973.2A CN116167620A (en) | 2023-02-28 | 2023-02-28 | Multi-dimensional risk dynamic evaluation method and system for large-scale vehicle exhibition fire disaster |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310172973.2A CN116167620A (en) | 2023-02-28 | 2023-02-28 | Multi-dimensional risk dynamic evaluation method and system for large-scale vehicle exhibition fire disaster |
Publications (1)
Publication Number | Publication Date |
---|---|
CN116167620A true CN116167620A (en) | 2023-05-26 |
Family
ID=86421724
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310172973.2A Pending CN116167620A (en) | 2023-02-28 | 2023-02-28 | Multi-dimensional risk dynamic evaluation method and system for large-scale vehicle exhibition fire disaster |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116167620A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116911594A (en) * | 2023-06-05 | 2023-10-20 | 北京市燃气集团有限责任公司 | Method and device for evaluating leakage emergency repair risk of gas pipeline |
CN117495113A (en) * | 2024-01-02 | 2024-02-02 | 海纳云物联科技有限公司 | Building fire safety assessment method, equipment and medium |
-
2023
- 2023-02-28 CN CN202310172973.2A patent/CN116167620A/en active Pending
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116911594A (en) * | 2023-06-05 | 2023-10-20 | 北京市燃气集团有限责任公司 | Method and device for evaluating leakage emergency repair risk of gas pipeline |
CN117495113A (en) * | 2024-01-02 | 2024-02-02 | 海纳云物联科技有限公司 | Building fire safety assessment method, equipment and medium |
CN117495113B (en) * | 2024-01-02 | 2024-05-28 | 海纳云物联科技有限公司 | Building fire safety assessment method, equipment and medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN116167620A (en) | Multi-dimensional risk dynamic evaluation method and system for large-scale vehicle exhibition fire disaster | |
Wei | Picture fuzzy cross-entropy for multiple attribute decision making problems | |
Wang et al. | Spatio-temporal modeling of criminal incidents using geographic, demographic, and Twitter-derived information | |
Li et al. | Extension of the TOPSIS for multi-attribute group decision making under Atanassov IFS environments | |
Liang et al. | A probabilistic interval-valued hesitant fuzzy gained and lost dominance score method based on regret theory | |
Yu et al. | Modeling uncertain and dynamic interdependencies of infrastructure systems using stochastic block models | |
Garg et al. | Multiple‐attribute decision‐making problem using TOPSIS and Choquet integral with hesitant fuzzy number information | |
CN113223264A (en) | QPSO-BP neural network-based intelligent fire early warning system and method | |
CN111626199A (en) | Abnormal behavior analysis method for large-scale multi-person carriage scene | |
Almotahari et al. | Impact of topology and congestion on link criticality rankings in transportation networks | |
Xu et al. | Method for large group emergency decision making with complex preferences based on emergency similarity and interval consistency | |
CN111523088A (en) | Ecological environment evaluation method based on DPSIR model | |
CN113362959A (en) | Sudden respiratory infectious disease risk prediction model for regional epidemic prevention and control | |
Xu et al. | Integrating an option-oriented attitude analysis into investigating the degree of stabilities in conflict resolution | |
Tüysüz et al. | Evaluating social sustainable development factors using multi-experts Z-fuzzy AHP | |
CN103838806A (en) | Analysis method for subject participation behaviors of user in social network | |
CN115599650A (en) | Health degree evaluation method and device of IT system, electronic equipment and storage medium | |
Das et al. | A comprehensive methodology for quantification of Bow-tie under type II fuzzy data | |
Keikha | Introducing a new type of HFSs and its application in solving MAGDM problems | |
CN112766402A (en) | Algorithm selection method and device and electronic equipment | |
Yusuf et al. | Causal inference methods and their challenges: the case of 311 data | |
Nikfalazar et al. | Fuzzy risk analysis by similarity-based multi-criteria approach to classify alternatives | |
Mead | Requirements prioritization case study using AHP | |
Luo et al. | Human emergency behaviour and psychological stress characteristic mining based on large-scale emergencies | |
Su et al. | Fuzzy FMECA risk evaluation and its applications in Chinese train control systems based on cloud model |
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 |