CN116739391B - Multi-system rail transit emergency collaborative decision-making method and device - Google Patents
Multi-system rail transit emergency collaborative decision-making method and device Download PDFInfo
- Publication number
- CN116739391B CN116739391B CN202311017094.9A CN202311017094A CN116739391B CN 116739391 B CN116739391 B CN 116739391B CN 202311017094 A CN202311017094 A CN 202311017094A CN 116739391 B CN116739391 B CN 116739391B
- Authority
- CN
- China
- Prior art keywords
- fault
- fuzzy
- state
- influence
- rail transit
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 58
- 238000011156 evaluation Methods 0.000 claims abstract description 71
- 230000006870 function Effects 0.000 claims abstract description 46
- 238000013507 mapping Methods 0.000 claims description 23
- 238000005259 measurement Methods 0.000 claims description 22
- 238000011282 treatment Methods 0.000 claims description 19
- 238000004891 communication Methods 0.000 claims description 14
- 238000003860 storage Methods 0.000 claims description 12
- 230000008859 change Effects 0.000 claims description 9
- 238000012544 monitoring process Methods 0.000 claims description 9
- 230000032683 aging Effects 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 7
- 238000011002 quantification Methods 0.000 claims description 7
- 238000013139 quantization Methods 0.000 claims description 6
- 238000010276 construction Methods 0.000 claims description 5
- 238000005070 sampling Methods 0.000 claims description 5
- 238000007789 sealing Methods 0.000 claims description 4
- 230000004888 barrier function Effects 0.000 claims description 2
- 239000004973 liquid crystal related substance Substances 0.000 claims 2
- XQCFHQBGMWUEMY-ZPUQHVIOSA-N Nitrovin Chemical compound C=1C=C([N+]([O-])=O)OC=1\C=C\C(=NNC(=N)N)\C=C\C1=CC=C([N+]([O-])=O)O1 XQCFHQBGMWUEMY-ZPUQHVIOSA-N 0.000 claims 1
- 238000011160 research Methods 0.000 description 18
- 230000008569 process Effects 0.000 description 11
- 238000005516 engineering process Methods 0.000 description 10
- 238000006731 degradation reaction Methods 0.000 description 8
- 230000015556 catabolic process Effects 0.000 description 6
- 238000011835 investigation Methods 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 5
- 238000007726 management method Methods 0.000 description 5
- 238000001514 detection method Methods 0.000 description 4
- 238000012546 transfer Methods 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 230000018109 developmental process Effects 0.000 description 3
- 230000010354 integration Effects 0.000 description 3
- 230000008520 organization Effects 0.000 description 3
- 230000003068 static effect Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000003247 decreasing effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000004927 fusion Effects 0.000 description 2
- 238000012821 model calculation Methods 0.000 description 2
- 238000013439 planning Methods 0.000 description 2
- 230000001550 time effect Effects 0.000 description 2
- 238000011269 treatment regimen Methods 0.000 description 2
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000013210 evaluation model Methods 0.000 description 1
- 238000000556 factor analysis Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000011158 quantitative evaluation Methods 0.000 description 1
- 238000011897 real-time detection Methods 0.000 description 1
- 238000013468 resource allocation Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- 230000007480 spreading Effects 0.000 description 1
- 238000003892 spreading Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
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
- G06Q10/0637—Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals
- G06Q10/06375—Prediction of business process outcome or impact based on a proposed change
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/251—Fusion techniques of input or preprocessed data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N7/00—Computing arrangements based on specific mathematical models
- G06N7/01—Probabilistic graphical models, e.g. probabilistic networks
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Strategic Management (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Evolutionary Biology (AREA)
- Educational Administration (AREA)
- Marketing (AREA)
- Computational Mathematics (AREA)
- Algebra (AREA)
- Probability & Statistics with Applications (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Computing Systems (AREA)
- General Business, Economics & Management (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention relates to the technical field of multi-system rail transit, in particular to a multi-system rail transit emergency collaborative decision method and device based on a fuzzy Bayesian network. In the invention, the relevance between the Bayesian probability measure multidimensional characteristic index and different fault influence factors is adopted, and a time-varying scoring function is constructed to integrate characteristic information with different timeliness, so as to quantify the fuzzy state of fault occurrence. In addition, the fault influence is graded based on the severity of influence operation, a plurality of fuzzy functions are fused in the network, and the fuzzy importance of fuzzy states corresponding to different faults and continuously changing in global operation state evaluation is respectively described; on the basis, the comprehensive grading value of the rail transit system operation is calculated, and the state grade and the potential operation risk of the rail transit system are presumed.
Description
Technical Field
The invention relates to the technical field of multi-system rail transit, in particular to a multi-system rail transit emergency collaborative decision method and device based on a fuzzy Bayesian network.
Background
In recent years, with the continuous development of computer technology, artificial intelligence technology, prediction technology, and simulation technology, research on emergency decision methods guided by knowledge management (e.g., knowledge of existing cases, emergency plans, disaster prediction, etc.) has been widely conducted, and many representative research results have been obtained. For example, a transportation scheduling decision support system in emergency, an emergency decision system based on rule reasoning, an emergency logistics decision support system based on a plurality of systems, a decision support system framework of dynamic multi-target emergency rescue material logistics, an emergency decision knowledge matching method based on a maximum convention sub-category and the like.
(1) At present, research results lack of emergency linkage modes and mechanism researches of various systems of rail transit, and emergency treatment pain points of the mutual influence of the multiple systems of the rail transit network are difficult to support. The existing research is developed from single-system emergency safety guarantee of urban rails, railways and the like, even single-line emergency safety guarantee, but the emergency linkage research on multi-system rail transit networked operation is very little. How to achieve efficient emergency handling efficiency through more unified coordinated emergency linkages has been a major problem facing large cities.
(2) The existing research is shallow in research on multi-specialized feedback decisions and multi-variety coordination cooperation in rail transit emergency linkage, the emergency decision comprehensiveness is poor, and the emergency treatment efficiency is limited. A large number of researches are developed for passenger flow organization, driving dispatching, station personnel allocation, emergency resource allocation and the like, and contents related to multiple professions and multiple working conditions are mainly solved by constructing a plan, however, the selection of an emergency strategy under an actual emergency event is always an optimal decision obtained by comprehensive optimization of multiple professions and multiple working conditions, and the accuracy and rapidity of global decision cannot be fundamentally improved by current research and technical means.
The urban ring urban mass multisystem rail transit system has the characteristic of cooperative integration, and when an emergency occurs in the operation management process, the whole body can be pulled to be sent, so that mass cooperation in the emergency process is particularly important. The students comprehensively use the group network planning method and the computer collaborative work technology, start from the practical requirement of the collaborative decision of the emergency group, develop the research of the group collaborative emergency decision pattern expression method according to the group-introduced group network planning technology, use the means of group decision, knowledge management and the like, and construct the research of the collaborative decision overall coordination method of the emergency group. Based on the model expression and overall coordination method of emergency group collaborative decision, the computer collaborative work among different emergency management departments is realized by utilizing a multimedia communication technology, and the emergency group collaborative man-machine interaction scheme decision system is designed by combining multimedia with an adjacent technology.
In the emergency response process, an effective emergency scheme, namely an emergency decision method based on case reasoning, is often required to be generated according to historical experience.
The thought of multi-objective emergency decision research is that in view of the multi-objective, multi-factor and complex and changeable evolution rules of emergency events, the application of the multi-objective decision theory and method to emergency decisions becomes a research hotspot formed recently.
In summary, although remarkable results are obtained in the field of emergency decision research of emergency events, the feature research content of emergency decision of the emergency events is rich, only a single feature is researched, and common research among features is lacking. Considerable progress is made in the aspects of evaluation and evaluation methods and emergency decision-making systems for emergency plans, but in the aspects of investigation of emergency plans, investigation of influences of faults on a multi-system rail transit system and investigation of emergency treatment schemes are in scattered states.
Disclosure of Invention
Aiming at the problems, the invention provides a multi-system rail transit emergency collaborative decision method and device.
A multi-system rail transit emergency collaborative decision-making method, comprising:
sorting historical data of equipment and multi-system rail transit system operation, classifying and quantifying the data according to fault types and influence factor types based on the historical data;
counting the quantized data, calculating prior probability and conditional probability of events of various types of faults and actual measurement values of influencing factors, and constructing a Bayesian network based on the correlation between the prior probability and the conditional probability of the events of various types of faults and actual measurement values of influencing factors;
Based on the Bayesian network, calculating and measuring the relative importance of all characteristic indexes under each fault mapping, constructing a time-varying scoring function of the fault state, and measuring the burst fault state;
when the sudden fault occurs, collecting actual measurement values of all influence factors of the fault to be evaluated, and calculating grading values of all fault states based on a time-varying grading function; determining severity grades corresponding to various faults, calculating fuzzy importance corresponding to various fault states, and calculating relative importance in global operation state evaluation of the system of each grade;
based on the Bayesian network, calculating the fuzzy weight of each sudden fault comprehensive index, and calculating the fuzzy comprehensive scoring value of the global operation state of the system to be evaluated;
and obtaining the state grade of the system according to the fuzzy comprehensive grading value of the global operation state of the system, and deciding an emergency scheme.
Further, the classifying and quantifying the data according to the fault type and the influence factor type specifically includes:
according to whether the influence factors change with time and space and combining the business characteristics of multi-system rail transit operation, the influence factors are divided into a plurality of categories including time factors, space-time factors and space-time independent factors.
Further, the constructing a bayesian network specifically includes:
based on the implicit association knowledge in the historical data resources of the multi-system rail transit system, a three-layer Bayesian network containing influence factors, fault information and global operation states is constructed and used for describing the association relationship among the global operation states, the fault information and the influence factors of the system.
Further, the bayesian network includes:
the top layer of the Bayesian network is a global operation state layer of the multi-system rail transit system, and is determined by integrating state information of all sudden faults;
the Bayesian network middle layer is a fault information layer and consists of generated faultsConstructing;
the Bayesian network bottom layer is an influence factor layer and is formed by dynamically detecting dataA is a real-time monitoring index a corresponding to a fault set I 1 ...a k Is a set of (3).
Further, the correlation between the two based on the Bayesian probability quantification specifically comprises:
based on the association relation between the Bayesian probability quantification fault and the influence factors, adopting the Bayesian probability to measure the actual measurement value of the influence factors as the valueThe degree of importance of the event of (a) to the fault, i.e
；
Wherein: n represents the number of possible values of the influencing factor, Representing different sudden failure events +.>Indicating the occurrence of sudden failure->Event of (2)>Indicating that sudden failure ∈>State of (2); x represents the value of the measured value of the influence factor of +.>Event of (2); />And->For the prior probability->For conditional probability +.>、/>And->And is obtained through statistics of historical sample data.
Further, the calculating and measuring the relative importance of all the characteristic indexes under each fault mapping and measuring the burst fault state specifically includes:
on the basis of probability statistics on historical operation data resources of the multi-system rail transit system, the correlation knowledge between influence factors and fault influence severity is quantified by adopting the Bayesian theorem, and influence factor information with different timeliness under the mapping of the influence factors is integrated by constructing an timeliness scoring function.
Further, constructing the aging scoring function integrates the influence factor information with different timeliness under the mapping, including: based on [0,1 ]]Scoring values in the range quantitatively describe the fuzzy state of the sudden fault; scoring value of corresponding state of each burst faultCalculated by the following formula:
；
wherein:and->Respectively indicate malfunction->The number of the mapped influence factor reference evaluation indexes and the real-time monitoring indexes; alpha represents the effectiveness of the influence factor reference evaluation index in the fault state measure and is equal to the sampling time point of the reference evaluation index >Real-time evaluation time->The length of the interval time between the two is related; />Representing the relative importance of influencing factors in the corresponding fault state measure,/for>In combination with bayesian probability computation:
。
further, the determining the severity level corresponding to each fault, calculating the fuzzy importance corresponding to each fault state, and the relative importance in the global operation state evaluation of each level system specifically includes:
based on the difference of fault severity, dividing all fault severity possibly occurring into a plurality of stages, constructing different fuzzy functions to respectively describe the influence degree of the occurrence of different level faults on the multi-system rail transit system under different operation states, wherein the influence degree is recorded asFault severity level->Multiple system traffic system operation status level ∈>；
The fuzzy importance of the first-level faults is represented by a Gaussian fuzzy function, the fuzzy importance of the second-level faults is represented by a triangular fuzzy number, the fuzzy importance of the third-level faults is represented by a parabolic fuzzy membership function, and the formula is expressed as follows in sequence:
；
；
；
wherein:to the operation state level of the multi-system traffic systemlVariable parameter of->，/>The method comprises the steps of carrying out a first treatment on the surface of the Parameter->And k is set according to the operation experience.
Further, the calculating the fuzzy weight of each sudden fault comprehensive index to obtain a fuzzy comprehensive grading value of the global operation state of the system to be evaluated, and obtaining the state grade according to the fuzzy comprehensive grading value specifically includes:
the global operation state of the system is determined by integrating all the state information of faults;representing the relative importance of the same fault in system global operational state assessment at different levels, wherein，/>，/>；
By calculating v l m At v l s Obtaining the fuzzy weight coefficient of the system in the global operation state evaluation:
；
the fuzzy comprehensive grading value of the global operation state of the system is P=E×V, and the state grade is obtained according to the grading P.
Further, the decision emergency scheme according to the fuzzy comprehensive grading value of the global operation state of the system specifically comprises the following steps:
determining a current limiting level according to the range of the fuzzy comprehensive grading value P of the global operation state of the system;the value of (2) is selected according to experience or actual conditions;
adopting primary current limiting measures to limit the current of a payment area in the station;
adopting a secondary current limiting measure to limit the current of a non-pay area in the station;
by taking the following steps ofThree-stage current limiting measures are out-of-station current limiting;
Adopting four-stage current limiting, wherein the current limiting measure is station sealing;
and determining an adjustment period for adjusting the running chart according to the fault influence time.
A multi-system rail transit emergency collaborative decision-making device, comprising: the system comprises a classification and quantization unit, a modeling unit, an evaluation unit and an emergency scheme unit;
the classification and quantization unit is used for sorting and quantizing historical data resources of equipment and multi-system rail transit system operation, and classifying and quantizing the data according to fault types and influence factor types based on the historical data;
the modeling unit is used for counting samples and calculating prior probability and conditional probability of events of various types of faults and actual measurement values of influencing factors, and constructing a Bayesian network based on correlation between the prior probability and the conditional probability of the events of various types of faults and actual measurement values of influencing factors; based on the Bayesian network, calculating and measuring the relative importance of all characteristic indexes under each fault mapping, constructing a time-varying scoring function of the fault state, and measuring the burst fault state;
the evaluation unit is used for collecting actual measurement values of all influence factors of the fault to be evaluated when the sudden fault occurs, and calculating the grading value of each fault state based on a time-varying grading function; determining severity grades corresponding to various faults, calculating fuzzy importance corresponding to various fault states, and calculating relative importance in global operation state evaluation of the system of each grade; based on the Bayesian network, calculating the fuzzy weight of each sudden fault comprehensive index, and calculating the fuzzy comprehensive scoring value of the global operation state of the system to be evaluated;
And the emergency scheme unit is used for obtaining the state grade decision emergency scheme according to the fuzzy comprehensive grading value of the global operation state of the system.
An electronic device comprises a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory are communicated with each other through the communication bus;
a memory for storing a computer program;
and the processor is used for realizing the multi-system rail transit emergency collaborative decision method when executing the programs stored in the memory.
A computer readable storage medium having stored thereon a computer program which when executed by a processor implements the multi-system rail transit emergency collaborative decision-making method described above.
The invention has at least the following beneficial effects:
according to the invention, by analyzing the characteristics of multi-system collaborative emergency treatment, the factors affecting multi-system operation by faults are subjected to deep analysis and quantitative calculation. Aiming at the problems of fuzzy sudden fault degree and uncertain global operation state of the multi-system rail transit system in the operation process, the improved Bayesian network fault evaluation and global operation state evaluation method based on the fusion fuzzy function is provided.
In the invention, the relevance between the Bayesian probability measure multidimensional characteristic index and different fault influence factors is adopted, and a time-varying scoring function is constructed to integrate characteristic information with different timeliness, so as to quantify the fuzzy state of fault occurrence. In addition, the fault influence is graded based on the severity of influence operation, a plurality of fuzzy functions are fused in the network, and the fuzzy importance of fuzzy states corresponding to different faults and continuously changing in global operation state evaluation is respectively described; on the basis, the comprehensive grading value of the rail transit system operation is calculated, and the state grade and the potential operation risk of the rail transit system are presumed.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention may be realized and attained by the structure particularly pointed out in the written description and drawings.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can 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-system rail transit emergency collaborative decision-making method according to an embodiment of the invention;
FIG. 2 is a block diagram of a fuzzy Bayesian network model for fault evaluation and global operational state evaluation in accordance with an embodiment of the present invention;
FIG. 3 is a schematic illustration of the ambiguous significance of different level faults in system operation status assessment subject to minor faults;
fig. 4 is a flowchart of fuzzy bayesian network bursty fault assessment and global operational state assessment according to an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. 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 study field of emergency decision of emergency event has been made by students, the feature study content of emergency decision of emergency event is rich, but only the single feature is studied, and the common study between features is lacking. Considerable progress is made in the aspects of evaluation and evaluation methods and emergency decision-making systems for emergency plans, but in the aspects of investigation of emergency plans, investigation of influences of faults on a multi-system rail transit system and investigation of emergency treatment schemes are in scattered states.
Therefore, the invention provides a multi-system rail transit emergency collaborative decision-making method and device, and the multi-system rail transit emergency collaborative decision-making method and device comprises a multi-system rail transit emergency collaborative decision-making method, an electronic device and a computer readable storage medium.
According to the invention, by analyzing the characteristics of multi-system collaborative emergency treatment, the factors affecting multi-system operation by faults are subjected to deep analysis and quantitative calculation. Aiming at the problems of fuzzy sudden fault degree and uncertain global operation state of the multi-system rail transit system in the operation process, the improved Bayesian network fault evaluation and global operation state evaluation method based on the fusion fuzzy function is provided.
In a first aspect, as shown in fig. 1, the present invention provides a multi-system rail transit emergency collaborative decision-making method, which includes:
sorting historical data resources of equipment and multi-system rail transit system operation, classifying and quantifying data according to fault types and influence factor types;
counting samples, calculating prior probability and conditional probability of events of which the actual measurement values of various types of faults occur and influence factors take values, and constructing a three-layer Bayesian network containing influence factors, fault information and global operation states based on the correlation between the prior probability and the conditional probability of the events of which the actual measurement values of the influence factors take values;
Calculating and measuring the relative importance of all characteristic indexes under each fault mapping, and measuring the burst fault state;
determining severity grades corresponding to various faults, calculating fuzzy importance corresponding to various fault states, and calculating relative importance in global operation state evaluation of the system of each grade;
calculating the fuzzy weight of each sudden fault comprehensive index to obtain a fuzzy comprehensive grading value of the global operation state of the system to be evaluated, and obtaining the state grade according to the fuzzy comprehensive grading value;
and deciding an emergency scheme according to the fuzzy comprehensive grading value of the global operation state of the system.
In this embodiment, the classifying and quantifying the data according to the fault type and the influence factor type specifically includes:
according to whether the influence factors change with time and space and combining the business characteristics of multi-system rail transit operation, the influence factors are divided into four major categories which are time factors, space-time factors and space-time independent factors.
In this embodiment, the constructing a three-layer bayesian network including an influencing factor, fault information and a global operation state specifically includes:
based on implicit association knowledge in historical data resources of the multi-system rail transit system, an association relationship among a global operation state, fault information and influence factors of the three-layer Bayesian network description system is constructed;
The top layer is a global operation state layer of the multi-system rail transit system and is determined by integrating state information of all sudden faults; the middle layer is a fault information layer and is formed by the generated faults; the bottom layer is an influence factor layer and is composed of dynamic detection data, and is composed ofIndicating trouble->Aggregation of real-time monitoring indexes under mapping。
In this embodiment, the quantifying the relevance between the two based on bayesian probability specifically includes:
in order to describe the association relation between faults and influence factors, the measured value of the influence factors is measured by Bayesian probability to be the value(n is the number of possible values of the influencing factors), the degree of importance to the fault, i.e
；
Wherein:representing different sudden eventsA barrier event; x represents the value of the measured value of the influence factor of +.>Event of (2); />And->For the prior probability->The probability distribution in the historical sample data is utilized to approximate the probability which is obtained by sample statistics calculation.
In this embodiment, the calculating and measuring the relative importance of all the feature indexes under each fault mapping and measuring the burst fault state specifically includes:
on the basis of probability statistics on historical operation data resources of the multi-system rail transit system, adopting a Bayesian theorem to quantify association knowledge between influence factors and fault influence severity; meanwhile, in order to measure the fuzzy state of the fault, constructing an aging scoring function to integrate influence factor information with different timeliness under the mapping;
In order to describe the fuzzy degradation process of the fault state, the influence factor information with different timeliness under the mapping of the time effect function is constructed and integrated based on [0,1]A score value within the range quantitatively describes the fuzzy state of the sudden fault, and the lower the score value is, the higher the severity of the fault occurrence is. Recording deviceScoring the corresponding state of each sudden fault
；
Wherein:and->Respectively indicate malfunction->The number of the mapped influence factor reference evaluation indexes and the real-time monitoring indexes; alpha represents the effectiveness of the impact factor reference evaluation index in the fault state measure, and the interval time between the reference evaluation index sampling time point and the real-time evaluation time point (>) The longer the interval time, the lower the validity of the reference evaluation index data, the +.>F (x) is a continuous decreasing function, and is determined according to operation experience;describing the relative importance of influencing factors in the corresponding fault state measure,/for>In combination with bayesian probability computation:
。
in this embodiment, determining severity levels corresponding to various faults, calculating fuzzy importance corresponding to each fault state, and relative importance in global operation state evaluation of each level system specifically includes:
Based on the difference of the severity of the faults, the invention divides all the severity of the faults possibly occurring into 4 levels, and the higher the level is, the higher the corresponding severity is; in addition, the resistance of the multi-system rail transit system to sudden faults is different in different operation states, namely the damage caused by the multi-system rail transit system in different operation states is different due to the occurrence of the same fault; different fuzzy functions are constructed to respectively describe the occurrence of different level faults to multiple systems under different operation statesThe influence degree of the rail transit system is recorded as，/>，/>；
When the multi-system rail transit system is in the same running state, the degradation of the first-level fault only affects the stable operation of the system to a certain extent; for a secondary fault, the invention assumes that its fault condition is linearly related to its extent of impact on system operation; for three-level faults with high hazard, the degradation degree of the three-level faults can influence the safety and stable operation of the system when the degradation degree is low. On the basis, the invention adopts a Gaussian blur function, a triangular blur number and a parabolic blur membership function to describe the blur importance of different levels of faults respectively:
；
；
；
Wherein:for the variable parameter concerning l +.>，/>The method comprises the steps of carrying out a first treatment on the surface of the Parameters (parameters)And k is set according to the operation experience.
In this embodiment, the calculating the fuzzy weight of each sudden fault comprehensive indicator to obtain a fuzzy comprehensive score of the global operation state of the system to be evaluated, and obtaining the state level according to the fuzzy comprehensive score specifically includes:
the bayesian network model shows that the global operation state of the system is determined by integrating all state information of faults. Recording deviceDescribing the relative importance of the same fault in the evaluation of the global operational status of the system at different levels, wherein +.>，/>，/>；
And calculating to obtain the fuzzy weight coefficient in the system global operation state evaluation:
；
fuzzy comprehensive scoring value of the global operation state of the system: p=e×v, on the basis of which the state level at which the system is located is deduced.
In this embodiment, the decision on the emergency scheme according to the fuzzy comprehensive score value of the global operation state of the system specifically includes:
determining a current limiting level according to the range of the fuzzy comprehensive grading value P of the global operation state of the system;the value of (2) is selected according to experience or actual conditions;
adopting primary current limiting measures to limit the current of a payment area in the station;
Adopting a secondary current limiting measure to limit the current of a non-pay area in the station;
three-stage current limiting is adopted, and the current limiting measure is off-site current limiting;
adopting four-stage current limiting, wherein the current limiting measure is station sealing;
and determining an adjustment period for adjusting the running chart according to the fault influence time.
In a second aspect, the present invention provides a multi-system rail transit emergency collaborative decision-making device, including: the system comprises a classification quantization unit, a modeling unit, a model calculation unit and an emergency scheme unit;
the classification and quantization unit is used for sorting and quantizing historical data resources of equipment and multi-system rail transit system operation according to fault types and influence factor types;
the modeling unit is used for counting samples and calculating prior probability and conditional probability of events of which the actual measurement values of various types of faults occur and influence factors take values, and based on the correlation between the prior probability and the conditional probability, the modeling unit quantifies the correlation between the prior probability and the conditional probability, and constructs a three-layer Bayesian network containing influence factors, fault information and global operation states;
the model calculation unit is used for calculating and measuring the relative importance of all characteristic indexes under each fault mapping and measuring the burst fault state; determining severity grades corresponding to various faults, calculating fuzzy importance corresponding to various fault states, and calculating relative importance in global operation state evaluation of the system of each grade; calculating the fuzzy weight of each sudden fault comprehensive index to obtain a fuzzy comprehensive grading value of the global operation state of the system to be evaluated, and obtaining the state grade according to the fuzzy comprehensive grading value;
And the emergency scheme unit is used for deciding an emergency scheme according to the fuzzy comprehensive grading value of the global operation state of the system.
In specific implementation, the implementation processes of the multi-system rail transit emergency cooperative decision device and the multi-system rail transit emergency cooperative decision method are in one-to-one correspondence, and are not repeated here.
In a third aspect, the present invention provides an electronic device, including a processor, a communication interface, a memory, and a communication bus, where the processor, the communication interface, and the memory complete communication with each other through the communication bus;
a memory for storing a computer program;
and the processor is used for realizing the multi-system rail transit emergency collaborative decision method when executing the programs stored in the memory.
In a fourth aspect, the present invention provides a computer readable storage medium having stored thereon a computer program which when executed by a processor implements the multi-system rail transit emergency collaborative decision-making method described above.
The computer-readable storage medium may be embodied in the apparatus/means described in the above embodiments; or may exist alone without being assembled into the apparatus/device. The computer-readable storage medium carries one or more programs which, when executed, implement methods in accordance with embodiments of the present disclosure.
According to embodiments of the present disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium, which may include, for example, but is not limited to: a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this disclosure, a computer-readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
In order for those skilled in the art to better understand the present invention, the principles of the present invention are described below with reference to the accompanying drawings:
the emergency treatment condition is inevitably brought about by people, technology, management or environment, and the emergency condition brings about propagation, spreading and hazard expansion due to continuous expansion of the scale of a rail transit network and diversified development of a rail transit system, so that larger social influence is caused. The emergency treatment level of the multi-system rail transit is improved to ensure the stable and reliable operation of the transit system, and the emergency treatment level becomes a key problem facing each large city. The stable operation of facility equipment is the basis of the safe and stable operation of a rail transit system, and the fault of the facility equipment has great influence on the operation.
The panoramic running state of the rail transit system is polymorphic and uncertain under the influence of various uncertain factors and sudden events, and the safety and stable running of the rail transit system are threatened. Along with the development of information detection and storage technology, a large amount of characteristic index change and historical fault information of the data resource description equipment in operation are accumulated in the rail transit system, and useful associated knowledge is extracted from the multidimensional data with different timeliness, so that sudden fault evaluation and influence degree evaluation on operation in the operation process of the rail transit system are realized, and the method has very important theoretical research and engineering application values.
1 multi-system cooperative emergency treatment feature
Because the emergency has the characteristics of uncertainty, dynamic property and the like, the conditions of various information, dynamic information change and the like usually exist in the evolution process, so that a decision maker is difficult to obtain reasonable decision results in a short time, the existing emergency decision method is biased to the selection of an emergency treatment scheme for the emergency, the influence of the emergency on the rail transit operation organization is not analyzed, and the effective decision of the emergency scheme of each system is difficult to realize.
2 Multi-System operation factor analysis for Equipment failure influence
The rail transit infrastructure is linear and continuously distributed, the influence degree of faults on multi-system operation is influenced by various factors, and the influence conditions of the same faults in different time ranges and space ranges on the operation are different, for example, the influence of the faults in early peak time periods on the operation is larger than Yu Pingfeng time periods, and the influence of the faults in stations with multi-line transfer on the operation is larger than that of stations with non-transfer, and the like. These influencing factors are closely related to time and space, and the influencing factors of different time ranges and different space positions are different, and the quantitative value of the influencing factors is difficult. According to whether the influence factors change with time and space, and combining the service characteristics of multi-system rail transit operation, authors divide the influence factors into four major categories, namely time factors, space-time factors and space-time independent factors, and the specific division and the example are shown in table 1.
Table 1 Fault influencing Multi-System operation factor partitioning
3 Emergency decision model construction based on fuzzy reasoning
3.1 Bayesian network failure assessment and Global operational State evaluation model construction
The influence factor data required by fault evaluation and global operation state evaluation can be divided into two major types of static basic data consisting of an initial value and a limiting threshold value (a value range) and dynamic data which can be acquired in real time, and the two major types have different timeliness. Recording the real-time detection index of each influence factor as. The severity of the fault consequences is divided into four classes: catastrophic, critical, mild. Thus, the severity of the consequences of a fault affecting operation in the present invention is classified as catastrophic, critical, slight, noted +.>。
The invention aims to identify potential risks based on the fuzzy states of static basic data and dynamic data resource measurement faults, thereby realizing the evaluation of global operation states. The Bayesian network is a probability graph which utilizes priori knowledge to establish association constraint relation among random variables, and the dependency relation among the random variables is represented by nodes and directional arrows, so that the Bayesian network has good capability of processing uncertainty logic relation. The invention constructs the association relation among the global operation state, the fault information and the influence factors of the three-layer Bayesian network description system based on the implicit association knowledge in the historical data resources of the multi-system rail transit system, as shown in figure 2. The top layer is a global operation state layer of the multi-system rail transit system and is determined by integrating state information of all sudden faults; the middle layer is a fault information layer and is formed by the generated faults; the bottom layer is an influence factor layer and consists of dynamic detection data, Indicating trouble->And (5) monitoring the set of indexes in real time under mapping.
3.2 data-driven Bayesian network fault assessment
In order to describe the association relation between the multi-dimensional and heterogeneous influence factors and faults, on the basis of probability statistics on historical operation data resources of the multi-system track traffic system, the Bayesian theorem is adopted to quantify the association knowledge between the influence factors and the severity of the fault influence. Meanwhile, in order to measure the fuzzy state of the fault, an aging scoring function is constructed to integrate the influence factor information with different timeliness under the mapping.
(1) Extraction of fault information associated knowledge
In order to describe the association relation between faults and influence factors, the measured value of the influence factors is measured by adopting Bayesian probability and is taken as the value based on the assignment method（nPossible extraction of factorsThe number of values), the degree of importance to the fault, i.e
（1）
Wherein:representing different sudden fault events; x represents the value of the measured value of the influence factor of +.>Event of (2); />And->For the prior probability->The probability distribution in the historical sample data is utilized to approximate the probability which is obtained by sample statistics calculation.
(2) Fuzzy fault state measurement
In the operation process of multi-system rail transit, the states corresponding to the sudden faults are not only determined to be 'generated' and 'not generated', but are converted from 'generated' to 'influencing operation', and a series of variable fuzzy intermediate states can be experienced during the period of 'generating' and 'influencing operation'. In order to describe the fuzzy degradation process of the fault state, the influence factor information with different timeliness under the mapping of the time effect function is constructed and integrated based on [0,1 ]A score value within the range quantitatively describes the fuzzy state of the sudden fault, and the lower the score value is, the higher the severity of the fault occurrence is. Recording deviceScoring the corresponding state of each sudden fault
（2）
Wherein:and->Respectively indicate malfunction->The number of the mapped influence factor reference evaluation indexes and the real-time monitoring indexes; alpha represents the effectiveness of the impact factor reference evaluation index in the fault state measure, and the interval time between the reference evaluation index sampling time point and the real-time evaluation time point (>) The longer the interval time, the lower the validity of the reference evaluation index data, the +.>F (x) is a continuous decreasing function, and is determined according to operation experience;describing the relative importance of influencing factors in the corresponding fault state measure,/for>In combination with bayesian probability computation:
（3）
3.3 fuzzy reasoning for Bayesian network multi-state evaluation
The degree of influence of the occurrence of different faults on the operation of multi-system rail transit is unbalanced, and the relative importance of different fault states in the overall operation state evaluation of the system is in fuzzy change. Therefore, on the basis of classifying the severity level of all faults, different fuzzy functions are adopted to describe the fuzzy importance of the faults in different states, and the evaluation of the global operation state of the system is realized by integrating all fault state information.
(1) Fuzzy significance description of fault state information in system global operation state evaluation
Based on the difference of the severity of the faults, the invention divides all the severity of the faults possibly occurring into 4 levels, and the higher the level is, the higher the severity is correspondingly. In addition, the resistance of the multi-system rail transit system to sudden faults in different operation states is different, namely the damage caused by the multi-system rail transit system in different operation states is different due to the occurrence of the same fault. Therefore, the invention constructs different fuzzy functions to respectively describe the influence degree of the occurrence of different grade faults on the multi-system track traffic system under different operation states, which is recorded as，/>，/>Taking as an example the system in an operating state subject to a slight fault, as shown in fig. 3.
When the multi-system rail transit system is in the same running state, the degradation of the first-level fault only affects the stable operation of the system to a certain extent; for a secondary fault, the invention assumes that its fault condition is linearly related to its extent of impact on system operation; for three-level faults with high hazard, the degradation degree of the three-level faults can influence the safety and stable operation of the system when the degradation degree is low. On the basis, the invention adopts a Gaussian blur function, a triangular blur number and a parabolic blur membership function to describe the blur importance of different levels of faults respectively:
（4）
（5）
（6）
Wherein:to be aboutlVariable parameter of->，/>The method comprises the steps of carrying out a first treatment on the surface of the Parameter->Andkaccording to the operation experience.
(2) Fuzzy inference of system global operational state
As can be seen from the bayesian network model of fig. 2, the global operation state of the system is determined by integrating all the state information of the faults. Recording deviceDescribing the relative importance of the same fault in the evaluation of the global operational status of the system at different levels, wherein +.>，/>，/>. And calculating to obtain the fuzzy weight coefficient in the system global operation state evaluation:
（7）
fuzzy comprehensive scoring value of the global operation state of the system: p=e×v, on the basis of which the state level at which the system is located is deduced.
(3) Emergency treatment level determination
1) Class of current limiting measures
And determining the current limiting level according to the range of the fuzzy comprehensive grading value P of the global operation state of the system.The value of (2) is chosen empirically or in practice.
Adopting primary current limiting measures to limit the current of a payment area in the station;
adopting a secondary current limiting measure to limit the current of a non-pay area in the station;
three-stage current limiting is adopted, and the current limiting measure is off-site current limiting;
four-stage current limiting is adopted, and the current limiting measure is station sealing.
2) Determining an adjustment period for adjusting a driving pattern
According to the time of failureAnd determining an adjustment period for adjusting the driving operation diagram.
3.4 implementation steps of the fuzzy Bayesian network fault evaluation and global operation state evaluation method
And extracting the associated knowledge between the faults and the influencing factors from the historical data resources, measuring the fuzzy fault state, and diagnosing the potential risk of the fuzzy fault state. On the basis, the importance degree of different faults on the global operation state of the system under different levels is described by adopting fuzzy numbers, and the global operation state level of the system is deduced through the integration of all fault state information. As shown in fig. 4, the specific implementation steps are as follows:
step 1: and sorting historical data resources of equipment and multi-system rail transit system operation, and classifying data according to fault types and influence factor types.
Step 2: and counting samples, calculating prior probability and conditional probability of events of which the actual measurement values of various types of faults occur and influence factors take values, quantifying the relevance between the prior probability and the conditional probability based on Bayesian probability (formula (1)), and constructing a three-layer Bayesian network containing influence factors, fault information and global operation states. The construction of the Bayesian network and the construction of the fault function are based on extracting the associated knowledge between the fault and the influencing factors.
Step 3: and calculating and measuring the relative importance of all characteristic indexes under each fault mapping based on the formula (3), and further measuring the burst fault state according to the formula (2).
Step 4: determining severity levels corresponding to various faults, calculating fuzzy importance corresponding to various fault states according to formulas (4) - (6), and calculating relative importance in global operation state evaluation of the system at various levels.
Step 5: and (3) calculating the fuzzy weight of each sudden fault comprehensive index according to the formula (7), obtaining a fuzzy comprehensive grading value of the global operation state of the system to be evaluated, and obtaining the state grade according to the fuzzy comprehensive grading value.
Step 6: and deciding an emergency scheme according to the fuzzy comprehensive grading value of the global operation state of the system.
The rail transit infrastructure is linear and continuously distributed, the influence degree of faults on multi-system operation is influenced by various factors, and the influence conditions of the same faults in different time ranges and space ranges on the operation are different, for example, the influence of the faults in early peak time periods on the operation is larger than Yu Pingfeng time periods, and the influence of the faults in stations with multi-line transfer on the operation is larger than that of stations with non-transfer, and the like. These influencing factors are closely related to time and space, and the influencing factors of different time ranges and different space positions are different, and the quantitative value of the influencing factors is difficult. According to whether the influence factors change with time and space, the service characteristics of multi-system rail transit operation are combined, the factors influencing the multi-system operation by faults are deeply analyzed, the influence factors are divided into four major categories, namely time factors, space-time factors and factors irrelevant to space and time, and a quantitative calculation method of the factors is provided.
Based on static basic data and dynamic detection data related to equipment operation and system operation states, the invention realizes the measurement of the sudden fault fuzzy state and the quantitative evaluation of the system global operation state in stages, and solves the uncertainty problem of sudden fault state fuzzy and global operation state conversion. The emergency treatment strategy obtained by combining the system characteristics and the associated knowledge implicit in the data can be closer to the actual situation, has higher credibility, and is beneficial to the efficient treatment of the emergency event by the manager.
Because the emergency event has the characteristics of uncertainty, dynamic property and the like, the conditions of various information, dynamic information change and the like usually exist in the evolution process, so that a decision maker is difficult to obtain reasonable decision results in a short time, the existing emergency decision method for the emergency fault is biased to the selection of an emergency disposal scheme for the event, the influence of the emergency event on the rail transit operation organization is not analyzed, and the effective allocation of emergency resources of various systems is difficult to realize.
The invention fully utilizes the accumulated data resources in the operation of the multi-system track traffic system, constructs the aging scoring function to quantify the fuzzy state of the fault, adopts different fuzzy functions to describe the importance degree of the fault in the overall operation state evaluation of the system based on the severity degree difference of the fault, improves the evaluation of the severity degree of the sudden fault and the overall operation state evaluation of the multi-system track traffic system by a Bayesian network method, and solves the limitation of the prior method. In the process of measuring the fuzzy fault state, not only the relevance between the influence factors and the fault occurrence is considered, but also the time efficiency difference is reflected; based on different severity of faults, different fuzzy functions are adopted to describe the influence degree of different fault states on the global operation of the system, the integration of all fault state information of the system is realized, and the accuracy of the global operation state evaluation of the system is improved. The emergency treatment strategy obtained by combining the system characteristics and the associated knowledge implicit in the data can be closer to the actual situation, has higher credibility, and is beneficial to the efficient treatment of the emergency event by the manager.
Although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (8)
1. The multi-system rail transit emergency collaborative decision-making method is characterized by comprising the following steps of:
sorting historical data of equipment and multi-system rail transit system operation, and classifying and quantifying the data according to fault types and influence factor types in the historical data;
counting the quantized data, calculating prior probability and conditional probability of events of various types of faults and actual measurement values of influencing factors, and constructing a Bayesian network based on the correlation between the prior probability and the conditional probability of the events of various types of faults and actual measurement values of influencing factors;
based on the Bayesian network, calculating and measuring the relative importance of all characteristic indexes under each fault mapping, constructing a time-varying scoring function of the fault state, and measuring the burst fault state;
when the sudden fault occurs, collecting actual measurement values of all influence factors of the fault to be evaluated, and calculating grading values of all fault states based on a time-varying grading function; determining severity grades corresponding to various faults, calculating fuzzy importance corresponding to various fault states, and calculating relative importance in global operation state evaluation of the system of each grade;
Based on the Bayesian network, calculating the fuzzy weight of each sudden fault comprehensive index, and calculating the fuzzy comprehensive scoring value of the global operation state of the system to be evaluated;
obtaining the state grade of the system according to the fuzzy comprehensive grading value of the global operation state of the system, and deciding an emergency scheme;
the correlation between the two based on Bayesian probability quantification specifically comprises the following steps:
based on the association relation between the Bayesian probability quantification fault and the influence factors, adopting the Bayesian probability to measure the actual measurement value of the influence factors as the valueThe degree of importance of the event of (a) to the fault, i.e
；
Wherein: n represents the number of possible values of the influencing factor,representing different sudden failure events +.>Indicating the occurrence of sudden failure->Event of (2)>Indicating that sudden failure ∈>State of (2); x represents the value of the measured value of the influence factor of +.>Event of (2); />And->For the prior probability->For conditional probability +.>、/>And->The historical sample data are counted to obtain;
the calculating and measuring the relative importance of all the characteristic indexes under each fault mapping and measuring the burst fault state specifically comprises the following steps:
on the basis of probability statistics on historical operation data resources of the multi-system rail transit system, adopting Bayesian theorem to quantify correlation knowledge between influence factors and fault influence severity, and constructing an aging scoring function to integrate influence factor information with different timeliness under the mapping;
Constructing an aging scoring function to integrate influence factor information with different timeliness under the mapping, wherein the method comprises the following steps of: based on [0,1 ]]Scoring values in the range quantitatively describe the fuzzy state of the sudden fault; scoring value of corresponding state of each burst faultCalculated by the following formula:
；
wherein:and->Respectively indicate malfunction->The number of the mapped influence factor reference evaluation indexes and the real-time monitoring indexes; alpha represents the effectiveness of the influence factor reference evaluation index in the fault state measure and is equal to the sampling time point of the reference evaluation indexReal-time evaluation time->The length of the interval time between the two is related; />Representing the relative importance of influencing factors in the corresponding fault state measure,/for>In combination with bayesian probability computation:
；
the determining the severity level corresponding to each fault, calculating the fuzzy importance corresponding to each fault state and the relative importance in the global operation state evaluation of each level system specifically comprises the following steps:
based on the difference of fault severity, dividing all fault severity possibly occurring into a plurality of stages, constructing different fuzzy functions to respectively describe the influence degree of the occurrence of different level faults on the multi-system rail transit system under different operation states, wherein the influence degree is recorded as Fault severity level->Operation state grade of multi-system traffic system；
The fuzzy importance of the first-level faults is represented by a Gaussian fuzzy function, the fuzzy importance of the second-level faults is represented by a triangular fuzzy number, the fuzzy importance of the third-level faults is represented by a parabolic fuzzy membership function, and the formula is expressed as follows in sequence:
；
；
；
wherein:to the operation state level of the multi-system traffic systemlIs used for the control of the temperature of the liquid crystal display,，/>the method comprises the steps of carrying out a first treatment on the surface of the Parameter->And k is set according to operation experience;
calculating the fuzzy weight of each sudden fault comprehensive index to obtain a fuzzy comprehensive grading value of the global operation state of the system to be evaluated, and obtaining the state grade according to the fuzzy comprehensive grading value, wherein the method specifically comprises the following steps:
the global operation state of the system is determined by integrating all the state information of faults;indicating the same reasonRelative importance of barriers in system global operation status assessment at different levels, wherein，/>，/>；
Calculating fuzzy weight coefficients in the system global operation state evaluation:
；
the fuzzy comprehensive grading value of the global operation state of the system is P=E×V, and the state grade is obtained according to the grading P.
2. The multi-system rail transit emergency collaborative decision-making method according to claim 1, characterized in that,
The data classification and quantification are carried out according to the fault type and the influence factor type, and specifically comprise the following steps:
according to whether the influence factors change with time and space and combining the business characteristics of multi-system rail transit operation, the influence factors are divided into a plurality of categories including time factors, space-time factors and space-time independent factors.
3. The multi-system rail transit emergency collaborative decision-making method according to claim 1, characterized in that,
the construction of the Bayesian network specifically comprises the following steps:
based on the implicit association knowledge in the historical data resources of the multi-system rail transit system, a three-layer Bayesian network containing influence factors, fault information and global operation states is constructed and used for describing the association relationship among the global operation states, the fault information and the influence factors of the system.
4. A multi-system rail transit emergency collaborative decision-making method according to any one of claims 1-3, characterized in that,
the bayesian network comprises:
the top layer of the Bayesian network is a global operation state layer of the multi-system rail transit system, and is determined by integrating state information of all sudden faults;
the Bayesian network middle layer is a fault information layer and consists of generated faults Constructing;
the Bayesian network bottom layer is an influence factor layer and is formed by dynamically detecting dataA is a real-time monitoring index a corresponding to a fault set I 1 ...a k Is a set of (3).
5. The multi-system rail transit emergency collaborative decision-making method according to claim 1, characterized in that,
the decision emergency scheme according to the fuzzy comprehensive grading value of the global operation state of the system specifically comprises the following steps:
determining a current limiting level according to the range of the fuzzy comprehensive grading value P of the global operation state of the system;the value of (2) is selected according to experience or actual conditions;
adopting primary current limiting measures to limit the current of a payment area in the station;
adopts a secondary current limiting and current limiting measureApplying a current limit to a non-pay zone within the station;
three-stage current limiting is adopted, and the current limiting measure is off-site current limiting;
adopting four-stage current limiting, wherein the current limiting measure is station sealing;
and determining an adjustment period for adjusting the running chart according to the fault influence time.
6. The utility model provides a emergent collaborative decision-making device of multisystem track traffic which characterized in that includes: the system comprises a classification and quantization unit, a modeling unit, an evaluation unit and an emergency scheme unit;
the classification and quantization unit is used for sorting and quantizing historical data resources of equipment and multi-system rail transit system operation according to fault types and influence factor types;
The modeling unit is used for counting samples and calculating prior probability and conditional probability of events of various types of faults and actual measurement values of influencing factors, and constructing a Bayesian network based on correlation between the prior probability and the conditional probability of the events of various types of faults and actual measurement values of influencing factors; based on the Bayesian network, calculating and measuring the relative importance of all characteristic indexes under each fault mapping, constructing a time-varying scoring function of the fault state, and measuring the burst fault state;
the evaluation unit is used for collecting actual measurement values of all influence factors of the fault to be evaluated when the sudden fault occurs, and calculating the grading value of each fault state based on a time-varying grading function; determining severity grades corresponding to various faults, calculating fuzzy importance corresponding to various fault states, and calculating relative importance in global operation state evaluation of the system of each grade; based on the Bayesian network, calculating the fuzzy weight of each sudden fault comprehensive index, and calculating the fuzzy comprehensive scoring value of the global operation state of the system to be evaluated;
the emergency scheme unit is used for obtaining a state grade decision emergency scheme according to the fuzzy comprehensive grading value of the global operation state of the system;
the correlation between the two based on Bayesian probability quantification specifically comprises the following steps:
Based on the association relation between the Bayesian probability quantification fault and the influence factors, adopting the Bayesian probability to measure the actual measurement value of the influence factors as the valueThe degree of importance of the event of (a) to the fault, i.e
；
Wherein: n represents the number of possible values of the influencing factor,representing different sudden failure events +.>Indicating the occurrence of sudden failure->Event of (2)>Indicating that sudden failure ∈>State of (2); x represents the value of the measured value of the influence factor of +.>Event of (2); />And->For the a priori probabilities,/>for conditional probability +.>、/>And->The historical sample data are counted to obtain;
the calculating and measuring the relative importance of all the characteristic indexes under each fault mapping and measuring the burst fault state specifically comprises the following steps:
on the basis of probability statistics on historical operation data resources of the multi-system rail transit system, adopting Bayesian theorem to quantify correlation knowledge between influence factors and fault influence severity, and constructing an aging scoring function to integrate influence factor information with different timeliness under the mapping;
constructing an aging scoring function to integrate influence factor information with different timeliness under the mapping, wherein the method comprises the following steps of: based on [0,1 ]]Scoring values in the range quantitatively describe the fuzzy state of the sudden fault; scoring value of corresponding state of each burst fault Calculated by the following formula:
；
wherein:and->Respectively indicate malfunction->The number of the mapped influence factor reference evaluation indexes and the real-time monitoring indexes; alpha represents the effectiveness of the influence factor reference evaluation index in the fault state measure and is equal to the sampling time point of the reference evaluation indexReal-time evaluation time->The length of the interval time between the two is related; />Representing the relative importance of influencing factors in the corresponding fault state measure,/for>In combination with bayesian probability computation:
；
the determining the severity level corresponding to each fault, calculating the fuzzy importance corresponding to each fault state and the relative importance in the global operation state evaluation of each level system specifically comprises the following steps:
based on the difference of fault severity, dividing all fault severity possibly occurring into a plurality of stages, constructing different fuzzy functions to respectively describe the influence degree of the occurrence of different level faults on the multi-system rail transit system under different operation states, wherein the influence degree is recorded asFault severity level->Operation state grade of multi-system traffic system；
The fuzzy importance of the first-level faults is represented by a Gaussian fuzzy function, the fuzzy importance of the second-level faults is represented by a triangular fuzzy number, the fuzzy importance of the third-level faults is represented by a parabolic fuzzy membership function, and the formula is expressed as follows in sequence:
；
；
；
Wherein:to the operation state level of the multi-system traffic systemlIs used for the control of the temperature of the liquid crystal display,，/>the method comprises the steps of carrying out a first treatment on the surface of the Parameter->And k is set according to operation experience;
calculating the fuzzy weight of each sudden fault comprehensive index to obtain a fuzzy comprehensive grading value of the global operation state of the system to be evaluated, and obtaining the state grade according to the fuzzy comprehensive grading value, wherein the method specifically comprises the following steps:
the global operation state of the system is determined by integrating all the state information of faults;indicating that the same fault is at different levelsRelative importance in system global operational state assessment, wherein，/>，/>；
Calculating fuzzy weight coefficients in the system global operation state evaluation:
；
the fuzzy comprehensive grading value of the global operation state of the system is P=E×V, and the state grade is obtained according to the grading P.
7. The electronic equipment is characterized by comprising a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory are communicated with each other through the communication bus;
a memory for storing a computer program;
the processor is used for realizing the multi-system rail transit emergency collaborative decision-making method according to any one of claims 1-5 when executing the program stored in the memory.
8. A computer readable storage medium having stored thereon a computer program, wherein the computer program when executed by a processor implements the multi-system rail transit emergency collaborative decision-making method of any of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311017094.9A CN116739391B (en) | 2023-08-14 | 2023-08-14 | Multi-system rail transit emergency collaborative decision-making method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311017094.9A CN116739391B (en) | 2023-08-14 | 2023-08-14 | Multi-system rail transit emergency collaborative decision-making method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116739391A CN116739391A (en) | 2023-09-12 |
| CN116739391B true CN116739391B (en) | 2024-01-19 |
Family
ID=87902962
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311017094.9A Active CN116739391B (en) | 2023-08-14 | 2023-08-14 | Multi-system rail transit emergency collaborative decision-making method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116739391B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111724076A (en) * | 2020-06-24 | 2020-09-29 | 西南交通大学 | Regional multi-type rail transit passenger flow dynamic distribution method under operation interruption condition |
| CN115938124A (en) * | 2022-12-29 | 2023-04-07 | 南昌轨道交通集团有限公司 | Urban rail transit emergency influence prediction method, system and product |
| CN116011813A (en) * | 2022-12-28 | 2023-04-25 | 交控科技股份有限公司 | Urban rail transit emergency monitoring method and device, electronic equipment and storage medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11004333B2 (en) * | 2018-11-29 | 2021-05-11 | International Business Machines Corporation | Detecting influential factors for traffic congestion |
-
2023
- 2023-08-14 CN CN202311017094.9A patent/CN116739391B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111724076A (en) * | 2020-06-24 | 2020-09-29 | 西南交通大学 | Regional multi-type rail transit passenger flow dynamic distribution method under operation interruption condition |
| CN116011813A (en) * | 2022-12-28 | 2023-04-25 | 交控科技股份有限公司 | Urban rail transit emergency monitoring method and device, electronic equipment and storage medium |
| CN115938124A (en) * | 2022-12-29 | 2023-04-07 | 南昌轨道交通集团有限公司 | Urban rail transit emergency influence prediction method, system and product |
Non-Patent Citations (3)
| Title |
|---|
| 城市交通系统安全运营状态风险评估——以北京市轨道交通为例;刘福泽 等;《管理评论》;第32卷(第7期);第219-224页 * |
| 基于时效评分函数和贝叶斯概率的电力变压器状态实时评估;孙鹏 等;《高电压技术》;第44卷(第4期);第1071-1075页 * |
| 基于贝叶斯网络的高速公路突发事件态势评估研究;赵朋;王建伟;孙茂棚;周雅欣;;公路交通科技(第09期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116739391A (en) | 2023-09-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11335179B1 (en) | Water environment risk prediction and early warning method | |
| Jakaria et al. | Smart weather forecasting using machine learning: a case study in tennessee | |
| CN110059963A (en) | A kind of tunnel risk evaluating method based on fuzzy polymorphism Bayesian network | |
| CN109657880A (en) | A kind of Collision Accidents of Ships grade prediction technique and system based on Bayesian network | |
| CN116777223B (en) | Urban underground pipe network safety comprehensive risk assessment method and system | |
| CN105678481A (en) | Pipeline health state assessment method based on random forest model | |
| Cheng et al. | Obstacle diagnosis of green competition promotion: a case study of provinces in China based on catastrophe progression and fuzzy rough set methods | |
| CN109947806A (en) | A kind of Super High construction safety accident emergency aid decision-making method of case-based reasioning | |
| CN106530715A (en) | Road network traffic state prediction method based on fuzzy Markov process | |
| CN112529327A (en) | Method for constructing fire risk prediction grade model of buildings in commercial areas | |
| Liu et al. | A comprehensive risk analysis of transportation networks affected by rainfall‐induced multihazards | |
| CN104318717A (en) | Rainstorm debris flow early warning method under shortage conditions of historical data | |
| CN112465304A (en) | Railway turnout area train derailment accident assessment method based on Bayesian network | |
| CN112418571A (en) | Method and device for enterprise environmental protection comprehensive evaluation | |
| CN116720324A (en) | Traction substation key equipment fault early warning method and system based on prediction model | |
| CN113837473A (en) | Charging equipment fault rate analysis system and method based on BP neural network | |
| Wujie et al. | Analyzing and predicting railway operational accidents based on fishbone diagram and Bayesian networks | |
| CN117078191A (en) | Data-driven multi-system rail transit emergency collaborative decision-making method and device | |
| CN116739391B (en) | Multi-system rail transit emergency collaborative decision-making method and device | |
| Giardina et al. | Fuzzy environmental analogy index to develop environmental similarity maps for designing air quality monitoring networks on a large-scale | |
| CN112434887A (en) | Water supply network risk prediction method combining network kernel density estimation and SVM | |
| Bu et al. | Factors affecting the resilience of subway operations under emergencies–using improved DEMATEL model | |
| Dunea et al. | Fuzzy inference systems for estimation of air quality index | |
| CN115906669A (en) | Dense residual error network landslide susceptibility evaluation method considering negative sample selection strategy | |
| Hosseinlou et al. | Predicting and identifying traffic hot spots applying neuro-fuzzy systems in intercity roads |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |