CN110427015A - A kind of boiler afterheat explosion accident diagnostic analysis method - Google Patents
A kind of boiler afterheat explosion accident diagnostic analysis method Download PDFInfo
- Publication number
- CN110427015A CN110427015A CN201910711426.0A CN201910711426A CN110427015A CN 110427015 A CN110427015 A CN 110427015A CN 201910711426 A CN201910711426 A CN 201910711426A CN 110427015 A CN110427015 A CN 110427015A
- Authority
- CN
- China
- Prior art keywords
- explosion accident
- waste heat
- fuzzy
- root node
- heat boiler
- 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
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B23/00—Testing or monitoring of control systems or parts thereof
- G05B23/02—Electric testing or monitoring
- G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
- G05B23/0259—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterized by the response to fault detection
- G05B23/0262—Confirmation of fault detection, e.g. extra checks to confirm that a failure has indeed occurred
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/20—Pc systems
- G05B2219/24—Pc safety
- G05B2219/24065—Real time diagnostics
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
A kind of boiler afterheat explosion accident diagnostic analysis method, belong to waste heat boiler accident diagnosis analysis field, the present invention provides a kind of diagnosis efficiency height, maintenance cost is low, the generation that can prevent accident, the boiler afterheat explosion accident diagnostic analysis method that can guarantee waste heat boiler safe operation.In the present invention, construct Bayesian network model, obtain the root node prior probability of waste heat boiler fault model, obtain the posterior probability of root node, establish influence factor collection, establish evaluate collection, determine the fuzzy matrix for assessment of list influence factor, determine factorial power sets, calculate the fuzzy comprehensive evoluation matrix of waste heat boiler explosion accident factorial power sets, posterior probability is diagnosed to be by Bayesian network diagnostic method, comprehensive diagnos is carried out in conjunction with Judgement Method, and to its influence factor descending progress sequence, to obtain the sequence of boiler afterheat explosion accident factor.Present invention is mainly used for the diagnosis of boiler afterheat explosion accident.
Description
Technical field
The invention belongs to waste heat boiler accident diagnosis analysis fields, and in particular to a kind of boiler afterheat explosion accident diagnosis point
Analysis method.
Background technique
With the rapid development of economy, people more and more pay attention to the utilization rate and environmental issue of the energy.In this background
Under, waste heat boiler is increasingly paid attention to by enterprise as general energy device, to improve the utilization efficiency of the energy.With waste heat pot
A large amount of uses of furnace, safety problem are also increasingly paid attention in the industry.Waste heat boiler is useless by what is generated in industrial processes
Gas, waste material, waste liquid heat water is heated generate steam or hot water and be supplied to other technical process, system is extremely complex, holds
The unexpected release of energy is easily caused greatly to threaten people and equipment belt, especially bursting of boilers problem, influence more very.Cause
This, is carried out fault diagnosis to waste heat boiler accident, finds the main factor of accident, the generation again prevented accident with this.With
A large amount of uses of waste heat boiler, safety problem are also increasingly paid attention in the industry.In view of pressure-bearing class special equipment belongs to height can
By property system, fault rate is often very low, can not obtain a large amount of data, the destructive testing of this kind of more complex system
It is with high costs, it obtains a large amount of visual test data and does not also have economic feasibility, Bayesian network is asked for solving uncertainty
Topic and data deficiencies problem have great advantage, and are once considered as solving the optimal selection of uncertain problem, therefore by Bayes
Network application is into waste heat boiler accident diagnosis.From at present to the research of diagnostic techniques from the point of view of, Most scholars will diagnose problem
Core concentrate on diagnosis accuracy on, but we should also consider diagnosis economy problems.
It is therefore desirable to which a kind of diagnosis efficiency is high, maintenance cost is low, the generation that can prevent accident, can guarantee waste heat pot
The boiler afterheat explosion accident diagnostic analysis method of furnace safe operation.
Summary of the invention
The present invention is for existing diagnostic analysis method diagnosis efficiency is low, maintenance cost is high, the generation that cannot prevent accident, no
The defect that can guarantee waste heat boiler safe operation, provides that a kind of diagnosis efficiency is high, maintenance cost is low, can prevent accident hair
Boiler afterheat explosion accident diagnostic analysis method that is raw, can guaranteeing waste heat boiler safe operation.
A kind of technical solution of boiler afterheat explosion accident diagnostic analysis method according to the present invention is as follows:
A kind of boiler afterheat explosion accident diagnostic analysis method according to the present invention, it the following steps are included:
Step 1: building Bayesian network model: according to waste heat boiler explosion accident determine Bayesian network node and
Causality;Knowledge base is established, Bayesian network is constructed according to rule-based knowledge base, establishes the Bayes of waste heat boiler explosion accident
Network model:
Step 2: obtaining the root node prior probability of waste heat boiler fault model: where the root node prior probability packet
It includes root node to break down probability and root node exact probability, for node existing for historical data, take according to historical data
Method its fault occurrence frequency, as root section are calculated according to the number that root node breaks down in recent years in historical data
Put the probability that breaks down;Or the not root node of historical data incomplete for historical data, linguistic variable is carried out at blurring
It manages to get root node exact probability is arrived;
Step 3: obtaining the posterior probability of root node: the Bayesian network uses directed acyclic graph mode, passes through pattra leaves
This network reasoning obtains the posterior probability of waste heat boiler explosion accident;
Step 4: establishing influence factor collection: by carrying out fuzzy evaluation to each root node, wherein the influence of root node
Factor includes the complexity u of detection method1, detection speed u2, detection accuracy u3With the economy u of detection4, establish shadow
Ring set of factors U={ u1,u2,u3,u4};
Step 5: establishing evaluate collection: according to the practical operation situation of afterheat boiler system, obtaining system in the process of running
Fault message, PASCAL evaluation PASCAL is carried out to diagnostic result, and 5 level models is divided into, evaluate collection is established, in conjunction with influence factor
It determines linguistic variable, the linguistic variable is indicated with membership function;
Step 6: determining the fuzzy matrix for assessment of list influence factor: it gives a mark to the influence factor of each grade, score value
It is calculated by hundred-mark system, obtained score substitutes into membership function, after normalized, obtains V1Single influence factor of grade is fuzzy
Jdgement matrix;
Remaining grade V2, V3, V4, the fuzzy matrix for assessment table of the influence factor membership function of V5 are obtained according to same method
Up to formula;Score is substituted into expression formula to get to single influence factor fuzzy evaluating matrix R of i-th of nodei;
Step 7: determining factorial power sets: factorial power sets are influence degree of a certain factor to system jam
Set, the flexible strategy of factor are obtained by analytic hierarchy process (AHP);Analytic hierarchy process (AHP) is to be compared factor two-by-two, is divided by significance level
At 5 grades, respectively 1,3,5,7,9;Through normalized, the factorial power sets expression formula for obtaining i-th of node is Ai;
Step 8: calculating the fuzzy comprehensive evoluation matrix of waste heat boiler explosion accident factorial power sets;Bi=Ai·Ri;
Step 9: comprehensive diagnos: posterior probability is diagnosed to be by Bayesian network diagnostic method, in conjunction with fuzzy evaluation side
Method judges out fuzzy comprehensive evoluation weighted value when each root node considers four factors, is examined by above two method synthesis
It is disconnected, determine that comprehensive diagnos formula is Di=di·qi;Obtain when waste heat boiler occur explosion time, and to its influence factor by greatly to
Small progress sequence, to obtain the sequence of boiler afterheat explosion accident factor.
Further: the membership function includes Triangle-Profile, normal distribution, trapezoidal profile and the distribution of LR type;In step
In rapid five, the membership function handles the linguistic variable of evaluate collection using Triangle-Profile.
Further: in step 6, the fuzzy matrix for assessment of waste heat boiler explosion accident root node is as follows:
……
Further: in step 7, the factorial power sets expression formula of i-th of node are as follows:
Ai=(A1 i A2 i A3 i A4 i);
The weight sets of the waste heat boiler explosion accident influence factor is as follows:
A1=(0.2 0.4 0.2 0.2);
A2=(0.2 0.2 0.3 0.3);
A3=(0.2 0.3 0.2 0.3);
……
A17=(0.1 0.2 0.3 0.4);
A18=(0.3 0.1 0.5 0.1).
Further: in step 8, the fuzzy comprehensive evoluation matrix of the waste heat boiler explosion accident factorial power sets
Are as follows:
BiFor X1Fuzzy comprehensive evoluation matrix;
AiFor X1Factorial power sets;
RiFor X1Single factor test fuzzy matrix for assessment;
X2-X18Fuzzy comprehensive evoluation matrix algorithm and X1It is identical, to calculate X1-X18Fuzzy comprehensive evoluation square
Battle array;
Further: in step 9, X being diagnosed to be by Bayesian network diagnostic method1Posterior probability q1=
0.1135, X1Fuzzy comprehensive evoluation are as follows:
B1=(0 0 0.36 0.64 0);
The comprehensive diagnos result of waste heat boiler explosion accident is calculated according to comprehensive diagnos formula
In formula, D1For X1Comprehensive diagnos result;
d1For X1Fuzzy comprehensive evoluation weighted value;
N be Comprehensive Evaluation grade, n=1,2,3,4,5;
bn1For X1Belong to the comprehensive evaluation value of n-th each grade;
Obtain X1Comprehensive diagnos result D1=(3 × 0.36+4 × 0.64) × 0.1135=0.4131;
The comprehensive diagnos of each root node is similarly obtained as a result, and sorting to it.
A kind of beneficial effect of boiler afterheat explosion accident diagnostic analysis method according to the present invention is:
A kind of boiler afterheat explosion accident diagnostic analysis method of the present invention using Bayesian network method and obscures
Evaluation method combines, and studies waste heat boiler Accident-causing, comprehensively considers the influence such as probability of malfunction, diagnostic method difficulty or ease and accuracy
Factor realizes the optimization of fault diagnosis, improves diagnosis efficiency, reduces maintenance cost;It can guarantee that waste heat boiler is safely operated, in advance
Accident prevention occurs, and is diagnosed first by Bayesian network method to waste heat boiler explosion accident, obtains each root node and occurs
Posterior probability when failure;Then detection method complexity, detection speed, inspection of the Judgement Method to each root node are introduced
Accuracy and economy of survey etc. are judged, and the fuzzy comprehensive evoluation of each root node is obtained;Finally according to posterior probability
The main reason for fuzzy evaluation with root node obtains comprehensive diagnos, must be out of order is personnel leave post, bourdon tube damages etc., in turn
Prevention in time can effectively prevent waste heat boiler and explosion accident occurs.Obtain according to the present invention waste heat boiler explode it is main
Reason, and successively solved;Reinforce the management system of enterprise, prevention personnel leave post problem without reason.It is combined by two methods
Carrying out diagnosis to waste heat boiler explosion accident can determine, can be to waste heat pot in conjunction with fuzzy evaluation and Bayesian network diagnostic method
Furnace explosion accident is comprehensively analyzed, and is sought to optimize diagnostic method, is more met the requirement in real process for diagnosis, make
Diagnosis is more effective, has more economy.It takes other failure factors into consideration, such as the material property of pressure-containing member, welding procedure and sets
Standby complex working condition etc. is studied, to obtain comprehensive density of infection grade, is then ranked up diagnosis.
Detailed description of the invention
Fig. 1 is a kind of flow chart of boiler afterheat explosion accident diagnostic analysis method;
Fig. 2 is the Bayesian network model of waste heat boiler explosion accident;
Fig. 3 is Triangle-Profile figure.
Specific embodiment
Below with reference to embodiment, the following further describes the technical solution of the present invention, and however, it is not limited to this, all right
Technical solution of the present invention is modified or replaced equivalently, and without departing from the spirit and scope of the technical solution of the present invention, should all be contained
Lid is within the protection scope of the present invention.
Embodiment 1
Illustrate the present embodiment in conjunction with Fig. 1, Fig. 2 and Fig. 3, in the present embodiment, a kind of boiler residual involved in the present embodiment
Thermal explosion Analysis on Fault Diagnosis method, it the following steps are included:
Step 1: building Bayesian network model: the foundation of waste heat boiler hazard model relies primarily on data collection, searches
Document and expert opinion;Data collection is the current check data preservation according to afterheat boiler system in actual moving process,
And the historical summary of failure occurred;Searching document is the Study on Fault according to scientific research personnel to afterheat boiler system, is determined
The node and causality of Bayesian network;Expert opinion method mainly uses causality questionnaire, then by knowledge engineering
The knowledge base of Shi Jianli expert system finally constructs Bayesian network according to rule-based knowledge base;Establish waste heat boiler explosion accident
Bayesian network model each nodename is as shown in table 1 in Fig. 1 as shown in Figure 1::
1 each nodename of waste heat boiler explosion accident of table
Step 2: obtaining the root node prior probability of waste heat boiler fault model: the priori of waste heat boiler fault model is general
Rate obtains, for there are the node of historical data, taking the method according to historical data, according to root in recent years in historical data
The number of nodes break down, calculates its fault occurrence frequency, and as root node breaks down probability;For historical data incompleteness
Or the root node of historical data, the method for taking expertise are not provided according to expertise mainly, and the language of expert is become
Amount carries out Fuzzy processing, obtains exact probability;
Waste heat boiler explosion condition probability represents the logical relation between node, similar with accident tree logic gate, item
Part probability tables are as shown in table 3, and the present embodiment only provides the conditional probability table of node M 1, other nodes are similar therewith.
The conditional probability table of 3 M1 of table
Step 3: obtaining the posterior probability of root node: Bayesian network uses directed acyclic graph mode, intuitive expression joint
Probability distribution and its conditional independence substantially reduce reckoning difficulty for diagnostic reasoning, and variable number is more, and effect is more significant;It is logical
Bayesian Network Inference is crossed, the posterior probability for obtaining waste heat boiler explosion accident is as shown in table 4:
The posterior probability of 4 waste heat boiler explosion accident of table
By Bayesian network fault diagnosis as a result, it is available when waste heat boiler occur explosion time, it is influenced by
Small sequencing is arrived greatly are as follows: { X2, X4, X3, X7, X5, X6, X1, X12, X13, X8, X16, X11, X14, X18, X15, X10, X17, X9}。
Root node fuzzy evaluation: fuzzy evaluation is complexity, the detection speed, inspection to the detection method of each root node
The assessment of the accuracy of survey and the economy of detection etc..By carrying out fuzzy evaluation to root node, change diagnose in the past during
Probability of malfunction is unique influence factor, improves and diagnoses comprehensive and economy.
Step 4: establishing influence factor collection: influence factor collection U={ u1,u2,u3,u4, (detection method complexity u1, inspection
Degree of testing the speed u2, the accuracy u of detection3With the economy u of detection4)。
Step 5: establishing evaluate collection: according to the practical operation situation of afterheat boiler system, obtaining system in the process of running
Fault message, PASCAL evaluation PASCAL is carried out to diagnostic result, and is divided into 5 level models, establishes evaluation set, linguistic variable by
The influence of domain expert's combination failure provides, and linguistic variable is indicated with membership function, membership function includes Triangle-Profile, normal state
Distribution, trapezoidal profile and the distribution of LR type etc., referring to the advantage of Triangle-Profile, processing problem is easy and convenient, therefore uses triangle
It is distributed to handle the linguistic variable of evaluate collection.
5 factor grade classification table of table
Step 6: determining the fuzzy matrix for assessment of list influence factor: giving a mark to each influence factor, score value presses percentage
System calculates, and obtained score substitutes into Triangle-Profile, after normalized, obtains the Fuzzy Influence square of each influence factor
Battle array;Triangle-Profile is as shown in Figure 3:
Membership function v1Expression formula are as follows:
According to the available membership function V of same method2, V3, V4, V5Expression formula.According to score, substitute into expression formula,
Obtain the fuzzy evaluating matrix R of single influence factor of i-th of componenti.Fuzzy the commenting of waste heat boiler explosion accident root node
It is as follows to sentence matrix:
……
Step 7: determining factorial power sets: factorial power sets are influence degree of a certain factor to system jam
Set, the flexible strategy of factor are obtained by analytic hierarchy process (AHP), and analytic hierarchy process (AHP) can effectively reduce the influence of expert's subjective factor.
Analytic hierarchy process (AHP) is to be compared factor two-by-two, and of equal importance is 1, and slightly important is 3, hence it is evident that important is 5, by force
It is strong it is important be 7, absolutely essential is 9.Through normalized, respective weights collection A is obtainedi.The factorial power sets table of i-th of component
Up to formula are as follows:
Ai=(A1 i A2 i A3 i A4 i)
Waste heat boiler explosion accident factorial power sets are as follows:
A1=(0.2 0.4 0.2 0.2);
A2=(0.2 0.2 0.3 0.3);
A3=(0.2 0.3 0.2 0.3);
……
A17=(0.1 0.2 0.3 0.4);
A18=(0.3 0.1 0.5 0.1).
Step 8: calculating the fuzzy comprehensive evoluation matrix of waste heat boiler explosion accident factorial power sets;With alarm failure
X1For, calculate its fuzzy comprehensive evoluation matrix:
BiFor X1Fuzzy comprehensive evoluation;
AiFor X1Factorial power sets;
RiFor X1Single factor judgment matrix.
X2-X18Fuzzy comprehensive assessment and X1It is identical, it repeats no more.
Step 9: comprehensive diagnos: comprehensive diagnos is to be diagnosed to be posterior probability by Bayesian network diagnostic method, in conjunction with mould
Paste evaluation method judges out each root node and considers detection method complexity, detection speed, the accuracy of detection and detection
Weight when four factors of economy, the diagnosis that two methods comprehensively consider.
This method not only has the advantage of Bayesian network processing uncertain problem, but also combines multifactor impact
Comprehensive Evaluation, so that the more scientific, reasonability using Bayesian network fault diagnosis.With X1For, pass through Bayesian network
Diagnostic method is diagnosed to be X1Posterior probability q1=0.1135, X1Fuzzy comprehensive evoluation are as follows:
B1=(0 0 0.36 0.64 0);
According to formula
In formula, D1For X1Comprehensive diagnos result;
d1For X1Fuzzy comprehensive evoluation weighted value;
N be Comprehensive Evaluation grade, n=1,2,3,4,5;
bn1For X1Belong to the comprehensive evaluation value of n-th each grade;
Obtain X1Comprehensive diagnos result D1=(3 × 0.36+4 × 0.64) × 0.1135=0.4131;
The comprehensive diagnos for similarly obtaining each root node the results are shown in Table shown in 6:
Each root node comprehensive diagnos D of table 6i
By Bayesian network method and Judgement Method in conjunction with progress comprehensive diagnos as a result, available work as waste heat
When boiler explosion, descending sequencing is influenced on it are as follows: { X5, X4, X3, X2, X6, X7, X13, X1, X12, X16, X14,
X18, X15, X10, X17, X8, X11, X9}。
According to the sequence of above-mentioned influence factor, it can be derived that the sequence of boiler afterheat explosion accident factor, utilize Bayes
When network diagnoses waste heat boiler explosion, bourdon tube damage X is obtained4It is the main reason for waste heat boiler explodes, needs
It to be solved at first;And Bayesian network method combination Judgement Method carries out comprehensive diagnos, when considering detection method
When the problems such as complexity, detection speed, the economy of the accuracy of detection and detection, personnel leave post X5It is waste heat boiler
The main reason for explosion accident, it should reinforce the management system of enterprise, prevention personnel leave post problem without reason.Pass through two methods pair
Waste heat boiler explosion accident carries out diagnosis comparison, can define, can be to remaining in conjunction with fuzzy evaluation and Bayesian network diagnostic method
Heat boiler explosion accident is comprehensively analyzed, and is sought to optimize diagnostic method, is more met in real process and diagnosis is wanted
It asks, makes that diagnosis is more effective, more economy.
Claims (6)
1. a kind of boiler afterheat explosion accident diagnostic analysis method, which is characterized in that it the following steps are included:
Step 1: building Bayesian network model: determining the node and cause and effect of Bayesian network according to waste heat boiler explosion accident
Relationship;Knowledge base is established, Bayesian network is constructed according to rule-based knowledge base, establishes the Bayesian network of waste heat boiler explosion accident
Model:
Step 2: obtaining the root node prior probability of waste heat boiler fault model: where the root node prior probability includes root
Nodes break down probability and root node exact probability take the side according to historical data for node existing for historical data
Method calculates its fault occurrence frequency according to the number that root node breaks down in recent years in historical data, and as root node is sent out
Raw probability of malfunction;Or the not root node of historical data incomplete for historical data, carries out Fuzzy processing for linguistic variable, i.e.,
Obtain root node exact probability;
Step 3: obtaining the posterior probability of root node: the Bayesian network uses directed acyclic graph mode, passes through Bayesian network
Network reasoning obtains the posterior probability of waste heat boiler explosion accident;
Step 4: establishing influence factor collection: by carrying out fuzzy evaluation to each root node, wherein the influence factor of root node
Complexity u including detection method1, detection speed u2, detection accuracy u3With the economy u of detection4, establish influence because
Element collection U={ u1,u2,u3,u4};
Step 5: establishing evaluate collection: according to the practical operation situation of afterheat boiler system, obtaining the event of system in the process of running
Hinder information, PASCAL evaluation PASCAL is carried out to diagnostic result, and be divided into 5 level models, establish evaluate collection, determined in conjunction with influence factor
Linguistic variable indicates the linguistic variable with membership function;
Step 6: determining the fuzzy matrix for assessment of list influence factor: giving a mark to the influence factor of each grade, score value presses hundred
System is divided to calculate, obtained score substitutes into membership function, after normalized, obtains V1Single influence factor fuzzy evaluation of grade
Matrix;
Remaining grade v2, v3, v4, the fuzzy matrix for assessment expression of the influence factor membership function of v5 are obtained according to same method
Formula;Score is substituted into expression formula to get to single influence factor fuzzy evaluating matrix R of i-th of nodei;
Step 7: determining factorial power sets: factorial power sets are set of a certain factor to the influence degree of system jam,
The flexible strategy of factor are obtained by analytic hierarchy process (AHP);Analytic hierarchy process (AHP) is to be compared factor two-by-two, is divided into 5 by significance level
Grade, respectively 1,3,5,7,9;Through normalized, the factorial power sets expression formula for obtaining i-th of node is Ai;
Step 8: calculating the fuzzy comprehensive evoluation matrix of waste heat boiler explosion accident factorial power sets;Bi=Ai·Ri;
Step 9: comprehensive diagnos: being diagnosed to be posterior probability by Bayesian network diagnostic method, in conjunction with Judgement Method, comment
Sentence fuzzy comprehensive evoluation weighted value when each root node out considers four factors, by above two method comprehensive diagnos, really
Determining comprehensive diagnos formula is Di=di·qi;It obtains that explosion time occurs when waste heat boiler, and to the descending progress of its influence factor
Sequentially.
2. a kind of boiler afterheat explosion accident diagnostic analysis method according to claim 1, which is characterized in that described to be subordinate to
Function includes Triangle-Profile, normal distribution, trapezoidal profile and the distribution of LR type;In step 5, the membership function uses three
It is angular to be distributed to handle the linguistic variable of evaluate collection.
3. a kind of boiler afterheat explosion accident diagnostic analysis method according to claim 1, which is characterized in that in step 6
In, the fuzzy matrix for assessment of waste heat boiler explosion accident root node is as follows:
……
4. a kind of boiler afterheat explosion accident diagnostic analysis method according to claim 1, which is characterized in that in step 7
In, the factorial power sets expression formula of i-th of node are as follows:
Ai=(A1 i A2 i A3 i A4 i);
The weight sets of the waste heat boiler explosion accident influence factor is as follows:
A1=(0.2 0.4 0.2 0.2);
A2=(0.2 0.2 0.3 0.3);
A3=(0.2 0.3 0.2 0.3);
……
A17=(0.1 0.2 0.3 0.4);
A18=(0.3 0.1 0.5 0.1).
5. a kind of boiler afterheat explosion accident diagnostic analysis method according to claim 1, which is characterized in that in step 8
In, the fuzzy comprehensive evoluation matrix of the waste heat boiler explosion accident factorial power sets are as follows:
BiFor X1Fuzzy comprehensive evoluation matrix;
AiFor X1Factorial power sets;
RiFor X1Single factor test fuzzy matrix for assessment;
X2-X18Fuzzy comprehensive evoluation matrix algorithm and X1It is identical, to calculate X1-X18Fuzzy comprehensive evoluation matrix.
6. a kind of boiler afterheat explosion accident diagnostic analysis method according to claim 1, which is characterized in that in step 9
In, X is diagnosed to be by Bayesian network diagnostic method1Posterior probability q1=0.1135, X1Fuzzy comprehensive evoluation are as follows:
B1=(0 0 0.36 0.64 0);
The comprehensive diagnos result of waste heat boiler explosion accident is calculated according to comprehensive diagnos formula
In formula, D1For X1Comprehensive diagnos result;
d1For X1Fuzzy comprehensive evoluation weighted value;
N be Comprehensive Evaluation grade, n=1,2,3,4,5;
bn1For X1Belong to the comprehensive evaluation value of n-th each grade;
Obtain X1Comprehensive diagnos result D1=(3 × 0.36+4 × 0.64) × 0.1135=0.4131;
The comprehensive diagnos of each root node is similarly obtained as a result, and sorting to it.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910711426.0A CN110427015A (en) | 2019-08-02 | 2019-08-02 | A kind of boiler afterheat explosion accident diagnostic analysis method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910711426.0A CN110427015A (en) | 2019-08-02 | 2019-08-02 | A kind of boiler afterheat explosion accident diagnostic analysis method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110427015A true CN110427015A (en) | 2019-11-08 |
Family
ID=68413840
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910711426.0A Pending CN110427015A (en) | 2019-08-02 | 2019-08-02 | A kind of boiler afterheat explosion accident diagnostic analysis method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110427015A (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111553590A (en) * | 2020-04-27 | 2020-08-18 | 中国电子科技集团公司第十四研究所 | Radar embedded health management system |
CN112507290A (en) * | 2020-12-07 | 2021-03-16 | 国电南瑞科技股份有限公司 | Distribution equipment fault probability prejudging method and device and storage medium |
CN113537695A (en) * | 2021-05-28 | 2021-10-22 | 东莞理工学院 | Quantitative evaluation method for excessive emission risk of flue gas pollutants of waste incineration power plant |
CN114118760A (en) * | 2021-11-19 | 2022-03-01 | 西南交通大学 | RAMS demand analysis method for key parts of high-speed train |
CN115169506A (en) * | 2022-09-06 | 2022-10-11 | 中铁第四勘察设计院集团有限公司 | Method and system for rapidly diagnosing faults of power supply and transformation key equipment |
CN117150879A (en) * | 2023-07-14 | 2023-12-01 | 华能国际电力股份有限公司上海石洞口第二电厂 | Super-heater overtemperature early warning method and device based on fuzzy comprehensive evaluation model |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106846155A (en) * | 2017-03-29 | 2017-06-13 | 哈尔滨理工大学 | Submarine pipeline leakage accident methods of risk assessment based on fuzzy Bayesian network |
CN110059963A (en) * | 2019-04-20 | 2019-07-26 | 北京交通大学 | A kind of tunnel risk evaluating method based on fuzzy polymorphism Bayesian network |
-
2019
- 2019-08-02 CN CN201910711426.0A patent/CN110427015A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106846155A (en) * | 2017-03-29 | 2017-06-13 | 哈尔滨理工大学 | Submarine pipeline leakage accident methods of risk assessment based on fuzzy Bayesian network |
CN110059963A (en) * | 2019-04-20 | 2019-07-26 | 北京交通大学 | A kind of tunnel risk evaluating method based on fuzzy polymorphism Bayesian network |
Non-Patent Citations (1)
Title |
---|
马德仲等: "贝叶斯网络和模糊评判结合的滚动轴承故障诊断", 《哈尔滨理工大学学报》 * |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111553590A (en) * | 2020-04-27 | 2020-08-18 | 中国电子科技集团公司第十四研究所 | Radar embedded health management system |
CN111553590B (en) * | 2020-04-27 | 2021-09-24 | 中国电子科技集团公司第十四研究所 | Radar embedded health management system |
CN112507290A (en) * | 2020-12-07 | 2021-03-16 | 国电南瑞科技股份有限公司 | Distribution equipment fault probability prejudging method and device and storage medium |
CN112507290B (en) * | 2020-12-07 | 2024-04-30 | 国电南瑞科技股份有限公司 | Power distribution equipment fault probability pre-judging method, device and storage medium |
CN113537695A (en) * | 2021-05-28 | 2021-10-22 | 东莞理工学院 | Quantitative evaluation method for excessive emission risk of flue gas pollutants of waste incineration power plant |
CN113537695B (en) * | 2021-05-28 | 2023-11-21 | 东莞理工学院 | Quantitative evaluation method for risk of excessive emission of flue gas pollutants in garbage incineration power plant |
CN114118760A (en) * | 2021-11-19 | 2022-03-01 | 西南交通大学 | RAMS demand analysis method for key parts of high-speed train |
CN114118760B (en) * | 2021-11-19 | 2023-04-07 | 西南交通大学 | RAMS demand analysis method for key parts of high-speed train |
CN115169506A (en) * | 2022-09-06 | 2022-10-11 | 中铁第四勘察设计院集团有限公司 | Method and system for rapidly diagnosing faults of power supply and transformation key equipment |
CN117150879A (en) * | 2023-07-14 | 2023-12-01 | 华能国际电力股份有限公司上海石洞口第二电厂 | Super-heater overtemperature early warning method and device based on fuzzy comprehensive evaluation model |
CN117150879B (en) * | 2023-07-14 | 2024-04-09 | 华能国际电力股份有限公司上海石洞口第二电厂 | Super-heater overtemperature early warning method and device based on fuzzy comprehensive evaluation model |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110427015A (en) | A kind of boiler afterheat explosion accident diagnostic analysis method | |
Kushwaha et al. | Risk analysis of cutting system under intuitionistic fuzzy environment | |
Li et al. | Risk assessment of mine ignition sources using fuzzy Bayesian network | |
Guo et al. | Criticality evaluation of petrochemical equipment based on fuzzy comprehensive evaluation and a BP neural network | |
Li et al. | Fuzzy logic-based approach for identifying the risk importance of human error | |
Mayadevi | A Review on Expert System Applications in Power Plants | |
Lau et al. | A fuzzy-based decision support model for engineering asset condition monitoring–A case study of examination of water pipelines | |
CN103218689A (en) | Analyzing method and analyzing device for operator state assessment reliability | |
CN112464565B (en) | Equipment fault early warning method integrating intelligent modeling and fuzzy rules | |
Papakonstantinou et al. | Simulation based machine learning for fault detection in complex systems using the functional failure identification and propagation framework | |
Shojaee et al. | Applying SVSSI sampling scheme to np-chart to decrease the time of detecting shifts using Markov chain approach and Monte Carlo simulation | |
Ishak et al. | Implementation statistical quality control (sqc) and fuzzy failure mode and effect analysis (fmea): a systematic review | |
Ikonomopoulos et al. | A hybrid neural network---fuzzy logic approach to nuclear power plant transient identification | |
Bera et al. | A multiple-criteria decision analysis for criticality of boiler tube failures in interval type-2 fuzzy environment | |
Zainol et al. | Failure Prediction for High Voltage Induction Motor using Artificial Neural Network (ANN) | |
Yu et al. | Study on a comprehensive indicator and online classification of early warning of low frequency oscillation in power system | |
Bogatenkov et al. | ENERGYSAVINGWITH THE HELP OF INFORMATION AND MEASURING SYSTEMS: SECURITY SYSTEM MODELING | |
Yu et al. | An online fault diagnosis method for nuclear power plant based on combined artificial neural network | |
CN107544024A (en) | A kind of generator brush slip ring burn fault degree diagnostic method | |
Singh et al. | An Overview of Reliability, Availability, Maintainability, and Safety Strategies for Complex Systems in Various Process Industries | |
Sultanov et al. | Analysis of assessment of the technical condition of equipment of generating systems | |
Abdul-Wahab et al. | Troubleshooting the brine heater of the MSF plant fuzzy logic-based expert system | |
Gong et al. | Risk transmission evaluation for parallel construction of warships based on IFCM and the cloud model | |
Sun et al. | Research on Fault Diagnosis of Reactor Coolant Accident in Nuclear Power Plant Based on Radial Basis Function and Fuzzy Neural Network | |
Zheng et al. | Domestic and international human reliability research field development tracking |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191108 |
|
RJ01 | Rejection of invention patent application after publication |