CN111582603A - Intelligent early warning method for coal and gas outburst based on multi-source information fusion - Google Patents

Intelligent early warning method for coal and gas outburst based on multi-source information fusion Download PDF

Info

Publication number
CN111582603A
CN111582603A CN202010426878.7A CN202010426878A CN111582603A CN 111582603 A CN111582603 A CN 111582603A CN 202010426878 A CN202010426878 A CN 202010426878A CN 111582603 A CN111582603 A CN 111582603A
Authority
CN
China
Prior art keywords
early warning
index
rule
coal
confidence
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.)
Granted
Application number
CN202010426878.7A
Other languages
Chinese (zh)
Other versions
CN111582603B (en
Inventor
宁小亮
赵旭生
张庆华
马国龙
宋志强
李明建
和树栋
谈国文
车禹恒
蒲阳
崔俊飞
覃木广
刁勇
梁军
邓敢博
唐韩英
姚亚虎
王麒翔
岳俊
张士岭
罗广
廖成
赵吉玉
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
CCTEG Chongqing Research Institute Co Ltd
Original Assignee
CCTEG Chongqing Research Institute Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by CCTEG Chongqing Research Institute Co Ltd filed Critical CCTEG Chongqing Research Institute Co Ltd
Priority to CN202010426878.7A priority Critical patent/CN111582603B/en
Publication of CN111582603A publication Critical patent/CN111582603A/en
Application granted granted Critical
Publication of CN111582603B publication Critical patent/CN111582603B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
    • G06Q50/02—Agriculture; Fishing; Mining
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
    • G06Q50/10—Services
    • G06Q50/26—Government or public services
    • G06Q50/265—Personal security, identity or safety
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S10/00—Systems supporting electrical power generation, transmission or distribution
    • Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications

Abstract

The invention provides an intelligent early warning method for coal and gas outburst based on multi-source information fusion, which comprises the following steps: acquiring historical data of coal and gas outburst early warning indexes, and carrying out normalization processing on the acquired historical data; performing association analysis on the historical early warning indexes by adopting an association rule algorithm, and calculating the support degree and the confidence degree of each historical early warning index; establishing a coal and gas outburst early warning index optimization rule based on the association rule, and performing early warning index optimization; constructing a confidence coefficient distribution rule of the early warning index; the method comprises the steps of collecting real-time indexes of coal and gas outburst, calculating the real-time indexes to obtain confidence degrees of the real-time indexes, forming a confidence degree distribution table of the real-time indexes, carrying out evidence synthesis on the real-time indexes by adopting an evidence theory algorithm to obtain decision results, and distributing coal and gas outburst early warning results according to the decision results, so that automatic screening of coal and gas outburst early warning indexes, automatic fusion analysis and decision of multiple indexes, automatic tracing of early warning reasons and dynamic updating and optimization of a model are realized, intelligent early warning of the coal and gas outburst is realized, and accuracy of the early warning results is ensured.

Description

Intelligent early warning method for coal and gas outburst based on multi-source information fusion
Technical Field
The invention relates to a coal and gas outburst early warning method, in particular to an intelligent coal and gas outburst early warning method based on multi-source information fusion.
Background
Prediction and early warning are the first links of prevention and control of coal and gas outburst disasters, at present, most mines adopt a few static indexes (such as structure, gas, soft stratification, drill chip desorption indexes, initial rate of gas emission from drill holes, drill chip amount and the like) to carry out risk prediction, and the problems of single index, non-dynamic state in time, discontinuous space and the like, insufficient and timely analysis of hidden danger information and the like exist, so that the prediction accuracy is low; meanwhile, although the original coal mine monitoring system plays a role in reducing gas accidents to a certain extent, a lot of immature and incomplete places exist overall, the monitoring system can only perform simple conversion, storage, display and printing on original data, the data resource mining and analysis depth is not enough, major disaster hidden dangers cannot be found in time, and the early warning function of the whole system is not strong.
Therefore, in order to solve the above technical problems, it is necessary to provide a new technical means.
Disclosure of Invention
In view of the above, the invention aims to provide an intelligent early warning method for coal and gas outburst based on multi-source information fusion, aiming at the problems that the multi-source information fusion degree of the coal and gas outburst is not high, an early warning model is relatively solidified, the self-analysis and optimization capability is not enough, the early warning intelligence level is not high, and the like, the method combining association rules and an evidence theory algorithm is adopted, so that the automatic screening of the early warning indexes of the coal and gas outburst, the automatic fusion analysis and decision of multiple indexes, the automatic tracing of the early warning reasons and the dynamic updating and optimization of the model are realized, the intelligent early warning of the coal and gas outburst is realized, and the accuracy.
The invention provides an intelligent early warning method for coal and gas outburst based on multi-source information fusion, which comprises the following steps:
s1, collecting historical data of coal and gas outburst, and carrying out normalization processing on the collected historical data to obtain a historical early warning index;
s2, performing association analysis on the historical early warning indexes by adopting an association rule algorithm, and calculating the support degree and confidence degree of each historical early warning index;
s3, establishing a coal and gas outburst early warning index optimization rule based on the association rule, and performing early warning index optimization;
s4, establishing a confidence coefficient distribution rule of the early warning index;
and S5, acquiring real-time indexes of coal and gas outburst, calculating the real-time indexes to obtain confidence degrees of the real-time indexes, forming a confidence degree distribution table of the real-time indexes, performing evidence synthesis on the real-time indexes by adopting an evidence theory algorithm to obtain decision results, and issuing early warning results of the coal and gas outburst according to the decision results.
Further, the method also includes step S6:
and S6, analyzing the early warning result by adopting an expert judgment method, recalculating the confidence coefficient of the historical early warning index according to the analysis result and the association rule algorithm, adjusting the confidence coefficient distribution rule, and returning to the step S1.
Further, step S2 specifically includes:
s21, determining an association rule item of the historical early warning index:
let the item be imThe set of terms is I, wherein,m＝1,2，…，k，I＝{i1，i2，…，ikitem is represented by an early warning index ZnForming;
if the early warning index Z isnIs a qualitative index, then an early warning index Z is givennIs an item;
if the early warning index Z isnAs a quantitative index, Zn≥Zn0+ L.j or Zn≤Zn0+ l.j is an item, where j ═ 1,2, …, k, Zn0Is an early warning index ZnL is the analysis step length;
let T be a transaction set, which is a non-empty subset of item set I, | T | be item set frequency;
s22, constructing an association rule algorithm model: defining association rules
Figure BDA0002499046980000021
A is a rule precondition and represents an early warning index, and B is a rule result and represents that the rule result has a prominent danger;
calculating support degree S and confidence degree C:
Figure BDA0002499046980000031
Figure BDA0002499046980000032
and dividing the association rules according to the support degree and the confidence degree:
firstly, a rule with high support degree and high confidence level is considered as a strong association rule; secondly, a rule with low support degree and high confidence level is considered as a strong association rule if the rule is a qualitative index, and is considered as a weak association item if the rule is a quantitative index; thirdly, considering the rule as a weak association rule with high support degree and low confidence coefficient; and fourthly, considering the rule as a weak association rule with low support degree and low confidence coefficient.
Further, step S3 specifically includes:
determining a minimum support Smin：
Figure BDA0002499046980000033
Wherein α is the minimum support factor;
determining a minimum confidence Cmin；
Determining a preferred rule:
if the support degree S is larger than or equal to SminIf the support degree of the association rule is high, otherwise, the support degree is low;
if the confidence coefficient C is more than or equal to CminIf the confidence level of the association rule is high, otherwise, the confidence level is low;
and screening the early warning indexes according to the optimal rule.
Further, step S4 specifically includes:
s41, establishing a coal and gas outburst early warning grade: green, orange and red grades, and the early warning grade is increased in sequence;
s42, establishing an evidence theory identification framework theta: Θ is { red, orange, green }, and the evidence theorizes that the probability of identifying the frame Θ is 2Θ→[0,1]And satisfies the function p of
Figure BDA0002499046980000034
And is
Figure BDA0002499046980000035
Where X is a subset of the evidence theory recognition framework and p (X) assigns a value for confidence, then: evidence theory identifies a subset of the framework as: { red }, { orange }, { green }, and Θ, the confidence interval for each subset is:
Figure BDA0002499046980000041
s43, if the early warning index is a qualitative index:
if the early warning index Z isnWhen the expressed phenomenon appears, the confidence C of the index is assigned to the subset { red } or { orange }, and the residual probability 1-C is assigned to the subset theta;
if the early warning index Z isnWhen the phenomenon is not present, the phenomenon will beAll probabilities of the early warning indicator are assigned to the subset Θ;
if the early warning index is a quantitative index:
the early warning indexes are divided into 3 intervals: zn∈[Z0,+∞)、Zn∈[λ·Z0,Z0)、Zn∈(-∞,λ·Z0) Wherein Z is0Is an index critical value, and lambda is a field coefficient;
and distributing the confidence C of the early warning index to the subset corresponding to the dynamically acquired index value belonging interval, and distributing the residual probability 1-C to other subsets.
Further, step S5 specifically includes:
constructing an evidence synthesis formula:
Figure BDA0002499046980000042
x1, X2, …, Xn denote n subsets of recognition frameworks,
Figure BDA0002499046980000043
establishing a decision value calculation model:
Figure BDA0002499046980000044
calculating a decision value g (X) for the subset X1, X2, …, Xn according to a decision value calculation modelq) If:
g(Xq) Max { g ({ red }), g ({ orange }), g ({ green }) }, then XqTo fuse the early warning results, q represents the subset red, orange, or green.
Further, step S6 specifically includes:
finding out the basic confidence degree assigned value m with the maximum focal element corresponding to the early warning resultnIf m isn-mn′And (c) not more than n ', wherein n is not equal to n ', and is a preset threshold value, the indexes corresponding to the evidence n and the evidence n ' are the early warning reasons, otherwise, only the index corresponding to the evidence n is the early warning sourceThus;
and after the early warning result is issued, periodically evaluating the early warning accuracy by adopting an expert judgment method, and adjusting the model parameters according to the evaluation result and the newly added historical data.
The invention has the beneficial effects that: according to the invention, aiming at the problems of low fusion degree of multi-source information of coal and gas outburst, relative solidification of early warning models, insufficient self-analysis and optimization capability, low intelligent level of early warning and the like, a method combining association rules and an evidence theory algorithm is adopted, so that automatic screening of coal and gas outburst early warning indexes, automatic fusion analysis and decision of multi-indexes, automatic tracing of early warning reasons and dynamic updating optimization of the models are realized, intelligent early warning of coal and gas outburst is realized, and the accuracy of early warning results is ensured.
Drawings
The invention is further described below with reference to the following figures and examples:
FIG. 1 is a flow chart of the present invention.
Detailed Description
The invention is described in further detail below with reference to the drawings of the specification:
the invention provides an intelligent early warning method for coal and gas outburst based on multi-source information fusion, which comprises the following steps:
s1, collecting historical data of coal and gas outburst, and carrying out normalization processing on the collected historical data to obtain a historical early warning index;
s2, performing association analysis on the historical early warning indexes by adopting an association rule algorithm, and calculating the support degree and confidence degree of each historical early warning index;
s3, establishing a coal and gas outburst early warning index optimization rule based on the association rule, and performing early warning index optimization;
s4, establishing a confidence coefficient distribution rule of the early warning index;
s5, collecting real-time indexes of coal and gas outburst, calculating the real-time indexes to obtain confidence degrees of the real-time indexes, forming a confidence degree distribution table of the real-time indexes, carrying out evidence synthesis on the real-time indexes by adopting an evidence theory algorithm to obtain a decision result, and distributing early warning results of the coal and gas outburst according to the decision result.
In this embodiment, the method further includes step S6:
s6, analyzing the early warning result by adopting an expert judgment method, recalculating the confidence coefficient of the historical early warning index according to the analysis result and the association rule algorithm, adjusting the confidence coefficient distribution rule, returning to the step S1, and taking the current early warning index as the historical early warning index, specifically:
finding out the basic confidence degree assigned value m with the maximum focal element corresponding to the early warning resultnIf m isn-mn′The index corresponding to the evidence n and the evidence n 'is an early warning reason if the threshold value is not more than n', otherwise, only the index corresponding to the evidence n is the early warning reason;
after the early warning result is issued, an expert judgment method is adopted to periodically evaluate the early warning accuracy, and the model parameters are adjusted according to the evaluation result and the newly added historical data.
In this embodiment, step S2 specifically includes:
s21, determining an association rule item of the historical early warning index:
let the item be imThe term set is I, wherein m is 1,2, …, k, I is { I ═ I1，i2，…，ikItem is represented by an early warning index ZnForming;
if the early warning index Z isnIs a qualitative index, then an early warning index Z is givennIs an item;
if the early warning index Z isnAs a quantitative index, Zn≥Zn0+ L.j or Zn≤Zn0+ l.j is an item, where j ═ 1,2, …, k, Zn0Is an early warning index ZnL is the analysis step length;
let T be a transaction set, which is a non-empty subset of item set I, | T | be item set frequency;
s22, constructing an association rule algorithm model: defining association rules
Figure BDA0002499046980000061
A is a rule precondition and represents an early warning index, and B is a rule result and represents that the rule result has a prominent danger;
calculating support degree S and confidence degree C:
Figure BDA0002499046980000071
Figure BDA0002499046980000072
and dividing the association rules according to the support degree and the confidence degree:
firstly, a rule with high support degree and high confidence level is considered as a strong association rule; secondly, a rule with low support degree and high confidence level is considered as a strong association rule if the rule is a qualitative index, and is considered as a weak association item if the rule is a quantitative index; thirdly, considering the rule as a weak association rule with high support degree and low confidence coefficient; and fourthly, considering the rule as a weak association rule with low support degree and low confidence coefficient. For example:
the early warning indexes comprise:
drill cutting desorption index K1Maximum drill cuttings quantity SmaxGas emission index V, coal thickness change rate M, whether take place power phenomenon D, whether be in structure influence district G etc. wherein, whether take place power phenomenon D, whether be in structure influence district G is qualitative index, as shown in Table 1:
Figure BDA0002499046980000073
TABLE 1
In table 1, the 1 st to 10 th groups of data are history data, and the 11 th group of data are real-time index data;
in this embodiment, step S3 specifically includes:
determining a minimum support Smin：
Figure BDA0002499046980000074
Wherein α is the minimum support factor;
determining a minimum confidence Cmin；
Determining a preferred rule:
if the support degree S is larger than or equal to SminIf the support degree of the association rule is high, otherwise, the support degree is low;
if the confidence coefficient C is more than or equal to CminIf the confidence level of the association rule is high, otherwise, the confidence level is low;
screening the early warning indexes according to the optimization rule, wherein the value of each parameter is determined according to the actual state of the site, for example, α is 0.8, Cmin0.7, then Smin＝0.48，CminThe parameters set by the association rule item are as in table 2:
Figure BDA0002499046980000081
TABLE 2
Through the calculation of the method, the confidence coefficient and the critical value of the early warning index based on the association rule are as shown in a table 3:
Figure BDA0002499046980000082
TABLE 3
In this embodiment, step S4 specifically includes:
s41, establishing a coal and gas outburst early warning grade: green, orange and red grades, and the early warning grade is increased in sequence;
s42, establishing an evidence theory identification framework theta: Θ is { red, orange, green }, and the evidence theorizes that the probability of identifying the frame Θ is 2Θ→[0,1]And satisfies the function p of
Figure BDA0002499046980000083
And is
Figure BDA0002499046980000084
Where X is a subset of the evidence theory recognition framework and p (X) assigns a value for confidence, then: evidence theory identifies a subset of the framework as: { red }, { orange }, { green }, and Θ, the confidence interval for each subset is:
Figure BDA0002499046980000085
s43, if the early warning index is a qualitative index:
if the early warning index Z isnWhen the expressed phenomenon appears, the confidence C of the index is assigned to the subset { red } or { orange }, and the residual probability 1-C is assigned to the subset theta;
if the early warning index Z isnWhen the phenomenon is not presented, all probabilities of the early warning index are distributed to the subset theta;
if the early warning index is a quantitative index:
the early warning indexes are divided into 3 intervals: zn∈[Z0,+∞)、Zn∈[λ·Z0,Z0)、Zn∈(-∞,λ·Z0) Wherein Z is0Is an index critical value, and lambda is a field coefficient;
the confidence degree C of the early warning index is assigned to the subset corresponding to the dynamically acquired index value belonging interval, and then the remaining probabilities 1-C are assigned to other subsets, based on the above example, as shown in tables 4 and 5:
Figure BDA0002499046980000091
TABLE 4 basic confidence assignment rules
Figure BDA0002499046980000092
TABLE 5 basic confidence coefficient
Coefficient of performance1To4All are confidence distribution coefficients;
in this embodiment, step S5 specifically includes:
constructing an evidence synthesis formula:
Figure BDA0002499046980000093
wherein X1, X2, …, Xn denote n subsets of the recognition framework,
Figure BDA0002499046980000094
establishing a decision value calculation model:
Figure BDA0002499046980000095
calculating a decision value g (X) for the subset X1, X2, …, Xn according to a decision value calculation modelq) If:
g(Xq) Max { g ({ red }), g ({ orange }), g ({ green }) }, then XqTo fuse the early warning results, q represents the subset red, orange, or green.
Specifically, the method comprises the following steps: the basic probability distribution for group 11 data is shown in table 6:
Figure BDA0002499046980000101
TABLE 6
Figure BDA0002499046980000102
TABLE 7
Table 7 shows the evidence synthesis results, and it can be seen from this table that: the subset { red } is a final early warning result, which indicates that the working face has outstanding danger, and the prediction result is accurate after the prediction and the actual working condition verification of the method.
Finally, the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting, although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all of them should be covered in the claims of the present invention.

Claims (7)

1. An intelligent early warning method for coal and gas outburst based on multi-source information fusion is characterized in that: the method comprises the following steps:
s1, collecting historical data of coal and gas outburst, and carrying out normalization processing on the collected historical data to obtain a historical early warning index;
s2, performing association analysis on the historical early warning indexes by adopting an association rule algorithm, and calculating the support degree and confidence degree of each historical early warning index;
s3, establishing a coal and gas outburst early warning index optimization rule based on the association rule, and performing early warning index optimization;
s4, establishing a confidence coefficient distribution rule of the early warning index;
and S5, acquiring real-time indexes of coal and gas outburst, calculating the real-time indexes to obtain confidence degrees of the real-time indexes, forming a confidence degree distribution table of the real-time indexes, performing evidence synthesis on the real-time indexes by adopting an evidence theory algorithm to obtain decision results, and issuing early warning results of the coal and gas outburst according to the decision results.
2. The intelligent early warning method for coal and gas outburst based on multi-source information fusion according to claim 1, which is characterized in that: further comprising step S6:
and S6, analyzing the early warning result by adopting an expert judgment method, recalculating the confidence coefficient of the historical early warning index according to the analysis result and the association rule algorithm, adjusting the confidence coefficient distribution rule, and returning to the step S1.
3. The intelligent early warning method for coal and gas outburst based on multi-source information fusion according to claim 1, which is characterized in that: in step S2, the method specifically includes:
s21, determining an association rule item of the historical early warning index:
let the item be imThe term set is I, wherein m is 1,2, …, k, I is { I ═ I1，i2，…，ikItem is represented by an early warning index ZnForming;
if the early warning index Z isnIs a qualitative index, then an early warning index Z is givennIs an item;
if the early warning index Z isnAs a quantitative index, Zn≥Zn0+ L.j or Zn≤Zn0+ l.j is an item, where j ═ 1,2, …, k, Zn0Is an early warning index ZnL is the analysis step length;
let T be a transaction set, which is a non-empty subset of item set I, | T | be item set frequency;
s22, constructing an association rule algorithm model: defining association rules
Figure FDA0002499046970000021
A is a rule precondition and represents an early warning index, and B is a rule result and represents that the rule result has a prominent danger;
calculating support degree S and confidence degree C:
Figure FDA0002499046970000022
Figure FDA0002499046970000023
and dividing the association rules according to the support degree and the confidence degree:
firstly, a rule with high support degree and high confidence level is considered as a strong association rule; secondly, a rule with low support degree and high confidence level is considered as a strong association rule if the rule is a qualitative index, and is considered as a weak association item if the rule is a quantitative index; thirdly, considering the rule as a weak association rule with high support degree and low confidence coefficient; and fourthly, considering the rule as a weak association rule with low support degree and low confidence coefficient.
4. The intelligent early warning method for coal and gas outburst based on multi-source information fusion according to claim 3, characterized in that: step S3 specifically includes:
determining a minimum support Smin：
Figure FDA0002499046970000024
Wherein α is the minimum support factor;
determining a minimum confidence Cmin；
Determining a preferred rule:
if the support degree S is larger than or equal to SminIf the support degree of the association rule is high, otherwise, the support degree is low;
if the confidence coefficient C is more than or equal to CminIf the confidence level of the association rule is high, otherwise, the confidence level is low;
and screening the early warning indexes according to the optimal rule.
5. The intelligent early warning method for coal and gas outburst based on multi-source information fusion according to claim 4, characterized in that: step S4 specifically includes:
s41, establishing a coal and gas outburst early warning grade: green, orange and red grades, and the early warning grade is increased in sequence;
s42, establishing an evidence theory identification framework theta: Θ is { red, orange, green }, and the evidence theorizes that the probability of identifying the frame Θ is 2Θ→[0,1]And satisfies the function p of
Figure FDA0002499046970000031
And is
Figure FDA0002499046970000032
Where X is a subset of the evidence theory recognition framework and p (X) assigns a value for confidence, then: evidence theory identifies a subset of the framework as: { red }, { orange }, { green }, and Θ, the confidence interval for each subset is:
Figure FDA0002499046970000033
s43, if the early warning index is a qualitative index:
if the early warning index Z isnWhen the expressed phenomenon appears, the confidence C of the index is assigned to the subset { red } or { orange }, and the residual probability 1-C is assigned to the subset theta;
if the early warning index Z isnWhen the phenomenon is not presented, all probabilities of the early warning index are distributed to the subset theta;
if the early warning index is a quantitative index:
the early warning indexes are divided into 3 intervals: zn∈[Z0,+∞)、Zn∈[λ·Z0,Z0)、Zn∈(-∞,λ·Z0) Wherein Z is0Is an index critical value, and lambda is a field coefficient;
and distributing the confidence C of the early warning index to the subset corresponding to the dynamically acquired index value belonging interval, and distributing the residual probability 1-C to other subsets.
6. The intelligent early warning method for coal and gas outburst based on multi-source information fusion according to claim 5, characterized in that: step S5 specifically includes:
constructing an evidence synthesis formula:
Figure FDA0002499046970000034
wherein X1, X2, …, Xn denote n subsets of the recognition framework,
Figure FDA0002499046970000035
establishing a decision value calculation model:
Figure FDA0002499046970000036
calculating a decision value g (X) for the subset X1, X2, …, Xn according to a decision value calculation modelq) If:
g(Xq) Max { g ({ red }), g ({ orange }), g ({ green }) }, then XqTo fuse the early warning results, q represents the subset red, orange, or green.
7. The intelligent early warning method for coal and gas outburst based on multi-source information fusion according to claim 5, characterized in that: step S6 specifically includes:
finding out the basic confidence degree assigned value m with the maximum focal element corresponding to the early warning resultnIf m isn-mn' is less than or equal to, wherein n is not equal to n ', and is a preset threshold value, the indexes corresponding to the evidence n and the evidence n ' are early warning reasons, otherwise, only the index corresponding to the evidence n is the early warning reason;
and after the early warning result is issued, periodically evaluating the early warning accuracy by adopting an expert judgment method, and adjusting the model parameters according to the evaluation result and the newly added historical data.
CN202010426878.7A 2020-05-19 2020-05-19 Intelligent early warning method for coal and gas outburst based on multi-source information fusion Active CN111582603B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010426878.7A CN111582603B (en) 2020-05-19 2020-05-19 Intelligent early warning method for coal and gas outburst based on multi-source information fusion

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010426878.7A CN111582603B (en) 2020-05-19 2020-05-19 Intelligent early warning method for coal and gas outburst based on multi-source information fusion

Publications (2)

Publication Number Publication Date
CN111582603A true CN111582603A (en) 2020-08-25
CN111582603B CN111582603B (en) 2022-09-13

Family

ID=72126911

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010426878.7A Active CN111582603B (en) 2020-05-19 2020-05-19 Intelligent early warning method for coal and gas outburst based on multi-source information fusion

Country Status (1)

Country Link
CN (1) CN111582603B (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112926270A (en) * 2021-03-18 2021-06-08 西安科技大学 Gas multi-factor coupling relation analysis and early warning model construction method
CN113298382A (en) * 2021-05-26 2021-08-24 北京交通大学 Confidence calculation-based method for fusing operation and maintenance service knowledge of high-speed train
CN116882548A (en) * 2023-06-15 2023-10-13 中国矿业大学 Tunneling roadway coal and gas outburst prediction method based on dynamic probability reasoning
CN116882548B (en) * 2023-06-15 2024-05-17 中国矿业大学 Tunneling roadway coal and gas outburst prediction method based on dynamic probability reasoning

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20080008573A (en) * 2006-07-20 2008-01-24 성균관대학교산학협력단 Method for extracting association rule from xml data
JP2016091381A (en) * 2014-11-06 2016-05-23 新コスモス電機株式会社 Detector
CN106874671A (en) * 2017-02-15 2017-06-20 淄博祥龙测控技术有限公司 A kind of algorithm of the data-driven for spontaneous fire in coal mine big data platform
CN107605536A (en) * 2017-11-02 2018-01-19 湖南科技大学 Coal and gas prominent real-time early warning device and method based on Multi-source Information Fusion
CN108470222A (en) * 2018-02-08 2018-08-31 卢新明 A kind of Multi symptom for typical event prediction increases letter method
CN108763729A (en) * 2018-05-24 2018-11-06 西安交通大学 Process industry Mechatronic Systems couple state appraisal procedure based on network structure entropy
CN109026130A (en) * 2018-08-17 2018-12-18 西安科技大学 A kind of recognition methods of mine gas data exception
CN110297141A (en) * 2019-07-01 2019-10-01 武汉大学 Fault Locating Method and system based on multilayer assessment models

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20080008573A (en) * 2006-07-20 2008-01-24 성균관대학교산학협력단 Method for extracting association rule from xml data
JP2016091381A (en) * 2014-11-06 2016-05-23 新コスモス電機株式会社 Detector
CN106874671A (en) * 2017-02-15 2017-06-20 淄博祥龙测控技术有限公司 A kind of algorithm of the data-driven for spontaneous fire in coal mine big data platform
CN107605536A (en) * 2017-11-02 2018-01-19 湖南科技大学 Coal and gas prominent real-time early warning device and method based on Multi-source Information Fusion
CN108470222A (en) * 2018-02-08 2018-08-31 卢新明 A kind of Multi symptom for typical event prediction increases letter method
CN108763729A (en) * 2018-05-24 2018-11-06 西安交通大学 Process industry Mechatronic Systems couple state appraisal procedure based on network structure entropy
CN109026130A (en) * 2018-08-17 2018-12-18 西安科技大学 A kind of recognition methods of mine gas data exception
CN110297141A (en) * 2019-07-01 2019-10-01 武汉大学 Fault Locating Method and system based on multilayer assessment models

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
JS QIAN 等: "Data Processing Model of Coalmine Gas Early-Warning System", 《JOURNAL OF CHINA UNIVERSITY OF MINING & TECHNOLOGY》 *
宁小亮: "基于多源信息融合的煤与瓦斯突出动态预警模型", 《矿业安全与环保》 *
石记斌 等: "关联分析数据挖掘在煤矿瓦斯安全监测预警中的应用", 《能源与环保》 *

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112926270A (en) * 2021-03-18 2021-06-08 西安科技大学 Gas multi-factor coupling relation analysis and early warning model construction method
CN112926270B (en) * 2021-03-18 2023-05-05 西安科技大学 Gas multi-factor coupling relation analysis and early warning model construction method
CN113298382A (en) * 2021-05-26 2021-08-24 北京交通大学 Confidence calculation-based method for fusing operation and maintenance service knowledge of high-speed train
CN113298382B (en) * 2021-05-26 2024-04-16 北京交通大学 High-speed railway train operation and maintenance service knowledge fusion-oriented method based on confidence calculation
CN116882548A (en) * 2023-06-15 2023-10-13 中国矿业大学 Tunneling roadway coal and gas outburst prediction method based on dynamic probability reasoning
CN116882548B (en) * 2023-06-15 2024-05-17 中国矿业大学 Tunneling roadway coal and gas outburst prediction method based on dynamic probability reasoning

Also Published As

Publication number Publication date
CN111582603B (en) 2022-09-13

Similar Documents

Publication Publication Date Title
CN107610469B (en) Day-dimension area traffic index prediction method considering multi-factor influence
CN106951984B (en) Dynamic analysis and prediction method and device for system health degree
CN106600115A (en) Intelligent operation and maintenance analysis method for enterprise information system
CN111582603B (en) Intelligent early warning method for coal and gas outburst based on multi-source information fusion
CN112132233A (en) Criminal personnel dangerous behavior prediction method and system based on effective influence factors
CN111179592B (en) Urban traffic prediction method and system based on spatio-temporal data flow fusion analysis
CN116843071B (en) Transportation network operation index prediction method and device for intelligent port
CN109491339B (en) Big data-based substation equipment running state early warning system
CN116228021A (en) Mine ecological restoration evaluation analysis method and system based on environment monitoring
CN112185108B (en) Urban road network congestion mode identification method, equipment and medium based on space-time characteristics
CN114971356A (en) Electric power engineering project progress prediction system and method
CN110851422A (en) Data anomaly monitoring model construction method based on machine learning
CN115828390A (en) Four-pre-function implementation method for safety monitoring of hydraulic and hydroelectric engineering
CN116480412A (en) Mine disaster rescue method and device
CN116644954B (en) Intelligent decision-making method for construction safety risk of pumping and accumulating engineering
CN116703148B (en) Cloud computing-based mine enterprise risk portrait method
CN111145535B (en) Travel time reliability distribution prediction method under complex scene
CN109816250B (en) Method for determining maintenance priority of concrete bridges in highway network
CN116452191A (en) Intelligent rural water supply data collection and analysis system and method based on big data
CN115471135A (en) Environment-friendly service analysis system
CN109448379A (en) A kind of identification of sporadic traffic events of social media data and localization method
CN109635008A (en) A kind of equipment fault detection method based on machine learning
CN114066288A (en) Intelligent data center-based emergency detection method and system for operation road
CN115795143B (en) Information evaluation system and method based on computer
CN107358348A (en) A kind of method that plan fault-tolerance is improved based on OEE

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