CN107103434A - A kind of people is because of key element Analysis of Potential diagnostic method - Google Patents
A kind of people is because of key element Analysis of Potential diagnostic method Download PDFInfo
- Publication number
- CN107103434A CN107103434A CN201710380136.3A CN201710380136A CN107103434A CN 107103434 A CN107103434 A CN 107103434A CN 201710380136 A CN201710380136 A CN 201710380136A CN 107103434 A CN107103434 A CN 107103434A
- Authority
- CN
- China
- Prior art keywords
- people
- key element
- decision
- analysis
- sample
- 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
- 238000004458 analytical method Methods 0.000 title claims abstract description 54
- 238000002405 diagnostic procedure Methods 0.000 title claims abstract description 27
- 238000004519 manufacturing process Methods 0.000 claims abstract description 18
- 238000003745 diagnosis Methods 0.000 claims abstract description 14
- 238000012360 testing method Methods 0.000 claims abstract description 10
- 238000010276 construction Methods 0.000 claims description 15
- 230000008859 change Effects 0.000 claims description 14
- 238000000034 method Methods 0.000 claims description 14
- 230000004927 fusion Effects 0.000 claims description 12
- 230000008447 perception Effects 0.000 claims description 9
- 230000006870 function Effects 0.000 claims description 7
- 238000005457 optimization Methods 0.000 claims description 7
- 238000009826 distribution Methods 0.000 claims description 5
- 239000008186 active pharmaceutical agent Substances 0.000 claims description 4
- 230000003044 adaptive effect Effects 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000011156 evaluation Methods 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 238000005070 sampling Methods 0.000 claims description 3
- 239000004744 fabric Substances 0.000 claims 1
- 238000005516 engineering process Methods 0.000 abstract description 8
- 238000006243 chemical reaction Methods 0.000 abstract description 2
- 241001269238 Data Species 0.000 abstract 1
- 238000007726 management method Methods 0.000 description 8
- 230000000694 effects Effects 0.000 description 6
- 239000002245 particle Substances 0.000 description 5
- 230000035479 physiological effects, processes and functions Effects 0.000 description 5
- 230000010354 integration Effects 0.000 description 4
- 230000032683 aging Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 3
- 230000001149 cognitive effect Effects 0.000 description 3
- 239000000463 material Substances 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 230000006837 decompression Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 230000004069 differentiation Effects 0.000 description 2
- 230000008713 feedback mechanism Effects 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 230000010534 mechanism of action Effects 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 238000010248 power generation Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000029058 respiratory gaseous exchange Effects 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000009412 basement excavation Methods 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 230000019771 cognition Effects 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 230000004630 mental health Effects 0.000 description 1
- 238000002156 mixing Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 230000010349 pulsation Effects 0.000 description 1
- 238000010223 real-time analysis Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000002459 sustained effect Effects 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
- 230000009897 systematic effect Effects 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
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06398—Performance of employee with respect to a job function
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Educational Administration (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- Health & Medical Sciences (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Public Health (AREA)
- Primary Health Care (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of people because of key element Analysis of Potential diagnostic method, comprise the steps of:Step S1, collection worker at the production line's all standing people build people because of key element basic index data acquisition system because of element information;Step S2, according to people because key element basic index data acquisition system build people because of key element extensive analysis model;Step S3, structure people are because of key element Analysis of Potential diagnosis decision model;Step S4, input employee's sample data to be measured, obtain people because of the decision-making of key element comprehensive diagnos and its confidence assessment.The present invention considers subjective and objective people because of the Data Physical difference and feature of key element, analytical technology is compressed based on big datas such as information conversion, extensive analysis, realize that the depth for perceiving information of testing and assessing to the magnanimity of the covering informant of electric power one group is excavated to merge, so that basic index data set physical significance becomes apparent from, more objective comprehensively reflection people is because of the data characteristics of key element.
Description
Technical field
The present invention relates to safety management field, and in particular to a kind of people is because of key element Analysis of Potential diagnostic method.
Background technology
Safety in production is a fundamental state policy of China, is to ensure that economic construction sustained, stable and coordinated development and society are pacified
Fixed primary condition, is also the important symbol of progress of social civilization.The safety in production of electric power is not only before electric power industry development
Carry and basis, be also that electric power enterprise plays social benefit and improves the guarantee of Business Economic Benefit, " Safety first, precaution crucial "
Policy be power generation build eternal theme.
Electric power generation system is the bulky systems being made up of a variety of key elements such as material equipment, personnel.Wherein, as important set
Into three digest journals such as the material technology system of part, humanistic community system and individual Member Systems, with people because key element (physiology,
Psychology, sign) namely " people because dominance " to be coupled the crucial tie of whole safety production system, influence each other, phase interaction
With, together constitute electric power enterprise safety in production material conditions, humanistic environment and participate in main body so that electric power safety production is in
Now significant time-varying dynamic and system complexity feature, determine exploration electric power enterprise during keeping the safety in production, it is necessary to handle
Hold its rule of keeping the safety in production.
From the point of view of electric power enterprise safety production system, people, thing, ring are the fundamentals for maintaining its safe condition, these three
Effect and status of the key element in enterprise safety operation are all unquestionable.But in actual production, people, thing, ring three elements for
The value of the security reliability of maintenance system is the presence of significant difference, wherein, environmental factor can with " people " and " thing " change
And change;Meanwhile, " thing " because insecurity level greatly declined, improve " thing " because level of security need it is substantial amounts of science and technology throw
Enter and be possible to produce effects;And " people " is because of the first cause of the electric power enterprise production accident caused by, by " people " is because what is had
The outstanding features such as learnability, Modulatory character, its reliability still has wide room for promotion.
But at present, to people because the research practice of the key element mechanism of action and its reliability is still within starting stage, dependence person
The shallow-layer explorative research less effective of work independence and equipment assisted decompression.Unification, specification, effective people are especially a lack of because wanting
Plain cognitive and appraisal procedure, therefore, by improving electric power safety production because of the intervention regulation and control of key element to people, promoting cost efficiency
Still shoulder heavy responsibilities.Its difficult point is mainly reflected in:
(1) people is because of the apparent cognitive complexity of key element, and target variable is normative, availability is difficult
Human body is as complicated biology system, and its physiology, psychology, sign et al. are mainly shown as the god of complexity because of key element
Comprehensive through, the external sector signal of kinematic system perceives response, therefore, to the apparent cognitive still difficulty of its complicated mechanism of action
It is larger.By continuing to develop in recent years, at present, the two kinds of technical ways used in application study are included based on biology
The objective of the physiological signals such as electricity, physics pulse, breathing surveys perception, and the test and appraisal of the text based on subjective psychology quality.But on
Two methods are stated, its mechanism of perception and result presentation mode have larger difference, be people because of key element association mechanism cognition and enter
The regulation and control of one step analysis and utilization bring great difficulty.
(2) the subjective dependence of existing appraisal procedure is strong, and the diagnosis result of decision is unilateral single
The intelligent algorithm analyzed based on electric power big data is more in electric power system dispatching operation and equipment state assessment etc.
Individual field is used widely, the stronger artificial neural network algorithm of such as fuzzy supervised learning ability, linear space separability
Can preferable Gauss Bayes linear regression procedure and the preferable support vector cassification of high dimensional nonlinear space segmentation performance
Deng many sorting techniques of intelligence.
But there is problems with above-mentioned practicing for single algorithm:First, algorithm critical performance parameters and association are defeated
Entering index needs to rely on subjective experience selection, and algorithm does not possess the ability of parameter index relevance excavation in itself;Second, single calculate
Method case study applicability is different, and the diagnosis result of decision obtained using single algorithm is unilateral single, causes misdiagnosis rate high.
(3) different population posies feature is ignored, the effective durability of system is not good enough
For the line operating personnel of electric power one, according to work position feature and the difference of job requirements, change can be divided into
O&M, a variety of populations such as line live-line work are dispatched in power station maintenance debugging, end of stand, the different population people reflected because
Key element effect source and primary and secondary feature are also not quite similar, and the people using equipment assisted decompression as target is because of key element intervention shallow-layer at present
Using, do not take into full account above-mentioned post feature difference to algorithm index relevance and diagnose decision making reliability shadow
Ring.
(4) effect checking process of feedback redundancy, quick response feedback mechanism shortcoming
At present, effect verifies feedback mechanism is generally filled in by feedback contact table and user visits et al. force feedback authentication
Formula is constituted, and effect checking feedback procedure redundancy is cumbersome, and human cost is high, ageing not good, it is impossible to meet electric power safety production pair
People assesses ageing requirement because of key element.
The content of the invention
It is an object of the invention to provide a kind of people because of key element Analysis of Potential diagnostic method, deposited with solving above-mentioned prior art
The problem of.
To reach above-mentioned purpose, the invention provides a kind of people because of key element Analysis of Potential diagnostic method, comprise the steps of:
Step S1, collection worker at the production line's all standing people build people because of key element basic index data acquisition system because of element information;
Step S2, according to people because key element basic index data acquisition system build people because of key element extensive analysis model;
Step S3, structure people are because of key element Analysis of Potential diagnosis decision model;
Step S4, input employee's sample data to be measured, obtain people because of the decision-making of key element comprehensive diagnos and its confidence assessment.
Above-mentioned people because of key element Analysis of Potential diagnostic method, wherein, in addition to step S5, by background system to diagnosis decision-making
As a result issue push is carried out, instructs because of key element hidden danger to recall into pedestrian and administers.
Above-mentioned people because of key element Analysis of Potential diagnostic method, wherein, in step sl, the people because element information comprising visitor
See perception information and subjective perception information.
Above-mentioned people because of key element Analysis of Potential diagnostic method, wherein, in step s 2, specifically comprise the steps of:
Step S21, by people because key element basic index data are divided into quantitative change Classical field and qualitative change section domain;
Step S22, the Classical field according to division and section domain construction people are because of key element extensive analysis model.
Above-mentioned people because of key element Analysis of Potential diagnostic method, wherein, in step s3, specifically comprise the steps of:
Step S31, based on the analysis of sample statistics characteristic estimating, adaptive sample is carried out to basic index set sample data set
This over-sampling is merged;
Step S32, parallel multiple-objection optimization carried out to index set and algorithm set based on balanced sample set, and to set
Relevance depth is excavated, and bad subset non-to index/algorithm Pareto features solves optimal linked character subset;
Step S33, to optimal characteristics vector and optimum classifier set combination property carry out test checking after,
The diagnosis result of decision to optimum classifier set carries out reliability fusion, and generation is directed to the people of different groups because of key element Analysis of Potential
Diagnose decision model.
Above-mentioned people because of key element Analysis of Potential diagnostic method, wherein, in step S31, specifically comprise the steps of:
Step S311, according to people because basic index data set is divided into four subsets by key element Status Type:State is excellent,
In good condition, state is qualified, state is unqualified;
Step S312, the calculating a few sample collection sample number to be fused, it is calculated for each a small number of data set samples
With respect to k adjacent to ratio, on this basis, ratio is closed on to relative k calculating Density Distribution is normalized;
Step S313, weighted sampled probability density estimation function of the construction based on Gaussian Profile, and it is close from the probability
A few sample collection sample number to be fused of being sampled in distribution is spent, construction meets a small number of data sets of fusion of sample equilibrium condition.
Above-mentioned people because of key element Analysis of Potential diagnostic method, wherein, in step S33, specifically comprise the steps of:
Step S331, the non-bad algorithm result of decision set structure decision matrixs of Pareto according to association;
Step S332, every a line to decision matrix take pessimistic attitude strategy and optimism policy calculation OWA to calculate respectively
Son, i.e., take the minimum value and maximum of the row evaluation of estimate respectively, obtains multiple decision informations interval;
Step S333, interval left column is considered as pessimistic information source, its right row is carried out to it respectively as optimistic information source
Normalization, construction represents the fuzzy decision vector of pessimistic attitude and optimism;
Step S334, the basic brief inference using α-cut methods being converted into fuzzy decision vector in DS evidence theories, and
Final integrated decision-making rule is obtained based on Dempster-Shafer reliability fusion rules, so as to judge people because of key element sample
End-state type affiliation.
Relative to prior art, the invention has the advantages that:
(1) subjective and objective people is considered because of the Data Physical difference and feature of key element, based on information conversion, extensive analysis etc.
Big data compresses analytical technology, realizes that the depth for perceiving information of testing and assessing to the magnanimity of the covering informant of electric power one group is excavated and merges, makes
Obtain basic index data set physical significance to become apparent from, more objective comprehensively reflection people is because of the data characteristics of key element.
(2) the different line operation colonies of electric power one, the subdivision differentiation of identical operation colony different conditions type are taken into full account,
Comprehensively utilize the artificial intelligence technologys such as parallel multiple-objection optimization, evidence theory information depth integration and build people because of key element Analysis of Potential
Decision model is diagnosed, intelligent diagnostics integrated decision-making information bank is established, makes the diagnosis result of decision fairer and more reasonable.
Brief description of the drawings
Fig. 1 is the present inventor because of the flow chart of key element Analysis of Potential diagnostic method;
Fig. 2 is for structure people because key element Analysis of Potential diagnoses the flow chart of decision model;
Fig. 3 is the flow chart that multiobjective optimization index/algorithm relation integration parallel optimization is excavated with depth.
Embodiment
Below in conjunction with accompanying drawing, by specific embodiment, the invention will be further described, and these embodiments are merely to illustrate
The present invention, is not limiting the scope of the invention.
As shown in figure 1, being comprised the steps of the invention provides a kind of people because of key element Analysis of Potential diagnostic method:
Step S1, collection worker at the production line's all standing people build people because of key element basic index data acquisition system because of element information;
Step S2, according to people because key element basic index data acquisition system build people because of key element extensive analysis model;
Step S3, structure people are because of key element Analysis of Potential diagnosis decision model;
Step S4, input employee's sample data to be measured, obtain people because of the decision-making of key element comprehensive diagnos and its confidence assessment.
Above-mentioned people because of key element Analysis of Potential diagnostic method, wherein, in addition to step S5, by background system to diagnosis decision-making
As a result issue push is carried out, instructs because of key element hidden danger to recall into pedestrian and administers.
Background system real-time collecting employee's index sample information on the regular payroll, realizes data analysis and learning management, user monitoring
The basic functions such as management, communication acquisition management, abnormal user active forewarning.On above-mentioned functions optimized integration, first with reference to cloud
Platform construction " employee-teams and groups-company " multistage network framework, and backstage Analysis of Policy Making and push are carried out, complete employee personal pre-
Alert, problem escalation, teams and groups are periodically integrated, adjust guidance, and company leader's backtracking is dredged, the different Functional divisions of index management and control, real
Existing resource-sharing and information mutual communication, ageing, the lifting electric power safety life to greatest extent that enhancing people eliminates by key element hidden danger
The cost efficiency ability of production.
The system meets different computer hardwares and the portability and interoperability of operating system, with flat across many hardware
The characteristics of platform, system Construction scale can have very large option leeway according to computer type difference.Systematic difference can be according to user
Demand be distributed on different machines, equipment both can be based on risc architecture or based on CISC structures.Weight
The node wanted supports two-shipper, double net patterns, with the reliability of safeguards system, and realizes load balancing, and advance data collection can
Support to receive remote action data with network mode in a usual manner, server uses redundant configuration, database server and disk battle array
Row can use cluster management, constitute the data center of the whole network.
Background analysis also includes real time propelling movement with supplying system and recalls application platform, enables after test employee's real-time reception
The real-time analysis decision information that the service of platform System Back-end is pushed, teams and groups and company management and control personnel can also receive immediately, inquiry person
Work status type, and backtracking management and control online is carried out, without artificial return visit, operating efficiency is greatly improved, the normal of movement is realized
Stateization monitors demand.
Above-mentioned people because of key element Analysis of Potential diagnostic method, wherein, in step sl, the people because element information comprising visitor
See perception information and subjective perception information.The objective perception information is gathered by wearable physiology sensing equipment, is mainly included
The physiology real time information such as pulsation, breathing.Supervisor's information is gathered by cell-phone customer terminal, and subjective quality is provided with it and is surveyed from old
Table is commented, subjective quality covers mental health state, post power quality, post capability quality and post personality element from old test and appraisal
The subjective psychology physiology key element of the comprehensive general post competency of electric power worker at the production line of reflection comprehensively such as matter, using multinomial standardization
, self with good reliability and validity carries out synthesis measuring to measured employee, and entered by level weighted analysis
Overall psychological quality of the row from old test and appraisal Quantitative marking, on this basis each measured employee of Comprehensive Assessment.
Above-mentioned people because of key element Analysis of Potential diagnostic method, wherein, in step s 2, specifically comprise the steps of:
Step S21, by people because key element basic index data be divided into quantitative change Classical field (normal condition basic quantitative change requirement
Scope) and qualitative change section domain (the qualitative change scope that state changes);
Step S22, the Classical field according to division and section domain construction people are because of key element extensive analysis model.
As shown in Fig. 2 above-mentioned people is because of key element Analysis of Potential diagnostic method, wherein, in step s3, specifically comprising following
Step:
Step S31, based on the analysis of sample statistics characteristic estimating, adaptive sample is carried out to basic index set sample data set
This over-sampling is merged;
Step S32, as shown in figure 3, excellent to index set and the parallel multiple target of algorithm set progress based on balanced sample set
Change, and set associativity depth is excavated, bad subset non-to index/algorithm Pareto features solves optimal linked character subset;
The particle rapidity and location updating of multiple target effective information adaptive particle swarm optimization algorithm (EIA-MOPSO) are based on
Following weight criterion:(1) Inertia:Based on nearest movement velocity vector;(2) memory term:Based on same particle optimal particle position
Put vector;(3) global keys:Based on population history optimum particle position information.Pass through Inertia, memory term and global keys three
Ranking operation, it is ensured that global optimum's characteristic of final gained Pareto feature noninferior solutions.
Step S33, to optimal characteristics vector and optimum classifier set combination property carry out test checking after,
The diagnosis result of decision to optimum classifier set carries out reliability fusion, and generation is directed to the people of different groups because of key element Analysis of Potential
Diagnose decision model.
Obtain Pareto non-bad index sets and its association associated for different conditions type crowd sample set
, it is necessary to effectively be believed the single result of decision of many algorithms by effective combined decision rule after the non-bad algorithm sets of Pareto
Breath fusion, so as to obtain the more objective rational comprehensive diagnos result of decision.The process is using fuzzy careful based on evidential reasoning
Average (FCOWA-ER) the reliability blending algorithm of careful Ordered Weighted, it is the uncertain inference side under a kind of multiple attribute decision making (MADM) framework
Method.The basis of this method is DS evidence theories, and basic thought is under multiple attribute decision making (MADM) framework, respectively with most pessimistic and most optimistic
Attitude constructs two fuzzy membership functions, mass the function mPess and mOpti of two kinds of attitudes of correspondence is obtained by α-cut, most
Last decision-making is made based on Dempster rules of combination and decision rule afterwards.
Above-mentioned people because of key element Analysis of Potential diagnostic method, wherein, in step S31, specifically comprise the steps of:
Step S311, according to people because basic index data set is divided into four subsets by key element Status Type:State is excellent,
In good condition, state is qualified, state is unqualified;
Step S312, the calculating a few sample collection sample number to be fused, it is calculated for each a small number of data set samples
With respect to k adjacent to ratio, on this basis, ratio is closed on to relative k calculating Density Distribution is normalized;
Step S313, weighted sampled probability density estimation function of the construction based on Gaussian Profile, and it is close from the probability
A few sample collection sample number to be fused of being sampled in distribution is spent, construction meets a small number of data sets of fusion of sample equilibrium condition.
Above-mentioned people because of key element Analysis of Potential diagnostic method, wherein, in step S33, specifically comprise the steps of:
Step S331, the non-bad algorithm result of decision set structure decision matrixs of Pareto according to association;
Step S332, every a line to decision matrix take pessimistic attitude strategy and optimism policy calculation OWA to calculate respectively
Son, i.e., take the minimum value and maximum of the row evaluation of estimate respectively, obtains multiple decision informations interval;
Step S333, interval left column is considered as pessimistic information source, its right row is carried out to it respectively as optimistic information source
Normalization, construction represents the fuzzy decision vector of pessimistic attitude and optimism;
Step S334, the basic brief inference using α-cut methods being converted into fuzzy decision vector in DS evidence theories, and
Final integrated decision-making rule is obtained based on Dempster-Shafer reliability fusion rules, so as to judge people because of key element sample
End-state type affiliation.
In summary, the present invention considers subjective and objective people because of the Data Physical difference and feature of key element, is become based on information
Change, the big data such as extensive analysis compression analytical technology, realize the depth that information of testing and assessing is perceived to the magnanimity of the covering informant of electric power one group
Degree excavates fusion so that basic index data set physical significance becomes apparent from, and more objective comprehensively reflection people is because of the number of key element
According to feature.The present invention simultaneously taken into full account the different line operation colonies of electric power one, identical operation colony different conditions type it is thin
Divide differentiation, comprehensively utilize the artificial intelligence technologys such as parallel multiple-objection optimization, evidence theory information depth integration and build people because wanting
Plain Analysis of Potential diagnoses decision model, establishes intelligent diagnostics integrated decision-making information bank, allows the diagnosis result of decision is more fair to close
Reason.
Although present disclosure is discussed in detail by above preferred embodiment, but it should be appreciated that above-mentioned
Description is not considered as limitation of the present invention.After those skilled in the art have read the above, for the present invention's
A variety of modifications and substitutions all will be apparent.Therefore, protection scope of the present invention should be limited to the appended claims.
Claims (7)
1. a kind of people is because of key element Analysis of Potential diagnostic method, it is characterised in that comprise the steps of:
Step S1, collection worker at the production line's all standing people build people because of key element basic index data acquisition system because of element information;
Step S2, according to people because key element basic index data acquisition system build people because of key element extensive analysis model;
Step S3, structure people are because of key element Analysis of Potential diagnosis decision model;
Step S4, input employee's sample data to be measured, obtain people because of the decision-making of key element comprehensive diagnos and its confidence assessment.
2. people as claimed in claim 1 is because of key element Analysis of Potential diagnostic method, it is characterised in that also including step S5, by rear
Platform system carries out issue push to the diagnosis result of decision, instructs because of key element hidden danger to recall into pedestrian and administers.
3. people as claimed in claim 1 is because of key element Analysis of Potential diagnostic method, it is characterised in that in step sl, the people
Because element information includes objective perception information and subjective perception information.
4. people as claimed in claim 1 is because of key element Analysis of Potential diagnostic method, it is characterised in that in step s 2, specific bag
Containing following steps:
Step S21, by people because key element basic index data are divided into quantitative change Classical field and qualitative change section domain;
Step S22, the Classical field according to division and section domain construction people are because of key element extensive analysis model.
5. people as claimed in claim 1 is because of key element Analysis of Potential diagnostic method, it is characterised in that in step s3, specific bag
Containing following steps:
Step S31, based on the analysis of sample statistics characteristic estimating, adaptive sample mistake is carried out to basic index set sample data set
Sampling fusion;
Step S32, parallel multiple-objection optimization carried out to index set and algorithm set based on balanced sample set, and to set associative
Property depth excavate, bad subset non-to index/algorithm Pareto features solves optimal linked character subset;
Step S33, to optimal characteristics vector and optimum classifier set combination property carry out test checking after, to most
The diagnosis result of decision of excellent grader set carries out reliability fusion, and generation is directed to the people of different groups because key element Analysis of Potential is diagnosed
Decision model.
6. people as claimed in claim 5 is because of key element Analysis of Potential diagnostic method, it is characterised in that in step S31, specific bag
Containing following steps:
Step S311, basic index data set is divided into four subsets:State is excellent, in good condition, state is qualified, state not
It is qualified;
Step S312, the calculating a few sample collection sample number to be fused, its is calculated with respect to k for each a small number of data set samples
Neighbouring ratio, on this basis, closes on ratio to relative k and calculating Density Distribution is normalized;
Step S313, weighted sampled probability density estimation function of the construction based on Gaussian Profile, and divide from the probability density
Sampled in cloth a few sample collection sample number to be fused, construction meets a small number of data sets of fusion of sample equilibrium condition.
7. people as claimed in claim 5 is because of key element Analysis of Potential diagnostic method, it is characterised in that in step S33, specific bag
Containing following steps:
Step S331, the non-bad algorithm result of decision set structure decision matrixs of Pareto according to association;
Step S332, every a line to decision matrix take pessimistic attitude strategy and optimism policy calculation OWA operators respectively, i.e.,
The minimum value and maximum of the row evaluation of estimate are taken respectively, obtain multiple decision informations interval;
Step S333, interval left column is considered as pessimistic information source, its right row carries out normalizing to it respectively as optimistic information source
Change, construction represents the fuzzy decision vector of pessimistic attitude and optimism;
Step S334, the basic brief inference using α-cut methods being converted into fuzzy decision vector in DS evidence theories, and be based on
Dempster-Shafer reliability fusion rules obtain final integrated decision-making rule, so as to judge that people is final because of key element sample
Status Type belongs to.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710380136.3A CN107103434A (en) | 2017-05-25 | 2017-05-25 | A kind of people is because of key element Analysis of Potential diagnostic method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710380136.3A CN107103434A (en) | 2017-05-25 | 2017-05-25 | A kind of people is because of key element Analysis of Potential diagnostic method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107103434A true CN107103434A (en) | 2017-08-29 |
Family
ID=59670514
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710380136.3A Pending CN107103434A (en) | 2017-05-25 | 2017-05-25 | A kind of people is because of key element Analysis of Potential diagnostic method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107103434A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107992880A (en) * | 2017-11-13 | 2018-05-04 | 山东斯博科特电气技术有限公司 | A kind of optimal lump classification method for diagnosing faults of power transformer |
CN113656123A (en) * | 2021-07-28 | 2021-11-16 | 上海纽盾科技股份有限公司 | Information evaluation method, device and system for equal protection evaluation |
CN116109296A (en) * | 2023-04-07 | 2023-05-12 | 北京中建源建筑工程管理有限公司 | Positioning repair method and system for hidden danger of building quality |
-
2017
- 2017-05-25 CN CN201710380136.3A patent/CN107103434A/en active Pending
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107992880A (en) * | 2017-11-13 | 2018-05-04 | 山东斯博科特电气技术有限公司 | A kind of optimal lump classification method for diagnosing faults of power transformer |
CN113656123A (en) * | 2021-07-28 | 2021-11-16 | 上海纽盾科技股份有限公司 | Information evaluation method, device and system for equal protection evaluation |
CN113656123B (en) * | 2021-07-28 | 2023-05-16 | 上海纽盾科技股份有限公司 | Information evaluation method, device and system for equal-protection evaluation |
CN116109296A (en) * | 2023-04-07 | 2023-05-12 | 北京中建源建筑工程管理有限公司 | Positioning repair method and system for hidden danger of building quality |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Barak et al. | A novel hybrid fuzzy DEA-Fuzzy MADM method for airlines safety evaluation | |
Ju et al. | Evaluating emergency response capacity by fuzzy AHP and 2-tuple fuzzy linguistic approach | |
Wolfslehner et al. | Mapping indicator models: From intuitive problem structuring to quantified decision-making in sustainable forest management | |
Feng et al. | An intelligent decision support system for fuzzy comprehensive evaluation of urban development | |
Hartati et al. | Electre methods in solving group decision support system bioinformatics on gene mutation detection simulation | |
Wang et al. | A construction of smart city evaluation system based on cloud computing platform | |
CN107103434A (en) | A kind of people is because of key element Analysis of Potential diagnostic method | |
Nichols et al. | Evaluation of environmental assessment methods | |
Edjossan-Sossou et al. | A decision-support methodology for assessing the sustainability of natural risk management strategies in urban areas | |
CN105956390A (en) | Ecological safety early-warning and evaluating visualization system and method | |
CN107220765A (en) | A kind of people is because of key element Analysis of Potential diagnostic system | |
Gong et al. | CARESim: An integrated agent-based simulation environment for crime analysis and risk evaluation (CARE) | |
Zhichong et al. | Framework of spatial decision support system for large-scale public building evacuation | |
López et al. | Multicriteria Decision Model to Support the Evaluation of Common Jurisdiction Violence in the Capital Cities of the States of Mexico | |
CN114218290A (en) | Selection method for equipment human-computer interaction interface usability evaluation | |
Wang et al. | LSTM-based alarm prediction in the mobile communication network | |
Ahmed et al. | A university leader selection novel intelligent system based on Fuzzy-AHP and PROMETTEE II | |
Páscoa et al. | Effectiveness index as an organizational cockpit instrument | |
Li | Sports policy and training decision support method based on wireless sensor network | |
Wei et al. | Understanding requirements for technology-supported healthy aging | |
Hikmawati et al. | Multi-Criteria Recommender System for Determining Risk Level of Covid-19 | |
Xu et al. | Evaluation on service quality in institutional pensions based on a novel hierarchical DEMATEL method for PLTSs | |
Savchenko-Synyakova et al. | The Tools for Intelligent Data Analysis, Modeling and Forecasting Of Social and Economic Processes | |
Begicheva | Donabedian Approach for Simulation Modeling to Evaluate the Quality of Emergency Medical Services in a Large Metropolitan Area: A Case Study | |
Chen et al. | A research on the Taipei MRT passenger traffic prediction model |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170829 |
|
RJ01 | Rejection of invention patent application after publication |