CN103150685A - System and method of intelligent repair schedule optimization compilation - Google Patents

System and method of intelligent repair schedule optimization compilation Download PDF

Info

Publication number
CN103150685A
CN103150685A CN2013100442341A CN201310044234A CN103150685A CN 103150685 A CN103150685 A CN 103150685A CN 2013100442341 A CN2013100442341 A CN 2013100442341A CN 201310044234 A CN201310044234 A CN 201310044234A CN 103150685 A CN103150685 A CN 103150685A
Authority
CN
China
Prior art keywords
algorithm
module
grading
model
library module
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
CN2013100442341A
Other languages
Chinese (zh)
Other versions
CN103150685B (en
Inventor
荀辰龙
蒲天骄
周海明
郑杰
赵立强
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.)
State Grid Corp of China SGCC
China Electric Power Research Institute Co Ltd CEPRI
Original Assignee
State Grid Corp of China SGCC
China Electric Power Research Institute Co Ltd CEPRI
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 State Grid Corp of China SGCC, China Electric Power Research Institute Co Ltd CEPRI filed Critical State Grid Corp of China SGCC
Priority to CN201310044234.1A priority Critical patent/CN103150685B/en
Publication of CN103150685A publication Critical patent/CN103150685A/en
Application granted granted Critical
Publication of CN103150685B publication Critical patent/CN103150685B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Landscapes

  • Medical Treatment And Welfare Office Work (AREA)

Abstract

The invention provides a system and a method for intelligent repair schedule optimization compilation. The system comprises a model algorithm filtering module, an evaluation rating module, a model algorithm library module and a goal constraint library module. The model algorithm filtering module obtains rating information and algorithms and models corresponding to the rating information from the model algorithm library module, filters the rating information and chooses the algorithm which is highest in rating to carry out optimization compilation operation. A user rates the optimization compilation operation result through the evaluation rating module, and stores the rating result in the model algorithm library module or the goal constraint library module. An algorithm which can meet requirements of the specific user can be filtered from a store where a large number of algorithms are accumulated according to the method adjustment of the user and history rating. After use for a long time, algorithm choices in difference and parameter preset in difference, pointing to different conditions, can be also accumulated, and the intelligent repair optimization compilation system can also be more adaptive to various environments and requirements of dynamic change.

Description

A kind of intelligent Maintenance Schedule Optimization workout system and method
Technical field
The invention belongs to the turnaround plan technical field, be specifically related to a kind of intelligent Maintenance Schedule Optimization workout system and method.
Background technology
The Plant maintenance plan establishment of intelligence is the requirement of following intelligent grid, now both at home and abroad the Maintenance Schedule Optimization problem is had a large amount of research, and proposed different algorithms or modeling method for different goal constraints.Yet huge difficulty is arranged but when implementing, because not being simple one or two target or constraint, the establishment of the Maintenance Schedule Optimization in reality can not summarize, although often establishment plan has out reached this target by some way, but performance is extremely disappointing on another index, manually establishment is revised so have to again, expends a large amount of manpower energy.
And for China, the develop rapidly of electric utility often makes the algorithm in a corresponding area lose efficacy soon, and some algorithm even also not have to adjust just to be become before the best algorithm that agrees with most because the introduction of new equipments or new line loses effectiveness in a large number.Want this moment to tend to waste a large amount of manpower energy according to the new algorithm of reality exploitation in real time, become the task of top priority and introduce a kind of intelligent workout system that to learn of expanding.
Summary of the invention
In order to overcome above-mentioned the deficiencies in the prior art, the invention provides a kind of intelligent Maintenance Schedule Optimization workout system and method, algorithm screening and the coupling according to goal constraint and data scale type of intelligence, and after repeatedly using, can means adjustment and the historical grading according to the user filter out the demand that satisfies the specific user from a large amount of algorithm deposit of accumulation.And after using for a long time, select and parameter is preset and also can be accumulated for the algorithms of different under different situations, intelligent Maintenance Schedule Optimization workout system also can more and more adapt to environment and the requirement of various dynamic changes.
In order to realize the foregoing invention purpose, the present invention takes following technical scheme:
A kind of intelligent Maintenance Schedule Optimization workout system is provided, and described system comprises mould calculation screening module, estimates grading module, model algorithm library module and goal constraint library module; Described mould is calculated the screening module and obtain grading information and algorithm and model corresponding to this grading information from described model algorithm library module, and described grading information is screened, select the highest algorithm of grading and be optimized the establishment computing, the user will optimize the establishment operation result by described evaluation grading module and grade, and rating result is stored in described model algorithm library module or goal constraint library module.
Described mould is calculated the screening module and is automatically required to select Different Optimization algorithm or model according to varying environment, it takes out the algorithm that can satisfy environmental requirement from grading information, and therefrom select the highest algorithm of grading and be optimized the establishment computing, if do not satisfy the information of environmental requirement in grading information, feed back to the operator and require it default.
After the importing operation result was provided, described evaluation grading module was standard according to accuracy or accuracy to optimization establishment operation result, or estimates grading take the satisfaction that expends time in or stock number is worked out computing as standard to this suboptimization.
Grading is estimated and the user right hook, if certain user repeatedly grades extremely or the default algorithm grading information that will change for the himself; And if multiple-objection optimization establishment operation result is unsuccessful, complete optimization establishment computing and import operation result satisfied by adjusting environmental parameter at last, by estimating this user of grading module records, the multiple goal center of gravity under this environment is partial to and is recorded in the goal constraint library module, will automatically adjust the multiple goal center of gravity if same situation occurs next time.
Different optimized algorithm and the models of described model algorithm library module stored, and is used for storage optimization algorithm and model under varying environment requires and the grading information under different user; The user is manually pre-if the content of extended model algorithms library module.
Described goal constraint library module is used for variety classes target or constraint object storage, and provide by the user and select to arrange the information of many conditions under in various degree, and the target that sets or constraint are sent into mould as condition calculate in the screening module and screen, then be optimized the establishment computing.
Described model algorithm library module and goal constraint library module all can be expanded, the selection of described evaluation grading module records user to equilibrium point under multiple goal.
A kind of intelligent Maintenance Schedule Optimization preparation method is provided simultaneously, said method comprising the steps of:
Step 1: set up to be used for different optimized algorithms and model, optimized algorithm and model under varying environment requires and goal constraint library module and model algorithm library module that the grading information under different user is stored;
Step 2: again optimize in the process of establishment, mould is calculated the screening module and is selected the highest algorithm of grading to be optimized the establishment computing from the model algorithm library module according to the input message of this establishment;
Step 3: after optimization establishment computing is completed, graded to optimizing the establishment operation result by described evaluation grading module by the user, if it is satisfied to optimize the establishment operation result, the grading that improves optimized algorithm and model, if it is dissatisfied to optimize the establishment operation result, the grading of optimized algorithm and model.
Described input message comprises target, constraint, Cycle Length, data type and data scale.
Compared with prior art, beneficial effect of the present invention is:
1. utilize constraint and target unified Modeling to make the multiple goal balance become possibility, and then utilize mould calculation screening system that best Maintenance Schedule Optimization preparation method is provided;
2. intelligent Maintenance Schedule Optimization workout system provided by the invention possesses extensibility, deposit this system in after algorithm newly developed can being preset, also can with depositing this system in after the target of new demand or constraint interface, can satisfy like this electric power apparatus examination needs that day by day change;
3. have the hommization advantage, can adapt to according to the use of different user, satisfying the preference of different user, and remember this preference, to bring good experience;
4. possess intelligently, can complete after the operation of repeatedly adjusting, grade that optimal algorithm is selected and the target center of gravity stresses;
5. can save in a large number as power equipment changes and upgrade or revise the manpower and materials that algorithm brings, only need to adjust parameter, evaluation result, just bootable intelligent Maintenance Schedule Optimization workout system is made suitable algorithm, intelligence Maintenance Schedule Optimization workout system also can not disappear for the memory of former environment, if environment becomes again, system can adjust immediately.
Description of drawings
Fig. 1 is intelligent Maintenance Schedule Optimization workout system structural topology figure in the embodiment of the present invention;
Fig. 2 is intelligent Maintenance Schedule Optimization preparation method process flow diagram in the embodiment of the present invention.
Embodiment
Below in conjunction with accompanying drawing, the present invention is described in further detail.
As Fig. 1, a kind of intelligent Maintenance Schedule Optimization workout system is provided, described system comprises mould calculation screening module, estimates grading module, model algorithm library module and goal constraint library module; Described mould is calculated the screening module and obtain grading information and algorithm and model corresponding to this grading information from described model algorithm library module, and described grading information is screened, select the highest algorithm of grading and be optimized the establishment computing, the user will optimize the establishment operation result by described evaluation grading module and grade, and rating result is stored in described model algorithm library module or goal constraint library module.
Described mould is calculated the screening module and is automatically required to select Different Optimization algorithm or model according to varying environment, it takes out the algorithm that can satisfy environmental requirement from grading information, and therefrom select the highest algorithm of grading and be optimized the establishment computing, if do not satisfy the information of environmental requirement in grading information, feed back to the operator and require it default.
After the importing operation result was provided, described evaluation grading module was standard according to accuracy or accuracy to optimization establishment operation result, or estimates grading take the satisfaction that expends time in or stock number is worked out computing as standard to this suboptimization.
Grading is estimated and the user right hook, if certain user repeatedly grades extremely or the default algorithm grading information that will change for the himself; And if multiple-objection optimization establishment operation result is unsuccessful, complete optimization establishment computing and import operation result satisfied by adjusting environmental parameter at last, by estimating this user of grading module records, the multiple goal center of gravity under this environment is partial to and is recorded in the goal constraint library module, will automatically adjust the multiple goal center of gravity if same situation occurs next time.
Different optimized algorithm and the models of described model algorithm library module stored, and is used for storage optimization algorithm and model under varying environment requires and the grading information under different user; The user is manually pre-if the content of extended model algorithms library module.
Described goal constraint library module is used for variety classes target or constraint object storage, and provide by the user and select to arrange the information of many conditions under in various degree, and the target that sets or constraint are sent into mould as condition calculate in the screening module and screen, then be optimized the establishment computing.By the method for change objectification, how dissimilar target and constraint expansion are advanced in this database.And relation between each several part: offer the user and be used for arranging the environmental baseline parameter, then send into model discrimination module and computing workout system, and can obtain and store the establishment center of gravity tendency of this user under specific target-rich environment from the grading evaluation module.
Described model algorithm library module and goal constraint library module all can be expanded, the selection of described evaluation grading module records user to equilibrium point under multiple goal.
Described goal constraint library module has extensibility, by the method for change objectification, how dissimilar target and constraint expansion is advanced in this database.The goal constraint library module offers the user and is used for arranging the environmental baseline parameter, then sends into the model discrimination module, and can obtain and store the establishment center of gravity tendency of this user under specific target-rich environment from the grading evaluation module.
As Fig. 2, a kind of intelligent Maintenance Schedule Optimization preparation method is provided simultaneously, said method comprising the steps of:
Step 1: set up to be used for different optimized algorithms and model, optimized algorithm and model under varying environment requires and goal constraint library module and model algorithm library module that the grading information under different user is stored;
Step 2: again optimize in the process of establishment, mould is calculated the screening module and is selected the highest algorithm of grading to be optimized the establishment computing from the model algorithm library module according to the input message of this establishment;
Step 3: after optimization establishment computing is completed, graded to optimizing the establishment operation result by described evaluation grading module by the user, if it is satisfied to optimize the establishment operation result, the grading that improves optimized algorithm and model, if it is dissatisfied to optimize the establishment operation result, the grading of optimized algorithm and model.
Described input message comprises target, constraint, Cycle Length, data type and data scale.
Should be noted that at last: above embodiment is only in order to illustrate that technical scheme of the present invention is not intended to limit, although with reference to above-described embodiment, the present invention is had been described in detail, those of ordinary skill in the field are to be understood that: still can modify or be equal to replacement the specific embodiment of the present invention, and do not break away from any modification of spirit and scope of the invention or be equal to replacement, it all should be encompassed in the middle of claim scope of the present invention.

Claims (9)

1. intelligent Maintenance Schedule Optimization workout system is characterized in that: described system comprises that mould calculates the screening module, estimates grading module, model algorithm library module and goal constraint library module; Described mould is calculated the screening module and obtain grading information and algorithm and model corresponding to this grading information from described model algorithm library module, and described grading information is screened, select the highest algorithm of grading and be optimized the establishment computing, the user will optimize the establishment operation result by described evaluation grading module and grade, and rating result is stored in described model algorithm library module or goal constraint library module.
2. intelligent Maintenance Schedule Optimization workout system according to claim 1, it is characterized in that: described mould is calculated the screening module and is automatically required to select Different Optimization algorithm or model according to varying environment, it takes out the algorithm that can satisfy environmental requirement from grading information, and therefrom select the highest algorithm of grading and be optimized the establishment computing, if do not satisfy the information of environmental requirement in grading information, feed back to the operator and require it default.
3. intelligent Maintenance Schedule Optimization workout system according to claim 1, it is characterized in that: after the importing operation result is provided, described evaluation grading module is standard according to accuracy or accuracy to optimization establishment operation result, or estimates grading take the satisfaction that expends time in or stock number is worked out computing as standard to this suboptimization.
4. intelligent Maintenance Schedule Optimization workout system according to claim 3, is characterized in that: grade and estimate and the user right hook, if certain user repeatedly extremely grades or presets the algorithm grading information that will change for the himself; And if multiple-objection optimization establishment operation result is unsuccessful, complete optimization establishment computing and import operation result satisfied by adjusting environmental parameter at last, by estimating this user of grading module records, the multiple goal center of gravity under this environment is partial to and is recorded in the goal constraint library module, will automatically adjust the multiple goal center of gravity if same situation occurs next time.
5. intelligent Maintenance Schedule Optimization workout system according to claim 1, it is characterized in that: different optimized algorithm and the models of described model algorithm library module stored, and is used for storage optimization algorithm and model under varying environment requires and the grading information under different user; The user is manually pre-if the content of extended model algorithms library module.
6. intelligent Maintenance Schedule Optimization workout system according to claim 1, it is characterized in that: described goal constraint library module is used for variety classes target or constraint object storage, and provide by the user and select to arrange the information of many conditions under in various degree, and the target that sets or constraint are sent into mould as condition calculate in the screening module and screen, then be optimized the establishment computing.
7. according to claim 5 or 6 described intelligent Maintenance Schedule Optimization workout systems, it is characterized in that: described model algorithm library module and goal constraint library module all can be expanded, the selection of described evaluation grading module records user to equilibrium point under multiple goal.
8. intelligent Maintenance Schedule Optimization preparation method is characterized in that: said method comprising the steps of:
Step 1: set up to be used for different optimized algorithms and model, optimized algorithm and model under varying environment requires and goal constraint library module and model algorithm library module that the grading information under different user is stored;
Step 2: again optimize in the process of establishment, mould is calculated the screening module and is selected the highest algorithm of grading to be optimized the establishment computing from the model algorithm library module according to the input message of this establishment;
Step 3: after optimization establishment computing is completed, graded to optimizing the establishment operation result by described evaluation grading module by the user, if it is satisfied to optimize the establishment operation result, the grading that improves optimized algorithm and model, if it is dissatisfied to optimize the establishment operation result, the grading of optimized algorithm and model.
9. intelligent Maintenance Schedule Optimization preparation method according to claim 8, it is characterized in that: described input message comprises target, constraint, Cycle Length, data type and data scale.
CN201310044234.1A 2013-02-04 2013-02-04 A kind of intelligence Maintenance Schedule Optimization workout system Active CN103150685B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201310044234.1A CN103150685B (en) 2013-02-04 2013-02-04 A kind of intelligence Maintenance Schedule Optimization workout system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201310044234.1A CN103150685B (en) 2013-02-04 2013-02-04 A kind of intelligence Maintenance Schedule Optimization workout system

Publications (2)

Publication Number Publication Date
CN103150685A true CN103150685A (en) 2013-06-12
CN103150685B CN103150685B (en) 2016-08-10

Family

ID=48548740

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201310044234.1A Active CN103150685B (en) 2013-02-04 2013-02-04 A kind of intelligence Maintenance Schedule Optimization workout system

Country Status (1)

Country Link
CN (1) CN103150685B (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104077651A (en) * 2014-06-12 2014-10-01 国家电网公司 Power grid maintenance plan optimization method
CN104217255A (en) * 2014-09-02 2014-12-17 浙江大学 Electrical power system multi-target overhaul optimization method under market environment
CN106845755A (en) * 2016-11-18 2017-06-13 中国电力科学研究院 A kind of interruption maintenance planning professional skill appraisal procedure and system

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101334796A (en) * 2008-02-29 2008-12-31 浙江师范大学 Personalized and synergistic integration network multimedia search and enquiry method
CN102722852A (en) * 2012-06-15 2012-10-10 中国电力科学研究院 Method for compiling overhaul ticket

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101334796A (en) * 2008-02-29 2008-12-31 浙江师范大学 Personalized and synergistic integration network multimedia search and enquiry method
CN102722852A (en) * 2012-06-15 2012-10-10 中国电力科学研究院 Method for compiling overhaul ticket

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
于宏涛: "基于蚁群算法输电线路检修计划的制定", 《计算机应用研究》 *
张小敏等: "专家系统技术在地区电网检修计划编制中的应用", 《电工电能新技术》 *
董雷等: "一种供电系统检修计划自动制定系统的设计方法", 《现代电力》 *

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104077651A (en) * 2014-06-12 2014-10-01 国家电网公司 Power grid maintenance plan optimization method
CN104077651B (en) * 2014-06-12 2015-08-19 国家电网公司 Maintenance scheduling for power systems optimization method
CN104217255A (en) * 2014-09-02 2014-12-17 浙江大学 Electrical power system multi-target overhaul optimization method under market environment
CN104217255B (en) * 2014-09-02 2017-06-13 浙江大学 A kind of power system multiple target optimized maintenance method under market environment
CN106845755A (en) * 2016-11-18 2017-06-13 中国电力科学研究院 A kind of interruption maintenance planning professional skill appraisal procedure and system

Also Published As

Publication number Publication date
CN103150685B (en) 2016-08-10

Similar Documents

Publication Publication Date Title
CN102637203B (en) Method for processing electric quantity data and monitoring master station for automatic electric energy metering systems
CN104077651B (en) Maintenance scheduling for power systems optimization method
CN103902537A (en) Multi-service log data storage processing and inquiring system and method thereof
CN106021733B (en) A kind of fast custom design service system of production line
CN103020360A (en) Integration design method of intelligent substation based on three-dimensional design platform and professional software
CN103150685A (en) System and method of intelligent repair schedule optimization compilation
CN107612045A (en) A kind of Power Plant generated energy intelligent dispensing system and method
CN106026080A (en) System and method for automatically controlling generating capacity of power plant
CN106229978A (en) The pre-judging method of platform district low-voltage problem and system
CN103337040B (en) Wind electricity generation scheduling compilation system on basis of wind electricity volatility, and compilation method thereof
CN104680427A (en) Planning system for comprehensive optimization of regional power distribution network
CN104810834B (en) Many section 500kV electric network reactive compensations switching strategy optimization methods based on voltage sensibility
CN116739187B (en) Reservoir optimal scheduling decision method, device, computer equipment and storage medium
CN103501003A (en) Line loss control system
CN107615183A (en) In Model Predictive Control application program relative to best performance values premium properties system and method
CN107965883A (en) Cloud computing system and method, multi-gang air-conditioner management system and method
CN102497135A (en) Rule-engine-based method for monitoring photovoltaic power station
CN106452837B (en) A kind of intelligent substation switch Dynamic Configuration
CN104931776A (en) Architectural energy consumption item metering system and method based on virtual fusion technology
Soares et al. Optimal generation and transmission expansion planning addressing short-term constraints with co-optimization of energy and reserves
CN103500071B (en) Method and device for storing performance index data quantitatively
CN115713352A (en) Power plant operation calculation analysis method based on graphical modeling technology
CN113050573B (en) Production rhythm-based energy-saving method for air compressor
CN101938367B (en) Method and system for enabling comprehensive network management system to realize performance access of lower network management system in telecommunication network
CN204331791U (en) A kind of electric flux intelligent decision analytic system

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
C14 Grant of patent or utility model
GR01 Patent grant