CN117057593A - Hydropower station maintenance strategy dynamic optimization method under multiple constraint conditions - Google Patents
Hydropower station maintenance strategy dynamic optimization method under multiple constraint conditions Download PDFInfo
- Publication number
- CN117057593A CN117057593A CN202311311674.9A CN202311311674A CN117057593A CN 117057593 A CN117057593 A CN 117057593A CN 202311311674 A CN202311311674 A CN 202311311674A CN 117057593 A CN117057593 A CN 117057593A
- Authority
- CN
- China
- Prior art keywords
- overhaul
- language
- hydropower station
- task
- optimization
- 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
Links
- 238000012423 maintenance Methods 0.000 title claims abstract description 60
- 238000005457 optimization Methods 0.000 title claims abstract description 54
- 238000000034 method Methods 0.000 title claims abstract description 41
- 230000002068 genetic effect Effects 0.000 claims description 16
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 16
- 230000008569 process Effects 0.000 claims description 9
- 210000000349 chromosome Anatomy 0.000 claims description 6
- 238000013519 translation Methods 0.000 claims description 5
- 230000035772 mutation Effects 0.000 claims description 4
- 238000001514 detection method Methods 0.000 claims description 3
- 238000011156 evaluation Methods 0.000 claims description 3
- 230000006870 function Effects 0.000 claims description 3
- 230000008439 repair process Effects 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 230000005611 electricity Effects 0.000 description 3
- 101100517651 Caenorhabditis elegans num-1 gene Proteins 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007717 exclusion Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0633—Workflow analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- 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
- G06Q10/20—Administration of product repair or maintenance
-
- 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
- G06Q50/06—Electricity, gas or water supply
-
- 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
A hydropower station overhaul strategy dynamic optimization method under a multi-constraint condition comprises the following steps: step one: analyzing a service flow of a hydropower station maintenance plan, and summarizing core service constraint conditions and service targets; step two: abstracting and formally defining the result of the step one to form a language in the field of hydropower station maintenance planning and scheduling, and using the language to describe the constraint and optimization targets of the maintenance tasks of most hydropower stations; step three: describing an overhaul plan by using a language in the field of hydroelectric overhaul; step four: transmitting the result of the step three to a language analyzer in the hydroelectric overhaul field, translating the language into the input of a bottom layer combination optimization algorithm by the language analyzer in the hydroelectric overhaul field, and calling the combination optimizer to solve the result to obtain a final scheduling result; step five: and according to the output of the optimized scheduling plan, visually displaying the starting time and the ending time of each task in a Gantt chart mode, so that manual fine adjustment is facilitated, and finally, a hydropower station maintenance plan is formed.
Description
Technical Field
The invention relates to the technical field of hydroelectric power generation, in particular to a hydropower station maintenance strategy dynamic optimization method.
Background
In a large hydropower station, a plurality of hydropower units are often arranged, operation and maintenance optimization of the hydropower station is classified into a plurality of categories, such as A repair, B repair, C repair and D repair, and overhaul of the hydropower station is also performed by disassembling equipment operation and maintenance optimization tasks at a component level, meanwhile, the hydropower station is subject to human factors and hydrology conditions, the units for operation and maintenance optimization are limited, and the operation and maintenance optimization relationship among the equipment is also subjected to various constraint conditions such as dependency, time inclusion, operation and maintenance optimization construction period and the like.
The existing operation and maintenance method is concerned with decision information, constraint conditions and definition of optimization targets of specific scenes in the professional field, and then a general optimization algorithm is used for searching a scheduling result, so that the research on operation optimization of the hydropower industry is lacking, and if various complex constraints of the operation and maintenance optimization are changed or new constraint conditions are considered, a great deal of modification is needed, and the operation and maintenance method cannot be quickly adapted to service changes.
Therefore, the invention provides the description language capable of rapidly determining the operation optimization, and the constraint conditions and the targets in the operation optimization of the hydropower equipment can be accurately described, so that the invention can rapidly adapt to the change of the service scene.
Disclosure of Invention
The invention precisely describes various constraints and targets of the operation and maintenance optimization of the water and electricity equipment through analysis and understanding of the operation and maintenance optimization strategy of the water and electricity equipment and abstract constraint condition primitive words of the definition industry, thereby providing a method capable of solving the problem of the operation and maintenance optimization scheduling of various water and electricity equipment. The description language of operation optimization can be rapidly determined, and constraint conditions and targets in annual overhaul of hydropower station equipment can be accurately described, so that the method can be rapidly adapted to changes of service scenes.
In order to solve the technical problems, the invention adopts the following technical scheme:
a hydropower station overhaul strategy dynamic optimization method under a multi-constraint condition defines a service domain language to describe an overhaul scene of a hydropower station according to characteristics of the service scene of the hydropower station, and then obtains a dynamic optimization result in a language interpretation mode, wherein the dynamic optimization method comprises the following steps:
step one: analyzing a service flow of a hydropower station maintenance plan, and combing factors to be considered in the establishment of the hydropower station maintenance plan, wherein the service optimization target and maintenance constraint are specifically included, and the service optimization target comprises: optimal equivalent availability factor, no water discard, and minimal overlap of time for a specific service task; the overhaul constraint conditions include: (1) Analyzing the total starting time and the total ending time of the current overhaul according to the past year and the real-time water supply condition; (2) According to the overhaul history of the unit, determining the overhaul type of the unit in the current period, and further determining the time required by overhaul; (3) Determining the total number of overhauls which can be carried out simultaneously for each type according to the conditions of the overhauling team personnel; (4) Taking holidays contained in the current overhaul period into consideration, and converting the calendar days into working days; (5) Determining the total number of the overhauls at most simultaneously according to the service requirement of the actual overhauling capacity; (6) The overhaul of important parts in the overhaul of the unit is decomposed and is arranged as sub-overhaul tasks, and all the sub-overhaul tasks are required to be completed in the period of the total overhaul task of the unit;
step two: abstracting and formally defining each service constraint condition and service target to form language in the field of hydropower station maintenance plan scheduling, and using the language to describe the optimization target and constraint condition of the hydropower station maintenance plan;
step three: according to the annual plan and the requirements of hydroelectric overhaul, determining the overhaul types to be carried out on various equipment, and an acceptable overhaul time range, and simultaneously carrying out the overhaul quantity, wherein the overhaul quantity is described by the language of the hydroelectric overhaul field;
step four: providing the defined language of the hydropower overhaul field to a language analyzer of the hydropower overhaul field, translating the language into the input of a bottom layer combination optimization algorithm by the language analyzer of the hydropower overhaul field, and calling the combination optimizer to solve the language to obtain a scheduling plan;
step five: optimizing the scheduling plan output, visually displaying the starting time and the ending time of each task in a Gantt chart mode, then manually fine-adjusting to form a hydropower station maintenance strategy, and providing the maintenance strategy for a maintenance team to execute so as to realize maintenance on hydropower station equipment.
Preferably, the domain language in step two comprises the following semantic definitions: the basic elements of the language are TASKs, TASK marks are uniformly used in the definition of the primitive language, and when the language is actually used, suffix-free numbers are used for marking, and the language is marked from 0; numerical values are marked by NUM in the definition of the primitive language, and are directly expressed by the numerical values in specific practical use, and specific meanings are interpreted according to the definition of the primitive language; the primitive language is divided into constraint type and target type, which are used for expressing constraint condition and expected target result; the target is a fixed primitive description; all descriptions are used "; "number split.
Preferably, the vital components include a generator and a water conduction system.
Preferably, genetic algorithms are employed to solve for combinatorial optimization.
Preferably, a genetic algorithm is adopted to solve the combination optimization, and an optimization solution is found according to a constraint condition formula after translation, and the specific steps are as follows: (1) chromosome coding: a method for converting a feasible solution of a problem in a scheduling solution space from the solution space to a search space of a genetic algorithm adopts a binary coding method, and takes the starting time and the ending time of each task as coding elements of the solution space; (2) initial population generation and related algorithm parameters: maximum evolution algebra T, population size M, crossover probability Pc, mutation probability Pm, randomly generating M individuals as an initialization population P0; (3) fitness value evaluation detection: the fitness function shows the goodness of the individual or the solution, and the fitness of each individual in the group P (t) is calculated; (4) genetic operators, three genetic operators in total: (a) selecting: selecting good individuals from the old population to form a new population with a certain probability, so as to reproduce and obtain next generation individuals, wherein the probability of the selected individuals is related to the fitness value, and the higher the fitness value of the individuals is, the higher the probability of the selected individuals is; (b) crossing: the crossover operation refers to randomly selecting two individuals from a population, and inheriting the excellent characteristics of a parent string to a child string through the exchange combination of two chromosomes, so as to generate new excellent individuals; (c) variation: in order to prevent genetic algorithm from falling into local optimal solution in the optimization process, individual variation is required in the searching process; (5) termination judgment condition: and within a certain time range, taking the individual with the greatest fitness obtained in the evolution process as the optimal solution output, and terminating the operation.
Compared with the prior art, the invention has the following technical effects:
the invention defines a maintenance scene of the hydropower industry in a business field language mode, has higher abstract property and universality, converts the interpretation of the business field language into a universal combined optimized input condition, and then invokes a universal optimizing engine to find an optimized scheme. In the face of various complex business scenes, a user can obtain the result of optimizing the scheduling by simply describing various constraint conditions and various task variables and optimizing targets. The whole scheme integrates the knowledge of the hydropower industry, can solve the maintenance scheduling problem of most hydropower units, has better flexibility and intelligence in the industry, does not need binding and special software, and can be realized by only re-describing according to the field language and re-optimizing calculation when various constraint conditions and targets change.
Drawings
The invention is further illustrated by the following examples in conjunction with the accompanying drawings:
fig. 1 is an overall flow chart of the present invention.
Detailed Description
A hydropower station overhaul strategy dynamic optimization method under a multi-constraint condition is characterized in that according to the characteristics of a hydropower station service scene, a service domain language is defined to describe the hydropower station overhaul scene, and then a dynamic optimization result is obtained in a language interpretation mode, and the dynamic optimization method comprises the following steps:
step one: analyzing a service flow of a hydropower station maintenance plan, and combing factors to be considered in the establishment of the hydropower station maintenance plan, wherein the service optimization target and maintenance constraint are specifically included, and the service optimization target comprises: optimal equivalent availability factor, no water discard, and minimal overlap of time for a specific service task; the overhaul constraint conditions include: (1) Analyzing the total starting time and the total ending time of the current overhaul according to the past year and the real-time water supply condition; (2) According to the overhaul history of the unit, determining the overhaul type of the unit in the current period, and further determining the time required by overhaul; (3) Determining the total number of overhauls which can be carried out simultaneously for each type according to the conditions of the overhauling team personnel; (4) Taking holidays contained in the current overhaul period into consideration, and converting the calendar days into working days; (5) Determining the total number of the overhauls at most simultaneously according to the service requirement of the actual overhauling capacity; (6) The overhaul of important parts in the overhaul of the unit is decomposed and is arranged as sub-overhaul tasks, and all the sub-overhaul tasks are required to be completed in the period of the total overhaul task of the unit;
step two: abstracting and formally defining each service constraint condition and service target to form language in the field of hydropower station maintenance plan scheduling, and using the language to describe the optimization target and constraint condition of the hydropower station maintenance plan;
step three: according to the annual plan and the requirements of hydroelectric overhaul, determining the overhaul types to be carried out on various equipment, and an acceptable overhaul time range, and simultaneously carrying out the overhaul quantity, wherein the overhaul quantity is described by the language of the hydroelectric overhaul field;
step four: providing the defined language of the hydropower overhaul field to a language analyzer of the hydropower overhaul field, translating the language into the input of a bottom layer combination optimization algorithm by the language analyzer of the hydropower overhaul field, and calling the combination optimizer to solve the language to obtain a scheduling plan;
step five: optimizing the scheduling plan output, visually displaying the starting time and the ending time of each task in a Gantt chart mode, then manually fine-adjusting to form a hydropower station maintenance strategy, and providing the maintenance strategy for a maintenance team to execute so as to realize maintenance on hydropower station equipment.
In step two, the domain language contains the following semantic definitions:
1) The basic elements of the language are TASKs, TASK marks are uniformly used in the definition of the primitive language, and when the language is actually used, suffix-free numbers are used for marking, and the language is marked from 0; n represents the largest number;
2) Numerical values are marked by NUM in the definition of the primitive language, and are directly expressed by the numerical values in specific practical use, and specific meanings are interpreted according to the definition of the primitive language;
3) The primitive language is divided into constraint type and target type, which are used for expressing constraint condition and expected target result;
4) The target is a fixed primitive description;
5) All descriptions are used "; "number split.
The constraint primitive is defined as follows:
task- > (TASK, TASK, TASK..): expressing task dependency relations, wherein the left-side tasks of the sign primitive language are executed and completed before all the right-side tasks, and the number of the right-side tasks can be multiple;
task_interval= (NUM ): identifying the earliest starting time and the latest ending time of a task, wherein NUM is a numerical value and can only have two values;
task- (TASK, TASK, TASK..): expressing task inclusion relation, wherein the sign primitive left task includes all right tasks, namely the starting time is smaller than the starting time of all right tasks, and the ending time is larger than the ending time of all right tasks;
task < > (TASK, TASK, TASK..): expressing the mutual exclusion relation of tasks, wherein the left task of the sign primitive language must not have time intersection with all right tasks;
5. (TASK, TASK.) =num: total number of concurrent overhauls in the task set;
task_duration=num: the time required for maintenance tasks is in days.
The target primitive is defined as follows:
min_overlap: the overlapping of the time of the maintenance tasks is minimum;
in the third step, according to the annual plan and the requirement of hydroelectric overhaul, the overhaul types of various equipment to be carried out are determined, the acceptable overhaul time range is determined, and the number of overhauls is carried out simultaneously, and is described by the language of the hydroelectric overhaul field, specifically as follows:
1) And (3) determining equipment overhaul time length: determining according to the time constant of various overhauls of each equipment, wherein the corresponding constraint primitive is described as TASK_DURATION;
2) Determination of equipment overhaul starting time range: one device is described as TASK_INTERVAL according to the requirements of manufacturers and corresponding constraint primitive;
3) Total number control of concurrent overhauls: according to the condition of overhauling resources, the corresponding constraint primitive is described as (TASK ), and the TASK is a specific overhauling TASK number;
4) Dependency definition of task overhauls: some tasks must be performed after the completion of the subsequent tasks, for example, maintenance of the water guide bearing must be performed after maintenance of the water guide shoe, which is correspondingly described as: TASK- > (TASK), TASK being a specific service TASK number;
5) And (3) mutex control of maintenance tasks: according to the condition of overhaul resources, for example, the A-type overhaul TASK of a certain unit cannot be overlapped with the B-type overhaul TASK of another unit in time, the corresponding constraint primitive is described as TASK </TASK >, and TASK is a specific overhaul TASK number;
6) Definition of task inclusion relationship: for the overhaul of a large water turbine unit, the overhaul of several important parts (such as a generator and a water guide system) is disassembled, and then an integral test is added, and the overhaul task of the whole water turbine unit is the overhaul of the important parts, which is correspondingly described as: TASK- (TASK ), TASK is a specific service TASK number.
In the fourth step, the defined language analyzer in the hydroelectric overhaul field is translated into the input of the bottom layer combination optimization algorithm through language analysis, and the combination optimizer is called to solve, so that the final scheduling result is given. The core data structure is an Interval binary (end) representing the start time and the end time of a task, and based on the data structure, the translation rule of the constraint primitive is as follows:
task- > (TASK, TASK, TASK..): end time of left task < start time of all right tasks, ∀ interval_right. Start < interval_left. End;
task_interval= (num_1, NUM 2): the start time of the task > earliest time and the end time of the task < latest end time: num_1<interval.start and interval.end<NUM_2;
task- (TASK, TASK, TASK..): start time of left task < start time of all tasks on right side and end time of left task > end time of all tasks on right side, ∀ interval_right. Start > interval_left. Start and ∀ interval_right. End < interval_left. End;
4.TASK<>(TASK, TASK, TASK..): the left and right task sets have no intersection,the is_inter judges whether the two intervals are intersected, if yes, 1 is returned, otherwise, 0 is returned, and interval_left represents a left task;
5. (TASK, TASK.) =num: at any point in time, in the left task list, there are at most NUM scheduled tasks,the is_inter judges whether the two sections are intersected, if yes, 1 is returned, otherwise, 0 is returned, interval_i and interval_j represent sections of the task list in the primitive language;
task_duration=num: for each maintenance task, task end time-task start time = NUM, interval. End-interval start = NUM;
the translation rules of the target primitive are as follows:
min_overlap: the sum of the overlapping times of all tasks is minimal,wherein, the inter is to calculate the intersection size of two intervals, interval_i, interval_j represents the interval of any task;
in the fourth step, a genetic algorithm is adopted to solve the combination optimization, and an optimization solution is found according to a constraint condition formula after translation, and the method specifically comprises the following steps:
1) Chromosome coding is performed: a conversion method for converting a feasible solution of a problem in a scheduling solution space from the solution space to a search space of a genetic algorithm, wherein a binary coding method is adopted, and the starting time and the ending time of each task are taken as coding elements of the solution space;
2) Generating an initial population and related algorithm parameters: maximum evolution algebra T, population size M, crossover probability Pc, mutation probability Pm, randomly generating M individuals as an initialization population P0;
3) And (3) carrying out fitness value evaluation detection: the fitness function shows the goodness of the individual or the solution, the fitness of each individual in the group P (t) is calculated, and the fitness transformation is carried out by adopting the linear scale transformation;
4) Acquiring a genetic operator;
(1) Selecting: the selection operation selects excellent individuals from the old population to form a new population with a certain probability so as to reproduce the next generation of individuals. The selected probability of the individual is related to the fitness value, and the higher the fitness value of the individual is, the larger the selected probability is;
(2) Crossing: the crossover operation refers to randomly selecting two individuals from a population, and inheriting the excellent characteristics of a parent string to a child string through the exchange combination of two chromosomes so as to generate new excellent individuals, wherein the method adopts a uniform crossover method;
(3) Variation: in order to prevent the genetic algorithm from falling into a local optimal solution in the optimization process, individuals need to be mutated in the search process, and the method adopts single-point mutation;
5) Termination judgment conditions: and within a certain time range, taking the individual with the greatest fitness obtained in the evolution process as the best solution output, and terminating the operation.
Examples:
the target hydropower plant has 12 units, a certain year has 0,1,7 units for A-type overhauling, 5,6 units for B-type overhauling, 2,3,10 units for C-type overhauling, and 4,9,11 units for D-type overhauling. Wherein, the A type overhauls and needs 30 days, and the B type overhauls and needs 40 days, and the C type overhauls and needs 55 days, and the D type overhauls and needs 60 days, can carry out 2A type overhauls simultaneously, and 2B type overhauls, and 1C type overhauls, and 2D type overhauls at most carry out 4 maintenance tasks simultaneously. The No. 0 unit has sub-maintenance tasks of three important devices, which respectively take 10 days, 15 days and 12 days. And unit No. 2 must be serviced before unit No. 2,6, 13.
The task constraints above may be described in the following domain language:
dependency relationship:
2->(2,6,13) ；
a time range of// tasks, one year time, wherein 12,13,14 are sub-equipment maintenance tasks of the machine number 0;
0_INTERVAL=(0,355);1_INTERVAL=(0,355);2_INTERVAL=(0,355);3_INTERVAL=(0,355) ；
4_INTERVAL=(0,355);5_INTERVAL=(0,355);6_INTERVAL=(0,355);7_INTERVAL=(0,355) ；
8_INTERVAL=(0,355);9_INTERVAL=(0,355);10_INTERVAL=(0,355);11_INTERVAL=(0,355)；
12_INTERVAL=(0,355);13_INTERVAL=(0,355);14_INTERVAL=(0,355) ；
time required for the task, including sub-equipment overhaul task time;
type a tasks: 0_duty=30, 1_duty=30, 7_duty=30;
type B tasks: 5_duty=40, 6_duty=40;
type C tasks: 2_duty=55, 3_duty=55, 10_duty=55;
type D task: 4_duty=60, 9_duty=60, 11_duty=60;
subtasks of machine number 0: 12_duty=10, 13_duty=15, 14_duty=12;
subtask inclusion relationship for task number// 0;
0-(12,13,14)；
the total number of each type of overhaul;
（0,1,7）= 2；（5,6）= 2；（2,3,10）= 1；（4,9,11）= 2；
the total number of concurrent overhauls;
（0,1,7,5,6，2,3,10，4,9,11）=4。
the invention defines a maintenance scene of the hydropower industry in a business field language mode, has higher abstract property and universality, converts the interpretation of the business field language into a universal combined optimized input condition, and then invokes a universal optimizing engine to find an optimized scheme. In the face of various complex business scenes, a user can obtain the result of optimizing the scheduling by simply describing various constraint conditions and various task variables and optimizing targets.
The whole scheme integrates the knowledge of the hydropower industry, can solve the maintenance scheduling problem of most hydropower units, has better flexibility and intelligence in the industry, does not need binding and special software, and can be realized by only re-describing according to the field language and re-optimizing calculation when various constraint conditions and targets change.
Claims (5)
1. A hydropower station overhaul strategy dynamic optimization method under a multi-constraint condition is characterized by comprising the following steps of: according to the characteristics of the service scene of the hydropower station, defining a service domain language to describe the overhaul scene of the hydropower station, and then obtaining a dynamic optimization result in a language interpretation mode, wherein the dynamic optimization method comprises the following steps:
step one: analyzing a service flow of a hydropower station maintenance plan, and combing factors to be considered in the establishment of the hydropower station maintenance plan, wherein the service optimization target and maintenance constraint are specifically included, and the service optimization target comprises: optimal equivalent availability factor, no water discard, and minimal overlap of time for a specific service task; the overhaul constraint conditions include: (1) Analyzing the total starting time and the total ending time of the current overhaul according to the past year and the real-time water supply condition; (2) According to the overhaul history of the unit, determining the overhaul type of the unit in the current period, and further determining the time required by overhaul; (3) Determining the total number of overhauls which can be carried out simultaneously for each type according to the conditions of the overhauling team personnel; (4) Taking holidays contained in the current overhaul period into consideration, and converting the calendar days into working days; (5) Determining the total number of the overhauls at most simultaneously according to the service requirement of the actual overhauling capacity; (6) The overhaul of important parts in the overhaul of the unit is decomposed and is arranged as sub-overhaul tasks, and all the sub-overhaul tasks are required to be completed in the period of the total overhaul task of the unit;
step two: abstracting and formally defining each service constraint condition and service target to form language in the field of hydropower station maintenance plan scheduling, and using the language to describe the optimization target and constraint condition of the hydropower station maintenance plan;
step three: according to the annual plan and the requirements of hydroelectric overhaul, determining the overhaul types to be carried out on various equipment, and an acceptable overhaul time range, and simultaneously carrying out the overhaul quantity, wherein the overhaul quantity is described by the language of the hydroelectric overhaul field;
step four: providing the defined language of the hydropower overhaul field to a language analyzer of the hydropower overhaul field, translating the language into the input of a bottom layer combination optimization algorithm by the language analyzer of the hydropower overhaul field, and calling the combination optimizer to solve the language to obtain a scheduling plan;
step five: optimizing the scheduling plan output, visually displaying the starting time and the ending time of each task in a Gantt chart mode, then manually fine-adjusting to form a hydropower station maintenance strategy, and providing the maintenance strategy for a maintenance team to execute so as to realize maintenance on hydropower station equipment.
2. The method for dynamically optimizing hydropower station overhaul strategies under the multi-constraint condition according to claim 1, wherein the method comprises the following steps: the domain language in step two contains the following semantic definitions: the basic elements of the language are TASKs, TASK marks are uniformly used in the definition of the primitive language, and when the language is actually used, suffix-free numbers are used for marking, 0 … N is adopted, and marking is started from 0; numerical values are marked by NUM in the definition of the primitive language, and are directly expressed by the numerical values in specific practical use, and specific meanings are interpreted according to the definition of the primitive language; the primitive language is divided into constraint type and target type, which are used for expressing constraint condition and expected target result; the target is a fixed primitive description; all descriptions are used "; "number split, N denotes the largest number.
3. The method for dynamically optimizing hydropower station maintenance strategies under the condition of multiple constraints according to claim 2, wherein the method comprises the following steps: the important components include a generator and a water conduction system.
4. The method for dynamically optimizing hydropower station maintenance strategies under the condition of multiple constraints according to claim 2, wherein the method comprises the following steps: genetic algorithms are used to solve for combinatorial optimization.
5. The method for dynamically optimizing hydropower station overhaul strategies under the condition of multiple constraints according to claim 4, wherein the method comprises the following steps: the genetic algorithm is adopted to carry out combined optimization solving, and an optimization solution is found according to a constraint condition formula after translation, and the specific steps are as follows: (1) chromosome coding: a method for converting a feasible solution of a problem in a scheduling solution space from the solution space to a search space of a genetic algorithm adopts a binary coding method, and takes the starting time and the ending time of each task as coding elements of the solution space; (2) initial population generation and related algorithm parameters: maximum evolution algebra T, population size M, crossover probability Pc, mutation probability Pm, randomly generating M individuals as an initialization population P0; (3) fitness value evaluation detection: the fitness function shows the goodness of the individual or the solution, and the fitness of each individual in the group P (t) is calculated; (4) genetic operators, three genetic operators in total: (a) selecting: selecting good individuals from the old population to form a new population with a certain probability, so as to reproduce and obtain next generation individuals, wherein the probability of the selected individuals is related to the fitness value, and the higher the fitness value of the individuals is, the higher the probability of the selected individuals is; (b) crossing: the crossover operation refers to randomly selecting two individuals from a population, and inheriting the excellent characteristics of a parent string to a child string through the exchange combination of two chromosomes, so as to generate new excellent individuals; (c) variation: in order to prevent genetic algorithm from falling into local optimal solution in the optimization process, individual variation is required in the searching process; (5) termination judgment condition: and within a certain time range, taking the individual with the greatest fitness obtained in the evolution process as the optimal solution output, and terminating the operation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311311674.9A CN117057593B (en) | 2023-10-11 | 2023-10-11 | Hydropower station maintenance strategy dynamic optimization method under multiple constraint conditions |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311311674.9A CN117057593B (en) | 2023-10-11 | 2023-10-11 | Hydropower station maintenance strategy dynamic optimization method under multiple constraint conditions |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117057593A true CN117057593A (en) | 2023-11-14 |
| CN117057593B CN117057593B (en) | 2023-12-12 |
Family
ID=88659441
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311311674.9A Active CN117057593B (en) | 2023-10-11 | 2023-10-11 | Hydropower station maintenance strategy dynamic optimization method under multiple constraint conditions |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117057593B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103093084A (en) * | 2012-12-28 | 2013-05-08 | 中国电力科学研究院 | Unified modeling method of device maintenance objectives and constraints |
| US20150302332A1 (en) * | 2013-05-03 | 2015-10-22 | Gansu Electric Power Corporation Wind Power Technology Center | Maintenance schedule optimization method for electric power system including large-scale wind power |
| CN112380722A (en) * | 2020-11-25 | 2021-02-19 | 三峡大学 | Hydropower station equipment maintenance operation instruction automatic generation method based on genetic algorithm |
| WO2023115842A1 (en) * | 2021-12-24 | 2023-06-29 | 中国电力科学研究院有限公司 | Data-driven offline and online integrated simulation system and method for power distribution network |
-
2023
- 2023-10-11 CN CN202311311674.9A patent/CN117057593B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103093084A (en) * | 2012-12-28 | 2013-05-08 | 中国电力科学研究院 | Unified modeling method of device maintenance objectives and constraints |
| US20150302332A1 (en) * | 2013-05-03 | 2015-10-22 | Gansu Electric Power Corporation Wind Power Technology Center | Maintenance schedule optimization method for electric power system including large-scale wind power |
| CN112380722A (en) * | 2020-11-25 | 2021-02-19 | 三峡大学 | Hydropower station equipment maintenance operation instruction automatic generation method based on genetic algorithm |
| WO2023115842A1 (en) * | 2021-12-24 | 2023-06-29 | 中国电力科学研究院有限公司 | Data-driven offline and online integrated simulation system and method for power distribution network |
Non-Patent Citations (1)
| Title |
|---|
| 胡晨旭 等: "一体化调度计划辅助决策架构及关键技术", 电力系统自动化, no. 01 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117057593B (en) | 2023-12-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Pezzotta et al. | The product service system lean design methodology (PSSLDM) integrating product and service components along the whole PSS lifecycle | |
| Pezzotta et al. | Towards a methodology to engineer industrial product-service system–Evidence from power and automation industry | |
| CN107464025B (en) | Supply chain demand prediction and intelligent decision method based on big data | |
| Kantola et al. | Innovative products and services for sustainable societal development: Current reality, future potential and challenges | |
| Davy et al. | Dual embeddedness? Innovation capabilities, multinational subsidiaries, and solar power development in South Africa | |
| Beyaz et al. | A multi-criteria decision-making model for digital transformation in manufacturing: a case study from automotive supplier industry | |
| Aadithya et al. | Lean manufacturing in fabrication industry: literature review and framework proposal | |
| Salo et al. | Groupware support for requirements management in new product development | |
| Zohrehvandi et al. | A fuzzy project buffer management algorithm: a case study in the construction of a renewable project | |
| CN116757650B (en) | Project management and resource scheduling method based on machine learning | |
| Choudhary et al. | Knowledge discOvery And daTa minINg inteGrated (KOATING) Moderators for collaborative projects | |
| CN117057593B (en) | Hydropower station maintenance strategy dynamic optimization method under multiple constraint conditions | |
| Ławrynowicz | Integration of production planning and scheduling using an expert system and a genetic algorithm | |
| Benassi et al. | Going revolutionary: The impact of 4IR technology development on firm performance | |
| Oehmen et al. | Risk management in lean PD | |
| CN100465888C (en) | Method for automatically establishing procedure body | |
| Rodrigues et al. | Digital transformation project portfolio selection/prioritization: Literature review and future directions | |
| Boiko et al. | Towards Data Integration for Hybrid Energy System Decision-Making Processes: Challenges and Architecture | |
| Monostori et al. | Real-time, cooperative enterprises for customised mass production | |
| Shamsuddin et al. | Technological capability assessment process: a perspective | |
| Mojsilović et al. | Workforce analytics for the services economy | |
| Gupta et al. | Integrating the multi-objective elephant herding optimization based time–cost trade-off model with earned value management | |
| Bayrak et al. | Procedure Model for Industry 4.0 Realization for Operations Improvement of Manufacturing Organizations | |
| Irfan | A methodology for modelling energy use in the agriculture sector for the Pakistan integrated energy model | |
| Panizzi et al. | Refining a Software System Deployment Process Model: A Case Study |
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 |