CN114764653A - Comprehensive operation and maintenance scheduling method with minimized cost - Google Patents
Comprehensive operation and maintenance scheduling method with minimized cost Download PDFInfo
- Publication number
- CN114764653A CN114764653A CN202210330784.9A CN202210330784A CN114764653A CN 114764653 A CN114764653 A CN 114764653A CN 202210330784 A CN202210330784 A CN 202210330784A CN 114764653 A CN114764653 A CN 114764653A
- Authority
- CN
- China
- Prior art keywords
- maintenance
- unit
- vehicle
- vehicles
- evolution
- 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
- 238000012423 maintenance Methods 0.000 title claims abstract description 168
- 238000000034 method Methods 0.000 title claims abstract description 55
- 238000005259 measurement Methods 0.000 claims description 20
- 230000008569 process Effects 0.000 claims description 13
- 238000004422 calculation algorithm Methods 0.000 claims description 9
- 238000004891 communication Methods 0.000 claims description 7
- 230000005611 electricity Effects 0.000 claims description 7
- 238000005457 optimization Methods 0.000 claims description 5
- 230000003111 delayed effect Effects 0.000 claims description 4
- 230000009191 jumping Effects 0.000 claims description 4
- 230000001172 regenerating effect Effects 0.000 claims description 4
- 230000007774 longterm Effects 0.000 claims description 3
- 230000009467 reduction Effects 0.000 claims description 3
- 238000004321 preservation Methods 0.000 claims 1
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 230000002860 competitive effect Effects 0.000 description 5
- 230000008901 benefit Effects 0.000 description 4
- 238000011084 recovery Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000002068 genetic effect Effects 0.000 description 3
- 230000035772 mutation Effects 0.000 description 3
- 238000010248 power generation Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000010835 comparative analysis Methods 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 230000008439 repair process Effects 0.000 description 2
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000003780 insertion Methods 0.000 description 1
- 230000037431 insertion Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012821 model calculation Methods 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- 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
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06312—Adjustment or analysis of established resource schedule, e.g. resource or task levelling, or dynamic rescheduling
-
- 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
- G06Q10/067—Enterprise or organisation modelling
-
- 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)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Quality & Reliability (AREA)
- Development Economics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Educational Administration (AREA)
- Data Mining & Analysis (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Evolutionary Computation (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a cost minimized comprehensive operation and maintenance scheduling method, which comprises the following steps: s1, collecting data; s2, establishing a scheduling model; and S3, executing the model scheduling scheme. The invention has the beneficial effects that: and (4) taking various factors in the operation and maintenance scheduling into consideration, and making a better comprehensive operation and maintenance scheduling decision.
Description
Technical Field
The invention relates to the technical field of operation and maintenance scheduling methods, in particular to a cost-minimized comprehensive operation and maintenance scheduling method.
Background
At present, the operation and maintenance level of a wind power plant is closely related to the generated energy and generated generation income, the traditional personnel and vehicle scheduling method which relies on experience or carries out operation and maintenance arrangement randomly cannot meet the actual requirements of an operation and maintenance center and an owner, and a comprehensive operation and maintenance scheduling method which comprehensively considers the cost minimization of the future generation income of a wind generating set is urgently needed, so that the owner can obtain greater income.
In the prior art, an operation and maintenance center mainly depends on staff experience in the operation and maintenance scheduling process of a unit and selects an operation and maintenance route, and a scientific and reasonable method is lacked for guidance.
For example, an "intelligent vehicle dispatching system" disclosed in chinese patent literature has a publication number: CN112712243A, filing date thereof: in 12/24/2020, the intelligent scheduling system solution aims to improve scheduling efficiency, reduce intervention scheduling, improve vehicle utilization rate, optimize a driving route, reduce oil consumption, save cost, ensure transportation timeliness of concrete, reduce vehicle overstock of pouring tasks and risk of material breakage, and guarantee fair and reasonable departure arrangement of each driver, but has the problems that operation and maintenance vehicles and personnel scheduling methods are blindly and randomly selected when the operation and maintenance route is selected.
Disclosure of Invention
Aiming at the defects that the scheduling methods of operation and maintenance vehicles and personnel in the prior art are blind and random, the invention provides a comprehensive operation and maintenance scheduling method with minimized cost, and the comprehensive operation and maintenance scheduling method takes various factors in operation and maintenance scheduling into consideration to make a more optimal comprehensive operation and maintenance scheduling decision.
The technical scheme is that the comprehensive operation and maintenance scheduling method with minimized cost comprises the following steps:
s1, collecting data;
s2, establishing a scheduling model;
and S3, executing the model scheduling scheme.
In the scheme, data information is collected, data support is provided for building a scheduling model, the scheduling model is built, and a better comprehensive operation and maintenance scheduling decision is automatically made, so that the improved genetic algorithm is provided, the population diversity is strong, the convergence speed is high, the exploration range is wide, and the exchange evolution is deep.
Preferably, in step S1, the collected data includes operation and maintenance unit information, wind condition information, fault information, and operation and maintenance personnel status information.
Preferably, the operation and maintenance unit information includes longitude information of the unit and latitude information of the unit; the wind condition information comprises actual measurement data of wind measurement equipment of the unit, actual measurement data of a wind field wind measurement tower and long-term actual measurement data of a meteorological station, the wind measurement duration of the wind measurement equipment data of the unit is judged, if the wind measurement duration meets the specified requirement and has validity, the data is preferentially adopted, and otherwise, the data is interpolated and revised according to the wind measurement tower and the meteorological station data; the fault information comprises a serious fault, a general fault and normal operation, the unit with the serious fault can generate loss immediately, the unit with the general fault can generate loss with different degrees according to the length of operation time due to the reason of alarming, and the unit with the normal operation can generate loss due to the fact that potential faults are not detected in time; the state information of the operation and maintenance personnel comprises whether the operation and maintenance personnel are on duty or not, whether the operation and maintenance personnel are idle or not, the current task ending time and the current position, and data are obtained by traversing the operation and maintenance personnel database.
In the scheme, an operation and maintenance scheduling model with minimum comprehensive cost considering personnel cost, vehicle cost, fan shutdown loss cost and potential risk operation cost is established; various conditions which can cause the fan to generate power generation loss are fully considered, so that the dispatching target is more practical; the representativeness of the wind measuring data is considered in many aspects, so that the future wind condition can be more accurately predicted; in the dispatching process, the influence of competitive internet power price and the running state of the unit are considered, so that the comprehensive benefit is maximized; in the dispatching of the personnel, the difference of the personnel is fully considered, and the operation and maintenance cost and the operation and maintenance skill are combined, so that the method is more feasible; in the dispatching of the vehicle, the influence of the vehicle type on the operation and maintenance cost is fully considered, so that the result has higher practicability.
Preferably, in step S2, the creating of the scheduling model includes the following steps:
s21, establishing a model algorithm and initializing an algorithm function;
s22, generating an initial population;
s23, dividing into several groups;
s24, cross evolution;
s25, carrying out variant evolution;
s26, selecting elite, evolving elite and preserving elite.
In the scheme, a scheduling model is established, the initial population is a model research object, the initial population is averagely divided into a plurality of populations, model calculation and comparison are facilitated, cross evolution and mutation evolution processing are performed on the model, coordination relations among a unit, a vehicle and an engineer are facilitated, elite selection, elite evolution and elite reservation processing are performed on the model, a model scheme is convenient to determine, and benefits of the model scheme are improved.
Preferably, in step S21, the model algorithm is as follows:
min Z＝CT+CD+Cp+Ccar；
CDi＝αθf(t′i)CTi；
the constraints of the model are as follows:
in the formula, CTRepresenting the loss of the generated energy when the wind turbine generator stops; cDRepresenting the loss of delayed maintenance of the wind turbine, namely the potential risk caused by faulty operation and the loss of the future service life of the wind turbine; cpThe personnel cost in the operation and maintenance process is represented; ccarRepresenting the traffic cost in the operation and maintenance process; z represents the total cost of the operation and maintenance task; cTiRepresenting the unit time shutdown loss cost of the unit i;
representing a downtime function of the unit i; mu.siThe unit electricity price of the unit i is represented; etaiThe unit i is a reduction factor influenced by wake flow, unit utilization rate, energy loss and the like; piRepresenting the power of the unit i; viRepresenting the wind speed of the unit i; f (P)i,Vi) Representing a power function of the unit i; 1 to n represent the number of the unit needing to be maintained, and 0 represents an operation and maintenance center; cDiRepresenting the unit time risk cost of delaying maintenance of the unit i; t'iRepresenting the time for delaying maintenance of the unit i; α is a risk factor less than 1; f (t'i) Representation delay dimensionA repair time function proportional to the repair time; ckRepresents the maintenance cost per unit time of employee k;
representing the maintenance time of employee k at crew i; xikWhen the unit i is maintained by the staff k, the value is 1, otherwise, the value is 0; chRepresents a unit distance cost of the vehicle h; dijRepresenting the actual distance between the unit i and the unit j;
when the vehicle h is shown from the set i to the set j,
otherwise, the value is 0; beta is ahRepresents the fixed cost of the vehicle h; h represents the total number of vehicles available for the operation and maintenance center;
the total number of people in the vehicle is shown when the vehicle h starts from the unit i and arrives at the unit j; qhRepresents the maximum number of persons carrying the vehicle h; r isjIndicates the number of people getting on crew j; r'jIndicates the number of people getting off at unit j;
representing the time when the vehicle h arrives at the set i;
representing the time required by the staff k to maintain the unit i;
representing the time required for the vehicle h to travel from bank i to bank j.
In the scheme, on the basis of data, an operation and maintenance scheduling model with minimum comprehensive cost considering personnel cost, vehicle cost, fan shutdown loss cost and potential risk operation cost is established; various conditions which can cause the fan to generate power generation loss are fully considered, so that the dispatching target is more practical; the representativeness of the wind measuring data is considered in many aspects, so that the future wind condition can be more accurately predicted; in the dispatching process, the influence of competitive on-line electricity price and the running state of the unit are considered, so that the comprehensive benefit is maximized; in the dispatching of the personnel, the difference of the personnel is fully considered, and the operation and maintenance cost and the operation and maintenance skill are combined, so that the method is more feasible; in the dispatching of the vehicle, the influence of the vehicle type on the operation and maintenance cost is fully considered, so that the result is more practical; the improved genetic algorithm has strong population diversity, high convergence rate, wide exploration range and deep exchange evolution, and can effectively solve the problems.
Preferably, in steps S22-S23, initializing the population and dividing it into several groups, including the following steps:
s221: determining the size G, the maximum iteration number MAX and the number NUM _ z of the population;
s222: g/2 individuals are generated in a random mode;
s223: g/2 individuals are generated in an optimization mode;
s224: the individuals generated in step S222 and step S223 are fully mixed to form a population with the scale G, and the G individuals are randomly assigned to NUM _ z populations, wherein the number of individuals per population is NUM _ G.
In the scheme, the population is initialized and averagely divided into a plurality of ethnic groups, half individuals are generated respectively in a random mode and an optimization mode, the problems of data unicity and contingency are solved from a data source, the individuals are fully mixed, the data aggregation condition is avoided, and the model experiment result is more accurate.
Preferably, the method for randomly generating individuals in step S222 is as follows: randomly selecting a vehicle from a vehicle library, randomly selecting a fan from a fan library, randomly selecting an engineer meeting the operation and maintenance requirements of the fan from an operation and maintenance engineer library according to the operation and maintenance tasks of the fan, distributing the engineer to the vehicle, detecting whether the vehicle is overloaded or not, if the vehicle is not overloaded, the fan and the corresponding engineer are served by the vehicle, otherwise, the fan and the corresponding engineer are randomly distributed to other vehicles for serving; the method for optimizing and generating the individuals in the step S223 comprises the following steps: randomly selecting a vehicle, randomly selecting a fan from a fan library, randomly selecting an engineer meeting fan operation and maintenance requirements from an operation and maintenance engineer library according to the operation and maintenance task of the fan to distribute to the vehicle, detecting whether the vehicle is overloaded, if the vehicle is not overloaded, serving the fan and a corresponding engineer by the vehicle, selecting the fan with the smallest angle with the fan by taking an operation and maintenance center as a circle center, randomly arranging the corresponding operation and maintenance engineer to carry out operation and maintenance, distributing to the vehicle, judging whether the vehicle is overloaded until the vehicle is fully loaded, and being incapable of serving more fans; if the vehicle is overloaded, the fans and corresponding engineers are randomly assigned to other available vehicles.
In the scheme, the random mode and the optimization mode have obvious difference, so that the problem of high individual similarity selected by the two modes is further avoided, and the model experiment result is more accurate.
Preferably, the cross-evolution in step S24 performs a random evolution or a preferred evolution based on the range of generated random numbers, the random evolution comprising the steps of:
s241, selecting an individual Pb with the maximum fitness in the group;
s242, randomly selecting two individuals except Pb, and respectively marking the individuals as A and D;
s243, randomly selecting service chains of two vehicles in the individuals A and D, respectively recording the service chains as a and D, contrastively analyzing the operation units of the a and the D, placing the operation units shared by the two vehicles in Tab, storing the unit unique to a in Ta, and storing the unit unique to D in Td;
s244, interchanging the units served by the a and the d;
s245, traversing the service chains of other vehicles in the individual A, and deleting the same set in A and Td; traversing and checking service chains of other vehicles in the individual D, and deleting the same set in the D and the Ta;
s246, randomly selecting a unit from Ta, transferring the unit and the corresponding engineer to other random vehicles in the individual A for service, and if the vehicles are overloaded or the engineers conflict, replacing other vehicles until all the units in Ta are distributed to be served by other vehicles of the individual A;
s247, randomly selecting one unit from the Td, transferring the unit and the corresponding engineer to other random vehicles in the D individuals for service, and replacing other vehicles if the vehicles are overloaded or the engineers conflict, until all the units in the Td are distributed to be served by other vehicles of the D individuals;
s248, calculating fitness for the evolved individuals A 'and D', respectively, if f (A ') is less than or equal to f (A), replacing A with A', otherwise, keeping A unchanged, and if f (D ') is less than or equal to f (D), replacing D with D', otherwise, keeping D unchanged;
s249, if neither A nor D is replaced by updating, executing step S244 to step S248, if A and D have updating situation, executing step S25, otherwise, executing step S243 to step S248 in a circulating manner until the maximum cross evolution times is met, jumping out of the circulating manner, at this time, regenerating two individuals according to the method of step S222 and step S223, replacing A and D respectively, and then executing step S25;
in the scheme, the individuals are subjected to random evolution or optimized evolution according to the range of the generated random numbers, so that the evolution directions of the individuals are inconsistent, the difference is further improved, the individuals are updated and replaced according to the individual fitness, and the model systematicness and accuracy are improved.
Preferably, the evolutionary variation in step S25 includes the following steps:
s251: randomly selecting an individual in the population, named as E, and carrying out random variation evolution;
s252: making a random variation evolution strategy, wherein the evolution strategy is as follows:
firstly, interchanging operation and maintenance units among vehicles;
secondly, operation and maintenance units between vehicles are increased;
inserting the path in the vehicle;
exchanging paths in the vehicle;
exchanging the operation sequence of an engineer;
exchanging the operation units by engineers;
s253: sequentially executing evolution strategies (c) - (E) on the individual E to form a new individual E ', if f (E ') is less than or equal to f (E), replacing E with E ', otherwise, keeping E unchanged, and continuing to execute the step S254;
s254: and (4) carrying out evolution strategies of (i) - (ii) and (v) - (iii) on the individual E in sequence to form a new individual E ', if f (E ') is less than or equal to f (E), replacing E with E ', and otherwise, keeping E unchanged.
In the scheme, the evolution strategy processing is carried out on the individual, the coordination relationship among the unit, the vehicle and the engineer is further adjusted,
the model result is more accurate.
Preferably, the selecting of elite, the evolving of elite and the preserving of elite in step S26 comprises the following steps:
s261: calculating the fitness of individuals in the ethnic groups, and selecting the individual with the highest fitness in each ethnic group to form an elite group;
s262: carrying out evolutionary cross evolution or variant evolution on the individual Pg with the maximum fitness in the elite population;
s263: the optimal Pg 'and the worst Pw after communication, if f (Pg') is less than or equal to f (Pg), the Pg 'is replaced by the Pg', otherwise, the Pw is replaced by the Pg 'with the Pg' kept unchanged;
s264: performing secondary communication and evolution on the elite population;
s265: mixing and rearranging all individuals;
s266: finishing one iteration evolution, wherein the iteration number max is max + 1;
s267: the iteration times reach the maximum iteration times MAX;
s268: outputting the individual Pg with the maximum fitness among all individuals in the population, and outputting the corresponding fitness f (Pg);
s269: and forming a specific vehicle and personnel operation and maintenance scheduling scheme according to the vehicle service chain of the individual Pg.
In the scheme, the elite selection, the elite evolution and the elite reservation treatment are carried out on the individuals, the individuals with the highest fitness are selected to form the elite population, the elite population is subjected to the evolution treatment, the mixture and the rearrangement are carried out, the individuals with the highest fitness are selected in an iterative manner, and the accuracy of the model scheme is improved.
The beneficial effects of the invention are: and (4) taking various factors in the operation and maintenance scheduling into consideration, and making a better comprehensive operation and maintenance scheduling decision.
Drawings
Fig. 1 is a schematic flow chart of a cost-minimized integrated operation and maintenance scheduling method according to the present invention.
FIG. 2 is a schematic diagram of a scheduling model flow of the integrated operation and maintenance scheduling method with minimized cost according to the present invention.
FIG. 3 is a schematic diagram of cross-evolution selection of a cost-minimized integrated operation and maintenance scheduling method according to the present invention.
Fig. 4 is a schematic diagram of a scheme of a cost-minimized integrated operation and maintenance scheduling method according to the present invention.
Detailed Description
The technical scheme of the invention is further specifically described by the following embodiments and the accompanying drawings.
The embodiment is as follows: as shown in fig. 1, fig. 2, fig. 3 and fig. 4, a cost-minimized integrated operation and maintenance scheduling method includes the following steps:
step 1: collecting information of the unit needing to be operated and maintained, including position, wind speed, fault and the like, through an SCADA system;
the position comprises longitude, latitude and other information of the unit.
Wind speeds include the following three: measured data of wind measuring equipment carried by the unit; actual measurement data of the anemometer tower in the wind field; long-term actual measurement data of a participating meteorological station near a wind field.
The faults include the following three types: the faults are serious, and the machine set is shut down; when the fault is general, the unit generates alarm and needs to be repaired, but is not stopped; the normal operation of the unit needs regular inspection.
The potential loss generated by different faults is different, and the loss can be generated when the machine is stopped immediately; the unit is alarmed but not stopped, and loss in different degrees is generated according to the length of the operation time due to the alarm; the normal inspection unit can generate loss caused by potential faults discovered by not inspecting in time;
step 2: predicting the wind speed of the position of the unit in a future period of time according to the collected wind condition information, and the specific steps are as follows;
step 2.1: firstly, judging whether the wind measuring time of the unit wind measuring equipment data meets the specified requirements or not and whether the unit wind measuring equipment data has validity or not, and if the unit wind measuring equipment data has validity, preferentially adopting the data; otherwise, the data needs to be interpolated and revised according to the data of the anemometer tower and the meteorological station;
step 2.2: importing the collected effective data into a wind speed prediction module, and analyzing and predicting the wind speed condition in a future period of time;
and 3, step 3: according to the collected fault information, the potential maintenance time required by each fan and the inventory condition of relevant required spare parts are judged;
the method for judging the maintenance time of the fan comprises two methods: judging the time consumed for repairing a certain fault according to the experience of a field operation and maintenance engineer; and judging by means of a fault database of the wind power plant.
And the database stores the faults of the conventional fan and the corresponding fault recovery time, and the system provides a predicted value of the fault recovery time through the comparative analysis of the faults.
Determining the fault time is related to the fault type, if the fault has obvious reference in a fault library, the prediction time of the fault library is taken as the standard, otherwise, the experience of a field operation and maintenance engineer is taken as the standard;
the stock condition of the spare parts can also affect the recovery of the failure, and if the spare parts are lost and need to be purchased again, the recovery time of the failure can be obviously increased.
And 4, step 4: traversing the operation and maintenance personnel database to obtain the state of each operation and maintenance personnel;
the operation and maintenance personnel state comprises: whether the task is on duty or not, whether the task is idle or not, the current task ending time, the current position and the like;
and 5: the scheduling module calculates an operation and maintenance scheduling scheme with the minimum cost according to the information such as the states of operation and maintenance personnel, information of units required to be maintained, spare part information and the like, and the main steps are as follows:
step 5.1, the minimum operation and maintenance total cost is taken as a target, namely fitness, and an objective function is established as follows:
min Z＝CT+CD+Cp+Ccar ⑴
in the above formula, Z represents the total cost of the operation and maintenance task, CTIndicating loss of generated energy when the wind turbine is shut down, CDRepresenting the loss of delayed maintenance of the wind turbine, i.e. the potential risk of faulty operation and the loss of future life of the turbine, CpRepresenting the cost of personnel in the operation and maintenance process, CcarAnd the traffic cost in the operation and maintenance process is shown.
In the first technical scheme, the first step is,
CDi＝αθf(t′i)CTi ⑷
the constraints of the model are as follows:
in the first embodiment, Z represents a total cost of the operation and maintenance task; cTiRepresenting the unit time shutdown loss cost of the unit i;
representing a downtime function of the unit i; mu.siThe unit electricity price of the unit i is represented; etaiThe unit i is a reduction factor influenced by wake flow, unit utilization rate, energy loss and the like; p isiRepresenting the power of the unit i; viRepresenting the wind speed of the unit i; f (P)i,Vi) Representing a power function of the unit i; 1 to n represent the number of the unit needing maintenance, and 0 represents the operation and maintenance center; cDiRepresenting the unit time risk cost of delaying maintenance of the unit i; t'iRepresenting the time of postponing maintenance of the unit i; α is a risk factor less than 1; f (t'i) A function of time representing a delay in maintenance, proportional to the maintenance time; ckRepresents the maintenance cost per unit time of employee k;
representing the maintenance time of the employee k at the unit i; xikWhen the unit i is maintained by the staff k, the value is 1, otherwise, the value is 0; chRepresents the cost per unit distance of the vehicle h; dijRepresenting the actual distance between the unit i and the unit j;
when the vehicle h is shown from the set i to the set j,
otherwise, the value is 0; beta is ahRepresents the fixed cost of the vehicle h; h represents the total number of vehicles available for the operation and maintenance center;
the total number of people in the vehicle is shown when the vehicle h starts from the unit i and arrives at the unit j; qhRepresents the maximum number of persons carrying the vehicle h; r isjIndicates the number of people getting on crew j; r'jIndicates the number of people getting off at unit j;
representing the time when the vehicle h arrives at the set i;
the time required by the staff k to maintain the unit i is represented;
representing the time required for the vehicle h to travel from bank i to bank j.
Wherein the formula quietness indicates that the number of used vehicles must not exceed the total number of available vehicles; the formula is shown in a simple manner and the formula is shown in a self-adaptive manner, so that the number of people carried by the vehicle from any set of units does not exceed the maximum number of people carried by the vehicle; the formula is that the personnel starting from the operation and maintenance center finally return to the operation and maintenance center; the formula shows that for the units i and j with the arrival sequence, the maintenance starting time of the unit j is after the maintenance time of the unit i is finished; formula units represent that each unit is served by one vehicle only once a day; the formula reference shows that the vehicle finally returns to the operation and maintenance center after departing from the operation and maintenance center.
The loss cost of the generated energy of the wind turbine generator is influenced by the generated power, the competitive electricity price and the shutdown time of the fan, and the larger the generated power is, the higher the competitive electricity price is, the longer the shutdown time is, the larger the loss cost of the generated energy is, and the smaller the loss cost is otherwise.
The wind turbine generator is stopped mainly under the following conditions: normal maintenance and manual shutdown; when a fault occurs, the machine is forced to stop; maintenance is carried out, and the machine is normally stopped; in operation and maintenance, extreme weather, such as strong wind and thunderstorm, causes delayed shutdown; in severe weather, the wind speed is greater than the maximum wind speed, and the machine is stopped in a risk avoiding mode; and upgrading the unit and stopping the unit in a planned way.
The labor cost can be influenced by the level of operation and maintenance personnel and the maintenance time, the higher the level of the operation and maintenance personnel is, the longer the maintenance time is, the larger the consumed labor cost is, and the smaller the maintenance time is.
The traffic cost is influenced by the unit distance cost and the distance of the vehicle, and the larger the unit distance cost is, the longer the distance is, the larger the traffic cost is, and the smaller the traffic cost is otherwise.
And step 5.2: initializing the population, and determining the size G, the maximum iteration number MAX and the number NUM _ z of the population.
Step 5.3: g/2 individuals are generated in a random mode, and the specific process is as follows:
step 5.3.1: randomly selecting a vehicle from a vehicle library, randomly selecting a fan from a fan library, randomly selecting an engineer meeting fan operation and maintenance requirements from an operation and maintenance engineer library according to the operation and maintenance task of the fan, allocating the engineer to the vehicle, detecting whether the vehicle is overloaded, if not, allocating the fan and the corresponding engineer to the vehicle for service, otherwise, randomly allocating the fan and the corresponding engineer to other vehicles for service, judging whether the vehicle is overloaded, and so on, and allocating the fan and the corresponding engineer to different vehicles for service in sequence until all the fans have corresponding vehicles and engineers for service.
Step 5.3.2: step 5.3.1 is executed in a circulating way for G/2 times to generate G/2 individuals;
step 5.4: g/2 individuals are generated in an optimization mode, and the specific process is as follows:
step 5.4.1: randomly selecting a vehicle, randomly selecting a fan from a fan library, randomly selecting an engineer meeting the operation and maintenance requirements of the fan from an operation and maintenance engineer library according to the operation and maintenance task of the fan, allocating the engineer to the vehicle, detecting whether the vehicle is overloaded or not, if the vehicle is not overloaded, serving the fan and the corresponding engineer by the vehicle, then selecting the fan with the smallest angle with the fan by taking an operation and maintenance center as a circle center, randomly arranging the corresponding operation and maintenance engineer to perform operation and maintenance, allocating the operator to the vehicle, judging whether the vehicle is overloaded or not, and so on until the vehicle is fully loaded and cannot serve more fans any more; if the vehicle is overloaded, the fans and corresponding engineers are randomly distributed to other available vehicles and are circularly carried out until all the fans have services of the corresponding vehicles and the corresponding engineers;
step 5.4.2: step 5.4.1 is executed circularly for G/2 times to generate G/2 individuals;
step 5.5: fully mixing G/2 individuals generated in the steps 5.3 and 5.4 to form a population with the scale of G;
step 5.6: calculating the fitness of G individuals according to the formula, wherein the individual with the highest fitness, namely the individual with the lowest total cost, is named Pg, and then distributing the G individuals to NUM _ z groups randomly, wherein the number of the individuals of each group is NUM _ G; g is NUM _ z · NUM _ G.
Step 5.7: and (3) carrying out selective cross evolution and variant evolution in each group in turn, wherein the specific processes are as follows:
step 5.7.1: the individual with the highest fitness in the population is named as Pb;
step 5.7.2: generating a random number, if the value is larger than 0.5, performing step 5.7.3 to perform random evolution, otherwise, performing step 5.7.4 to perform preferential evolution;
step 5.7.3: carrying out random evolution, and specifically comprising the following steps:
step 5.7.3.1: randomly selecting two individuals except Pb, and respectively marking the individuals as A and D;
step 5.7.3.2: randomly selecting service chains of two vehicles in the individuals A and D, respectively recording the service chains as a and D, carrying out comparative analysis on the operation units of the a and the D, then placing the operation units shared by the two vehicles in Tab, storing the unit unique to the a in Ta, and storing the unit unique to the D in Td;
step 5.7.3.3: exchanging the machine sets served by the a and the d;
step 5.7.3.4: traversing the service chain of other vehicles in the individual A, and deleting the service chain of the other vehicles in the individual A, wherein the service chain is the same as the service chain of the machine group in the Td;
step 5.7.3.5: traversing and checking the service chain of other vehicles in the individual D, and deleting the service chain which is the same as the service chain in the Ta;
step 5.7.3.6: randomly selecting a unit from Ta, transferring the unit and the corresponding engineer to other random vehicles in the individual A for service, judging whether the vehicles are overloaded or not and whether the engineers conflict or not, if so, replacing other vehicles for service, judging whether the vehicles are overloaded or not again and whether the engineers conflict or not, and repeating the operation until all the units in Ta are distributed to be served by other vehicles of the individual A;
step 5.7.3.7: randomly selecting one unit from the Td, transferring the unit and the corresponding engineer to other random vehicles in the D individual for service, judging whether the vehicles are overloaded or not and whether the engineers conflict or not, if so, replacing other vehicles for service, judging whether the vehicles are overloaded or not and whether the engineers conflict or not again, and repeating the operation until all the units in the Td are distributed to be served by other vehicles of the D individual;
step 5.7.3.8: respectively naming the evolved individuals as A 'and D', respectively calculating the fitness of the evolved individuals according to a formula, if f (A ') is less than or equal to f (A), replacing A with A', otherwise, keeping A unchanged, and if f (D ') is less than or equal to f (D), replacing D with D', otherwise, keeping D unchanged;
step 5.7.3.9: if neither A nor D is updated and replaced, executing steps 5.7.3.2 to 5.7.3.8 again, if A and D have updating conditions, executing step 5.7.5, otherwise, executing steps 5.7.3.2 to 5.7.3.8 in a loop mode until the maximum cross evolution times N _ S is met, jumping out of the loop mode, at the moment, regenerating two individuals according to the methods of step 5.3 and step 5.4, replacing A and D respectively, and then executing step 5.7.5;
step 5.7.4: carrying out preferred evolution, and specifically comprising the following steps:
step 5.7.4.1: randomly selecting an individual named R;
step 5.7.4.2: randomly selecting a service chain of one vehicle in an individual R, named as R, randomly selecting a service chain of one vehicle in Pb, named as b, comparing and analyzing operation and maintenance units of R and b, then placing the operation and maintenance units common to the two vehicles in Trb, storing the unit unique to R in Tr, and storing the unit unique to b in Tb;
step 5.7.4.3: interchanging the units served by r and b;
step 5.7.4.4: traversing and checking the service chain of other vehicles in the individual R, and deleting the service chain which is the same as the service chain in the Tb;
step 5.7.4.5: traversing and checking the service chain of other vehicles in the individual Pb, and deleting the service chain of the other vehicles from the individual Pb, wherein the service chain is the same as the service chain of the unit in the Tr;
step 5.7.4.6: randomly selecting a unit from the Tr, transferring the unit and an engineer corresponding to the unit to other random vehicles in the R individuals for service, judging whether the vehicles are overloaded or conflict with each other, if so, replacing other vehicles for service, judging whether the vehicles are overloaded or conflict with each other again, and repeating the steps until all the units in the Tr are distributed to be served by other vehicles in the R individuals;
step 5.7.4.7: randomly selecting a unit from Tb, transferring the unit and corresponding engineers to other random vehicles in the individual Pb for service, judging whether the vehicles are overloaded or not and whether the engineers are in conflict or not, if so, replacing other vehicles for service, judging whether the vehicles are overloaded or not again and whether the engineers are in conflict or not, and repeating the operation until all the units in Tb are distributed to be served by other vehicles in the individual Pb;
step 5.7.4.8: respectively naming the evolved individuals as R 'and Pb', respectively calculating the fitness of the evolved individuals according to a formula, if f (R ') is less than or equal to f (R), replacing R with R', otherwise, keeping R unchanged, and if f (Pb ') is less than or equal to f (Pb), replacing Pb with Pb', otherwise, keeping Pb unchanged;
step 5.7.4.9: if R and Pb are not updated and replaced, executing steps 5.7.4.2 to 5.7.4.8 again, if R and Pb have updating conditions, executing step 5.7.5, otherwise, executing steps 5.7.4.2 to 5.7.4.8 in a circulating mode until the maximum cross evolution frequency N _ S is met, jumping out of the circulating mode, at the moment, according to the method of step 5.4, regenerating an individual, replacing R, and then executing step 5.7.5;
step 5.7.5: carrying out mutation evolution operation, which comprises the following steps:
step 5.7.5.1: randomly selecting an individual in the population, named as E, and carrying out random variation evolution;
step 5.7.5.2: the random variation evolution strategy has the following:
1. interchanging operation and maintenance units among vehicles: randomly selecting two vehicles, and then respectively selecting a section of route from each operation and maintenance unit for interchange;
2. the inter-vehicle operation and maintenance unit is increased: randomly selecting a unit, and inserting the unit and the corresponding engineer into the operation and maintenance route of another vehicle;
3. vehicle inner path insertion: randomly selecting a set, and inserting the set and the corresponding engineer into other positions of the vehicle path;
4. interchange of paths in the vehicle: randomly selecting two sets of units, and interchanging the positions of the two sets of units;
5. exchanging the operation sequence of an engineer: randomly selecting an engineer who carries out multiple operation and maintenance operations, and interchanging the sequence of operating the unit;
6. and (3) interchanging the operation units by an engineer: randomly selecting two engineers, and exchanging the operation units of the engineers;
step 5.7.5.3: carrying out evolution strategies 3-6 on the individual E in sequence to form a new individual E ', if f (E ') is less than or equal to f (E), replacing E with E ', and if not, keeping E unchanged, and continuing to carry out the step 5.7.5.4;
step 5.7.5.4: carrying out evolution strategies 1-2 and 5-6 on the individual E in sequence to form a new individual E ', if f (E ') is less than or equal to f (E), replacing E with E ', and otherwise, keeping E unchanged;
step 5.7.6: performing a preferred mutation evolution operation, replacing the random individual E in the step 5.7.5 with the optimal individual Pb in the ethnic group, and then performing the step 5.7.5 again;
step 5.8: sequentially executing the steps 5.7.1 to 5.7.6 for N _ z times, and performing N _ z evolutions in the population;
step 5.9: calculating the fitness of individuals in NUM _ z ethnic groups, and selecting the individual with the highest fitness in each ethnic group to form an elite group;
step 5.10: the individuals with the maximum fitness in the elite population are named Pg, and evolution communication is carried out according to the mode of the step 5.7;
step 5.11: the optimal individual after the communication is named as Pg ', the worst individual is named as Pw, if f (Pg ') ≦ f (Pg), Pg ' is replaced by Pg ', otherwise, Pg is kept unchanged, and Pw is replaced by Pg ';
step 5.12: sequentially executing the steps 5.10 and 5.11, and carrying out N _ j times of communication and evolution on the elite population;
step 5.13: mixing and rearranging all individuals;
step 5.14: finishing one iteration evolution, wherein the iteration number max is max + 1;
step 5.15: judging whether a termination condition is met, wherein the iteration number reaches a maximum iteration number MAX, if so, executing the step 5.16, otherwise, returning to execute the step 5.6;
step 5.16: outputting the individual Pg with the maximum fitness among all individuals in the population and the corresponding fitness f (Pg);
step 5.17: forming a specific vehicle and personnel operation and maintenance scheduling scheme according to the vehicle service chain of the individual Pg;
step 6: according to the operation and maintenance scheduling scheme, the operation and maintenance tasks of each unit are distributed to specific operation and maintenance personnel;
and 7: each operation and maintenance worker starts operation and maintenance work on the fan according to task arrangement;
and step 8: and after the working personnel finish a task, updating the state of the unit and the state of the working personnel, retrieving a task arrangement list of the working personnel, if the working personnel are not empty, continuing to perform subsequent operation and maintenance tasks, otherwise, returning to the operation and maintenance center to wait for task arrangement.
Example (c): a certain wind power operation and maintenance center has a set of units to be operated and maintained, information such as positions, operation states and fault reasons of the units is shown in the following tables 1, 2 and 3, at present, the operation and maintenance center has 7 idle operation and maintenance engineers, information such as capabilities and positions of the operators is shown in the table 4, the operation and maintenance center has 5 vehicles for use, information of each vehicle is shown in the table 5, a fan operation potential risk factor is 0.05, the average vehicle running speed is 60KM/h, and a reasonable operation and maintenance scheme is arranged, so that the total maintenance cost is minimum.
Table 1 operation and maintenance unit information table
TABLE 2 wind speed (m/s) -power (KW) curve chart for operation and maintenance unit
Table 3 wind speed forecasting meter for operation and maintenance unit
TABLE 4 Engineers information Table
Table 5 available vehicle information table.
According to the method of the present application, a population size G is determined to be 100, a maximum iteration number MAX is determined to be 100, a population number NUM _ z is determined to be 5, a population evolution number N _ z is determined to be 5, and an elite team evolution number N _ j is determined to be 5, in this example, with a goal of minimizing a total operation and maintenance cost, after the cost minimization comprehensive operation and maintenance scheduling method of the present invention is executed, an operation and maintenance scheduling scheme shown in table 6 is obtained, and a specific form path is shown in fig. 4.
Table 6 operation and maintenance scheduling scheme table.
An operation and maintenance scheduling model with minimum comprehensive cost considering personnel cost, vehicle cost, fan shutdown loss cost and potential risk operation cost is established; various conditions which can cause the fan to generate power generation loss are fully considered, so that the dispatching target is more practical; the representativeness of the wind measuring data is considered in many aspects, so that the future wind condition can be more accurately predicted; in the dispatching process, the influence of competitive on-line electricity price and the running state of the unit are considered, so that the comprehensive benefit is maximized; in the dispatching of the personnel, the difference of the personnel is fully considered, and the operation and maintenance cost and the operation and maintenance skill are combined, so that the method is more feasible; in the dispatching of the vehicles, the influence of the vehicle types on the operation and maintenance cost is fully considered, so that the result is more practical; the improved genetic algorithm has strong population diversity, high convergence rate, wide exploration range and deep exchange evolution, and can effectively solve the problems.
Claims (10)
1. A cost-minimized comprehensive operation and maintenance scheduling method is characterized by comprising the following steps:
s1, collecting data;
s2, establishing a scheduling model;
and S3, executing the model scheduling scheme.
2. The integrated operation and maintenance scheduling method with minimized cost according to claim 1, wherein the collected data in step S1 includes operation and maintenance crew information, wind condition information, fault information and operation and maintenance personnel status information.
3. The integrated operation and maintenance scheduling method with minimized cost according to claim 2, wherein the operation and maintenance unit information comprises longitude information of the unit, latitude information of the unit; the wind condition information comprises actual measurement data of wind measurement equipment of the unit, actual measurement data of a wind field wind measurement tower and long-term actual measurement data of a meteorological station, the wind measurement duration of the wind measurement equipment data of the unit is judged, if the wind measurement duration meets the specified requirement and has validity, the data is preferentially adopted, and otherwise, the data is interpolated and revised according to the wind measurement tower and the meteorological station data; the fault information comprises a serious fault, a general fault and normal operation, the unit with the serious fault can generate loss immediately, the unit with the general fault can generate loss with different degrees according to the length of operation time due to the reason of alarming, and the unit with the normal operation can generate loss due to the fact that potential faults are not detected in time; the state information of the operation and maintenance personnel comprises whether the operation and maintenance personnel are on duty or not, whether the operation and maintenance personnel are idle or not, the current task ending time and the current position, and data are obtained by traversing the operation and maintenance personnel database.
4. The integrated operation and maintenance scheduling method with minimized cost according to claim 1, wherein the step S2 of establishing the scheduling model comprises the steps of:
s21, establishing a model algorithm and initializing an algorithm function;
s22, generating an initial population;
s23, dividing into several groups;
s24, cross evolution;
s25, carrying out variant evolution;
s26, selecting elite, evolving elite and preserving elite.
5. The integrated operation and maintenance scheduling method with minimized cost according to claim 4, wherein in step S21, the model algorithm is as follows:
min Z＝CT+CD+Cp+Ccar；
CDi＝αθf(t′i)CTi；
the constraints of the model are as follows:
in the formula, CTRepresenting the loss of the generated energy when the wind turbine generator stops; cDRepresenting the loss of delayed maintenance of the wind turbine, namely the potential risk caused by faulty operation and the loss of the future service life of the wind turbine; cpRepresenting the personnel cost in the operation and maintenance process; ccarRepresenting the traffic cost in the operation and maintenance process; z represents the total cost of the operation and maintenance task; cTiRepresenting the unit time shutdown loss cost of the unit i;
representing a downtime function of the unit i; mu.siRepresenting unit electricity price of the unit i; etaiThe unit i is a reduction factor influenced by wake flow, unit utilization rate, energy loss and the like; p isiRepresenting the power of the unit i; viRepresenting the wind speed of the unit i; f (P)i,Vi) Representing a power function of the unit i; 1 to n represent the number of the unit needing to be maintained, and 0 represents an operation and maintenance center; cDiRepresenting the unit time risk cost of delaying maintenance of the unit i; t'iRepresenting the time for delaying maintenance of the unit i; α is a risk factor less than 1; f (t'i) A function of time representing a delay in maintenance, proportional to the maintenance time; ckRepresents the maintenance cost per unit time of employee k;
representing the maintenance time of the employee k at the unit i; xikWhen the unit i is maintained by the staff k, the value is 1, otherwise, the value is 0; chRepresents the cost per unit distance of the vehicle h; d is a radical ofijRepresenting the actual distance between the unit i and the unit j;
when the vehicle h is shown from the set i to the set j,
otherwise, the value is 0; beta is ahRepresents a fixed cost for the vehicle h; h represents the total number of vehicles available for the operation and maintenance center;
the total number of people in the vehicle is shown when the vehicle h starts from the unit i and arrives at the unit j; qhRepresents the maximum number of persons carrying the vehicle h; r isjIndicates the number of people getting on crew j; r'jIndicates the number of people getting off at unit j;
representing the time when the vehicle h arrives at the set i;
representing the time required by the staff k to maintain the unit i;
representing the time required for the vehicle h to travel from bank i to bank j.
6. The method for integrated operation and maintenance scheduling with minimized cost as claimed in claim 4, wherein the step S22-S23 for initializing the population and averagely dividing into several populations comprises the following steps:
s221: determining the size G, the maximum iteration number MAX and the number NUM _ z of the population;
s222: g/2 individuals are generated in a random mode;
s223: g/2 individuals are generated in an optimization mode;
s224: the individuals generated in step S222 and step S223 are fully mixed to form a population with the scale G, and the G individuals are randomly assigned to NUM _ z populations, wherein the number of individuals per population is NUM _ G.
7. The integrated operation and maintenance scheduling method with minimized cost according to claim 6, wherein the step S222 of randomly generating the individuals comprises: randomly selecting a vehicle from a vehicle library, randomly selecting a fan from a fan library, randomly selecting an engineer meeting the operation and maintenance requirements of the fan from an operation and maintenance engineer library according to the operation and maintenance tasks of the fan, distributing the engineer to the vehicle, detecting whether the vehicle is overloaded or not, if the vehicle is not overloaded, the fan and the corresponding engineer are served by the vehicle, otherwise, the fan and the corresponding engineer are randomly distributed to other vehicles for serving; the method for optimizing and generating the individuals in the step S223 comprises the following steps: randomly selecting a vehicle, randomly selecting a fan from a fan library, randomly selecting an engineer meeting fan operation and maintenance requirements from an operation and maintenance engineer library according to the operation and maintenance task of the fan to distribute to the vehicle, detecting whether the vehicle is overloaded, if the vehicle is not overloaded, serving the fan and a corresponding engineer by the vehicle, selecting the fan with the smallest angle with the fan by taking an operation and maintenance center as a circle center, randomly arranging the corresponding operation and maintenance engineer to carry out operation and maintenance, distributing to the vehicle, judging whether the vehicle is overloaded until the vehicle is fully loaded, and being incapable of serving more fans; if the vehicle is overloaded, the fans and corresponding engineers are randomly assigned to other available vehicles.
8. The integrated operation and maintenance scheduling method with minimized cost according to claim 4, wherein the cross evolution in step S24 is a random evolution or a preferred evolution according to the generated random number range, and the random evolution comprises the following steps:
s241, selecting an individual Pb with the maximum fitness in the group;
s242, randomly selecting two individuals except Pb, and respectively marking the individuals as A and D;
s243, randomly selecting service chains of two vehicles in the individuals A and D, respectively recording the service chains as a and D, contrastively analyzing the operation units of the a and the D, placing the operation units shared by the two vehicles in Tab, storing the unit unique to a in Ta, and storing the unit unique to D in Td;
s244, interchanging the units served by a and d;
s245, traversing the service chains of other vehicles in the individual A, and deleting the same set in A and Td; traversing and checking service chains of other vehicles in the individual D, and deleting the same set in the D and the Ta;
s246, randomly selecting a unit from Ta, transferring the unit and the corresponding engineer to other random vehicles in the individual A for service, and if the vehicles are overloaded or the engineers conflict, replacing other vehicles until all the units in Ta are distributed to be served by other vehicles of the individual A;
s247, randomly selecting one unit from the Td, transferring the unit and the corresponding engineer to other random vehicles in the D individuals for service, and replacing other vehicles if the vehicles are overloaded or the engineers conflict, until all the units in the Td are distributed to be served by other vehicles of the D individuals;
s248, calculating fitness for the evolved individuals A 'and D', respectively, if f (A ') is less than or equal to f (A), replacing A with A', otherwise, keeping A unchanged, and if f (D ') is less than or equal to f (D), replacing D with D', otherwise, keeping D unchanged;
s249, if neither A nor D is replaced by updating, executing the step S244 to the step S248, if A and D have updating conditions, executing the step S25, otherwise, executing the step S243 to the step S248 in a circulating manner until the maximum cross evolution times is met, jumping out of the circulating manner, at the moment, regenerating two individuals according to the method of the step S222 and the step S223, respectively replacing A and D, and then executing the step S25.
9. The integrated operation and maintenance scheduling method with minimized cost according to claim 4, wherein the step S25 of diversity evolution comprises the following steps:
s251: randomly selecting an individual in the population, named as E, and carrying out random variation evolution;
s252: making a random variation evolution strategy, wherein the evolution strategy is as follows:
firstly, interchanging operation and maintenance units among vehicles;
secondly, operation and maintenance units between vehicles are increased;
inserting the path in the vehicle;
exchanging paths in the vehicle;
exchanging the operation sequence of an engineer;
sixthly, operating unit interchange by an engineer;
s253: sequentially executing an evolution strategy (-C) to the individual E to form a new individual E ', if f (E ') is less than or equal to f (E), replacing the E with the E ', otherwise, keeping the E unchanged, and continuously executing the step S254;
s254: and (4) carrying out evolution strategies of (i) - (c) and (v) - (c) on the individual E in sequence to form a new individual E ', if f (E ') is less than or equal to f (E), replacing E with E ', and otherwise, keeping E unchanged.
10. The integrated operation and maintenance scheduling method with minimized cost according to claim 4, wherein the selecting elite, the evolution of elite and the preservation of elite in step S26 comprises the following steps:
s261: calculating the fitness of individuals in the ethnic groups, and selecting the individual with the highest fitness in each ethnic group to form an elite group;
s262: carrying out evolutionary cross evolution or variant evolution on the individual Pg with the maximum fitness in the elite population;
s263: the optimal Pg 'and the worst Pw after communication, if f (Pg') is less than or equal to f (Pg), the Pg 'is replaced by the Pg', otherwise, the Pw is replaced by the Pg 'with the Pg' kept unchanged;
s264: performing secondary communication and evolution on the elite population;
s265: mixing and rearranging all individuals;
s266: finishing one iteration evolution, wherein the iteration number max is max + 1;
s267: the iteration times reach the maximum iteration times MAX;
s268: outputting the individual Pg with the maximum fitness among all individuals in the population, and outputting the corresponding fitness f (Pg);
s269: and forming a specific vehicle and personnel operation and maintenance scheduling scheme according to the vehicle service chain of the individual Pg.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210330784.9A CN114764653A (en) | 2022-03-30 | 2022-03-30 | Comprehensive operation and maintenance scheduling method with minimized cost |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210330784.9A CN114764653A (en) | 2022-03-30 | 2022-03-30 | Comprehensive operation and maintenance scheduling method with minimized cost |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114764653A true CN114764653A (en) | 2022-07-19 |
Family
ID=82364774
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210330784.9A Pending CN114764653A (en) | 2022-03-30 | 2022-03-30 | Comprehensive operation and maintenance scheduling method with minimized cost |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114764653A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116187983A (en) * | 2023-04-26 | 2023-05-30 | 山西恒信风光新能源技术有限公司 | Wind turbine generator operation and maintenance management method, device, equipment and storage medium |
-
2022
- 2022-03-30 CN CN202210330784.9A patent/CN114764653A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116187983A (en) * | 2023-04-26 | 2023-05-30 | 山西恒信风光新能源技术有限公司 | Wind turbine generator operation and maintenance management method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113420382B (en) | Hydrogen production and transportation and hydrogenation scheduling system based on big data | |
| CN113222387B (en) | Multi-objective scheduling and collaborative optimization method for hydrogen fuel vehicle | |
| CN109255972B (en) | Optimization method of ground public transport fixed line timetable based on big data | |
| CN111695744B (en) | Maintenance equipment demand prediction analysis system based on big data | |
| Rakhmangulov et al. | Design of an ITS for Industrial Enterprises | |
| CN110803204B (en) | On-line control method for keeping running stability of high-speed train | |
| CN114399095A (en) | Cloud-side-cooperation-based dynamic vehicle distribution path optimization method and device | |
| CN107301510A (en) | A kind of tank service truck and ferry bus coordinated dispatching method based on genetic algorithm | |
| CN114764653A (en) | Comprehensive operation and maintenance scheduling method with minimized cost | |
| Cao et al. | Optimal capacity allocation under random passenger demands in the high-speed rail network | |
| CN115527369A (en) | Large passenger flow early warning and evacuation method under large-area delay condition of airport hub | |
| Wang et al. | A data-driven hybrid control framework to improve transit performance | |
| Mnif et al. | A multi-objective formulation for multimodal transportation network's planning problems | |
| CN116882673A (en) | Coal supply chain system and scheduling method | |
| CN116308000A (en) | Logistics scheme evaluation method and device, electronic equipment and readable storage medium | |
| Deng et al. | Research on bus passenger traffic forecasting model based on gps and ic card data | |
| Ochkasov et al. | Approaches to the improving the locomotive fleet management system | |
| Lin et al. | An Approach to the High-level Maintenance Planning for EMU Trains Based on Simulated Annealing | |
| CN113869545A (en) | Method and system for predicting power consumption of unmanned tramcar | |
| He et al. | The shunting scheduling of EMU first-level maintenance in a stub-end depot | |
| Borucka et al. | Predicting the seasonality of passengers in railway transport based on time series for proper railway development | |
| Zhang et al. | Multiple regression method of daily average mileage to predict the overhaul plan of china railway high-speed electric motor unit | |
| CN112069632B (en) | Distribution network emergency repair stagnation point position distribution method adopting feeder line fault prediction result | |
| Tian | A short-turning strategy for the management of bus bunching considering variable spatial-temporal running time | |
| Feng et al. | A systematic framework for maintenance scheduling and routing for off-shore wind farms by minimizing predictive production loss |
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 |