CN110298456A - Plant maintenance scheduling method and device in group system - Google Patents
Plant maintenance scheduling method and device in group system Download PDFInfo
- Publication number
- CN110298456A CN110298456A CN201910602097.6A CN201910602097A CN110298456A CN 110298456 A CN110298456 A CN 110298456A CN 201910602097 A CN201910602097 A CN 201910602097A CN 110298456 A CN110298456 A CN 110298456A
- Authority
- CN
- China
- Prior art keywords
- efficiency
- equipment
- load
- output power
- model
- 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 101
- 238000000034 method Methods 0.000 title claims abstract description 41
- 238000009826 distribution Methods 0.000 claims abstract description 40
- 238000013178 mathematical model Methods 0.000 claims description 21
- 230000007423 decrease Effects 0.000 claims description 16
- 238000012549 training Methods 0.000 claims description 13
- 238000005553 drilling Methods 0.000 claims description 11
- 230000009466 transformation Effects 0.000 claims description 7
- 238000007477 logistic regression Methods 0.000 claims description 6
- 238000004088 simulation Methods 0.000 claims description 6
- 238000004611 spectroscopical analysis Methods 0.000 claims description 6
- 238000013480 data collection Methods 0.000 claims description 3
- 238000005265 energy consumption Methods 0.000 abstract description 10
- 230000006870 function Effects 0.000 description 7
- 238000004422 calculation algorithm Methods 0.000 description 6
- 230000008859 change Effects 0.000 description 6
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 230000002068 genetic effect Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000005057 refrigeration Methods 0.000 description 4
- 230000005611 electricity Effects 0.000 description 3
- 230000002035 prolonged effect Effects 0.000 description 3
- 238000003860 storage Methods 0.000 description 3
- 241001269238 Data Species 0.000 description 2
- 238000013459 approach Methods 0.000 description 2
- 238000012886 linear function Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 239000002699 waste material Substances 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000000151 deposition Methods 0.000 description 1
- 238000004043 dyeing Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 238000011946 reduction process Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000002922 simulated annealing Methods 0.000 description 1
- 239000008400 supply water Substances 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 238000010200 validation analysis 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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06315—Needs-based resource requirements planning or analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Physics & Mathematics (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses plant maintenance scheduling method and devices in a kind of group system, this method comprises: establishing the corresponding efficiency degenerated mode of each equipment in group system；Determine the efficiency of the equipment and the relationship of load, and according to the load of each equipment of the relation allocation of the efficiency and load；Forecasting system future output power demand；According to the corresponding efficiency degenerated mode of each equipment, the load and the system future output power demand of distribution, plant maintenance scheduling plan is determined., can be with reasonable distribution apparatus of load using the present invention, so that equipment is run in best efficiency section as far as possible, total energy consumption is minimum；And it can effectively improve the intelligence and validity of plant maintenance scheduling.
Description
Technical field
The present invention relates to data processing fields, and in particular to plant maintenance scheduling method and device in a kind of group system.
Background technique
The annual energy consumption of industrial energy equipment (such as ice maker, air compressor machine) is very huge, efficiency level be one very
Important index, for example, if the ice maker efficiency decline 1% of a 1000kW, operates capable of consuming for saving in 1 year
It slips one new machine of enough purchases.Therefore, it is necessary to the maintenances that the energy device to these high power consumptions carries out certain strategy, so that
Equipment keeps higher efficiency horizontal.And maintenance needs cost economical, time and human cost, the maintenance of equipment stops
Machine can not influence production requirement, so being usually to formulate maintenance scheduling by experienced engineer.But artificial scheduling can deposit
In following problems:
(1) maintenance scheduling has optimization space, it may occur that " cross and safeguard " wastes maintenance cost, or " owing maintenance ", cause energy consumption
Loss；
(2) waste of manpower, each scheduling plan needs experienced engineer to do, time-consuming and laborious, and these experiences
It is difficult to pass on, the cost of training education is higher.
Summary of the invention
The embodiment of the present invention provides plant maintenance scheduling method and device in a kind of group system, logical to solve the prior art
The deficiency for manually carrying out maintenance scheduling is crossed, the intelligence and validity of plant maintenance scheduling are improved.
For this purpose, the invention provides the following technical scheme:
Plant maintenance scheduling method in a kind of group system, which comprises
Establish the corresponding efficiency degenerated mode of each equipment in group system；
Determine the efficiency of the equipment and the relationship of load, and according to each equipment of the relation allocation of the efficiency and load
Load；
Forecasting system future output power demand；
According to the corresponding efficiency degenerated mode of each equipment, the load and the system future output power demand of distribution
Amount, determines plant maintenance scheduling plan.
Optionally, the corresponding efficiency degenerated mode of each equipment in group system of establishing includes:
Collect the historical data of the equipment；
Efficiency is calculated according to the historical data, obtains multiple discrete energy valid value；
Efficiency degenerated mode corresponding with the equipment is constructed based on the multiple discrete energy valid value.
Optionally, described that efficiency degenerated mode packet corresponding with the equipment is constructed based on the multiple discrete energy valid value
It includes:
Based on the multiple discrete energy valid value, efficiency corresponding with the equipment is constructed using any one following method
Degenerated mode: curve matching, logistic regression, statistical-simulation spectrometry.
Optionally, the load of each equipment of the relation allocation according to the efficiency and load includes:
It is the relationship of output power and actual power consumption amount by the efficiency and the transformation of load；
According to load distribution principle founding mathematical models, the load distribution principle includes: to meet group system current
Under the premise of output power demand, guarantee that group system can imitate highest, amount of equipment power consumption is most saved；
Using the mathematical model and the relationship of the output power and actual power consumption amount, the load of each equipment is determined.
Optionally, described defeated according to the corresponding efficiency degenerated mode of each equipment, the load of distribution and the system future
Power demand out determines that plant maintenance scheduling plan includes:
Plant maintenance scheduling model is established as target to minimize totle drilling cost；
Training pattern parameter；
Plant maintenance scheduling plan is obtained according to the model parameter.
Plant maintenance scheduling device in a kind of group system, described device include:
Efficiency degenerated mode establishes module, for establishing the corresponding efficiency degenerated mode of each equipment in group system；
Distribution module is loaded, for determining the efficiency of the equipment and the relationship of load, and according to the efficiency and load
Each equipment of relation allocation load；
Prediction module is used for forecasting system future output power demand；
Arranging module is safeguarded, for the load and the system according to the corresponding efficiency degenerated mode of each equipment, distribution
The following output power demand determines plant maintenance scheduling plan.
Optionally, the efficiency degenerated mode establishes module and includes:
Data collection module, for collecting the historical data of the equipment；
Energy valid value computing unit calculates efficiency according to the historical data for calculating, obtains multiple discrete energy
Valid value；
Energy efficiency model establishes unit, for constructing efficiency corresponding with the equipment based on the multiple discrete energy valid value
Degenerated mode.
Optionally, the energy efficiency model establishes unit, specifically for based on the multiple discrete energy valid value, utilization is following
Any one method constructs efficiency degenerated mode corresponding with the equipment: curve matching, logistic regression, statistical-simulation spectrometry.
Optionally, the load distribution module includes:
Relation determination unit, for determining the efficiency of the equipment and the relationship of load；
Relationship converting unit, for being the pass of output power and actual power consumption amount by the transformation of the efficiency and load
System；
Mathematical model establishes unit, for according to load distribution principle founding mathematical models, the load distribution principle packet
It includes: under the premise of meeting group system present output power demand, guaranteeing that group system can imitate highest, amount of equipment power consumption most
It saves；
Load determining unit, for the relationship using the mathematical model and the output power and actual power consumption amount, really
The load of fixed each equipment.
Optionally, the maintenance arranging module includes:
Scheduling model foundation unit, for establishing plant maintenance scheduling model as target to minimize totle drilling cost；
Training unit is used for training pattern parameter；
Scheduling plan output unit, for obtaining plant maintenance scheduling plan according to the model parameter.
A kind of electronic equipment, comprising: one or more processors, memory；
For the memory for storing computer executable instructions, the processor is executable for executing the computer
Instruction, to realize mentioned-above method.
A kind of readable storage medium storing program for executing, is stored thereon with instruction, and described instruction is performed to realize mentioned-above method.
Plant maintenance scheduling method and device, establish in group system and respectively set in group system provided in an embodiment of the present invention
Standby corresponding efficiency degenerated mode；Determine the efficiency of the equipment and the relationship of load, and according to the pass of the efficiency and load
System distributes the load of each equipment；Forecasting system future output power demand；According to the corresponding efficiency degenerated mode of each equipment, divide
The load and the system future output power demand matched, determine plant maintenance scheduling plan.The present invention program is by commenting
Estimate the current efficiency of every equipment and equipment itself efficiency as caused by load is different to change, it can be with reasonable distribution equipment
Load, so that equipment is run in best efficiency section as far as possible, total energy consumption is minimum；Moreover, comprehensively considering the efficiency decline of equipment
Trend is predicted according to the load of current efficiency optimal allocation and the target requirement amount in system future, establishes prolonged equipment dimension
Scheduling model is protected, to replace traditional artificial scheduling, to effectively improve the intelligence and validity of plant maintenance scheduling.
Detailed description of the invention
In order to illustrate the technical solutions in the embodiments of the present application or in the prior art more clearly, below will be to institute in embodiment
Attached drawing to be used is needed to be briefly described, it should be apparent that, the accompanying drawings in the following description is only one recorded in the present invention
A little embodiments are also possible to obtain other drawings based on these drawings for those of ordinary skill in the art.
Fig. 1 is a kind of flow chart of plant maintenance scheduling method in group system of the embodiment of the present invention；
Fig. 2 is energy efficiency of equipment decline curve schematic diagram in the embodiment of the present invention；
Fig. 3 is the efficiency degenerated mode schematic diagram of ice maker in the embodiment of the present invention；
Fig. 4 is the relation curve of the efficiency of ice maker and load in the embodiment of the present invention；
Fig. 5 is the relation curve of the output power of ice maker and actual power consumption amount in the embodiment of the present invention；
Fig. 6 is ice maker system using influence result of the different plant maintenance scheduling modes to system；
Fig. 7 is a kind of structural block diagram of plant maintenance scheduling device in group system of the embodiment of the present invention；
Fig. 8 is a kind of structural block diagram that distribution module is loaded in the embodiment of the present invention.
Specific embodiment
The scheme of embodiment in order to enable those skilled in the art to better understand the present invention with reference to the accompanying drawing and is implemented
Mode is described in further detail the embodiment of the present invention.
The embodiment of the present invention provides plant maintenance scheduling method and device in a kind of group system, and the embodiment of the present invention provides
Group system in plant maintenance scheduling method and device, establish the corresponding efficiency degenerated mode of each equipment in group system；Really
The efficiency of the fixed equipment and the relationship of load, and according to the load of each equipment of the relation allocation of the efficiency and load；Prediction
System future output power demand；Not according to the corresponding efficiency degenerated mode of each equipment, the load of distribution and the system
Carry out output power demand, determines plant maintenance scheduling plan.
As shown in Figure 1, be a kind of flow chart of plant maintenance scheduling method in group system of the embodiment of the present invention, including with
Lower step:
Step 101, the corresponding efficiency degenerated mode of each equipment in group system is established.
The efficiency of energy device is generally indicated that this energy valid value is got over by the output power of the equipment/equipment actual power consumption amount
Illustrate that the energy conversion efficiency of equipment is higher greatly, performance is better.Distinct device is due to service life difference or factory plate model etc.
The trend of difference, efficiency decline is discrepant.General energy efficiency of equipment decline curve is as shown in Figure 2, wherein when horizontal axis is
Between, the longitudinal axis is efficiency, and the actual value of efficiency is as shown in the curve L1 in Fig. 2, and variation tendency is as shown in the curve L2 in Fig. 2.
In embodiments of the present invention, the corresponding efficiency of the equipment can be established respectively for each equipment in group system
Degenerated mode.The efficiency degenerated mode reflects the decline trend of the efficiency of equipment, that is to say, that energy valid value changes over time
Trend.
It, can be by the historical data of the collection equipment, according to the historical data when establishing efficiency degenerated mode
Efficiency is calculated, multiple discrete energy valid value are obtained；It is corresponding with the equipment to be then based on the multiple discrete energy valid value building
Efficiency degenerated mode, for example, by the modes such as curve matching or logistic regression or statistical-simulation spectrometry to obtain
State the corresponding efficiency degenerated mode of equipment.
It should be noted that for the historical data of collection, it is also necessary to carry out noise reduction process, that is, remove exception therein
Value, so that finally obtained efficiency degenerated mode is more acurrate.
Using the efficiency degenerated mode, the energy valid value of next a period of time equipment can be predicted.
Since the efficiency decline trend of distinct device would also vary from, in embodiments of the present invention, need to be directed to
Each equipment in group system establishes the corresponding efficiency degenerated mode of the equipment respectively.
Step 102, the efficiency of the equipment and the relationship of load are determined, and according to the relation allocation of the efficiency and load
The load of each equipment.
According to the different target requirement amount of system (such as refrigerating capacity or gas consumption etc.), need to own in group system
The general power of equipment output meets the needs of different, for this reason, it may be necessary to which load is assigned in different equipment.To ask efficiency maximum
Change, the best equipment of performance can be selected in principle and be loaded into upper loading limit, and so on.However general equipment, efficiency and
There can be certain relationship between load, load too high or the too low efficiency that can all make equipment decline.
It is previously noted that efficiency can be indicated by output power/actual power consumption amount, and load can by actual power consumption amount/
Rated energy consumption indicates that therefore, can be by the relationship of efficiency and load: efficiency=F (load) be converted into output power and reality
The relationship of power consumption: output power=F'(actual power consumption amount), transfer principle is as follows:
It is available according to output power/actual power consumption amount=F (actual power consumption amount/rated energy consumption):
Output power=actual power consumption amount × F (actual power consumption amount/rated energy consumption)；
Due to rated energy consumption and F be it is known, it can be concluded that the relationship of output power and power consumption: output power
=F'(actual power consumption amount).
Based on the above principles, when carrying out load distribution, first according to the efficiency of current device, the equipment is evaluated
The relationship of efficiency and load.Since the efficiency and load relationship of equipment are more constant, calibration validation will do it in equipment factory,
But the practical efficiency of equipment can be with time decline be used, therefore, can be according to current efficiency, to load-energy when dispatching from the factory
Effect relationship is modified, and obtains the relationship of equipment current efficiency and load.
It then is the relationship of output power and actual power consumption amount by the efficiency of the equipment and the transformation of load, specifically
The expression of available segment approximate linear function, expression formula such as formula (1):
Wherein, x indicates the current actual power consumption amount of equipment, and f (x) indicates output of the equipment under current actual power consumption amount
Power, m1 ... m9 indicates power consumption interval value.
It should be noted that each parameter in above formula can be adjusted according to equipment difference.
For the multiple devices in group system, the load of reasonable distribution individual device is needed, is reached in output work
Under the premise of rate meets current demand, system can imitate highest, amount of equipment power consumption is most saved purpose.Therefore, of the invention real
It applies in example, following load distribution principle can be set: under the premise of meeting group system present output power demand, guaranteeing collection
System can imitate highest to group, amount of equipment power consumption is most saved.
When distributing the load of each equipment, institute can be then utilized according to above-mentioned load distribution principle founding mathematical models
The relationship for stating mathematical model and above-mentioned output power and actual power consumption amount can determine the load of currently each equipment.Specifically, may be used
It is solved, be can be obtained each with converting standard linear programming problem for above-mentioned piecewise function f (x) using the mathematical model
The actual power consumption amount of equipment, and then the load of available each equipment.
Step 103, forecasting system future output power demand.
Whether for which kind of equipment and application environment, can according to the target requirement amount of group system (such as refrigerating capacity,
Or gas consumption etc.) determine the output power demand of group system.It therefore, in embodiments of the present invention, can be to future one
Output power needed for system is predicted in the section time.
In embodiments of the present invention, a large amount of historical datas (i.e. system output power) training prediction mould can be acquired in advance
Type, specifically, can use in time series predicting model or machine learning regression model (such as Random Forest model,
SVM, neural network model etc.), using historical data for the previous period as input, using the data of subsequent a period of time as defeated
It is trained out, obtains prediction model.
Step 104, according to the efficiency degenerated mode of each equipment, the load distribution model and the system future need
The amount of asking determines plant maintenance scheduling plan.
To operate energy device in a good efficiency level, need to carry out regularly maintenance, target is
Total system reduces totle drilling cost to the greatest extent under the premise of meeting aims of systems demand.The totle drilling cost such as may include fortune
Turn the fixed cost of the electricity charge and maintenance.
In general, group system plant maintenance has following three features:
1) the efficiency decline trend of equipment is almost the same within each maintenance period, it is believed that approximately uniform；
2) maintenance is time-consuming fixed every time, completes within a time cycle；
3) efficiency of equipment returns to original state after maintenance every time.
Based on These characteristics, in embodiments of the present invention, following mathematical model can establish:
By time discretization, the chronomere of maintenance scheduling is determined, such as unit of day, if total length of time is T, note
Time is t, t=0,1,2,3 ..., T；
The system output power demand at each time point according to above-mentioned steps 103 it is found that be t function, be denoted as R
(t)；
There is N platform equipment, is denoted as n, n=1,2,3 ..., N；
The constant expense of maintenance is denoted as A；
Decision variable is xt,n={ 0,1 } indicates whether n equipment arranges maintenance, sequence { x in tt,nIndicate whole
A maintenance plan；
Pn({xt,n, t) it indicates according to { xt,nPlan, energy valid value of the n equipment in t；
F(R(t),Pn({xt,n, t)) power consumption when indicating the t being calculated according to the load that each equipment distribute, it inputs
The energy valid value of individual device when system output power demand and t when for t, energy valid value of each equipment in t is according to step
The efficiency degenerated mode of 101 foundation is available；
According to the mathematical model built, objective function is total cost, including the electricity charge and total execution maintenance time in total time
Several expenses obtains plant maintenance scheduling model, such as formula 2:
The plant maintenance scheduling model can be solved with heuritic approach, and the heuritic approach such as can be following
Any one: genetic algorithm, particle swarm algorithm, simulated annealing etc..For this sentences genetic algorithm, the dyeing of genetic algorithm
Body is a maintenance programmed sequence { xt,n, fitness function is formula 2, by the continuous iteration of intersection, variation, selection operation,
It is finally reached fitness function convergence, obtains model parameter.Best maintenance plan can be obtained according to the model parameter, i.e., on
State sequence { xt,n}。
It should be noted that each equipment in group system can have different maintenance time points, that is to say, that
In each maintenance, maintenance only can be carried out to some or the equipment component in group system.
Plant maintenance scheduling method in group system provided in an embodiment of the present invention, by establishing each equipment in group system
Corresponding efficiency degenerated mode；Determine the efficiency of the equipment and the relationship of load, and according to the relationship of the efficiency and load
Distribute the load of each equipment；Forecasting system future output power demand；According to the corresponding efficiency degenerated mode of each equipment, distribution
Load and the system future output power demand, determine plant maintenance scheduling plan.The present invention program passes through assessment
The current efficiency of every equipment and equipment itself efficiency as caused by load is different change, can be negative with reasonable distribution equipment
It carries, so that equipment is run in best efficiency section as far as possible, total energy consumption is minimum；Moreover, the efficiency decline for comprehensively considering equipment becomes
Gesture is predicted according to the load of current efficiency optimal allocation and the target requirement amount in system future, establishes prolonged plant maintenance
Scheduling model, to replace traditional artificial scheduling, to effectively improve the intelligence and validity of plant maintenance scheduling.
Below with reference to specific example present invention be described in more detail scheme.
By taking ice maker (also known as frozen water machine) as an example, it is assumed that be provided with three ice makers, respectively ice maker A, ice maker in group system
B, ice maker C.
The principle of ice maker is to convert electrical energy into refrigerating capacity, that is, reduces the water flow temperature by ice maker, the expression of refrigerating capacity
Formula are as follows:
Refrigerating capacity (RT)=water flow (m3/ h) × (return water temperature (DEG C)-supply water temperature (DEG C)) × water specific heat capacity
(4.1868kj/kg DEG C) × water density (1000kg/m3)/3600/(3.517kW/RT)；
It therefore, can be using refrigerating capacity/power consumption as the efficiency of ice maker, with COP (Coefficient Of
Performance it) indicates, COP value is higher, and the refrigerating capacity for illustrating unit power consumption is higher, and ice maker efficiency is better.
1) the corresponding efficiency degenerated mode of each ice maker in group system is established
The efficiency of ice maker is indicated with COP.Using method described in preceding step 101, according to the historical data of each ice maker,
The multiple discrete energy valid value for obtaining corresponding to each ice maker generate efficiency change curve using these energy valid value, then pass through letter
Number y=1/ (ax+b)+c (wherein, a, b, c are undetermined parameter, and usage history data carry out curve fitting to obtain) is to the efficiency
Change curve carries out curve fitting, the curve after being fitted.The trend of efficiency decline is characterized using the curve after the fitting,
That is efficiency degenerated mode, the corresponding efficiency degenerated mode of three ice makers are as shown in Figure 3, wherein LA is that the corresponding efficiency of ice maker A declines
Model is moved back, LB is the corresponding efficiency degenerated mode of ice maker B, and LC is the corresponding efficiency degenerated mode of ice maker C.
Using the corresponding efficiency degenerated mode of each ice maker, the energy valid value of next a period of time each ice maker can be predicted.
2) load distribution model is established
According to system current refrigeration demand, needs to load and be assigned in different equipment, it is former to ask efficiency to maximize
The best equipment of performance can be selected on then is loaded into upper loading limit, and so on.However general efficiency equipment can have one
Best efficiency section, load too high or it is too low can all cause equipment to operate in non-optimal efficiency section, efficiency decline.
According to system current refrigeration demand, the overall power requirement amount that equipment exports in system can be determined.It is negative establishing
When carrying distribution model, first according to the efficiency of current ice maker, the efficiency of the ice maker and the relationship of load are evaluated, such as Fig. 4 institute
Show；It then is the relationship of output power and actual power consumption amount by the efficiency and the transformation of load, as shown in figure 5, specifically
The expression of available segment approximate linear function, expression formula can be found in front formula (1).
For convenience, separately below with x1, x2, x3Indicate the actual power consumption amount of three ice makers, f1(x1)、f2(x2)、f3
(x3) indicate output power of each ice maker under currently practical power consumption.
For more ice makers, the load of each ice maker of reasonable distribution is needed, reaches and is meeting current refrigeration capacity demand
Under the premise of, guarantee the purpose that group system can imitate highest, amount of equipment power consumption is most saved.
Based on mentioned above principle, following mathematical model can establish:
min x1+x2+x3
S.t.
f1(x1)+f2(x2)+f3(x3)≥RTneed
0≤x1, x2, x3≤Power_max
Wherein, RTneedIndicate that the current desired output power of group system, Power_max indicate the maximum power consumption of ice maker
Amount.
It should be noted that above-mentioned mathematical model is equally applicable to the cluster system of any ice maker or other equipment
System.
The mathematical model can convert mark for the relation function f (x) of the output power of above-mentioned ice maker and actual power consumption amount
Almost linear planning problem is solved, and the actual power consumption amount of each equipment, and then the load of available each equipment can be obtained.
3) system output power Demand Forecast
For ice maker group system, the target requirement amount of system is ice maker refrigerating capacity, can be needed according to system future
Refrigerating capacity determines the output power demand of system.In practical applications, algorithm there are many refrigerating capacitys in forecasting system future, than
The actual refrigerating capacity of history such as be can choose as aims of systems demand, then determine that system is defeated according to aims of systems demand
Power demand out.
4) plant maintenance scheduling
Choosing one day is a unit time, carries out scheduling, i.e. T=360 to maintenances in 360 days.The system of every day
Refrigeration requirement uses history truthful data, convenient for comparing.Ice maker has three, and a maintenance constant expense is 5000 yuan/time, establishes
The plant maintenance scheduling model of above-mentioned formula 2 simultaneously solves, and obtains plant maintenance scheduling plan.
The beneficial effect of scheme in order to further illustrate the present invention, Fig. 6 are shown ice maker system and are tieed up using different equipment
Protect influence result of the scheduling mode to system.
In Fig. 6, L61 is the COP value of the ice maker system of existing maintenance strategy implement, and L62 is to implement once according to every 3 months
The COP value for the ice maker system that maintenance (regular maintenance strategy) is implemented, L63 are according to maintenance scheduling side provided in an embodiment of the present invention
The COP value for the ice maker system that case is implemented, comparing result are as shown in table 1 below:
Table 1
In summary result can be seen that the optimization of the maintenance scheduling by the present invention program, compare existing maintenance scheduling
Plan, totle drilling cost can reduce by 1.7%；Conventional maintenance scheduling plans in 3 months are compared, totle drilling cost can reduce by 0.85%.
Correspondingly, the embodiment of the present invention also provides plant maintenance scheduling device in a kind of group system, as shown in fig. 7, being
A kind of structural block diagram of the device.
In this embodiment, described device includes following module:
Efficiency degenerated mode establishes module 701, for establishing the corresponding efficiency degenerated mode of each equipment in group system；
Distribution module 702 is loaded, for determining the efficiency of the equipment and the relationship of load, and according to the efficiency and is born
The load of each equipment of the relation allocation of load；
Prediction module 703 is used for forecasting system future output power demand；
Arranging module 704 is safeguarded, for according to the load of the corresponding efficiency degenerated mode of each equipment, distribution and described
System future output power demand determines plant maintenance scheduling plan.
In embodiments of the present invention, the efficiency degenerated mode, which establishes module 701, can be directed to respectively setting in group system
It is standby, the corresponding efficiency degenerated mode of the equipment is established respectively.The decline for the efficiency that the efficiency degenerated mode reflects equipment becomes
Gesture, that is to say, that the trend that energy valid value changes over time.Specifically, the efficiency degenerated mode establishes module 701 and may include
Following each unit:
Data collection module, for collecting the historical data of the equipment；
Energy valid value computing unit calculates efficiency according to the historical data for calculating, obtains multiple discrete energy
Valid value；
Energy efficiency model establishes unit, for constructing efficiency corresponding with the equipment based on the multiple discrete energy valid value
Degenerated mode, for example, utilizing any one following method building efficiency degenerated mode corresponding with the equipment: curve matching,
Logistic regression, statistical-simulation spectrometry.
In embodiments of the present invention, a kind of specific structure of the load distribution module 702 is as shown in figure 8, include following
Each unit
Relation determination unit 721, for determining the efficiency of the equipment and the relationship of load；
Relationship converting unit 722, for being output power and actual power consumption amount by the transformation of the efficiency and load
Relationship；
Mathematical model establishes unit 723, for according to load distribution principle founding mathematical models, the load distribution principle
It include: to guarantee that group system can imitate highest, amount of equipment power consumption under the premise of meeting group system present output power demand
Most save；
Load determining unit, for the relationship using the mathematical model and the output power and actual power consumption amount, really
The load of fixed each equipment.
Above-mentioned prediction module 703, which specifically can use prediction model trained in advance, which carrys out forecasting system future output power, needs
The amount of asking.The prediction model can be obtained by acquiring the training of a large amount of historical datas, specific training process similarly to the prior art,
Details are not described herein.
Above-mentioned maintenance arranging module 704 can obtain plant maintenance scheduling plan by plant maintenance scheduling model.It builds
The principle for founding the plant maintenance scheduling model is as follows: making group system under the premise of meeting aims of systems demand, as far as possible
Reduce totle drilling cost.The totle drilling cost such as may include the fixed cost for operating the electricity charge and maintenance.
Correspondingly, a kind of specific structure of the maintenance arranging module 704 may include following each unit:
Scheduling model foundation unit, for establishing plant maintenance scheduling model as target to minimize totle drilling cost；It is described to set
The establishment process of standby maintenance scheduling model can be found in the description in the embodiment of the present invention method of front, and details are not described herein；
Training unit is used for training pattern parameter, for example can use genetic algorithm training and obtain the plant maintenance row
The parameter of journey model；
Scheduling plan output unit, for obtaining plant maintenance scheduling plan according to the model parameter.
It should be noted that each equipment in group system can have different maintenance time points, that is to say, that
In each maintenance, maintenance only can be carried out to some or the equipment component in group system.
It should be noted that for each embodiment of plant maintenance scheduling device in above-mentioned group system, due to each mould
Block, the function realization of unit are similar with corresponding method, therefore describe to compare to each embodiment of the dialogue generating means
Simply, related place can be found in the corresponding portion explanation of embodiment of the method.
Plant maintenance scheduling device in group system provided in an embodiment of the present invention, by establishing each equipment in group system
Corresponding efficiency degenerated mode；Determine the efficiency of the equipment and the relationship of load, and according to the relationship of the efficiency and load
Distribute the load of each equipment；Forecasting system future output power demand；According to the corresponding efficiency degenerated mode of each equipment, distribution
Load and the system future output power demand, determine plant maintenance scheduling plan.The present invention program passes through assessment
The current efficiency of every equipment and equipment itself efficiency as caused by load is different change, can be negative with reasonable distribution equipment
It carries, so that equipment is run in best efficiency section as far as possible, total energy consumption is minimum；Moreover, the efficiency decline for comprehensively considering equipment becomes
Gesture is predicted according to the load of current efficiency optimal allocation and the target requirement amount in system future, establishes prolonged plant maintenance
Scheduling model, to replace traditional artificial scheduling, to effectively improve the intelligence and validity of plant maintenance scheduling.
It should be noted that description and claims of this specification and term " first " in above-mentioned attached drawing, "
Two " etc. be to be used to distinguish similar objects, without being used to describe a particular order or precedence order.It should be understood that using in this way
Data be interchangeable under appropriate circumstances, so as to the embodiment of the present invention described herein can in addition to illustrating herein or
Sequence other than those of description is implemented.In addition, term " includes " and " having " and their any deformation, it is intended that cover
Cover it is non-exclusive include, for example, the process, method, system, product or equipment for containing a series of steps or units are not necessarily limited to
Step or unit those of is clearly listed, but may include be not clearly listed or for these process, methods, product
Or other step or units that equipment is intrinsic.
All the embodiments in this specification are described in a progressive manner, same and similar portion between each embodiment
Dividing may refer to each other, and each embodiment focuses on the differences from other embodiments.Moreover, described above
System embodiment it is only schematical, wherein module and unit can be or can not also as illustrated by the separation member
It is to be physically separated, it can be located in a network unit, or may be distributed over multiple network units.It can root
According to actual need that some or all of the modules therein is selected to achieve the purpose of the solution of this embodiment.Ordinary skill
Personnel can understand and implement without creative efforts.
Those of ordinary skill in the art will appreciate that all or part of the steps in realization above method embodiment is can
It is completed with instructing relevant hardware by program, the program can store in computer-readable storage medium,
Storage medium designated herein, such as: ROM/RAM, magnetic disk, CD.
Correspondingly, the embodiment of the present invention also provides a kind of device for plant maintenance scheduling method in group system, should
Device is a kind of electronic equipment, for example, can be mobile terminal, computer, tablet device, Medical Devices, body-building equipment, individual
Digital assistants etc..The electronic equipment may include one or more processors, memory；Wherein, the memory is for depositing
Computer executable instructions are stored up, the processor is for executing the computer executable instructions, to realize previous embodiments
The method.
The embodiment of the present invention has been described in detail above, and specific embodiment used herein carries out the present invention
It illustrates, method and device of the invention that the above embodiments are only used to help understand, is only the present invention one
The embodiment divided, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art are not doing
Every other embodiment obtained under the premise of creative work out, should fall within the scope of the present invention, this specification
Content should not be construed as limiting the invention.Therefore, all within the spirits and principles of the present invention, it is made it is any modification,
Equivalent replacement, improvement etc., should all be included in the protection scope of the present invention.
Claims (10)
1. plant maintenance scheduling method in a kind of group system, which is characterized in that the described method includes:
Establish the corresponding efficiency degenerated mode of each equipment in group system；
Determine the efficiency of the equipment and the relationship of load, and according to the negative of each equipment of the relation allocation of the efficiency and load
It carries；
Forecasting system future output power demand；
According to the corresponding efficiency degenerated mode of each equipment, the load and the system future output power demand of distribution, really
Locking equipment safeguards scheduling plan.
2. the method according to claim 1, wherein the corresponding efficiency of each equipment in group system of establishing declines
Moving back model includes:
Collect the historical data of the equipment；
Efficiency is calculated according to the historical data, obtains multiple discrete energy valid value；
Efficiency degenerated mode corresponding with the equipment is constructed based on the multiple discrete energy valid value.
3. according to the method described in claim 2, it is characterized in that, described based on the multiple discrete building of energy valid value and institute
Stating the corresponding efficiency degenerated mode of equipment includes:
Based on the multiple discrete energy valid value, efficiency corresponding with the equipment is constructed using any one following method and is failed
Model: curve matching, logistic regression, statistical-simulation spectrometry.
4. the method according to claim 1, wherein described respectively set according to the efficiency and the relation allocation of load
Standby load includes:
It is the relationship of output power and actual power consumption amount by the efficiency and the transformation of load；
According to load distribution principle founding mathematical models, the load distribution principle includes: currently to export meeting group system
Under the premise of power demand, guarantee that group system can imitate highest, amount of equipment power consumption is most saved；
Using the mathematical model and the relationship of the output power and actual power consumption amount, the load of each equipment is determined.
5. method according to any one of claims 1 to 4, which is characterized in that described to be declined according to the corresponding efficiency of each equipment
The load and the system future output power demand for moving back model, distribution, determine that plant maintenance scheduling plan includes:
Plant maintenance scheduling model is established as target to minimize totle drilling cost；
Training pattern parameter；
Plant maintenance scheduling plan is obtained according to the model parameter.
6. plant maintenance scheduling device in a kind of group system, which is characterized in that described device includes:
Efficiency degenerated mode establishes module, for establishing the corresponding efficiency degenerated mode of each equipment in group system；
Distribution module is loaded, for determining the efficiency of the equipment and the relationship of load, and according to the pass of the efficiency and load
System distributes the load of each equipment；
Prediction module is used for forecasting system future output power demand；
Safeguard arranging module, for according to the corresponding efficiency degenerated mode of each equipment, distribution load and the system future
Output power demand determines plant maintenance scheduling plan.
7. device according to claim 6, which is characterized in that the efficiency degenerated mode establishes module and includes:
Data collection module, for collecting the historical data of the equipment；
Energy valid value computing unit calculates efficiency according to the historical data for calculating, obtains multiple discrete energy valid value；
Energy efficiency model establishes unit, for constructing efficiency decline corresponding with the equipment based on the multiple discrete energy valid value
Model.
8. device according to claim 7, which is characterized in that
The energy efficiency model establishes unit, specifically for utilizing any one following side based on the multiple discrete energy valid value
Method constructs efficiency degenerated mode corresponding with the equipment: curve matching, logistic regression, statistical-simulation spectrometry.
9. device according to claim 6, which is characterized in that the load distribution module includes:
Relation determination unit, for determining the efficiency of the equipment and the relationship of load；
Relationship converting unit, for being the relationship of output power and actual power consumption amount by the transformation of the efficiency and load；
Mathematical model establishes unit, for according to load distribution principle founding mathematical models, the load distribution principle include:
Under the premise of meeting group system present output power demand, guarantee that group system can imitate highest, amount of equipment power consumption is most saved；
Load determining unit determines each for the relationship using the mathematical model and the output power and actual power consumption amount
The load of equipment.
10. according to the described in any item devices of claim 6 to 9, which is characterized in that the maintenance arranging module includes:
Scheduling model foundation unit, for establishing plant maintenance scheduling model as target to minimize totle drilling cost；
Training unit is used for training pattern parameter；
Scheduling plan output unit, for obtaining plant maintenance scheduling plan according to the model parameter.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910602097.6A CN110298456A (en) | 2019-07-05 | 2019-07-05 | Plant maintenance scheduling method and device in group system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910602097.6A CN110298456A (en) | 2019-07-05 | 2019-07-05 | Plant maintenance scheduling method and device in group system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110298456A true CN110298456A (en) | 2019-10-01 |
Family
ID=68030365
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910602097.6A Pending CN110298456A (en) | 2019-07-05 | 2019-07-05 | Plant maintenance scheduling method and device in group system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110298456A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111210157A (en) * | 2020-01-13 | 2020-05-29 | 上海威派格智慧水务股份有限公司 | Dynamic storage adjusting method for water tank |
| CN111414070A (en) * | 2020-03-06 | 2020-07-14 | 苏州浪潮智能科技有限公司 | Case power consumption management method and system, electronic device and storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104392334A (en) * | 2014-12-12 | 2015-03-04 | 冶金自动化研究设计院 | Joint optimized scheduling method for multiple types of generating sets of self-supply power plant of iron and steel enterprise |
| CN105321042A (en) * | 2015-10-19 | 2016-02-10 | 金航数码科技有限责任公司 | Genetic algorithm-based advanced plan scheduling system and method |
| US20160077507A1 (en) * | 2014-09-11 | 2016-03-17 | Gerald Bernard Sheble | Resource control by probability tree convolution production cost valuation by iterative equivalent demand duration curve expansion (aka. tree convolution) |
| CN105809297A (en) * | 2016-05-18 | 2016-07-27 | 西南石油大学 | Thermal power plant environment economic dispatching method based on multi-target differential evolution algorithm |
| CN107103401A (en) * | 2011-03-24 | 2017-08-29 | 迅应科技有限公司 | The method and node of power consumption in control distribution network |
| CN109028468A (en) * | 2018-06-13 | 2018-12-18 | 北京天泽智云科技有限公司 | Ice maker group system energy consumption optimization method and device based on big data analysis |
| CN109359884A (en) * | 2018-10-31 | 2019-02-19 | 南京航空航天大学 | Workshop operation plan and rescheduling method for complex aviation equipment structure |
-
2019
- 2019-07-05 CN CN201910602097.6A patent/CN110298456A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107103401A (en) * | 2011-03-24 | 2017-08-29 | 迅应科技有限公司 | The method and node of power consumption in control distribution network |
| US20160077507A1 (en) * | 2014-09-11 | 2016-03-17 | Gerald Bernard Sheble | Resource control by probability tree convolution production cost valuation by iterative equivalent demand duration curve expansion (aka. tree convolution) |
| CN104392334A (en) * | 2014-12-12 | 2015-03-04 | 冶金自动化研究设计院 | Joint optimized scheduling method for multiple types of generating sets of self-supply power plant of iron and steel enterprise |
| CN105321042A (en) * | 2015-10-19 | 2016-02-10 | 金航数码科技有限责任公司 | Genetic algorithm-based advanced plan scheduling system and method |
| CN105809297A (en) * | 2016-05-18 | 2016-07-27 | 西南石油大学 | Thermal power plant environment economic dispatching method based on multi-target differential evolution algorithm |
| CN109028468A (en) * | 2018-06-13 | 2018-12-18 | 北京天泽智云科技有限公司 | Ice maker group system energy consumption optimization method and device based on big data analysis |
| CN109359884A (en) * | 2018-10-31 | 2019-02-19 | 南京航空航天大学 | Workshop operation plan and rescheduling method for complex aviation equipment structure |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111210157A (en) * | 2020-01-13 | 2020-05-29 | 上海威派格智慧水务股份有限公司 | Dynamic storage adjusting method for water tank |
| CN111210157B (en) * | 2020-01-13 | 2023-05-12 | 上海威派格智慧水务股份有限公司 | Dynamic water tank regulating and accumulating method |
| CN111414070A (en) * | 2020-03-06 | 2020-07-14 | 苏州浪潮智能科技有限公司 | Case power consumption management method and system, electronic device and storage medium |
| CN111414070B (en) * | 2020-03-06 | 2021-10-15 | 苏州浪潮智能科技有限公司 | A chassis power consumption management method, system, electronic device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wang et al. | Balancing risk and cost in fuzzy economic dispatch including wind power penetration based on particle swarm optimization | |
| CN111753431B (en) | Computing method and computing equipment for optimal configuration in comprehensive energy system | |
| CN107578124A (en) | Short-term power load forecasting method based on multi-layer improved GRU neural network | |
| CN116207739B (en) | Optimal scheduling method and device for power distribution network, computer equipment and storage medium | |
| US20240006891A1 (en) | Two-stage self-organizing optimized aggregation method and system for distributed resources of virtual power plant (vpp) | |
| CN111401604A (en) | Power system load power prediction method and energy storage power station power distribution method | |
| CN107093896A (en) | A kind of industrial load Optimized Operation modeling method based on demand response | |
| CN114971048A (en) | Zero-carbon park comprehensive energy planning simulation method and system and computer equipment | |
| CN107612045A (en) | A kind of Power Plant generated energy intelligent dispensing system and method | |
| CN110298456A (en) | Plant maintenance scheduling method and device in group system | |
| CN110323768B (en) | Power distribution method and system for electrochemical energy storage power station | |
| CN112785022B (en) | Method and system for excavating electric energy substitution potential | |
| CN111079966B (en) | Generalized load space prediction method and system | |
| CN112784439A (en) | Energy internet planning method and device based on discretization model | |
| CN118157128A (en) | Dynamic scheduling control method and system for virtual power plant resource aggregation | |
| CN112039058A (en) | Unit combination method, system, medium and equipment based on wind power prediction interval | |
| Shuvo et al. | Optimal dispatch for a microgrid with distributed generations and ev charging load | |
| CN114881364B (en) | A comprehensive energy system optimization scheduling method, system, equipment and medium | |
| CN117424204A (en) | Source-network-load-storage collaborative planning method considering source-load uncertainty | |
| CN117422219A (en) | Resource optimization disposal method based on energy demand response | |
| CN113471966A (en) | Large industrial load flexible regulation and control method considering interrupt priority | |
| CN104484756B (en) | A kind of enterprise's efficiency method for improving the microgrid of generating containing wind-light storage | |
| CN118983830B (en) | Optimal configuration method of energy storage capacity for photovoltaic and energy storage combined system considering source-load uncertainty | |
| CN119647677A (en) | Virtual power plant scheduling optimization method and system | |
| CN107292423A (en) | Energy efficiency power plant based on uncertain method is distributed rationally and factory's net planing method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191001 |
|
| RJ01 | Rejection of invention patent application after publication |