CN106530130A - Dynamic evolutionary modeling and energy-saving optimization method of oil extraction process of oil field machine - Google Patents
Dynamic evolutionary modeling and energy-saving optimization method of oil extraction process of oil field machine Download PDFInfo
- Publication number
- CN106530130A CN106530130A CN201610999735.9A CN201610999735A CN106530130A CN 106530130 A CN106530130 A CN 106530130A CN 201610999735 A CN201610999735 A CN 201610999735A CN 106530130 A CN106530130 A CN 106530130A
- Authority
- CN
- China
- Prior art keywords
- variable
- sample
- moment
- covariance
- value
- 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
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
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Z—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS, NOT OTHERWISE PROVIDED FOR
- G16Z99/00—Subject matter not provided for in other main groups of this subclass
Abstract
The invention provides a dynamic evolutionary modeling and energy-saving optimization method of the oil extraction process of an oil field machine. The method comprises the following steps of: determining an efficiency influence factor and a performance variable in an oil extraction process of the oil field machine; carrying out dimension reduction processing on a load variable in a sample to construct a new sample, and carrying out normalization on the new sample; on the basis of the normalized new sample, constructing a neural network model; utilizing a ST-UKFNN (Strong Trace Unscented Kalman Filtering Neural Network) algorithm to estimate the optimal state of a state variable formed by a weight threshold value in the neural network model; utilizing an optimal state variable to reconstruct the updated neural network model to obtain an oil extraction process model of the oil field machine; constructing a preference function of a practical daily liquid yield, and utilizing a MOGA (Multi-Objective Genetic Algorithm) to carry out optimization on the respective upper limit and lower limit of a decision variable; and introducing the optimized decision variable into the oil extraction process model of the oil field machine, calculating the system performance of the optimized decision variable, and comparing the calculated value with the average value of the system performance of a practical sample. When the method is utilized, the production efficiency of the oil field machine can be improved, and energy consumption can be lowered.
Description
Technical field
The present invention relates to oil field machine adopts technical field, more specifically, it is related to a kind of oil field machine and adopts process dynamics and develop build
Mould and energy conservation optimizing method.
Background technology
It is a kind of mechanical oil production model that oil field machine recovers the oil, mainly by motor, ground drive apparatus and down-hole pumping unit
Three parts constitute.Oil field machine oil recovery process is broadly divided into upper and lower two strokes, and upstroke, i.e. horse head suspension point are moved upwards, need to be carried
Rod string and fluid column are played, motor need to consume substantial amounts of energy;Down stroke, i.e. horse head suspension point are moved downward, oil field machine roofbolt
Turn to pull and motor is done work.During roofbolt moves up and down, fluid column load generating period change so that oil field machine system
It is larger in aspect energy consumptions such as motor acting, transmission devices, so that system operating efficiency is low.
The content of the invention
In view of the above problems, it is an object of the invention to provide a kind of oil field machine adopts process dynamics evolutionary Modeling and energy saving optimizing
Method, to solve the problems, such as that above-mentioned background technology is proposed.
The oil field machine that the present invention is provided adopts process dynamics evolutionary Modeling and energy conservation optimizing method, including:
Step S1:Determine the efficiency affecting factors in the machine oil recovery process of oil field, constitute efficiency observation variables collection { x1,x2,
x3,L xn};And, the performance variable of oil field machine process system is chosen, performance observational variable set { y is constituted1,y2};
Wherein, x1For jig frequency decision variable, x2For effective stroke decision variable, x3~x5Respectively calculate pump efficiency environment to become
Amount, moisture content environmental variance, average power factor environmental variance, x6~xnIt is load environment variable;Performance Observation variable
Number l=2, y1For daily fluid production rate, y2For day power consumption;
Step S2:Variables collection { x is observed according to efficiency1,x2,x3,L xnAnd Performance Observation variables collection { y1,y2, adopt
Collection builds the sample value matrix [x of the observational variable of neural network model by ST-UKFNN algorithms1, x2L xn, y1, y2];Wherein,
The sampling period is set as T, during collection observational variable, if the sampling period is less than T, in the T cycles
Sample averaged is using the sample [I, Y] as the T cycles;If the sampling period is more than T, rejects the observation for collecting and become
Amount;Wherein, using the I in sample as input sample, using the Y in sample as output sample;
Step S3:Dimensionality reduction is carried out to load environment variable using pivot analysis algorithm, new load pivot variable is built
{Lz1,Lz2,...,Lzd};
Wherein, build new load pivot variable { Lz1,Lz2,...,LzdFor d load pivot component, each load master
The dimension of first component is identical with the quantity of sample [I, Y];
Step S4:Non- load variable and d load pivot component are reconfigured, new input sample I is built1, and to new
Input sample I1It is normalized with output sample Y, the sample after being normalizedWhich belongs to [- 1,1];Wherein,
Non- load variable includes jig frequency decision variable x1, effective stroke decision variable x2, calculate pump efficiency environmental variance x3, moisture content environment
Variable x4, average power factor environmental variance x5;
Step S5:Based on the sample after normalizationBuild the initial shape of neural network model and neural network model
State variable X, and, by the sample after normalizationInAs the input of neural network model, by the sample after normalization
ThisInAs the output of neural network model;
Wherein, neural network model is:
Wherein, IkFor the vector sample value of training sample, and as the input of neural network model,For network inputs
Connection weight of the layer to the neuron of hidden layer,For the threshold value of the neuron of network input layer to hidden layer,It is implicit
Connection weight of the layer to the neuron of network output layer,For the threshold value of hidden layer to the neuron of network output layer, wherein, i
=1,2 ... S0;J=1,2 ... S1;K=1,2 ... S2;S0For the quantity of the neuron of network input layer, S1For the god of network hidden layer
The quantity of Jing units, S2For the quantity of the neuron of network output layer;
Original state variable X is:
Step S6:The optimum state variable of neural network model is estimated using ST-UKFNN algorithms;
Step S7:Using optimum state variable as neural network modelWithReconstruct nerve net
Network expression formula, obtains oil field machine oil recovery process model;
Step S8:Build daily fluid production rate y1Preference function perfc(y);
Step S9:Using MOGA algorithms to daily fluid production rate y1Preference function perfc(y1) and day power consumption y2Carry out many mesh
The optimizing optimization of mark extreme value, obtains meeting the decision variable of produce reality;
Step S10:By the decision variable combining environmental variable after optimization, oil field machine oil recovery process model is brought into, calculate excellent
The systematic function of the decision variable after change, is compared with the mean value of the systematic function of actual sample, if determining after optimization
Mean value of the systematic function of plan variable more than the systematic function of actual sample, using the decision variable after optimization to actual production
Instructed;Otherwise repeat the above steps S1-S9, until the systematic function of the decision variable after optimization more than actual sample is
Till the mean value of system performance.
The oil field machine that the present invention is provided adopts process dynamics evolutionary Modeling and energy conservation optimizing method, is dug by ST-UKFNN algorithms
The production law of pick oil field machine, and MOGA algorithm optimizations oil field machine production process optimizing decision parameter is utilized, improve production process
Efficiency.
Description of the drawings
By reference to the explanation below in conjunction with accompanying drawing and the content of claims, and with to the present invention more comprehensively
Understand, other purposes and result of the present invention will be more apparent and should be readily appreciated that.In the accompanying drawings:
The contribution rate block diagram of former component based on Fig. 1;
Fig. 2 is daily fluid production rate fitted figure;
Fig. 3 is day power consumption fitted figure;
Preference function figures of the Fig. 4 for daily fluid production rate;
Fig. 5 is the Pareto disaggregation figures of daily fluid production rate preference value and day power consumption;
Fig. 6 is the Pareto disaggregation figures of daily fluid production rate actual value and day power consumption.
Specific embodiment
Name Resolution
ST-UKFNN:Strong Trace Unscented Kalman FilterNeuralNetwork, are followed the trail of without mark by force
Kalman filtering neutral net.
MOGA:Multi-objective genetic algorithm, multi-objective genetic algorithm
The oil field machine that the present invention is provided adopts process dynamics evolutionary Modeling and energy conservation optimizing method, including:
Step S1:Determine the efficiency affecting factors in the machine oil recovery process of oil field, constitute efficiency observation variables collection { x1,x2,
x3,L xn};And, the performance variable of oil field machine process system is chosen, performance observational variable set { y is constituted1,y2}。
Wherein, x1For jig frequency decision variable, x2For effective stroke decision variable, x3~x5Respectively calculate pump efficiency environment to become
Amount, moisture content environmental variance, average power factor environmental variance, x6~xnIt is load environment variable;Performance Observation variable
Number l=2, y1For daily fluid production rate, y2For day power consumption.
In the present invention, Performance Influence Factor is chosen as shown in table 1 with performance indications:
Table 1
Types of variables | Name variable |
Decision variable | Jig frequency |
Decision variable | Effective stroke |
Environmental variance | Calculate pump efficiency |
Environmental variance | Moisture content |
Environmental variance | Average power factor |
Environmental variance | Load |
Output variable | Daily fluid production rate |
Output variable | Day power consumption |
Step S2:Variables collection { x is observed according to efficiency1,x2,x3,L xnAnd Performance Observation variables collection { y1,y2, adopt
Collection builds the sample value matrix [x of the observational variable of neural network model by ST-UKFNN algorithms1, x2L xn, y1, y2]。
The sampling period is set as T, during collection observational variable, if the sampling period is less than T, in the T cycles
Sample averaged is using the sample [I, Y] as the T cycles, the i.e. sample of the observational variable of [I, Y] by neural network model
This value matrix [x1, x2L xn, y1, y2] obtain after averaged value;If the sampling period is more than T, illustrate there is showing for sample deficiency
As directly rejecting the observational variable for collecting, using the I in sample as input sample, using the Y in sample as output sample.
Sample [I, Y] is as shown in table 2:
Table 2
Step S3:Dimensionality reduction is carried out to load environment variable using pivot analysis algorithm, new load pivot variable is built
{Lz1,Lz2,...,Lzd}。
Wherein, build new load pivot variable { Lz1,Lz2,...,LzdFor d load pivot component, each load master
The dimension of first component is identical with the quantity of the sample [I, Y];
The present invention carries out setting up neutral net as component environment variable using 144 points of load that indicator card describes data
Model, sets up neural network model for parameter dimensions disaster using 144 dimension datas.So utilize pivot analysis algorithm
(Principal ComponentAnalysis, PCA) carries out dimension-reduction treatment to load environment variable, builds new load pivot
Variable, the set that new load pivot variable is constituted:{Lz1,Lz2,...,Lzd, which is d load pivot component, each pivot
Component dimension is identical with the quantity of sample [X, Y].The work(diagram data is made to be:Sample contribution rate of accumulative total is set
Precent=0.90;As shown in figure 1, obtaining the contribution rate and contribution rate of accumulative total of front 5 pivot components.
So, front 2 pivot component B1, B2 are taken as the characteristic variable of load environment variable, its partial value such as following table institute
Show:
3 partial pivot component data of table
Step S4:Non- load variable and d load pivot component are reconfigured, new input sample I is built1, and to new
Input sample I1It is normalized with output sample Y, the sample after being normalizedWhich belongs to [- 1,1];Wherein,
Non- load variable includes jig frequency decision variable x1, effective stroke decision variable x2, calculate pump efficiency environmental variance x3, moisture content environment
Variable x4, average power factor environmental variance x5。
Step S5:Based on the sample after normalizationBuild the initial shape of neural network model and neural network model
State variable X, and, by the sample after normalizationInAs the input of neural network model, by the sample after normalization
ThisInAs the output of neural network model;
Wherein, the neural network model of structure is:
Wherein, IkFor the vector sample value of training sample, and as the input of neural network model,For network inputs
Connection weight of the layer to the neuron of hidden layer,For the threshold value of network input layer to the neuron of the hidden layer,For hidden
Connection weight containing layer to the neuron of network output layer,For the threshold value of hidden layer to the neuron of network output layer, wherein,
I=1,2 ... S0;J=1,2 ... S1;K=1,2 ... S2;S0For the quantity of the neuron of network input layer, S1For network hidden layer
The quantity of neuron, S2For the quantity of the neuron of network output layer;
The original state variable X of structure is:
Step S6:State variable X of neural network model is estimated using ST-UKFNN algorithms, to obtain optimum state change
Amount, the weight threshold for completing institute's established model update so that resulting model more meets actual production process.
The process of the optimum state variable of neural network model is estimated using ST-UKFNN algorithms, including:
Step S61:Sigma samplings are carried out to original state variable X, 2n+1 sampled point, initialization control 2n+1 is obtained
The distribution parameter alpha of individual sampled point, parameter κ to be selected, and non-negative right factor beta, sample to the Sigma of original state variable X
It is as follows:
Wherein,For (k-1) moment optimum state variable i-th row, n be state matrix dimension, pk-1For (k-
1) covariance of the optimum state variable at moment.
Step S62:The weight of each sampled point is calculated, the weight of each sampled point is as follows:
Wherein, WcTo calculate the weight of the covariance of state variable, WmPower during to calculate state estimation and observation prediction
Weight,It isFirst row,It isFirst row.
Step S63:By the state equation of Discrete time Nonlinear Systems by the optimum at (k-1) moment of each sampled point
The state estimation of state variable is transformed to the state estimation of the state variable at k momentAnd, by the shape for merging the k moment
State is estimatedVector, obtain the k moment state variable state prior estimateWith covariance Pk|k-1;
The state estimation of the state variable at k momentFor:
Wherein, wkFor process noise, its covariance matrix QkFor cov (wk,wj)=Qkδkj,
The state prior estimate of the state variable at k momentFor:
Covariance P of the state variable at k momentk|k-1For:
Step S64:The state for setting up the state variable at k moment is estimated by the observational equation of Discrete time Nonlinear Systems
MeterObservation with the k moment is predictedContact with complete observation prediction, and estimate the k moment observation prediction association side
Difference
The average of the observation prediction at k momentFor:
Wherein,
Above-mentioned formula (8) and formula (9) establish the state estimation of the state variable at k momentObservation with the k moment is predicted
EstimateBetween relation.
Wherein, νkFor observation noise, its covariance matrix RkFor cov (vk,vj)=Rkδkj,
The covariance of the observation prediction at k momentFor:
Wherein, strong tracing algorithm, i.e. fading factor λ are introduced hereink+1Strengthen the trace ability of model to improve model essence
Degree;
Nk+1=Vk+1-βRk+1 (14)
Wherein, β is the reduction factor, β >=1;
Step S65:Calculate covariance P between the state variable at k moment and observation predictionxy,k:
Step S66:By setting up covariance Pxy,kWith covariance PykRelation, update the k moment state variable state
Estimate and covariance, obtain the optimum state variable at k moment.
Wherein, covariance P of the state variable of foundationxy,kWith covariance P of observation predictionykRelation be:
Wherein, KkFor gain matrix, when realizing the state estimation of the optimum state variable for updating the k moment and update k with this
Covariance P of the state variable at quarterk;And,
State estimation X of the state variable at the k moment after renewalkkFor:
Covariance P of the state variable at the k moment after renewalkFor:
Pk=λk+1Pk|k-1-KkPykKk T (20)
By state estimation X of the state variable at the k moment after renewalkWith covariance PkAs the optimum variable at k moment.
Step S67:The optimum state variable at the k moment of acquisition is substituted into into step S51 and re-starts sigma samplings, circulation
Step S61-S67, obtains the optimum state variable of neural network model.
The structural parameters of the optimum state variable of neural network model are as follows:
(1) daily fluid production rate model structure parameter
w2(1 × 20)=[- 0.06-0.63...-0.07-0.60] b2(1 × 1)=[2.42]
(2) day power consumption model structure parameter
w2(1 × 20)=[0.01 1.03 ... 1.04-0.21] b2(1 × 1)=[- 1.16]
Step S7:Using optimum state variable as neural network modelWithReconstruct nerve net
Network expression formula, obtains oil field machine oil recovery process model.
Constructed oil field machine oil recovery process model accuracy is as shown in Figures 2 and 3.
Step S8:Build daily fluid production rate y1Preference function perfc(y)。
In system process parameters optimization is calculated, it is considered to there are to different parameters different fancy grades, advised using physics
Draw constructing system preference function.Daily fluid production rate optimal value is set as y1best, setting value is ybest, in setting value ybestSurrounding is a certain
Contiguous range [ybest-△y,ybest+ △ y] in fluctuation for very satisfied (HD), and in [ybest-△y-△y1,ybest-△y],
[ybest+△y,ybest+△y+△y1] in for satisfied (D), be subjected to (T) successively, be unsatisfied with (U) and very dissatisfied
(HU), corresponding preference value is interval uses [1,2], and [2,4], [4,6], [6,8], [8,10] represent.
It is assumed that using the average daily fluid production rate of all samples as given daily fluid production rate and the preference value of fabulous degree
(47.38).The minimum of a value (40.22) and maximum (56.92) of all daily fluid production rate data are concurrently set as unacceptable domain
Critical value.So design preference degree interval is:[1,2], [2,4], [4,6], [6,8], [8,10] etc., and the preference for designing
The boundary value in the actual daily fluid production rate interval corresponding to interval border value is as shown in table 4,
Preference function is as shown in Figure 4.
The boundary value correspondence table of 4 preference function of table
Preference is interval | Daily fluid production rate left boundary value | Daily fluid production rate right boundary value |
[1,2] | [44.99,47.38] | [47.38,50.56] |
[2,4] | [43.25,44.99] | [50.56,52.89] |
[4,6] | [42.02,43.25] | [52.89,54.49] |
[6,8] | [41.07,42.02] | [54.49,55.79] |
[8,10] | [40.22,41.07] | [55.79,56.92] |
Fitting obtains the preference function of daily fluid production rate:
Step S9:Using MOGA algorithms to daily fluid production rate y1Preference function perfc(y1) and day power consumption y2Carry out many mesh
The optimizing optimization of mark extreme value, obtains meeting the decision variable of produce reality.
The process of optimization, including:
Step S91:By decision variable individuality P=[x1 x2 L xn] the comparison of fitness function value find optimal
Body;Wherein, the performance variable function of part maximizing is carried out renormalization acquisition multiple target fitness function is:
Wherein,It is the oil field machine oil recovery process model built by ST-UKFNN algorithms:
The characteristics of with reference to being most worth to the search of minimum of a value direction, the performance variable function of part maximizing is carried out into anti-normalizing
Change, so as to obtain fitness function, in the present invention, the daily fluid production rate obtained during being calculated due to optimization is closer to optimal
Value it is better, day power consumption it is more low better, renormalization is carried out by formula (22) and obtains formula (21).
Step S92:The mean value of the environmental variance of CALCULATING OILFIELD machine process system:
Wherein, environmental variance includes the calculating pump efficiency environmental variance x3, moisture content environmental variance x4, average power factor
Environmental variance x5, quantity of the N for the input sample of environmental variance.
5 environmental variance mean value table of table
Step S93:Using jig frequency decision variable x1With effective stroke decision variable x2Parent population P is built, wherein,
Wherein, K is the individuality in parent population PQuantity;L is initialized population sample
Quantity, L=50;GEN is maximum genetic algebra, GEN=100.
Step S94:According to bound x of decision variablei,min≤xi≤xi,max(i=1,2, L n) initialize father population P.
Wherein, the process of initialization father population P is:From jig frequency decision variable x1Span in random value giveFrom effective stroke decision variable x2Span in random value give
Step S95:Initialized father population P is carried out first time genetic iteration (GEN=1) to produce population of future generation.
The process of first time genetic iteration is carried out to initialized father population P, including:
Step S951:The being dominant property of each solution in initialized father population P is checked according to fitness function;Wherein, for
One solution i, its grade riEqual to 1 plus number n better than solution ii, i.e. ri=ni+1。
Due to the solution for not being better than noninferior solution in initialized father population P, so the grade of noninferior solution is equal to 1.
Step S952:By in initialized population P it is all it is individual be layered according to grade ascending order, then by with one it is linear
(or other) respective function to each individuality distribution one initial adaptive value.
Generally select make the adaptive value N individuality of grade (correspondence optimum) of distribution and 1 (corresponding to the individuality of worst grade) it
Between respective function.
Step S953:The mean value of the initial adaptive value of each individuality each grade Nei is calculated, the mean value is each etc.
The specified adaptive value of each individuality in level.
Step S954:By formula (25) calculate standardization in any one grade between any two individuality i and j away from
From:
Wherein, fs maxAnd fs minFor the maximum and minimum of a value of k-th object function.
Step S955:Being calculated by formula (26) has same grade r with solution iiEach solution dij;
Wherein, α=1 be Sharing Function, σshareFor default microhabitat radius;
Summation of each individual microhabitat number for Sharing Function value in the grade:
Wherein, μ (ri) for all grades be riNumber of individuals.
In order to keep the diversity solved in noninferior solution, microhabitat number is introduced in the individuality of each grade.
Step S956:The specified adaptive value of each individuality is obtained into the shared suitable of each individuality divided by respective microhabitat number
Should be worth.
Step S957:Change of scale is done to all individual shared adaptive values in each grade.
It is to keep the average of all individualities of each grade to the purpose that individual shared adaptive value does dimensional variation
Shared adaptive value specifies adaptive value identical with average, i.e., each individual identical probability is chosen to use.
Step S958:To carrying out through each grade of change of scale, ratio selection, single-point intersect, variation is calculated under obtaining
Generation population.
Step S96:GEN step S93~step S95 of circulation, obtains GEN and exports as optimum results for population;Its
In,
Pareto disaggregation is obtained, daily fluid production rate preference function is with day power consumption Pareto disaggregation as shown in figure 5, daily fluid production rate
Actual value is as shown in Figure 6 with the Pareto disaggregation of day power consumption.
Before and after optimization is understood by optimization gained Pareto solution set analysis, Contrast on effect is as shown in table 6:
6 Optimal Parameters of table correspondence object function exports contrast table with produce reality
The average loss-rate of producing of optimization lifts about 3%, has reached the effect of optimization of energy efficiency, has illustrated that this result is effective.
Step S10:Decision variable combining environmental variable after optimization, the oil field machine for bringing the foundation of ST-UKFNN algorithms into are adopted
Oily process model, the systematic function of the decision variable after calculation optimization are compared with the mean value of the systematic function of actual sample
Compared with if the systematic function of the decision variable after optimization is more than the mean value of the systematic function of actual sample, after optimization
Decision variable is instructed to actual production;Otherwise repeat the above steps S1-S9, until the systematicness of the decision variable after optimization
Till the mean value of the systematic function that can be more than actual sample.
Daily fluid production rate is the more superior and more good closer to the more low then effect of optimal value, day power consumption.
The above, the only specific embodiment of the present invention, but protection scope of the present invention is not limited thereto, any
Those familiar with the art the invention discloses technical scope in, change or replacement can be readily occurred in, should all be contained
Cover within protection scope of the present invention.Therefore, protection scope of the present invention described should be defined by scope of the claims.
Claims (4)
1. a kind of oil field machine adopts process dynamics evolutionary Modeling and energy conservation optimizing method, including:
Step S1:Determine oil field machine adopt during efficiency affecting factors, constitute efficiency observation variables collection { x1,x2,x3,L
xn};And, the performance variable of oil field machine process system is chosen, performance observational variable set { y is constituted1,y2};
Wherein, x1For jig frequency decision variable, x2For effective stroke decision variable, x3~x5Respectively calculate pump efficiency environmental variance, contain
Water rate environmental variance, average power factor environmental variance, x6~xnIt is load environment variable;Number l=of Performance Observation variable
2, y1For daily fluid production rate, y2For day power consumption;
Step S2:Variables collection { x is observed according to efficiency1,x2,x3,L xnAnd Performance Observation variables collection { y1,y2, collection is logical
Cross the sample value matrix [x that ST-UKFNN algorithms build the observational variable of neural network model1, x2L xn, y1, y2];Wherein,
The sampling period is set as T, during collection observational variable, if the sampling period is less than T, to the sample in the T cycles
Averaged is using the sample [I, Y] as the T cycles;If the sampling period is more than T, the observational variable for collecting is rejected;Its
In, using the I in sample as input sample, using the Y in sample as output sample;
Step S3:Dimensionality reduction is carried out to load environment variable using pivot analysis algorithm, new load pivot variable { L is builtz1,
Lz2,...,Lzd};
Wherein, build new load pivot variable { Lz1,Lz2,...,LzdFor d load pivot component, each load pivot point
The dimension of amount is identical with the quantity of the sample [I, Y];
Step S4:Non- load variable and d load pivot component are reconfigured, new input sample I is built1, and to new input
Sample I1It is normalized with output sample Y, the sample after being normalizedWhich belongs to [- 1,1];Wherein, non-load
Variable includes jig frequency decision variable x1, effective stroke decision variable x2, calculate pump efficiency environmental variance x3, moisture content environmental variance x4、
Average power factor environmental variance x5;
Step S5:Based on the sample after the normalizationBuild the initial of neural network model and the neural network model
State variable X, and, by the sample after the normalizationInAs the input of the neural network model, by institute
State the sample after normalizationInAs the output of the neural network model;
Wherein, the neural network model is:
Wherein, IkFor the vector sample value of the training sample, and as the input of the neural network model,It is defeated for network
Enter layer to the connection weight of the neuron of hidden layer,For the threshold value of network input layer to the neuron of the hidden layer,For
Connection weight of the hidden layer to the neuron of network output layer,For the nerve of the hidden layer to the network output layer
The threshold value of unit, wherein, i=1,2 ... S0;J=1,2 ... S1;K=1,2 ... S2;S0For the number of the neuron of the network input layer
Amount, S1For the quantity of the neuron of the network hidden layer, S2For the quantity of the neuron of the network output layer;
The original state variable X is:
Step S6:The optimum state variable of the neural network model is estimated using ST-UKFNN algorithms;
Step S7:Using the optimum state variable as the neural network modelWithReconstruct god
Jing network expressions, obtain oil field machine oil recovery process model;
Step S8:Build daily fluid production rate y1Preference function perfc(y1);
Step S9:Using MOGA algorithms to daily fluid production rate y1Preference function perfc(y1) and day power consumption y2Carry out multiple target pole
Value optimizing optimization, obtains meeting the decision variable of produce reality;
Step S10:By the decision variable combining environmental variable after optimization, the oil field machine oil recovery process model is brought into, calculate excellent
The systematic function of the decision variable after change, is compared with the mean value of the systematic function of actual sample, if determining after optimization
Mean value of the systematic function of plan variable more than the systematic function of actual sample, using the decision variable after optimization to actual production
Instructed;Otherwise repeat the above steps S1-S9, until the systematic function of the decision variable after optimization more than actual sample is
Till the mean value of system performance.
2. oil field machine as claimed in claim 1 adopts process dynamics evolutionary Modeling and energy conservation optimizing method, and step S6 includes:
Step S61:Sigma samplings are carried out to the original state variable X, 2n+1 sampled point, initialization control 2n+1 is obtained
The distribution parameter alpha of individual sampled point, parameter κ to be selected, and non-negative right factor beta, the Sigma to the original state variable X
Sampling is as follows:
Wherein,For (k-1) moment optimum state variable estimate i-th row, n be state matrix dimension, pk-1For (k-
1) covariance of the optimum state variable at moment;
Step S62:The weight of each sampled point is calculated, the weight of each sampled point is as follows:
Wherein, WcTo calculate the weight of the covariance of state variable, WmWeight during to calculate state estimation and observation prediction,It isFirst row,It isFirst row;
Step S63:By the state equation of Discrete time Nonlinear Systems by the optimum state at (k-1) moment of each sampled point
The state estimation of variable is transformed to the state estimation of the state variable at k momentAnd by merging the state estimation at k momentVector, obtain the k moment state variable state prior estimateAnd covarianceWherein,
The state estimationFor:
Wherein, wkFor process noise, its covariance matrix QkFor cov (wk,wj)=Qkδkj,
The state prior estimateFor:
Covariance P of the state variablek|k-1For:
Step S64:The state estimation of the state variable at k moment is set up by the observational equation of Discrete time Nonlinear SystemsWith the observation predicted estimate at k momentBetween contact with complete observation prediction, and estimate the k moment observation prediction
Covariance Pyk;
The average of the observation prediction at the k momentFor:
Wherein,
Wherein, νkFor observation noise, its covariance matrix RkFor cov (vk,vj)=Rkδkj,
Covariance P of the observation prediction at the k momentykFor:
Wherein, above-mentioned formula λk+1For fading factor,
Nk+1=Vk+1-βRk+1 (14)
Wherein, β is the reduction factor (β >=1);
Wherein, ρ ∈ (0,1);
Step S65:Calculate covariance P between the state variable at k moment and observation predictionxy,k:
Step S66:By setting up covariance Pxy,kWith covariance PykRelation, update the k moment state variable state estimation
And covariance, obtain the optimum state variable at k moment;
Step S67:The optimum state variable at the k moment of acquisition is substituted into into step S61 and re-starts sigma samplings, circulation step
S61-S67, obtains the optimum state variable of the neural network model.
3. oil field machine as claimed in claim 2 adopts process dynamics evolutionary Modeling and energy conservation optimizing method;Wherein, in step S66
Covariance P of the state variable of foundationxy,kWith covariance P of observation predictionykRelation be:
Wherein, KkFor gain matrix, the state estimation of the optimum state variable for updating the k moment is realized with this and the shape at k moment is updated
Covariance P of state variablek;And,
State estimation X of the optimum state variable at the k moment after renewalk|kFor:
Covariance P of the state variable at the k moment after renewalkFor:
Pk=λk+1Pk|k-1-KkPykKk T (20)
By state estimation X of the state variable at the k moment after renewalkWith covariance PkAs the optimum state variable at k moment.
4. oil field machine as claimed in claim 1 adopts process dynamics evolutionary Modeling and energy conservation optimizing method, wherein, step S9 bag
Include:
Step S91:By decision variable individuality P=[x1x2L xn] fitness function value comparison find optimized individual;Its
In, the performance variable function of part maximizing is carried out renormalization acquisition fitness function is:
Wherein,It is the oil field machine oil recovery process model built by ST-UKFNN algorithms:
Step S92:The mean value of the environmental variance of the oil field machine process system is calculated by formula (23):
Wherein, the environmental variance includes the calculating pump efficiency environmental variance x3, the moisture content environmental variance x4, it is described average
Power factor environmental variance x5, N is the quantity of the input sample of the environmental variance;
Step S93:Using the jig frequency decision variable x1With the effective stroke decision variable x2Parent population P is built, wherein,
Wherein, K is the individuality in parent population PQuantity;L is initialized population sample size,
L=50;GEN is maximum genetic algebra, GEN=100;
Step S94:According to bound x of decision variablei,min≤xi≤xi,max(i=1,2, L n) initialize father population P;Wherein,
Initialization father population P process be:From the jig frequency decision variable x1Span in random value giveFrom the effective stroke decision variable x2Span in random value give
Step S95:Initialized father population P is carried out first time genetic iteration (GEN=1) to produce population of future generation;To first
The father population P of beginningization carries out the process of first time genetic iteration, including:
Step S951:The being dominant property of each solution in initialized father population P is checked according to fitness function;Wherein, for one
Solution i, its grade riEqual to 1 plus number n better than solution ii, i.e. ri=ni+1;
Step S952:By in initialized father population P it is all it is individual be layered according to grade ascending order, then by with one it is linear
Respective function is to each individuality one initial adaptive value of distribution;
Step S953:The mean value of the initial adaptive value of each individuality each grade Nei is calculated, the mean value is in each grade
The specified adaptive value of each individuality;
Step S954:Standardization distance in any one grade between any two individuality i and j is calculated by formula (25):
Wherein,WithFor the maximum and minimum of a value of k-th object function;
Step S955:Being calculated by formula (26) has same grade r with solution iiEach solution dij;
Wherein, α=1, σshareFor default microhabitat radius;
Summation of each individual microhabitat number for Sharing Function value in the grade:
Wherein, μ (ri) for all grades be riNumber of individuals;
Step S956:The specified adaptive value of each individuality is obtained into the shared adaptation of each individuality divided by respective microhabitat number
Value;
Step S957:Change of scale is done to all individual shared adaptive values in each grade;
Step S958:Ratio selection, single-point intersection, the variation calculating acquisition next generation are carried out to each grade through change of scale
Population;
Step S96:GEN=GEN+1, circulates 100 step S93~steps S95, obtains GEN for population as optimum results
Output;Wherein,
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610999735.9A CN106530130A (en) | 2016-11-14 | 2016-11-14 | Dynamic evolutionary modeling and energy-saving optimization method of oil extraction process of oil field machine |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610999735.9A CN106530130A (en) | 2016-11-14 | 2016-11-14 | Dynamic evolutionary modeling and energy-saving optimization method of oil extraction process of oil field machine |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106530130A true CN106530130A (en) | 2017-03-22 |
Family
ID=58351538
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610999735.9A Pending CN106530130A (en) | 2016-11-14 | 2016-11-14 | Dynamic evolutionary modeling and energy-saving optimization method of oil extraction process of oil field machine |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106530130A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108776831A (en) * | 2018-05-15 | 2018-11-09 | 中南大学 | A kind of complex industrial process Data Modeling Method based on dynamic convolutional neural networks |
CN108804721A (en) * | 2017-04-26 | 2018-11-13 | 重庆科技学院 | Based on the Fault Diagnoses of Oil Pump method adaptively without mark Kalman filter and RBF neural |
-
2016
- 2016-11-14 CN CN201610999735.9A patent/CN106530130A/en active Pending
Non-Patent Citations (1)
Title |
---|
No relevant documents disclosed * |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108804721A (en) * | 2017-04-26 | 2018-11-13 | 重庆科技学院 | Based on the Fault Diagnoses of Oil Pump method adaptively without mark Kalman filter and RBF neural |
CN108804721B (en) * | 2017-04-26 | 2021-09-14 | 重庆科技学院 | Oil pumping machine fault diagnosis method based on self-adaptive unscented Kalman filtering and RBF neural network |
CN108776831A (en) * | 2018-05-15 | 2018-11-09 | 中南大学 | A kind of complex industrial process Data Modeling Method based on dynamic convolutional neural networks |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107730006B (en) | Building near-zero energy consumption control method based on renewable energy big data deep learning | |
CN106777866A (en) | Technology Modeling and optimization method are purified towards energy-saving high sulfur-containing natural gas | |
CN105045941B (en) | Pumping unit parameter optimization method based on Unscented kalman filtering | |
CN106779148B (en) | A kind of method for forecasting wind speed of high speed railway line of multi-model multiple features fusion | |
Zarei et al. | Study on parameters effective on the performance of a humidification-dehumidification seawater greenhouse using support vector regression | |
CN101980298B (en) | Multi-agent genetic clustering algorithm-based image segmentation method | |
CN108954680A (en) | A kind of air-conditioning energy consumption prediction technique based on operation data | |
CN106869990B (en) | Coal gas Permeability Prediction method based on LVQ-CPSO-BP algorithm | |
CN105046326A (en) | Oil pumping unit parameter optimization method based on indicator diagram principal component analysis | |
CN110807544B (en) | Oil field residual oil saturation distribution prediction method based on machine learning | |
CN109492748B (en) | Method for establishing medium-and-long-term load prediction model of power system based on convolutional neural network | |
CN102609766B (en) | Method for intelligently forecasting wind speed in wind power station | |
Karkevandi-Talkhooncheh et al. | Application of hybrid adaptive neuro-fuzzy inference system in well placement optimization | |
CN106355003B (en) | Markov chain Monte-Carlo automatic history matching method and system based on t distributions | |
CN106529042A (en) | Computational intelligence-based oilfield mining parameter dynamic evolution modeling and optimizing method | |
CN104951847A (en) | Rainfall forecast method based on kernel principal component analysis and gene expression programming | |
CN104680025A (en) | Oil pumping unit parameter optimization method on basis of genetic algorithm extreme learning machine | |
CN103903072A (en) | High-dimensional multi-target set evolutionary optimization method based on preference of decision maker | |
CN106502096B (en) | Oil field machine based on preference multiple-objection optimization adopts process decision parameter optimization method | |
CN103793887A (en) | Short-term electrical load on-line predicting method based on self-adaptation enhancing algorithm | |
CN106530130A (en) | Dynamic evolutionary modeling and energy-saving optimization method of oil extraction process of oil field machine | |
CN109583588A (en) | A kind of short-term wind speed forecasting method and system | |
Wang et al. | A new approach of obtaining reservoir operation rules: Artificial immune recognition system | |
CN104732067A (en) | Industrial process modeling forecasting method oriented at flow object | |
CN104680023A (en) | Multi-objective-decision-based pumping unit parameter optimization method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | 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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170322 |