CN106530130A - Dynamic evolutionary modeling and energy-saving optimization method of oil extraction process of oil field machine - Google Patents

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

Oil field machine adopts process dynamics evolutionary Modeling and energy conservation optimizing method

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 x_n}；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～x_nIt 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 x_nAnd 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 x_n, 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 {L_z1,L_z2,...,L_zd}；

Wherein, build new load pivot variable { L_z1,L_z2,...,L_zdFor 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, I_kFor 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 perf_c(y)；

Step S9：Using MOGA algorithms to daily fluid production rate y₁Preference function perf_c(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 x_n}；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～x_nIt 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 x_nAnd 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 x_n, 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 x_n, 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 {L_z1,L_z2,...,L_zd}。

Wherein, build new load pivot variable { L_z1,L_z2,...,L_zdFor 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:{L_z1,L_z2,...,L_zd, 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, I_kFor 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, p_k-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, W_cTo calculate the weight of the covariance of state variable, W_mPower 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 P_k|k-1；

The state estimation of the state variable at k momentFor：

Wherein, w_kFor process noise, its covariance matrix Q_kFor cov (w_k,w_j)=Q_kδ_kj,

The state prior estimate of the state variable at k momentFor：

Covariance P of the state variable at k moment_k|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, ν_kFor observation noise, its covariance matrix R_kFor cov (v_k,v_j)=R_kδ_kj,

The covariance of the observation prediction at k momentFor：

Wherein, strong tracing algorithm, i.e. fading factor λ are introduced herein_k+1Strengthen the trace ability of model to improve model essence Degree；

N_k+1=V_k+1-βR_k+1 (14)

Wherein, β is the reduction factor, β >=1；

Step S65：Calculate covariance P between the state variable at k moment and observation prediction_xy,k：

Step S66：By setting up covariance P_xy,kWith covariance P_ykRelation, 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 foundation_xy,kWith covariance P of observation prediction_ykRelation be：

Wherein, K_kFor 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 quarter_k；And,

State estimation X of the state variable at the k moment after renewal_kkFor：

Covariance P of the state variable at the k moment after renewal_kFor：

P_k=λ_k+1P_k|k-1-K_kP_ykK_k ^T (20)

By state estimation X of the state variable at the k moment after renewal_kWith covariance P_kAs 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 perf_c(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 y_1best, setting value is y_best, in setting value y_bestSurrounding is a certain Contiguous range [y_best-△y,y_best+ △ y] in fluctuation for very satisfied (HD), and in [y_best-△y-△y₁,y_best-△y], [y_best+△y,y_best+△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 perf_c(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 x_n] 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 variable_i,min≤x_i≤x_i,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 r_iEqual to 1 plus number n better than solution i_i, i.e. r_i=n_i+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, f_s ^maxAnd f_s ^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 i_iEach solution d_ij；

Wherein, α=1 be Sharing Function, σ_shareFor default microhabitat radius；

Summation of each individual microhabitat number for Sharing Function value in the grade：

Wherein, μ (r_i) for all grades be r_iNumber 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 x_n}；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～x_nIt 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 x_nAnd 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 x_n, 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 built_z1, L_z2,...,L_zd}；

Wherein, build new load pivot variable { L_z1,L_z2,...,L_zdFor 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：

$Y=\underset{j=1}{\overset{s_2}{\Σ}}\left(f\right(\underset{i=1}{\overset{S_1}{\Σ}}{w}_{ik}^1{I}_k+b_i^1\left)\right)\·w_{kj}^2+b_j^2---\left(1\right)$

Wherein, I_kFor 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：

$X={\left[\begin{array}{cccccccc}{w}_{11}^{1}L& w_{s_0{s}_1}^1& b_1^{1}L& b_{s_1}^1& w_{11}^{2}L& w_{s_1{s}_2}^2& b_1^{2}L& b_{s_2}^2\end{array}\right]}^T---\left(2\right)$

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 perf_c(y₁)；

Step S9：Using MOGA algorithms to daily fluid production rate y₁Preference function perf_c(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：

$\left\{\begin{array}{c}{\hat{X}}_{k-1|k-1}^{\left(i\right)}=X_{k-1}+\sqrt{(n+\mathrm{\λ})p_{k-1}},i=1:n\\ {\hat{X}}_{k-1|k-1}^{\left(i\right)}=X_{k-1}-\sqrt{(n+\mathrm{\λ})p_{k-1}},i=n+1:2n\\ \mathrm{\λ}=a^2(n+\mathrm{\κ})-n\end{array}\right.---\left(3\right)$

Wherein,For (k-1) moment optimum state variable estimate i-th row, n be state matrix dimension, p_k-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：

$\left\{\begin{array}{c}{W}_m^{\left(0\right)}=\mathrm{\λ}/(n+\mathrm{\λ})\\ W_c^{\left(0\right)}=\mathrm{\λ}/(n+\mathrm{\λ})+(1-{\mathrm{\α}}^2+\mathrm{\β})\\ W_m^{\left(i\right)}=W_c^{\left(i\right)}=\mathrm{\λ}/(2\×(n+\mathrm{\λ}\left)\right),i=1:2n\end{array}\right.---\left(4\right)$

Wherein, W_cTo calculate the weight of the covariance of state variable, W_mWeight 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：

$X_{k|k-1}^{\left(i\right)}=F\left(X_{k-1|k-1}^{\left(i\right)}\right)+w_k---\left(5\right)$

Wherein, w_kFor process noise, its covariance matrix Q_kFor cov (w_k,w_j)=Q_kδ_kj,

The state prior estimateFor：

${\hat{X}}_{k|k-1}=\underset{i=0}{\overset{2n}{\Σ}}{W}_m^{\left(i\right)}\·X_{k|k-1}^{\left(i\right)}---\left(6\right)$

Covariance P of the state variable_k|k-1For：

$P_{k|k-1}=\underset{i=0}{\overset{2n}{\Σ}}{W}_c^{\left(i\right)}\·(X_{k|k-1}^{\left(i\right)}-{\hat{X}}_{k|k-1}){(X_{k|k-1}^{\left(i\right)}-{\hat{X}}_{k|k-1})}^T+Q_{K-1}---\left(7\right)$

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 P_yk；

The average of the observation prediction at the k momentFor：

${\hat{Y}}_{k|k-1}=\underset{i=0}{\overset{2n}{\Σ}}{W}_m^{\left(i\right)}\·Y_{k|k-1}^{\left(i\right)}+v_k---\left(8\right)$

Wherein,

Wherein, ν_kFor observation noise, its covariance matrix R_kFor cov (v_k,v_j)=R_kδ_kj,

${\mathrm{\δ}}_{kj}=\left\{\begin{array}{cc}0& k\≠j\\ 1& k=j\end{array}\right.;$

Covariance P of the observation prediction at the k moment_ykFor：

$P_{y_k}={\mathrm{\λ}}_{k+1}\underset{i=0}{\overset{2n}{\Σ}}{W}_c^{\left(i\right)}\·(Y_{k|k-1}^{\left(i\right)}-{\hat{Y}}_{k|k-1}){(Y_{k|k-1}^{\left(i\right)}-{\hat{Y}}_{k|k-1})}^T+R_k---\left(10\right)$

Wherein, above-mentioned formula λ_k+1For fading factor,

${\mathrm{\λ}}_{k+1}=\left\{\begin{array}{cc}{\mathrm{\λ}}_0,& {\mathrm{\λ}}_0>1\\ 1,& {\mathrm{\λ}}_0\≤1\end{array}\right.---\left(11\right)$

${\mathrm{\λ}}_0=\frac{tr{N}_{k+1}}{tr{M}_{k+1}}---\left(12\right)$

$M_{k+1}=\underset{i=0}{\overset{2n}{\Σ}}{W}_c^{\left(i\right)}\·(Y_{k|k-1}^{\left(i\right)}-{\hat{Y}}_{k|k-1}){(Y_{k|k-1}^{\left(i\right)}-{\hat{Y}}_{k|k-1})}^T+R_k---\left(13\right)$

N_k+1=V_k+1-βR_k+1 (14)

Wherein, β is the reduction factor (β >=1)；

$V_{k+1}=\left\{\begin{array}{cc}{e}_k{e}_k^T& k=0\\ \frac{{\mathrm{\ρV}}_k+e_k{e}_k^T}{1+\mathrm{\ρ}}& k\≥1\end{array}\right.---\left(15\right)$

$e_k=Y_{k|k-1}^{\left(i\right)}-\underset{i=0}{\overset{2n}{\Σ}}{W}_m^{\left(i\right)}\·g\left(\underset{k=1}{\overset{s_2}{\Σ}}\right(f\left(\underset{i=1}{\overset{S_1}{\Σ}}{w}_{ji}^1{X}_{k|k-1}^{\left(i\right)}+b_j^1\right))\·w_{kj}^2+b_k^2)---\left(16\right)$

Wherein, ρ ∈ (0,1)；

Step S65：Calculate covariance P between the state variable at k moment and observation prediction_xy,k：

$P_{xy,k}={\mathrm{\λ}}_{k+1}\underset{i=0}{\overset{2n}{\Σ}}{W}_c^{\left(i\right)}\·(X_{k|k-1}^{\left(i\right)}-{\hat{X}}_{k|k-1}){(Y_{k|k-1}^{\left(i\right)}-{\hat{Y}}_{k+1})}^T---\left(17\right)$

Step S66：By setting up covariance P_xy,kWith covariance P_ykRelation, 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 foundation_xy,kWith covariance P of observation prediction_ykRelation be：

$K_k=\frac{P_{xy,k}}{P_{y,k}}---\left(18\right)$

Wherein, K_kFor 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 variable_k；And,

State estimation X of the optimum state variable at the k moment after renewal_k|kFor：

$X_{k|k}=X_k={\hat{X}}_{k|k-1}+K_k(Y_k-{\hat{Y}}_{k|k-1})---\left(19\right)$

Covariance P of the state variable at the k moment after renewal_kFor：

P_k=λ_k+1P_k|k-1-K_kP_ykK_k ^T (20)

By state estimation X of the state variable at the k moment after renewal_kWith covariance P_kAs 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 x_n] fitness function value comparison find optimized individual；Its In, the performance variable function of part maximizing is carried out renormalization acquisition fitness function is：

$objFun\left(X\right)=\left[\begin{array}{cc}{\mathrm{perf}}_c\left(g^{-1}\right({\hat{y}}_1\left(f\right(X)\left)\right))& g^{-1}\left({\hat{y}}_2\right(f\left(X\right)\left)\right)\end{array}\right]---\left(21\right)$

Wherein,It is the oil field machine oil recovery process model built by ST-UKFNN algorithms：

$\hat{Y}\left(X\right)={\left[\begin{array}{cc}{\hat{y}}_1\left(X\right)& {\hat{y}}_2\left(X\right)\end{array}\right]}^T---\left(22\right)$

Step S92：The mean value of the environmental variance of the oil field machine process system is calculated by formula (23)：

${\stackrel{\‾}{x}}_i=\frac{1}{N}\underset{k=1}{\overset{N}{\Σ}}{x}_{ik},i=3,L,M---\left(23\right)$

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,

$P=\left\{(x_{1m}^P,x_{2m}^P)\right|1\≤m\≤K\}---\left(24\right)$

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 variable_i,min≤x_i≤x_i,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 r_iEqual to 1 plus number n better than solution i_i, i.e. r_i=n_i+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)：

$d_{ij}=\sqrt{\underset{s=1}{\overset{k}{\Σ}}{\left(\frac{f_s^{\left(i\right)}-f_s^{\left(j\right)}}{f_s^{max}-f_s^{min}}\right)}^2}---\left(25\right)$

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 i_iEach solution d_ij；

Wherein, α=1, σ_shareFor default microhabitat radius；

Summation of each individual microhabitat number for Sharing Function value in the grade：

${\mathrm{nc}}_i=\underset{j=1}{\overset{r\left(r_i\right)}{\Σ}}sh\left(d_{ij}\right)---\left(27\right)$

Wherein, μ (r_i) for all grades be r_iNumber 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,