AU2020103709A4 - A modified particle swarm intelligent optimization method for solving high-dimensional optimization problems of large oil and gas production systems - Google Patents
A modified particle swarm intelligent optimization method for solving high-dimensional optimization problems of large oil and gas production systems Download PDFInfo
- Publication number
- AU2020103709A4 AU2020103709A4 AU2020103709A AU2020103709A AU2020103709A4 AU 2020103709 A4 AU2020103709 A4 AU 2020103709A4 AU 2020103709 A AU2020103709 A AU 2020103709A AU 2020103709 A AU2020103709 A AU 2020103709A AU 2020103709 A4 AU2020103709 A4 AU 2020103709A4
- Authority
- AU
- Australia
- Prior art keywords
- particle
- value
- formula
- calculating
- gas production
- 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.)
- Ceased
Links
- 239000002245 particle Substances 0.000 title claims abstract description 224
- 238000005457 optimization Methods 0.000 title claims abstract description 108
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 69
- 238000000034 method Methods 0.000 title claims abstract description 48
- 230000035772 mutation Effects 0.000 claims abstract description 38
- 238000009826 distribution Methods 0.000 claims abstract description 18
- 238000004260 weight control Methods 0.000 claims abstract description 14
- 230000003044 adaptive effect Effects 0.000 claims abstract description 8
- 238000004364 calculation method Methods 0.000 claims abstract description 8
- NAWXUBYGYWOOIX-SFHVURJKSA-N (2s)-2-[[4-[2-(2,4-diaminoquinazolin-6-yl)ethyl]benzoyl]amino]-4-methylidenepentanedioic acid Chemical compound C1=CC2=NC(N)=NC(N)=C2C=C1CCC1=CC=C(C(=O)N[C@@H](CC(=C)C(O)=O)C(O)=O)C=C1 NAWXUBYGYWOOIX-SFHVURJKSA-N 0.000 claims abstract description 7
- 238000001739 density measurement Methods 0.000 claims abstract description 7
- 239000013598 vector Substances 0.000 claims description 46
- 238000013178 mathematical model Methods 0.000 claims description 4
- 238000013461 design Methods 0.000 abstract description 7
- 230000008569 process Effects 0.000 abstract description 7
- 230000006872 improvement Effects 0.000 abstract description 6
- 238000004134 energy conservation Methods 0.000 abstract description 4
- 230000009467 reduction Effects 0.000 abstract description 4
- 230000004069 differentiation Effects 0.000 abstract 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 20
- 239000000243 solution Substances 0.000 description 19
- 238000005265 energy consumption Methods 0.000 description 12
- 230000006870 function Effects 0.000 description 12
- 238000002347 injection Methods 0.000 description 9
- 239000007924 injection Substances 0.000 description 9
- 238000004065 wastewater treatment Methods 0.000 description 9
- 238000006073 displacement reaction Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 239000007788 liquid Substances 0.000 description 4
- 239000010865 sewage Substances 0.000 description 3
- 241000607479 Yersinia pestis Species 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- 239000002351 wastewater Substances 0.000 description 2
- 241000251468 Actinopterygii Species 0.000 description 1
- 101100493820 Caenorhabditis elegans best-1 gene Proteins 0.000 description 1
- 101100233056 Caenorhabditis elegans ima-2 gene Proteins 0.000 description 1
- 101100129500 Caenorhabditis elegans max-2 gene Proteins 0.000 description 1
- 101100328154 Mus musculus Clmn gene Proteins 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000003129 oil well Substances 0.000 description 1
- BULVZWIRKLYCBC-UHFFFAOYSA-N phorate Chemical compound CCOP(=S)(OCC)SCSCC BULVZWIRKLYCBC-UHFFFAOYSA-N 0.000 description 1
- 230000002028 premature Effects 0.000 description 1
- 238000012545 processing 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Forestry; Mining
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/25—Design optimisation, verification or simulation using particle-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N7/00—Computing arrangements based on specific mathematical models
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Business, Economics & Management (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Mining & Mineral Resources (AREA)
- Computing Systems (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Agronomy & Crop Science (AREA)
- Animal Husbandry (AREA)
- Marine Sciences & Fisheries (AREA)
- Molecular Biology (AREA)
- Artificial Intelligence (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of cross design of energy conservation,
consumption reduction, capital reduction, efficiency improvement and intelligent
calculation of an oil and gas production system, in particular to an modified particle
swarm intelligent optimization method for solving high-dimensional optimization
problems of large oil and gas production systems. The specific technical scheme is as
follows: an modified particle swarm intelligent optimization method for solving high
dimensional optimization problems of large oil and gas production systems, which
according to the solution principle of standard particle swarm algorithm, the high
dimensional optimum problem solution mode and the obvious characteristic that
information differentiation among multi-variables, provides three improved operators
and corresponding optimization solution processes of the adaptive Cauchy disturbance
operator, the leaming-type Gaussian mutation operator and the adjustment operator by
probability, in order to solve the problems that the standard particle swarm algorithm is
easy to fall into local optimum, low in convergence speed and poor in robustness when
comes to solve the high-dimensional optimization problem, so as to meet the technical
urgent need of optimization design of complex large-scale oil and gas production
systems.
-1/3
By applying the feasibility criterion, the optimization model of
the large-scale oil and gas production system is disposed.
Initializing the parameters of population size, the termination
condition, the basic parameters of PSO algorithm, and the basic
parameters ofmodified onerators.
Generating the initial particle population of large-scale oil and gas
production system, determining the optimal particle and the
history optimal particle ofthe initial particle population
Updating the speed and locationofallthe
particles
Yes Are the constraints
satisfied?
No
Adjusting the speed and the
Position of articles
Calculating the fitness value, updating the
current optimalrtileaccle and the historical
optimal particle
Whether to Optimal scheme for the
terminate? yes u e large-scale oil and gas
<
production system
O
Calculating the Cauchy distribution position control parameter according to the
formula (1), generating the disturbance offsets according to the formula (2),
updating the current optimal particle according to the formula (3)
Arranging the fitness values of the particles in a descending order,
randomly select some particles with low fitness values to perform
Gaussian mutation operator according to the formula (4) and (5)
According to formulas (6), (7) and (8), respectively, calculating the weight control
factor, the particle adjustment control value and the density measurement factor,
judging whether the adjustment probability is smaller than a random number by
adopting the formula (9), if so, adjusting particles according to the formula (10)
Calculating the fitness value, updating the
current global optimal particle and the
historical optimal particle
Figure 1
Description
-1/3
By applying the feasibility criterion, the optimization model of the large-scale oil and gas production system is disposed. Initializing the parameters of population size, the termination condition, the basic parameters of PSO algorithm, and the basic parameters ofmodified onerators.
Generating the initial particle population of large-scale oil and gas production system, determining the optimal particle and the history optimal particle ofthe initial particle population
Updating the speed and locationofallthe particles
Yes Are the constraints satisfied?
No
Adjusting the speed and the Position of articles
Calculating the fitness value, updating the current optimalrtileaccle and the historical optimal particle
Whether to Optimal scheme for the terminate? yes u e large-scale oil and gas
production system < O
Calculating the Cauchy distribution position control parameter according to the formula (1), generating the disturbance offsets according to the formula (2), updating the current optimal particle according to the formula (3)
Arranging the fitness values of the particles in a descending order, randomly select some particles with low fitness values to perform Gaussian mutation operator according to the formula (4) and (5)
According to formulas (6), (7) and (8), respectively, calculating the weight control factor, the particle adjustment control value and the density measurement factor, judging whether the adjustment probability is smaller than a random number by adopting the formula (9), if so, adjusting particles according to the formula (10)
Calculating the fitness value, updating the current global optimal particle and the historical optimal particle
Figure 1
A modified particle swarm intelligent optimization method for solving
high-dimensional optimization problems of large oil and gas production systems
The invention relates to the technical field of cross design of energy conservation,
consumption reduction, capital reduction, efficiency improvement and intelligent
calculation of the oil and gas production system, in particular to an modified particle
swarm intelligent optimization method for solving high-dimensional optimization
problems of large oil and gas production systems.
In the field of intelligent calculation technology, some scholars have invented
intelligent optimization algorithms such as particle swarm algorithm, ant swarm
algorithm, bee swarm algorithm, fish swarm algorithm, among which the particle
swarm algorithm is applied to the solution and analysis of various engineering
problems with the advantages of simple algorithm structure and capability of parallel
calculation.
With the increasing complexity of multi-system collaborative general
optimization, large-scale layout optimization and multi-parameters operation
optimization in the oil and gas production filed, many high-dimensional optimization
problems need to be solved urgently. In the process of solving the high-dimensional
optimization problems of standard particle swarm algorithm, because the searching
ability of the optimal particle for the better solution is insufficient, and because of the
mutual attraction between the particles, the population is difficult to jump out after
being gathered around the local optimum, so that the algorithm converges early, and the condition that the algorithm does not converge even occurs when the parameters of the algorithm are not set properly.
The research results of particle swarm optimization at home and abroad mainly focus on the adjustment of inertia weight, the optimization of algorithm steps, the change of speed updating mode, etc. These optimization improvements improve the solution accuracy and convergence speed to a certain extent, but the global search of the whole solution space is not realized under the mode that the optimal particle controls the evolution process of the population, especially the optimization performance improvement research of the particle swarm optimization based on the high-dimensional characteristic is scarce. Moreover, the relative distribution and dimension information of particles are not utilized effectively, which leads to the unsatisfactory results of the existing improved particle swarm optimization methods in solving high-dimensional oil and gas production optimization problems.
Aiming at the defects of the prior art, the invention provides an modified particle swarm intelligent optimization method for solving high-dimensional optimization problems of large oil and gas production systems, which solves the problems that standard particle swarm algorithm is easy to fall into local optimum, the convergence speed is low, and the cooperative solution effect of large-scale variables is poor.
In order to achieve the above purpose, the invention is realized by the following technical scheme:
The modified particle swarm intelligent optimization method for solving high-dimensional optimization problems of large oil and gas production systems comprises the following steps:
Step 1: converting the constrained high-dimensional large-scale oil and gas
production system optimization mathematical model into the objective function for
evaluating the decision scheme and the constraints for judging whether the scheme is
feasible according to the feasibility criterion, initializing control parameters of the
modified particle swarm optimization method, including standard particle swarm
algorithm parameters, the adaptive Cauchy disturbance operator parameters, the
learning-type Gaussian mutation operator parameters, the parameters of adjustment
operator by probability, the population scale parameter and termination condition
parameter.
Step 2: generating the initial particle population of the large-scale oil and gas
production system optimization problem, calculating the fitness value, and storing the
initial history optimal individual pbest(0) and current global optimal individual
gbest(O) .
Step 3: updating the speed v(t) and the position x,(t) of the each particle, and
the updated particle population is obtained.
Step 4: judging whether the constraint conditions are satisfied, if so, turning to
step 5, otherwise, adjusting the particles which do not accord with the constraint
conditions, and then turning to step 5;
Step 5: calculating the fitness value of the updated particle population, and
updating the historical optimal particle pest, and the optimal particle best.
Step 6: judging whether the termination conditions are met, if so, turning to step
11, if not, turning to step 7.
Step 7: executing the adaptive Cauchy disturbance operator for the updated
particle population.
Step 8: executing the learning-type Gaussian mutation operator for the particle
population after executing the Cauchy disturbance operator.
Step 9: executing the adjustment operator by probability for the improved
particle population after executing the Gaussian mutation operator;
Step 10: calculating the fitness value of the particle population processed in the
step 9, updating the historical optimal particle pbest(t) and the current global
optimal particle gbest(t) , and then turning to the step 3.
And 11: stopping calculation, and outputting the optimal scheme for the
large-scale oil and gas production systems.
Preferably, the step 7 comprises the following specific steps:
7.1: calculating the mean value of the historical optimal solutions of all the
particles on the kth dimension, and determining the disturbance range of the current
optimum particle on the kth dimension according to the formula (1).
My Kpbest, avek = (1)
Where the ave is the mean value of the historical optimum solutions of all the
particles on the kth dimension, the pbesti, is the dimension value of the particle
i on the kth dimension, the Mp is the size of the particle population.
Step 7.2: determining a position control parameter of the Cauchy distribution of
the t iteration, and generating P disturbance offset according to the formula (2).
1 Ack=Q-" )-[Cauchy(gbest,-ave,y)-Cauchy(ave,-gbest,,y)] 2
(2)
Where the Askj is the jth disturbance offset of the kth dimension of the
current optimal particle, j=1,2,L PR , the Cauchy(gbest- avek,y) and
Cauchy(avek- gbestk,y) are the random numbers satisfying the Cauchy distribution
with the ave, - gbest, and gbest, - ave, as the position parameters, the gbest is
the kth dimension value of the current optimal particle, and the t is a random
number of the interval [0, 1].
Step 7.3: updating the kth dimension of the current optimal particle according
to the formula (3) based on the P disturbance offset.
gbest' rgbest, lgbest, + Akmax max(f(gbestk + Ask'j)) > f(gbestk) f(gbestk) > max(f(gbestk + Ak]j)) (3)
Where the gbest' is the kth dimension value of the current optimal particle
after the offset, and the As,,max is one maximizes the fitness value in all offsets
Akj
Preferably, the step 8 comprises the following steps: arranging all particles in
descending order according to the fitness value after the step 7 being executed,
selecting B, particles with lower fitness value to carry out mutation operation,
calculating the number Z of mutation dimensions of each selected particle,
randomly selecting Z dimensions of each particle, and carrying out mutation on
each mutation dimension according to the formula (4).
x',k wx+§6 -Gaussian(O,1)- (gbest () (-x4))
Where x,,k denotes the value of the kth dimension of the jth particle,
a, represents the random value of interval [0,1], Gaussian(0,1) is a random number which obeys the standard Gauss distribution, zj denotes the number of dimensions of xj that perform the mutation and zj=D- random, # represents the control factor and the formula for # is as follows.
=max (pIax - ) 1+sin(rc( ))| (5) 2 max 2]
Where the 8x,,m are the upper and lower bounds of the values of the
control factor.
Preferably, the step 9 comprises the following specific steps:
Step 9.1: calculating the weight control factor according to the formula (6).
=a -(2a-". ) t (6) max
Where the A is a weight control factor, the A. and A are the feasible
maximum value and minimum value of the weight control factor, the t is a current
iteration number, and the I_ is the maximum iteration number.
Step 9.2: calculating the adjustment control value of the particles according to the formula (7).
f(Xi) fnE ex( - x7
fhesifors/ IY i1 1- j=1
Where the #, is the adjustment control value of the i particle, the x1 and
Xj are the value vector of the particles i and j respectively, the f(xi) is the
fitness value of the particle i , the fave , fes, and f ors, are the average value, the best value and the worst value of the fitness values of all the particles, the E, is the gain factor, which is a positive real number larger than 1.
Step 9.3: calculating the density measurement factor u according to the formula (8).
z = max(|gbest - pbesti)) (8)
Where the maxO denotes to obtain the maximum value of elements in
parentheses, the gbest is the value vector of the current optimal particle, the
pbestri is the value vector of historical optimal particle of the randomly selected
particle.
Step 9.4: calculating and judging whether the formula (9) is satisfied, if so, moving the particle i according to the formula (10), otherwise, keeping the original position of the particle.
ed < random (9)
x = u x gbest flaussian(0,1, D) (10)
Where the randO is a random number in the interval [0, 1], the x is the
value vector of particle i after moving according to probability, and the
Gaussian(O,1,D) is a D-dimensional random vector obeying standard Gaussian
distribution.
The invention has the following beneficial effects:
1. The method is suitable for solving the high-dimensional optimization problems such as collaborative overall optimization of multiple production systems in oil fields, layout optimization of large-scale oil and gas production systems, and operation parameters optimization of large-scale oil and gas production systems with high-efficiency and high-accuracy. The proposed method can assists oil and gas production managers (decision makers) in energy-saving and efficiency-increasing optimization design of large-scale oil and gas production systems.
2. 2. The intelligent optimization method provided by the invention can
effectively obtain the optimal decision scheme of the high-dimensional large-scale oil
and gas production systems, which can meet the urgent need of the optimization
design technology of the complex large-scale oil and gas production system. And the
method can be applied to similar high-dimensional engineering optimization problems
in other fields.
3. According to the problems that the basic particle swarm optimization
algorithm is easy to fall into local optimum, the convergence speed is slow, and the
large-scale variable collaborative solution effect is poor, three modified operators are
proposed to form the modified particle swarm intelligent optimization method with
excellent local and global search capabilities. In order to jump out of the local
optimum and guide the whole population to explore new feasible solutions, the
Cauchy perturbation operator of the adaptive optimization process is designed by
evaluating the neighbourhood information of all dimensions of the current optimal
particle. According to the difference of information carried by good and bad particles
in the population, a Gaussian mutation operator with learning ability is constructed to
ensure the diversity of the population in the later evolution period and enhance the
ability of meticulous search of the algorithm; Considering the complexity of the
solution space of the high-dimensional optimization problem, taking the compactness
of the individual's relative spatial position distribution as the density, considering the
quality factor and the density factor comprehensively, the adjustment operator by
probability is established, which accelerates the convergence at the initial stage and
avoids premature convergence at the later stage. The intelligent optimization method
provided by the invention has strong global searching capability, fast convergence
speed and excellent applicability to the high-dimensional optimization problem of a large oil and gas production systems.
Figure 1 is a flow chart of solution processes for the modified particle swarm
intelligent optimization method.
Figure 2 is the schematic diagram of collaborative optimization of
multi-production system in oilfield based on modified particle swarm intelligent
optimization method.
Figure 3 is the iterative convergence graph for a high-dimensional optimization
embodiment of the modified particle swarm intelligent optimization method for the
large oil and gas production system.
The modified particle swarm intelligent optimization method for solving
high-dimensional optimization problems of large oil and gas production systems
specifically comprises the following steps:
Step 1: converting the constrained high-dimensional large-scale oil and gas
production system optimization mathematical model into the objective function for
evaluating the decision scheme and the constraints for judging whether the scheme is
feasible according to the feasibility criterion, initializing control parameters of the
modified particle swarm optimization method, including standard particle swarm
algorithm parameters, the adaptive Cauchy disturbance operator parameters, the
learning-type Gaussian mutation operator parameters, the parameters of adjustment
operator by probability, the population scale parameter and termination condition
parameter.
Step 2: generating the initial particle population of the large-scale oil and gas
production system optimization problem, calculating the fitness value, and storing the initial history optimal individual pbest1 (0) and current global optimal individual gbest(O) .
Step 3: updating the speed v(t) and the position x,(t) of the each particle, and
the updated particle population is obtained.
Step 4: judging whether the constraint conditions are satisfied, if so, turning to step 5, otherwise, adjusting the particles which do not accord with the constraint conditions, and then turning to step 5;
Step 5: calculating the fitness value of the updated particle population, and
updating the historical optimal particle pbest and the global optimal particle
gbest.
Step 6: judging whether the termination conditions are met, if so, turning to step 11, if not, turning to step 7.
Step 7: executing the adaptive Cauchy disturbance operator for the updated particle population.
The method specifically comprises the following steps:
7.1: calculating the mean value of the historical optimal solutions of all the particles on the kth dimension, and determining the disturbance range of the current optimum particle on the kth dimension according to the formula (1).
My Ypbest ave= M(1)
Where the avek is the mean value of the historical optimum solutions of all the
particles on the kth dimension, the pbesti,k is the dimension value of the particle
i on the kth dimension, the M, is the size of the particle population.
Step 7.2: determining a position control parameter of the Cauchy distribution of
the t iteration, and generating P disturbance offset according to the formula (2).
1 Ak =(r, -- )[Cauchy(gbestk-ave,y)-Cauchy(avek-gbest,y)] 2 (2)
Where the Ackj is the jth disturbance offset of the kth dimension of the
current optimal particle, j=1,2,L PR , the Cauchy(gbest- avek,y) and
Cauchy(avek- gbestk,y) are the random numbers satisfying the Cauchy distribution
with the avek- gbestk and gbestk- avek as the position parameters, the gbest is
the kth dimension value of the current optimal particle, and the t is a random
number of the interval [0, 1].
Step 7.3: updating the kth dimension of the current optimal particle according
to the formula (3) based on the P disturbance offset.
r gbest±+Askax |(gbestk max(f(gbest+ Askj))> f(gbest) f(gbestk)>max(f(gbestk+Ask ))
Where the gbest' is the kth dimension value of the current optimal particle
after the offset, and the As,,max is one maximizes the fitness value in all offsets
Step 8: executing the learning-type Gaussian mutation operator for the particle population after executing the Cauchy disturbance operator.
Specifically, arranging all particles in descending order according to the fitness
value after the step 7 being executed, selecting B, particles with lower fitness value
to carry out mutation operation, calculating the number Z of mutation dimensions
of each selected particle, randomly selecting Z, dimensions of each particle, and
carrying out mutation on each mutation dimension according to the formula (4).
x' =a-x, +§f-Gaussian(0,1)-(gbest-xjk) (4)
Where X,,k denotes the value of the kth dimensionofthe jth particle,
ai represents the random value of interval [0,1], Gaussian(0,1) isarandom
number which obeys the standard Gauss distribution, zj denotes the number of
dimensionsof xj that perform the mutation and zj=D-rando, p represents
the control factor and the formula for # isasfollows.
1 t 1 7 5 pq=p.mx (Wm -18,1i) 1+sin(rc( ) |1 (5) 2 Ima 2
Where the /,mi,, are the upper and lower bounds of the values of the
control factor.
Step 9: executing the adjustment operator by probability for the improved
particle population after executing the Gaussian mutation operator.
The method specifically comprises the following steps:
Step 9.1: calculating the weight control factor according to the formula (6).
A= Am.- (Amax - Amin) t(6) 1max
Where the A is a weight control factor, the Am and Anu are the feasible
maximum value and minimum value of the weight control factor, the t is a current
iteration number, and the I. is the maximum iteration number.
Step 9.2: calculating the adjustment control value of the particles according to
the formula (7).
IL Mp
(1-A ""z+ 1- i- (7) f fPM best1 wors/t 1-Xi 1- j=1
Where the #, is the adjustment control value of the i particle, the xi and
xj are the value vector of the particles i and j respectively, the f(x) is the
fitness value of the particle i , the f,,,, f1", and f o,, are the average value, the
best value and the worst value of the fitness values of all the particles, the E, is the
gain factor, which is a positive real number larger than 1.
Step 9.3: calculating the density measurement factor z according to the
formula (8).
w = max(|gbest - pbest,|) (8)
Where the maxO denotes to obtain the maximum value of elements in
parentheses, the gbest is the value vector of the current optimal particle, the
pbestri is the value vector of historical optimal particle of the randomly selected
particle.
Step 9.4: calculating and judging whether the formula (9) is satisfied, if so,
moving the particle i according to the formula (10), otherwise, keeping the original
position of the particle.
e() < randO (9)
x=a x gbestgflaussian(0,1, D) (10)
Where the randO is a random number in the interval [0, 1], the X is the
value vector of particle i after moving according to probability, and the
Gaussian(0,1,D) is a D-dimensional random vector obeying standard Gaussian
distribution.
Step 10: calculating the fitness value of the particle population processed in the
step 9, updating the historical optimal particle pbest(t) and the current optimal
particle gbest(t) , and then turning to the step 3.
And 11: stopping calculation, and outputting the optimal scheme for the large-scale oil and gas production systems.
The invention is further illustrated in detail below.
Referring to Figures 1-2, the invention discloses a modified particle swarm intelligent optimization method for solving high-dimensional optimization problems of large oil and gas production systems, which comprises the following steps:
Step 1: initializing the inertia weight w and learning factors cI,c 2 of standard
particle swarm algorithm, the scale parameters r and disturbance offset number P
of the Cauchy disturbance operator, the minimum value min and the maximum
value #max for control factor of the Gaussian mutation operator, the minimum value
and the maximum value of weight control factor min,Amax of adjustment operators
by probability, the population size n and the maximum iteration times Ix the
feasibility criterion could be adopted to process the optimization model of large-scale oil and gas production systems, and read and store target functions and constraints.
Step 2: generating the initial particle population of the large-scale oil and gas production system optimization problem, calculating the fitness value, and storing the
initial history optimal individual pbest(0) and current global optimal individual
gbest(O) .
Step 3: updating the speed v(t) and the position x,(t) of the each particle, and
the updated particle population is obtained.
Step 4: judging whether the constraint conditions are satisfied, if so, turning to step 5, otherwise, adjusting the particles which do not accord with the constraint conditions, and then turning to step 5;
Step 5: calculating the fitness value of the updated particle population, and
updating the historical optimal particle pest, and the optimal particle best.
Step 6: judging whether the termination conditions are met, if so, turning to step 11, if not, turning to step 7.
Step 7: for the updated particle population, calculating the mean value of the historical optimal solutions of all the current particles in the kth dimension, determining the position control parameters of the Cauchy distribution for the tth
iteration according to the formula (1), generating the disturbance offset P according
to the formula (2), updating the current optimal particles by adopting the formula (3), and turning to the step 8.
Step 8: arranging all particles of the particle population in descending order according to the fitness value for the particle population after the Cauchy disturbance
operator operation, selecting B, particles with lower fitness value to execute
mutation operation, calculating the number Z of mutation dimensions for each mutation particle, randomly selecting the mutation dimension of the particle Zj, calculating the control factor according to the formula (5), carrying out mutation on each mutation dimension according to the formula (4), and turning to the step 9.
Step 9: calculating the weight control factor A(t) according to the formula (6)
for particle population after executing the leaming-type Gaussian mutation operator,
calculating the adjustment control values of all particles according to the formula (7),
then calculating the density measurement factor 0 determined by the current
general optimal solution and the historical optimal solution of the population
according to the formula (8), then calculating the adjustment probability value
according to the formula (9) and judging whether the transfer probability value is
smaller than the random number r., if so, adjusting the particles according to the
formula (10), and turning to step 10, if not, performing no operation, turning to step
10.
Step 10: calculating the fitness value of the particle population after the Cauchy
disturbance operator is executed, and updating the historical optimal individual
pbest, and the current global optimal individual gbest, and turning to step 3.
Step 11: stopping calculation, and outputting the optimal scheme of the
large-scale oil and gas production systems.
The invention will be further described with reference to specific embodiments.
EMBODIMENT 1
Taking the large-scale oil and gas production system as an example, the problem
of multi-system collaborative parameters optimization is solved.
1. Optimization problem description
The surface engineering of an oilfield includes oil-gas gathering and
transportation system, wastewater treatment system and waterflooding system. The oil and gas gathering and transportation system includes 778 oil production wells, 50 metering stations, 9 transfer stations and 2 joint stations, the sewage treatment system includes 2 ordinary sewage treatment stations and 3 advanced sewage treatment stations, and the water injection system includes 3 water injection stations and 826 water injection wells. All stations, oil wells and water wells are represented as node units, and the pipelines connecting the node units are represented as edges. The oilfield surface engineering is attributed to a large-scale oil and gas network production system, and its production scheme optimization is a high-dimensional multi-system collaborative parameters optimization problem. To solve this problem, the multi-system collaborative optimization model and optimization sub-model are as follows:
(1) Mathematical model of multi-system cooperative parameter optimization
1) Objective function
(1) Taking the main operation parameters of the large-scale oil and gas
production system as decision variables, and taking the minimum total energy
consumption as the objective, the following objective function is established.
ni n Ec = f( IPGTGT TGT PWT QWT' JIW I (IW)
Where Ec is the total energy consumption of large oil and gas production system,
Ye Indicates the total number of economic production periods, GT QeGT TGT
pressure vectors, flow vectors and temperature vectors representing the inlet and
outlet ends of the gathering and transportation subsystem in economic operation time,
P,,,QWT respectively representing the pressure vector and flow vector at the inlet
and outlet ends of the wastewater treatment subsystem in economic operation time,
P,Q,respectively representing the pressure vector and flow vector at the inlet and
outlet ends of the waterflooding subsystem in economic operation time.
(2) Setting up the following objective function with the maximum operation
efficiency of the system as the objective.
nx qS = f( YI, PGT QGT TGT WT' QWT' IW IQW) (12)
Where the 7s represents the operation efficiency of the large-scale oil and gas
production system.
(2) Constraints
(1) The sub-systems of oil and gas gathering, wastewater treatment and
waterflooding should be restricted by the flow characteristics.
SGT( QT T T) 0 t = 2
Sw( P TQ) = 0 t = 1, 2,--, Y (14)
S,,(P),, Q )= 0 t = 1, 2,-- Y (15)
Where the SGT( represents the equations of temperature drop and pressure
drop for the pipeline flow in the gathering and transportation sub-system, and the
P , QG and TGT represents the pressure vector, the flow vector and the
temperature vector of the inlet ends and the outlet ends of the gathering and
transportation sub-system in the tth time period. The ST (represents the pressure
drop equations of the pipeline flow in the pipeline in the wastewater treatment
sub-system, the PW and Q' represents the pressure vector and the flow vector in
the inlet ends and the outlet ends of the wastewater treatment subsystem in the tth
time period respectively; the S1,( represents the pressure drop equations of the
pipeline flow in the pipeline in the water injection sub-system; and the P/, and
Q represents the pressure vector and the flow vector of the inlet end and the outlet
end of the waterflooding sub-system in the tth time period respectively.
(2) The production parameters in each sub-system should be restricted by a certain range of values.
Qn CL CL, a tx = 1,2, lY (16)
SCLinin SCL SCLnx te=1,2, (17)
SCLD,min SCLD J SCLD,max el (1,,8)
Wherein,Q CL'Q&CLmn'QsCL,n. representing the running flow at the inlet and
outlet of all subsystems in the timet period, vectors of the minimum feasible flow
and vectors of the maximum feasible flow, the PSCL ' PStCL,nU PSICL,nW representing the
operating pressures at the inlet and outlet ends of all subsystems in the time tth
period, vectors of the minimum feasible pressure and vectors of the maximum feasible
pressure, PSCL 'PStCLmin PstCLn representing the operating temperatures at the inlet
and outlet ends of all subsystems in the time tth period, PSCL ' PSCL,min ' SCL,nca
representing the minimum feasible temperature and vectors of the maximum feasible
temperature.
(3) The flow of liquid in large-scale oil and gas production system should be
restricted by the law of energy conservation.
ENSCL(CL SCL 0t= E~sCL(Q~CLt cLTLD SCLD 1,2, ... , Y(19) el
Where the ENSCL represents the energy conservation constraint of the large-scale oil and gas production system.
(4) The flow of liquid in large-scale oil and gas production system should be
restricted by the law of mass conservation.
M~~sCL(Q~CLt cLTLD 0t= 1, 2, ..., Y, (20) MNSCL rsCL pSCL tSCLD ea
Where the MNSCL( ) represents the mass conservation constraint of a large-scale oil and gas production system.
(3) Multi-system collaborative parameter optimization sub-model
1) Parameter optimization model of the oil and gas gathering and transportation
sub-system
(1) Objective function
The objective function of parameters optimization of oil and gas gathering and
transportation subsystem is established with the mixed hot water quantity and mixed
hot water temperature as decision variables and the minimum energy consumption of
the subsystem as the goal.
nii n E(TT, QTW) = fWTE(QTW' +TW + D(QGTW' PGTW) +>E(QGTW'TGTW) (21)
Where E ()represents the total energy consumption of oil and gas gathering
and transportation subsystem, fwTE() indicates the processing energy consumption
of each station in the subsystem, fwD() is the dynamic energy consumption of
subsystem, fE()is the thermal energy consumption of subsystem, Q T represents
the vector of mixed hot water quantity of the subsystem, T T indicates the vector of
mixed hot water temperature of the subsystem.
(2) Constraints
The following constraints are established according to the actual limitations of
the oil and gas gathering and transportation system.
V/(T ,,Q ,) 0 (22)
) (T ,TTQ ,)0 (23)
g (TGQtP,) 0 (24) g0T , ) (25) rG(QTW Q T) 0 (26)
Where G()indicates the constraints of pipe flow pressure drop of oil and gas
gathering and transportation subsystem, a ()indicates the equations of pipe flow
temperature drop of subsystem, gN()represents the pressure inequality constraint of
the subsystem, g T() represents the temperature inequality constraint of the
subsystem, rN() represents flow conservation constraint.
(4) Parameter optimization model of the wastewater treatment sub-system
1) Objective function
Aiming at minimizing the transportation energy consumption of wastewater
subsystem and the cost of purchasing clean water, the objective function is established
as follows.
ni n F1 (QWT', 'WT,' HWT) = fWT(QW', €W'') + f(QWT', H"'') 'WT,'
+ fw(Q'WT', tWT, HWT')
(27)
Where F,"() represents the total energy consumption of the wastewater
treatment subsystem, f4B() is cost of purchasing clean water, fs"indicatesthe transportation energy consumption from source stations to wasterwater treatment
stations in the subsystem, fw indicates the transportation energy consumption from
wasterwater treatment stations to waterflooding stations in subsystem, Q`
represents the amount of water transported between stations in the subsystem, €'' is
-1 decision vector indicating whether to transport water between stations in the subsystem, HWTI represents the decision vector of pump displacement between stations in the subsystem.
2) Constraints
According to the actual limitations of the wastewater treatment system, the
constraint conditions are established as follows.
N QWT ', WT )= 0 (28)
sQ = 0 (29)
qK ( TQW'' ') > 0 (30)
gWF( QWF'$F' HWTo) 0 (31)
Where N () indicates the constraint of reinjection demand of the wasterwater
treatment subsystem, s.()represents the flow conservation constraint of the node
units of the subsystem, OwTrepresents the inequality constraint of stations load rate
in subsystem, g'T() are pressure-constrained inequality equations.
(5) Parameter optimization model of the waterflooding sub-system
1) Objective function
Taking the start-stop state and displacement of water injection pump as decision
variables, and aiming at the minimum total energy consumption of waterflooding
subsystem, the objective function is established as follows.
ni n F/wJ'(q'w'', y'J'') = f(ws(qw'', y'''') (32)
Where the F'() represents the total energy consumption of the waterflooding
sub-system, the q'W' represents the 0-1 decision vector , which indicates whether the water injection pump in the sub-system is started, and the y'" represents the displacement decision vector of the water injection pump in the sub-system.
2) Constraints
Constraints are established based on the actual limitations of the waterflooding
sub-system.
,ws(qwt Wt 0 (33)
hws(qJw, ywt) 0 (34)
zws(qIwt wt) =0 (35)
p,WS(qJJW t) 0 (36)
Where lWs() indicates the constraint of the working characteristics of the water
injection pumps, hws() Indicates the constraint of the high efficiency zone of the
water injection pump in the subsystem; uws() indicate the flow conservation
constraint of subsystem; pws() indicates the subsystem pressure constraint.
2. Solution process conditions setting.
The solution of the embodiment is realized by a Matlab 2014b platform, and the parameter setting of the modified particle swarm intelligent optimization method in
the invention is the initialization inertia weight w =0.8, the learning factor c1 = 2
and c2 = 2, the scale parameter r = 0.5 and the disturbance offset number P =20
of the Cauchy disturbance operator, the minimum value fmi =le-10 and the
maximum value Ix=0.85 of the control factor of the Gaussian mutation operator,
the minimum value a= 0.001 and the maximum value nax = 0.65 of the
adjustment operator by probability, the population size n = 50 and the maximum
iteration times Imax =1000 .
3. Comparison and analysis of optimization results.
The main production parameters of the large-scale oil and gas production system
in this embodiment, including hot water mixing quantity vector, hot water mixing
temperature vector, transport relation vector, transport quantity vector, pump start-up
state and pump displacement vector, and pressure vector can reach more than 3300
decision variables in total. Table 1 shows the overall comparison between the
optimization results of the modified particle swarm intelligent optimization method
and the current production scheme. Compared with the current production scheme of
oil field, the scheme obtained by modified particle swarm intelligent optimization
method saves 0.15x lO'kW-h of annual electricity consumption, with a saving ratio of
10.2%; The annual operation cost is reduced by 24 million yuan, and the saving ratio
is 12.06%; The gas consumption per ton of liquid per day of the oil and gas gathering
and transportation subsystem is reduced by 0.31m 3/d, and the saving ratio is 16.86%;
The load rate of wastewater treatment subsystem is increased by 8.99%, and the
average pump efficiency of waterflooding subsystem is increased by 5.6%. It shows
that the modified particle swarm intelligent optimization method can effectively solve
the decision-making problem of ultra-high dimensional operation optimization of
large oil and gas production system, with strong applicability and high solution
accuracy, and realizes the optimization design of oil field surface engineering with
great energy saving and efficiency improvement. The robustness and convergence of
the improved particle swarm intelligent optimization method are solved for 10 times.
As shown in Figure 3, the intelligent optimization method in the present invention can
converge to the optimal scheme every time, with fast convergence speed and strong
robustness.
Table 1 The comparison between the current scheme and the scheme obtained by modified particle swarm intelligent optimization method
Oil and gas gathering and Wastewater treatment Waterflooding Annual transportation sub-system sub-system sub-system Annual power operation Power consumption cost (100 consumption Gas Unit Unit Average (kW-h) million of daily ton consumption consumption Load consumption pump yuan) liquid perday (kW h/d) rate (kW h/d) efficiency (kW-h/d) (m3 /d)
Current 1.47x10 8kW-h 1.99 1.79 1.72 0.45 73.23 6.35 70.91 scheme
Scheme obtained by modified 1.32x10 8kW-h 1.75 1.57 1.43 0.34 80.46 6.11 75.12 particle swarm method
Optimization 10.20% 12.06% 12.29% 16.86 24.44% 8.99% 3.78% 5.60% proportion
The results show that the modified particle swarm intelligent optimization
method proposed by the invention is a new global optimization method, which has
excellent effect on solving the operation parameters optimization problem of
high-dimensional oil and gas production system. Because the intelligent optimization
method has the characteristic of solving without mathematical information of the
model, the modified intelligent optimization method is universal and could be applied
to explore the global optimal scheme of other engineering problems. Therefore, the
modified particle swarm intelligent optimization method in the invention also has
good optimization effect on the layout optimization problem of large-scale oil and gas
production systems and the overall optimization problem of multi-system cooperation.
The above embodiment only describe the preferred mode of the invention, but do
not limit the scope of the invention. On the premise of not departing from the design
spirit of the invention, various modifications and improvements made by ordinary
technicians in the field to the technical scheme of the invention shall fall within the
protection scope determined by the claims of the invention.
Claims (4)
1. A modified particle swarm intelligent optimization method for solving
high-dimensional optimization problems of large oil and gas production systems is
characterized by comprising the following steps:
Step 1: converting the constrained high-dimensional large-scale oil and gas
production system optimization mathematical model into the objective function for
evaluating the decision scheme and the constraints for judging whether the scheme is
feasible according to the feasibility criterion, initializing control parameters of the
modified particle swarm optimization method, including standard particle swarm
algorithm parameters, the adaptive Cauchy disturbance operator parameters, the
learning-type Gaussian mutation operator parameters, the parameters of adjustment
operator by probability, the population scale parameter and termination condition
parameter.
Step 2: generating the initial particle population of the large-scale oil and gas
production system optimization problem, calculating the fitness value, and storing the
initial history optimal individual pbest,(0) and current global optimal individual
gbest(O).
Step 3: updating the speed v1 (t) and the position x,(t) of the each particle, and
the updated particle population is obtained.
Step 4: judging whether the constraint conditions are satisfied, if so, turning to
step 5, otherwise, adjusting the particles which do not accord with the constraint
conditions, and then turning to step 5;
Step 5: calculating the fitness value of the updated particle population, and
updating the historical optimal particle pbest and the optimal particle gbest.
Step 6: judging whether the termination conditions are met, if so, turning to step
11, if not, turning to step 7.
Step 7: executing the adaptive Cauchy disturbance operator for the updated
particle population.
Step 8: executing the learning-type Gaussian mutation operator for the particle
population after executing the Cauchy disturbance operator.
Step 9: executing adjustment operator by probability for the improved particle
population after executing the Gaussian mutation operator.
Step 10: calculating the fitness value of the particle population processed in the
step 9, updating the historical optimal particle pbest,(t) and the current global
optimal particle gbest(t) , and then turning to the step 3.
And 11: stopping calculation, and outputting an optimal scheme for the
large-scale oil and gas production system.
2. The modified particle swarm intelligent optimization method for solving
high-dimensional optimization problems of large oil and gas production systems
according to claim 1 is characterized by comprising the following steps:
7.1: calculating the mean value of the historical optimal solutions of all the
particles on the kth dimension, and determining the disturbance range of the current
optimum particle on the kth dimension according to the formula (1).
My pbest, avek (1)
Where the avek is the mean value of the historical optimum solutions of all the
particles on the kth dimension, the pbestik is the dimension value of the particle
i on the kth dimension, the M, is the size of the particle population.
Step 7.2: determining a position control parameter of the Cauchy distribution of
the t iteration, and generating P disturbance offset according to the formula (2).
1 Asj= ("-)[Cauchy(gbestk - avek,y)- Cauchy(avek - gbestk,y)]
(2)
Where the A., k is the jth disturbance offset of the kth dimension of the
current optimal particle, j=1,2,L ,PR , the Cauchy(gbestk- avek,y) and
Cauchy(avek- gbestk,y) are the random numbers satisfying the Cauchy distribution
with the avek - gbestk and gbestk - avek as the position parameters, the gbestk is
the kth dimension value of the current optimal particle, and the , is a random
number of the interval [0, 1].
Step 7.3: updating the kth dimension of the current optimal particle according
to the formula (3) based on the P disturbance offset.
best' gbestk + Akx max(f (gbest + Aek,)) > f (gbestk) |( gbestk f (gbestr) > max(f (gbest +Aek,))
Where the gbest' is the kth dimension value of the current optimal particle
after the offset, and the Ak,max is one maximizes the fitness value in all offsets
Ackj
3. The modified particle swarm intelligent optimization method for solving
high-dimensional optimization problems of large oil and gas production systems according to claim 1 is characterized in that the step 8 comprises the following steps: arranging all particles in descending order according to the fitness value after the step
7 being executed, selecting B, particles with lower fitness value to carry out
mutation operation, calculating the number Z of mutation dimensions of each
selected particle, randomly selecting Z dimensions of each particle, and carrying
out mutation on each mutation dimension according to the formula (4).
X'ik-a xik +#- Gaussian(O,1).(gbest - xjk) (4)
Where x,, denotes the value of the kth dimension of the jth particle,
ai represents the random value of interval [0,1], Gaussian(0,1) is a random
number which obeys the standard Gauss distribution, zj denotes the number of
dimensionsof xj that perform the mutation and z=D. rand(, # represents
the control factor and the formula for # isasfollows.
max I(lmax -min) 1+sin(rc( t )) (5) 2 1 ma 2]
Where the fmax#min are the upper and lower bounds of the values of the
control factor.
4. The modified particle swarm intelligent optimization method for solving
high-dimensional optimization problems of large oil and gas production systems
according to claim 1 is characterized in that the step 9 comprises the following steps:
Step 9.1: calculating the weight control factor according to the formula (6).
=mx A)t(6)
Where the A is a weight control factor, the 21 and Aim are the feasible
maximum value and minimum value of the weight control factor, the t is a current
iteration number, and the Im. is the maximum iteration number.
Step 9.2: calculating the adjustment control value of the particles according to
the formula (7).
IMP
f .0 EY Xi - X $,=(1 ) " /+XI1- fave (7) 1 1P
Where the #, is the adjustment control value of the i particle, the x,. and
x1 are the value vector of the particles i and i respectively, the f(x,) is the
fitness value of the particle i , the f,,,, fes, andf.os, are the average value, the
best value and the worst value of the fitness values of all the particles, the E, is the
gain factor, which is a positive real number larger than 1.
Step 9.3: calculating the density measurement factor 6 according to the
formula (8).
z = max(|gbest - pbest,,) (8)
Where the maxO denotes to obtain the maximum value of elements in
parentheses, the best is the value vector of the current optimal particle, the
pbesti is the value vector of historical optimal particle of the randomly selected
particle.
Step 9.4: calculating and judging whether the formula (9) is satisfied, if so,
moving the particle i according to the formula (10), otherwise, keeping the original
position of the particle.
e(-0 < random (9)
x= ar x gbestgGaussian(0,1, D) (10)
Where the random is a random number in the interval [0, 1], the x is the
value vector of particle i after moving according to probability, and the
Gaussian(O,1,D) is a D-dimensional random vector obeying standard Gaussian
distribution.
-1/3-
-1/3-
By applying the feasibility criterion, the optimization model of the large-scale oil and gas production system is disposed. Initializing the parameters of population size, the termination condition, the basic parameters of PSO algorithm, and the basic parameters of modified operators.
Generating the initial particle population of large-scale oil and gas production system, determining the optimal particle and the history optimal particle of the initial particle population 2020103709
Updating the speed and location of all the particles
Yes Are the constraints satisfied?
No Adjusting the speed and the position of particles
Calculating the fitness value, updating the current optimal particle and the historical optimal particle
Whether to Optimal scheme for the terminate? large-scale oil and gas Yes production system
No
Calculating the Cauchy distribution position control parameter according to the formula (1), generating the disturbance offsets according to the formula (2), updating the current optimal particle according to the formula (3)
Arranging the fitness values of the particles in a descending order, randomly select some particles with low fitness values to perform Gaussian mutation operator according to the formula (4) and (5)
According to formulas (6), (7) and (8), respectively, calculating the weight control factor, the particle adjustment control value and the density measurement factor, judging whether the adjustment probability is smaller than a random number by adopting the formula (9), if so, adjusting particles according to the formula (10)
Calculating the fitness value, updating the current global optimal particle and the historical optimal particle
Figure 1
-2/3-
Figure 2
-3/3-
Figure 3
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| AU2020103709A AU2020103709A4 (en) | 2020-11-26 | 2020-11-26 | A modified particle swarm intelligent optimization method for solving high-dimensional optimization problems of large oil and gas production systems |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| AU2020103709A AU2020103709A4 (en) | 2020-11-26 | 2020-11-26 | A modified particle swarm intelligent optimization method for solving high-dimensional optimization problems of large oil and gas production systems |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| AU2020103709A4 true AU2020103709A4 (en) | 2021-02-11 |
Family
ID=74502368
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| AU2020103709A Ceased AU2020103709A4 (en) | 2020-11-26 | 2020-11-26 | A modified particle swarm intelligent optimization method for solving high-dimensional optimization problems of large oil and gas production systems |
Country Status (1)
| Country | Link |
|---|---|
| AU (1) | AU2020103709A4 (en) |
Cited By (40)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112994099A (en) * | 2021-03-05 | 2021-06-18 | 河北工业大学 | High-proportion distributed photovoltaic grid-connected consumption capacity analysis method |
| CN113033755A (en) * | 2021-03-08 | 2021-06-25 | 沈阳大学 | Bacterial foraging optimization method with Weber-Ficna emotional mutation operation |
| CN113283645A (en) * | 2021-05-14 | 2021-08-20 | 大连海事大学 | Traffic flow distribution method based on parallel mixed group intelligent optimization |
| CN113489004A (en) * | 2021-07-20 | 2021-10-08 | 中国人民解放军陆军勤务学院 | Optimization method for economic operation of multi-energy power supply system |
| CN113554216A (en) * | 2021-06-28 | 2021-10-26 | 南京工业大学 | Multi-objective optimization method for mixed manufacturing of Kfold-LSTM mixed variation optimizing macromolecules |
| CN113570555A (en) * | 2021-07-07 | 2021-10-29 | 温州大学 | Two-dimensional segmentation method of multi-threshold medical image based on improved grasshopper algorithm |
| CN113623256A (en) * | 2021-07-23 | 2021-11-09 | 苏州浪潮智能科技有限公司 | Fan rotating speed control method and device |
| CN113642802A (en) * | 2021-08-24 | 2021-11-12 | 国网江苏省电力有限公司营销服务中心 | Comprehensive energy station energy optimization scheduling method and system based on carbon metering model |
| CN113703319A (en) * | 2021-08-26 | 2021-11-26 | 合肥工业大学 | Joint module inequality constraint optimal robust control method based on reinforcement learning |
| CN113759333A (en) * | 2021-07-14 | 2021-12-07 | 中国人民解放军空军预警学院 | Wind turbine multipath echo micromotion parameter estimation method based on whale optimization algorithm |
| CN113836791A (en) * | 2021-08-28 | 2021-12-24 | 西安交通大学 | Mobile semi-implicit particle method key parameter optimization method based on genetic algorithm |
| CN113872192A (en) * | 2021-09-26 | 2021-12-31 | 国网电力科学研究院武汉能效测评有限公司 | Hospital power grid load optimization control system and control method |
| CN113919721A (en) * | 2021-10-19 | 2022-01-11 | 华北电力大学（保定） | Distributed power supply multi-target planning method with coordinated reliability and economy |
| CN113947009A (en) * | 2021-08-31 | 2022-01-18 | 西北大学 | Sparse LSTM landslide dynamic prediction method based on Cauchy disturbance sparrow optimization |
| CN113962447A (en) * | 2021-10-08 | 2022-01-21 | 哈尔滨工业大学（威海） | Complex equipment batch long-term maintenance plan optimization method based on improved particle swarm optimization |
| CN113987806A (en) * | 2021-10-29 | 2022-01-28 | 吉林大学 | Atmospheric mode optimization method based on proxy model |
| CN114063451A (en) * | 2021-10-13 | 2022-02-18 | 东南大学 | Data-driven control method for optimizing fuel cell oxygen excess |
| CN114121296A (en) * | 2021-12-09 | 2022-03-01 | 上海森亿医疗科技有限公司 | Data-driven clinical information rule extraction method, storage medium and device |
| CN114169117A (en) * | 2021-12-13 | 2022-03-11 | 国家电网有限公司 | Power transmission network extension planning method based on improved particle swarm optimization |
| CN114186169A (en) * | 2021-11-26 | 2022-03-15 | 西南石油大学 | Method for evaluating conveying efficiency of natural gas gathering and transportation pipeline |
| CN114967428A (en) * | 2022-07-29 | 2022-08-30 | 济南大学 | Unmanned life buoy optimal robust control method based on improved particle swarm algorithm |
| CN115049118A (en) * | 2022-06-02 | 2022-09-13 | 太原理工大学 | Method for realizing optimal capacity of natural gas production facility based on improved particle screening algorithm |
| CN115081301A (en) * | 2022-07-11 | 2022-09-20 | 国网安徽省电力有限公司电力科学研究院 | Dynamic carbon emission evolution method based on mixed PSO-MKPLS |
| CN115146426A (en) * | 2022-07-12 | 2022-10-04 | 西安飞蜂智能科技有限公司 | Rural sewage transfer station and treatment station planning method based on topological network data |
| CN115907415A (en) * | 2022-12-19 | 2023-04-04 | 海南港航通用码头有限公司 | Intelligent dispatching system based on bulk and general cargo wharf |
| CN116128014A (en) * | 2023-04-17 | 2023-05-16 | 深圳市明源云科技有限公司 | Hydrant layout method, device, electronic equipment and computer readable storage medium |
| CN116152316A (en) * | 2023-04-17 | 2023-05-23 | 山东省工业技术研究院 | Image registration method based on self-adaptive parameter particle swarm algorithm |
| CN116449687A (en) * | 2023-06-16 | 2023-07-18 | 济南大学 | Improved-type marine rescue flying wing disturbance observation PID control method |
| CN116739311A (en) * | 2023-08-11 | 2023-09-12 | 山东赛马力发电设备有限公司 | Comprehensive energy system planning method and system with multiple energy hubs |
| CN116757333A (en) * | 2023-08-12 | 2023-09-15 | 中国人民解放军96901部队 | Classification dustbin optimal configuration method based on resident satisfaction |
| CN116757491A (en) * | 2023-05-18 | 2023-09-15 | 济南大学 | Energy storage system optimal configuration method and energy storage system based on artificial fish swarm algorithm |
| CN117010728A (en) * | 2023-10-07 | 2023-11-07 | 华北电力大学 | Comprehensive power generation cost optimization method for thermal power enterprises |
| CN117035373A (en) * | 2023-10-09 | 2023-11-10 | 中国电建集团山东电力管道工程有限公司 | Intelligent management method and system for pipeline prefabrication production line |
| CN117123131A (en) * | 2023-10-25 | 2023-11-28 | 克拉玛依市蓝润环保科技有限责任公司 | Petroleum aid production equipment and method thereof |
| CN117236152A (en) * | 2023-11-10 | 2023-12-15 | 国网浙江省电力有限公司宁波供电公司 | Twin simulation method and system for new energy power grid |
| CN117313554A (en) * | 2023-11-28 | 2023-12-29 | 中国科学技术大学 | Multi-section combined multi-objective optimization method, system, equipment and medium for coking production |
| CN117452802A (en) * | 2023-11-08 | 2024-01-26 | 上海上源泵业制造有限公司 | Low-carbon water supply control method and system |
| CN117540643A (en) * | 2024-01-10 | 2024-02-09 | 西安特力科技术股份有限公司 | Method for realizing high-density winding of tooth slot motor by adopting intelligent optimization algorithm |
| CN117950310A (en) * | 2024-03-27 | 2024-04-30 | 济南大学 | Control method based on programmable electric load shoulder-pushing trainer |
| CN118052153A (en) * | 2024-04-16 | 2024-05-17 | 上海叁零肆零科技有限公司 | Natural gas pipe network data optimization method, storage medium and electronic equipment |
-
2020
- 2020-11-26 AU AU2020103709A patent/AU2020103709A4/en not_active Ceased
Cited By (68)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112994099B (en) * | 2021-03-05 | 2023-12-19 | 河北工业大学 | High-proportion distributed photovoltaic grid-connected digestion capacity analysis method |
| CN112994099A (en) * | 2021-03-05 | 2021-06-18 | 河北工业大学 | High-proportion distributed photovoltaic grid-connected consumption capacity analysis method |
| CN113033755A (en) * | 2021-03-08 | 2021-06-25 | 沈阳大学 | Bacterial foraging optimization method with Weber-Ficna emotional mutation operation |
| CN113283645B (en) * | 2021-05-14 | 2023-11-07 | 大连海事大学 | Traffic flow distribution method based on parallel hybrid group intelligent optimization |
| CN113283645A (en) * | 2021-05-14 | 2021-08-20 | 大连海事大学 | Traffic flow distribution method based on parallel mixed group intelligent optimization |
| CN113554216A (en) * | 2021-06-28 | 2021-10-26 | 南京工业大学 | Multi-objective optimization method for mixed manufacturing of Kfold-LSTM mixed variation optimizing macromolecules |
| CN113554216B (en) * | 2021-06-28 | 2023-07-28 | 南京工业大学 | Kfold-LSTM hybrid variation optimizing polymer hybrid manufacturing multi-objective optimizing method |
| CN113570555A (en) * | 2021-07-07 | 2021-10-29 | 温州大学 | Two-dimensional segmentation method of multi-threshold medical image based on improved grasshopper algorithm |
| CN113570555B (en) * | 2021-07-07 | 2024-02-09 | 温州大学 | Two-dimensional segmentation method of multi-threshold medical image based on improved grasshopper algorithm |
| CN113759333A (en) * | 2021-07-14 | 2021-12-07 | 中国人民解放军空军预警学院 | Wind turbine multipath echo micromotion parameter estimation method based on whale optimization algorithm |
| CN113759333B (en) * | 2021-07-14 | 2024-04-02 | 中国人民解放军空军预警学院 | Wind turbine multipath echo jiggle parameter estimation method based on whale optimization algorithm |
| CN113489004A (en) * | 2021-07-20 | 2021-10-08 | 中国人民解放军陆军勤务学院 | Optimization method for economic operation of multi-energy power supply system |
| CN113623256A (en) * | 2021-07-23 | 2021-11-09 | 苏州浪潮智能科技有限公司 | Fan rotating speed control method and device |
| CN113642802A (en) * | 2021-08-24 | 2021-11-12 | 国网江苏省电力有限公司营销服务中心 | Comprehensive energy station energy optimization scheduling method and system based on carbon metering model |
| CN113642802B (en) * | 2021-08-24 | 2024-02-02 | 国网江苏省电力有限公司营销服务中心 | Comprehensive energy station energy optimization scheduling method and system based on carbon metering model |
| CN113703319B (en) * | 2021-08-26 | 2023-07-28 | 合肥工业大学 | Joint module inequality constraint optimal robust control method based on reinforcement learning |
| CN113703319A (en) * | 2021-08-26 | 2021-11-26 | 合肥工业大学 | Joint module inequality constraint optimal robust control method based on reinforcement learning |
| CN113836791A (en) * | 2021-08-28 | 2021-12-24 | 西安交通大学 | Mobile semi-implicit particle method key parameter optimization method based on genetic algorithm |
| CN113947009B (en) * | 2021-08-31 | 2024-03-08 | 西北大学 | Sparse LSTM landslide dynamic prediction method based on Cauchy disturbance sparrow optimization |
| CN113947009A (en) * | 2021-08-31 | 2022-01-18 | 西北大学 | Sparse LSTM landslide dynamic prediction method based on Cauchy disturbance sparrow optimization |
| CN113872192A (en) * | 2021-09-26 | 2021-12-31 | 国网电力科学研究院武汉能效测评有限公司 | Hospital power grid load optimization control system and control method |
| CN113872192B (en) * | 2021-09-26 | 2024-03-12 | 国网电力科学研究院武汉能效测评有限公司 | Hospital power grid load optimization control system and control method |
| CN113962447A (en) * | 2021-10-08 | 2022-01-21 | 哈尔滨工业大学（威海） | Complex equipment batch long-term maintenance plan optimization method based on improved particle swarm optimization |
| CN113962447B (en) * | 2021-10-08 | 2024-05-28 | 哈尔滨工业大学（威海） | Complex equipment batch long-term maintenance plan optimization method based on improved particle swarm algorithm |
| CN114063451A (en) * | 2021-10-13 | 2022-02-18 | 东南大学 | Data-driven control method for optimizing fuel cell oxygen excess |
| CN114063451B (en) * | 2021-10-13 | 2023-09-01 | 东南大学 | Data driving control method for optimizing fuel cell peroxy amount |
| CN113919721B (en) * | 2021-10-19 | 2024-05-17 | 华北电力大学（保定） | Reliability and economy coordinated distributed power source multi-objective planning method |
| CN113919721A (en) * | 2021-10-19 | 2022-01-11 | 华北电力大学（保定） | Distributed power supply multi-target planning method with coordinated reliability and economy |
| CN113987806A (en) * | 2021-10-29 | 2022-01-28 | 吉林大学 | Atmospheric mode optimization method based on proxy model |
| CN113987806B (en) * | 2021-10-29 | 2024-04-26 | 吉林大学 | Atmosphere mode optimization method based on proxy model |
| CN114186169A (en) * | 2021-11-26 | 2022-03-15 | 西南石油大学 | Method for evaluating conveying efficiency of natural gas gathering and transportation pipeline |
| CN114186169B (en) * | 2021-11-26 | 2023-12-12 | 西南石油大学 | Natural gas gathering and transportation pipeline transportation efficiency evaluation method |
| CN114121296A (en) * | 2021-12-09 | 2022-03-01 | 上海森亿医疗科技有限公司 | Data-driven clinical information rule extraction method, storage medium and device |
| CN114121296B (en) * | 2021-12-09 | 2024-02-02 | 上海森亿医疗科技有限公司 | Data-driven clinical information rule extraction method, storage medium and equipment |
| CN114169117A (en) * | 2021-12-13 | 2022-03-11 | 国家电网有限公司 | Power transmission network extension planning method based on improved particle swarm optimization |
| CN115049118A (en) * | 2022-06-02 | 2022-09-13 | 太原理工大学 | Method for realizing optimal capacity of natural gas production facility based on improved particle screening algorithm |
| CN115081301B (en) * | 2022-07-11 | 2024-04-16 | 国网安徽省电力有限公司电力科学研究院 | Carbon emission dynamic evolution method based on mixed PSO-MKPLS |
| CN115081301A (en) * | 2022-07-11 | 2022-09-20 | 国网安徽省电力有限公司电力科学研究院 | Dynamic carbon emission evolution method based on mixed PSO-MKPLS |
| CN115146426A (en) * | 2022-07-12 | 2022-10-04 | 西安飞蜂智能科技有限公司 | Rural sewage transfer station and treatment station planning method based on topological network data |
| CN115146426B (en) * | 2022-07-12 | 2024-05-03 | 西安飞蜂智能科技有限公司 | Rural sewage transfer station and treatment station planning method based on topology network data |
| CN114967428B (en) * | 2022-07-29 | 2022-11-22 | 济南大学 | Unmanned lifebuoy optimal robust control method based on improved particle swarm algorithm |
| CN114967428A (en) * | 2022-07-29 | 2022-08-30 | 济南大学 | Unmanned life buoy optimal robust control method based on improved particle swarm algorithm |
| CN115907415A (en) * | 2022-12-19 | 2023-04-04 | 海南港航通用码头有限公司 | Intelligent dispatching system based on bulk and general cargo wharf |
| CN116128014B (en) * | 2023-04-17 | 2023-08-04 | 深圳市明源云科技有限公司 | Hydrant layout method, device, electronic equipment and computer readable storage medium |
| CN116152316A (en) * | 2023-04-17 | 2023-05-23 | 山东省工业技术研究院 | Image registration method based on self-adaptive parameter particle swarm algorithm |
| CN116128014A (en) * | 2023-04-17 | 2023-05-16 | 深圳市明源云科技有限公司 | Hydrant layout method, device, electronic equipment and computer readable storage medium |
| CN116757491A (en) * | 2023-05-18 | 2023-09-15 | 济南大学 | Energy storage system optimal configuration method and energy storage system based on artificial fish swarm algorithm |
| CN116449687B (en) * | 2023-06-16 | 2023-09-08 | 济南大学 | Improved-type marine rescue flying wing disturbance observation PID control method |
| CN116449687A (en) * | 2023-06-16 | 2023-07-18 | 济南大学 | Improved-type marine rescue flying wing disturbance observation PID control method |
| CN116739311A (en) * | 2023-08-11 | 2023-09-12 | 山东赛马力发电设备有限公司 | Comprehensive energy system planning method and system with multiple energy hubs |
| CN116739311B (en) * | 2023-08-11 | 2023-11-07 | 山东赛马力发电设备有限公司 | Comprehensive energy system planning method and system with multiple energy hubs |
| CN116757333A (en) * | 2023-08-12 | 2023-09-15 | 中国人民解放军96901部队 | Classification dustbin optimal configuration method based on resident satisfaction |
| CN117010728A (en) * | 2023-10-07 | 2023-11-07 | 华北电力大学 | Comprehensive power generation cost optimization method for thermal power enterprises |
| CN117010728B (en) * | 2023-10-07 | 2024-01-02 | 华北电力大学 | Comprehensive power generation cost optimization method for thermal power enterprises |
| CN117035373B (en) * | 2023-10-09 | 2024-01-23 | 中国电建集团山东电力管道工程有限公司 | Intelligent management method and system for pipeline prefabrication production line |
| CN117035373A (en) * | 2023-10-09 | 2023-11-10 | 中国电建集团山东电力管道工程有限公司 | Intelligent management method and system for pipeline prefabrication production line |
| CN117123131A (en) * | 2023-10-25 | 2023-11-28 | 克拉玛依市蓝润环保科技有限责任公司 | Petroleum aid production equipment and method thereof |
| CN117123131B (en) * | 2023-10-25 | 2024-02-02 | 克拉玛依市蓝润环保科技有限责任公司 | Petroleum aid production equipment and method thereof |
| CN117452802A (en) * | 2023-11-08 | 2024-01-26 | 上海上源泵业制造有限公司 | Low-carbon water supply control method and system |
| CN117452802B (en) * | 2023-11-08 | 2024-05-14 | 上海上源泵业制造有限公司 | Low-carbon water supply control method |
| CN117236152B (en) * | 2023-11-10 | 2024-04-09 | 国网浙江省电力有限公司宁波供电公司 | Twin simulation method and system for new energy power grid |
| CN117236152A (en) * | 2023-11-10 | 2023-12-15 | 国网浙江省电力有限公司宁波供电公司 | Twin simulation method and system for new energy power grid |
| CN117313554B (en) * | 2023-11-28 | 2024-03-29 | 中国科学技术大学 | Multi-section combined multi-objective optimization method, system, equipment and medium for coking production |
| CN117313554A (en) * | 2023-11-28 | 2023-12-29 | 中国科学技术大学 | Multi-section combined multi-objective optimization method, system, equipment and medium for coking production |
| CN117540643A (en) * | 2024-01-10 | 2024-02-09 | 西安特力科技术股份有限公司 | Method for realizing high-density winding of tooth slot motor by adopting intelligent optimization algorithm |
| CN117950310A (en) * | 2024-03-27 | 2024-04-30 | 济南大学 | Control method based on programmable electric load shoulder-pushing trainer |
| CN117950310B (en) * | 2024-03-27 | 2024-06-07 | 济南大学 | Control method based on programmable electric load shoulder-pushing trainer |
| CN118052153A (en) * | 2024-04-16 | 2024-05-17 | 上海叁零肆零科技有限公司 | Natural gas pipe network data optimization method, storage medium and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| AU2020103709A4 (en) | A modified particle swarm intelligent optimization method for solving high-dimensional optimization problems of large oil and gas production systems | |
| CN110288164B (en) | Predictive control method for building air-conditioning refrigeration station system | |
| CN109768573A (en) | Var Optimization Method in Network Distribution based on multiple target difference grey wolf algorithm | |
| CN105404151A (en) | Sewage processing process dynamic multi-target optimization control method | |
| CN104779611A (en) | Economic dispatch method for micro grid based on centralized and distributed double-layer optimization strategy | |
| CN112952807B (en) | Multi-objective optimization scheduling method considering wind power uncertainty and demand response | |
| CN109472413A (en) | Consider the garden integrated energy system Optimization Scheduling of hot pipe network transmission characteristic | |
| Liu et al. | Two-stage optimal economic scheduling for commercial building multi-energy system through internet of things | |
| Shang et al. | Production scheduling optimization method based on hybrid particle swarm optimization algorithm | |
| CN111767677A (en) | GA algorithm-based cascade pump station group lift optimal distribution method | |
| CN111325306A (en) | ABC-PSO hybrid algorithm-based water supply pump set scheduling method | |
| CN116263897A (en) | Distributed power supply optimal configuration method based on multi-target particle swarm algorithm | |
| CN113191083B (en) | Optimization design method of flue gas waste heat recovery system considering all-working-condition external parameter change | |
| Kawada et al. | Creating swing-up patterns of an acrobot using evolutionary computation | |
| CN113555907A (en) | Distributed multi-energy system rolling optimization control method considering non-ideal communication condition | |
| CN114004047A (en) | Electric heating gas interconnection multi-energy system matrix operation model modeling method | |
| CN112923533A (en) | Multi-agent-based hierarchical distributed optimization control method for central air-conditioning system | |
| Lu et al. | Energy Consumption Optimization Analysis of LNG Receiving Station Based on Genetic Algorithm | |
| CN111290354A (en) | Modularized data center waste heat efficient utilization control management system based on cloud computing | |
| Rui-Hong | Chemical Process Optimization Based on Improved Particle Swarm Algorithm | |
| Liu et al. | Study on multi-objective optimization of oil production process | |
| CN113283755B (en) | Intelligent scheduling decision-making method for workshops | |
| He et al. | Research on modeling and solving algorithm of steelmaking continuous casting production scheduling | |
| CN114992520B (en) | Control method of water-doped heat tracing system of oil transfer station in unattended mode | |
| CN114839929B (en) | Energy-saving assembly line whale scheduling optimization method and integrated system for electrolytic aluminum |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| FGI | Letters patent sealed or granted (innovation patent) | ||
| MK22 | Patent ceased section 143a(d), or expired - non payment of renewal fee or expiry |