CN113139695A - Offshore thermal recovery and production increase period deck distribution method, computer device and storage medium - Google Patents
Offshore thermal recovery and production increase period deck distribution method, computer device and storage medium Download PDFInfo
- Publication number
- CN113139695A CN113139695A CN202110510138.6A CN202110510138A CN113139695A CN 113139695 A CN113139695 A CN 113139695A CN 202110510138 A CN202110510138 A CN 202110510138A CN 113139695 A CN113139695 A CN 113139695A
- Authority
- CN
- China
- Prior art keywords
- particle
- initial
- value
- area
- iteration
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 46
- 238000011084 recovery Methods 0.000 title claims abstract description 26
- 238000009826 distribution Methods 0.000 title claims abstract description 8
- 238000003860 storage Methods 0.000 title claims abstract description 8
- 238000004519 manufacturing process Methods 0.000 title abstract description 12
- 239000002245 particle Substances 0.000 claims abstract description 147
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 8
- 230000006870 function Effects 0.000 claims description 15
- 238000004590 computer program Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 4
- 150000001875 compounds Chemical class 0.000 claims description 3
- 230000003247 decreasing effect Effects 0.000 claims description 3
- 238000013461 design Methods 0.000 abstract description 2
- 238000005553 drilling Methods 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 3
- 238000005457 optimization Methods 0.000 description 3
- 230000000638 stimulation Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004836 empirical method Methods 0.000 description 1
- 230000019637 foraging behavior Effects 0.000 description 1
- 230000002431 foraging effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000011664 nicotinic acid Substances 0.000 description 1
- 239000003208 petroleum Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
- G06Q10/043—Optimisation of two dimensional placement, e.g. cutting of clothes or wood
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06312—Adjustment or analysis of established resource schedule, e.g. resource or task levelling, or dynamic rescheduling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- 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
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Quality & Reliability (AREA)
- Development Economics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Educational Administration (AREA)
- Agronomy & Crop Science (AREA)
- Animal Husbandry (AREA)
- Marine Sciences & Fisheries (AREA)
- Mining & Mineral Resources (AREA)
- Primary Health Care (AREA)
- Feedback Control In General (AREA)
Abstract
The invention relates to a deck distribution method, a computer device and a storage medium in the offshore thermal recovery and production increase period. The method comprises the following steps: s1, determining the occupied area S (i) and the importance degree Z (i) of each of m pieces of equipment during the offshore thermal recovery operation or the yield increasing operation, wherein i is 1-m, and determining the available area V of a platform deck; s2, performing T-round iteration on the accepting and rejecting states of m devices by using a particle swarm algorithm, wherein T is the maximum iteration number, sequentially recording the global optimal position g of the whole particle swarm of each round of iteration and the total importance sum gbest of the globally selected devices, and g and gbest after T-round iteration are the final global optimal position and the global optimal value. The invention can optimize the platform area allocation scheme, can select the equipment with the highest total arrangement value, and enables the platform design to be more scientific and reasonable.
Description
Technical Field
The invention relates to the technical field of petroleum engineering artificial intelligence application, in particular to a platform deck area optimal allocation method during offshore thermal recovery and yield increase operation, a computer device and a storage medium.
Background
During the thermal recovery or yield increase operation of an offshore oil and gas field, the deck area or space of a drilling platform or an oil production platform (hereinafter referred to as a platform) is extremely limited, and how to place as many key thermal recovery or yield increase equipment as possible in the limited deck area or space is a key step for ensuring the smooth performance of the thermal recovery and yield increase operation. At present, the arrangement of the equipment is mainly determined by an empirical method or rough calculation, and the design is often not scientific enough.
Therefore, how to comprehensively consider the available deck area of the offshore drilling and production platform and the occupied area and importance of equipment required by thermal recovery and production increase operation is to provide an optimal distribution method for the deck area of the platform during the offshore thermal recovery and production increase operation, so that equipment site guarantee is provided for the thermal recovery or production increase operation of the offshore oil field, and the method is a technical problem which needs to be solved urgently in the field.
Disclosure of Invention
In view of the above, the present invention is directed to provide a method, a computer device and a storage medium for optimally allocating a deck area of a platform during thermal recovery and yield increase operations on the sea, which are suitable for solving the problem of optimally allocating the deck area during key operations such as thermal recovery or yield increase on the sea platform, so as to place drilling and production equipment with the highest total value as much as possible in a limited deck area or space.
The invention firstly provides an optimal distribution method for the deck area of an offshore platform, which comprises the following steps:
s1, determining the occupied area S (i) and the importance degree Z (i) of each of m pieces of equipment during the offshore thermal recovery operation or the yield increasing operation, wherein i is 1-m, and determining the available area V of a platform deck;
s2, performing T-round iteration on the accepting and rejecting states of m devices by using a particle swarm algorithm, wherein T is the maximum iteration number, sequentially recording the global optimal position (namely device accepting) g of the whole particle swarm of each round of iteration and the total importance sum gbest of the globally selected devices, and g and gbest after the T-round iteration are the final global optimal position and the global optimal value.
According to an embodiment of the present invention, the step of S2 includes:
s21, presetting the number N of particles, the maximum iteration number T, learning factors C1 and C2, the dimension D of the particles, the maximum value Wmax and the minimum value Wmin of the inertia weight, the maximum value Vmax and the minimum value Vmin of the speed and a penalty function coefficient Cf;
s22, initializing positions x (i, j) of N particles, wherein i represents the ith particle, j represents the jth equipment, x (i, j) is 0 and represents abandon, x (i, j) is 1 and represents use, and the initial positions of the particles are represented by random numbers between 0 and 1;
s23, initializing the speeds v (i, j) of the N particles, wherein the initial speed is between Vmin and Vmax, the positive speed means that x (i, j) is increased, and the negative speed means that x (i, j) is decreased;
s24, calculating an initial optimal position p (i, j) and an initial optimal value pbest (i) of each particle, where the initial optimal value pbest (i) is the sum of the importance of the selected devices, where i is 1 to N, and N total values, and the initial optimal position p (i, j) of each particle is equal to the initial position x (i, j);
s25, calculating an initial global optimal position g and an initial global optimal value gbest of the whole particle swarm:
traversing from the 1 st particle to the Nth particle, selecting the maximum initial optimal value pbest (i) in all the N particles as an initial global optimal value gbest, and taking the corresponding particle position x (i, j) as an initial global optimal position g;
s26, performing a first round of iterative operation, updating the positions x (i, j) of all N particles, recalculating the initial optimal value pbest (i) of each particle according to the new positions x (i, j) of the N particles, selecting the maximum value as the global optimal value gbest after the first round of iteration, and taking the corresponding particle position x (i, j) as the global optimal position after the first round of iteration;
and S27, performing 2 nd to T th iterations according to the iteration method of S26, and sequentially recording the global optimal position g and the global optimal value gbest of each iteration, wherein the g and the gbest after the T iterations are the final global optimal position and the final global optimal value.
According to one embodiment of the present invention, in step S21, the number of particles N is 20 × m, the maximum number of iterations T is 30 × m, the learning factor C1 is C2 is 1.5, the dimension D of the particles is equal to the number of devices m involved, the maximum value of the inertia weight Wmax is 0.9, the minimum value of the inertia weight Wmin is 0.4, the maximum value of the velocity is 0.4
Minimum value of speed
Coefficient of penalty function
In the formula (I), the compound is shown in the specification,
is the average value of the importance of the equipment, S (i) is the occupied area of the equipment, m is the number of the equipment, and V is the total available area of the deck.
According to one embodiment of the present invention, the initial position of each particle in step S24 is a random number between 0 and 1, excluding 0 or 1 itself.
According to an embodiment of the present invention, in step S24, the initial optimal value pbest (i) of the ith particle is as follows:
wherein i is 1 to N; x (i, j) is the initial position of the particle; z (j) is the importance of device j.
According to an embodiment of the present invention, after pbest (i) is calculated according to the formula, the following method is further included:
calculating the total area V (i) of the equipment represented by each particle, and the total area V (i) of the equipment represented by the ith particle:
wherein i is 1 to N; x (i, j) is the initial position of the particle; s (j) is the area of the device j;
pbest (i) is the initial optimum for the particle, provided that V (i) is less than or equal to the available area V;
if V (i) > usable area V, the initial optimum value pbest (i) ═ pbest (i) -Cf × [ V (i) -V ], Cf is the penalty function coefficient.
According to an embodiment of the present invention, in step S27, the method for updating the position x (i, j) includes:
first, the dynamic inertia weight w is calculated, and the formula is as follows:
w＝Wmax-(Wmax-Wmin)×k/T
wherein k represents the kth iteration, Wmax is the maximum inertia weight value, and Wmin is the minimum inertia weight value;
the velocity v (i, j) of the jth device for the ith particle is then updated as follows:
v (i, j) new w × v (i, j) + C1 × rand x [ p (i, j) -x (1, j) ] + C2 × rand x [ g-x (1, j) ]
Wherein, C1 and C2 are learning factors;
if the obtained v (i, j) is not between Vmin and Vmax, the regularization processing is carried out:
v (i, j) new rand x (Vmax-Vmin) + Vmin;
and calculating a position updating coefficient vx (i, j) of the jth equipment of the ith particle according to v (i, j), wherein the formula is as follows:
wherein i represents the ith particle, and j represents the jth equipment;
then, the position of the ith particle is updated to obtain new x (i, j), and the formula is as follows:
wherein x (i, j) new-1 indicates that the device is selected, and x (i, j) new-0 indicates that the device is discarded; and rand represents a random number between 0 and 1.
According to one embodiment of the invention, the final global optimum position represents the preferred device and/or the abandoned device, and the final global optimum value represents the highest sum of the values of the selected devices, and the area does not exceed the available area of the platform.
The invention also provides a computer device, which comprises a memory and a processor; the memory for storing a computer program; the processor is configured to implement the steps of the offshore platform deck area optimal allocation method when executing the computer program.
The invention also proposes a computer storage medium having a computer program stored thereon, which, when being executed by a processor, carries out the steps of the method for optimal allocation of deck area of an offshore platform.
The optimal distribution method for the platform deck area during the offshore thermal recovery and yield increasing operation comprehensively considers the available deck area of the offshore drilling and production platform and the occupied area and the importance of equipment required by the thermal recovery and yield increasing operation, and based on the particle swarm algorithm, the equipment with the highest total value can be distributed on the premise of not exceeding the available deck area or space, so that the equipment site guarantee is provided for the offshore oil field thermal recovery or yield increasing operation.
Drawings
Fig. 1 is a flow chart of a method for optimally allocating deck area of a platform during offshore thermal recovery and stimulation operations according to an embodiment of the invention.
Detailed Description
The preferred embodiments of the present invention will be described in detail below with reference to the accompanying drawings so that the objects, features and advantages of the invention can be more clearly understood. It should be understood that the embodiments shown in the drawings are not intended to limit the scope of the present invention, but are merely intended to illustrate the spirit of the technical solution of the present invention.
The invention provides a method for optimally distributing the deck area of a platform during the offshore thermal recovery and yield increase operation based on a particle swarm algorithm by comprehensively considering the available deck area of an offshore drilling and production platform and the occupied area and the importance of equipment required by the thermal recovery and yield increase operation. The method can arrange equipment with the highest total value degree on the premise of not exceeding the available area or space of the deck, and provides equipment site guarantee for offshore oil field thermal recovery or yield increase operation.
The particle swarm optimization based on the invention simulates the flight route in the foraging process of the bird swarm, and the optimal solution is searched by learning individual experience and swarm experience in a cooperative iteration way, so that the mathematical process is easy to realize, and no excessive parameters need to be adjusted.
In order to achieve the purpose, the embodiment of the invention adopts the following technical scheme:
as shown in fig. 1, a method for optimally allocating deck area of a platform during offshore thermal recovery and stimulation operations includes the following steps:
1) listing m equipment occupation areas S (i) and importance degrees Z (i) which are possibly needed during the offshore thermal recovery operation and the yield increasing operation, wherein i is 1-m, and defining the available area V of a platform deck.
The value of the equipment importance degree Z (i) can be determined according to the ratio of the number of times of selecting the equipment to be arranged to the total operation number of times in the past operation record, and the importance degree Z (i) determined by the method is more objective and real.
2) In the preset example, the number of particles N, the maximum iteration number T, the learning factor C1 equal to C2, the dimension D of the particles (the value D is equal to the number m of the equipment units), the maximum value Wmax and the minimum value Wmin of the inertia weight, the maximum value Vmax and the minimum value Vmin of the speed, and a penalty function coefficient Cf are preset.
3) The method comprises the steps of initializing x (i, j) positions of N particles (i represents the ith particle, j represents the jth equipment), wherein x (i, j) is 0 and represents abandon, x (i, j) is 1 and represents use, and the initial positions are represented by random numbers between 0 and 1 and represent that the states of m equipment are between abandon and use at first.
The velocities v (i, j) of the N particles are initialized, the initial velocity is between Vmin and Vmax, a positive velocity indicates an increase in x (i, j), and a negative velocity indicates a decrease in x (i, j).
4) Calculating an initial optimal position p (i, j) and an initial optimal value pbest (i) (namely the sum of the importance of the selected equipment), wherein i is 1 to N, and the initial optimal position p (i, j) of each particle is the initial position x (i, j) of the 3 rd step, and the initial optimal value pbest (i) is shown in the formula.
5) And calculating the initial global optimal position g and the initial global optimal value gbest of the whole particle swarm.
Traversing from the 1 st particle to the Nth particle, selecting the largest pbest (i) in all the N particles as an initial global optimal value gbest, and taking the corresponding particle position x (i, j) as an initial global optimal position g.
6) And (4) carrying out a first round of iterative operation (carrying out T rounds in total), updating the positions x (i, j) of all the N particles to obtain new x (i, j), recalculating the pbest (i) of each particle by using the step 4) according to the new positions x (i, j) of the N particles, selecting the maximum value as the global optimal value gbest after the first round of iteration, and newly taking the corresponding particle position x (i, j) as the global optimal position after the first round of iteration. The update procedure for position x (i, j) is as follows.
7) And then performing iteration from 2 to T, and sequentially recording the global optimal position g and the global optimal value gbest of each iteration, wherein the g and the gbest after the T iteration are the final global optimal position and the global optimal value.
In the above methodIn step 2), the number of particles N is 20 × m, the maximum number of iterations T is 30 × m, the learning factor C1 is C2 is 1.5, the dimension D of the particles is equal to the number of devices m involved, the recommended maximum value Wmax of the inertial weight is 0.9 and the minimum value Wmin is 0.4, and the maximum value of the velocity is 0.4
And minimum value
Coefficient of penalty function
In the formula (I), the compound is shown in the specification,
is the average value of the importance of the equipment, S (i) is the floor area of the equipment, m is the number of the equipment, and V is the total area of the deck.
The algorithm parameter setting in the steps comprises a fixed value and a function value, wherein four parameters of learning factors C1 and C2, a maximum value Wmax and a minimum value Wmin of the inertia weight are fixed values, and five parameters of the number N of particles, the maximum iteration time T, the maximum speed value, the minimum value and a penalty function coefficient are not fixed values but functions which change along with the area and the importance of the equipment.
In the conventional particle swarm optimization, the values of five parameters, namely the number N of particles, the maximum iteration number T, the maximum speed value, the minimum value and the penalty function coefficient, are fixed values, but the value taking method can cause the program to be incapable of running, so that the function value mode is adopted in the invention to ensure the normal running of the algorithm program. In addition, when the learning factors C1 and C2 and the four parameters of the maximum value Wmax and the minimum value Wmin of the inertia weight are fixed values, the calculation convergence rate is high.
In the method, the initial position of each particle in the step 3-4) is a random number between 0 and 1 instead of 0 or 1 per se, which indicates that the initial state of each device is a fuzzy state between use and abandonment instead of an exact alternative state. The fuzzy trade-off has the advantages that the trade-off of each device is equal initially, and the influence of personal preference on the trade-off of the devices is avoided.
In the above method, in step 4), the initial optimum value pbest (i) of the ith particle is as follows:
wherein i is 1 to N; x (i, j) is the initial position of the particle; z (j) is the importance of device j.
After pbest (i) is obtained, the total area v (i) of the device represented by each particle is calculated, for example, the total area v (i) of the device represented by the ith particle:
wherein i is 1 to N; x (i, j) is the initial position of the particle; s (j) is the area of the device j.
Pbest (i) is the initial optimum for the particle, provided that V (i) is less than or equal to the available area V;
if V (i) > usable area V, the initial optimum value pbest (i) ═ pbest (i) -Cf × [ V (i) -V ] for the particle.
In the above method, in step 5), the largest pbest (i) in all the particles is used as the initial global optimum value, and the corresponding particle position is used as the initial global optimum position, where the position is a random number between 0 and 1, and this indicates that the initial global optimum position is also a fuzzy state between use and abandonment.
In the above method, in step 6), the updating step of the particle position x (i, j) is as follows:
first, calculating a dynamic inertia weight w:
w＝Wmax-(Wmax-Wmin)×k/T
where k represents the kth iteration.
The velocity v (i, j) of the jth device for the ith particle is then updated as follows:
v (i, j) new w × v (i, j) + C1 × rand x [ p (i, j) -x (1, j) ] + C2 × rand x [ g-x (1, j) ]
If the obtained v (i, j) is not between Vmin and Vmax, the regularization processing is carried out:
v (i, j) New rand x (Vmax-Vmin) + Vmin
And calculating a position updating coefficient vx (i, j) of the jth equipment of the ith particle according to v (i, j), wherein the formula is as follows:
in the formula, i represents the ith particle, and j represents the jth equipment.
Then, the position of the ith particle is updated to obtain new x (i, j), and the formula is as follows:
wherein x (i, j) new-1 indicates that the device is selected, and x (i, j) new-0 indicates that the device is discarded; rand represents a random number between 0 and 1.
In step 6), the velocity v (i, j) is updated by calculating the dynamic inertia weight w, such as v (i, j) new w × v (i, j) + C1 × rand x [ p (i, j) -x (1, j) ] + C2 × rand x [ g-x (1, j) ], where the first term is the historical inertia, the second term is the individual experience, and the third term is the group experience. In the step, the individual experience and the group experience are comprehensively learned to obtain a new speed, so that the fault tolerance is stronger. The inertia weight w is a dynamic value which changes along with the iteration turns, and can provide the most appropriate inertia weight in each iteration turn, thereby preventing the phenomenon that the program can not be converged due to a static value.
And 6), obtaining a new speed v (i, j), and then further calculating a position updating coefficient vx (i, j), wherein the positions of all particles are updated to be 0 or 1 by comparing the position updating coefficient with the random number between 0 and 1, the pbest (i) of each particle is newly calculated by using the new position x (i, j), the maximum value is selected as the global optimal value after the first iteration, and the corresponding particle position is selected as the global optimal position after the first iteration. Thus, after the first iteration, all the device states are changed from the paste state to the exact alternative state. And subsequently, carrying out multiple rounds of iteration by the step 7) and optimizing the accepting and rejecting states.
In the step 7), the final global optimal position g and the final global optimal value gbest are obtained by repeating the mode of the step 6). The final global optimal position represents the preferred equipment and the abandoned equipment, and the final global optimal position represents that the sum of the values of the selected equipment is the highest and the area does not exceed the available area of the platform. Through multiple practical verifications, the setting of the parameters (including fixed values and function values) can ensure stable program operation and high convergence rate.
The particle swarm optimization based on the invention belongs to an artificial intelligent bionic algorithm, and by simulating the cooperative foraging behavior of biological groups such as bird groups and the like, the individual experience and the group experience are comprehensively considered, and the optimal solution is iteratively searched through reasonable parameter setting. The method has the advantages of high search speed, programmable realization, stable algorithm operation, easy acceptance and understanding by field engineers, memorability among iteration rounds, continuous approach to the optimal solution in each iteration round, and reliable result.
Examples
The invention will be further described with reference to the accompanying drawings, but the invention is not limited to the following examples.
As shown in FIG. 1, the optimal distribution method for the platform deck area during the offshore thermal recovery and stimulation operation provided by the invention comprises the following steps:
1) listing the possible 10 equipment occupied areas S and the importance Z during the offshore thermal recovery operation or the production increase operation, and defining the available deck area V of the platform as 1600 square meters.
2) In the preset calculation example, the number N of particles is 200, the maximum number of iterations T is 300, the learning factor C1 is C2 is 1.5, the dimension D of the particles is 10, the maximum value Wmax of the inertial weight is 0.9, the minimum value Wmin is 0.4, the maximum value Vmax of the velocity is 0.725, the minimum value Vmin is-0.725, and the penalty function coefficient Cf is 0.038.
3) The method comprises the steps of initializing positions x (i, j) of 200 particles (i represents the ith particle, j represents the jth equipment), wherein x (i, j) is 0 and represents abandon, x (i, j) is 1 and represents use, and the initial positions are represented by random numbers between 0 and 1 and represent that the states of 10 pieces of equipment are between abandon and use at first.
Particle position initialization
| No | Device 1 | Device 2 | Device 3 | Device 4 | Device 5 | Device 6 | Device 7 | Device 8 | Device 9 | Device 10 |
| x(1,j) | 0.51 | 0.55 | 0.91 | 0.54 | 0.13 | 0.94 | 0.08 | 0.28 | 0.83 | 0.47 |
| x(2,j) | 0.84 | 0.55 | 0.02 | 0.43 | 0.53 | 0.38 | 0.63 | 0.62 | 0.05 | 0.57 |
| … | … | … | … | … | … | … | … | … | … | … |
| x(200,j) | 0.81 | 0.65 | 0.49 | 0.94 | 0.99 | 0.09 | 0.77 | 0.02 | 0.53 | 0.36 |
The velocities v (i, j) of the 200 particles are initialized, the initial velocity is between Vmin and Vmax, a positive velocity means that x (i, j) is increased, and a negative velocity means that x (i, j) is decreased.
Particle velocity initialization
| No | Device 1 | Device 2 | Device 3 | Device 4 | Device 5 | Device 6 | Device 7 | Device 8 | Device 9 | Device 10 |
| v(1,j) | -0.34 | 0.48 | -0.52 | 0.25 | 0.16 | 0.13 | 0.48 | 0.60 | -0.37 | -0.10 |
| v(2,j) | -0.36 | -0.68 | -0.15 | -0.13 | -0.01 | -0.58 | 0.43 | 0.15 | -0.29 | 0.53 |
| … | ||||||||||
| v(200,j) | 0.59 | 0.08 | 0.59 | 0.40 | -0.41 | -0.69 | -0.12 | 0.49 | 0.05 | -0.11 |
4) The initial optimal position p (i, j) and the initial optimal value pbest (i) (i.e. the sum of the device importance) for each particle are calculated.
The initial optimal position p (i, j) of each particle is the initial position x (i, j) of step 3.
Calculating an initial optimum value pbest (i) for each particle, for example, an initial optimum value pbest (1) for the first particle, as follows:
pbest(1)＝0.51×0.6+0.55×0.75+…+0.47×0.85＝4.19
calculating the total area of the device represented by each particle, V (i), for example the total area of the device represented by the first particle, V (1):
V(1)＝0.51×190+0.55×210+…+0.47×130＝1081㎡
pbest (i) is the initial optimum for the particle, provided that V (i) is less than or equal to the available area V;
if V (i) > available area V, the initial optimum value of the particle is pbest (i) -Cf × [ V (i) -V ].
Thus, the initial optimum value pbest (i) (i 1 to 200, and 200 values in total) for each particle was obtained.
Initial optimal position and initial optimal value of each particle
5) And calculating the initial global optimal position g and the initial global optimal value gbest of the whole particle swarm.
Traversing from the 1 st particle to the 200 th particle, selecting the largest pbest (i) of the 200 particles as an initial global optimal value gbest, and taking the corresponding particle position x (i, j) as an initial global optimal position g.
In this example, the initial global optimum value, get, is 5.94.
The corresponding initial global optimal position is the 160 th particle, and the position specific information is as follows:
initial global optimum position and initial global optimum value of particle swarm
6) A first iteration (total of 300T) is performed, in which the 1 st to 200 th particles are traversed, and the 1 st particle is taken as an example, and the dynamic inertia weight w is first calculated:
w＝Wmax-(Wmax-Wmin)×1/T＝0.9-(0.9-0.4)×1/300＝0.89
in the formula, 1 represents the 1 st iteration.
Then, the speed of the jth equipment of the 1 st particle is updated, for example, the speed of the 1 st equipment is updated as follows:
v (1,1) new w × v (1,1) + C1 × rand x [ p (1, j) -x (1,1) ] + C2 × rand x [ g-x (1,1) ]
＝0.89×-0.34+1.5×rand×(0.51-0.51)+1.5×rand×(0.97-0.51)＝-0.24
If the obtained v (1, j) is not between Vmin and Vmax, the regularization processing is carried out:
v (1, j) New ═ rand x (Vmax-Vmin) + Vmin
New velocity of 1 st particle
| No | Device 1 | Device 2 | Device 3 | Device 4 | Device 5 | Device 6 | Device 7 | Device 8 | Device 9 | Device 10 |
| v(1,j) | -0.34 | 0.48 | -0.52 | 0.25 | 0.16 | 0.13 | 0.48 | 0.60 | -0.37 | -0.10 |
| v (1, j) new | -0.24 | 0.45 | -0.49 | 0.27 | 0.26 | 0.12 | 0.52 | 0.62 | -0.33 | -0.05 |
And calculating a position updating coefficient vx (1, j) of the jth equipment in the 1 st particle according to the new velocity v (1, j), wherein the position updating coefficient vx (1,1) of the 1 st equipment is expressed as follows:
and then updating the position of the 1 st particle, if vx (1, j) of the j-th equipment is greater than a random number rand between 0 and 1, selecting the j-th equipment if x (1, j) of the j-th equipment is 1, otherwise abandoning the equipment if x (1, j) is 0, thus obtaining a new position x (1, j) of the 1 st particle as follows:
new position of the 1 st particle
| No | Device 1 | Device 2 | Device 3 | Device 4 | Device 5 | Device 6 | Device 7 | Device 8 | Device 9 | Device 10 |
| v(1,j) | -0.34 | 0.48 | -0.52 | 0.25 | 0.16 | 0.13 | 0.48 | 0.60 | -0.37 | -0.10 |
| v (1, j) new | -0.24 | 0.45 | -0.49 | 0.27 | 0.26 | 0.12 | 0.52 | 0.62 | -0.33 | -0.05 |
| vx(1,j) | 0.44 | 0.61 | 0.38 | 0.57 | 0.56 | 0.53 | 0.63 | 0.65 | 0.42 | 0.49 |
| x (1, j) is new | 1 | 0 | 1 | 1 | 0 | 1 | 0 | 1 | 0 | 1 |
At this point, after the position x (1, j) of the 1 st particle in the first iteration is updated, the position x (2, j) of the 2 nd particle is continuously updated until the positions of all 200 particles are updated.
And (4) recalculating the pbest (i) of each particle by using the step 4) according to the new positions of 200 particles, selecting the maximum value as the global optimal value gbest after the first iteration, and newly taking the corresponding particle position x (i, j) as the global optimal position g after the first iteration.
7) And then performing 2 nd to 300 th iteration, and sequentially recording the global optimal position g and the global optimal value gbest of each iteration, wherein the g and the gbest after 300 iterations are the final global optimal position and the global optimal value. The final global optimum gbest in this example is 6.15. The final global optimal position g, as follows:
after the 300 th iteration, the global optimal position and the global optimal value of the particle swarm
The results show that: all the devices except the 5 th and 7 th devices can be transported to a platform, the total floor area is 1580 square meters, and the total value of the devices is 6.15.
The above description is only an exemplary embodiment of the present invention, and should not be taken as limiting the scope of the invention, and any person skilled in the art should understand that they can make equivalent changes and modifications without departing from the concept and principle of the present invention. It should be noted that the components of the present invention are not limited to the above-mentioned whole application, and various technical features described in the present specification can be selected to be used alone or in combination according to actual needs, so that the present invention naturally covers other combinations and specific applications related to the present invention.
Claims (10)
1. A method for optimal allocation of deck area on an offshore platform, the method comprising the steps of:
s1, determining the occupied area S (i) and the importance degree Z (i) of each of m pieces of equipment during the offshore thermal recovery operation or the yield increasing operation, wherein i is 1-m, and determining the available area V of a platform deck;
s2, performing T-round iteration on the accepting and rejecting states of m devices by using a particle swarm algorithm, wherein T is the maximum iteration number, sequentially recording the global optimal position g of the whole particle swarm of each round of iteration and the total importance sum gbest of the globally selected devices, and g and gbest after T-round iteration are the final global optimal position and the global optimal value.
2. The offshore platform deck area optimal allocation method of claim 1, wherein the step S2 comprises:
s21, presetting the number N of particles, the maximum iteration number T, learning factors C1 and C2, the dimension D of the particles, the maximum value Wmax and the minimum value Wmin of the inertia weight, the maximum value Vmax and the minimum value Vmin of the speed and a penalty function coefficient Cf;
s22, initializing positions x (i, j) of N particles, wherein i represents the ith particle, j represents the jth equipment, x (i, j) is 0 and represents abandon, x (i, j) is 1 and represents use, and the initial positions of the particles are represented by random numbers between 0 and 1;
s23, initializing the speeds v (i, j) of the N particles, wherein the initial speed is between Vmin and Vmax, the positive speed means that x (i, j) is increased, and the negative speed means that x (i, j) is decreased;
s24, calculating an initial optimal position p (i, j) and an initial optimal value pbest (i) of each particle, where the initial optimal value pbest (i) is the sum of the importance of the selected devices, where i is 1 to N, and N total values, and the initial optimal position p (i, j) of each particle is equal to the initial position x (i, j);
s25, calculating an initial global optimal position g and an initial global optimal value gbest of the whole particle swarm:
traversing from the 1 st particle to the Nth particle, selecting the maximum initial optimal value pbest (i) in all the N particles as an initial global optimal value gbest, and taking the corresponding particle position x (i, j) as an initial global optimal position g;
s26, performing a first round of iterative operation, updating the positions x (i, j) of all N particles, recalculating the initial optimal value pbest (i) of each particle according to the new positions x (i, j) of the N particles, selecting the maximum value as the global optimal value gbest after the first round of iteration, and taking the corresponding particle position x (i, j) as the global optimal position after the first round of iteration;
and S27, performing 2 nd to T th iterations according to the iteration method of S26, and sequentially recording the global optimal position g and the global optimal value gbest of each iteration, wherein the g and the gbest after the T iterations are the final global optimal position and the final global optimal value.
3. The method for optimal distribution of deck area of offshore platform according to claim 2, wherein in step S21, the number of particles N is 20 × m, the maximum number of iterations T is 30 × m, the learning factor C1 is C2 is 1.5, the dimension D of the particles is equal to the number of devices involved, the maximum value of the inertial weight Wmax is 0.9, the minimum value of the inertial weight Wmin is 0.4, and the maximum value of the velocity is 0.4
Minimum value of speed
Coefficient of penalty function
In the formula (I), the compound is shown in the specification,
is the average value of the importance of the equipment, S (i) is the occupied area of the equipment, m is the number of the equipment, and V is the total available area of the deck.
4. The method for optimally allocating the deck area of the offshore platform according to the claim 2 or the claim 3, wherein the initial position of each particle in the step S24 is a random number between 0 and 1, excluding 0 or 1.
5. The offshore platform deck area optimal allocation method according to claim 2 or 3, wherein in step S24, the initial optimal value pbest (i) of the i-th particle is as follows:
wherein i is 1 to N; x (i, j) is the initial position of the particle; z (j) is the importance of device j.
6. The optimal deck area allocation method for offshore platforms as claimed in claim 5, wherein after pbest (i) is calculated according to the formula, the method further comprises the following steps:
calculating the total area V (i) of the equipment represented by each particle, and the total area V (i) of the equipment represented by the ith particle:
wherein i is 1 to N; x (i, j) is the initial position of the particle; s (j) is the area of the device j;
pbest (i) is the initial optimum for the particle, provided that V (i) is less than or equal to the available area V;
if V (i) > usable area V, the initial optimum value pbest (i) ═ pbest (i) -Cf × [ V (i) -V ], Cf is the penalty function coefficient.
7. The offshore platform deck area optimal allocation method according to claim 2, 3 or 6, wherein the updating method of the position x (i, j) in the step S27 comprises:
first, the dynamic inertia weight w is calculated, and the formula is as follows:
w＝Wmax-(Wmax-Wmin)×k/T
wherein k represents the kth iteration, Wmax is the maximum inertia weight value, and Wmin is the minimum inertia weight value;
the velocity v (i, j) of the jth device for the ith particle is then updated as follows:
v (i, j) new w × v (i, j) + C1 × rand x [ p (i, j) -x (1, j) ] + C2 × rand x [ g-x (1, j) ]
Wherein C1 and C2 are learning factors;
if the obtained v (i, j) is not between Vmin and Vmax, the regularization processing is carried out:
v (i, j) new rand x (Vmax-Vmin) + Vmin;
and calculating a position updating coefficient vx (i, j) of the jth equipment of the ith particle according to v (i, j), wherein the formula is as follows:
wherein i represents the ith particle, and j represents the jth equipment;
then, the position of the ith particle is updated to obtain new x (i, j), and the formula is as follows:
wherein x (i, j) new-1 indicates that the device is selected, and x (i, j) new-0 indicates that the device is discarded; rand represents a random number between 0 and 1.
8. Method for optimal allocation of deck area of an offshore platform according to claim 1 or 2 or 3 or 6, characterized in that said final global optimal position represents preferred equipment and/or abandoned equipment, the final global optimal value representing the highest sum of values of the selected equipment, the area not exceeding the available area of the platform.
9. A computer device comprising a memory and a processor; the memory for storing a computer program; the processor, when executing the computer program, for performing the steps of the offshore platform deck area optimal allocation method according to any of claims 1 to 8.
10. A computer storage medium, characterized in that the storage medium has stored thereon a computer program which, when being executed by a processor, carries out the steps of the offshore platform deck area optimal allocation method according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110510138.6A CN113139695A (en) | 2021-05-11 | 2021-05-11 | Offshore thermal recovery and production increase period deck distribution method, computer device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110510138.6A CN113139695A (en) | 2021-05-11 | 2021-05-11 | Offshore thermal recovery and production increase period deck distribution method, computer device and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113139695A true CN113139695A (en) | 2021-07-20 |
Family
ID=76817133
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110510138.6A Pending CN113139695A (en) | 2021-05-11 | 2021-05-11 | Offshore thermal recovery and production increase period deck distribution method, computer device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113139695A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113468793A (en) * | 2021-07-21 | 2021-10-01 | 中海石油(中国)有限公司 | Cluster well platform position optimization method, system and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102508431A (en) * | 2011-11-04 | 2012-06-20 | 江苏科技大学 | Thrust distribution method for power positioning system of offshore drilling platform |
| CN103984989A (en) * | 2014-05-08 | 2014-08-13 | 中国石油大学(华东) | Method and system for optimizing layout of oil rig device |
| US20180107952A1 (en) * | 2016-10-14 | 2018-04-19 | Conocophillips Company | Connectivity based approach for field development optimization |
| CN107992965A (en) * | 2017-11-27 | 2018-05-04 | 河北省水利工程局 | Small watershed water and soil resources coordination optimizing method based on particle cluster algorithm |
| CN110782087A (en) * | 2019-10-24 | 2020-02-11 | 大连海事大学 | Offshore emergency material optimal scheduling method and system |
| EP3644267A1 (en) * | 2018-10-26 | 2020-04-29 | Tata Consultancy Services Limited | Method and system for online monitoring and optimization of mining and mineral processing operations |
-
2021
- 2021-05-11 CN CN202110510138.6A patent/CN113139695A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102508431A (en) * | 2011-11-04 | 2012-06-20 | 江苏科技大学 | Thrust distribution method for power positioning system of offshore drilling platform |
| CN103984989A (en) * | 2014-05-08 | 2014-08-13 | 中国石油大学(华东) | Method and system for optimizing layout of oil rig device |
| US20180107952A1 (en) * | 2016-10-14 | 2018-04-19 | Conocophillips Company | Connectivity based approach for field development optimization |
| CN107992965A (en) * | 2017-11-27 | 2018-05-04 | 河北省水利工程局 | Small watershed water and soil resources coordination optimizing method based on particle cluster algorithm |
| EP3644267A1 (en) * | 2018-10-26 | 2020-04-29 | Tata Consultancy Services Limited | Method and system for online monitoring and optimization of mining and mineral processing operations |
| CN110782087A (en) * | 2019-10-24 | 2020-02-11 | 大连海事大学 | Offshore emergency material optimal scheduling method and system |
Non-Patent Citations (4)
| Title |
|---|
| 唐承: "基于灵敏度分析的***可靠性稳健分配优化方法", ***工程理论与实践, vol. 37, no. 7, pages 1903 - 1909 * |
| 杨晓燕;陈国龙;郭文忠;: "基于粒子群优化的最小属性约简算法", 福州大学学报(自然科学版), vol. 38, no. 02, pages 193 - 197 * |
| 王逢德;肖文生;刘健;徐葱葱;杨旭;耿玉豪;: "基于改进粒子群算法的海洋钻机***布局优化", 中国石油大学学报(自然科学版), vol. 40, no. 02, pages 123 - 128 * |
| 黄川;吕靖;艾云飞;: "基于水域精细划分的VTS雷达站选址配置优化", 交通运输工程学报, no. 03, pages 198 - 211 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113468793A (en) * | 2021-07-21 | 2021-10-01 | 中海石油(中国)有限公司 | Cluster well platform position optimization method, system and storage medium |
| CN113468793B (en) * | 2021-07-21 | 2024-05-24 | 中海石油(中国)有限公司 | Cluster well platform position optimization method, system and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111065103B (en) | Multi-objective optimization wireless sensor network node deployment method | |
| CN112016812B (en) | Multi-unmanned aerial vehicle task scheduling method, system and storage medium | |
| US6269351B1 (en) | Method and system for training an artificial neural network | |
| CN104636801A (en) | Transmission line audible noise prediction method based on BP neural network optimization | |
| CN108171315B (en) | Multi-unmanned aerial vehicle task allocation method based on SMC particle swarm algorithm | |
| CN108573303A (en) | It is a kind of that recovery policy is improved based on the complex network local failure for improving intensified learning certainly | |
| CN110288048B (en) | Submarine pipeline risk assessment method of SVM directed acyclic graph | |
| Thirumalainambi et al. | Training data requirement for a neural network to predict aerodynamic coefficients | |
| CN110363343A (en) | A kind of the GROUP OF HYDROPOWER STATIONS intelligent optimization dispatching method and system of mixed self-adapting | |
| Janikow | A genetic algorithm method for optimizing the fuzzy component of a fuzzy decision tree | |
| CN113139695A (en) | Offshore thermal recovery and production increase period deck distribution method, computer device and storage medium | |
| CN115689070B (en) | Energy prediction method for optimizing BP neural network model based on monarch butterfly algorithm | |
| CN105808582A (en) | Parallel generation method and device of decision tree on the basis of layered strategy | |
| Lin et al. | Designing mamdani type fuzzy rule using a collaborative FCM scheme | |
| CN113128617B (en) | Spark and ASPSO based parallelization K-means optimization method | |
| CN117519244B (en) | Unmanned plane cluster collaborative detection multi-target path planning method and system | |
| Reddy et al. | Capacitor placement using fuzzy and particle swarm optimization method for maximum annual savings | |
| Korejo et al. | Multi-population methods with adaptive mutation for multi-modal optimization problems | |
| CN114676640A (en) | Building arrangement method based on genetic algorithm and MADDPG algorithm | |
| Teoh et al. | A columnar competitive model with simulated annealing for solving combinatorial optimization problems | |
| Chen et al. | Training fuzzy logic controller software components by combining adaptation algorithms | |
| CN107944623A (en) | A kind of optimization method and its application based on saccharomycete budding breeding | |
| CN112344934B (en) | GNG network-based construction method for deletable environment topology map | |
| CN117268391B (en) | Intelligent planning method and system for deformed aircraft based on target layered architecture | |
| CN113468793B (en) | Cluster well platform position optimization method, system and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |