Goto

Layer | Fill | Outline |
---|

Theme | Visible | Selectable | Appearance | Zoom Range (now: 0) |
---|

Fill | Stroke |
---|---|

Abstract Steam injection is a common EOR method for the recovery of heavy crude. This type of oil, or bitumen, is extremely viscous at the reservoirs standard temperature and almost immobile. As a result, steam and other fluids are injected into these reservoirs to enable the transfer of latent heat to the oil-bearing formation and allow them to flow. The paper introduces a new and efficient algorithm for optimal steam allocation from a series of generators given a changing delivery target at certain time intervals. The solution is addressing the efficiency of the generators as well as the steam distribution to producing wells as a key component in the design of steam-based thermal operations. Particle Swarm Optimization (PSO), motivated by the social behavior of bird flocks or fish schooling, was first introduced by Kennedy and Eberhart as a population-based optimization technique. In 2004 Sun, Xu and Feng proposed a new version of PSO, Quantum-behaved Particle Swarm Optimization (QPSO), which was inspired by quantum mechanics and trajectory analysis of PSO mechanism. As a quantum system, characterized as an uncertain system when compared to the classical stochastic systems, every particle can appear at any position within a certain probability, thus enabling the swarm to search in the whole feasible region. Additionally, in the QPSO algorithm there are no velocity vectors for particles, thus it has fewer parameters to be adjusted, which makes it easier to implement. In this paper, a modified QPSO algorithm was employed to solve the steam generators optimization problem described above. First, efficiency curves are established for each one of the different steam generators. For the group of steam generators considered, the objective was to maximize the sum of their efficiencies by adjusting the generated steam from every generator. Additionally, there are operational and design constraints on the generators such as the minimum and maximum amount of steam generated from each generator, the sum of the steam output from all generators, steam quality, etc. Several experiments were generated and are described in the paper. The results show that the modified QPSO was able to produce an optimum realistic solution significant superior to current practices in the field.

algorithm, Artificial Intelligence, constraint, Efficiency, evolutionary algorithm, generator, machine learning, modified quantum-behaved particle swarm optimization, optimization, optimization problem, particle, Particle Swarm Optimization, proceedings, QPSO algorithm, quantum-behaved particle swarm optimization, search space, steam generator, steam generator optimization, swarm optimization, Upstream Oil & Gas

SPE Disciplines: Data Science & Engineering Analytics > Information Management and Systems > Artificial intelligence (1.00)

Technology:

Cao, Yaofeng (University of Science and Technology Beijing) | He, Fulian (China University of Mining and Technology) | Li, Kaiqing (University of Science and Technology Beijing) | Han, Hongqiang (University of Science and Technology Beijing) | Xie, Shengrong (China University of Mining and Technology) | Yan, Hong (China University of Mining and Technology)

The initial stress field is very important in rock mechanics. The particle swarm optimization (PSO) algorithm developing in recent years is a stochastic optimization algorithm based on swarm intelligence. By use of the theory of particle swarm optimization (PSO) algorithm, a modified PSO algorithm is proposed for the calculation of the initial stress field. PSO algorithm possesses advantages. Then by use of integrating the advantages of other traditional methods and taking into account the factors affecting the initial stress, the reasonability of the present method is shown by a case study. The intelligent inversion analysis of initial stress field in Xinyuan coal mine is carried out by using the particle swarm (PSO) algorithm. The field results show the method is accurate and high velocity which conforms well to the practical data.

The initial stress field is a never mining-induced natural stress that lies in the strata. Also as we known that the original rock stress, rock initial stress and so on. It is the fundamental forces that caused by mining engineering, civil engineering, water conservancy and hydropower, and various other underground or open-pit rock and soil excavation deformation and destruction. To achieve a scientific design and decision-making in mining and geotechnical engineering excavation, it is a necessary precondition that accurate information on initial stress. It is decided by several tectonic movements, which include the loading and unloading caused by crustal movements, the thermal stress caused by magmatic activity, changes in physical and chemical properties of rock mass and so on. However, it is impossible to solution quantitatively, based on the development history of the earth, the initial stress field for the engineering application. It mainly depend on the measured data, but a few measuring points is hard to meet the needs of construction projects.

algorithm, Artificial Intelligence, back analysis, convergence rate, eberhart, Engineering, equation, evolutionary algorithm, initial stress field, inversion analysis, machine learning, metals & mining, optimization, optimization back analysis, particle, particle swarm algorithm, Particle Swarm Optimization, Proc, PSO algorithm, solution space, Upstream Oil & Gas

Country:

- North America > United States (0.48)
- Asia > China (0.33)

Industry:

- Materials > Metals & Mining (0.55)
- Construction & Engineering (0.55)
- Energy > Oil & Gas > Upstream (0.35)

SPE Disciplines: Data Science & Engineering Analytics > Information Management and Systems > Artificial intelligence (1.00)

Technology:

Seismic traveltime tomography is an optimization problem that requires large computational efforts. Therefore, linearized techniques are commonly used for their low computational cost. These local optimization methods are likely to get trapped in a local minimum as they critically depend on the initial model. On the other hand, common global optimization techniques such as Genetic Algorithm (GA) or Simulated Annealing (SA) are insensitive to the initial model but are computationally expensive and require many controlling parameters. Particle Swarm Optimization (PSO) is a rather new global optimization approach with few parameters that has shown excellent convergence rates and is straightforwardly parallelizable, allowing a good distribution of the workload. However, while it can traverse several local minima of the evaluated misfit function, classical implementation of PSO can get trapped in local minima at later iterations as particles inertia dim.

We propose a Competitive PSO (CPSO) to allow "worst" particles to explore the model parameter space and eventually find a better minimum. A tomography algorithm based on CPSO is successfully applied on a 3D synthetic case corresponding to a typical calibration shot geometry in a hydraulic fracturing context.

Presentation Date: Tuesday, October 18, 2016

Start Time: 1:25:00 PM

Location: Lobby D/C

Presentation Type: POSTER

annual meeting, Artificial Intelligence, competitive particle swarm optimization, CPSO, evolutionary algorithm, geometry, global minimum, iteration, machine learning, optimization problem, particle, Particle Swarm Optimization, premature convergence, PSO, Rastrigin function, seg seg international exposition, Traveltime Tomography, Upstream Oil & Gas, velocity model

SPE Disciplines: Data Science & Engineering Analytics > Information Management and Systems > Artificial intelligence (1.00)

Technology:

Lu, Yun (Huazhong University of Science and Technology) | Zhou, Kai (Dalian Naval Academy) | Li, Weijia (Huazhong University of Science and Technology) | Tian, Wenzhuo (Huazhong University of Science and Technology) | Wang, Xiao (China Shipbuilding Industry Corporation)

**Abstract**

Based on a 6-DOF flight simulator driven by electricity, the experiments show that certain parameters of the AC servo driver have a great impact on the stability of the platform. The study of the optimization for controlling parameters of the AC servo drivers is carried out by the continuous change to the controlling parameters, aiming to improve the performances of the platform in stabilization and frequency response by Particle Swarm Optimization. The result shows that the Particle Swarm optimization algorithm is fitted for the system of the controlling parameter optimization.

6-dof flight simulator, air transportation, Artificial Intelligence, control parameter, cylinder, evolutionary algorithm, fitness function value, flight simulator, integral time constant, iteration, machine learning, optimal solution, optimization, optimization algorithm, parameter optimization, particle, Particle Swarm Optimization, platform, servo motor, stability

Industry:

- Transportation > Air (0.72)
- Government > Military > Training (0.62)

Technology:

Chang, Qi (Harbin Engineering University) | Feng, Guo-qing (Harbin Engineering University) | Li, Chen-feng (Harbin Engineering University) | Ren, Hui-long (Harbin Engineering University, HEU Qingdao Ship Science and Technology Co Ltd) | Shen, Xiao-xi (Harbin Engineering University)

ABSTRACT.

For a large quantity of variables and low efficiency problems in ship structural optimization, based on the particle swarm optimization (PSO), a structural optimization method for deck grillage of large oil tanker is carried out. The mid-section of an 8,0000 tons tanker is taken as an example, while the minimum cross-sectional area taken as the design target and the dimensions of the structural members in sides and bottom taken as constants, the original dimensions and arrangements parameters of the ship to be optimized are regarded as the initial values in PSO. According to the related descriptive requirements of the common structural rules for bulk carriers and oil tankers (HCSR), PSO is innovatively integrated into the optimization process of the target ship deck structure through the self-programming program, where the specifications of common shipbuilding plating and stiffeners are proposed as the alternative material library. Compared to the original structures, the weight of the ship decreases 2.81% by using the optimal design method based on PSO presented in this study, which further proves that the proposed structural optimization method for deck grillage of large oil tanker based on PSO is effective to deck grillage's structural optimization combined with finite element analysis.

INTRODUCTION

Common Structural Rules for Bulk Carriers and Oil Tankers (CSR) (IACS, 2006) are divided into two parts: the Common Structural Rules for Bulk Carriers (CSR-BC) and the Common Structural Rules for Oil Tankers (CSR-OT), which are compiled by different members of the International Association of Classification Societies (IACS). As a result, the different technical routes and technological backgrounds of the two parts lead to uncoordinated problems in commonness (Gang and Daokun, 2011). In order to harmonize the two parts and eliminate these unnecessary differences, on July 1, 2012, the first draft of HCSR was promulgated (IACS, 2015) and the self-trial in each classification society was completed in 2013. On July 1, 2015, HCSR formally came into force.

Artificial Intelligence, deck grillage, design variable, dimension, evolutionary algorithm, freight & logistics services, genetic algorithm, machine learning, marine transportation, oil tanker, optimization, optimization problem, particle, Particle Swarm Optimization, PSO, requirement, ship structure, stiffener, structural optimization method, Thickness

Industry:

- Transportation > Marine (1.00)
- Transportation > Freight & Logistics Services > Shipping > Tanker (1.00)
- Energy > Oil & Gas (1.00)

Technology:

Thank you!