Multi-objective optimization of petroleum engineering problems using a hybrid workflow: Combination of particle swarm optimization, fuzzy logic, imperialist competitive algorithm and response surface methodology

Optimization techniques are used to find the strategies for chemically enhanced oil recovery in a sandstone reservoir. This research develops a multi-objective optimization methodology by combining experimental design methods and artificial intelligence techniques. The capability of this hybrid artificial intelligence methodology is evaluated in the optimal design of control variables to achieve the highest performance of a surfactant/polymer injection project into a sandstone reservoir. In the first step, a two-level full factorial design is used to screen initial control variables. Thereafter a response surface methodology (RSM) is employed to optimize the RF and NPV of a CEOR application. The neuro-simulation technique provides the required outputs for screening and RSM designs. The performance of network is improved using the imperialist competitive algorithm (ICA). Having precise fitness functions, multi-attribute optimization was performed using particle swarm optimization (PSO) and fuzzy logic (FL). This paper discusses the advantages of different perspectives over single-objective approaches. Using the RF-objective PSO algorithm, RF exceeded 64% of original oil in place (OOIP), while the profit of project slumped to $5.90 MM. On the other hand, NPV-attribute PSO increased NPV to $8.48 MM. Meanwhile, RF, as the technical success of the project, plunged to less than 53% OOIP. However, the proposed multi-objective algorithm increased RF to 57% OOIP with NPV of $8.11 MM, solving the trade-off between technical and economic terms. The results of this study indicate the efficacy of proposed hybrid workflow for multi-attribute decision-making of CEOR field implementation.