Abstract
The improvement of operational planning in the field of oil refinery management is becoming increasingly essential and valid. The influential primary factor, among others, is the ever-changing economic climate. The industry must continually assess the potential impacts of variations in the final product demand, price fluctuations, crude oil compositions and even seek out immediate opportunities within the market. The Master Production Schedule (MPS) is a planned process within the Production Management System that provides a mechanism for active collaboration between the marketing and manufacturing processes. However, the problem of MPS is a predictable non-deterministic, polynomial-time and NP-hard combination optimisation issue. The global search for the best solution to the MPS problem involves determination and funds that many industries are reluctant to provide. Hence, the alternative approach using meta-heuristics could provide desirable and workable answers in a realistic computing period. In this paper, a unique hybrid Multi-Objective Evolutionary Imperialist Competitive Algorithm (MOEICA) is proposed. The algorithm combines the advantages of an Imperialist Competitive Algorithm (ICA) and a Genetic Algorithm (GA) to optimise a multi-objective master production schedule (MOMPS). The primary objective is to integrate the ICA with GA operators. The paper will also apply the optimised MOMPS to the Kalak Refinery System (KRS) operations using the proposed algorithm. The application involves determining the available capacity of each production line by estimating the parametric values for all failures. In addition, the gross requirements using demand forecasting and neural networks are defined. The proposed algorithm proved efficient in resolving the issues of the MOMPS model within KRS compared to the NSGAII and MOPSO algorithms. The results reflect that the novel MOEICA algorithm outperformed NSGAII and MOPSO in almost all measurements.
Highlights
Oil refinery production planning is a vital but complex, intricate system
In this formulation, each character expresses the value as follows. p: Total number of planning periods, TH: Total planning horizon, EIkp: Ending inventory level generated for product k at period p, RNMkp: Requirements not met for product k at period p, BSSkp: Quantity below safety inventory level for product k at period p, BIkp: Initial inventory level of the product k at period p, OHk: Initial available inventory, at the first scheduling period, GRkp: Gross requirement for product k at period p, SSkp: Safety inventory level for product k at period p, MPSTkp: Total quantity to be manufactured of the product k at period p, n: The number of days in each planning period
The findings indicate that the superior algorithm based on performance is Multi-Objective Evolutionary Imperialist Competitive Algorithm (MOEICA) as evident in the quality metric; Quality Metric (QM) = 1
Summary
Oil refinery production planning is a vital but complex, intricate system. Production plan optimisation requires a mathematical model to represent the production system that can be utilised by the optimisation model. For a manufacturing company to remain competitive in a global market, the customer’s requirements must be consistently and promptly met with a high standard of products and services This is challenging for industry decision-makers, in current market conditions. A hybrid Multi-Objective Evolutionary Algorithm (MOEICA) has been proposed to solve a multi-objective MPS problem. This algorithm applies the concepts of the Imperialist Competitive Algorithm (ICA) and the Genetic Algorithm (GA). The study exposed some weaknesses of simulated annealing such as overcoming the local optimum (Soares and Vieira, 2008) developed a novel genetic algorithm structure for resolving MPS problems. A detailed explanation of the mathematical model is presented in the paper: Min EI
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
