Neural Fuzzy Control of the Indoor Air Quality Onboard a RO–RO Ship Garage

Abstract

Air quality control is necessary to improve the environmental condition in particular Indoor Air Quality (IAQ), which has a direct impact on a living organism. In marine application, the International Maritime Organization (IMO) made standards to determine the gas emission limits and specify the air circulation in IAQ in addition to employing in energy-efficient and energy management system which leads to reduce emission and enhance the environmental condition by efficient and economical way. Applying advanced energy management policies and control could be achieved by energy consumption. In this paper, an intelligent neuro-fuzzy controller has been designed to model and control carbon monoxide (CO) concentration for a real case study of a high-speed craft passenger ship with a vehicle garage onboard for a liner between Egypt and Saudi Arabia ports. The relation between emitted CO and the number of cars and their positions has been modelled using artificial neural network (ANN). The ANN model has been built and validated based on real measurements of CO at different ventilation conditions of the case study. Different fuzzy controllers, fixed and adaptive, are designed to control CO during loading and unloading states. Scaling factors of fuzzy controller are adapted using two different ways namely Supervisor Fuzzy Controller (SFC) and Particle Swamp Optimization (PSO). Simulation results have analysed the proposed control system at different conditions. The obtained outcomes manifest the fact that the controller tends to work robustly and efficiently to maintain CO at the permissible allowed range.