A Synergetic Intelligent Fault Prognosis Framework to support Product Life Cycle Considering Environmentally Conscious Production

Abstract

The recent problems of increased oil prices, global warming, and environmental pollution highlighted the urgent need for cost effective, reliable and environmentally conscious production process. Hence to achieve clean and healthy production, the chemical process industry strives to continually improve their preparedness and awareness through adaptive inference logic by effectively extracting and signaturing cascade clues from past experiences and predicting the possible scenarios of risk and its sources. These sources are usually related to equipment life cycle, starting from suppliers' evaluation and ending by its salvage or disposal. Methods are thus needed to effectively utilize data collected and knowledge available in order to make the right decision at the right moment. Despite the considerable technological advancement, these decisions still depend heavily on human expertise, which is, although very valuable, are subject to errors, and may be lost due to death, retirement or resignation. Therefore, an integrated equipment health management system that takes into consideration the equipment life cycle, which leads to environmentally conscious production, is proposed. In order to manage and develop environmentally conscious plant operation, it is essential to provide a synergetic intelligent fault diagnosis and prognosis framework embedded in systematic interoperable platform with respect to product life cycle, process safety and environmental measures. The proposed system employs a systematic expert knowledge structure considering operation execution, process safety and control, warranty policies, and environmental issues during equipment life cycle to assist the user in evaluating uncertainties and the process of decision making.

Ontology-Based Support for Hazard and Operability Studies

“…• a framework to support fault prognosis in gas and oil production plants [6], • conceptual ontology for HAZOP studies [7],…”