A Multi-Expert System for chlorine electrolyzer monitoring

摘要: The Chlor-Alkali production is one of the largest industrial scale electro-synthesis in world. Plants with more than 1000 individual reactors are common, where chlorine and hydrogen only separated by 0.2mm thin membranes. Wrong operating conditions can cause explosions highly toxic gas releases, but also irreversible damages very expensive cell components dramatic maintenance costs loss. In this paper, a Multi-Expert System based on first-order logic rules Decision Forests proposed to detect any abnormal membrane electrolyzers advice operator accordingly. Robustness missing data - which represents an important issue applications general achieved means Dynamic Selection strategy. Experiments performed real-world electrolyzer indicate that system significantly different modes, even presence high levels or ''wrong'' data, as consequence maloperation -, essential for precise fault detection generation.