Study Of Intelligent Soft Sensor Modeling For Furnace Temperature Of Coal-Water Slurry Gasifier And It's Application

China is rich in coal resources but poor in petroleum and natural gas resources, this special structure of energy resources lead to the long-term status that coal resources in a dominant position. Clean coal technology, which has been developed to convert raw coal into syngas (composed primarily of H2 and CO) with advantages such as pollutants reduction, high efficiency of energy conversion and so on, meets the challenge of worldwide energy safety and sustainable development. The Opposed Multi-Burner (OMB) Coal-Water Slurry (CWS) gasification is a new large-scale coal gasification technology with higher product yield, lower oxygen and coal consumption than that of Texaco CWS gasification technology. However, current furnace temperature measurements of OMB and other gaisifiers are unstable and even short-life due to the extreme internal environment:high temperature and pressure, strong air-steam and corrosion, etc.Therefore a new data-driven soft sensor modeling technique for furnace temperature of OMB gasifier is proposed and studied in this paper, which including multiple-linear regression based on least square, LS-SVM regression, predictive model integrating Principal Component Analysis (PCA) and BP neural network, etc. Also the selection of secondary variables and model structure of BP neural network are studied in this paper. Results indicate that, the data-driven soft sensor model has a promising performance with good predictive precision.Considering possible variability in actual production conditions, an intelligent soft sensor multiple-modeling for furnace temperature of OMB gasifier based on rule-Fuzzy C-Means (FCM) clustering is proposed and additional rule base is studied in this paper.Besides, a multiple Oxygen-Coal ratio coordinated policy is also proposed in this paper to keep the furnace temperature's balance and ensure gasification plant's stable production.