Hybrid Compressor Model for Optimal Operation of Compressed Dry Air System in LCD Production Industry

Abstract

Compressed dry air (CDA) is a widely used utility in liquid crystal display (LCD) production industry usually utilized as an air knife and an air curtain for room and glass cleaning to prohibit particles from entering the chamber. CDA is consumed in various sites of the production line and demand for CDA fluctuates largely from moment to moment. Therefore, it is common to supply compressed air with a number of small-capacity compressors rather than few large-capacity ones. To find an optimal operating strategy of such a compressor network, a first hybrid modeling technique of an ideal model and an empirical model is used to predict the efficiency and power consumption of each compressor. Ideal compression work is calculated using thermodynamic equation with slight modification. An artificial neural network is configured to predict the efficiency. Then, actual power consumption of each compressor is given by the ratio of ideal work to efficiency. Then, optimization procedure is applied to search optimal operating configuration. The proposed method is applied to LCD production industry to show good prediction accuracy. Energy saving of total compression work is achieved by optimization scenario of segregating full-load and part-load compressor group.