期刊名称：International Journal of Distributed Sensor Networks
印刷版ISSN：1550-1329
电子版ISSN：1550-1477
出版年度：2016
卷号：2016
DOI：10.1155/2016/4145373
出版社：Hindawi Publishing Corporation
摘要：Aiming at the synthesis process through the ethylene polymerization by virtue of fluidized bed reactors, this paper proposed a different approach for agglomeration monitoring and early alarming in polymerization reaction with Gaussian test of wavelet packet entropies from low-frequency audible acoustic signals. In comparison to high-frequency acoustic emission signals, audible acoustic signals can reduce the signal bandwidth, simplify the signal processing circuit, facilitate the real-time measurement, and fault detection. Compared with the approach based on regression modeling and pattern recognition, this approach can overcome the defects of false alarm and missing alarm caused by inadequate samples and weak generalization capability of diagnosis model and is easy to be implemented. Experiments in a pilot plant have verified the effectiveness of the approach, and earlier warning could be realized compared with the existing approaches on the production apparatus (material level detection and temperature measurement).
