摘要
从工业生产过程实用的观点出发,鉴于小波变换能有效地对信号进行消噪的优点和支持向量机的卓越学习性能,探讨基于小波和支持向量机的故障趋势预报,并结合专家系统建立解释机制。将其用于工业精对苯二甲酸(PTA)生产过程中对二甲苯(PX)氧化反应器尾氧浓度故障预报的结果表明:该方法能准确地对尾氧浓度故障趋势进行预测,并同时给出故障产生的概率大小,为PX氧化反应器的安全平稳操作提供了保证。
The wavelet transform can eliminate the signal noise and support vector machine （SVM） is a class of regression method with good generalization ability. In terms of view of industry process, this paper presents a novel fault trend prediction method based on the wavelet and SVM. Combined with expert system, this technique is applied to fault trend prediction of tail oxygen concentration in the PX oxidation reactor of industrial purified terephthalic acid （PTA） process. This technique makes it possible to predict fault trend of tail oxygen concentration and diagnose the fault probability. It ensures the safe and stable operation of PX oxidation reactor.
出处
《计算机与应用化学》
CAS
CSCD
北大核心
2008年第1期73-76,共4页
Computers and Applied Chemistry
