摘要
为了保证间歇生产过程的安全、可靠运行,人们不仅希望在过程发生故障后能够及时进行故障诊断,更希望在只有微小故障征兆出现时就能够对故障的发展进行预报。对间歇过程进行故障预报研究已经成为目前过程控制领域的一个重要研究方向。针对间歇生产过程发生渐变故障的特点,结合Fisher判别分析方法,提出了基于特征投影差异度的故障预报方法。通过建立特征投影差异度的时间序列模型,预报未来生产批次的差异度,并将其与差异度阈值对比,进而实现间歇过程的故障预报及故障诊断。通过注射成型生产过程的数据对该方法进行实验验证,结果表明了所提方法的有效性。
In order to ensure the safety and reliability of batch production processes, people not only hope to diagnose fault timely when it occurs but also hope to forecast the incipient fault in the initial stage when the fault symptom is not evident. Nowadays, research on batch process fault prediction has become an important topic in process control field. According to the characteristics of incipient fault of batch process, combined with Fisher discriminant analysis, a fault prediction method based on feature projection difference is proposed in this paper. In this method, the time se- quence model of feature projection difference is established, the difference for the subsequent batch is predicted and compared with the difference threshold ,then the fault prediction and fault diagnosis for batch processes can be real- ized. The data of an injection molding production process are used to verify the proposed method, and the experiment results prove the effectiveness of the proposed method.
出处
《仪器仪表学报》
EI
CAS
CSCD
北大核心
2014年第2期441-446,共6页
Chinese Journal of Scientific Instrument
基金
国家自然科学基金(61374146
61174130)
中央高校基本科研业务费专项资金(N110304010
N120404020)资助项目
关键词
故障预报
特征投影差异度
间歇过程
时间序列
fault prediction
feature projection difference
batch process
time sequence
