With the development of industrial information technology, deep learning (DL) has been successfully applied in chemical process fault detection. However, the features of incipient faults could not be more evident at the initial stage, which makes it difficult for deep learning to fully mine the feature probability information, resulting in poor performance of incipient fault monitoring. This paper proposes an intelligent predictive model based on mechanistic modeling to predict incipient faults and determine optimal response times for vinyl chloride production (VCP) processes. Firstly, a dynamic simulation of the VCP production process is performed to obtain datasets of early faults. Secondly, data dimensionality reduction is performed by cleverly combining spearman ranking correlation coefficient (SRCC) and slow feature analysis (SFA). Then, a long short-term memory network (LSTM) with attention mechanism (AM) is built to predict the future trends of key variables. Finally, the optimal response time for different types of incipient faults is determined by comparing the effectiveness of various control schemes. Compared with traditional methods, the R2 of the proposed prediction model corresponding to different step sizes can reach 99.7%, 99.5%, 99.2%, and 98.7%. In addition, the response times for single and parallel faults are 2 and 2.5 h, which helps to control and eliminate potential incidents in advance.

中文翻译：

---

基于深度学习的氯乙烯生产过程初期故障智能预测


随着工业信息技术的发展，深度学习 （DL） 已成功应用于化工过程故障检测。然而，初期故障的特征在初始阶段再明显不过了，这使得深度学习难以充分挖掘特征概率信息，导致初期故障监测性能不佳。本文提出了一种基于机理建模的智能预测模型，用于预测初期故障并确定氯乙烯生产 （VCP） 过程的最佳响应时间。首先，对 VCP 生产过程进行动态仿真，以获得早期故障的数据集;其次，巧妙地结合 spearman 排序相关系数 （SRCC） 和慢特征分析 （SFA） 进行数据降维;然后，构建具有注意力机制 （AM） 的长短期记忆网络 （LSTM） 来预测关键变量的未来趋势;最后，通过比较各种控制方案的有效性来确定不同类型初期故障的最佳响应时间。与传统方法相比，所提预测模型对应不同步长的R2可以达到99.7%、99.5%、99.2%和98.7%。此外，单个和并联故障的响应时间分别为 2 小时和 2.5 小时，这有助于提前控制和消除潜在事故。