The barely satisfactory monitoring situation of the hypertoxic fluorochemical engineering processes requires the application of advanced strategies. In order to deal with the non-linear mechanism of the processes and the highly complicated correlation among variables, a wavelet transform-assisted convolutional neural network (CNN) based multi-model dynamic monitoring method was proposed. A preliminary CNN model was first trained to detect faults and to diagnose part of them with minimum computational burden and time delay. Then, a wavelet assisted secondary CNN model was trained to diagnose the remaining faults with the highest possible accuracy. In this step, benefitting from the scale decomposition capabilities of the wavelet transform function, the inherent noise and redundant information could be filtered out and the useful signal was transformed into a higher compact space. In this space, a well-designed secondary CNN model was trained to further improve the fault diagnosis performance. The application on a refrigerant-producing process located in East China showed that not only regular faults but also hard to diagnose faults were successfully detected and diagnosed. More importantly, the unique online queue assembly updating strategy proposed remarkably reduced the inherent time delay of the deep-learning methods. Additionally, the application of it on the widely used Tennessee Eastman process benchmark strongly proved the superiority of it in fault detection and diagnosis over other deep-learning methods.

Hypertoxic materials make it critical to ensure the safety of the fluorochemical engineering processes. This mainly depends on the over maintenance or the manual operations due to the lack of precise models and mechanism knowledge. To quantify the deviations of the operating variables and the product quality from their target values at the same time and to overcome the measurement delay of the product quality, a novel quality integrated fuzzy inference system (QFIS) was proposed to estimate the reliability of the operation status as well as the product quality to enhance the performance of the safety monitoring system. To this end, a novel quality-weighted multivariate inverted normal loss function was proposed to quantify the deviation of the product quality from the target value to overcome the measurement delay. Vital safety process variables were identified according to the expert knowledge. Afterward, the quality loss and the vital variables were inputs to an elaborate fuzzy inference system to estimate the process reliability of the fluorochemical engineering processes. By integrating the abundant expert knowledge and a data-driven quality prediction model to design the fuzzy rules of QFIS, not only the operation reliability but also the product quality can be monitored on-line. Its superiority in estimating system reliability has been strongly proved by the application of a real fluorochemical engineering process located in East China. Moreover, the application of the Tennessee Eastman process also confirmed its generalization performance for other complicated black-box chemical processes.