The performance of a chemical process plant can gradually degrade due to deterioration of the process equipment and unpermitted deviation of the characteristic variables of the system. Hence, advanced supervision is required for early detection, isolation and correction of abnormal conditions. This work presents the use of an adaptive neuro-fuzzy inference system (ANFIS) for online fault diagnosis of a gas-phase polypropylene production process with emphasis on fast and accurate diagnosis, multiple fault identification and adaptability. The most influential inputs are selected from the raw measured data sets and fed to multiple ANFIS classifiers to identify faults occurring in the process, eliminating the requirement of a detailed process model. Simulation results illustrated that the proposed method effectively diagnosed different fault types and severities, and that it has a better performance compared to a conventional multivariate statistical approach based on principal component analysis (PCA). The proposed method is shown to be simple to apply, robust to measurement noise and able to rapidly discriminate between multiple faults occurring simultaneously. This method is applicable for plant-wide monitoring and can serve as an early warning system to identify process upsets that could threaten the process operation ahead of time.
Extensive application of metal powder, particularly in nanosize could potentially lead to catastrophic dust explosion, due to their pyrophoric behavior, ignition sensitivity, and explosivity. To assess the appropriate measures preventing accidental metal dust explosions, it is vital to understand the physicochemical properties of the metal dust and their kinetic mechanism. In this work, explosion severity of aluminum and silver powder, which can be encountered in a passivated emitter and rear contact (PERC) solar cell, was explored in a 0.0012 m3 cylindrical vessel, by varying the particle size and powder concentration. The P max and dP/dt max values of metal powder were demonstrated to increase with decreasing particle size. Additionally, it was found that the explosion severity of silver powder was lower than that of aluminum powder due to the more apparent agglomeration effect of silver particles. The reduction on the specific surface area attributed to the particles' agglomeration affects the oxidation reaction of the metal powder, as illustrated in the thermogravimetric (TG) curves. A sluggish oxidation reaction was demonstrated in the TG curve of silver powder, which is contradicted with aluminum powder. From the X-ray photoelectron spectroscopy (XPS) analysis, it is inferred that silver powder exhibited two reactions in which the dominant reaction produced Ag and the other reaction formed Ag2O. Meanwhile, for aluminum powder, explosion products only comprise Al2O3.