A data‐driven approach for flow corrosion characteristic parameters prediction in an air cooler

Abstract

A data‐driven soft measurement method based on a multiunit back propagation neural network (MBPNN) is presented in this study. This model aims to estimate the characteristic parameters that can reflect the flow corrosion of the reactor effluent air cooler (REAC). Flow corrosion failure during the hydrogenation process presents a serious concern to the petrochemical industry. In this paper, a safety evaluation of flow corrosion failure for a petrochemical diesel hydrogenation unit is first carried out. During the investigation, it is found that there is a risk of NH4Cl crystallization at around 187°C. Then, considering flow‐induced corrosion and ammonium salt deposition, main characteristic parameters are determined, including NH4Cl crystallization temperature (TC), air cooler tube bundle minimum and maximum flow rate (Vmin and Vmax), air cooler inlet liquid water content (CW), and NH4HS concentration (CA). Finally, the data‐driven model based on a multiunit back propagation neural network (MBPNN) is constructed. An improved particle swarm optimization (PSO) approach is employed to initialize the main parameters of the model. Compared with a multioutput back propagation neural network (BPNN) model and MBPNN model without an optimization algorithm, the presented data‐driven model is proved to have high accuracy, a fast convergence rate, and high reliability.

Prediction of Criminal Suspect Characteristics with Application of Wavelet Neural Networks

“…In the era of big data, with the advancement of wireless communication, mobile computing and positioning technology, spatio-temporal information of real-life moving objects can already be easily obtained [1][2]. People's movement behavior data can be better collected by using cell phone location information, and the movement trajectory contains time data along with specific location data, so it is actually a kind of spatio-temporal data [3][4]. A single spatio-temporal information point contains some semantic information, and if specific spatio-temporal information points are aggregated, specific trajectory information can be formed, such as human activity trajectories, transportation activity trajectories, animal activity trajectories, natural law activity trajectories and trajectories collected by video surveillance.…”