Parametric study and modeling of cross-flow heat exchanger fouling in phosphoric acid concentration plant using artificial neural network

Aguel, Saoussen El; Meddeb, Zina; Jeday, Mohamed Razak

doi:10.1016/j.jprocont.2019.10.001

Cited by 17 publications

(2 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Artificial neural networks (ANNs) are also showing promising results, significantly improving the accuracy of some industrial fouling models. Aguel et al [90] studied the thermal performance of a cross-flow heat exchanger in phosphoric acid concentration plant and derived a mathematical model, improved by ANN with backpropagation, which can be used for predicting a cleaning schedule for the heat exchanger. Alsadaie et al [91] tackled dynamic modelling of CaCO 3 and Mg(OH) 2 fouling in multistage flash desalination.…”

Section: Modelling Crystallization Foulingmentioning

confidence: 99%

A Review of Crystallization Fouling in Heat Exchangers

et al. 2021

View full text Add to dashboard Cite

A vast majority of heat exchangers suffer from unwanted deposition of material on the surface, which severely inhibits their performance and thus marks one of the biggest challenges in heat transfer. Despite numerous scientific investigations, prediction and prevention of fouling remain unresolved issues in process engineering and are responsible for large economic losses and environmental damage. This review article focuses specifically on crystallization fouling, providing a comprehensive overview of the state-of-the-art of fouling in heat exchangers. The fundamentals of the topic are discussed, as the term fouling resistance is introduced along with distinct fouling behaviour, observed in laboratory and industrial environments. Insight into subsequent phases of the fouling process is provided, along with the accompanying microscale events. Furthermore, the effects of fluid composition, temperature, flow velocity, surface condition, nucleate boiling and composite fouling are comprehensively discussed. Fouling modelling is systematically reviewed, from the early work of Kern and Seaton to recently used artificial neural networks and computational fluid dynamics. Finally, the most common fouling mitigation approaches are presented, including design considerations and various on-line strategies, as well as off-line cleaning. According to our review, several topics require further study, such as the initial stage of crystal formation, the effects of ageing, the interplay of two or more fouling mechanisms and the underlying phenomena of several mitigation strategies.

show abstract

Section: Modelling Crystallization Foulingmentioning

confidence: 99%

A Review of Crystallization Fouling in Heat Exchangers

et al. 2021

View full text Add to dashboard Cite

show abstract

“…In recent years, common soft-sensor modelling methods have included the least-squares support vector machine (LSSVM), convolutional neural network, and latent variable methods. [12][13][14][15] Zeng and Ge [16] studied a model based on dynamic Bayesian networks (DBNs) for industrial processes. This method can accurately indicate the structure of dynamic variables by constructing a series of DBNs to identify the relevant characteristic variables of the quality variables.…”

Section: Introductionmentioning

confidence: 99%

Dynamic nonlinear soft sensor modelling method using linear slow feature analysis and least squares support vector regression for batch processes

Zhang,

Liu,

Zhang

et al. 2023

Can J Chem Eng

View full text Add to dashboard Cite

Data‐driven soft sensor models have been extensively utilized in industrial processes. Batch processes are usually employed to manufacture low‐volume and high value‐added products in chemical, materials, and pharmaceutical industries. The most distinctive features of batch process lie in nonlinear, repetition, and slow time varying characteristics. In this paper, a data‐driven soft sensor modelling method based on linear slow feature analysis (LSFA) and least squares support vector regression (LSSVR) is proposed. In this method, LSFA was used to effectively capture the driving force behind the data features that change as slowly as possible. Then, a LSSVR model was constructed between the extracted slow feature variables and quality variables. Finally, a numerical example, industrial penicillin fermentation processes, and cobalt oxalate synthesis process were utilized to confirm the prediction accuracy and model reliability of the proposed approach.

show abstract