Evaluation of micromixing in helically coiled microreactors using artificial intelligence approaches

• Published in: Chemical engineering journal (Lausanne, Switzerland : 1996) Switzerland : 1996), 2019-01, Vol.356, p.570-579
• Main Authors: Izadi, Mahtab, Rahimi, Masoud, Beigzadeh, Reza
• Format: Article
• Language: English
• Subjects: ANFIS; ANN; Helically coiled tube; Micromixing; Villermaux/Dushman reaction
• ISSN: 1385-8947; 1873-3212
• DOI: 10.1016/j.cej.2018.09.052

•The micromixing in coiled microreactors was investigated experimentally.•Artificial intelligence methods such as ANN and ANFIS were used for modeling.•Geometries and segregation index were model input and target, respectively.•The ANN provide the mean relative error less than 2% for predicting test data.•The results show higher precision for the ANN model in comparison with ANFIS. Artificial neural network (ANN) and adaptive neuro-fuzzy inference system (ANFIS) models were employed to evaluate micromixing in micro-helically coiled tubes. For this purpose, the value of segregation index (Xs) in Villermaux/Dushman reaction was obtained in twelve helically microchannels. The Reynolds number (Re), curvature ratio (δ), torsion (ϒ), and the ratio of the volume flow rate of alkaline solution to the acid solution were used as the model input data. The validity of the models was evaluated through one-fourth of the total experimental data, which were not applied in the training procedure. The mean relative error (MRE), mean square error (MSE), and absolute fraction of variance (R2) for ANN model was 0.83%, 1.65 × 10−10, and 0.9994 respectively. The corresponding calculated values for ANFIS were 1.14%, 5.08 × 10−10, and 0.9980. The estimation precision for both models are appropriate and the results indicated that the ANN approach has higher precision than ANFIS.