Temperature Control of Heaters in Cable Extrusion Machine using PSO-ANFIS Controller

Most electrical cable manufacturing companies in Ghana and other parts of the world use solid-state based relay for controlling temperatures of heaters during cable extrusion process. Due to the on-off nature of such relays, the flow of heat is not continuous and mostly unreliable. As a result, most of the extruded cables have surface defects such as cracks, pimples and voids which affects the quality of the manufactured cable. The consequence of this is that the cable does not pass the quality assurance test hence, it is usually scraped off. This causes the companies to loose large amount of money due to material wastage. To overcome this challenge, an Adaptive Neuro Fuzzy Inference System (ANFIS) controller tuned with Particle Swarm Optimisation (PSO) algorithm was designed to provide continuous temperature control during the extrusion process. To ascertain the robustness of the designed controller, it was compared with other conventional and intelligent controllers such as the Proportional Integral (PI), Fuzzy, Fuzzy-PI, and ANFIS controller. The controllers were designed and simulated using MATLAB/Simulink software. The results obtained indicated that the PSO-ANFIS controller was robust in achieving stability in terms of temperature variations.

[1]  R. Erol,et al.  A Comparative Study of Neural Networks and ANFIS for Forecasting Attendance Rate of Soccer Games , 2017 .

[2]  Eunyoung Park,et al.  A Study on the Halo Surface Defect of Injection Molded Products , 2017 .

[3]  Weisi Lin Multimedia Analysis, Processing and Communications , 2011 .

[4]  Ravi Samikannu,et al.  Design of Synthetic Optimizing Neuro Fuzzy Temperature Controller for Dual Screw Profile Plastic Extruder Using Labview , 2011 .

[5]  Rajendra Murmu,et al.  Temperature Control for Plastic Extrusion Process , 2015 .

[6]  Yuhui Shi,et al.  Particle swarm optimization: developments, applications and resources , 2001, Proceedings of the 2001 Congress on Evolutionary Computation (IEEE Cat. No.01TH8546).

[7]  R. A. Ofosu,et al.  Determination of Optimal PI Gains For Fuzzy-PI Controller Using Bacterial Foraging Algorithm ( BFA ) , 2016 .

[8]  Mohsen Hajihassani,et al.  The Contribution of Particle Swarm Optimization to Three-Dimensional Slope Stability Analysis , 2014, TheScientificWorldJournal.

[9]  Nafrizuan Mat Yahya,et al.  Numerical Analysis of Fuzzy Logic Temperature and Humidity Control System in Pharmaceutical Warehouse Using MATLAB Fuzzy Toolbox , 2018 .

[10]  Manuel Flota-Bañuelos,et al.  Photovoltaic Module Temperature Estimation: A Comparison Between Artificial Neural Networks and Adaptive Neuro Fuzzy Inference Systems Models , 2016 .

[11]  Cyril Belavý,et al.  FEM based modelling and control of temperature field in extruder barrel , 2018, 2018 Cybernetics & Informatics (K&I).

[12]  S. Ravi,et al.  Design of Synthetic Optimizing Neuro Fuzzy Temperature Controller for Twin Screw Profile Plastic Extruder Using Labview , 2014, Intell. Autom. Soft Comput..

[13]  Chamil Abeykoon,et al.  A Novel Model-Based Controller for Polymer Extrusion , 2014, IEEE Transactions on Fuzzy Systems.

[14]  Chonghua Wang,et al.  A study of membership functions on mamdani-type fuzzy inference system for industrial decision-making , 2015 .

[15]  Harold F. Giles,et al.  Extrusion : The Definitive Processing Guide and Handbook Ed. 2 , 2013 .