A neuro-fuzzy decoupling approach for real-time drying room control in meat manufacturing

A coupling model of temperature and relative humidity was proposed using ANFIS.Decoupling control of temperature and relative humidity in drying room was developed.The decoupling approach was developed for a large real-time meat drying room.The simulation results show the fluctuation of relative humidity was reduced to ?0.6%. This paper proposes a method to resolve a strong coupling between temperature and relative humidity in drying room control systems. The coupling issue not only affects the control accuracy but also causes system instability, unnecessary adjustment, and extra energy consumption. A real-time temperature and relative humidity decoupling control method is reported in this paper. An improved aspirated psychrometer was used as a relative humidity measurement unit, which achieved relative humidity measurement accuracy of ?0.7%. The decoupling approach was developed based on a large real-time drying room, whose physical size was 22i?15i?3.5m. A decoupling approach was developed using the adaptive neuro-fuzzy inference system for the control of temperature and relative humidity in the drying room. The simulated result shows that after the decoupling treatment, the relative humidity fluctuation was reduced from ?2.5% to ?0.6%.

[1]  Seyed Mohammad Ali Mohammadi,et al.  A new mathematical dynamic model for HVAC system components based on Matlab/Simulink , 2012 .

[2]  Konstantinos G. Arvanitis,et al.  A nonlinear feedback technique for greenhouse environmental control , 2003 .

[3]  Simon X. Yang,et al.  Coupling analysis and control of temperature and relative humidity in a drying room , 2013, 2013 IEEE International Conference on Information and Automation (ICIA).

[4]  J. M. Cohen,et al.  Mexico City : México , 1965 .

[5]  Fang Zhu,et al.  Research on Decoupling Control in Temperature and Humidity Control Systems , 2011, CCTA.

[6]  Abdelkader Mami,et al.  Decoupling Control Approach for Neonate Incubator System , 2012 .

[7]  Morteza M. Ardehali,et al.  Wavelet based artificial neural network applied for energy efficiency enhancement of decoupled HVAC system , 2012 .

[8]  T. Becker,et al.  Impact of air humidity in industrial heating processes on selected quality attributes of bread rolls , 2011 .

[9]  Jian Wang,et al.  Application of a fuzzy decoupling control algorithm for simultaneous control of both temperature and humidity , 2006, International Symposium on Precision Mechanical Measurements.

[10]  Jia Liang.  Feedforward Decoupling for Multivariable Fuzzy Control System , 2004 .

[11]  Rubiyah Yusof,et al.  Decoupled HVAC System via Non-Linear Decoupling Algorithm to Control the Parameters of Humidity and Temperature through the Adaptive Controller , 2014 .

[12]  Denis Bruneau,et al.  Drying and smoking of meat: heat and mass transfer modeling and experimental analysis , 2005 .

[13]  G. Lekutai,et al.  Self-tuning control of nonlinear systems using neural network adaptive frame wavelets , 1997, 1997 IEEE International Conference on Systems, Man, and Cybernetics. Computational Cybernetics and Simulation.

[14]  Guang Geng,et al.  On performance and tuning of PID controllers in HVAC systems , 1993, Proceedings of IEEE International Conference on Control and Applications.

[15]  Jyh-Shing Roger Jang,et al.  ANFIS: adaptive-network-based fuzzy inference system , 1993, IEEE Trans. Syst. Man Cybern..

[16]  Michio Sugeno,et al.  Fuzzy identification of systems and its applications to modeling and control , 1985, IEEE Transactions on Systems, Man, and Cybernetics.

[17]  Yuan Feng,et al.  A Kind of Temperature and Humidity Adaptive Predictive Decoupling Method in Wireless Greenhouse Environmental Test Simulation System , 2013 .

[18]  M. Velez-Reyes,et al.  Decoupled control of temperature and relative humidity using a variable-air-volume HVAC system and non-interacting control , 2001, Proceedings of the 2001 IEEE International Conference on Control Applications (CCA'01) (Cat. No.01CH37204).