Mohamed Azlan Hussain

Prediction of pores formation (porosity) in foods during drying: generic models by the use of hybrid neural network

Abstract General porosity prediction models of food during air-drying have been developed using regression analysis and hybrid neural network techniques. Porosity data of apple, carrot, pear, potato, starch, onion, lentil, garlic, calamari, squid, and celery were used to develop the model using 286 data points obtained from the literature. The best generic model was developed based on four inputs as temperature of drying, moisture content, initial porosity, and product type. The error for predicting porosity using the best generic model developed is 0.58%, thus identified as an accurate prediction model.

Hybrid neural network—prior knowledge model in temperature control of a semi-batch polymerization process

Nonlinear process control is a challenging research topic at present. In recent years, neural network and hybrid neural networks have been much studied especially for modeling of nonlinear system. It has however been applied mainly as an estimator in parts of various control systems and the idea of utilizing it directly as a neural-controller has not been studied. Hence the contribution of this work is to use an inverse neural network in hybrid with a first principle model for the direct control of a nonlinear semi-batch polymerization process. These hybrid models were utilized in the direct inverse control strategy to track the set point of the temperature of the polymerization reactor under nominal condition and with various disturbances. For comparison purposes, the standard neural network and proportional-integral-derivative controller were also implemented in these control strategies. Adaptation mechanisms to improve the results have also been carried out to test the capability of these hybrid methods in control. The simulation results show the advantages and robustness of utilizing the neural network in this hybrid strategy especially when an adaptive algorithm is implemented.

Performance of different types of controllers in tracking optimal temperature profiles in batch reactors

Abstract Performance of three different types of controllers in tracking the optimal reactor temperature profiles in batch reactor is considered hear. A complex exothermic batch reaction scheme is used for this purpose. The optimal reactor temperature profiles are obtained by solving optimal control problems off-line. Dual mode (DM) control with propotional-integral (PI) and proportional-integral-derivative (PID) and generic model control (GMC) algorithms are used to design the controllers to track the optimal temperature profiles (dynamic set points). Neutral network technique is used as the on-line estimator the amount of heat released by the chemical reaction within th GMC algorithm. The GMC controller coupled with a neural network based heat-release estimator is found to be more effective and robust than the PI and PID controllers in tracking the optimal temperature profiles to obtain the desired products on target.

Implementation of an inverse-model-based control strategy using neural networks on a partially simulated exothermic reactor

Recently, the use of control strategies based upon inverse process models for non-linear systems has been found promising. The requirement of a true analytical inverse can be avoided when neural network models are used; they have the ability to approximate both the forward and the inverse system dynamics. Although many simulation studies have illustrated the use of neural network inverse models for control, very few on-line applications have been reported. This paper describes a novel implementation of a neural network inverse-model based control method on a experimental system—a partially simulated reactor, designed to test the use of such non-linear algorithms. The implementation involved the control of the reactor temperature in the face of set point changes and load disturbances despite the existence of significant plant/model mismatch. Comparison was also made with conventional PID cascade control in several cases. The results obtained show the capability of these neural-network-based controllers and, incidentally, point out the differences between simulation studies and on-line experimental tests. Since the system in this study was only mildly non-linear, in some cases, the performance was comparable to that achieved by classical controllers while in other cases an improved control was achieved.

Analysis and Experimental Study of Magnetorheological-Based Damper for Semiactive Suspension System Using Fuzzy Hybrids

In this paper, the development and implementation of a novel semiactive suspension control of a quarter-car model using a hybrid-fuzzy-logic-based controller have been done. The proposed quarter-car model can be described as a nonlinear two-degree-of-freedom system, which is subject to system disturbances from different road profiles. In order to implement the suspension system experimentally, the magnetorheological (MR) fluid has been used as an adjustable damper. The MR damper is a control device that consists of a hydraulic cylinder filled with magnetically polarizable particles suspended in a liquid. The MR damper rapidly dissipates vibration by absorbing energy. In this paper, proportional-integral-derivative (PID), fuzzy logic, and hybrid controllers are used to control the semiactive car suspension system. The results show that both fuzzy logic and hybrid controllers are quite suitable to eliminate road disturbances for the semiactive suspension system considerably as compared to the conventional PID controller.

Neural network inverse model-based controller for the control of a steel pickling process

The present work investigates the use of neural network direct inverse model-based control strategy (NNDIC) to control a steel pickling process. The process is challenging due to the fact that the pH of effluent streams must be regulated accurately to protect aquatic and human welfare, and to comply with limits imposed by legislation. At the same time, the concentration of acid solution in the pickling step needs to be maintained at the optimum value in order to obtain the maximum reaction rate. Various changes in the open-loop dynamics are performed before implementation of the inverse neural network modeling technique. The optimal neural network architectures are determined by the mean squared error (MSE) minimization technique. The robustness of the proposed inverse model neural network control strategy is investigated with respect to changes in disturbances, model mismatch and noise effects. Simulation results show the superiority of the NNDIC controller in the cases involving disturbance, model mismatch and noise while the conventional controller gives better results in the nominal case.

Thermal conductivity prediction of fruits and vegetables using neural networks

Abstract Artificial neural network was used to predict the thermal conductivity of various fruits and vegetables (apples, pears, corn starch, raisins and potatoes). Neural networks was also used to model the error between the experimental value and that of the theoretical model developed. Two separate networks were used to perform these separate tasks. The optimum configuration of the networks was obtained by trial and error basis using the multilayered approach with the backpropagation and Levenberg‐Marquardt Methods used concurrently in the training of the networks. The results showed that the these networks has the ability to model the thermal conductivity as well as to predict the model/experimental error accurately. The networks can then be used as correction factor to the model in a hybrid approach and gave better prediction of thermal conductivity than the model itself.

Mathematical Model and Advanced Control for Gas-phase Olefin Polymerization in Fluidized-bed Catalytic Reactors

In this study, the developments in modeling gas-phase catalyzed olefin polymerization fluidized-bed reactors (FBR) using Ziegler-Natta catalyst is presented. The modified mathematical model to account for mass and heat transfer between the solid particles and the surrounding gas in the emulsion phase is developed in this work to include site activation reaction. This model developed in the present study is subsequently compared with well-known models, namely, the bubble-growth, well-mixed and die constant bubble size models for porous and non porous catalyst. The results we obtained from the model was very close to the constant bubble size model, well-mixed model and bubble growth model at the beginning of the reaction but its overall behavior changed and is closer to the well-mixed model compared with the bubble growth model and constant bubble size model after half an hour of operation. Neural-network based predictive controller are implemented to control the system and compared with the conventional PID controller, giving acceptable results.

Design of a Fuzzy Logic Controller for Regulating Substrate Feed to Fed-Batch Fermentation

Fuzzy logic control based on the Takagi-Sugeno inference method has been applied for the regulation of feed rate to a fed-batch fermentation process. The process chosen is the bakers yeast fermentation. The simulation results show that the conventional fuzzy logic controller produces oscillations in the process response. To improve the performance of the conventional scheme, implementation of adaptive and hybrid control schemes are proposed. Significant improvements in the controller performance could be achieved by combining these two approaches. The adaptive control scheme reduces severe oscillations and the hybrid control scheme enhances control precision.

Model-based control strategies for a chemical batch reactor with exothermic reactions

Batch reactor control provides a very challenging problem for the process control engineer. This is because a characteristic of its dynamic behavior shows a high nonlinearity. Since applicability of the batch reactor is quite limited to the effectiveness of an applied control strategy, the use of advanced control techniques is often beneficial. This work presents the implementation and comparison of two advanced nonlinear control strategies, model predictive control (MPC) and generic model control (GMC), for controlling the temperature of a batch reactor involving a complex exothermic reaction scheme. An extended Kalman filter is incorporated in both controllers as an on-line estimator. Simulation studies demonstrate that the performance of the MPC is slightly better than that of the GMC control in nominal case. For model mismatch cases, the MPC still gives better control performance than the GMC does in the presence of plant/model mismatch in reaction rate and heat transfer coefficient.