I. Garcia-Moral

Object-oriented approach applied to ANFIS modeling and control of a distillation column

Abstract Neurofuzzy networks are hybrid systems that combine neural networks with fuzzy systems, and the Adaptive Neuro-Fuzzy inference system (ANFIS) is a particular case in which a fuzzy system is implemented in the framework of an adaptive neural network. This neurofuzzy approach represents an effective structure to the modeling of plant dynamics, and the oriented-object programming environments offer an intuitive way to address this task. In this paper the MODELICA object-oriented environment has been applied to the ANFIS modeling and indirect control of the heavy and light product composition in a binary methanol-water distillation column by using the adaptive Levenberg–Marquardt approach. The results obtained demonstrate the potential of the adaptive ANFIS scheme under MODELICA for the dual control of composition both for changes in set points with null stationary error even when disturbances are present.

Dual composition control and soft estimation for a pilot distillation column using a neurogenetic design

Abstract Artificial neural networks exhibit a great potential for both model based control and software sensing due to their non-linear identification capabilities. This paper proposes the use of adaptive neural networks applied to the prediction of product composition starting from secondary variable measurements, and to both dual composition control and inventory control for a continuous ethanol–water nonlinear pilot distillation column monitored under LabVIEW. A principal component analysis based algorithm has been applied to select the optimal net input vector for the soft sensor. Genetic algorithms are used for the automatic choice of the optimum control law based on a neural network model of the plant. The proposed real time control scheme offers a high speed of response for changes in set points and null stationary error for both dual composition control and inventory control, and reveals the potential use of this control strategy when an experimental multivariable set-up is addressed.

Indirect adaptive structure for multivariable neural identification and control of a pilot distillation plant

This paper describes the design and implementation of an indirect adaptive controller that uses neural networks both for identification and control of an experimental pilot distillation column containing a mixture of ethanol and water. The MATLAB platform is applied both for the neural identification and control of the distillation plant using the Levenberg-Marquardt approach, enabling also optimal input/output net configuration. The neural controller performance has been analyzed and illustrated via experimental tests on the pilot distillation column monitored under the LabVIEW platform. Both platforms have been linked together by constituting an integrated process control interface. The obtained experimental results demonstrate the effectiveness of the neural indirect adaptive control scheme as compared to proportional-integrative-derivative, when real-time multivariable control is demanded, even in presence of disturbances.

Direct control with radial basis function networks: stability analysis and applications

Abstract In the present paper, neural control and identification of general nonlinear plants are accomplished using radial basis function (RBF) networks. A neural controller is adjusted oil-line by using the orthogonal least squares (OLS) method. A stability analysis has been performed using the conicity criterion, and based upon this a new training data set is elicited so that a stable neural controller is obtained. Applications both to a nonlinear fluid level system and to an inverted pendulum are detailed, demonstrating the effectiveness of the proposed method. Training time with the OLS method are reduced compared to standard backpropagation technique.

An input-output based robust stabilization criterion for neural-network control of nonlinear systems

A stabilization method based on the input-output conicity criterion is presented. Conventional learning algorithms are applied to adjust the controller dynamics, and robust stability of the closed-loop system is guaranteed by modifying the training patterns which yield unstable behavior. The methodology developed expands the class of nonlinear systems to be controlled using neural control schemes, so that the stabilization of a broad class of neural-network-based control systems, even with unknown dynamics, is assured. Straightforwardness in the application of this method is evident in contrast to the Lyapunov function approach.

Control architecture based on a radial basis function network. Application to a fluid level system

Nonlinear radial basis functions (RBF) at single layer hidden units of a neural net have proven to be effective in generating complex nonlinear mapping and at the same time facilitate fast learning. In the present paper off-line Gaussian control and identification of general nonlinear plants are realized. An iterative method to determine the desired controller output is described, and based upon this, a neural controller is adjusted by using the orthogonal least squares method. Neural identification of the plant is necessary to derive the parameter adjustments of the neural controller. The performance of the Gaussian approach has been demonstrated by off-line reference model neural control. Applications both to a general nonlinear plant and to a highly nonlinear fluid level system are detailed. It is shown that training times with orthogonal least squares method are dramatically reduced during control compared to standard backpropagation-of-the-error-through-the-plant technique. Finally, neural control is compared to PI control, showing the neural approach better generalization properties.

Object-Oriented Neurofuzzy Modeling and Control of a Binary Distillation Column by Using MODELICA

Neurofuzzy networks offer an alternative approach both for the identification and the control of nonlinear processes in process engineering. The lack of software tools for the design of controllers based on hybrid neural networks and fuzzy models is particularly pronounced in this field. MODELICA is an oriented-object environment widely used which allows system-level developers to perform rapid prototyping and testing. Such programming environment offers an intuitive approach to both adaptive modeling and control in a great variety of engineering disciplines. In this paper we have developed an oriented-object model of binary distillation column with nonlinear dynamics, and an ANFIS (Adaptive-Network-based Fuzzy Inference System) neurofuzzy scheme has been applied to derive both an identification model and a adaptive controller to regulate distillation composition. The results obtained demonstrate the effectiveness of the neurofuzzy control scheme when the plant’s dynamics is given by a set of nonlinear differential algebraic equations (DAE).

Neural and Genetic Control Approaches in Process Engineering

Nowadays, advanced control systems are playing a fundamental role in plant operations because they allow for effective plant management. Typically, advanced control systems rely heavily on real-time process modeling, and this puts strong demands on developing effective process models that, as a prime requirement, have to exhibit real-time responses. Because in many instances detailed process modeling is not viable, efforts have been devoted towards the development of approximate dynamic models.

Aeration control and parameter soft estimation for a wastewater treatment plant using a neurogenetic design

Biochemical oxygen demand and chemical oxygen demand are the most important parameters for wastewater management and planning, which represents the oxygen consumption from degradation of organic material. Insufficient levels of dissolved oxygen prevent the successful degradation of organic matter present, whereas too high levels cause a waste of energy and hence decreased efficiency. Therefore, the need for controlling dissolved oxygen through adequate aeration and sludge pumping operations is of great importance. This paper proposes the use of artificial neural networks applied both to the prediction of both oxygen demand parameters starting from secondary variable measurements and to the control of dissolved oxygen in aeration tanks for a nonlinear wastewater treatment model benchmark. Genetic algorithms are used for the automatically choice of the optimum control law based on the neural network model of the plant. The results show how this combined scheme can be effectively employed in aeration control.

Stabilization of Neural Control Systems Using the Conicity Criterion

Abstract Stable designs of neural based controllers have relied on the existence of a Lyapunov energy function or have been based upon the local controllability of the system under consideration. In this paper a stability analysis is realized using the conicity criterion, and based upon this, a RBF neural controller is adjusted, so that the closed loop dynamic is stable. A stabilization technique is fonnulated and application to an inherently unstable system, i.e. an inverted pendulum is also described, demonstrating through simulation the effectiveness of the proposed method.