J. Fernandez de Canete

An Adaptive Neuro-Fuzzy Approach to Control a Distillation Column

In this paper we use a control strategy that enhances a fuzzy controller with self-learning capability for achieving the control of a binary methanol-propanol distillation column. An Adaptive-Network-based Fuzzy Inference System (ANFIS) architecture extended to cope with multivarible systems has been used. This allows the tuning of parameters both of the membership functions and the consequents in a Sugeno-type inference system. To satisfy the control objectives the backpropagation gradient descent through the plant method is applied, hence identification of the plant dynamics is also needed. The performance of the resulting neuro-fuzzy controller under different reference settings for the concentration of methoanol demonstrates the stabilisation of the concentration profiles in the column, leading to an effective methanol composition control.

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.

Object-oriented modeling and simulation of the closed loop cardiovascular system by using SIMSCAPE

The modeling of physiological systems via mathematical equations reflects the calculation procedure more than the structure of the real system modeled, with the simulation environment SIMULINK™ being one of the best suited to this strategy. Nevertheless, object-oriented modeling is spreading in current simulation environments through the use of the individual components of the model and its interconnections to define the underlying dynamic equations. In this paper we describe the use of the SIMSCAPE™ simulation environment in the object-oriented modeling of the closed loop cardiovascular system. The described approach represents a valuable tool in the teaching of physiology for graduate medical students.

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.

First-principles modeling of fluid and solute exchange in the human during normal and hemodialysis conditions

A first-principles computer model of fluid and solute exchange under both physiological and hemodialysis condition is presented. The whole system has been modeled and simulated under the MODELICA integrated environment, which uses a hierarchical modeling strategy. The model performance has been analyzed by simulation in the light of existing hypothesis and physiological data used here for validation purposes. The results obtained provide a physiological interpretative key to patients hemodynamic behavior during hemodialysis.

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.

Modelling of long-term and short-term mechanisms of arterial pressure control in the cardiovascular system: An object-oriented approach

A mathematical model that provides an overall description of both the short- and long-term mechanisms of arterial pressure regulation is presented. Short-term control is exerted through the baroreceptor reflex while renal elimination plays a role in long-term control. Both mechanisms operate in an integrated way over the compartmental model of the cardiovascular system. The whole system was modelled in MODELICA, which uses a hierarchical object-oriented modelling strategy, under the DYMOLA simulation environment. The performance of the controlled system was analysed by simulation in light of the existing hypothesis and validation tests previously performed with physiological data, demonstrating the effectiveness of both regulation mechanisms under physiological and pathological conditions.

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.

Neural-network-based stable control by using harmonic analysis: Application to a nonlinear DC motor drive

In this paper, we make an application of the harmonic balance (HB) analysis technique for studying oscillations in neural-network-based control systems where the closed-loop system can be transformed into a linear and a feedback nonlinear part (“Luré regulator problem”). The main goal of the present paper is to establish a test for the stability of limit cycles arising from a neural-network-control-based scheme operating over continuous nonlinear plants. The HB technique has been applied to the stability analysis of a quasilinearised nonlinear DC motor drive. The simple geometric interpretation of this technique contrasts other stability analysis techniques, such as Lyapunov, Input/Output, etc.