Passive Control of Plume Interference on Slender Axisymmetric Bodies

The physics of the plume-induced shock and separation, particularly at high plume to exit pressure ratios with and without shock-turbulent boundary-layer control methods, were studied using computational techniques. Mass-averaged Navier-Stokes equations with a two-equation turbulence model were solved by using a fully implicit finite volume scheme and time.marching algorithm. The control methodologies for shock interactions included a porous tail and a porous extension attached at the nozzle exit or trailing edge. The porous tail produced a weaker shock and fixed the shock position on the control surface. The effect of the porous extension on shock interactions was mainly to restrain the plume from strongly underexpanding during a change in flight conditions. These techniques could give an additional dimension to the design and control of supersonic missiles.

Second-Order Training of Adaptive Critics for Online Process Control

A new algorithm for training of nonlinear optimal neuro-controllers (in the form of the model-free, action-dependent, adaptive critic paradigm). Overcomes problems with existing stochastic backpropagation training: need for data storage, parameter shadowing and poor convergence, offering significant benefits for online applications.

A two-stage algorithm for identification of nonlinear dynamic systems

This paper investigates the two-stage stepwise identification for a class of nonlinear dynamic systems that can be described by linear-in-the-parameters models, and the model has to be built from a very large pool of basis functions or model terms. The main objective is to improve the compactness of the model that is obtained by the forward stepwise methods, while retaining the computational efficiency. The proposed algorithm first generates an initial model using a forward stepwise procedure. The significance of each selected term is then reviewed at the second stage and all insignificant ones are replaced, resulting in an optimised compact model with significantly improved performance. The main contribution of this paper is that these two stages are performed within a well-defined regression context, leading to significantly reduced computational complexity. The efficiency of the algorithm is confirmed by the computational complexity analysis, and its effectiveness is demonstrated by the simulation results.

A Hybrid Forward Algorithm for RBF Neural Network Construction

This paper proposes a novel hybrid forward algorithm (HFA) for the construction of radial basis function (RBF) neural networks with tunable nodes. The main objective is to efficiently and effectively produce a parsimonious RBF neural network that generalizes well. In this study, it is achieved through simultaneous network structure determination and parameter optimization on the continuous parameter space. This is a mixed integer hard problem and the proposed HFA tackles this problem using an integrated analytic framework, leading to significantly improved network performance and reduced memory usage for the network construction. The computational complexity analysis confirms the efficiency of the proposed algorithm, and the simulation results demonstrate its effectiveness

A novel approach to dynamic modelling of polymer extrusion for improved process control

Polymer extrusion is a complex process and the availability of good dynamic models is key for improved system operation. Previous modelling attempts have failed adequately to capture the non-linearities of the process or prove too complex for control applications. This work presents a novel approach to the problem by the modelling of extrusion viscosity and pressure, adopting a grey box modelling technique that combines mechanistic knowledge with empirical data using a genetic algorithm approach. The models are shown to outperform those of a much higher order generated by a conventional black box technique while providing insight into the underlying processes at work within the extruder.

An agent-based control mechanism for WFQ in IP networks

This paper presents a new packet scheduling scheme called agent-based WFQ to control and maintain QoS parameters in virtual private networks (VPNs) within the confines of adaptive networks. Future networks are expected to be open heterogeneous environments consisting of more than one network operator. In this adaptive environment, agents act on behalf of users or third-party operators to obtain the best service for their clients and maintain those services through the modification of the scheduling scheme in routers and switches spanning the VPN. In agent-based WFQ, an agent on the router monitors the accumulated queuing delay for each service. In order to control and to keep the end-to-end delay within the bounds, the weights for services are adjusted dynamically by agents on the routers spanning the VPN. If there is an increase or decrease in queuing delay of a service, an agent on a downstream router informs the upstream routers to adjust the weights of their queues. This keeps the end-to-end delay of services within the specified bounds and offers better QoS compared to VPNs using static WFQ. This paper also describes the algorithm for agent-based WFQ, and presents simulation results. (C) 2003 Elsevier Science Ltd. All rights reserved.

Modelling the MAPK signalling pathway using a two-stage identification algorithm

Signal transduction pathways describe the dynamics of cellular response to input signalling molecules at receptors on the cell membrane. The Mitogen-Activated Protein Kinase (MAPK) cascade is one of such pathways that are involved in many important cellular processes including cell growth and proliferation. This paper describes a black-box model of this pathway created using an advanced two-stage identification algorithm. Identification allows us to capture the unique features and dynamics of the pathway and also opens up the possibility of regulatory control design. In the approach described, an optimal model is obtained by performing model subset selection in two stages, where the terms are first determined by a forward selection method and then modified using a backward selection model refinement. The simulation results demonstrate that the model selected using the two-stage algorithm performs better than with the forward selection method alone.

A novel continuous forward algorithm for RBF neural modelling

A continuous forward algorithm (CFA) is proposed for nonlinear modelling and identification using radial basis function (RBF) neural networks. The problem considered here is simultaneous network construction and parameter optimization, well-known to be a mixed integer hard one. The proposed algorithm performs these two tasks within an integrated analytic framework, and offers two important advantages. First, the model performance can be significantly improved through continuous parameter optimization. Secondly, the neural representation can be built without generating and storing all candidate regressors, leading to significantly reduced memory usage and computational complexity. Computational complexity analysis and simulation results confirm the effectiveness.

Learning soft computing control strategies in a modular neural network architecture

Modelling and control of nonlinear dynamical systems is a challenging problem since the dynamics of such systems change over their parameter space. Conventional methodologies for designing nonlinear control laws, such as gain scheduling, are effective because the designer partitions the overall complex control into a number of simpler sub-tasks. This paper describes a new genetic algorithm based method for the design of a modular neural network (MNN) control architecture that learns such partitions of an overall complex control task. Here a chromosome represents both the structure and parameters of an individual neural network in the MNN controller and a hierarchical fuzzy approach is used to select the chromosomes required to accomplish a given control task. This new strategy is applied to the end-point tracking of a single-link flexible manipulator modelled from experimental data. Results show that the MNN controller is simple to design and produces superior performance compared to a single neural network (SNN) controller which is theoretically capable of achieving the desired trajectory. (C) 2003 Elsevier Ltd. All rights reserved.

Multiple Input Governor Control for a Diesel Generating Set

The paper presents a multiple input single output fuzzy logic governor algorithm that can be used to improve the transient response of a diesel generating set, when supplying an islanded load. The proposed governor uses the traditional speed input in addition to voltage and power factor to modify the fuelling requirements during various load disturbances. The use of fuzzy logic control allows the use of PID type structures that can provide variable gain strategies to account for non-linearities in the system. Fuzzy logic also provides a means of processing other input information by linguistic reasoning and a logical control output to aid the governor action during transient disturbance. The test results were obtained using a 50 kVA naturally aspirated diesel generator testing facility. Both real and reactive load tests were conducted. The complex load test results demonstrate that, by using additional inputs to the governor algorithm, enhanced generator transient speed recovery response can be obtained.