The series Advances in Industrial Control aims to report and encourage technology transfer in control engineering. The rapid development of control technology has an impact on all areas of the control discipline. New theory, new controllers, actuators, sensors, new industrial processes, computer methods, new applications, new philosophies ... , new challenges. Much of this development work resides in industrial reports, feasibility study papers and the reports of advanced collaborative projects. The series offers an opportunity for researchers to present an extended exposition of such new work in all aspects of industrial control for wider and rapid dissemination. Neural networks is one of those areas where an initial burst of enthusiasm and optimism leads to an explosion of papers in the journals and many presentations at conferences but it is only in the last decade that significant theoretical work on stability, convergence and robustness for the use of neural networks in control systems has been tackled. George Rovithakis and Manolis Christodoulou have been interested in these theoretical problems and in the practical aspects of neural network applications to industrial problems. This very welcome addition to the Advances in Industrial Control series provides a succinct report of their research. The neural network model at the core of their work is the Recurrent High Order Neural Network (RHONN) and a complete theoretical and simulation development is presented. Different readers will find different aspects of the development of interest. The last chapter of the monograph discusses the problem of manufacturing or production process scheduling.
Table of Contents1. Introduction.- 1.1 General Overview.- 1.2 Book Goals & Outline.- 1.3 Notation.- 2. Identification of Dynamical Systems Using Recurrent High-order Neural Networks.- 2.1 The RHONN Model.- 2.1.1 Approximation Properties.- 2.2 Learning Algorithms.- 2.2.1 Filtered Regressor RHONN.- 2.2.2 Filtered Error RHONN.- 2.3 Robust Learning Algorithms.- 2.4 Simulation Results.- Summary.- 3. Indirect Adaptive Control.- 3.1 Identification.- 3.1.1 Robustness of the RHONN Identifier Owing to Unmodeled Dynamics.- 3.2 Indirect Control.- 3.2.1 Parametric Uncertainty.- 3.2.2 Parametric plus Dynamic Uncertainties.- 3.3 Test Case: Speed Control of DC Motors.- 3.3.1 The Algorithm.- 3.3.2 Simulation Results.- Summary.- 4. Direct Adaptive Control.- 4.1 Adaptive Regulation Complete Matching.- 4.2 Robustness Analysis.- 4.2.1 Modeling Error Effects.- 4.2.2 Model Order Problems.- 4.2.3 Simulations.- 4.3 Modeling Errors with Unknown Coefficients.- 4.3.1 Complete Model Matching at |x| = 0.- 4.3.2 Simulation Results.- 4.4 Tracking Problems.- 4.4.1 Complete Matching Case.- 4.4.2 Modeling Error Effects.- 4.5 Extension to General Affine Systems.- 4.5.1 Adaptive Regulation.- 4.5.2 Disturbance Effects.- 4.5.3 Simulation Results.- Summary.- 5. Manufacturing Systems Scheduling.- 5.1 Problem Formulation.- 5.1.1 Continuous Control Input Definition.- 5.1.2 The Manufacturing Cell Dynamic Model.- 5.2 Continuous-time Control Law.- 5.2.1 The Ideal Case.- 5.2.2 The Modeling Error Case.- 5.3 Real-time Scheduling.- 5.3.1 Determining the Actual Discrete Dispatching Decision.- 5.3.2 Discretization Effects.- 5.4 Simulation Results.- Summary.- 6. Scheduling using RHONNs: A Test Case.- 6.1 Test Case Description.- 6.1.1 General Description.- 6.1.2 Production Planning & Layout in SHW.- 6.1.3 Problem Definition.- 6.1.4 Manufacturing Cell Topology.- 6.1.5 RHONN Model Derivation.- 6.1.6 Other Scheduling Policies.- 6.2 Results & Comparisons.- Summary.- References.