THE NEURAL NETWORKS IN CONTROL SYSTEMS

 The ever-increasing technological demands of our modem society require innovative approaches to highly demanding control problems. Artificial neural networks with their massive parallelism and learning capabilities offer the promise of better solutions, at least to some problem.

 Neural networks have the potential for very complicated behavior. They consist of many interconnected simple nonlinear systems, which are typically modeled by sigmoid functions. The massive interconnections of the rather simple neurons. which make up the human brain, provided the original motivation for the neural network models. The terms artijicial neural networks and connectionist models are typically used to distinguish them from the biological networks of neurons of living organisms. 

Neural networks are characterized by their network topology-that is, by the number of interconnections, the node characteristics that are classified by the type of nonlinear elements used, and the kind of learning rules implemented. 

CONTROL TECHNOLOGY

The use of neural networks in control systems can be seen as a natural step in the evolution of control methodology to meet new challenges. Looking back. the evolution in the control area has been fueled by three major needs: the need to deal with increasingly complex systems, the need to accomplish increasingly demanding design requirements, and the need to attain these requirements with less precise advanced knowledge of the plant and its environment-that is, the need to control under increased uncertainty. 

Today, the need to control, in a better way, increasingly complex dynamical systems under significant uncertainty has led to a reevaluation of the conventional control methods, and it has made the need for new methods quite apparent. It has also led to a more general concept of control, one that includes higher-level decision making, planning, and learning, which are capabilities necessary when higher degrees of system autonomy are desirable.

 Neural networks appear to offer new promising directions toward better understanding and perhaps even solving some of our most difficult control problem . The dynamical behavior, studied via differential equations, exhibits stable states, which act as basins of attraction for neighboring states as they develop in time. This time evolution toward these equilibrium points can be seen as the attraction of an imperfect pattern toward the correct one, stored as a stable equilibrium. Several design methods are presented to appropriately assign the weights, so that the resulting networks will behave as an associative memory. A neural network so designed can be useful in control as, for example, an advanced dictionary of different control algorithms; when certain operating conditions are present, they are matched to stored conditions. and the control action that corresponds to the conditions that most closely match the current operating conditions are selected. Other applications of associative memories to control are possible. 

A neural network emulator learns to identify the dynamic characteristics of the system. The controller, another multilayered network, then learns to control the emulator. The self-trained controller is then used to control the actual dynamic system. The learning continues as the emulator and controller improve as they track the physical process. 

Hardware implementations of neural networks are seen as necessary. Neural networks are used to process data from many sensors for the real-time control of mobile robots and to provide the necessary learning and adaptation capabilities for responding to the environmental changes in real time. For this. a structured hierarchical neural network and its learning algorithm are used, and the network is divided into two parts connected with each other via short memory units. This approach is applied to several robots, which learn to interact and participate in a form of the cops-and-robbers in “Integrating Neural Networks and Knowledge-Based Systems for Intelligent Robotic Control”. 

One of the key practical problems for many of the neuro control system is the generalisation issue, that is the ability of network to perform well in new situations. Generally those techniques which guarantee stability applied to a restricted class of systems. As the field of neuro control continues to progress stable neuro control methods will be developed for wider claases of systems.