Genetic algorithms (GA) are adaptive search techniques, based on the principles of natural genetics and natural selection, which, in control systems engineering, can be used as an optimization tool or as the basis of ...
详细信息
Genetic algorithms (GA) are adaptive search techniques, based on the principles of natural genetics and natural selection, which, in control systems engineering, can be used as an optimization tool or as the basis of more general adaptive systems. Following an introduction to the simple GA, important characteristics of GA are identified and controlapplications are described.< >
Classifier systems lie midway between neural networks and symbolic processing systems and potentially combine the benefits of both. They are parallel message-passing rule-based systems which use genetic algorithms to ...
详细信息
Classifier systems lie midway between neural networks and symbolic processing systems and potentially combine the benefits of both. They are parallel message-passing rule-based systems which use genetic algorithms to discover new rules as well as providing for reinforcement learning and programming. It has been proposed that a suitable application of genetic algorithms is to evolve robots. A most suitable way to use genetic algorithms to evolve the control systems for robots is within the framework provided by classifier systems. At a SERC workshop on learning systems a number of groups presented successful applications of the genetic algorithm to control problems. However, one cannot evolve complex systems with a simple genetic algorithm nor is it wise or safe to start from scratch in real applications where programmed knowledge can provide constraints for the genetic algorithm to work within. If the genetic algorithm is to be used to evolve control systems for industrial or commercial applications one of the best ways to do this is within the framework of classifier systems.< >
Fuzzy logic can be summed up as a technique for handling 'lexically imprecise propositions' and in particular answering queries through propagation of 'elastic constraints'. In simpler terms fuzzy logi...
详细信息
Fuzzy logic can be summed up as a technique for handling 'lexically imprecise propositions' and in particular answering queries through propagation of 'elastic constraints'. In simpler terms fuzzy logic might be considered as a providing a framework for handling rules (for control or decision making) which have been expressed in an imprecise form. Rule based systems are those which use expertise expressed as a set of rules. Rule based systems need not use fuzzy logic and indeed many have been built which use other forms of knowledge representation. However in controlapplications, rule based approaches have often needed to work with fuzzy representation because of the way the control expertise has been expressed. One of the key concepts of fuzzy logic is that of a linguistic variable. Take for example temperature which would be a linguistic variable in the control of a heater. It can take on linguistic value such as high, low and quite low. Such linguistic variables are embedded in the rules of a fuzzy controller and allow human control expertise to be represented. The paper considers why fuzzy control can be a technical solution, what the structure of a fuzzy controller is and what applications are being tackled. It concludes by considering where new developments will help in the application of fuzzy control.< >
The 'traditional' approach to diagnosis in plant and machinery has been to identify alarm conditions and present to the operator a indication of the alarm state when it arises. In certain pathological cases th...
详细信息
The 'traditional' approach to diagnosis in plant and machinery has been to identify alarm conditions and present to the operator a indication of the alarm state when it arises. In certain pathological cases the flow of alarms can be sudden and in such numbers that the operators quickly become overloaded. However operators are frequently very successful if given sufficient time to assimilate the information. An operator's understanding of the machinery processes may be limited to some prior experience and not the principles on which it operates. By resorting to a description of the process at the level of governing principles, there is a clearer opportunity to find and correct the problem. The author presents the framework for using qualitative models in a framework where evidence from external tests can be introduced. The framework takes the form of a series of knowledge sources in a knowledge-based supervisory system.< >
The process of control system is a well understood, structured and iterative process. One form of real time control involves real time design and in this approach to expert control the controller is designed or update...
详细信息
The process of control system is a well understood, structured and iterative process. One form of real time control involves real time design and in this approach to expert control the controller is designed or updated on a real time basis. It is this approach to expert control that is considered. A general knowledge base structure for expert controlbased on the 'blackboard' concept and object oriented design has been suggested.< >
Numerical control algorithms have a firm theoretical basis and a small class of algorithms typified by the three term controller is well accepted in the process industry. The basis for continuing to apply such algorit...
详细信息
Numerical control algorithms have a firm theoretical basis and a small class of algorithms typified by the three term controller is well accepted in the process industry. The basis for continuing to apply such algorithms is that in a well tuned form they often exercise excellent control and are robust in the face of certain changes in the process. In this context, the role of knowledgebasedcontrol is in the supervision of closed loop controllers based on traditional algorithms.< >
The paper is based on experience gained in the installation and commissioning of the LINKman rule basedcontrol system in cement plants and other industries. However despite the success of these techniques in cement t...
详细信息
The paper is based on experience gained in the installation and commissioning of the LINKman rule basedcontrol system in cement plants and other industries. However despite the success of these techniques in cement the number of such systems in use outside the cement industry is still very small. One reason appears to be concern about plant safety. The paper addresses this issue and then reviews the factors upon which the success of a project depends.< >
Implementing a process model using fuzzy methods has proved successful when considering the steady state determined models basedcontroller algorithm of Davison, and has given a much improved performance when compared...
详细信息
Implementing a process model using fuzzy methods has proved successful when considering the steady state determined models basedcontroller algorithm of Davison, and has given a much improved performance when compared to a design based on average process gains only. With the addition of dynamic response and process dead time compensation inherent in the self organising process at the highest level it is then possible to provide a direct and straightforward approach to tuning and adaptation of model basedcontrol algorithms.< >
The authors describe the application of a self-organising computer vision control system for fibre quality monitoring at hardboard mills. The system provides a continuous measurement of fibre quality and uses the rule...
详细信息
The authors describe the application of a self-organising computer vision control system for fibre quality monitoring at hardboard mills. The system provides a continuous measurement of fibre quality and uses the rule-basedcontroller to advise the machine operator to alter the refiner settings.< >
COGSYS is a real-time knowledge-based system which can function as a SCADA (Supervisory control and Data Acquisition) system, but with a more structured development language, declarative and procedural knowledge inste...
详细信息
COGSYS is a real-time knowledge-based system which can function as a SCADA (Supervisory control and Data Acquisition) system, but with a more structured development language, declarative and procedural knowledge instead of just procedural, and extra levels of processing. It was used at British Gas in conjunction with an existing PID (proportional, integral and derivative) control system on a methanator feedgas production plant. Four main areas were covered: control optimisation; condition monitoring; procedures; and alarm interpretation.< >
暂无评论