Artificial intelligence system for

BE-740S The development of a PC artificial intelligence system for the diagnosis and oroanosis of machine condition usina acoustic emission and acceleration Mr. A. Aurrecoechea gBKWS ... 

An artificial intelligence system for the chemistry of a fossil once-through steam system has been constructed. It is based on on-line monitors. It diagnoses both sensor and plant malfunction and removes malfunctioning sensors from diagnosis of plant malfunctions. The system has been tested off-line using real and synthesized power plant data and is now ready for testing in a plant. 

Elyashberg, M.E., Serov, V.V., and Gribov, L.A., Artificial Intelligence Systems for Molecular Spectral Analysis, Talanta, 34, 21, 1987. 

Computer library searching of spectral databases is routinely available. The database is usually a component part of the spectrometer although the search may be undertaken remotely. Several attempts have been made to develop artificial intelligence systems for direct spectral interpretation, but to date these have met with limited success. Advances in computer control have allowed multiexperiment analysis in which the spectrometer will follow a set of experiments sequentially while automatically adjusting operating parameters as directed by the results of the preceding experiment. Further advances in this area are anticipated. 

Winne, P.H., Project DOCENT-Phase II Artificially Intelligent Systems for Teaching and Learning, manuscript, 1988b. 

It is this integrative attitude that today characterizes most of the work in the area of intelligent systems for process engineering, as the editors of this volume have indicated in a recent review article. (4) It is this need for integrative approaches that has moved the applications of artificial intelligence into the mainstream of engineering activities. This is certainly the pivotal feature that characterizes the ten paradigms discussed in the subsequent chapters. 

These two actions by the computer are key to the success of this project. This is because it will be impossible for a human to consider all the possibilities of a large data set and to deduce the best (most simple and therefore cost effective) rules to use in order to choose the best protective materials to use. And when the data base is dynamically growing it would be impossible to use a highly structured artificial intelligence system where the user had to rewrite the program modifications himself every time there was a change in the information. 

Expert artificial intelligence system/205 are particularly pertinent to the development of robust separations strategies for the RPC isolation of larger synthetic peptides. 

In the lab, future expansion plans include the use of optical scanners for reading sample labels, operation of robots to relieve some of the manual operations and an artificial intelligence system to track quality control. In other areas, there will be an increase in the number of real time monitors, not necessarily because real time data is needed, but the cost can be small compared to sending out a field team. There will be some applications of direct monitoring by satellites such as LANDSAT D. Both of these will be incorporated into water quality models which will allow more intelligent choices of where to send a field team to collect samples for detailed analysis. 

Only a few production system models have attained the status of complete models of cognition, for example, ACT and SOAR. No commensurate connectionist models of cognition have yet been developed, although Rumelhart and McClelland clearly have such aspirations in their PDP work. Most connectionist models are still relatively narrow in scope. For the most part, they lag behind the production system models. The lag can be explained in terms of time. Production systems have been a major part of artificial intelligence research for many years and have been the focus of much research in cognitive science. Connectionist models are just now becoming accepted. 

The artificial intelligence systems to which sensor arrays are coupled supply the closest likeness to the human olfactory system. Some of the recent theories on olfaction require that the human nose has only relatively few types of receptor, each with low specificity. The activation of differing patterns of these receptors supplies the brain with sufficient information for an odour to be described, if not recognized. As a consequence of this belief, the volatile chemical-sensing systems commercially available only contain from 6 to 32 sensors, each having relatively low specificity. Statistical methods such as principal component analysis, canonical discriminant analysis and Euclidian distances are used for mapping or linked to artificial neural nets as an aid to classification of the odour fingerprints . 

For over a decade, a number of research teams have pursued the automation of this last, interpretative stage of the analytical spectroscopic process. There are two general ways of approaching this problem by using library searching systems or artificial intelligence systems (pattern recognition and expert systems) which are commented on below. 

---