User:Mdebellis/realtimeadaptaton

Real-time adaption

Industrial processes, data networks, and many other systems change their state and even their structure over time. Real time expert systems are designed to reason over time and change conclusions as the monitored system changes. Most of these systems must respond to constantly changing input data, arriving automatically from other systems such as process control systems or network management systems.

Representation includes features for defining changes in belief of data or conclusions over time. This is necessary because data becomes stale. Approaches to this can include decaying belief functions, or the simpler validity interval that simply lets data and conclusions expire after specified time period, falling to "unknown" until refreshed. An often-cited example (attributed to real time expert system pioneer Robert L. Moore) is a hypothetical expert system that might be used to drive a car. Based on video input, there might be an intermediate conclusion that a stop light is green and a final conclusion that it is OK to drive through the intersection. But that data and the subsequent conclusions have a very limited lifetime. You would not want to be a passenger in a car driven based on data and conclusions that were, say, an hour old.

The inference engine must track the times of each data input and each conclusion, and propagate new information as it arrives. It must ensure that all conclusions are still current. Facilities for periodically scanning data, acquiring data on demand, and filtering noise, become essential parts of the overall system. Facilities to reason within a fixed deadline are important in many of these applications.

An overview of requirements for a real-time expert system shell is given in. Examples of real time expert system applications are given in and. Several conferences were dedicated to real time expert system applications in the chemical process industries, including.