Intelligent Real-Time Monitoring

This paper describes a multi-tasking architecture for performing real-time monitoring and analysis using knowledge-based problem solving techniques. To handle asynchronous inputs and perform in real-time, the system consists of three or more distributed processes which run concurrently and communicate via a message passing scheme. The Data Management Process acquires, compresses, and routes the incoming sensor data to other processes. The Inference Process consists of a high performance inference engine that performs a real-time analysis on the state and health of the physical system. The I/O Process receives sensor data from the Data Management Process and status messages and recommendations from the Inference Process, updates its graphical displays in real time, and acts as the interface to the console operator. The distributed architecture has been interfaced to an actual spacecraft (NASA’s Bubble Space Telescope) and is able to process the incoming telemetry in “real-time” (i.e., several hundred data changes per second). As the application of knowledge-based systems evolves from an art to an engineering discipline, we can expect more challenging applications to be addressed. Some of the most challenging and interesting environments are found in real-time domains. Before going any further we should define precisely what we mean by the term real-time. O’Reilly and Cromarty [2] give a detailed discussion on the meaning of real-time and offer a formal definition: “There is a strict time limit by which the system must have produced a response, regardless of the algorithm employed”. We find it useful to categorize tasks of real-time systems into hard and soft real-time as discussed by Stankovic and Zhao [3]. We define a hard real-time task as one for which the correctness of the system depends not only on the result of computation, but also on the time at which the results are produced. Furthermore, if these strict timing constraints are not met, there may potentially be disastrous consequences. For such tasks, it is necessary to guarantee that timing constraints are met. In contrast, while soft real-time tasks have timing constraints, there may still be *This work was supported under Lockheed Independent Research and Development funds some value for completing the task after its deadline, and disastrous consequences do not result if these tasks miss their deadline. Many applications have both hard and soft real-time requirements. To meet all such deadlines in a system requires sophisticated scheduling algorithms and careful implementation. We will not discuss this topic since it is beyond the scope of this paper. A knowledge-based system operating in a real-time situation (e.g., satellite telemetry monitoring) will typically need to respond to a changing task environment involving an asynchronous flow of events and dynamically changing requirements with limitations on time, hardware, and other resources. A flexible software architecture is required to provide the necessary reasoning on rapidly changing data within strict time requirements while accommodating temporal reasoning, non-monotonicity, interrupt handling, and methods for handling noisy input data. Laffey et. al. [l] give a detailed discussion on the state-of-the-art in using knowledge-based techniques for real-time problems.