Sujeet Chand

Time templates for discrete event fault monitoring in manufacturing systems

The input and output signals of automated manufacturing systems can be characterized as observed time functions of discrete events. Fault monitoring is the online analysis of the process observations to determine if they correspond to a specification of correct process operation. In this paper, we describe a new fault monitoring method, called template monitoring. Template monitoring overcomes several limitations associated with methods based on traditional discrete event process models. The template monitoring method is easily distributable, and is suitable for monitoring concurrent event relationships. We derive analytical results for generating templates from timed automaton models and describe the use of templates for real-time monitoring and diagnostics.

Discrete-Event Based Monitoring and Diagnosis of Manufacturing Processes

We describe a decentralized control method that augments Boolean logic control to provide greatly enhanced diagnostics and monitoring of systems with discrete-valued sensors and actuators. Unlike conventional Boolean logic where logic is associated with the actuators, the new method defines a behavior and timing model for both sensors and actuators (called Control Elements). The behavior model is defined by a sequence of events called the event signature, in a Control Elements (CE) neighborhood. The event signature encodes a subset of the process state into each CE. We describe a method for the continuous evaluation of this signature to compute a measure of the likelihood of a CE to change state. This likelihood measure called an Expectation Function, is used to check and enforce the correct behavior of a CE. Also, each CE learns a statistical temporal model in real time. The temporal model predicts delays in the states of the CE as a function of the previous delays and the current delays in the evaluation of its event signature. The distributed behavior model and the on-line estimated timing model are applied to a simulated bottle filling station to illustrate the detection and-diagnosis of incorrect behavior and failures of Control Elements.

A DEVELOPMENT ENVIRONMENT FOR FUZZY RULE-BASED TRAFFIC CONTROL

We present a development environment for fuzzy rule-based traffic control systems. This Macintosh® environment allows a user to simulate traffic on a network of streets and create fuzzy decision rules for adjusting traffic signal timing parameters at the intersections. During simulation, various graphical displays help the user interactively debug and fine-tune the decision rules. When the results are satisfactory, C or Ada code can be automatically generated to implement the fuzzy knowledge base. We also describe a specific knowledge base developed using this environment and present some results.