Dynamic Across Time Autonomous — Sensing, Interpretation, Model Learning and Maintenance Theory (DATA -SIMLAMT)
A formal theory for the development of a generic model of an autonomous sensor is proposed and implemented. An autonomous sensor is defined as an intelligent sensor that has machine learning capabilities. It not only interprets the acquired data in accordance with an embedded expert system knowledge base, but is also capable of using this data to modify and enhance this knowledge base. Hence, the system is capable of learning and thereby improving its performance over time. The main objective of the model is to combine the capabilities of the physical sensor and an expert operator monitoring the sensor in real-time. The system has been successfully tested using various simulated data sets as well as a real thermistor that has been developed as an autonomous sensor. This work has significant impact on modem production systems since sensors form an integral part of all closed loop control systems, and modem manufacturing processes rely heavily on sensor based control systems. The long range aim of this work is to develop highly autonomous production systems that have self diagnostic, maintenance, self correction, and learning capabilities embedded at the local and global levels. This work builds upon work on a formalized theory for autonomous sensing called Dynamic Across Time Autonomous-Sensing, Interpretation, Model learning and Maintenance Theory (DATA-SEIALAMT) that has been supported by the NSF and the SME Education Foundation.
Mahajan, Ajay and Figueroa, Fernando, "Dynamic Across Time Autonomous — Sensing, Interpretation, Model Learning and Maintenance Theory (DATA -SIMLAMT)" (1995). Mechanical Engineering Faculty Research. 416.