Approach to Monitor and Assess the Quality of Sensor Data in Support of Calibration and Health Maintenance Navy SBIR FY2005.2 Sol No.: Navy SBIR FY2005.2 Topic No.: N05-132 Topic Title: Approach to Monitor and Assess the Quality of Sensor Data in Support of Calibration and Health Maintenance Proposal No.: N052-132-0216 Firm: Systems Planning and Analysis, Inc. 2001 N. Beauregard St Alexandria, Virginia 22311 Contact: Jason Kiddy Phone: (240) 296-1301 Web Site: www.spa.com Abstract: SPA proposed to develop an artificial neural network-based intelligent fault diagnostic system for monitoring the health and calibration of shipboard sensors. The proposed approach will monitor sensor responses in real time to identify sensors that are not operating according to specification. Once identified, the system will determine if re-calibration services are required or if other types of failures have occurred. The system will help reduce maintenance costs and manpower requirements while contributing to a reduced false-alarm rate. Testing of the developed system will be performed in conjunction with the University of Maryland Benefits: The sensor health monitoring methodology developed in this program will be applicable to a variety of other performance critical applications other than shipboard Navy sensors. Air and spacecraft instrumentation would benefit from a real-time fault diagnostic system. Automated vehicle (automobile) management and control systems are highly dependent on accurate and reliable sensor readings. In a more general sense, industrial process monitoring where critical equipment is monitored using multiple sensors would directly benefit from the technology by reducing downtime for false alarms and unnecessary pre-emptive maintenance. For all of these potential applications, the benefits will be similar to the Navy benefits of reduced maintenance, increased productivity, and lower false alarm rates. Return