Online Signal Validation for Assured Data Quality

Online signal data validation enables effective decision making for analysis, test, operation, maintenance, and certification of performance critical systems. For example, online data validation prevents a facility safety or control system from making critical decisions, such as the decision to shut down a process or abort a mission, on the basis of bad signal data. Online data validation improves process quality and efficiency by ensuring that closed loop control or scientific data analysis is performed using good data. Finally, online data validation increases system up time and decreases operations cost by enabling calibration and maintenance using on-condition criteria rather than time-inservice criteria. A new procedure to automatically validate and assess the quality of online signal data is presented. The procedure uses model based parameter estimation in conjunction with statistical fault detection and Bayesian fault diagnosis. Traditional data quality filters are integrated with the probability-based fault diagnosis procedure. An application to Space Shuttle Main Engine telemetry data monitoring is described.