Microphone Phased Array Machinery Fault Diagnostic System (Revised)

The objective of this effort is to develop a remote acoustics-based system to detect rotating equipment health status. The goal is an automated acoustic monitoring system that includes the necessary filtering/data manipulation techniques and expert system/classification/anomaly detection algorithms to diagnose the health of plant equipment (compressors, electric motors, gear trains, fans, etc) in an industrial high-bay area environment. The system will also have the capability to learn and recall the acoustic signature of novel faults and the capability to send an alarm. The health monitoring proposed here is based on a microphone phased array positioned such as to have a direct line of sight to the machine to be monitored. The microphone signals are recorded simultaneously and used to scan or beamform over a grid enclosing the machine to capture its acoustic signature. The acoustic image is then integrated to obtain the machine noise spectrum that is used to identify damage or faults by an automated expert system. The system will operate properly without human intervention while targeting and identifying developing faults. The objective of the Phase II effort is the development and demonstration of a prototype microphone phased array based fault monitoring system on a large-scale plant equipment.