GE monitors a large number of heavy duty equipment for energy generation, locomotives and aviation. These monitoring and diagnostic centers located world-wide sense, derive, transmit, analyze and view terabytes of sensory and calculated data each year. This is used to arrive at critical decisions pertaining to equipment life management - like useful life estimation, inventory planning and finally assuring a minimum level of performance to GE customers.

The application of Acoustic Emission (AE) technology for machine health monitoring is gaining ground as powerful tool for health diagnosis of rolling element bearings. The successful application of AE to life prognosis of bearings is very dependent on the ability of the technology to identify and locate a defect at its earliest stage. Determining source locations of AE signals originating in real time from materials under load is one of the major advantages of the technology.

The present work contains two parts. In the first part, high temperature integrated ultrasonic transducers (IUTs) made of thick piezoelectric composite films, were coated directly onto lubricant oil supply and sump lines of a modified CF700 turbojet engine. These piezoelectric films were fabricated using a sol-gel spray technology. By operating these IUTs in transmission mode, the amplitude and velocity of transmitted ultrasonic waves across the flow channel of the lubricant oil in supply and sump lines were measured during engine operation.

This paper describes the use of vibration analysis with a fully automated diagnostics system to detect common machine faults such as imbalance and misalignment as well as bearing and gearbox faults of offshore machines. Other faults types, e.g. when a large object hits the propeller blades may be detected using the STFT. As the mechanical properties of the structure can change because of changes of temperature and oil quality, these (and other) state data are also stored. The data fusion process is currently under work.

This paper reviews the application of oil debris monitoring as an effective PHM solution for wind turbine gearboxes. The paper explains the common surface fatigue damage mode of bearing and gear rolling elements and the characteristics of the destructive debris that result from this damage mode. The paper outlines a simple means of deriving accumulated debris count damage limits based upon basic gearbox component geometry and the use of moving averages for estimating rates of debris generation as a simple yet effective damage data-driven propagation model.

Researchers in tool condition monitoring often collect large amount of sensor signal data from experiments to study the complex tool condition relationships with signals. In order to provide new light into this process on a real-time basis, it is critical to identify and detect abnormality at the lowest resolution possible so that the wear behavior on each flute within a tool revolution can be clearly shown. A signal stream clustering method is developed to separate numerous tool-revolution signals into similar groups, each representing a specific set of corresponding events.

Aircraft engine bearing prognosis not only requires early detection of a bearing defect, but also the ability to predict bearing health conditions given certain operational scenarios. This paper summarizes a physics-based remaining useful life prediction method developed in the DARPA engine system prognosis (ESP) program. This investigation focuses on a typical roller bearing fault (or defect) on the outer raceway. Spall detection is based on the fusion of vibration and online oil debris sensors.

Actuator systems are employed widely in aerospace, transportation and industrial processes to provide power to critical loads, such as aircraft control surfaces. They must operate reliably and accurately in order for the vehicle / process to complete successfully its designated mission. Incipient actuator failure conditions may severely endanger the operational integrity of the vehicle / process and compromise its mission.

Time Synchronous Average (TSA) is an essential algorithmic tool for determining the condition of rotating equipment. Given its significance to diagnostics, it is important to understand the algorithms performance characteristics. This paper addresses four topics in relation to the TSA performance characteristics. The first topic is the evaluation of the performance (measured against gear fault detection) of 6 different TSA algorithms.