A testbed for data fusion for engine diagnostics and prognostics

A new life system approach to the Prognostic and Health Management (PHM) with survival analysis, dynamic hybrid fault models, evolutionary game theory, and three-layer survivability analysis

“…MacConnell (2007MacConnell ( , 2008) ISHM (Integrated Systems Health Management). Brotherton et al (2002Brotherton et al ( , 2003 identified one significant challenge in PHM: the low "Signal/Noise" ratio, a term they used analogically in fault detection. In other words, fault distribution is strongly skewed and the data in the long "tail" is hard to collect.…”

Prognostic modelling options for remaining useful life estimation by industry

“…They used a Dynamically Linked Ellipsoidal Basis Function neural network to analyse vibration data and then applied a decision tree to interpret the outputs [156]. Another dynamic network capable of fusing different types of input information is the Dynamic Wavelet Neural Network (DWNN) that uses a wavelet function as the activation function in hidden layer nodes.…”

“…Prognostics isy (direct quote) ISO13381-1 [2] An estimation of time to failure and risk for one or more existing and future failure modes Engel [3] The capability to provide early detecting of the precursor and/or incipient fault condition of a component, and to have the technology and means to manage and predict the progression of this fault condition to component failure Hess [167] Predictive diagnostics, which includes determining the remaining life or time span of proper operation of a component Wu [100] The prediction of future health states and failure modes based on current health assessment, historical trends and projected usage loads on the equipment and/or process Luo [5] Failure prognosis involves forecasting of system degradation based on observed system condition Brotherton [168] The ability to assess the current health of a part for a fixed time horizon or predict the time to failure Katipamul [169] Address(ing) the use of automated methods to detect and diagnose degradation of physical system performance, anticipate future failures, and project the remaining life of physical systems in acceptable operating state before faults or unacceptable degradations of performance occur Lewis [170] Prediction of when a failure may occur. To calculate the remaining useful life on an asset Smith [171] The capability to provide early detection and isolation of precursor and/or incipient fault condition to a component or sub-element failure condition, and to have the technology and means to manage and predict the progression of this fault condition to component failure Baruah [73] Prognostics builds upon the diagnostic assessment and are defined as the capability to predict the progression of this fault condition to component failure and estimate the remaining useful life (RUL) Heng et al [25] The forecast of an asset's remaining operational life, future condition, or risk to completion (c) an appreciation of future component operation is required; and (d) prognostics is related to, but not the same as, diagnostics.…”

Current Computational Trends in Equipment Prognostics

“…In recently published prognostics research, a great deal of attention has been focused on the use of machine learning techniques such as artificial neural networks, fuzzy logic-based models, classification and pattern recognition methods 23,24,25,26 .…”