Michael J. Roemer

Assessment of data and knowledge fusion strategies for prognostics and health management

Various data, feature and knowledge fusion strategies and architectures have been developed over the last several years for improving upon the accuracy, robustness and overall effectiveness of anomaly, diagnostic and prognostic technologies. Fusion of relevant sensor data, maintenance database information, and outputs from various diagnostic and prognostic technologies has proven effective in reducing false alarm rates, increasing confidence levels in early fault detection, and predicting time to failure or degraded condition requiring maintenance action. The data fusion strategies discussed are principally probabilistic in nature and are used to aid in directly identifying confidence bounds associated with specific component fault identifications and predictions. Dempster-Shafer fusion, Bayesian inference, fuzzy-logic inference, neural network fusion and simple weighting/voting are the algorithmic approaches that are discussed. Data fusion architectures such as centralized fusion, autonomous fusion, and hybrid fusion are described in terms of their applicability to fault diagnosis and prognosis. The final goal is to find the optimal combination of measured system data, data fusion algorithms, and associated architectures for obtaining the highest overall prediction/detection confidence levels associated with a specific application. To achieve this goal, a set of metrics has been developed for gauging the performance and effectiveness of a fusion strategy. Specifically, this paper demonstrates how various metrics are used for assessing individual and fused vibration-based diagnostic algorithms. Evaluation of the diagnostic strategies was performed using gearbox seeded-fault and accelerated failure data.

Development of diagnostic and prognostic technologies for aerospace health management applications

Effective aerospace health management integrates component, subsystem and system level health monitoring strategies, consisting of anomaly/diagnostic/prognostic technologies, with an integrated modeling architecture that addresses failure mode mitigation and life cycle costs. Included within such health management systems will be various failure mode diagnostic and prognostic (D/P) approaches ranging from generic signal processing and experience-based algorithms to the more complex knowledge and model-based techniques. While signal processing and experienced-based approaches to D/P have proven effective in many applications, knowledge and model-based strategies can provide further improvements and are not necessarily more costly to develop or maintain. This paper describes some generic prognostic and health management technical approaches to confidently diagnose the presence of failure modes or prognose a distribution on remaining time to failure. Specific examples of D/P strategies are presented that include Auxiliary Power Unit (APU) fuel system valves, APU performance degradation and hot section lifing, Power Take Off (PTO) shaft and AMAD snout bearing.

Enhancement of physics-of-failure prognostic models with system level features

To truly optimize the deployment of DoD assets, there exists a fundamental need for predictive tools that can reliably estimate the current and reasonably predict the future capacity of complex systems. Prognosis, as in all true predictions, has inherent uncertainty, which has been treated through probabilistic modeling approaches. The novelty in the current prognostic tool development is that predictions are made through the fusion of stochastic physics-of-failure models, relevant system or component level health monitoring data and various inspection results. Regardless of the fidelity of a prognostic model or the quantity and quality of the seeded fault or run-to-failure data, these models should be adaptable based on system health features such as vibration, temperature, and oil analysis. The inherent uncertainties and variability in material capacity and localized environmental conditions, as well as the realization that complex physics-of-failure understanding will always possess some uncertainty, all contribute to the stochastic nature of prognostic modeling. However, accuracy can be improved by creating a prognostic architecture instilled with the ability to account for unexpected damage events, fuse with diagnostic results, and statistically calibrate predictions based on inspection information and real-time system level features. In this paper, the aforementioned process is discussed and implemented first on controlled failures of single spur gear teeth and then on a helical gear contained within a drivetrain system. The stochastic, physics-of-failure models developed are validated with transitional run-to-failure data developed at Penn State ARL. Future work involves applying the advanced prognostics process to helicopter gearboxes.

Application of Prognostic Health Management in Digital Electronic Systems

Development of robust prognostics for digital electronic system health management will improve device reliability and maintainability for many industries with products ranging from enterprise network servers to military aircraft. Techniques from a variety of disciplines is required to develop an effective, robust, and technically sound health management system for digital electronics. The presented technical approach integrates collaborative diagnostic and prognostic techniques from engineering disciplines including statistical reliability, damage accumulation modeling, physics of failure modeling, signal processing and feature extraction, and automated reasoning algorithms. These advanced prognostic/diagnostic algorithms utilize intelligent data fusion architectures to optimally combine sensor data with probabilistic component models to achieve the best decisions on the overall health of digital components and systems. A comprehensive component prognostic capability can be achieved by utilizing a combination of health monitoring data and model-based estimates used when no diagnostic indicators are present. Both board and component level minimally-invasive and purely internal data acquisition methods will be paired with model-based assessments to demonstrate this approach to digital component health state awareness.

Electronic prognostics ¿ A case study using global positioning system (GPS).

Prognostic health management (PHM) of electronic systems presents challenges traditionally viewed as either insurmountable or otherwise not worth the cost of pursuit. Recent changes in weapons platform acquisition and support requirements has spurred renewed interest in electronics PHM, revealing possible applications, accessible data sources, and previously unexplored predictive techniques. The approach, development, and validation of electronic prognostics for a radiofrequency (RF) system are discussed in this paper. Conventional PHM concepts are refined to develop a three-tier failure mode and effects analysis (FMEA). The proposed method identifies prognostic features by performing device, circuit, and system-level modeling. Accelerated failure testing validates the identified diagnostic features. The results of the accelerated failure tests accurately predict the remaining useful life of a COTS GPS receiver to within plusmn5 thermal cycles. The solution has applicability to a broad class of mixed digital/analog circuitry, including radar and software defined radio

An Overview of Selected Prognostic Technologies With Application to Engine Health Management

The DoD has various vehicle platforms powered by high performance gas turbine engines that would benefit greatly from predictive health management technologies that can detect, isolate and assess remaining useful life of critical line replaceable units (LRUs) or subsystems. In order to meet these needs for next generation engines, dedicated prognostic algorithms must be developed that are capable of operating in an autonomous and real-time engine health management system software architecture that is distributed in nature. This envisioned prognostic and health management system should allow engine-level reasoners to have visibility and insight into the results of local diagnostic and prognostic technologies implemented down at the LRU and subsystem levels. To accomplish this effectively requires an integrated suite of prognostic technologies that can be applied to critical engine systems and can capture fault/failure mode propagation and interactions that occur in these systems, all the way up through the engine and eventually vehicle level. In the paper, the authors will present a generic set of selected prognostic algorithm approaches that can be applied to gas turbine engines, as well as provide an overview of the required reasoning architecture needed to integrate the prognostic information across the engine.

Methodologies for Adaptive Flight Envelope Estimation and Protection

This paper reports the latest development of several techniques for adaptive flight envelope estimation and protection system for aircraft under damage upset conditions. Through the integration of advanced fault detection algorithms, real-time system identification of the damage/faulted aircraft and flight envelop estimation, real-time decision support can be executed autonomously for improving damage tolerance and flight recoverability. Particularly, a bank of adaptive nonlinear fault detection and isolation estimators were developed for flight control actuator faults; a real-time system identification method was developed for assessing the dynamics and performance limitation of impaired aircraft; online learning neural networks were used to approximate selected aircraft dynamics which were then inverted to estimate command margins. As off-line training of network weights is not required, the method has the advantage of adapting to varying flight conditions and different vehicle configurations. The key benefit of the envelope estimation and protection system is that it allows the aircraft to fly close to its limit boundary by constantly updating the controller command limits during flight. The developed techniques were demonstrated on NASA s Generic Transport Model (GTM) simulation environments with simulated actuator faults. Simulation results and remarks on future work are presented.

Modeling aging effects of IGBTs in power drives by ringing characterization

This paper presents two types of aging modeling for IGBTs. The physical modeling allows a better understanding of the physical mechanics of failures while the functional model represents a more general approach that can be easily extended to model more complex systems. The latter also allows a better characterization of the ringing signal phenomenon, which was found to be characteristic of aged IGBTs. Based on the effects of aging on the ringing, a feature is proposed to capture these changes in real-time and use them as a diagnostic tool for components health state. A real power drive platform is implemented to experimentally verify the ringing characterization modeled and to demonstrate the repeatability of the ringing effects observed at high frequencies in the voltage and current of electrical components.

Online Ringing Characterization as a Diagnostic Technique for IGBTs in Power Drives

Embeddable features that are easily incorporated in traditional power drive systems are identified for prognostics and health management (PHM) systems. The proposed novel feature takes advantage of the original pulsewidth modulation (PWM) waveform produced by the inverter that is already available in the system as a succession of step functions to study the systems response at high frequencies. The high-order oscillatory responses (ringing) present in the voltages and currents of the system are a reflection of the interaction among the internal parametric components of the power devices, allowing device characterization. Evaluating the change over time of these parameters characterized from ringing becomes a key novel feature to assess the aging status of the power electronic circuit and electric machine with respect to transistor degradation. We propose the use of a low-cost bandpass analog filter centered at a high frequency, which is relevant as a feature input capable of aging tracking. The simplified model supporting ringing as a feature to evaluate component aging and its experimental evaluation are presented with experimental data, corroborating its viability as a practical real-time power device health-state indicator.

A Comprehensive Prognostics Approach for Predicting Gas Turbine Engine Bearing Life

Development of practical and verifiable prognostic approaches for gas turbine engine bearings will play a critical role in improving the reliability and availability of legacy and new acquisition aircraft engines. In addition, upgrading current United States Air Force (USAF) engine overhaul metrics based strictly on engine flight hours (EFH) and total accumulated cycles (TAC) with higher fidelity prognostic models will provide an opportunity to prevent failures in engines that operate under unusually harsh conditions, and will help avoid unnecessary maintenance on engines that operate under unusually mild conditions. A comprehensive engine bearing prognostic approach is presented in this paper that utilizes available sensor information on-board the aircraft such as rotor speed, vibration, lube system information and aircraft maneuvers to calculate remaining useful life for the engine bearings. Linking this sensed data with fatigue-based damage accumulation models based on a stochastic version of the Yu-Harris bearing life equations with projected engine operation conditions is implemented to provide the remaining useful life assessment. The combination of health monitoring data and model-based techniques provides a unique and knowledge rich capability that can be utilized throughout the bearing’s entire life, using model-based estimates when no diagnostic indicators are present and using the monitored features such as oil debris and vibration at later stages when failure indications are detectable, thus reducing the uncertainty in model-based predictions. A description and initial implementation of this bearing prognostic approach is illustrated herein, using bearing test stand run-to-failure data and engine test cell data.Copyright