Rolf F. Orsagh

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.

Prognostic health management for avionics system power supplies

This paper presents an integrated approach to switching mode power supply health management that implements techniques from engineering disciplines including statistical reliability modeling, damage accumulation models, physics of failure modeling, and sensor-based condition monitoring using automated reasoning algorithms. Novel features extracted from sensed parameters such as temperature, power quality, and efficiency were analyzed using advanced fault detection and damage accumulation algorithms. Using model-based assessments in the absence of fault indications, and updating the model-based assessments with sensed information when it becomes available provides health state awareness at any point in time. Intelligent fusion of this diagnostic information with historical component reliability statistics provides a robust health state awareness as the basis for accurate prognostic predictions. Complementary prognostic techniques including analysis of projected operating conditions by physics-based component aging models, empirical (trending) models, and system level failure progression models will be used to develop verifiable prognostic models. The diagnostic techniques, and prognostic models have been demonstrated through accelerated failure testing of switching mode power supplies

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

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

Prognostic health management for avionic systems

Maintenance of aircraft electronic systems has traditionally been performed in reaction to reported failures or through periodic system replacements. Recent changes in weapons platform acquisition and support requirements have spurred interest in application of prognostic health management (PHM) concepts developed for mechanical systems to electronic systems. The approach, development, and validation of prognostics for two types of electronic equipment are discussed in this paper. The two applications, a switch-mode power supply and a GPS receiver were selected based on their relatively high failure rates and relevance to many commonly used avionics systems. The method identifies prognostic features by performing device, circuit, and system-level modeling. Device modeling with equivalent circuit and mathematical physics of failure models describe parameter degradation resulting from damage accumulation for each device. Prognostic features extracted from a small array of sensors on the power supply, and from the GPS operational communication data stream are used to update life usage and failure progression models to provide an indication of the health state. The results of accelerated failure tests on both systems are used to illustrate the approach and demonstrate its effectiveness in predicting the useful life remaining. The solutions have applicability to power supplies in many avionic systems, and to a broad class of mixed digital/analog circuitry including radar and software defined radio

Prognostics/Diagnostics for Gas Turbine Engine Bearings

Development of robust in-flight prognostics or diagnostics for oil wetted gas turbine engine components will play a critical role in improving aircraft engine reliability and maintainability. Real-time algorithms for predicting and detecting bearing and gear failures are currently being developed in parallel with emerging flight-capable sensor technologies including in-line oil debris/condition monitors, and vibration analysis MEMS. 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 oil-wetted components. By utilizing a combination of health monitoring data and model-based techniques, a comprehensive component prognostic capability can be achieved throughout a components life, using model-based estimates when no diagnostic indicators are present and monitored features such as oil debris and vibration at later stages when failure indications are detectable. Implementation of these oil-wetted component prognostic modules will be illustrated in this paper using bearing and gearbox test stand run-to-failure data.Copyright

Advanced vibration diagnostics for engine test cells

Current engine test cell systems were designed to perform a simple vibration amplitude check. If the root mean square (RMS) vibration amplitude falls within specifications under programmed operating conditions with no need for adjustments, then the engine is considered to be ready for installation. Engine test cell vibration analysis techniques are being developed to improve engine reliability and availability while simultaneously reducing life cycle costs. The engine test cell vibration diagnostic system under development provides both real-time and post-test analysis of engine vibration data. The real-time vibration diagnostic system identifies sensor faults before they lead to an incorrect diagnosis and plots key vibration diagnostic features such as tracked orders during the test. Vibration sensor faults are a common cause of test cell ineffectiveness. The post-test vibration diagnostic software allows users to perform detailed examinations of vibration features including multiple engine order tracks and waterfall plots recorded by the real-time module. The post-test software also utilizes advanced feature extraction and analysis techniques (such as half engine orders, harmonics and sidebands) to diagnose incipient mechanical faults. In addition to describing the abovementioned techniques, this paper overviews vibration data transfer methods and design of the graphical user interface (GUI).

Upgrading engine test cells for improved troubleshooting and diagnostics

Upgrading military engine test cells with advanced diagnostic and troubleshooting capabilities will play a critical role in increasing aircraft availability and test cell effectiveness while simultaneously reducing engine operating and maintenance costs. Sophisticated performance and mechanical anomaly detection and fault classification algorithms utilizing thermodynamic, statistical, and empirical engine models are now being implemented as part of a United States Air Force Advanced Test Cell Upgrade Initiative. Under this program, a comprehensive set of realtime and post-test diagnostic software modules, including sensor validation algorithms, performance fault classification techniques and vibration feature analysis are being developed. An automated troubleshooting guide is also being implemented to streamline the troubleshooting process for both inexperienced and experienced technicians. This artificial intelligence based tool enhances the conventional troubleshooting tree architecture by incorporating probability of occurrence statistics to optimize the troubleshooting path. This paper describes the development and implementation of the F404 engine test cell upgrade at the Jacksonville Naval Air Station.

Upgrading Engine Test Cells for Improved Troubleshooting and Diagnostics

Upgrading military engine test cells with advanced diagnostic and troubleshooting capabilities will play a critical role in increasing aircraft availability and test cell effectiveness while simultaneously reducing engine operating and maintenance costs. Sophisticated performance and mechanical anomaly detection and fault classification algorithms utilizing thermodynamic, statistical, and empirical engine models are now being implemented as part of a United States Air Force Advanced Test Cell Upgrade Initiative. Under this program, a comprehensive set of real-time and post-test diagnostic software modules, including sensor validation algorithms, performance fault classification techniques and vibration feature analysis are being developed. An automated troubleshooting guide is also being implemented to streamline the troubleshooting process for both inexperienced and experienced technicians. This artificial intelligence based tool enhances the conventional troubleshooting tree architecture by incorporating probability of occurrence statistics to optimize the troubleshooting path. This paper describes the development and implementation of the F404 engine test cell upgrade at the Jacksonville Naval Air Station.Copyright

Looking past BIT - incipient fault detection and prognostics for avionics system power supplies

This paper presents an approach to enhancing current avionic system power supply diagnostics with prognostic techniques for improved equipment health management. The approach integrates techniques from engineering disciplines including automated testing, incipient fault detection and classification, fault to failure progression modeling, statistical reliability analysis, and automated reasoning. Novel features extracted from sensed parameters such as power quality, component operating temperature, control loop signature, and efficiency are analyzed using advanced fault detection and damage accumulation algorithms. Intelligent fusion of this diagnostic information with historical component reliability statistics provides a robust health state awareness as the basis for accurate prognostic predictions. Complementary prognostic techniques including analysis of projected operating conditions by physics-based component aging models and system level failure progression models are used to develop predictions of future equipment health. The diagnostic techniques and prognostic models have been demonstrated through accelerated failure testing of switching mode power supplies