Prognostics And Health Monitoring Research Articles

A Comprehensive Review on Low-Cost MEMS Accelerometers for Vibration Measurement: Types, Novel Designs, Performance Evaluation, and Applications

Maintenance of mechanical elements is considered to be the most crucial task in industry and affects the economics, predominantly. There are many techniques available for fault diagnosis and condition monitoring of rotatory machine elements and one of the popular tools is vibration monitoring. Analyzing vibrations would be useful in supervising equipment/machine components in an attempt to detect the significant change which is the cause of growing failures or faults. Broadly speaking, it comes under prognostics and health monitoring (PHM) and prevents unexpected failure and costly repair. Proficient predictive monitoring and on-board recognition of failures is a need of the Fourth Industrial Revolution. Several types of vibration analyzers and sensors are commercially available, however, their total budget is not affordable. This motivates reviewing the suitability of low-cost sensors for vibration monitoring. An inclusive review of a variety of applications wherein microelectromechanical system (MEMS)-based accelerometer is used is presented in this paper. This would support an open-design movement for creating open.

(Digital Presentation) Data-Driven Prognosis of Lithium-Ion Batteries Thermal Runaway Early Warning and Detection

Li-ion batteries (LIBs) are becoming ubiquitous in portable, stationary, and electrical energy storage applications that power various devices, from cell phones to the zero-emission plane. Market research suggests the $26.9 billion-a-year (2018) worldwide LIB market could reach $107 billion-a-year by 2025. Taking electric vehicles (EVs) for example, according to the Electric Drive Transportation Association (EDTA), the number of EV sales in the United States market has increased from 345 vehicles in 2010 to 331,617 in 2019, with a total cumulative number of 1.44 million vehicles over the ten-year sales period. This trend has also been observed in the global market as EVs' sales reached 2.1 million worldwide in 2019, boosting the stock to 7.2 million. Although the COVID-19 pandemic dramatically affected the global EV market and prompted the market to plummet over the year 2020 relative to 2019. The global EVs stock projections are expected to increase from 7.2 million to 14 million in 2025 and 25 million in 2030, accounting for 10% of global passenger vehicle sales in 2025 and 28% in 2030. Despite rapidly skidding into the EV era - a technical fait accompli- significant obstacles to vehicle electrification and adoption, especially the safety of their batteries, continue to threaten that future. The risk of anomaly generation and evolution (e.g., thermal runaway and exploration) is currently a major safety concern and challenge in applications powered by LIBs.The traditional first-principle simulations and comprehensive experiments are time-consuming or less effective in detecting and predicting the above problems induced by a synergistic effect of multiple degradation mechanisms. The above challenge eventually necessitates predictive or prognostic capability for Prognostics and Health Monitoring (PHM) under a complexly hostile working environment.This proposal will break away from existing practices, and instead, for the first time, the proposed data-driven prognosis (DDP) requires the assumption of the existence of a conservation principle but does not require a priori knowledge of the key mechanisms and boundary conditions. Alternatively, the exact form of the conservation functional is only specified locally, in the neighborhood of each observation point (and is assumed to be piecewise quadratic in the current work), whereas its global form remains unknown. The conservation principle is then defined as the minimization of system curvature at each observation point. The DDP methodology is based on the local curvature of the mathematical manifold representing the Euler-Lagrange governing equation of a system. The curvature represents a derivative of the total energy with respect to sensed variables, and instability is anticipated whenever the curvature exceeds a critical threshold, denoted by the inverse of the local length-scale of the manifold (or its extrinsic curvature). The length-scale, in turn, is calculated by solving the first moment of the state-space description (conservation of linear momentum) based on two consecutive time instants of measurements. In another sense, the DDP technique can estimate a mass normalized Energy Exchange Amplitude (EEA) that also represents a scaled “entropy rise” of the system. After acquiring the input data from the literatures, they were fed into DDP in a continuous order separated by each time step. At each time step, two consecutive time instances were considered that are sufficient to make the prognostication. The results of the simulation using the DDP are shown below. First the progression of PDI which shows the percentage of points that have reached different path dependence index (PDI) markers as shown in Figure 1 (a). It signifies the instants when the battery shows local instabilities. As shown in the figure, battery starts to show local instability from time instant 20 and beyond, highlighting the instability's progression. The chain length (CL) values and residual curvature information were analyzed as well and shown in Figure 1 (b) along with other criterias. As illustrated in the Figure, at time instant 10, the system crosses the critical chain length threshold and intensifies around time instance 20. Furthermore, the residual curvature (RC) value exceeds the critical threshold at time instance 19 and 21. The moment when all three criterias were met, the battery is expected to fail which is time instance 21 as shown in the Figure. Figure 1

Application of machine learning algorithms in prognostics and health monitoring of electronic systems: A review

In the modern age of digitalization, electronics are fundamental to any engineering system. With the current strong focus on the Internet of Things (IoT), autonomous vehicles and Industry 4.0, reliable electronics are gaining crucial importance. Predicting the health of complex systems is able to avoid catastrophic failures. Prognostic and Health Monitoring (PHM) approaches are an important step toward trustable and reliable electronics. Nowadays, Artificial Intelligence (AI) and machine learning (ML) algorithms are integrated into PHM approaches, enabling complex fault diagnosis. In this contribution, we provide an overview of the application of intelligent algorithms in PHM of electronics in a systematic manner. The challenges of prognostics in electronics are provided and a detailed overview of the available PHM precursors for various electronic components and the associated selection process is given. Based on the literature review conducted, the main research challenges with ML algorithms in PHM are discussed along with performances of each model.

(Digital Presentation) Data-Driven Prognosis of Battery Failure Detection and Prediction

Although the electric vehicle market is witnessing an unprecedented evolution, the fast adoption of these vehicles requires a more thorough status analysis of the battery performance's functionality and reliability. Due to their rechargeable nature, Lithium-ion batteries (LIBs) operation is subject to different irreversible processes during their charging and discharging cycles and causing capacity fade due to various degradation mechanisms. These processes generally result in battery capacity degradation, which usually results in battery failure, with consequences ranging from loss of operation, reduced capability, downtime, and catastrophic malfunctions. To address the issues mentioned above, numerous studies have been dedicated to proposing proper degradation model mechanisms for improving the reliability and availability of LIBs. However, due to accuracy and computational complexity challenges, most existing remaining useful life (RUL) and health prediction models focus on special degradation effects and ignore the integrated deterioration mechanisms, which generally involve batteries' capacity fade associated with the inadequacy of current health estimation tools. Thus, these shortcomings ultimately echo the need to devise novel tools to identify the dominant criteria negatively affecting battery performance and accurately predict the system's failure. The above challenges eventually necessitate a robust and reliable predictive or prognostic capability for prognostics and health monitoring (PHM) under a complexly hostile working environment. In this context, this investigation aims at proposing a novel data-driven approach called data-driven prognosis (DDP) that estimates the relevant constitutive parameters in situ and captures deviations from the expected degradation dynamics of the LIBs in addition to precise modeling of the degradation and capacity models. This talk will present a new data-driven approach using statistical pattern recognition and machine learning tools to detect batteries' anomalies and failures.

Data-Efficient Estimation of Remaining Useful Life for Machinery With a Limited Number of Run-to-Failure Training Sequences

Prognostics and Health Monitoring (PHM) of machinery is a research area with great relevance to industrial applications as it can serve as a foundation for safer, more cost-efficient operation and maintenance. The prediction of Remaining Useful Life (RUL) plays an important part in this field and has seen significant advances from the introduction of machine learning methods. However, these methods typically require model training with a large number of run-to-failure sequences, which are often not feasible to obtain due to the required time and cost investments. The present study addresses this issue by introducing a novel methodology, which first quantifies the deviation from the machine’s health and fault state and then calculates a machine Health Index (HI) prior to the prediction of RUL. In addition, the start of a degradation state is determined. Alternative implementations of the proposed methodology are compared utilising several methods, including Support Vector Regression (SVR), Long Short-Term Memory (LSTM) Neural Network (NN), Mahalanobis Distance (MD), and LSTM Autoencoder (AE) NN. The methodology is applied to the open turbofan degradation (C-MAPSS) and bearing vibration (FEMTO-ST PROGNOSTIA) datasets. When a reduced subset of training sequences is used, the prediction results demonstrate that the proposed methodology largely outperforms the baseline method without HI generation. For example, when comparing prediction errors of the C-MAPSS dataset at a reduction of the available number of training sequences to 5%, the proposed method shows an average prediction improvement by 6.5% - 19.2% relative to the baseline method. The presented approach is therefore suitable to improve model generalisation for cases with a limited number of training sequences. When the full training set is utilised, the most resource-saving variant of the proposed approach achieves an average training duration of 8.9% compared to the baseline method. Hence, an additional contribution of the presented data-efficient approach is the reduction of required computing resources, which has implications on training time, energy consumption, and environmental impact.

Data-Driven Prognosis of the Failure of Lithium-Ion Batteries

Although the electric vehicle market is witnessing an unprecedented evolution, the fast adoption of these vehicles requires a more thorough status analysis of the battery performance's functionality and reliability. Due to their rechargeable nature, Lithium-ion batteries (LIBs) operation is subject to different irreversible processes during their charging and discharging cycles and causing capacity fade due to various degradation mechanisms. These processes generally result in battery capacity degradation, which usually results in battery failure, with consequences ranging from loss of operation, reduced capability, downtime, and catastrophic malfunctions. To address the issues mentioned above, numerous studies have been dedicated to proposing proper degradation model mechanisms for improving the reliability and availability of LIBs. However, due to accuracy and computational complexity challenges, most existing remaining useful life (RUL) and health prediction models focus on special degradation effects and ignore the integrated deterioration mechanisms, which generally involve batteries' capacity fade associated with the inadequacy of current health estimation tools. Thus, these shortcomings ultimately echo the need to devise novel tools to identify the dominant criteria negatively affecting battery performance and accurately predict the system's failure. The above challenges eventually necessitate a robust and reliable predictive or prognostic capability for prognostics and health monitoring (PHM) under a complexly hostile working environment. In this context, this investigation aims at proposing a novel data-driven approach called data-driven prognosis (DDP) that estimates the relevant constitutive parameters in situ and captures deviations from the expected degradation dynamics of the LIBs in addition to precise modeling of the degradation and capacity models. This talk will present a new data-driven approach using statistical pattern recognition and machine learning tools to detect batteries' anomalies and failures.

Age and Condition-Based Preventive Replacement Timing for Periodic Aircraft Maintenance Checks

By anticipating impending failures and addressing those with preventive replacements, Condition-Based Maintenance (CBM) can provide several economic benefits to aircraft operators. While Prognostics and Health Monitoring (PHM) methods are widely available, scheduling of tasks originating from those methods is a relatively new challenge. To avoid incurring extra cost and ground-time, these maintenance tasks are typically scheduled during already existing (conventional) maintenance slots such as periodic checks. Following this strategy, an aircraft component would have to be replaced if a failure precursor is detected that is expected to result in failure between the next two checks. The decision following from that detection depends on the chosen decision threshold of the prognostic or diagnostic model, which can be represented by a point on the Receiver Operating Characteristic curve. Selecting the optimal operating point for each maintenance check is challenging, as it depends on the age-dependent reliability of the component, the performance of the prognostic (diagnostic) model, the interval of the periodic check and the cost of (corrective and preventive) maintenance. This paper presents an innovative method for selecting optimal operating points for all periodic checks throughout the lifetime of an aircraft component. This is done by means of a numerical optimization model that finds operating points that minimize the component’s total maintenance cost per flight hour. A case study on a compressor of a wide-body aircraft is presented, which shows that by using this method, additional economic value from existing PHM can be realized without the need for additional investments.

Remaining Useful Lifetime (RUL): Probabilistic Predictive Model

Reliability evaluations and assurances cannot be delayed until the device (system) is fabricated and put into operation. Reliability of an electronic product should be conceived at the early stages of its design; implemented during manufacturing; evaluated (considering customer requirements and the existing specifications), by electrical, optical and mechanical measurements and testing; checked (screened) during fabrication; and, if necessary and appropriate, maintained in the field during the product’s operation. Prognostics and health monitoring (PHM) effort can be of significant help, especially at the last, operational stage, of the product use. Accordingly, a simple and physically meaningful probabilistic predictive model is suggested for the evaluation of the remaining useful lifetime (RUL) of an electronic device (system) after an appreciable deviation from its normal operation conditions has been detected, and the corresponding increase in the failure rate and the change in the configuration of the wear-out portion of the bathtub curve has been assessed. The general concepts are illustrated by a numerical example. The model can be employed, along with other PHM forecasting and interfering tools and means, to evaluate and to maintain the high level of the reliability (probability of non-failure) of a device (system) at the operation stage of its lifetime.

Model-based strategy and surrogate function for health condition assessment of actuation devices

Prognostics and Health Monitoring (PHM) is a discipline aiming to determine in advance the Remaining Useful Life (RUL) of a system. To do so, the operation of the system is monitored in search of the early signs of degradation and incipient faults; then, a model for the propagation of faults is employed to estimate the propagation of damages and evaluate the RUL. Usually, a fault threshold is employed as a stopping criterion for the evaluation of damage propagation, but this is not a reliable method when dealing with multiple faults affecting the system at the same time. Specifically, the combined effect of two fault modes can cause the system not to meet its requirements well before the single faults reach their individual thresholds. In this work, we address a model-based strategy to estimate whether the system with incipient faults is still able to meet its performance requirements. The method is applied to aerospace actuators, and performance is evaluated in terms of dynamical response. This model-based algorithm is too slow to be evaluated in real-time, so a Support Vector Machine (SVM) is trained as a surrogate function to speed up the computation. The results and computational times of the full, physics based model and those of its surrogate are compared and discussed.

A High Fidelity Model Based Approach to Identify Dynamic Friction in Electromechanical Actuator Ballscrews using Motor Current

An enhanced model based approach to monitor friction within Electromechanical Actuator (EMA) ballscrews using motor current is presented. The research was motivated by a drive in the aerospace sector to implement EMAs for safety critical applications to achieve a More Electric Aircraft (MEA). Concerns in reliability and mitigating the single of point of failure (ballscrew jamming) have resulted in consideration of Prognostics and Health Monitoring (PHM) techniques to identify the onset of jamming using motor current. A higher fidelity model based approach is generated for a true representation of ballscrew degradation, whereby the motor is modelled using ‘dq axis’ transformation theory to include a better representation of the motor dynamics. The ballscrew kinematics are to include the contact mechanics of the main sources of friction through the Stribeck model. The simulations demonstrated feature extraction of the dynamic behaviour in the system using Iq current signals. These included peak starting current features during acceleration and transient friction variation. The simulated data were processed to analyse peak Iq currents and classified to represent three health states (Healthy, Degrading and Faulty) using k-Nearest Neighbour (k-NN) algorithm. A classification accuracy of ~74% was achieved.

PHM Based Adaptive Power Management System for a More Electric Aircraft

This research work presents a novel approach that addresses the concept of an adaptive power management system design and development framed in the Prognostics and Health Monitoring(PHM) perspective of an Electrical power Generation and distribution system(EPGS).PHM algorithms were developed to detect the health status of EPGS components which can accurately predict the failures and also able to calculate the Remaining Useful Life(RUL), and in many cases reconfigure for the identified system and subsystem faults. By introducing these approach on Electrical power Management system controller, we are gaining a few minutes lead time to failures with an accurate prediction horizon on critical systems and subsystems components that may introduce catastrophic secondary damages including loss of aircraft. The warning time on critical components and related system reconfiguration must permits safe return to landing as the minimum criteria and would enhance safety. A distributed architecture has been developed for the dynamic power management for electrical distribution system by which all the electrically supplied loads can be effectively controlled. The different failure modes were generated by injecting faults into the electrical power system using a fault injection mechanism. The data captured during these studies have been recorded to form a “Failure Database” for electrical system. A hardware in loop experimental study was carried out to validate the power management algorithm with FPGA-DSP controller. In order to meet the reliability requirements a Tri-redundant electrical power management system based on DSP and FPGA has been developed.

Wearable EEG-based Activity Recognition in PHM-related Service Environment via Deep Learning

It is of paramount importance to track the cognitive activity or cognitve attenion of the service personnel in a Prognostics and Health Monitoring (PHM) service related training or operation environment. The electroencephalography (EEG) data is one of the good candidates for cognitive activity recognition of the user. Analyzing electroencephalography (EEG) data in an unconstrained (natural) environment for understanding cognitive state and classifying human activity is a challenging task due to multiple reasons such as low signal-to-noise ratio, transient nature, lack of baseline availability and uncontrolled mixing of various tasks. This paper proposes a framework based on an emerging tool named deep learning that monitors human activity by fusing multiple EEG sensors and also selects a smaller sensor suite for a lean data collection system. Real-time classification of human activity from spatially non collocated multi-probe EEG is executed by applying deep learning techniques without performing any significant amount of data preprocessing and manual feature engineering. Two types of deep neural networks, deep belief network (DBN) and deep convolutional neural network (DCNN) are used at the core of the proposed framework, which automatically learns necessary features from EEG for a given classification task. Validation on extensive amount of data, which was collected from several subjects while they were performing multiple tasks (listening and watching) in PHM service training session, is presented and significant parallels are drawn from existing domain knowledge on EEG data understanding. Comparison with machine learning benchmark techniques shows that deep learning based tools are better at understanding EEG data for task classification. It is observed via sensor selection that a significantly smaller EEG sensor suite can perform at a comparable accuracy as the original sensor suite.

A spare parts inventory control model based on Prognostics and Health monitoring data under a fill rate constraint

The performance of any inventory control model depends on the quality of future demand forecasting. The better the accuracy of future demand predictions is, the lower is the safety inventory level needed to fulfill demands and meet fill rate requirements. In most real-world applications, historical demand profiles are commonly used to predict future demands. In the specific case of spare parts inventory, one way to improve the accuracy of demand prediction is to use information obtained by monitoring the degradation level of components. This approach may be especially important when demand behavior can vary over time, for instance, due to a change in the operational conditions. Thus, this paper aims at presenting a novel spare parts inventory control model for non-repairable items with periodic review. In the proposed model, Remaining Useful Life (RUL) predictions of monitored components obtained from a Prognostics and Health Monitoring (PHM) system are used to predict future demands for spare parts. It allows the reorder point, s, and the order-up-to level, S, to be dynamically adjusted as new PHM data become available. It is assumed that PHM data are updated periodically, with period R. The proposed model minimizes the total inventory cost subject to a fill rate constraint. Numerical experiments are carried out to compare the performance of the proposed [R, s, S] model with the classical [s, S] model in terms of average total cost per period and average inventory level. The results show that the proposed model yields a reduction in both the average total cost per period and the average inventory level.

Dynamic repair priority rule based on remaining useful life predictions

In this paper, we propose a novel repair priority rule for spare parts in a repair station with limited repair capacity to minimize total inventory cost per time unit. Inventory cost is composed of holding costs and backorder costs. The proposed rule uses Remaining Useful Life (RUL) predictions of functioning machines obtained from a Prognostics and Health Monitoring (PHM) system. An inventory system comprising a finite number of machines, one warehouse, and one single-server repair station is considered. Numerical experiments were conducted to compare the performance of the proposed model with the performance of three existing priority rules: a first-come, first-served (FCFS) rule, a static priority rule, and a dynamic priority rule. A testbed with 20 instances of the problem was considered. The results showed that the proposed PHM-based rule consistently reduces the inventory system cost.

Deep digital twins for detection, diagnostics and prognostics

A generic framework for prognostics and health monitoring (PHM) which is rapidly deployable to heterogeneous fleets of assets would allow for the automation of predictive maintenance scheduling directly from operational data. Deep learning based PHM implementations provide part of the solution, but their main benefits are lost when predictions still rely on historical failure data and case-by-case feature engineering. We propose a solution to these challenges in the form of a Deep Digital Twin (DDT). The DDT is constructed from deep generative models which learn the distribution of healthy data directly from operational data at the beginning of an asset’s life-cycle. As the DDT learns the distribution of healthy data it does not rely on historical failure data in order to produce an estimation of asset health. This article presents an overview of the DDT framework and investigates its performance on a number of datasets. Based on these investigations, it is demonstrated that the DDT is able to detect incipient faults, track asset degradation and differentiate between failure modes in both stationary and non-stationary operating conditions when trained on only healthy operating data.

Systems Engineering, Data Analytics, and Systems Thinking: Moving Ahead to New and More Complex Challenges

ABSTRACTDuring the last decade, industries in advanced economies have experienced significant changes in their engineering and manufacturing practices, processes, and technologies that have the potential to create a resurgence in their engineering and manufacturing activities. This phenomenon referred to as the Fourth Industrial Revolution or Industry 4.0 ‐ a term used commonly in Europe about high digitization in manufacturing, loosely equivalent to advanced manufacturing used in the United States. The term's basis comes from advanced manufacturing and engineering technologies, such as massive digitization, big data analytics, advanced robotics and adaptive automation, additive and precision manufacturing (3D printing), modeling and simulation, artificial intelligence, and the nano‐engineering of materials. This revolution presents challenges and opportunities to the systems engineering discipline. For example, virtually all systems will have porous and ill‐defined boundaries and requirements. Under Industry 4.0, systems will have access to large types and numbers of external devices, and enormous quantities of data, which must undergo analysis through data analytics. It is, therefore, the right time for enhancing the development and application of data‐driven and evidence‐based systems engineering. One of the trends in data analytics is the shift from detection to prognosis and predictive monitoring in systems testing and maintenance using prognostics and health monitoring (PHM). Also, it is proposed to practice evidence‐based risk management as a more effective approach for managing the systems’ risks.

Towards prognostics and health monitoring: The potential of fault detection by piezoresistive silicon stress sensor

A piezoresistive silicon based stress sensor has been demonstrated successfully as an effective tool to monitor the stresses inside electronic packages during various production processes. More recently, the sensor has been evaluated as a sensor for Prognostics and Health Monitoring (PHM) systems. This paper presents a systematic approach that evaluates its performance from the perspective of failure mode detection. A detailed Finite Element method (FEM) model of existing test vehicles is created. The test vehicle consists of six DPAK (Discrete Package) power packages and three stress sensors. The results of simulation are verified by the signals obtained from the stress sensor as well as the supplementary warpage measurements. After inserting various failure modes into the model, statistical pattern recognition algorithms are implemented for fault detection and classification. The proposed technique can identify detectable failures during reliability testing by utilizing the database of stress sensor responses for healthy and unhealthy state. Thus, the results establish a baseline for the applicability of the piezoresistive stress sensor for an on-line monitoring PHM methodology.

Analysis of the Results of Accelerated Aging Tests in Insulated Gate Bipolar Transistors

The introduction of fully electric vehicles (FEVs) into the mainstream has raised concerns about the reliability of their electronic components such as IGBT. The great variability in IGBT failure times caused by the very different operating conditions experienced and the stochasticity of their degradation processes suggests the adoption of condition-based maintenance approaches. Thus, the development of methods for assessing their healthy state and predicting their remaining useful life (RUL) is of key importance. In this paper, we investigate the results of performing accelerated aging tests. Our objective is to discuss the design and the results of accelerated aging tests performed on three different IGBT types within the electrical powertrain health monitoring for increased safety (HEMIS) of FEVs European Community project. During the tests, several electric signals were measured in different operating conditions. The results show that the case temperature $(T_{C})$ , the collector current $(I_{C})$ , and the collector–emitter voltage $(V_{{\rm CE}})$ are the failure precursor parameters that can be used for the development of a prognostic and health monitoring (PHM) system for FEV IGBTs and other medium-power switching supplies.

Deep Learning for Structural Health Monitoring: A Damage Characterization Application

Structural health monitoring (SHM) is usually focused on damage detection (e.g., Yes/No) or approximate estimation of damage size. Any additional details of the damage such as configuration, shape, networking, geometrical statistics, etc., are often either ignored or significantly simplified during SHM characterization. These details, however, can be extremely important for understanding of damage severity and estimations of follow-up damage growth risk. To avoid expensive human participation and/or over-conservative SHM decisions, solutions of computational recognition for damage characterization are needed. Autonomous SHM from visual data is one of the significant challenges in the field of structural prognostics and health monitoring (PHM). The main shortcomings of the image-based PHM algorithms arise from the lack of robustness and fidelity to handle the variability of environment and nature of damage types. In recent times, deep learning has drawn huge amount of traction in the field of machine learning and visual pattern recognition due to its superior performance compared to the state-of-the-art techniques. This paper proposes to formulate and apply a deep learning technique to characterize the damage in the form of cracks on a composite material. The deep learning architecture is constructed by multi-layer neural network that is based on the fundamentals of unsupervised representational learning theory. The robustness and the accuracy of the approach is validated on an extensive set of real image data collected via applying variable load conditions on the structure. The paper has shown a high characterization accuracy over a wide range of loading conditions with limited number of labeled training image data.

Prognostic Reasoner based Adaptive Power Management System for a More Electric Aircraft

This research work presents a novel approach that addresses the concept of an adaptive power management system design and development framed in the Prognostics and Health Monitoring(PHM) perspective of an Electrical power Generation and distribution system(EPGS).PHM algorithms were developed to detect the health status of EPGS components which can accurately predict the failures and also able to calculate the Remaining Useful Life(RUL), and in many cases reconfigure for the identified system and subsystem faults. By introducing these approach on Electrical power Management system controller, we are gaining a few minutes lead time to failures with an accurate prediction horizon on critical systems and subsystems components that may introduce catastrophic secondary damages including loss of aircraft. The warning time on critical components and related system reconfiguration must permits safe return to landing as the minimum criteria and would enhance safety. A distributed architecture has been developed for the dynamic power management for electrical distribution system by which all the electrically supplied loads can be effectively controlled.A hybrid mathematical model based on the Direct-Quadrature (d-q) axis transformation of the generator have been formulated for studying various structural and parametric faults. The different failure modes were generated by injecting faults into the electrical power system using a fault injection mechanism. The data captured during these studies have been recorded to form a “Failure Database” for electrical system. A hardware in loop experimental study were carried out to validate the power management algorithm with FPGA-DSP controller. In order to meet the reliability requirements a Tri-redundant electrical power management system based on DSP and FPGA has been developed.