Scott Poll

Prognostics Methods for Battery Health Monitoring Using a Bayesian Framework

This paper explores how the remaining useful life (RUL) can be assessed for complex systems whose internal state variables are either inaccessible to sensors or hard to measure under operational conditions. Consequently, inference and estimation techniques need to be applied on indirect measurements, anticipated operational conditions, and historical data for which a Bayesian statistical approach is suitable. Models of electrochemical processes in the form of equivalent electric circuit parameters were combined with statistical models of state transitions, aging processes, and measurement fidelity in a formal framework. Relevance vector machines (RVMs) and several different particle filters (PFs) are examined for remaining life prediction and for providing uncertainty bounds. Results are shown on battery data.

An integrated approach to battery health monitoring using bayesian regression and state estimation

The application of the Bayesian theory of managing uncertainty and complexity to regression and classification in the form of relevance vector machine (RVM), and to state estimation via particle filters (PF), proves to be a powerful tool to integrate the diagnosis and prognosis of battery health. Accurate estimates of the state-of-charge (SOC), the state-of-health (SOH) and state-of-life (SOL) for batteries provide a significant value addition to the management of any operation involving electrical systems. This is especially true for aerospace systems, where unanticipated battery performance may lead to catastrophic failures. Batteries, composed of multiple electrochemical cells, are complex systems whose internal state variables are either inaccessible to sensors or hard to measure under operational conditions. In addition, battery performance is strongly influenced by ambient environmental and load conditions. Consequently, inference and estimation techniques need to be applied on indirect measurements, anticipated operational conditions and historical data, for which a Bayesian statistical approach is suitable. Accurate models of electro-chemical processes in the form of equivalent electric circuit parameters need to be combined with statistical models of state transitions, aging processes and measurement fidelity, need to be combined in a formal framework to make the approach viable. The RVM, which is a Bayesian treatment of the support vector machine (SVM), is used for diagnosis as well as for model development. The PF framework uses this model and statistical estimates of the noise in the system and anticipated operational conditions to provide estimates of SOC, SOH and SOL. Validation of this approach on experimental data from Li-ion batteries is presented.

Probabilistic Model-Based Diagnosis: An Electrical Power System Case Study

We present in this paper a case study of the probabilistic approach to model-based diagnosis. Here, the diagnosed system is a real-world electrical power system (EPS), i.e., the Advanced Diagnostic and Prognostic Testbed (ADAPT) located at the NASA Ames Research Center. Our probabilistic approach is formally well founded and based on Bayesian networks (BNs) and arithmetic circuits (ACs). We pay special attention to meeting two of the main challenges often associated with real-world application of model-based diagnosis technologies: model development and real-time reasoning. To address the challenge of model development, we develop a systematic approach to representing EPSs as BNs, supported by an easy-to-use specification language. To address the real-time reasoning challenge, we compile BNs into ACs. AC evaluation (ACE) supports real-time diagnosis by being predictable, fast, and exact. In experiments with the ADAPT BN, which contains 503 discrete nodes and 579 edges and produces accurate results, the time taken to compute the most probable explanation using ACs has a mean of 0.2625 ms and a standard deviation of 0.2028 ms. In comparative experiments, we found that, while the variable elimination and join tree propagation algorithms also perform very well in the ADAPT setting, ACE was an order of magnitude or more faster.

A Comprehensive Diagnosis Methodology for Complex Hybrid Systems: A Case Study on Spacecraft Power Distribution Systems

The application of model-based diagnosis schemes to real systems introduces many significant challenges, such as building accurate system models for heterogeneous systems with complex behaviors, dealing with noisy measurements and disturbances, and producing valuable results in a timely manner with limited information and computational resources. The Advanced Diagnostics and Prognostics Testbed (ADAPT), which was deployed at the NASA Ames Research Center, is a representative spacecraft electrical power distribution system that embodies a number of these challenges. ADAPT contains a large number of interconnected components, and a set of circuit breakers and relays that enable a number of distinct power distribution configurations. The system includes electrical dc and ac loads, mechanical subsystems (such as motors), and fluid systems (such as pumps). The system components are susceptible to different types of faults, i.e., unexpected changes in parameter values, discrete faults in switching elements, and sensor faults. This paper presents Hybrid Transcend, which is a comprehensive model-based diagnosis scheme to address these challenges. The scheme uses the hybrid bond graph modeling language to systematically develop computational models and algorithms for hybrid state estimation, robust fault detection, and efficient fault isolation. The computational methods are implemented as a suite of software tools that enable diagnostic analysis and testing through simulation, diagnosability studies, and deployment on the experimental testbed. Simulation and experimental results demonstrate the effectiveness of the methodology.

Estimation of faults in DC electrical power system

This paper demonstrates a novel optimization-based approach to estimating fault states in a DC power system. The model includes faults changing the circuit topology along with sensor faults. Our approach can be considered as a relaxation of the mixed estimation problem. We develop a linear model of the circuit and pose a convex problem for estimating the faults and other hidden states. A sparse fault vector solution is computed by using l1 regularization. The solution is computed reliably and efficiently, and gives accurate diagnostics on the faults. We demonstrate a real-time implementation of the approach for an instrumented electrical power system testbed at NASA. Accurate estimates of multiple faults are computed in milliseconds on a PC. The approach performs well despite unmodeled transients and other modeling uncertainties present in the system.

In-flight fault detection and isolation in aircraft flight control systems

In this paper we consider the problem of test design for real-time fault detection and isolation (FDI) in the flight control system of fixed-wing aircraft. We focus on the faults that are manifested in the control surface elements (e.g., aileron, elevator, rudder and stabilizer) of an aircraft. For demonstration purposes, we restrict our focus on the faults belonging to nine basic fault classes. The diagnostic tests are performed on the features extracted from fifty monitored system parameters. The proposed tests are able to uniquely isolate each of the faults at almost all severity levels. A neural network-based flight control simulator, FLTZreg, is used for the simulation of various faults in fixed-wing aircraft flight control systems for the purpose of FDI

Evaluation, Selection, and Application of Model-Based Diagnosis Tools and Approaches

Model-based approaches have proven fruitful in the design and implementation of intelligent systems that provide automated diagnostic functions. A wide variety of models are used in these approaches to represent the particular domain knowledge, including analytic state-based models, input-output transfer function models, fault propagation models, and qualitative and quantitative physics-based models. Diagnostic applications are built around three main steps: observation, comparison, and diagnosis. If the modeling begins in the early stages of system development, engineering models such as fault propagation models can be used for testability analysis to aid definition and evaluation of instrumentation suites for observation of system behavior. Analytical models can be used in the design of monitoring algorithms that process observations to provide information for the second step in the process, comparison of expected behavior of the system to actual measured behavior. In the final diagnostic step, reasoning about the results of the comparison can be performed in a variety of ways, such as dependency matrices, graph propagation, constraint propagation, and state estimation. Realistic empirical evaluation and comparison of these approaches is often hampered by a lack of standard data sets and suitable testbeds. In this paper we describe the Advanced Diagnostics and Prognostics Testbed (ADAPT) at NASA Ames Research Center. The purpose of the testbed is to measure, evaluate, and mature diagnostic and prognostic health management technologies. This paper describes the testbed’s hardware, software architecture, and concept of operations. A simulation testbed that

A framework for systematic benchmarking of monitoring and diagnostic systems

In this paper, we present an architecture and a formal framework to be used for systematic benchmarking of monitoring and diagnostic systems and for producing comparable performance assessments of different diagnostic technologies. The framework defines a number of standardized specifications, which include a fault catalog, a library of modular test scenarios, and a common protocol for gathering and processing diagnostic data. At the center of the framework are 13 benchmarking metric definitions. The calculation of metrics is illustrated on a probabilistic model-based diagnosis algorithm utilizing Bayesian reasoning techniques. The diagnosed system is a real-world electrical power system, namely the Advanced Diagnostics and Prognostics Testbed (ADAPT) developed and located at the NASA Ames Research Center. The proposed benchmarking approach shows how to generate realistic diagnostic data sets for large-scale, complex engineering systems, and how the generated experimental data can be used to enable ldquoapples to applesrdquo assessments of the effectiveness of different diagnostic and monitoring algorithms.

Pilot Study of a Plug Load Management System: Preparing for Sustainability Base

NASA Ames Research Centers Sustainability Base is a new 50,000 sq. ft. high-performance office building targeting a LEED Platinum rating. Plug loads are expected to account for a significant portion of overall energy consumption because building design choices resulted in greatly reduced energy demand from Heating, Ventilation, and Air Conditioning (HVAC) and lighting systems, which are typically major contributors to energy consumption in traditional buildings. This paper reports on a pilot study where data from a variety of plug loads were collected in a reference office building to understand usage patterns, to make a preliminary assessment as to the effectiveness of controlling (i.e., turning off and on) selected loads, and to evaluate the utility of the plug load management system chosen for the study. Findings indicate that choosing energy efficient equipment, ensuring that power saving functionality is operating effectively, promoting beneficial occupant energy behavior, and employing plug load controls to turn off equipment when not in use can lead to significant energy savings. These recommendations will be applied to Sustainability Base and further studies of plug load management systems and techniques to reduce plug energy consumption will be pursued.

Predicting Real-Time Safety of the National Airspace System

Situation awareness is necessary for operators to make informed decisions regarding avoidance of airspace hazards. To this end, each operator must consolidate operationsrelevant information from disparate sources and apply extensive domain knowledge to correctly interpret the current state of the NAS as well as forecast its (combined) evolution over the duration of the NAS operation. This timeand workload-intensive process is periodically repeated throughout the operation so that changes can be managed in a timely manner. The imprecision, inaccuracy, inconsistency, and incompleteness of the incoming data further challenges the process. To facilitate informed decision making, this paper presents a model-based framework for the automated real-time monitoring and prediction of possible effects of airspace hazards on the safety of the National Airspace System (NAS). First, hazards to flight are identified and transformed into safety metrics, that is, quantities of interest that could be evaluated based on available data and are predictive of an unsafe event. The safety metrics and associated thresholds that specify when an event transitions from safe to unsafe are combined with models of airspace operations and aircraft dynamics. The framework can include any hazard to flight that can be modeled quantitatively. Models can be detailed and complex, or they can be considerably simplifed, as appropriate to the application. Real-time NAS safety monitoring and prediction begins with an estimate of the state of the NAS using the dynamic models. Given the state estimate and a probability distribution of future inputs to the NAS, we can then predict the evolution of the NAS the future state and the occurrence of hazards and unsafe events. The entire probability distribution of airspace safety metrics is computed, not just point estimates, without significant assumptions regarding the distribution type and/or parameters. We demonstrate our overall approach through a simulated scenario in which we predict the occurrence of some unsafe events and show how these predictions evolve in time as flight operations progress. Predictions accounting for common sources of uncertainty are included and it is shown how the predictions improve in time, become more confident, and change dynamically as new information is made available to the prediction algorithm.