Indranil Roychoudhury

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.

Efficient simulation of hybrid systems: A hybrid bond graph approach

Accurate and efficient simulations facilitate cost-effective design and analysis of large, complex, embedded systems, whose behaviors are typically hybrid, i.e. continuous behaviors interspersed with discrete mode changes. In this paper we present an approach for deriving component-based computational models of hybrid systems using hybrid bond graphs (HBGs), a multi-domain, energy-based modeling language that provides a compact framework for modeling hybrid physical systems. Our approach exploits the causality information inherent in HBGs to derive component-based computational models of hybrid systems as reconfigurable block diagrams. Typically, only small parts of the computational structure of a hybrid system change when mode changes occur. Our key idea is to identify the bonds and elements of HBGs whose causal assignments are invariant across system modes, and use this information to derive space-efficient reconfigurable block diagram models that may be reconfigured efficiently when mode changes occur. This reconfiguration is based on the incremental reassignment of causality implemented as the Hybrid Sequential Causal Assignment Procedure, which reassigns causality for the new mode based on the causal assignment of the previous mode. The reconfigurable block diagrams are general, and they can be transformed into simulation models for generating system behavior. Our modeling and simulation methodology, implemented as the Modeling and Transformation of HBGs for Simulation (MoTHS) tool suite, includes a component-based HBG modeling paradigm and a set of model translators for translating the HBG models into executable models. In this work, we use MoTHS to build a high-fidelity MATLAB Simulink model of an electrical power distribution system.

An event-based distributed diagnosis framework using structural model decomposition

Complex engineering systems require efficient on-line fault diagnosis methodologies to improve safety and reduce maintenance costs. Traditionally, diagnosis approaches are centralized, but these solutions do not scale well. Also, centralized diagnosis solutions are difficult to implement on increasingly prevalent distributed, networked embedded systems. This paper presents a distributed diagnosis framework for physical systems with continuous behavior. Using Possible Conflicts, a structural model decomposition method from the Artificial Intelligence model-based diagnosis (DX) community, we develop a distributed diagnoser design algorithm to build local event-based diagnosers. These diagnosers are constructed based on global diagnosability analysis of the system, enabling them to generate local diagnosis results that are globally correct without the use of a centralized coordinator. We also use Possible Conflicts to design local parameter estimators that are integrated with the local diagnosers to form a comprehensive distributed diagnosis framework. Hence, this is a fully distributed approach to fault detection, isolation, and identification. We evaluate the developed scheme on a four-wheeled rover for different design scenarios to show the advantages of using Possible Conflicts, and generate on-line diagnosis results in simulation to demonstrate the approach.

Distributed Prognostics Based on Structural Model Decomposition

Within systems health management, prognostics focuses on predicting the remaining useful life of a system. In the model-based prognostics paradigm, physics-based models are constructed that describe the operation of a system, and how it fails. Such approaches consist of an estimation phase, in which the health state of the system is first identified, and a prediction phase, in which the health state is projected forward in time to determine the end of life. Centralized solutions to these problems are often computationally expensive, do not scale well as the size of the system grows, and introduce a single point of failure. In this paper, we propose a novel distributed model-based prognostics scheme that formally describes how to decompose both the estimation and prediction problems into computationally-independent local subproblems whose solutions may be easily composed into a global solution. The decomposition of the prognostics problem is achieved through structural decomposition of the underlying models. The decomposition algorithm creates from the global system model a set of local submodels suitable for prognostics. Computationally independent local estimation and prediction problems are formed based on these local submodels, resulting in a scalable distributed prognostics approach that allows the local subproblems to be solved in parallel, thus offering increases in computational efficiency. Using a centrifugal pump as a case study, we perform a number of simulation-based experiments to demonstrate the distributed approach, compare the performance with a centralized approach, and establish its scalability.

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 structural model decomposition framework for systems health management

Systems health management (SHM) is an important set of technologies aimed at increasing system safety and reliability by detecting, isolating, and identifying faults; and predicting when the system reaches end of life (EOL), so that appropriate fault mitigation and recovery actions can be taken. Model-based SHM approaches typically make use of global, monolithic system models for online analysis, which results in a loss of scalability and efficiency for large-scale systems. Improvement in scalability and efficiency can be achieved by decomposing the system model into smaller local submodels and operating on these submodels instead. In this paper, the global system model is analyzed offline and structurally decomposed into local submodels. We define a common model decomposition framework for extracting submodels from the global model. This framework is then used to develop algorithms for solving model decomposition problems for the design of three separate SHM technologies, namely, estimation (which is useful for fault detection and identification), fault isolation, and EOL prediction. We solve these model decomposition problems using a three-tank system as a case study.

Developing IVHM Requirements for Aerospace Systems

The term Integrated Vehicle Health Management (IVHM) describes a set of capabilities that enable sustainable and safe operation of components and subsystems within aerospace platforms. However, very little guidance exists for the systems engineering aspects of design with IVHM in mind. It is probably because of this that designers have to use knowledge picked up exclusively by experience rather than by established process. This motivated a group of leading IVHM practitioners within the aerospace industry under the aegis of SAE’s HM-1 technical committee to author a document that hopes to give working engineers and program managers clear guidance on all the elements of IVHM that they need to consider before designing a system. This proposed recommended practice (ARP6883 [1]) will describe all the steps of requirements generation and management as it applies to IVHM systems, and demonstrate these with a “real-world” example related to designing a landing gear system. The team hopes that this paper and presentation will help start a dialog with the larger aerospace community and that the feedback can be used to improve the ARP and subsequently the practice of IVHM from a systems engineering point-of-view.

Requirements Flowdown for Prognostics and Health Management

Prognostics and Health Management (PHM) principles have considerable promise to change the game of lifecycle cost of engineering systems at high safety levels by providing a reliable estimate of future system states. This estimate is a key for planning and decision making in an operational setting. While technology solutions have made considerable advances, the tie-in into the systems engineering process is lagging behind, which delays fielding of PHM-enabled systems. The derivation of specifications from high level requirements for algorithm performance to ensure quality predictions is not well developed. From an engineering perspective some key parameters driving the requirements for prognostics performance include: (1) maximum allowable Probability of Failure (PoF) of the prognostic system to bound the risk of losing an asset, (2) tolerable limits on proactive maintenance to minimize missed opportunity of asset usage, (3) lead time to specify the amount of advanced warning needed for actionable decisions, and (4) required confidence to specify when prognosis is sufficiently good to be used. This paper takes a systems engineering view towards the requirements specification process and presents a method for the flowdown process. A case study based on an electric Unmanned Aerial Vehicle (e-UAV) scenario demonstrates how top level requirements for performance, cost, and safety flow down to the health management level and specify quantitative requirements for prognostic algorithm performance.

Experimental Validation of a Prognostic Health Management System for Electro-Mechanical Actuators

Electro-Mechanical Actuators (EMA) are gaining prominent roles in the next generation fly-by-wire aircraft and spacecraft. With these roles often being safety-critical (control surface or landing gear actuation, for instance), the key to faster adoption of EMA in aerospace applications is development of accurate and reliable prognostic health management (PHM) systems that not only detect and identify faults, but also predict how the identified they affect the remaining useful life (RUL) of both the faulty component and the actuator as a whole. Such information can be invaluable to pilots, controllers, and maintenance personnel in assessing how to complete or re-plan the desired mission with a sufficient safety margin. A team consisting of members of NASA Ames Diagnostic & Prognostic Group has developed a prototype PHM system for EMA that provides coverage for a number of faults modes typical to this type of actuators. The diagnostic portion of the system is implemented using a hybrid approach which utilizes both qualitative (bond graph, model-based) and quantitative (data-driven) reasoners to achieve low false positive and false negative detection rates and a high accuracy of diagnostic output. Once a fault has been diagnosed, the prognostic component, which is implemented using Gaussian Process Regression (GPR) principles, estimates the RUL of the component that is faulted. Experiments were conducted both in laboratory and flight conditions to validate the PHM system using an innovative Flyable Electromechanical Actuator (FLEA) test stand. The test stand allows experimental actuators to be subjected to environmental and operating conditions similar to what actuators on the host aircraft are experiencing, while providing researchers with the capability to safely inject and monitor propagation of various fault modes. Prognostic run-to-failure experiments were done in laboratory conditions on ballscrew jam and motor winding short faults. Flight experiments (albeit not run-to-failure) were conducted in collaboration with the US Army on UH-60 Blackhawk helicopters. The paper describes these experiments in detail and presents the results obtained from the PHM system with regard to the estimation of the RUL of the actuator.

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.