Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “fault classification”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 37 records · Page 2
All sourcesNASA NTRSDOE OSTI
NASA NTRS1990

Experimental fault characterization of a neural network

The effects of a variety of faults on a neural network is quantified via simulation. The neural network consists of a single-layered clustering network and a three-layered classification network. The percentage of vectors mistagged by the clustering network, the percentage of vectors misclassified by the classification network, the time taken for the network to stabilize, and the output values are all measured. The results show that both transient and permanent faults have a significant impact on the performance of the measured network. The corresponding mistag and misclassification percentages are typically within 5 to 10 percent of each other. The average mistag percentage and the average misclassification percentage are both about 25 percent. After relearning, the percentage of misclassifications is reduced to 9 percent. In addition, transient faults are found to cause the network to be increasingly unstable as the duration of a transient is increased. The impact of link faults is relatively insignificant in comparison with node faults (1 versus 19 percent misclassified after relearning). There is a linear increase in the mistag and misclassification percentages with decreasing hardware redundancy. In addition, the mistag and misclassification percentages linearly decrease with increasing network size.

Tan, Chang-Huong↗
NASA NTRS2005

Inductive Learning Approaches for Improving Pilot Awareness of Aircraft Faults

Neural network flight controllers are able to accommodate a variety of aircraft control surface faults without detectable degradation of aircraft handling qualities. Under some faults, however, the effective flight envelope is reduced; this can lead to unexpected behavior if a pilot performs an action that exceeds the remaining control authority of the damaged aircraft. The goal of our work is to increase the pilot s situational awareness by informing him of the type of damage and resulting reduction in flight envelope. Our methodology integrates two inductive learning systems with novel visualization techniques. One learning system, the Inductive Monitoring System (IMS), learns to detect when a simulation includes faulty controls, while two others, Inductive Classification System (INCLASS) and multiple binary decision tree system (utilizing C4.5), determine the type of fault. In off-line training using only non-failure data, IMS constructs a characterization of nominal flight control performance based on control signals issued by the neural net flight controller. This characterization can be used to determine the degree of control augmentation required in the pitch, roll, and yaw command channels to counteract control surface failures. This derived information is typically sufficient to distinguish between the various control surface failures and is used to train both INCLASS and C4.5. Using data from failed control surface flight simulations, INCLASS and C4.5 independently discover and amplify features in IMS results that can be used to differentiate each distinct control surface failure situation. In real-time flight simulations, distinguishing features learned during training are used to classify control surface failures. Knowledge about the type of failure can be used by an additional automated system to alter its approach for planning tactical and strategic maneuvers. The knowledge can also be used directly to increase the pilot s situational awareness and inform manual maneuver decisions. Our multi-modal display of this information provides speech output to issue control surface failure warnings to a lesser-used communication channel and provides graphical displays with pilot-selectable !eve!s of details to issues additional information about the failure. We also describe a potential presentation for flight envelope reduction that can be viewed separately or integrated with an existing attitude indicator instrument. Preliminary results suggest that the inductive approach is capable of detecting that a control surface has failed and determining the type of fault. Furthermore, preliminary evaluations suggest that the interface discloses a concise summary of this information to the pilot.

Spikovska, Lilly↗
NASA NTRS2019

NASA Lunar Lander Reference Design

With increased emphasis on lunar exploration and scientific investigation, there is a desire to deliver a wide variety of payloads to the lunar surface. Many of these payloads will require the use of surface mobility capability such as a rover. NASA has combined spacecraft and subsystem engineers from across the Agency to develop a ‘pallet’ lander design intended to deliver and easily deploy a medium-sized payload (~300 kg) to the polar regions of the Moon. The lander provides power to the payload from transit soon after lunar landing. The lander is not intended to survive the lunar night. The design of the lander was based on a minimum set of level 1 requirements where traditional risk, mass, and performance trade parameters were weighed lower than cost. In other words, the team did not sacrifice ‘good enough’ for ‘better’ or ‘best.’ As a NASA class D spacecraft (as defined in NPR 8705.4, Risk Classification for NASA Payloads, the lander employs single-string (i.e., zero-fault-tolerant) systems as a baseline. The design utilizes existing technologies and components where possible, though some enhancements have been targeted in areas such as precision autonomous landing and low-cost structural design/fabrication. It is important to note that these and other derived technologies are extensible to other lander designs and missions. This TP describes the requirements and approaches upon which the lander design is based; discusses key design decisions, analyses, and trades used to derive the design; provides a snapshot of each major subsystem; and identifies open items, issues, and challenges for which work is continuing.

L D Kennedy↗
NASA NTRS1984

Error detection process - Model, design, and its impact on computer performance

An analytical model is developed for computer error detection processes and applied to estimate their influence on system performance. Faults in the hardware, not in the design, are assumed to be the potential cause of transition to erroneous states during normal operations. The classification properties and associated recovery methods of error detection are discussed. The probability of obtaining an unreliable result is evaluated, along with the resulting computational loss. Error detection during design is considered and a feasible design space is outlined. Extension of the methods to account for the effects of extant multiple faults is indicated.

Shin, K. G.↗
NASA NTRS1973

Natural resources inventory and monitoring in Oregon with ERTS imagery

Multidiscipline team interpretation of ERTS satellite and highflight imagery is providing resource and land use information needed for land use planning in Oregon. A coordinated inventory of geology, soil-landscapes, forest and range vegetation, and land use for Crook County, illustrates the value of this approach for broad area and state planning. Other applications include mapping fault zones, inventory of forest clearcut areas, location of forest insect damage, and monitoring irrigation development. Computer classification is being developed for use in conjunction with visual interpretation.

Simonson, G. H.↗
NASA NTRS1993

Developing interpretable models with optimized set reduction for identifying high risk software components

Applying equal testing and verification effort to all parts of a software system is not very efficient, especially when resources are limited and scheduling is tight. Therefore, one needs to be able to differentiate low/high fault frequency components so that testing/verification effort can be concentrated where needed. Such a strategy is expected to detect more faults and thus improve the resulting reliability of the overall system. This paper presents the Optimized Set Reduction approach for constructing such models, intended to fulfill specific software engineering needs. Our approach to classification is to measure the software system and build multivariate stochastic models for predicting high risk system components. We present experimental results obtained by classifying Ada components into two classes: is or is not likely to generate faults during system and acceptance test. Also, we evaluate the accuracy of the model and the insights it provides into the error making process.

Briand, Lionel C.↗
NASA NTRS1983

Software fault tolerance for real-time avionics systems

Avionics systems have very high reliability requirements and are therefore prime candidates for the inclusion of fault tolerance techniques. In order to provide tolerance to software faults, some form of state restoration is usually advocated as a means of recovery. State restoration can be very expensive for systems which utilize concurrent processes. The concurrency present in most avionics systems and the further difficulties introduced by timing constraints imply that providing tolerance for software faults may be inordinately expensive or complex. A straightforward pragmatic approach to software fault tolerance which is believed to be applicable to many real-time avionics systems is proposed. A classification system for software errors is presented together with approaches to recovery and continued service for each error type.

Anderson, T.↗
NASA NTRS2009

Software Health Management: A Short Review of Challenges and Existing Techniques

Modern spacecraft (as well as most other complex mechanisms like aircraft, automobiles, and chemical plants) rely more and more on software, to a point where software failures have caused severe accidents and loss of missions. Software failures during a manned mission can cause loss of life, so there are severe requirements to make the software as safe and reliable as possible. Typically, verification and validation (V&V) has the task of making sure that all software errors are found before the software is deployed and that it always conforms to the requirements. Experience, however, shows that this gold standard of error-free software cannot be reached in practice. Even if the software alone is free of glitches, its interoperation with the hardware (e.g., with sensors or actuators) can cause problems. Unexpected operational conditions or changes in the environment may ultimately cause a software system to fail. Is there a way to surmount this problem? In most modern aircraft and many automobiles, hardware such as central electrical, mechanical, and hydraulic components are monitored by IVHM (Integrated Vehicle Health Management) systems. These systems can recognize, isolate, and identify faults and failures, both those that already occurred as well as imminent ones. With the help of diagnostics and prognostics, appropriate mitigation strategies can be selected (replacement or repair, switch to redundant systems, etc.). In this short paper, we discuss some challenges and promising techniques for software health management (SWHM). In particular, we identify unique challenges for preventing software failure in systems which involve both software and hardware components. We then present our classifications of techniques related to SWHM. These classifications are performed based on dimensions of interest to both developers and users of the techniques, and hopefully provide a map for dealing with software faults and failures.

Pipatsrisawat, Knot↗
NASA NTRS1991

Pattern-recognition techniques applied to performance monitoring of the DSS 13 34-meter antenna control assembly

The results of applying pattern recognition techniques to diagnose fault conditions in the pointing system of one of the Deep Space network's large antennas, the DSS 13 34-meter structure, are discussed. A previous article described an experiment whereby a neural network technique was used to identify fault classes by using data obtained from a simulation model of the Deep Space Network (DSN) 70-meter antenna system. Described here is the extension of these classification techniques to the analysis of real data from the field. The general architecture and philosophy of an autonomous monitoring paradigm is described and classification results are discussed and analyzed in this context. Key features of this approach include a probabilistic time-varying context model, the effective integration of signal processing and system identification techniques with pattern recognition algorithms, and the ability to calibrate the system given limited amounts of training data. Reported here are recognition accuracies in the 97 to 98 percent range for the particular fault classes included in the experiments.

Mellstrom, J. A.↗
NASA NTRS1989

Identification and interpretation of patterns in rocket engine data: Artificial intelligence and neural network approaches

This paper describes an expert system which is designed to perform automatic data analysis, identify anomalous events, and determine the characteristic features of these events. We have employed both artificial intelligence and neural net approaches in the design of this expert system. The artificial intelligence approach is useful because it provides (1) the use of human experts' knowledge of sensor behavior and faulty engine conditions in interpreting data; (2) the use of engine design knowledge and physical sensor locations in establishing relationships among the events of multiple sensors; (3) the use of stored analysis of past data of faulty engine conditions; and (4) the use of knowledge-based reasoning in distinguishing sensor failure from actual faults. The neural network approach appears promising because neural nets (1) can be trained on extremely noisy data and produce classifications which are more robust under noisy conditions than other classification techniques; (2) avoid the necessity of noise removal by digital filtering and therefore avoid the need to make assumptions about frequency bands or other signal characteristics of anomalous behavior; (3) can, in effect, generate their own feature detectors based on the characteristics of the sensor data used in training; and (4) are inherently parallel and therefore are potentially implementable in special-purpose parallel hardware.

Ali, Moonis↗
NASA NTRS1992

Providing an empirical basis for optimizing the verification and testing phases of software development

Applying equal testing and verification effort to all parts of a software system is not very efficient, especially when resources are limited and scheduling is tight. Therefore, one needs to be able to differentiate low/high fault density components so that the testing/verification effort can be concentrated where needed. Such a strategy is expected to detect more faults and thus improve the resulting reliability of the overall system. This paper presents an alternative approach for constructing such models that is intended to fulfill specific software engineering needs (i.e. dealing with partial/incomplete information and creating models that are easy to interpret). Our approach to classification is as follows: (1) to measure the software system to be considered; and (2) to build multivariate stochastic models for prediction. We present experimental results obtained by classifying FORTRAN components developed at the NASA/GSFC into two fault density classes: low and high. Also we evaluate the accuracy of the model and the insights it provides into the software process.

Briand, Lionel C.↗
NASA NTRS2006

Fault Management Techniques in Human Spaceflight Operations

This paper discusses human spaceflight fault management operations. Fault detection and response capabilities available in current US human spaceflight programs Space Shuttle and International Space Station are described while emphasizing system design impacts on operational techniques and constraints. Preflight and inflight processes along with products used to anticipate, mitigate and respond to failures are introduced. Examples of operational products used to support failure responses are presented. Possible improvements in the state of the art, as well as prioritization and success criteria for their implementation are proposed. This paper describes how the architecture of a command and control system impacts operations in areas such as the required fault response times, automated vs. manual fault responses, use of workarounds, etc. The architecture includes the use of redundancy at the system and software function level, software capabilities, use of intelligent or autonomous systems, number and severity of software defects, etc. This in turn drives which Caution and Warning (C&W) events should be annunciated, C&W event classification, operator display designs, crew training, flight control team training, and procedure development. Other factors impacting operations are the complexity of a system, skills needed to understand and operate a system, and the use of commonality vs. optimized solutions for software and responses. Fault detection, annunciation, safing responses, and recovery capabilities are explored using real examples to uncover underlying philosophies and constraints. These factors directly impact operations in that the crew and flight control team need to understand what happened, why it happened, what the system is doing, and what, if any, corrective actions they need to perform. If a fault results in multiple C&W events, or if several faults occur simultaneously, the root cause(s) of the fault(s), as well as their vehicle-wide impacts, must be determined in order to maintain situational awareness. This allows both automated and manual recovery operations to focus on the real cause of the fault(s). An appropriate balance must be struck between correcting the root cause failure and addressing the impacts of that fault on other vehicle components. Lastly, this paper presents a strategy for using lessons learned to improve the software, displays, and procedures in addition to determining what is a candidate for automation. Enabling technologies and techniques are identified to promote system evolution from one that requires manual fault responses to one that uses automation and autonomy where they are most effective. These considerations include the value in correcting software defects in a timely manner, automation of repetitive tasks, making time critical responses autonomous, etc. The paper recommends the appropriate use of intelligent systems to determine the root causes of faults and correctly identify separate unrelated faults.

O'Hagan, Brian↗
NASA NTRS1993

Experimental analysis of computer system dependability

This paper reviews an area which has evolved over the past 15 years: experimental analysis of computer system dependability. Methodologies and advances are discussed for three basic approaches used in the area: simulated fault injection, physical fault injection, and measurement-based analysis. The three approaches are suited, respectively, to dependability evaluation in the three phases of a system's life: design phase, prototype phase, and operational phase. Before the discussion of these phases, several statistical techniques used in the area are introduced. For each phase, a classification of research methods or study topics is outlined, followed by discussion of these methods or topics as well as representative studies. The statistical techniques introduced include the estimation of parameters and confidence intervals, probability distribution characterization, and several multivariate analysis methods. Importance sampling, a statistical technique used to accelerate Monte Carlo simulation, is also introduced. The discussion of simulated fault injection covers electrical-level, logic-level, and function-level fault injection methods as well as representative simulation environments such as FOCUS and DEPEND. The discussion of physical fault injection covers hardware, software, and radiation fault injection methods as well as several software and hybrid tools including FIAT, FERARI, HYBRID, and FINE. The discussion of measurement-based analysis covers measurement and data processing techniques, basic error characterization, dependency analysis, Markov reward modeling, software-dependability, and fault diagnosis. The discussion involves several important issues studies in the area, including fault models, fast simulation techniques, workload/failure dependency, correlated failures, and software fault tolerance.

Iyer, Ravishankar, K.↗
NASA NTRS1990

Initial results on fault diagnosis of DSN antenna control assemblies using pattern recognition techniques

Initial results obtained from an investigation using pattern recognition techniques for identifying fault modes in the Deep Space Network (DSN) 70 m antenna control loops are described. The overall background to the problem is described, the motivation and potential benefits of this approach are outlined. In particular, an experiment is described in which fault modes were introduced into a state-space simulation of the antenna control loops. By training a multilayer feed-forward neural network on the simulated sensor output, classification rates of over 95 percent were achieved with a false alarm rate of zero on unseen tests data. It concludes that although the neural classifier has certain practical limitations at present, it also has considerable potential for problems of this nature.

Smyth, P.↗
NASA NTRS1984

Systematic data interpretation of remote sensing in the reception of hydrocarbons, volume 1

The utilization of MSS-LANDSAT and RADAR imagery in the definition of morphostructural anomalies, which are indicative of hydrocarbon entrapment sites in the limit of the Middle and Lower Amazons basins was systemized. The identification and classification of the morphostructural anomalies were accomplished by means of the drainage network interpretation, based on the criteria previously proposed. Thirty anomalies were recognized, being subdivided into twenty domes, two fault controlled domes, six structural depressions, one fault controlled structural depression and one structure developed on a tilted fault block. Many anomalies are not randomly located. Rather, they seem to be aligned according to directions ENE and NNW, suggesting the presence of morphstructural trends in this part of the Amazons Basin. Significant orientations of lineaments were determined through statistical analysis, which defined many regional trends. The directions coincide with morphostructural trends orientations and with the directions of important structures in the Precambrian basement.

Demiranda, F. P.↗
NASA NTRS2009

(Quickly) Testing the Tester via Path Coverage

The configuration complexity and code size of an automated testing framework may grow to a point that the tester itself becomes a significant software artifact, prone to poor configuration and implementation errors. Unfortunately, testing the tester by using old versions of the software under test (SUT) may be impractical or impossible: test framework changes may have been motivated by interface changes in the tested system, or fault detection may become too expensive in terms of computing time to justify running until errors are detected on older versions of the software. We propose the use of path coverage measures as a "quick and dirty" method for detecting many faults in complex test frameworks. We also note the possibility of using techniques developed to diversify state-space searches in model checking to diversify test focus, and an associated classification of tester changes into focus-changing and non-focus-changing modifications.

evaluation of test systems↗
NASA NTRS2009

A New Monte Carlo Filtering Method for the Diagnosis of Mission-Critical Failures

Testing large-scale systems is expensive in terms of both time and money. Running simulations early in the process is a proven method of finding the design faults likely to lead to critical system failures, but determining the exact cause of those errors is still time-consuming and requires access to a limited number of domain experts. It is desirable to find an automated method that explores the large number of combinations and is able to isolate likely fault points. Treatment learning is a subset of minimal contrast-set learning that, rather than classifying data into distinct categories, focuses on finding the unique factors that lead to a particular classification. That is, they find the smallest change to the data that causes the largest change in the class distribution. These treatments, when imposed, are able to identify the settings most likely to cause a mission-critical failure. This research benchmarks two treatment learning methods against standard optimization techniques across three complex systems, including two projects from the Robust Software Engineering (RSE) group within the National Aeronautics and Space Administration (NASA) Ames Research Center. It is shown that these treatment learners are both faster than traditional methods and show demonstrably better results.

Gay, Gregory↗
NASA NTRS2010

Automatically Finding the Control Variables for Complex System Behavior

Testing large-scale systems is expensive in terms of both time and money. Running simulations early in the process is a proven method of finding the design faults likely to lead to critical system failures, but determining the exact cause of those errors is still time-consuming and requires access to a limited number of domain experts. It is desirable to find an automated method that explores the large number of combinations and is able to isolate likely fault points. Treatment learning is a subset of minimal contrast-set learning that, rather than classifying data into distinct categories, focuses on finding the unique factors that lead to a particular classification. That is, they find the smallest change to the data that causes the largest change in the class distribution. These treatments, when imposed, are able to identify the factors most likely to cause a mission-critical failure. The goal of this research is to comparatively assess treatment learning against state-of-the-art numerical optimization techniques. To achieve this, this paper benchmarks the TAR3 and TAR4.1 treatment learners against optimization techniques across three complex systems, including two projects from the Robust Software Engineering (RSE) group within the National Aeronautics and Space Administration (NASA) Ames Research Center. The results clearly show that treatment learning is both faster and more accurate than traditional optimization methods.

Gay, Gregory↗