Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “failure detection”

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 109 records · Page 6
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

Anomaly Detection in Seismic Data with Deep Learning: Application for Instrument Failure Detection and Forecasting

Seismic data quality assessment (QA) is the first and one of the most important steps before conducting any further data analysis. Traditional methods involve checking various metrics, such as spike detection and power spectral density, by setting strict thresholds or comparing data against synthetic benchmarks. However, these approaches often rely on pre-existing knowledge and assumptions about data anomalies, leading to potential misclassification of unusual cases. Here, in this study, we propose a deep autoencoder model, an unsupervised learning approach that evaluates data quality without making assumptions about normal and anomalous data, which can be used to identify deviations in recorded data that may indicate nascent instrument failure. We test the model with the U.S. International Monitoring System (IMS) seismic stations and demonstrate the capability of detecting anomalies on a monthly scale. This could prompt station operators to examine potential problems early, allowing sufficient time for instrument maintenance to prevent data outages. In addition, we use a new manually selected testing dataset to compare our model performance against two supervised machine learning (ML) approaches and a standard QA package, as baseline models. When applied to the dataset containing known data anomalies, performance of the supervised and unsupervised ML approaches is similar, with an accuracy of 88.1% for our model compared to ∼90% for the supervised ML approach and 78.2% for the standard QA package. Our model outperforms the baseline models when applied to new stations, where new types of data anomalies can be station-specific and not included in the training dataset. Finally, we show model transferability by training the model with data from the Global Seismograph Network only and applying it to the IMS network data. The results suggest that our model is generalizable and can be applied to new stations with good accuracy.

Lin, Jiun-Ting [Lawrence Livermore National Labora↗
DOE OSTI2023

Confidentiality-preserving machine learning algorithms for soft-failure detection in optical communication networks

Automated fault management is at the forefront of next-generation optical communication networks. The increase in complexity of modern networks has triggered the need for programmable and software-driven architectures to support the operation of agile and self-managed systems. In these scenarios, the European Telecommunications Standards Institute zero-touch network and service management approach is imperative. The need for machine learning algorithms to process the large volume of telemetry data brings safety concerns as distributed cloud-computing solutions become the preferred approach for deploying reliable communication network automation. This paper’s contribution is twofold. First, we propose a simple yet effective method to guarantee the confidentiality of the telemetry data based on feature scrambling. The method allows the operation of third-party computational services without direct access to the full content of the collected data. Additionally, the effectiveness of four unsupervised machine learning algorithms for soft-failure detection is evaluated when applied to the scrambled telemetry data. The methods are based on factor analysis, principal component analysis, nonlinear principal component analysis, and singular value decomposition. Most dimensionality reduction algorithms have the common property that they can maintain similar levels of fault classification performance while hiding the data structure from unauthorized access. Evaluations of the proposed algorithms demonstrate this capability.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS1992

Spacecraft dynamics characterization and control system failure detection, volume 1

The work under this grant has been directed to two aspects of the control of flexible spacecraft: (1) the modeling of deployed or erected structures including nonlinear joint characteristics; and (2) the detection and isolation of failures of the components of control systems for large space structures. The motivation for the first of these research tasks is the fact that very large assemblies in space will have to be built or deployed in situ. A likely scenario is, in fact, a combination of these wherein modules which are folded for transportation into orbit are erected to their final configuration and then jointed with other such erected modules to form the full assembly. Any such erectable modules will have joints. It remains to be seen whether or not joints designed for operational assemblies will have nonlinear properties, but it seems prudent to develop a methodology for dealing with that possibility. The motivation for the second of these research tasks is the fact that we foresee large assemblies in space which will require active control to damp vibrations and/or hold a desired shape. Lightweight structures will be very flexible, with many elastic modes having very low frequencies. In order to control these modes well, the control system will likely require many sensors and many actuators, probably distributed over much of the structure. The combination of a large number of control system components with long operational periods virtually guarantees that these systems will suffer control system component failures during operation. The control system must be designed to tolerate failures of some sensors and actuators, and still be able to continue to perform its function.

Source record↗
NASA NTRS1990

Spacecraft dynamics characterization and control system failure detection

Two important aspects of the control of large space structures are studied: the modeling of deployed or erected structures including nonlinear joint characteristics; and the detection and isolation of failures of the components of control systems for large space structures. The emphasis in the first task is on efficient representation of the dynamics of large and complex structures having a great many joints. The initial emphasis in the second task is on experimental evaluation of FDI methodologies using ground-based facilities in place at NASA Langley Research Center and Marshall Space Flight Center. The progress to date on both research tasks is summarized.

Vandervelde, Wallace E.↗
NASA NTRS1981

Model degradation effects on sensor failure detection

This paper discusses the effects of imperfect modeling on the detection and isolation of sensor failures. For systems with non-zero set points, deterministic inputs or non-zero noise biases, the model mismatch appears as a bias on the stochastic innovation process. This bias, if left unaccounted for, would be sufficient to declare a false alarm failure in one or more sensors. A practical design procedure based upon the Generalized Likelihood Ratio (GLR) form uses a finite data window sequential t-test to detect and isolate model mismatch effects and soft sensor failures. Application to an eighth order model of the QCSEE turbofan engine is discussed.

Leininger, G. G.↗
NASA NTRS1989

Failure detection and identification

Using the geometric concept of an unobservability subspace, a solution is given to the problem of detecting and identifying control system component failures in linear, time-invariant systems. Conditions are developed for the existence of a causal, linear, time-invariant processor that can detect and uniquely identify a component failure, first for the case where components can fail simultaneously, and then for the case where they fail only one at a time. Explicit design algorithms are provided when these conditions are satisfied. In addition to time-domain solvability conditions, frequency-domain interpretations of the results are given, and connections are drawn with results already available in the literature.

Massoumnia, Mohammad-Ali↗
NASA NTRS1992

Failure detection and fault management techniques for flush airdata sensing systems

A high-angle-of-attack flush airdata sensing system was installed and flight tested on the F-18 High Alpha Research Vehicle at NASA-Dryden. This system uses a matrix of pressure orifices arranged in concentric circles on the nose of the vehicle to determine angles of attack, angles of sideslip, dynamic pressure, and static pressure as well as other airdata parameters. Results presented use an arrangement of 11 symmetrically distributed ports on the aircraft nose. Experience with this sensing system data indicates that the primary concern for real-time implementation is the detection and management of overall system and individual pressure sensor failures. The multiple port sensing system is more tolerant to small disturbances in the measured pressure data than conventional probe-based intrusive airdata systems. However, under adverse circumstances, large undetected failures in individual pressure ports can result in algorithm divergence and catastrophic failure of the entire system. How system and individual port failures may be detected using chi sq. analysis is shown. Once identified, the effects of failures are eliminated using weighted least squares.

Whitmore, Stephen A.↗
NASA NTRS1975

Maximum likelihood failure detection techniques applied to the shuttle orbiter reaction control subsystem

A technique for on-board detection and identification of hard failures and leaks of the shuttle orbiter reaction control subsystem jets, during the orbital flight phase, is presented. The method uses gimbal angle and linear accelerometer measurements from the orbiter inertial measurement unit and requires no additional hardware. Extended Kalman filters with residual traps are employed for state estimation, and generalized likelihood ratio tests for jet failure identification. Rigid body simulation results indicate identification times of less than 2 seconds for hard jet failures and less than 70 seconds for jet leaks.

Deckert, J. C.↗
NASA NTRS1975

A survey of design methods for failure detection in dynamic systems

A number of methods for detecting abrupt changes (such as failures) in stochastic dynamical systems are surveyed. The class of linear systems is concentrated on but the basic concepts, if not the detailed analyses, carry over to other classes of systems. The methods surveyed range from the design of specific failure-sensitive filters, to the use of statistical tests on filter innovations, to the development of jump process formulations. Tradeoffs in complexity versus performance are discussed.

Willsky, A. S.↗
NASA NTRS1989

A real time microcomputer implementation of sensor failure detection for turbofan engines

An algorithm was developed which detects, isolates, and accommodates sensor failures using analytical redundancy. The performance of this algorithm was demonstrated on a full-scale F100 turbofan engine. The algorithm was implemented in real-time on a microprocessor-based controls computer which includes parallel processing and high order language programming. Parallel processing was used to achieve the required computational power for the real-time implementation. High order language programming was used in order to reduce the programming and maintenance costs of the algorithm implementation software. The sensor failure algorithm was combined with an existing multivariable control algorithm to give a complete control implementation with sensor analytical redundancy. The real-time microprocessor implementation of the algorithm which resulted in the successful completion of the algorithm engine demonstration, is described.

Delaat, John C.↗
NASA NTRS1990

A real time microcomputer implementation of sensor failure detection for turbofan engines

An algorithm was developed that detects, isolates, and accommodates sensor failures using analytical redundancy. The performance of this algorithm has been demonstrated on a full-scale F100 turbofan engine. The algorithm was implemented in real-time on a microprocessor-based controls computer which includes parallel processing and high order language programming. Parallel processing was used to achieve the required computational power for the real-time implementation. High order language programming was used in order to reduce the programming and maintenance costs of the algorithm implementation software. The sensor failure algorithm was combined with an existing multivariable control algorithm to give a complete control implementation with sensor analytical redundancy. The real-time microprocessor implementation of the algorithm, which resulted in the successful completion of the algorithm engine demonstration, is described.

Delaat, John C.↗
NASA NTRS2001

Lyapunov-Based Sensor Failure Detection And Recovery For The Reverse Water Gas Shift Process

Livingstone, a model-based AI software system, is planned for use in the autonomous fault diagnosis, reconfiguration, and control of the oxygen-producing reverse water gas shift (RWGS) process test-bed located in the Applied Chemistry Laboratory at KSC. In this report the RWGS process is first briefly described and an overview of Livingstone is given. Next, a Lyapunov-based approach for detecting and recovering from sensor failures, differing significantly from that used by Livingstone, is presented. In this new method, models used are in terms of the defining differential equations of system components, thus differing from the qualitative, static models used by Livingstone. An easily computed scalar inequality constraint, expressed in terms of sensed system variables, is used to determine the existence of sensor failures. In the event of sensor failure, an observer/estimator is used for determining which sensors have failed. The theory underlying the new approach is developed. Finally, a recommendation is made to use the Lyapunov-based approach to complement the capability of Livingstone and to use this combination in the RWGS process.

Haralambous, Michael G.↗
NASA NTRS2002

LYAPUNOV-Based Sensor Failure Detection and Recovery for the Reverse Water Gas Shift Process

Livingstone, a model-based AI software system, is planned for use in the autonomous fault diagnosis, reconfiguration, and control of the oxygen-producing reverse water gas shift (RWGS) process test-bed located in the Applied Chemistry Laboratory at KSC. In this report the RWGS process is first briefly described and an overview of Livingstone is given. Next, a Lyapunov-based approach for detecting and recovering from sensor failures, differing significantly from that used by Livingstone, is presented. In this new method, models used are in t e m of the defining differential equations of system components, thus differing from the qualitative, static models used by Livingstone. An easily computed scalar inequality constraint, expressed in terms of sensed system variables, is used to determine the existence of sensor failures. In the event of sensor failure, an observer/estimator is used for determining which sensors have failed. The theory underlying the new approach is developed. Finally, a recommendation is made to use the Lyapunov-based approach to complement the capability of Livingstone and to use this combination in the RWGS process.

Haralambous, Michael G.↗
NASA NTRS1971

Incipient failure detection.

In connection with the preparation for long-range space missions it is highly important to be able to identify potentially failure prone equipment in advance of the launch commitment. Physical phenomena investigated for this purpose include X-ray and gamma radiation, electrical noise, IR and UV radiation, and vibration energy. The technique selected must be capable of detecting the onset and evaluating the progression of conditions that represent basic causes which could lead to failure. As a result of the investigation, techniques based on acoustic energy release were selected as the most promising for incipient failure detection.

Griswold, J. W.↗
NASA NTRS1985

Signal analysis techniques for incipient failure detection in turbomachinery

Signal analysis techniques for the detection and classification of incipient mechanical failures in turbomachinery were developed, implemented and evaluated. Signal analysis techniques available to describe dynamic measurement characteristics are reviewed. Time domain and spectral methods are described, and statistical classification in terms of moments is discussed. Several of these waveform analysis techniques were implemented on a computer and applied to dynamic signals. A laboratory evaluation of the methods with respect to signal detection capability is described. Plans for further technique evaluation and data base development to characterize turbopump incipient failure modes from Space Shuttle main engine (SSME) hot firing measurements are outlined.

Coffin, T.↗
NASA NTRS1975

A survey of design methods for failure detection in dynamic systems

A number of methods for the detection of abrupt changes (such as failures) in stochastic dynamical systems were surveyed. The class of linear systems were emphasized, but the basic concepts, if not the detailed analyses, carry over to other classes of systems. The methods surveyed range from the design of specific failure-sensitive filters, to the use of statistical tests on filter innovations, to the development of jump process formulations. Tradeoffs in complexity versus performance are discussed.

Willsky, A. S.↗
NASA NTRS1980

Sensor/actuator failure detection and isolation for airbreathing propulsion systems

In this paper, the Generalized Likelihood Ratio (GLR) test is used to detect and isolate sensor and/or actuator failures when a digital computer simulation model of the physical system is available. The input to the GLR detector is an innovation sequence formed by subtracting the model outputs from the sensed outputs. Application of the GLR detector to the General Electric QCSEE turbofan engine demonstrates the utility of the proposed procedure.

Leininger, G. G.↗