Using neural networks for sensor validation

Mattern, Duane; Jaw, Link C.; Guo, Ten-Huei; Graham, Ronald E.; McCoy, W.L.

doi:10.2514/6.1998-3547

Cited by 33 publications

(14 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In their work they identified three consecutive sensor failures, which were generated in a similar fashion discussed in the current paper. Mattern and Jaw [11] describe the application of a NN to sensor failure detection and consequent substitution upon failure. The approach uses auto-associative neural networks in which the input vectors to a NN reproduce themselves as the output vectors of the NN.…”

Section: Introductionmentioning

confidence: 99%

SR-30 turbojet engine real-time sensor health monitoring using neural networks, and Bayesian belief networks

et al. 2006

View full text Add to dashboard Cite

This paper describes the use of artificial intelligence-based techniques for detecting and isolating sensor failures in a turbojet engine. Specifically, three artificial intelligence (AI) techniques are employed: artificial neural networks (NNs), statistical expectations, and Bayesian belief networks (BBNs). These techniques are combined into an overall system that is capable of distinguishing between sensor failure and engine failure-a critical capability in the operation of turbojet engines.The turbojet engine used in this study is an SR-30 developed by Turbine Technologies. Initially, NNs were designed and trained to recognize sensor failure in the engine. The increased random noise output from failing sensors was used as the key indicator. Next, a Bayesian statistical method was used to recognize sensor failure based on the bias error occurring in the sensors. Finally, a BBN was developed to interpret the results of the NN and statistical evaluations. The BBN determines whether single or multiple sensor failures signify engine failure, or whether sensor failures represent separate, unrelated incidences. The BBN algorithm is also used to distinguish between bias and noise errors on sensors used to monitor turbojet performance. The overall system is demonstrated to work equally well during start-up and main-stage operation of the engine. Results show that the method can efficiently detect and isolate single or multiple sensor failures within this dynamic environment.

show abstract

Section: Introductionmentioning

confidence: 99%

SR-30 turbojet engine real-time sensor health monitoring using neural networks, and Bayesian belief networks

et al. 2006

View full text Add to dashboard Cite

show abstract

“…The field of sensor FDI systems for aero engines has been studied over the past few decades [6], and plenty of related works have been reported [7][8][9][10][11][12][13][14]. Wallhagen and Arpasi [7] utilized analytical redundancy to address serious sensor fault in one of the engine spool speeds and the compressor outlet static pressure signal, which has set the theoretical basis and given an excellent instance for using the analytical redundancy to diagnose the engine control system.…”

Section: Introductionmentioning

confidence: 99%

Sensor Fault Diagnosis for Aero Engine Based on Online Sequential Extreme Learning Machine with Memory Principle

Huang

Lü

2017

Energies

View full text Add to dashboard Cite

Abstract:The on-board sensor fault detection and isolation (FDI) system is essential to guarantee the reliability and safety of an aero engine. In this paper, a novel online sequential extreme learning machine with memory principle (MOS-ELM) is proposed for detecting, isolating, and reconstructing the fault sensor signal of aero engines. In many practical online applications, the sequentially coming data chunk usually possesses a characteristic of timeliness, and the overdue training data may mislead the subsequent learning process. The proposed MOS-ELM can improve the training process by introducing the concept of memory principle into the online sequential extreme learning machine (OS-ELM) to tackle the timeliness of the data chunk. Simulations on some time series problems and some benchmark databases show that MOS-ELM performs better in generalization performance, stability, and prediction accuracy than OS-ELM. The experiment results of the MOS-ELM-based sensor fault diagnosis system also verify the excellent generalization performance of MOS-ELM and indicate the effectiveness and feasibility of the developed diagnosis system.

show abstract

“…[6] suggests the use of Auto-Associative Neural Networks to detect faulty sensors in an aircraft engine. However, instead of detecting a binary fault state and exploiting redundancy, we focus on arbitrary accuracy.…”

Section: Introductionmentioning

confidence: 99%

Quality of Location: Estimation, system integration and application

Berchtold

Riedel

Decker

et al. 2008

2008 5th International Conference on Networked Sensing Systems

View full text Add to dashboard Cite

Abstract-Accurate location measurement is an important research topic in Pervasive Computing systems and applications. To achieve high performance measurements, the knowledge of the quality of a measurement, a sensor cue, or an inferred location value is required. This paper presents a novel approach in the deliverance of an independent, unified Quality of Location (QoL) value for Location systems. The proposed approach is highly flexible, independent of technology and location inference mechanisms and approaches, integrable into any existing location system, and does neither require knowledge of sensor, nor of application characteristics. The paper proposes both a method to retrieve QoL for a given system, and shows its application in a setting using a simple ultrasound location system. Retrieving QoL requires a multi step process including a unsupervised subtractive clustering method for initial learning, and a supervised network based fuzzy inference systems (ANFIS) for refinement of the parameters. The approach described can be used in settings using heterogeneous systems, devices, and sensors. It is also usable at any abstraction layer and is able to run on small sensor node devices. Technical foundations of the algorithms are an adaptive network based fuzzy inference systems (ANFIS). In this paper we will show the technical principles, its application and evaluate the performance of the system.

show abstract

Using neural networks for sensor validation

Cited by 33 publications

References 10 publications

SR-30 turbojet engine real-time sensor health monitoring using neural networks, and Bayesian belief networks

SR-30 turbojet engine real-time sensor health monitoring using neural networks, and Bayesian belief networks

Sensor Fault Diagnosis for Aero Engine Based on Online Sequential Extreme Learning Machine with Memory Principle

Quality of Location: Estimation, system integration and application

Contact Info

Product

Resources

About