Engine Fault Analysis: Part I-Statistical Methods

Sood, Arun K.; Friedlander, Carl; Fahs, Ali Amin

doi:10.1109/tie.1985.350100

Cited by 44 publications

(14 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…á (n) max peak value of angular acceleration of nth The detection of engine mis re by instantaneous angucylinder lar velocity measurement can be performed in two ways. á (n) min valley value of angular acceleration of The rst is based on waveform analysis, in which the nth cylinder instantaneous velocity waveform is analysed directly and á (n) sum summed absolute value of angular the extracted feature used to identify whether mis re acceleration of nth cylinder exists in the engine by simple threshold or by more com-å minor positive value quite near zero plicated Bayesian decision theory [5][6][7]. The second is õ crankshaft angular position based on torque estimation, in which the instantaneous õ (n) max crankshaft angular position gas pressure torque (indicated torque) or individual cylcorresponding to ö (n) max inder pressure is calculated by an engine dynamics õ (n) min crankshaft angular position model, and from this the mis ring cylinder is identi ed corresponding to ö (n) min [8][9][10][11][12][13][14][15][16][17].…”

Section: I(n)mentioning

confidence: 99%

The on-line detection of engine misfire at low speed using multiple feature fusion with fuzzy pattern recognition

Liu

Ball

2002

Proceedings of the Institution of Mechanical Engineers, Part D:

View full text Add to dashboard Cite

This paper proposes a technique for the on-line detection of incipient engine mis re based on multiple feature fusion and fuzzy pattern recognition. The technique requires the measurement of instantaneous angular velocity signals. By processing the engine dynamics model equation in the angular frequency domain, four dimensionless features for mis re detection are de ned, along with fast feature-extracting algorithms. By directly analysing the waveforms of the angular velocity and the angular acceleration, six other dimensionless features are extracted. Via fuzzy pattern recognition, all the features are associated together as a fuzzy vector. This vector identi es whether the engine is healthy or faulty and then locates the position of a mis ring cylinder or cylinders if necessary. The experimental work conducted on a production engine operating at low speeds con rms that such a technique is able to work with the redundant and complementary information of all the features and that it leads to improved diagnostic reliability. It is fully expected that this technique will be simple to implement and will provide a useful practical tool for the on-line monitoring and real-time diagnosis of engine mis re in individual cylinders.

show abstract

Section: I(n)mentioning

confidence: 99%

The on-line detection of engine misfire at low speed using multiple feature fusion with fuzzy pattern recognition

Liu

Ball

2002

Proceedings of the Institution of Mechanical Engineers, Part D:

View full text Add to dashboard Cite

show abstract

“…Many engineers and researchers have focused on incipient fault detection and preventive maintenance, which aim at preventing motor faults from happening [5]- [9]. Usually, devices such as fuses, overload relays, and circuit breakers protect induction motors.…”

Section: B Importance Of System Monitoring and Fault Detectionmentioning

confidence: 99%

“…Different invasive and noninvasive approaches for motor incipient fault detection/diagnosis have been reported [2], [5]- [8]. Many of the motor incipient fault detection/diagnosis schemes can be applied noninvasively on-line without the need of expensive monitoring equipment by using a microprocessor.…”

Section: B Importance Of System Monitoring and Fault Detectionmentioning

confidence: 99%

“…With proper monitoring and fault detection/diagnosis schemes, the incipient faults can be detected in their early stages; thus, maintenance and downtime expenses can be reduced, and reliability can be improved. System identification and parameter estimation have previously been proposed for fault detection/diagnosis in motors [5]- [8], [13], [14]. As opposed to conventional techniques, where expensive equipment or accurate mathematical models are required, fuzzy logic and neural network (NN) technologies can be used to provide inexpensive but effective fault detection mechanism alternatives [15].…”

Section: B Importance Of System Monitoring and Fault Detectionmentioning

confidence: 99%

See 1 more Smart Citation

Fuzzy inference systems implemented on neural architectures for motor fault detection and diagnosis

Altug

Chen²,

Trussell

1999

IEEE Trans. Ind. Electron.

156

View full text Add to dashboard Cite

“…The operational safety, economy, and reliability of aeroengine are problems of primary concern for airline companies [1]. The fault diagnosis plays a key role in enhancing the working safety and reliability and reducing the operating cost of aircraft engine.…”

Section: Introductionmentioning

confidence: 99%

Aeroengine Fault Diagnosis Using Optimized Elman Neural Network

Huang

2017

Mathematical Problems in Engineering

View full text Add to dashboard Cite

A new Elman Neural Network (ENN) optimized by quantum-behaved adaptive particle swarm optimization (QAPSO) is introduced in this paper. According to the root mean square error, QAPSO is used to select the best weights and thresholds of the ENN in training samples. The optimized neural network is applied to aeroengine fault diagnosis and is compared with other optimized ENN, original ENN, BP, and Support Vector Machine (SVM) methods. The results show that the QAPSO-ENN is more accurate and reliable in the aeroengine fault diagnosis than the conventional neural network and other ENN methods; QAPSO-ENN has great diagnostic ability in small samples.

show abstract

Engine Fault Analysis: Part I-Statistical Methods

Cited by 44 publications

References 14 publications

The on-line detection of engine misfire at low speed using multiple feature fusion with fuzzy pattern recognition

The on-line detection of engine misfire at low speed using multiple feature fusion with fuzzy pattern recognition

Fuzzy inference systems implemented on neural architectures for motor fault detection and diagnosis

Aeroengine Fault Diagnosis Using Optimized Elman Neural Network

Contact Info

Product

Resources

About