Fault diagnosis in gears operating under non-stationary rotational speed using polar wavelet amplitude maps

Meltzer, G.; Dien, Nguyen Phong

doi:10.1016/j.ymssp.2004.01.009

Cited by 65 publications

(40 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…. , T K ) of the set T , defined according to (31), that fulfills (43). Next result, establishes a relation between the sought partition T of T and a partition P of the set Ψ computed in Step 2 of the algorithm.…”

Section: Justification Of Learning Algorithmmentioning

confidence: 97%

“…, K, defined according to (44). From (43) and (46) it follows that for each T i ∈ T and for each R k ∈ T i , it holds that…”

Section: Justification Of Learning Algorithmmentioning

confidence: 99%

“…A potential solution is to consider adaptive thresholds [19,24], and use apriori knowledge, either qualitative [33,62,31,23] or quantitative [53,25,47], to derive non-constant thresholds to take the time-varying uncertainties and disturbances into account. Furthermore since the residual depicted in Figure 1 is non-periodic, diagnosis approaches for machines working in non-stationary operating conditions [16,52,43,51] are not applicable. This paper instead proposes an adaptive statistical residual evaluation method, which exploits quantitative a-priori knowledge in the form of data.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Data-driven and adaptive statistical residual evaluation for fault detection with an automotive application

Svärd

Nyberg

Frisk

et al. 2014

Mechanical Systems and Signal Processing

View full text Add to dashboard Cite

An important step in model-based fault detection is residual evaluation, where residuals are evaluated with the aim to detect changes in their behavior caused by faults. To handle residuals subject to time-varying uncertainties and disturbances, which indeed are present in practice, a novel statistical residual evaluation approach is presented. The main contribution is to base the residual evaluation on an explicit comparison of the probability distribution of the residual, estimated online using current data, with a no-fault residual distribution. The no-fault distribution is based on a set of a-priori known no-fault residual distributions, and is continuously adapted to the current situation. As a second contribution, a method is proposed for estimating the required set of no-fault residual distributions off-line from no-fault training data. The proposed residual evaluation approach is evaluated with measurement data on a residual for fault detection in the gas-flow system of a Scania truck diesel engine. Results show that small faults can be reliable detected with the proposed approach in cases where regular methods fail.

show abstract

Section: Justification Of Learning Algorithmmentioning

confidence: 97%

“…, K, defined according to (44). From (43) and (46) it follows that for each T i ∈ T and for each R k ∈ T i , it holds that…”

Section: Justification Of Learning Algorithmmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Data-driven and adaptive statistical residual evaluation for fault detection with an automotive application

Svärd

Nyberg

Frisk

et al. 2014

Mechanical Systems and Signal Processing

View full text Add to dashboard Cite

show abstract

“…FFT could generate the statistical average characteristics under the circumstance of steady operations, but it cannot deal with time and frequency domain problems. The wavelet transform, as a time-frequency analysis approach, is widely used in fault feature extraction [11], but it could only use certain frequency bands to deal with the acquired signal [12].…”

Section: Introductionmentioning

confidence: 99%

Correlated EEMD and Effective Feature Extraction for Both Periodic and Irregular Faults Diagnosis in Rotating Machinery

2017

View full text Add to dashboard Cite

Intelligent fault diagnosis of complex machinery is crucial for industries to reduce the maintenance cost and to improve fault prediction performance. Acoustic signal is an ideal source for diagnosis because of its inherent characteristics in terms of being non-directional and insensitive to structural resonances. However, there are also two main drawbacks of acoustic signal, one of which is the low signal to noise ratio (SNR) caused by its high sensitivity and the other one is the low computational efficiency caused by the huge data size. These would decrease the performance of the fault diagnosis system. Therefore, it is significant to develop a proper feature extraction method to improve computational efficiency and performance in both periodic and irregular fault diagnosis. To enhance SNR of the acquired acoustic signal, the correlation coefficient (CC) method is employed to eliminate the redundant intrinsic mode functions (IMF), which comes from the decomposition procedure of pre-processing known as ensemble empirical mode decomposition (EEMD), because the higher the correlated coefficient of an IMF is, the more significant fault signatures it would contain, and the redundant IMF would compromise both the SNR and the computational cost performance. Singular value decomposition (SVD) and sample Entropy (SampEn) are subsequently used to extract the fault feature, by exploiting their sensitivities to irregular and periodic fault signals, respectively. In addition, the proposed feature extraction method using sparse Bayesian based pairwise coupled extreme learning machine (PC-SBELM) outperforms the existing pairwise-coupling probabilistic neural network (PC-PNN) and pairwise-coupling relevance vector machine (PC-RVM) by 1.8% and 2%, respectively, to achieve an accuracy of 93.9%. The experiments conducted on the periodic and irregular faults in the gears and bearings have demonstrated that the proposed hybrid fault diagnosis system is effective.

show abstract

“…The investigation of diagnostics of mechanical machines with aid of vibration measurements is described in many papers; McFadden [1] has described a series of seeded fault tests performed on the double-helical gears used in a marine gearbox and presents analyses of the vibration signals measured at two locations on the gearbox for each of five faults; Dalpiaz and Rivola [2] have assessed and compared the effectiveness and reliability of different vibration 10.2478/v10138-012-0002-z analysis techniques such as amplitude probability density for fault detection and diagnostics in cam mechanisms used in high performance automatic packaging machines; Meltzer and Nguyen [3] have studied the effectiveness of the continuous wavelet transform in vibro-acoustical diagnostics of gearboxes operating under non-stationary rotational speed, which has been illustrated by means of a program test for fault diagnosis on helical spur gears. The set-up conceived and described in this paper is mainly intended for educational and scientific purposes.…”

Section: Introductionmentioning

confidence: 99%

Educational Set-Up for Vibration Measurements in Vehicle Gearboxes

Achtenova¹,

Morsy²

2012

Journal of Middle European Construction and Design of Cars

View full text Add to dashboard Cite

SHRNUTÍV následujícím článku je představen zkušební stav vybudovaný za účelem diagnostiky chyb v převodovce pomocí měření vibrací na převodovce. Stav je využívaný zejména studenty automobilové specializace. Otevřený měřicí stav sestává ze dvou dynamometrů a je připraven pro upevnění různých typů převodovek. Jako testovací převodovka byla vybrána nejčastější typ převodovky pro příčnou zástavbu hnací ústrojí vpředu a pohon předních kol. Pro měření byly k dispozici dvě naprosto totožné a nové převodovky. Diferenciál byl blokován. Výkon byl odebírán pouze z jedné výstupní příruby. V jedné z převodovek byly uměle vyrobeny následující dvě závady:• Na vnitřním kroužku ložiska vstupního hřídele umístěného ze strany spojky byla vyfrézována podélná drážka o šířce 1 mm.• Důlky představující poškozením pittingem byly vybroušeny do boku zubu IV. rychlostního stupně. Upínací podstavec umožňuje rychlou výměnu převodovky. Při studentském měření je nejdříve jsou měřeny a analyzovány vibrace pomocí FFT, řádové a obálkové analýzy na nové převodovce. Poté je převodovka zaměněna za převodovku s uměle vytvořeným poškozením a za stejných podmínek jsou měřeny a analyzovány vibrace. Studenti mají identifikovat přítomnost a typ závad v převodovce. KLÍČOVÁ SLOVA: DETEKCE PITTINGU, DIAGNOSTIKA ZÁVAD LOŽISEK, DIAGNOSTIKA POMOCÍ MĚŘENÍ VIBRACÍ ABSTRACTIn this paper we present a set-up specifically prepared for an educational application. The aim of the set-up is to build an educational tool for students of automotive engineering. The open test stand we used is equipped with two dynamometers and can accommodate various automotive gearboxes. The most common type of gearbox intended for transversal powertrain placement in small and midsize vehicles was chosen as the test gearbox. At our disposal we had two identical and completely new gearboxes provided by a car manufacturer. The differential of the gearbox was blocked. The total power is taken-off from one side only. In one gearbox two artificial faults were introduced:• An orthogonal placed groove on the inner race with the initial width of 1 mm. The damaged bearing is a roller bearing located on the gearbox input shaft -on the clutch side.• Pitting defect ground on the teeth sides of the IV th speed. The mounting base of the test stand allows easy changing of the gearboxes. During the student training, the new undamaged gearbox is first measured. After completion of signal measurement and analysing by means of FFT, Order and Envelope analysis, the gearbox is changed for the damaged one. After measurements under the same conditions, the same type of analysis of the measured signal is performed. The students have to identify the type of damage(s) present in the damaged gearbox.

show abstract

Fault diagnosis in gears operating under non-stationary rotational speed using polar wavelet amplitude maps

Cited by 65 publications

References 7 publications

Data-driven and adaptive statistical residual evaluation for fault detection with an automotive application

Data-driven and adaptive statistical residual evaluation for fault detection with an automotive application

Correlated EEMD and Effective Feature Extraction for Both Periodic and Irregular Faults Diagnosis in Rotating Machinery

Educational Set-Up for Vibration Measurements in Vehicle Gearboxes

Contact Info

Product

Resources

About