Bayesian models for the determination of resonant frequencies in a DI diesel engine

Bodisco, Timothy A.; Reeves, Robert W.; Situ, Rong; Brown, Richard J.

doi:10.1016/j.ymssp.2011.06.014

Cited by 23 publications

(14 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Convolutional neural network [12] and Bayesian diagnosis method [13,14] have been proposed. Several other methods, the Monte Carlo method [15], the fuzzy diagnosis method [16], and the support vector machine (SVM) method [17,18], have been also applied in machine fault diagnosis with good performance. Additionally, novel approaches like Switching Unscented Kalman Filter method [19], Extreme Learning Machines [20], Online Dictionary Learning [21], and the discriminative nonnegative matrix factorization (DNMF) method [22] have been proposed.…”

Section: Introductionmentioning

confidence: 99%

A Study of Probabilistic Diagnosis Method for Three Kinds of Internal Combustion Engine Faults Based on the Graphical Model

Liu

Jiang

2019

Mathematical Problems in Engineering

View full text Add to dashboard Cite

A strategy for increasing the accuracy rate of internal combustion engine (ICE) fault diagnosis based on the probabilistic graphical model is proposed. In this method, a three-layer network with inference of probability is constructed, and both the material conditions and the signals collected from different engine parts are considered as the inputs of the system. Machine signals measured by sensors were processed in order to diagnose potential faults, which were presented as probabilities based on the components in layer 1, fault categories in layer 2, and fault symptoms in layer 3. The diagnosis model was built by using nodes and arcs, and the results depended on the connections between the fault categories and symptoms. The parameters of the network represented quantitative probabilistic relationships among all layers, and the conditional probabilities of each type of fault and relevant symptoms were summarized. Fault cases were simulated on a 12-cylinder diesel engine, and three fault types that often occur on ICEs were tested based on five different fault symptoms with different loads, respectively. The diagnostic capability of the method was investigated, reporting high accuracy rates.

show abstract

Section: Introductionmentioning

confidence: 99%

A Study of Probabilistic Diagnosis Method for Three Kinds of Internal Combustion Engine Faults Based on the Graphical Model

Liu

Jiang

2019

Mathematical Problems in Engineering

View full text Add to dashboard Cite

show abstract

“…Statistical modelling, within the Bayesian paradigm, is suggested to overcome these issues. As this is not a one-size-fits-all method, using this method is at the expense of simplicity [16]. However, it can be argued that in data analysis more emphasis should be given to scientific interest and less to mathematical convenience [21].…”

Section: Introductionmentioning

confidence: 99%

“…Whilst this adds complexity, it also ensures that the analyst is completely aware of the problem they are solving and reduces the potential risk of obtaining a misleading result. Moreover, in this application it allows for the analysis to be conducted independently, on individual engine cycles; thereby, allowing for inter-cycle variability studies and effectively removing the need for ad hoc methods such as cycle averaging [16,23].…”

Section: Introductionmentioning

confidence: 99%

A statistical model for combustion resonance from a DI diesel engine with applications

Bodisco

Low‐Choy

Masri

et al. 2015

Mechanical Systems and Signal Processing

Self Cite

View full text Add to dashboard Cite

Introduced in this paper is a Bayesian model for isolating the resonant frequency from combustion chamber resonance. The model shown in this paper focused on characterising the initial rise in the resonant frequency to investigate the rise of in-cylinder bulk temperature associated with combustion. By resolving the model parameters, it is possible to determine: the start of pre-mixed combustion, the start of diffusion combustion, the initial resonant frequency, the resonant frequency as a function of crank angle, the in-cylinder bulk temperature as a function of crank angle and the trapped mass as a function of crank angle. The Bayesian method allows for individual cycles to be examined without cycle-averaging-allowing inter-cycle variability studies. Results are shown for a turbo-charged, common-rail compression ignition engine run at 2000 rpm and full load.

show abstract

“…In opposition to Hickling et al manual 55 method, this must be automated for the real-time implementation of the algorithm. Although Bodisco et al [27] have discussed the possibility of determining the instantaneous frequency by statistical inference methods, the straightforward solution is using time-frequency analysis (e.g. the Short Time Fourier Transform (STFT) is used in [26]).…”

mentioning

confidence: 99%

A direct transform for determining the trapped mass on an internal combustion engine based on the in-cylinder pressure resonance phenomenon

Broatch

Guardiola

Plá

et al. 2015

Mechanical Systems and Signal Processing

View full text Add to dashboard Cite

ElsevierBroatch Jacobi, JA.; Guardiola García, C.; Pla Moreno, B.; Bares Moreno, P. (2015). A direct transform for determining the trapped mass on an internal combustion engine based on the in-cylinder pressure resonance phenomenon. Mechanical Systems and Signal Processing. 62-63:480-489. doi:10.1016/j.ymssp.2015.02.023. A direct transform for determining the trapped mass on an internal combustion engine based on the in-cylinder pressure resonance phenomenon AbstractIt has lately been demonstrated that the resonance of the in-cylinder pressure may be used for inferring the trapped mass in an internal combustion engine. The resonance frequency changes over time as the expansion stroke takes place, and hence time-frequency analysis techniques may be used for determining the instantaneous frequency. However, time-frequency analysis has different problems when obtaining the spectral content of the signal, e.g. Short-Time Fourier Transform dilutes the frequency spectrum, and the Wigner Distribution creates cross terms that difficult its interpretation. In addition, time-frequency analysis requires a significant computational burden. This paper presents a direct transform, based on the resonance phenomenon, which obtains the trapped mass by convolving the pressure trace with the theoretical resonance behaviour. The method permits avoiding the spectral problems of the time-frequency transformations by obtaining the trapped mass directly without the need of inferring the frequency content.

show abstract

Bayesian models for the determination of resonant frequencies in a DI diesel engine

Cited by 23 publications

References 20 publications

A Study of Probabilistic Diagnosis Method for Three Kinds of Internal Combustion Engine Faults Based on the Graphical Model

A Study of Probabilistic Diagnosis Method for Three Kinds of Internal Combustion Engine Faults Based on the Graphical Model

A statistical model for combustion resonance from a DI diesel engine with applications

A direct transform for determining the trapped mass on an internal combustion engine based on the in-cylinder pressure resonance phenomenon

Contact Info

Product

Resources

About