Misfire detection of a turbocharged diesel engine by using artificial neural networks

Liu, Bolan; Zhao, Changlu; Zhang, Fujun; Cui, Tao; Su, Jianyun

doi:10.1016/j.applthermaleng.2013.02.032

Cited by 53 publications

(25 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By using ANN, Bolan Liu et al detected misfire of a turbocharged diesel engine. Input factors in this study consisted of engine speed, intake temperature, intake pressure, exhaust temperature, water temperature, and fuel consumption . D. Goryntsev et al studied on misfire in a direct injection spark plug (DISP) ignition engine via large eddy simulation (LES).…”

Section: Introductionmentioning

confidence: 99%

Misfire detection of homogeneous charge compression ignition engines using matter‐element extension theory and thermodynamic multi zone model

Asghari

Saray

Neshat

2020

Env Prog and Sustain Energy

View full text Add to dashboard Cite

Nowadays, researchers tend to simulate and model the studied phenomena to reduce the calculation time and cost. Matter‐element extension model is a useful method that can be used to evaluate a wide range of data that belong to different subjects. In this study, this model is used to diagnose different engine's performance modes including misfire, normal, knock, and middle modes in which both of the mentioned modes are occurred simultaneously. To achieve this purpose, a set of performance and emission parameters acquired for a multi zonal model are chosen as input data to the model. Statistical analysis is done on a set of experimental data. First, ANOVA (analysis of variance) is used to determine parameters significant level. Then the proportional weights are given for the chosen parameters with respect to their importance. To do this, linear regression analysis is used for determination of weights. Two kinds of single objective and two objectives matter‐element extension models are employed to diagnose the engine's operation mode. The results show that both the single objective and two objectives models show a good conformity with the corresponding experimental results without acquiring empirical data. Single objective model can predict misfire, normal combustion, and knocking combustion. Meanwhile the two objectives model can predict the middle modes containing normal‐misfire, misfire‐knock, and knock‐normal accurately.

show abstract

Section: Introductionmentioning

confidence: 99%

Misfire detection of homogeneous charge compression ignition engines using matter‐element extension theory and thermodynamic multi zone model

Asghari

Saray

Neshat

2020

Env Prog and Sustain Energy

View full text Add to dashboard Cite

show abstract

“…Singh and co-workers [16] presented an improved engine misfire detection method via sound quality metrics of radiated sound and a support vector machine (SVM) classifier. Liu et al [17] proposed an effective misfire detection method for a turbocharged diesel engine based on an artificial neural network model. To detect misfire fault by comparing data with the actual crankshaft speed, Chen et al [18] adopted the extended neural network based on regression theory to calculate the crankshaft speed.…”

Section: Introductionmentioning

confidence: 99%

“…However, in-depth analysis has revealed that current data-driven methods for misfire fault diagnosis mainly utilize spectrum analysis, traditional wavelet decomposition, wavelet packet decomposition, and empirical mode decomposition to extract significant features [15,16,17,18,19,20,21,22,23,24,25,26,27]. Restricted by the Heisenberg uncertainty principle, the classical processing methods suffer from a relatively low time–frequency resolution.…”

Section: Introductionmentioning

confidence: 99%

Intelligent Fault Diagnosis of Diesel Engines via Extreme Gradient Boosting and High-Accuracy Time–Frequency Information of Vibration Signals

Tao

Qin

et al. 2019

Sensors

View full text Add to dashboard Cite

Accurate and timely misfire fault diagnosis is of vital significance for diesel engines. However, existing algorithms are prone to fall into model over-fitting and adopt low energy-concentrated features. This paper presents a novel extreme gradient boosting-based misfire fault diagnosis approach utilizing the high-accuracy time–frequency information of vibration signals. First, diesel engine misfire tests were conducted under different spindle speeds, and the corresponding vibration signals were acquired via a triaxial accelerometer. The time-domain features of signals were extracted by using a time-domain statistics method, while the high-accuracy time–frequency domain features were obtained via the high-resolution multisynchrosqueezing transform. Thereafter, considering the nonlinearity and high dimensionality of the original characteristic data sets, the locally linear embedding method was employed for feature dimensionality reduction. Eventually, to avoid model overfitting, the extreme gradient boosting algorithm was utilized for diesel engine misfire fault diagnosis. Experiments under different spindle speeds and comprehensive comparisons with other evaluation methods were conducted to demonstrate the effectiveness of the proposed extreme gradient boosting-based misfire diagnosis method. The results verify that the highest classification accuracy of the proposed extreme gradient boosting-based algorithm is up to 99.93%. Simultaneously, the classification accuracy of the presented approach is approximately 24.63% higher on average than those of algorithms that use wavelet packet-based features. Moreover, it is shown that it obtains the minimum root mean squared error and can effectively prevent the model from falling into overfitting.

show abstract

“…6,7 Numerous works have focused on signal sampling 8,9 and post-processing of vibration signals 10–12 over the past several decades, and an approach to misfire detection for a turbocharged diesel engine using neural networks has been proposed. 13…”

Section: Introductionmentioning

confidence: 99%

Detection of engine misfire using characteristic harmonics of angular acceleration

Song

Gao

Zhang

et al. 2019

Proceedings of the Institution of Mechanical Engineers, Part D:

View full text Add to dashboard Cite

A new torsional vibration–based method for the detection of engine misfires was proposed based on the discrete Fourier transform of angular acceleration of the crankshaft. By analysis of the sensitivity of the discrete Fourier transform to fluctuations in speed and load of the engine, the characteristic harmonics and characteristic discrete Fourier transforms of a cylinder were defined. Then cylinder misfires under any operating conditions were diagnosed by checking the characteristic discrete Fourier transforms of the cylinder at its characteristic harmonics. An experiment on a four-stroke, six-cylinder diesel engine showed that this method accurately identified misfire faults and the misfiring cylinders.

show abstract

Misfire detection of a turbocharged diesel engine by using artificial neural networks

Cited by 53 publications

References 17 publications

Misfire detection of homogeneous charge compression ignition engines using matter‐element extension theory and thermodynamic multi zone model

Misfire detection of homogeneous charge compression ignition engines using matter‐element extension theory and thermodynamic multi zone model

Intelligent Fault Diagnosis of Diesel Engines via Extreme Gradient Boosting and High-Accuracy Time–Frequency Information of Vibration Signals

Detection of engine misfire using characteristic harmonics of angular acceleration

Contact Info

Product

Resources

About