Real-time combustion torque estimation and dynamic misfire fault diagnosis in gasoline engine

Zheng, Taixiong; Li, Yongfu; Shi, Lichen

doi:10.1016/j.ymssp.2019.02.048

Cited by 27 publications

(18 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Zhang et al [ 71 ] studied the method to detect and diagnose the misfire in an engine using the group of Luenberger and the sliding mode technique. A Luenberger sliding mode observer opted for the estimation of engine combustion torque.…”

Section: Modeling Of Internal Combustion Enginesmentioning

confidence: 99%

Application of Artificial Neural Network for Internal Combustion Engines: A State of the Art Review

Bhatt

Shrivastava

2021

Arch Computat Methods Eng

View full text Add to dashboard Cite

The automotive industry is facing a crucial time. The transformation from internal combustion engines to new electrical technologies requires enormous investment, and hence the IC engines are likely to serve as a means of transportation for the coming decades. The search for sustainable green alternative fuel and operating parameter optimization is a current feasible solution and is a critical issue among the scientific community. Engine experiments are complicated, costly, and time-consuming, especially when the global economy is drastically down due to the COVID-19 pandemic and putting the limitation of social distancing. Industries are looking for proven computational solutions to address these issues. Recently, artificial neural network has been proven beneficial in several areas of engineering to reduce the time and experimentation cost. The IC engine is one of them. ANN has been used to predict and analyze different characteristics such as performance, combustion, and emissions of the IC engine to save time and energy. The complex nature of ANN may lead to computation time, energy, and space. Recent studies are centered on changing the network topology, deep learning, and design of ANN to get the highest performance. The present study summarizes the application of ANN to predict and optimize the complicated characteristics of various types of engines with different fuels. The study aims to investigate the network topologies adopted to design the model and thereafter statistical evaluation of the developed ANN models. A comparison of the ANN model with other prediction models is also presented.

show abstract

Section: Modeling Of Internal Combustion Enginesmentioning

confidence: 99%

Application of Artificial Neural Network for Internal Combustion Engines: A State of the Art Review

Bhatt

Shrivastava

2021

Arch Computat Methods Eng

View full text Add to dashboard Cite

show abstract

“…20 The observer based on the sliding mode is designed by assuming the crankshaft angular velocity as an input to estimate cylinder pressure, torque, or heat release rate. 21–24 The misfire is detected by threshold rules or the pattern recognition technique. For the parameter identification-based methods, the Kalman filter approach is introduced to estimate the torque owing to its excellent ability to resist interference from signal noise, phase-free estimation, and high robustness against parameterisation errors.…”

Section: Introductionmentioning

confidence: 99%

“…Osburn et al 48 selected the features from filtered speed signal, and utilised statistical pattern recognition method for misfire detection. Some other techniques, such as support vector machine, 49 linear parametric classifier, 26 and artificial neural network networks (ANNs) 24,50–52 have been employed for misfire detection. Thus, with multiple feature fusion, the correctness and robustness on misfire detection is improved.…”

Section: Introductionmentioning

confidence: 99%

Misfire detection of diesel engine based on convolutional neural networks

Zhang

Gao

et al. 2021

Proceedings of the Institution of Mechanical Engineers, Part D:

View full text Add to dashboard Cite

With the ever-stringent vehicles exhaust emission standard and higher requirements on on-board diagnostic technology, the importance of misfire detection in vehicle emission control is emerging. The performance of a traditional misfire detection algorithm predominantly depends on the features and classifier selected. Fixed and handcrafted features require either a reliable dynamic model of an engine or a large number of experiment data to define the threshold, and then, form a map. Since convolutional neural networks (CNNs) have an inherent adaptive design and integrate the feature extraction with classification functions into a compact learning framework, the misfire fault-sensitive features can be auto-discovered from raw speed signals. Furthermore, CNNs can detect the fault features of the misfire through network training with fewer engine operating conditions. In this paper, the theory and method of the misfire diagnosis based on CNNs are presented. The experimental data for network training and testing are sampled on a six-cylinder inline diesel engine. The misfire patterns containing every one-cylinder and two-cylinder misfire are tested under the wide speed and load conditions of the engine. The results show that when the engine operates under steady-state conditions, one-cylinder or two-cylinder complete misfires can be detected accurately by CNNs. In addition, one-cylinder partial misfire is employed to examine the adaptability of trained 1-D CNN. It turns out that when the partial misfire reaches the same level as half amount of the normal fuel injection quantity, one-cylinder partial misfire can be detected with accuracy more than 96%. At last, the misfire detection under the non-stationary conditions, such as acceleration or deceleration, is conducted. The results show the 1-D CNN performed well in a limited acceleration range, and network failure occurs when the absolute acceleration of the engine speed is more than 100 r/min/s.

show abstract

“…The ECU obtains real-time engine status during engine operation by collecting various excitation signals via the sensor, including the crankshaft position (CKP) signal, the camshaft position (CMP) signal, the knock signal, and the throttle signal [ 9 , 10 ]. Among all excitation signals, the CKP and CMP signals are the most critical for fuel injection regulation [ 11 , 12 , 13 ].…”

Section: Introductionmentioning

confidence: 99%

A Segmentation Model of ECU Excitation Signal Based on Characteristic Parameters

Zheng

Wang

2021

Sensors

View full text Add to dashboard Cite

According to the basic structure and working principle of the excitation signal sensors of a diesel engine electronic control unit (ECU), a segmentation model of an ECU excitation signal based on characteristic parameters (ESCP-SM) is proposed. In the ESCP-SM, the ECU excitation signal is divided into several parts, and each part has its characteristic parameters model. By using the same global parameters and strictly controlling each part’s proportional parameters, the ESCP-SM can achieve signal alignment and dynamic frequency modulation. Based on the simulation experiment, spectrum analysis proves that this modeling method ensures that the original signal’s effective information is not lost. Pearson similarity analysis shows that the similarity between the simulation signal and practical signal reaches 74%, exhibiting strong correlation. In addition, we set up a physical testing environment. ESCP-SM is realized based on virtual instrument technology, and provides excitation signals for a Komatsu 8 ECU. By modifying the parameter configuration, the ECU can drive the injector to work correctly.

show abstract

Real-time combustion torque estimation and dynamic misfire fault diagnosis in gasoline engine

Cited by 27 publications

References 25 publications

Application of Artificial Neural Network for Internal Combustion Engines: A State of the Art Review

Application of Artificial Neural Network for Internal Combustion Engines: A State of the Art Review

Misfire detection of diesel engine based on convolutional neural networks

A Segmentation Model of ECU Excitation Signal Based on Characteristic Parameters

Contact Info

Product

Resources

About