Chinese Journal of Mechanical Engineering >

2021 , Vol. 34 >Issue 2: 7 - 7

DOI: https://doi.org/10.1186/s10033-020-00525-4

Advanced Transportation Equipment

Cylinder Pressure Prediction of An HCCI Engine Using Deep Learning

  • Halit Ya?ar ,
  • Gültekin ?a??l ,
  • Orhan Torkul ,
  • Merve ?i?ci
展开
  • 1. Department of Mechanical Engineering, Engineering Faculty, Sakarya University, Esentepe Campus, 54187, Serdivan, Sakarya, Turkey;
    2. Department of Industrial Engineering, Engineering Faculty, Sakarya University, Esentepe Campus, 54187, Serdivan, Sakarya, Turkey

收稿日期: 2019-08-05

  修回日期: 2020-11-30

  网络出版日期: 2021-09-02

收起

Cylinder Pressure Prediction of An HCCI Engine Using Deep Learning

  • Halit Ya?ar ,
  • Gültekin ?a??l ,
  • Orhan Torkul ,
  • Merve ?i?ci
Expand
  • 1. Department of Mechanical Engineering, Engineering Faculty, Sakarya University, Esentepe Campus, 54187, Serdivan, Sakarya, Turkey;
    2. Department of Industrial Engineering, Engineering Faculty, Sakarya University, Esentepe Campus, 54187, Serdivan, Sakarya, Turkey

Received date: 2019-08-05

  Revised date: 2020-11-30

  Online published: 2021-09-02

Fold

摘要

Engine tests are both costly and time consuming in developing a new internal combustion engine. Therefore, it is of great importance to predict engine characteristics with high accuracy using artificial intelligence. Thus, it is possible to reduce engine testing costs and speed up the engine development process. Deep Learning is an effective artificial intelligence method that shows high performance in many research areas through its ability to learn high-level hidden features in data samples. The present paper describes a method to predict the cylinder pressure of a Homogeneous Charge Compression Ignition (HCCI) engine for various excess air coefficients by using Deep Neural Network, which is one of the Deep Learning methods and is based on the Artificial Neural Network (ANN). The Deep Learning results were compared with the ANN and experimental results. The results show that the difference between experimental and the Deep Neural Network (DNN) results were less than 1%. The best results were obtained by Deep Learning method. The cylinder pressure was predicted with a maximum accuracy of 97.83% of the experimental value by using ANN. On the other hand, the accuracy value was increased up to 99.84% using DNN. These results show that the DNN method can be used effectively to predict cylinder pressures of internal combustion engines.

关键词： Artificial neural network; Deep neural network; HCCI engine; Cylinder pressure; Excess air coefficient

本文引用格式

Halit Ya?ar , Gültekin ?a??l , Orhan Torkul , Merve ?i?ci . Cylinder Pressure Prediction of An HCCI Engine Using Deep Learning[J]. Chinese Journal of Mechanical Engineering, 2021 , 34(2) : 7 -7 . DOI: 10.1186/s10033-020-00525-4

Abstract

Engine tests are both costly and time consuming in developing a new internal combustion engine. Therefore, it is of great importance to predict engine characteristics with high accuracy using artificial intelligence. Thus, it is possible to reduce engine testing costs and speed up the engine development process. Deep Learning is an effective artificial intelligence method that shows high performance in many research areas through its ability to learn high-level hidden features in data samples. The present paper describes a method to predict the cylinder pressure of a Homogeneous Charge Compression Ignition (HCCI) engine for various excess air coefficients by using Deep Neural Network, which is one of the Deep Learning methods and is based on the Artificial Neural Network (ANN). The Deep Learning results were compared with the ANN and experimental results. The results show that the difference between experimental and the Deep Neural Network (DNN) results were less than 1%. The best results were obtained by Deep Learning method. The cylinder pressure was predicted with a maximum accuracy of 97.83% of the experimental value by using ANN. On the other hand, the accuracy value was increased up to 99.84% using DNN. These results show that the DNN method can be used effectively to predict cylinder pressures of internal combustion engines.

Key words： Artificial neural network; Deep neural network; HCCI engine; Cylinder pressure; Excess air coefficient

参考文献

[1] D Lee, S Kang, J Shin. Using deep learning techniques to forecast environmental consumption level. Sustainability, 2017, 9(10): 1–17.
[2] Y LeCun, Y Bengio, G Hinton. Deep learning. Nature, 2015, 521: 436–444.
[3] L Wei, Y Ding, R Su, et al. Prediction of human protein subcellular localization using deep learning. Journal of Parallel and Distributed Computing, 2017, 117: 212–217.
[4] A Martin, R Lara-Cabrera, F Fuentes-Hurtedo, et al. EvoDeep: A new evolutionary approach for automatic deep neural networks parametrization. Journal of Parallel and Distributed Computing, 2018, 117: 180–191.
[5] S Pang, J J Coz, Z Yu, et al. Deep learning to frame objects for visual target tracking. Engineering Applications of Artificial Intelligence, 2017, 65: 406–420.
[6] B Jan, H Farman, M Khan, et al. Deep learning in big data Analytics: A comparative study. Computers and Electrical Engineering, 2019, 75: 275–287.
[7] E O Aboagye, G J James, R Kumar. Evaluating the performance of deep neural networks for health decision making. Procedia Computer Science, 2018, 131: 866–872.
[8] Y Çay. Prediction of a gasoline engine performance with artificial neural network. Fuel, 2013, 111: 324–331.
[9] Y Çay, İ Korkmaz, A Çiçek, et al. Prediction of engine performance and exhaust emissions for gasoline and methanol using artificial neural network. Energy, 2013, 50: 177–186.
[10] V Manieniyan, G Vinodhini, R Senthilkumar, et al. Wear element analysis using neural networks of a DI diesel engine using biodiesel with exhaust gas recirculation. Energy, 2016, 114: 603–612.
[11] B Bahri, M Shahbakhti, A A Aziz. Real-time modeling of ringing in HCCI engines using artificial neural networks. Energy, 2017, 125: 509–518.
[12] R R Molkdaragh, S Jafarmadar, S Khalilaria, et al. Prediction of the performance and exhaust emissions of a compression ignition engine using a wavelet neural network with a stochastic gradient algorithm. Energy, 2018, 142: 1128–1138.
[13] H Bendu, B Deepak, S Murugan. Application of GRNN for the prediction of performance and exhaust emissions in HCCI engine using ethanol. Energy Conversion and Management, 2016, 122: 165–173.
[14] S Roy, R Banerjee, P K Bose. Performance and exhaust emissions prediction of a CRDI assisted single cylinder diesel engine coupled with EGR using artificial neural network. Applied Energy, 2014, 119: 330–340.
[15] J Rezaei, M Shahbakhti, B Bahri, et al. Performance prediction of HCCI engines with oxygenated fuels using artificial neural networks. Applied Energy, 2015, 138: 460–473.
[16] F Heister, M Froehlich. Non-lineir time series analysis of combustion pressure data for neural network training with the concept of mutual information. Proceedings of the Institution of Mechanical Engineers, D Journal of Automobile Engineering, 2001, 215(2): 299–304.
[17] C Benneth, J F Dunne, S Trimby, et al. Engine cylinder pressure reconstruction using crank kinematics and recurrently-trained neural networks. Mechanical Systems and Signal Processing, 2017, 85: 126–145.
[18] B Maass, J Deng, R Stobart. In-cylinder pressure modeling with artificial neural networks. SAE Technical Paper, 2011-01-1417, 2011, 10.4271/2011-01-1417
[19] H S Sarae, H Taghavifar, S Jafarmadar. Experimental and numerical consideration of the effect of CeO2 nanoparticles on diesel engine performance and exhaust emission with the aid of artificial neural network. Applied Thermal Engineering, 2017, 113: 663–672.
[20] J M Luján, H Climent, L M García-Cuevas, et al. Volumetric efficiency modelling of internal combustion engines based on a novel adaptive learning algorithm of artificial neural networks. Applied Thermal Engineering, 2017, 123: 625–634.
[21] F Şahin. Effects of engine parameters on ionization current and modeling of excess air coefficient by artificial neural network. Applied Thermal Engineering, 2015, 90: 94–101.
[22] K Goudarzi, A Moosaei, M Gharaati. Applying artificial neural networks (ANN) to the estimation of thermal contact conductance in the exhaust valve of internal combustion engine. Applied Thermal Engineering, 2015, 87: 688–697.
[23] G S Atsalakis, K P Valavanis. Surveying stock market forecasting techniques – Part Ⅱ: Soft computing methods. Expert Systems with Applications, 2009, 36: 5932–5941.
[24] S Chakravarty, P K Dash. A PSO based integrated functional link net and interval type-2 fuzzy logic system for predicting stock market indices. Applied Soft Computing, 2012, 12: 931–941.
[25] J J Wang, J Z Wang, Z G Zhang, et al. Stock index forecasting based on a hybrid model. Omega, 2012, 40: 758–766.
[26] C J Lu, J Y Wu. An efficient CMAC neural network for stock index forecasting. Expert Systems with Applications, 2011, 38: 15194–15201.
[27] F A Oliveira, C N Nobre, L E Zarate. Applying artificial neural networks to prediction of stock price and improvement of the directional prediction index – Case study of PETR4, Petrobras, Brazil. Expert Systems with Applications, 2013, 40: 7596–7606.
[28] C Tantithamthavorn, A E Hassan. An empirical comparison of model validation techniques for defect prediction models. IEEE Transactions on Software Engineering, 2017, 43: 1–18.
[29] M Malliaris, L Salchenberger. A neural network model for estimating option prices. Journal of Applied Intelligence, 1993, 3: 193–206.
[30] D Enke, S Thawornwong. The use of data mining and neural networks for forecasting stock market returns. Expert Systems with Applications, 2005, 29: 927–940.
[31] G E Peterson, S R Aylward, W E Bond, et al. Using Taguchi's method of experimental design to control errors in layered perceptrons. IEEE Transactions on Neural Networks, 1995, 6: 949–961.
[32] H Shi, M Xu, Q Ma, et al. A whole system assessment of novel deep learning approach on short-term load forecasting. Energy Procedia, 2017, 142: 2791–2796.
[33] K G Lore, D Stoecklein, M Davies, et al. A deep learning framework for causal shape transformation. Neural Networks, 2018, 98: 305–317.
[34] Y Dai, G Wang. A deep inference learning framework for healthcare. Pattern Recognition Letters, 2020, 139: 17–25.
[35] D P Kingma, J L Ba. Adam: a method for stochastic optimization. Proceedings of 3rd International Conference on Learning Representations (ICLR), San Diego, CA, USA, May 7–9, 2015: 1–41.
Options
文章导航

/

〈 〉

版权所有 © 《Chinese Journal of Mechanical Engineering》编辑部

技术支持：北京玛格泰克科技发展有限公司