Study on observation method of injection pressure curve in high pressure common rail system

Abstract

The performance of the diesel engine was determined by the injection pressure of the high pressure common rail system. The observation method of the injection pressure curve was of great value in evaluating the operating conditions of the diesel engine. However, the observation method could make it impossible to directly observe the injection pressure data on a high pressure common rail system in operation. In this paper, common rail pressure signals and control pulse widths, which were easy to collect, were used as the basis for proposing a GRU (Gated Recurrent Unit) based model for the observation of injection pressure curves of high pressure common rail system in order to solve the above problem. The accuracy and precision of the model was verified by the experiments and compared with commonly used simulation models. From the results, it was concluded that the overall accuracy of the injection pressure curve observation was similar to that of the simulation model, but the accuracy was higher around the peak of the injection pressure, as well as the equipment requirement was low and the calculation speed was fast. The mean EMD of the curvilinear observation model of injection pressure of high pressure common rail system is similar to that of the 1D simulation model, with 37.88 and 33.62 respectively. The overall difference in injection pressure between the two models is similar with 53.62 and 54.23 MPa respectively. On the same computing platform, the average computation time of the test set containing five states is 0.0113 s, and the simulation time of each running state is 12951.6 s using AMESim software.

Keywords

High pressure common rail system long short-term memory gated recurrent unit injection pressure observation method

Get full access to this article

View all access options for this article.

References

Bai

Lan

Fan

Liu

Investigation on the fuel injection stability of high pressure common rail system for diesel engines. Int J Engine Res 2021; 22(2): 616–631.

Ferrari

Pizzo

Fully predictive common rail fuel injection apparatus model and its application to global system dynamics analyses. Int J Engine Res 2017; 18(3): 273–290.

Hofmann

Schuckert

Wachtmeister

, et al. Optimal injection strategies to compensate for injector aging in common rail fuel systems. SAE technical paper 2018-01-1160, 2018.

Sun

Wang

Gao

Wang

Effects of structure parameters on the static electromagnetic characteristics of solenoid valve for an electronic unit pump. Energy Convers Manag 2016; 113(1): 119–130.

Napolitano

Guido

Beatrice

Ciaravino

Analysis of nozzle coking impact on emissions and performance of a Euro5 automotive diesel engine. SAE Int J Engines 2013; 6(3): 1801–1813.

Zhao

Xin

Simulating analysis of responding time of high pressure common rail injector. Comput Simul 2014; 31(11): 231–235.

Herfatmanesh

Peng

Ihracska

Lin

Zhang

Characteristics of pressure wave in common rail fuel injection system of high-speed direct injection diesel engines. Adv Mech Eng 2016; 8(5): 1–8.

Ferrari

Paolicelli

An indirect method for the real-time evaluation of the fuel mass injected in small injections in common rail diesel engines. Fuel 2017; 191(1): 322–329.

Ferrari

Salvo

Determination of the transfer function between the injected flow-rate and high-pressure time histories for improved control of common rail diesel engines. Int J Engine Res 2017; 18(3): 212–225.

10.

Lipton

Berkowitz

Elkan

CA.

A critical review of recurrent neural networks for sequence learning. Comput Sci 2015; 215: 15–25.

11.

Elman

JL.

Finding structure in time. Cognit Sci 1990; 14(2) 179-211.

12.

Jordan

MI.

Attractor dynamics and parallelism in a connectionist sequential machine. In: IEEE Computer Society Neural Networks Technology Series 1990, pp.112–127.

13.

Chen

Soo

. A comparative study of recurrent neural network architectures on learning temporal sequences. In: Proceedings of IEEE international conference on neural networks, Washington, DC, 1996, pp.1945–1950. New York: IEEE.

14.

Zhao

Jin

Wang

YZ.

A review of small sample learning research. Journal of Software 2021; 32(2): 349–369.

15.

Schuster

Paliwal

KK.

Bidirectional recurrent neural networks. IEEE Trans Signal Process 1997; 45(11): 2673–2681.

16.

Hochreiter

Schmidhuber

Long short-term memory. Neural Comput 1997; 9(8): 1735–1780.

17.

Smith

Williams

Linking the physical manifestation and performance effects of injector nozzle deposits in modern diesel engines. SAE Int J Fuel Lubr 2015; 8(2): 344–357.

18.

Zhang

Tian

Wen

Yang

Rao

Deep fault diagnosis for rotating machinery with scarce labeled samples. Chin J Electron 2020; 29(4): 693–704.

19.

Nikravan

Parsa

Hybrid adaptive random testing. Int J Comput Sci Math 2020; 11(3): 209–258.

20.

Zhou

Sun

Liu

, et al. AC-LSTM neural network for text classification. Computer Science 2015; 1(4): 39–44.

21.

Rahman

Mohammed

Azad

A new LSTM model by introducing biological cell state. In: 2016 3rd international conference on electrical engineering and information communication technology, Dhaka, Bangladesh, 2016, pp.1–6. New York: IEEE.

22.

Pulver

Lyu

LSTM with working memory. In: International joint conference on neural networks, Piscataway, NJ, 2017, pp.845–851. New York: IEEE.

23.

LY.

Research on fault diagnosis of diesel engine high pressure common rail system. Taiyuan: North University of China, 2022.

24.

Research on the observation method of fuel injection performance of high pressure common rail system. Taiyuan: North University of China, 2022.

25.

Tiexiong

Research on a small sample fault diagnosis method for a high-pressure common rail system. Adv Mech Eng 2021; 13(9): 1–20.