Citation: Wang, X.; Zhang, P.;
Gao, W.; Li, Y.; Wang, Y.; Pang, H.
Misfire Detection Using Crank Speed
and Long Short-Term Memory
Recurrent Neural Network. Energies
2022, 15, 300. https://doi.org/
10.3390/en15010300
Academic Editors: Luis
Hernández-Callejo, Sergio
Nesmachnow and Sara Gallardo
Saavedra
Received: 26 November 2021
Accepted: 29 December 2021
Published: 3 January 2022
Publisher’s Note: MDPI stays neutral
with regard to jurisdictional claims in
published maps and institutional affil-
iations.
Copyright: © 2022 by the authors.
Licensee MDPI, Basel, Switzerland.
This article is an open access article
distributed under the terms and
conditions of the Creative Commons
Attribution (CC BY) license (https://
creativecommons.org/licenses/by/
4.0/).
Article
Misfire Detection Using Crank Speed and Long Short-Term
Memory Recurrent Neural Network
Xinwei Wang
1,2
, Pan Zhang
3
, Wenzhi Gao
3,
*, Yong Li
3
, Yanjun Wang
3
and Haoqian Pang
3
1
State Key Laboratory of Engine Reliability, Weifang 261061, China; wangxinw@weichai.com
2
Weichai Power Co., Ltd., Weifang 261061, China
3
State Key Laboratory of Engines, Tianjin University, Tianjin 300350, China; zhangpan@tju.edu.cn (P.Z.);
li_yong@tju.edu.cn (Y.L.); wangyanjunz@tju.edu.cn (Y.W.); panghaoqian199817@gmail.com (H.P.)
* Correspondence: gaowenzhi@tju.edu.cn
Abstract:
In this work, a new approach was developed for the detection of engine misfire based
on the long short-term memory recurrent neural network (LSTM RNN) using crank speed signal.
The datasets are acquired from a six-cylinder-inline, turbo-charged diesel engine. Previous works
investigated misfire detection in a limited range of engine running speed, running load or misfire
types. In this work, the misfire patterns consist of normal condition, six types of one-cylinder misfire
faults and fifteen types of two-cylinder misfire faults. All the misfire patterns are tested under wide
range of running conditions of the tested engine. The traditional misfire detection method is tested
on the datasets first, and the result show its limitation on high-speed low-load conditions. The LSTM
RNN is a type of artificial neural network which has the ability of considering both the current
input in-formation and the previous input information; hence it is helpful in extracting features of
crank speed in which the misfire-induced speed fluctuation will last one or a few cycles. In order
to select the engine operating conditions for network training properly, five data division strategies
are attempted. For the sake of acquiring high performance of designed network, four types of
network structure are tested. The results show that, utilizing the datasets in this work, the LSTM
RNN based algorithm can overcome the limitation at high-speed low-load conditions of traditional
misfire detection method. Moreover, the network which takes fixed segment of raw speed signal as
input and takes misfire or fault-free labels as output achieves the best performance with the misfire
diagnosis accuracy not less than 99.90%.
Keywords: engine misfire; pattern recognition; fault detection; LSTM; time-frequency analysis
1. Introduction
Engine misfire is a phenomenon of no-burning in cylinder which may be caused by
insufficient fuel injection, bad fuel quality, insufficient ignition energy, or mechanical failure,
etc. Since misfire fault will cause abnormal engine running condition and air pollution,
many researchers have been trying to put forward effective methods to achieve accurate
and real-time misfire detection.
The techniques for engine misfire detection can be categorized according to the utilized
sensor signals, which includes the method using engine body vibration signal [
1
], the
method using acoustic signal [
2
], the method analyzing exhaust gas temperature [
3
], the
method monitoring in-cylinder iron current [
4
], and the method using crank speed [
5
].
The method using engine body vibration signal could sample much information, since the
vibration signal is sampled with high resolution and is related to in-cylinder combustion.
However, a large amount of computation is required for processing vibration data. The
method using acoustic signal has not solved the problem of noise interference in practical
implementation. The method analyzing the temperature of exhaust gas is limited by the
sensor’s response time. The method monitoring in-cylinder iron current needs to modify
Energies 2022, 15, 300. https://doi.org/10.3390/en15010300 https://www.mdpi.com/journal/energies
