Misfire detection of diesel engine based on convolutional neural networks

2021 ◽  
pp. 095440702098707
Author(s):  
Pan Zhang ◽  
Wenzhi Gao ◽  
Yong Li ◽  
Yanjun Wang
Keyword(s):  
Neural Networks ◽  
Diesel Engine ◽  
Convolutional Neural Networks ◽  
Adaptive Design ◽  
Detection Algorithm ◽  
Operating Conditions ◽  
Exhaust Emission ◽  
Emission Standard ◽  
Network Training ◽  
Misfire Detection

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.

DTCNNMI: A deep twin convolutional neural networks with multi-domain inputs for strongly noisy diesel engine misfire detection

Measurement ◽  
2021 ◽  
pp. 109548
Author(s):  
Chengjin Qin ◽  
Yanrui Jin ◽  
Jianfeng Tao ◽  
Dengyu Xiao ◽  
Honggan Yu ◽  
...  
Keyword(s):  
Neural Networks ◽  
Diesel Engine ◽  
Convolutional Neural Networks ◽  
Misfire Detection

scholarly journals Generation and Annotation of Simulation-Real Ship Images for Convolutional Neural Networks Training and Testing

2021 ◽  
Vol 11 (13) ◽  
pp. 5931
Author(s):  
Ji’an You ◽  
Zhaozheng Hu ◽  
Chao Peng ◽  
Zhiqiang Wang
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Image Annotation ◽  
Three Dimensional ◽  
Image Data ◽  
Detection Algorithm ◽  
Simulation Software ◽  
High Quality ◽  
Annotation Method ◽  
Detection Of Objects

Large amounts of high-quality image data are the basis and premise of the high accuracy detection of objects in the field of convolutional neural networks (CNN). It is challenging to collect various high-quality ship image data based on the marine environment. A novel method based on CNN is proposed to generate a large number of high-quality ship images to address this. We obtained ship images with different perspectives and different sizes by adjusting the ships’ postures and sizes in three-dimensional (3D) simulation software, then 3D ship data were transformed into 2D ship image according to the principle of pinhole imaging. We selected specific experimental scenes as background images, and the target ships of the 2D ship images were superimposed onto the background images to generate “Simulation–Real” ship images (named SRS images hereafter). Additionally, an image annotation method based on SRS images was designed. Finally, the target detection algorithm based on CNN was used to train and test the generated SRS images. The proposed method is suitable for generating a large number of high-quality ship image samples and annotation data of corresponding ship images quickly to significantly improve the accuracy of ship detection. The annotation method proposed is superior to the annotation methods that label images with the image annotation software of Label-me and Label-img in terms of labeling the SRS images.

scholarly journals Illumination-robust face recognition based on deep convolutional neural networks architectures

2020 ◽  
Vol 18 (2) ◽  
pp. 1015
Author(s):  
Ridha Ilyas Bendjillali ◽  
Mohammed Beladgham ◽  
Khaled Merit ◽  
Abdelmalik Taleb-Ahmed
Keyword(s):  
Neural Networks ◽  
Face Recognition ◽  
Convolutional Neural Networks ◽  
Feature Learning ◽  
Histogram Equalization ◽  
Detection Algorithm ◽  
Deep Convolutional Neural Networks ◽  
Biometric Technology ◽  
Equalization Algorithm ◽  
Robust Face Recognition

<p><span>In the last decade, facial recognition techniques are considered the most important fields of research in biometric technology. In this research paper, we present a Face Recognition (FR) system divided into three steps: The Viola-Jones face detection algorithm, facial image enhancement using Modified Contrast Limited Adaptive Histogram Equalization algorithm (M-CLAHE), and feature learning for classification. For learning the features followed by classification we used VGG16, ResNet50 and Inception-v3 Convolutional Neural Networks (CNN) architectures for the proposed system. Our experimental work was performed on the Extended Yale B database and CMU PIE face database. Finally, the comparison with the other methods on both databases shows the robustness and effectiveness of the proposed approach. Where the Inception-v3 architecture has achieved a rate of 99, 44% and 99, 89% respectively.</span></p>

Robust PPG Peak Detection Using Dilated Convolutional Neural Networks

2021 ◽  
Author(s):  
Kianoosh Kazemi ◽  
Juho Laitala ◽  
Iman Azimi ◽  
Pasi Liljeberg ◽  
Amir M. Rahmani
Keyword(s):  
Neural Networks ◽  
Heart Rate ◽  
Convolutional Neural Networks ◽  
Signal To Noise Ratio ◽  
Motion Artifact ◽  
Detection Algorithm ◽  
Peak Detection ◽  
Detection Methods ◽  
Method Performance ◽  
Data Generator

<div>Accurate peak determination from noise-corrupted photoplethysmogram (PPG) signal is the basis for further analysis of physiological quantities such as heart rate and heart rate variability. In the past decades, many methods have been proposed to provide reliable peak detection. These peak detection methods include rule-based algorithms, adaptive thresholds, and signal processing techniques. However, they are designed for noise-free PPG signals and are insufficient for PPG signals with low signal-to-noise ratio (SNR). This paper focuses on enhancing PPG noise-resiliency and proposes a robust peak detection algorithm for noise and motion artifact corrupted PPG signals. Our algorithm is based on Convolutional Neural Networks (CNN) with dilated convolutions. Using dilated convolutions provides a large receptive field, making our CNN model robust at time series processing. In this study, we use a dataset collected from wearable devices in health monitoring under free-living conditions. In addition, a data generator is developed for producing noisy PPG data used for training the network. The method performance is compared against other state-of-the-art methods and tested in SNRs ranging from 0 to 45 dB. Our method obtains better accuracy in all the SNRs, compared with the existing adaptive threshold and transform-based methods. The proposed method shows an overall precision, recall, and F1-score 80%, 80%, and 80% in all the SNR ranges. However, these figures for the other methods are below 78%, 77%, and 77%, respectively. The proposed method proves to be accurate for detecting PPG peaks even in the presence of noise.</div>

scholarly journals Robust Real-Time Detection of Laparoscopic Instruments in Robot Surgery Using Convolutional Neural Networks with Motion Vector Prediction

2019 ◽  
Vol 9 (14) ◽  
pp. 2865 ◽  
Author(s):  
Kyungmin Jo ◽  
Yuna Choi ◽  
Jaesoon Choi ◽  
Jong Woo Chung
Keyword(s):  
Neural Networks ◽  
Real Time ◽  
Convolutional Neural Networks ◽  
Detection System ◽  
Motion Vector ◽  
Detection Algorithm ◽  
Surgical Instruments ◽  
The Mean ◽  
Real Time Detection ◽  
Motion Vector Prediction

More than half of post-operative complications can be prevented, and operation performances can be improved based on the feedback gathered from operations or notifications of the risks during operations in real time. However, existing surgical analysis methods are limited, because they involve time-consuming processes and subjective opinions. Therefore, the detection of surgical instruments is necessary for (a) conducting objective analyses, or (b) providing risk notifications associated with a surgical procedure in real time. We propose a new real-time detection algorithm for detection of surgical instruments using convolutional neural networks (CNNs). This algorithm is based on an object detection system YOLO9000 and ensures continuity of detection of the surgical tools in successive imaging frames based on motion vector prediction. This method exhibits a constant performance irrespective of a surgical instrument class, while the mean average precision (mAP) of all the tools is 84.7, with a speed of 38 frames per second (FPS).

Development of a Torsional Behavior Powertrain Model for Multiple Misfire Detection

2005 ◽  
Author(s):  
Fabrizio Ponti
Keyword(s):  
Torsional Vibration ◽  
Engine Speed ◽  
Experimental Tests ◽  
Detection Algorithm ◽  
Operating Conditions ◽  
False Alarms ◽  
Time Interval ◽  
Short Time Interval ◽  
Torsional Behavior ◽  
Misfire Detection

Many methodologies have been developed in the past for misfire detection purposes based on the analysis of the instantaneous engine speed. The missing combustion is usually detected thanks to the sudden engine speed decrease that takes place after a misfire event. Misfire detection and in particular cylinder isolation is anyhow still a challenging issue for engines with a high number of cylinders, for engine operating conditions at low load or high engine speed and for multiple misfire events. When a misfire event takes place in fact a torsional vibration is excited and shows up in the instantaneous engine speed waveform. If a multiple misfire occurs this torsional vibration is excited more than once in a very short time interval. The interaction among these successive vibrations can generate false alarms or misdetection, and an increased complexity when dealing with cylinder isolation. The paper presents the development of a powertrain torsional behavior model in order to identify the effects of a misfire event on the instantaneous engine speed signal. The identified waveform has then been used to filter out the torsional vibration effects in order to enlighten the missing combustions even in the case of multiple misfire events. The model response is also used to quicken the setup process for the detection algorithm employed, evaluating before running specific experimental tests on a test bench facility, the values for the threshold and the optimal setup of the procedure. The proposed algorithm is developed in this paper for an SI L4 engine; Its application to other engine configurations is possible, as it is also discussed in the paper.

scholarly journals Research on the effectiveness of alternative propulsion sources in high-tonnage cargo transport

2021 ◽  
Vol 60 (4) ◽  
pp. 259-273
Author(s):  
Mariusz Wasiak ◽  
Piotr Zdanowicz ◽  
Marcin Nivette
Keyword(s):  
Carbon Dioxide Emissions ◽  
Economic Assessment ◽  
Road Transport ◽  
Operating Conditions ◽  
Environmental Benefits ◽  
Total Carbon ◽  
Transport Sector ◽  
Exhaust Emission ◽  
Emission Standard ◽  
The Eu

The progressive degradation of the environment makes implementing pro-ecological solutions in various areas of our lives more meaningful. These measures also apply to transport, responsible for around 30% of total carbon dioxide emissions in the EU. Implementing ecological solutions in road transport encounters various barriers resulting mainly from the specificity of transport tasks. One of the most promising solutions in the high-tonnage road transport sector seems to be LNG-fueled engines, which allow for similar operating conditions to traditional combustion vehicles. The article aims to identify the environmental benefits of the use of high-tonnage LNG-fueled vehicles in freight transport and to conduct a comprehensive assessment of the economic efficiency of this solution. The article assesses the effectiveness of using an LNG-fueled vehicle and a diesel-fueled vehicle that meets the highest exhaust emission standard in high-tonnage transport, both in terms of economy and an impact of these solutions on the environment. The research was carried out on a given route, taking into account variants of vehicle manning and simulations of transport cycle time. In conclusion, a discussion of the obtained results was carried out, emphasizing the factors determining the profitability of using high-tonnage vehicles with LNG drive or its lack. Regardless of the indicated lack of clarity in the economic assessment of the effectiveness of LNG drives in high-tonnage vehicles, the identified environmental benefits from implementing these solutions seem to be quite unequivocal. Thus, it should be expected that in the event of loss of economic competitiveness of these solutions, appropriate fiscal instruments should be used - especially since LNG drives in the policies of individual countries are considered pro-ecological solutions.

scholarly journals Aerial Images Processing for Car Detection using Convolutional Neural Networks: Comparison between Faster R-CNN and YoloV3

2019 ◽  
Author(s):  
Adel Ammar ◽  
Anis Koubaa ◽  
Mohanned Ahmed ◽  
Abdulrahman Saad
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
State Of The Art ◽  
Detection Algorithm ◽  
Aerial Images ◽  
Object Size ◽  
Car Detection ◽  
Images Processing ◽  
Different Characteristics ◽  
The Impact

In this paper, we address the problem of car detection from aerial images using Convolutional Neural Networks (CNN). This problem presents additional challenges as compared to car (or any object) detection from ground images because features of vehicles from aerial images are more difficult to discern. To investigate this issue, we assess the performance of two state-of-the-art CNN algorithms, namely Faster R-CNN, which is the most popular region-based algorithm, and YOLOv3, which is known to be the fastest detection algorithm. We analyze two datasets with different characteristics to check the impact of various factors, such as UAV&rsquo;s altitude, camera resolution, and object size. The objective of this work is to conduct a robust comparison between these two cutting-edge algorithms. By using a variety of metrics, we show that none of the two algorithms outperforms the other in all cases.

Sign in / Sign up

Export Citation Format

Share Document