Development of optimal diesel injection strategy based on the prediction of performance and emissions using deep neural network

2021 ◽  
pp. 146808742110577
Author(s):  
Erdoğan Güner ◽  
Aliriza Kaleli ◽  
Kadir Bakirci ◽  
Mehmet Akif Ceviz
Keyword(s):  
Neural Network ◽  
Deep Neural Network ◽  
Operating Conditions ◽  
Exhaust Emission ◽  
Pilot Injection ◽  
Data Set ◽  
Injection Strategy ◽  
Wide Range ◽  
Performance And Emissions ◽  
Main Injection

This study aims to determine the optimal injection strategy by predicting the performance and exhaust emission parameters of a four-cylinder CRDI engine under several operating conditions. The experimental determination procedure is challenging and expensive calibration task since it requires a high number of tests. Many studies have focused on a limited level of parameters. In this study, design of experiments technique and deep neural network (DNN) modeling are used together. The experimental data set for the model is created using Taguchi L16 and L32 orthogonal arrays. The DNN model is developed to predict [Formula: see text], [Formula: see text], HC, and CO emissions with speed, torque, injection timings and fuel quantities of each injection called as pilot1, pilot2, main, and post. In this way, it has become possible to evaluate the effects of a larger number of operating parameters in a wide range than the literature. The developed DNN model predicts the [Formula: see text], [Formula: see text], HC, and CO with R2 0.939, 0.943, 0.963, and 0.966, respectively. Additionally, RMSE and MAE values for the model are between 0.024 and 0.048. The proposed method compared with the conventional look-up table method performs better in reducing the complexity and cost of experiments and exploration of the effects of injection parameters on engine emission and performance characteristics in a wide engine operating range. In conclusion, until 2300 rpm at specified torque (90 Nm), it is found that 70% of fuel quantity should inject in main injection to minimize [Formula: see text] and [Formula: see text] emissions. The post injection quantity should be increased by reducing the amount of main injection from this operating condition on. Furthermore, it is observed that the ratios of pilot injection durations do not change with increasing engine speed, but quantity of first pilot injection is more than that of second pilot injection.

Analysis of Pilot Injection Effects on Combustion Noise in PPCI Diesel Engines

2016 ◽  
Author(s):  
Long Liu ◽  
Hongzi Fei ◽  
Jingtao Du
Keyword(s):  
Diesel Engines ◽  
High Frequency ◽  
Combustion Process ◽  
High Load ◽  
Operating Conditions ◽  
Combustion Noise ◽  
Pilot Injection ◽  
Injection Strategy ◽  
Injection Quantity ◽  
Main Injection

With the common-rail fuel injection systems widely used in diesel engines, the pilot injection strategy has been paid more attention for suppressing pollutants emissions and combustion noise. Using pilot injection strategies, leaner and more homogenous mixture formed in pilot spray results in the combustion process partially fulfill Premixed Charge Compression Ignition (PCCI). Therefore the combustion process of diesel engines with pilot injection strategy can be considered as partial PCCI (PPCI). Pilot injection causes the in-cylinder temperature increase before main injection, which shortens the ignition delay of main spray and consequently reduces the combustion noise, so that the pilot injection has potential to extend PPCI combustion model to high load operation. However, the mechanism of pilot injection effects on the combustion noise has not been fully understood, consequently it is difficult to estimate the lower combustion noise among different pilot injection conditions, that results in difficult selection of the pilot injection parameters in proper way. Thus, in this study, experiments were performed on a single-cylinder DI-diesel engine with pilot and main injection under high load operating conditions. The synthesized in-cylinder pressure levels (CPLs) in different frequency ranges as a novel method were proposed to analyze the pilot injection effects on combustion noise. The results reveal that pilot spray combustion mainly influences the high frequency combustion noise, and the later pilot injection timing causes the higher combustion noise. In the case of the short dwell between pilot and main injection, the increasing pilot injection quantity enhances the high frequency combustion noise. Meanwhile because of the pilot injection quantity increase, decrease of main injection quantity leads to lower combustion noise in middle frequency range.

scholarly journals Modelling analysis of multiple diesel injection strategies with one-dimensional simulation coupled with artificial neural networks

2017 ◽  
Vol 21 (1 Part B) ◽  
pp. 413-425
Author(s):  
Orkun Ozener ◽  
Muammer Ozkan ◽  
Levent Yuksek
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Optimization Problems ◽  
Thermodynamic Simulation ◽  
Model Parameters ◽  
Pilot Injection ◽  
Injection Strategy ◽  
Diesel Injection ◽  
Main Injection ◽  
Artificial Neural

In the modern Diesel injection systems the phasing of injection in the same cycle gives a high flexibility to engineers from the perspective of engines performance and emission optimization. Basically, the injection is separated in to three phases: the pilot, main, and post injection phases. The focus of this study is based on pilot injection strategy implementation, which can be used for emission control effectively. In this work, reference main and pilot + main injection strategy experiments were realized in a modern Diesel engine. The logged data groups were used to model the engine at 1-D thermodynamic simulation AVL BOOST. In the second stage of this work, the engine operating points which are not realized at test bench are made run at BOOST programme. The new model parameters of simulation are identified with artificial neural network technique. The results showed that the implementation of appropriate mass of pilot injection at the appropriate injection advance will reduce the NOx emissions compared to reference main injection strategy. For reducing CO emissions the pilot injection mass should also be kept in the same range with higher injection pressure that can be achieved. Usage of 1-D simulation programme coupled with artificial neural network was found useful up to a certain extent especially for parametric analyses and optimization problems via with validation of calibration parameters at a huge experimental data.

scholarly journals An efficient technique for CT scan images classification of COVID-19

2020 ◽  
pp. 1-14
Author(s):  
Esraa Hassan ◽  
Noha A. Hikal ◽  
Samir Elmuogy
Keyword(s):  
Neural Network ◽  
Diagnostic Tool ◽  
Deep Neural Network ◽  
Data Augmentation ◽  
Performance Metrics ◽  
Classification Model ◽  
Data Set ◽  
Training Models ◽  
The Earth ◽  
Diagnostic Time

Nowadays, Coronavirus (COVID-19) considered one of the most critical pandemics in the earth. This is due its ability to spread rapidly between humans as well as animals. COVID_19 expected to outbreak around the world, around 70 % of the earth population might infected with COVID-19 in the incoming years. Therefore, an accurate and efficient diagnostic tool is highly required, which the main objective of our study. Manual classification was mainly used to detect different diseases, but it took too much time in addition to the probability of human errors. Automatic image classification reduces doctors diagnostic time, which could save human’s life. We propose an automatic classification architecture based on deep neural network called Worried Deep Neural Network (WDNN) model with transfer learning. Comparative analysis reveals that the proposed WDNN model outperforms by using three pre-training models: InceptionV3, ResNet50, and VGG19 in terms of various performance metrics. Due to the shortage of COVID-19 data set, data augmentation was used to increase the number of images in the positive class, then normalization used to make all images have the same size. Experimentation is done on COVID-19 dataset collected from different cases with total 2623 where (1573 training,524 validation,524 test). Our proposed model achieved 99,046, 98,684, 99,119, 98,90 In terms of Accuracy, precision, Recall, F-score, respectively. The results are compared with both the traditional machine learning methods and those using Convolutional Neural Networks (CNNs). The results demonstrate the ability of our classification model to use as an alternative of the current diagnostic tool.

scholarly journals Deep Neural Network for Gender-Based Violence Detection on Twitter Messages

Mathematics ◽  
2021 ◽  
Vol 9 (8) ◽  
pp. 807
Author(s):  
Carlos M. Castorena ◽  
Itzel M. Abundez ◽  
Roberto Alejo ◽  
Everardo E. Granda-Gutiérrez ◽  
Eréndira Rendón ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Neural Network ◽  
Gender Violence ◽  
Strategic Decision ◽  
Learning Approaches ◽  
Gender Based Violence ◽  
Data Set ◽  
Violence Detection ◽  
Governmental Institutions ◽  
Gender Based

The problem of gender-based violence in Mexico has been increased considerably. Many social associations and governmental institutions have addressed this problem in different ways. In the context of computer science, some effort has been developed to deal with this problem through the use of machine learning approaches to strengthen the strategic decision making. In this work, a deep learning neural network application to identify gender-based violence on Twitter messages is presented. A total of 1,857,450 messages (generated in Mexico) were downloaded from Twitter: 61,604 of them were manually tagged by human volunteers as negative, positive or neutral messages, to serve as training and test data sets. Results presented in this paper show the effectiveness of deep neural network (about 80% of the area under the receiver operating characteristic) in detection of gender violence on Twitter messages. The main contribution of this investigation is that the data set was minimally pre-processed (as a difference versus most state-of-the-art approaches). Thus, the original messages were converted into a numerical vector in accordance to the frequency of word’s appearance and only adverbs, conjunctions and prepositions were deleted (which occur very frequently in text and we think that these words do not contribute to discriminatory messages on Twitter). Finally, this work contributes to dealing with gender violence in Mexico, which is an issue that needs to be faced immediately.

Development of a Hybrid Artificial Neural Network and Genetic Algorithm Model for Regime Identification of Slurry Transport in Pipelines

2009 ◽  
Vol 4 (1) ◽  
Author(s):  
Sandip K Lahiri ◽  
Kartik Chandra Ghanta
Keyword(s):  
Neural Network ◽  
Genetic Algorithm ◽  
Artificial Neural Network ◽  
Operating Conditions ◽  
Misclassification Error ◽  
Wide Range ◽  
Artificial Neural ◽  
Artificial Neural Network Ann ◽  
Pipeline Design ◽  
Hybrid Artificial Neural Network

Four distinct regimes were found existent (namely sliding bed, saltation, heterogeneous suspension and homogeneous suspension) in slurry flow in pipeline depending upon the average velocity of flow. In the literature, few numbers of correlations has been proposed for identification of these regimes in slurry pipelines. Regime identification is important for slurry pipeline design as they are the prerequisite to apply different pressure drop correlation in different regime. However, available correlations fail to predict the regime over a wide range of conditions. Based on a databank of around 800 measurements collected from the open literature, a method has been proposed to identify the regime using artificial neural network (ANN) modeling. The method incorporates hybrid artificial neural network and genetic algorithm technique (ANN-GA) for efficient tuning of ANN meta parameters. Statistical analysis showed that the proposed method has an average misclassification error of 0.03%. A comparison with selected correlations in the literature showed that the developed ANN-GA method noticeably improved prediction of regime over a wide range of operating conditions, physical properties, and pipe diameters.

scholarly journals RISC-V Virtual Platform-Based Convolutional Neural Network Accelerator Implemented in SystemC

Electronics ◽  
2021 ◽  
Vol 10 (13) ◽  
pp. 1514
Author(s):  
Seung-Ho Lim ◽  
WoonSik William Suh ◽  
Jin-Young Kim ◽  
Sang-Young Cho
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Network Model ◽  
Neural Network Model ◽  
Deep Neural Network ◽  
System Level ◽  
Neural Network Models ◽  
Data Set ◽  
Embedded Device ◽  
Virtual Platform

The optimization for hardware processor and system for performing deep learning operations such as Convolutional Neural Networks (CNN) in resource limited embedded devices are recent active research area. In order to perform an optimized deep neural network model using the limited computational unit and memory of an embedded device, it is necessary to quickly apply various configurations of hardware modules to various deep neural network models and find the optimal combination. The Electronic System Level (ESL) Simulator based on SystemC is very useful for rapid hardware modeling and verification. In this paper, we designed and implemented a Deep Learning Accelerator (DLA) that performs Deep Neural Network (DNN) operation based on the RISC-V Virtual Platform implemented in SystemC in order to enable rapid and diverse analysis of deep learning operations in an embedded device based on the RISC-V processor, which is a recently emerging embedded processor. The developed RISC-V based DLA prototype can analyze the hardware requirements according to the CNN data set through the configuration of the CNN DLA architecture, and it is possible to run RISC-V compiled software on the platform, can perform a real neural network model like Darknet. We performed the Darknet CNN model on the developed DLA prototype, and confirmed that computational overhead and inference errors can be analyzed with the DLA prototype developed by analyzing the DLA architecture for various data sets.

Automatic Transmission Shift Calibration Based on Parallel-Modulated Neural Network (PMNN) Friction Component Model

2004 ◽  
Author(s):  
M. Cao ◽  
K. W. Wang ◽  
Y. Fujii ◽  
W. E. Tobler
Keyword(s):  
Neural Network ◽  
Controller Design ◽  
Automatic Transmission ◽  
Applied Pressure ◽  
Operating Conditions ◽  
Component Model ◽  
Powertrain System ◽  
Friction Component ◽  
Wide Range ◽  
Shift Dynamics

The parallel-modulated-neural-network (PMNN) -based friction component model [19] provides a simple pressure-torque formula, which possesses much improved scalability with respect to the applied pressure. In this paper, the PMNN friction component model is implemented within a comprehensive powertrain model, to simulate the shifting process of an automatic transmission (AT) system under various operating conditions. Simulation results demonstrate that the PMNN model can be effectively applied as a part of powertrain system model to accurately predict transmission shift dynamics. A pressure-profiling scheme through a quadratic polynomial pressure-torque relationship from the PMNN model is developed for the transmission shifting optimization. This scheme is implemented to improve the transmission shifting quality under certain operating conditions. The pressure profiling results illustrate that the proposed pressure profiling technique can be potentially applied to a wide range of operating conditions. This study demonstrates that the PMNN architecture not only outperforms the conventional network modeling techniques in accuracy and numerical efficiency, but is also a new tool for AT controller design.

Experimental Validation and Design Simulations of a Passive Two-Phase Cooling System for Datacenters

2020 ◽  
Author(s):  
Jackson B. Marcinichen ◽  
John R. Thome ◽  
Raffaele L. Amalfi ◽  
Filippo Cataldo
Keyword(s):  
Thermal Performance ◽  
Experimental Validation ◽  
Cooling System ◽  
Electronics Cooling ◽  
Operating Conditions ◽  
Two Phase ◽  
Data Set ◽  
Pressure Drops ◽  
Wide Range ◽  
Important Challenge

Abstract Thermosyphon cooling systems represent the future of datacenter cooling, and electronics cooling in general, as they provide high thermal performance, reliability and energy efficiency, as well as capture the heat at high temperatures suitable for many heat reuse applications. On the other hand, the design of passive two-phase thermosyphons is extremely challenging because of the complex physics involved in the boiling and condensation processes; in particular, the most important challenge is to accurately predict the flow rate in the thermosyphon and thus the thermal performance. This paper presents an experimental validation to assess the predictive capabilities of JJ Cooling Innovation’s thermosyphon simulator against one independent data set that includes a wide range of operating conditions and system sizes, i.e. thermosyphon data for server-level cooling gathered at Nokia Bell Labs. Comparison between test data and simulated results show good agreement, confirming that the simulator accurately predicts heat transfer performance and pressure drops in each individual component of a thermosyphon cooling system (cold plate, riser, evaporator, downcomer (with no fitting parameters), and eventually a liquid accumulator) coupled with operational characteristics and flow regimes. In addition, the simulator is able to design a single loop thermosyphon (e.g. for cooling a single server’s processor), as shown in this study, but also able to model more complex cooling architectures, where many thermosyphons at server-level and rack-level have to operate in parallel (e.g. for cooling an entire server rack). This task will be performed as future work.

scholarly journals Deep Neural Network Algorithm Feedback Model with Behavioral Intelligence and Forecast Accuracy

Symmetry ◽  
2020 ◽  
Vol 12 (9) ◽  
pp. 1465
Author(s):  
Taikyeong Jeong
Keyword(s):  
Neural Network ◽  
Classification Accuracy ◽  
Deep Neural Network ◽  
Time Series Data ◽  
Training Data ◽  
Series Data ◽  
Context Aware ◽  
Data Set ◽  
Feedback Model ◽  
Data Connection

When attempting to apply a large-scale database that holds the behavioral intelligence training data of deep neural networks, the classification accuracy of the artificial intelligence algorithm needs to reflect the behavioral characteristics of the individual. When a change in behavior is recognized, that is, a feedback model based on a data connection model is applied, an analysis of time series data is performed by extracting feature vectors and interpolating data in a deep neural network to overcome the limitations of the existing statistical analysis. Using the results of the first feedback model as inputs to the deep neural network and, furthermore, as the input values of the second feedback model, and interpolating the behavioral intelligence data, that is, context awareness and lifelog data, including physical activities, involves applying the most appropriate conditions. The results of this study show that this method effectively improves the accuracy of the artificial intelligence results. In this paper, through an experiment, after extracting the feature vector of a deep neural network and restoring the missing value, the classification accuracy was verified to improve by about 20% on average. At the same time, by adding behavioral intelligence data to the time series data, a new data connection model, the Deep Neural Network Feedback Model, was proposed, and it was verified that the classification accuracy can be improved by about 8 to 9% on average. Based on the hypothesis, the F (X′) = X model was applied to thoroughly classify the training data set and test data set to present a symmetrical balance between the data connection model and the context-aware data. In addition, behavioral activity data were extrapolated in terms of context-aware and forecasting perspectives to prove the results of the experiment.

scholarly journals RUL Prediction of Switched Mode Power Supply Using a Kalman Filter Assisted Deep Neural Network

Processes ◽  
2021 ◽  
Vol 10 (1) ◽  
pp. 55
Author(s):  
Jae Eon Kwon ◽  
Tanvir Alam Shifat ◽  
Akeem Bayo Kareem ◽  
Jang-Wook Hur
Keyword(s):  
Neural Network ◽  
Kalman Filter ◽  
Power Supply ◽  
Deep Neural Network ◽  
Short Term Memory ◽  
Input Voltage ◽  
Operating Conditions ◽  
Atmospheric Conditions ◽  
Diverse Range ◽  
Switched Mode Power Supply

Switched-mode power supply (SMPS) has been of vital importance majorly in power management of industrial equipment with much-improved efficiency and reliability. Given the diverse range on loading and operating conditions of SMPS, several anomalies can occur in the device resulting to over-voltage, overloading, erratic atmospheric conditions, etc. Electrical over-stress (EOS) is one of the commonly used causes of failure among power electronic devices. Since there is a limitation for the SMPS in terms of input voltage and current (two methods of controlling an SMPS), the device has been subjected to an accelerated aging test using EOS. This study presents a two-fold approach to evaluate the overall state of health of SMPS using an integration of extended Kalman filter (EKF) and deep neural network. Firstly, the EKF algorithm would assist in fusing fault features to acquire an comprehensive degradation trend. Secondly, the degradation pattern of the SMPS has been monitored for four different electrical loadings, and a bi-directional long short-term memory (BiLSTM) deep neural network is trained for future predictions. The proposed model provides a unique approach and accuracy in SMPS fault indication with the aid of electrical parameters.

Sign in / Sign up

Export Citation Format

Share Document