Diesel Engine Working Cycle Utilizing Artificial Intelligent Systems

2014 ◽  
Vol 490-491 ◽  
pp. 1057-1062
Author(s):  
Marwa Ahmed Abd-El Hamied
Keyword(s):  
Diesel Engine ◽  
Intelligent Systems ◽  
Intelligent System ◽  
Cylinder Pressure ◽  
Artificial Intelligent ◽  
Engine Model ◽  
Working Cycle ◽  
Proposed Model ◽  
A New Technique ◽  
Artificial Neural Network Ann

In this paper a new technique is designed to build a model concerning cylinder pressure in diesel engine. The concept is to build a working cycle model utilizing artificial intelligent system. Artificial Immunity System (AIS) and Artificial Neural Network (ANN) are proposed as a new approach that can be used to simulate cylinder pressure for different crankshaft speed and loads. Experimental test results of diesel engine model (AD3.152 UR) are used to train AIS system and ANN. The proposed model succeeded to provide reliable result and prove to be useful in evaluating the quality of working cycle in diesel engine.

Numerical and Experimental Study on the Impact of Mild Cold EGR on Exhaust Emissions in a Biodiesel Fueled Diesel Engine

2021 ◽  
Author(s):  
Alex Oliveira ◽  
Junfeng Yang ◽  
Jose Sodre
Keyword(s):  
Diesel Engine ◽  
Fuel Consumption ◽  
Exhaust Emissions ◽  
Pollutant Emissions ◽  
Cylinder Pressure ◽  
Nox Formation ◽  
Ratio Distribution ◽  
Engine Model ◽  
Gas Recirculation ◽  
The Impact

Abstract This work evaluated the effect of cooled exhaust gas recirculation (EGR) on fuel consumption and pollutant emissions from a diesel engine fueled with B8 (a blend of biodiesel and Diesel 8:92%% by volume), experimentally and numerically. Experiments were carried out on a Diesel power generator with varying loads from 5 kW to 35 kW and 10% of cold EGR ratio. Exhaust emissions (e.g. THC, NOX, CO etc.) were measured and evaluated. The results showed mild EGR and low biodiesel content have minor impact of engine specific fuel consumption, fuel conversion efficiency and in-cylinder pressure. Meanwhile, the combination of EGR and biodiesel reduced THC and NOX up to 52% and 59%, which shows promising effect on overcoming the PM-NOX trade-off from diesel engine. A 3D CFD engine model incorporated with detailed biodiesel combustion kinetics and NOx formation kinetics was validated against measured in-cylinder pressure, temperature and engine-out NO emission from diesel engine. This valid model was then employed to investigate the in-cylinder temperature and equivalence ratio distribution that predominate NOx formation. The results showed that the reduction of NOx emission by EGR and biodiesel is obtained by a little reduction of the local in-cylinder temperature and, mainly, by creating comparatively rich combusting mixture.

First Principle Based Control Oriented Gasoline Engine Model Including Lumped Cylinder Dynamics

2018 ◽  
Vol 140 (8) ◽  
Author(s):  
Ahmed Yar ◽  
A. I. Bhatti ◽  
Qadeer Ahmed
Keyword(s):  
Gasoline Engine ◽  
Angular Speed ◽  
Rigid Bodies ◽  
First Principle ◽  
Cylinder Pressure ◽  
Single Cylinder ◽  
Engine Model ◽  
Proposed Model ◽  
Engine Cylinder ◽  
Diagnostic Capabilities

A novel first principle based control oriented model of a gasoline engine is proposed which also carries diagnostic capabilities. Unlike existing control oriented models, the formulated model reflects dynamics of the faultless as well as faulty engine with high fidelity. In the proposed model, the torque production subsystem is obtained by integration of further two subsystems that is model of a single cylinder torque producing mechanism and an analytical gasoline engine cylinder pressure model. Model of a single cylinder torque producing mechanism is derived using constrained equation of motion (EOM) in Lagrangian mechanics. While cylinder pressure is evaluated using a closed form parametric analytical gasoline engine cylinder pressure model. Novel attributes of the proposed model include minimal usage of empirical relations and relatively wider region of model validity. Additionally, the model provides model based description of crankshaft angular speed fluctuations and tension in the rigid bodies. Capacity of the model to describe the system dynamics under fault conditions is elaborated with case study of an intermittent misfire condition. Model attains new capabilities based on the said novel attributes. The model is successfully validated against experimental data.

Prediction of International Stock Markets Based on Hybrid Intelligent Systems

2016 ◽  
pp. 110-124
Author(s):  
Salim Lahmiri
Keyword(s):  
Neural Networks ◽  
Time Delay ◽  
Stock Market ◽  
Intelligent Systems ◽  
Fuzzy Inference ◽  
Intelligent System ◽  
Market Price ◽  
Hybrid Intelligent Systems ◽  
Out Of Sample ◽  
Artificial Neural Network Ann

This paper compares the accuracy of three hybrid intelligent systems in forecasting ten international stock market indices; namely the CAC40, DAX, FTSE, Hang Seng, KOSPI, NASDAQ, NIKKEI, S&P500, Taiwan stock market price index, and the Canadian TSE. In particular, genetic algorithms (GA) are used to optimize the topology and parameters of the adaptive time delay neural networks (ATNN) and the time delay neural networks (TDNN). The third intelligent system is the adaptive neuro-fuzzy inference system (ANFIS) that basically integrates fuzzy logic into the artificial neural network (ANN) to better model information and explain decision making process. Based on out-of-sample simulation results, it was found that contrary to the literature GA-TDNN significantly outperforms GA-ATDNN. In addition, ANFIS was found to be more effective in forecasting CAC40, FTSE, Hang Seng, NIKKEI, Taiwan, and TSE price level. In contrary, GA-TDNN and GA-ATDNN were found to be superior to ANFIS in predicting DAX, KOSPI, and NASDAQ future prices.

scholarly journals Repeatability of High-Pressure Measurement in a Diesel Engine Test Bed

Sensors ◽  
2020 ◽  
Vol 20 (12) ◽  
pp. 3478 ◽  
Author(s):  
Tomasz Skrzek ◽  
Mirosław Rucki ◽  
Krzysztof Górski ◽  
Jonas Matijošius ◽  
Dalibor Barta ◽  
...  
Keyword(s):  
Diesel Engine ◽  
Pressure Measurement ◽  
Ignition Process ◽  
Engine Test ◽  
Cylinder Pressure ◽  
Test Bed ◽  
Working Cycle ◽  
Crank Angle ◽  
Maximal Pressure ◽  
Measured Pressure

This paper addresses the issue of metrological accuracy of instantaneous in-cylinder pressure measurement in a diesel engine test bed. In studies, the central unit has been the single-cylinder AVL 5402 engine. The pressure measurement was performed with a sensor designed for thermodynamic analysis, and the results were related to the crank angle, where two rotations corresponding to the four-stroke working cycle were denoted as angles between −360° and +360°. The novelty of this paper is the proposition of how to perform a type A uncertainty estimation of the in-cylinder pressure measurement and to assess its repeatability. It was demonstrated that repeatability of the measurement during the ignition process was difficult to estimate because of the phenomena that cannot ensure the repeatability conditions. To solve the problem, two methods were proposed. In one method, the pressure was measured in the subsequent cycles immediately after the ignition was turned off, and in another method, the engine was driven by a starter. The latter method provided maximal pressure values much lower than during usual tests. The obtained repeatability of measured pressure was %EV = 0.4%, which proved high capability of the evaluated measurement system.

scholarly journals Linguistic Ontologies: Designing and Using in the Educational Intellectual Systems

2021 ◽  
Vol 4 (1) ◽  
pp. 97-111
Author(s):  
Olha Tkachenko ◽  
Kostiantyn Tkachenko ◽  
Oleksandr Tkachenko
Keyword(s):  
Computer Networks ◽  
Intelligent Systems ◽  
Semantic Analysis ◽  
Intelligent System ◽  
Subject Area ◽  
Intellectual System ◽  
Proposed Model ◽  
Small Set ◽  
Ontological Model ◽  
Linguistic Ontology

The purpose of the article is to investigate and consider the general trends, problems and prospects of designing and using linguistic ontologies in educational intellectual systems. The research methodology consists in semantic analysis methods of the basic concepts in the considered subject area (linguistic ontologies in the educational intellectual systems). The article discusses approaches to the use of linguistic models in modern educational intelligent systems. The novelty of the research is the analysis of the linguistic ontologies use in the educational intellectual systems. Conclusions. A model of linguistic ontology for the domain (disciplines “Computer Networks” and “Modelling Systems”) is presented. This model is used in the development of an educational intellectual system that supports online learning in these disciplines. The proposed model describes a set of relations of linguistic ontology, specially selected to describe the analyzed domain. To ensure these properties, it was proposed to use a small set of relationships. The proposed linguistic ontological model is implemented in an educational intelligent system that supports such disciplines as “Computer Networks” and “Modelling Systems”.

Development of a real-time two-stroke marine diesel engine model with in-cylinder pressure prediction capability

2017 ◽  
Vol 194 ◽  
pp. 55-70 ◽  
Author(s):  
Yuanyuan Tang ◽  
Jundong Zhang ◽  
Huibing Gan ◽  
Baozhu Jia ◽  
Yu Xia
Keyword(s):  
Diesel Engine ◽  
Real Time ◽  
Marine Diesel Engine ◽  
Cylinder Pressure ◽  
Engine Model ◽  
Marine Diesel ◽  
Prediction Capability

scholarly journals A Diesel Engine Modelling Approach for Ship Propulsion Real-Time Simulators

2019 ◽  
Vol 7 (5) ◽  
pp. 138 ◽  
Author(s):  
Marco Altosole ◽  
Ugo Campora ◽  
Massimo Figari ◽  
Michele Laviola ◽  
Michele Martelli
Keyword(s):  
Diesel Engine ◽  
Real Time ◽  
High Speed ◽  
Computation Time ◽  
Engine Model ◽  
Time Simulation ◽  
Proposed Model ◽  
Marine Diesel ◽  
Acceleration And Deceleration ◽  
Engine Components

A turbocharged diesel engine numerical model, suitable for real-time ship manoeuvre simulation, is presented in this paper. While some engine components (mainly the turbocharger, intercooler and manifolds) are modelled by a filling and emptying approach, the cylinder simulation is based on a set of five-dimensional numerical matrices (each matrix is generated by means of a more traditional thermodynamic model based on in-cylinder actual cycle). The new cylinder calculation approach strongly reduces the engine transient computation time, making it possible to transform the simulation model into a real-time executable application. As a case study, the simulation methodology is applied to a high speed four stroke turbocharged marine diesel engine, whose design and off design running data are available from the technical sheet. In order to verify the suitability of the proposed model in real-time simulation applications, a yacht propulsion plant simulator is developed. Numerical results in ship acceleration and deceleration manoeuvres are shown, reducing the simulation running time of 99% in comparison with the corresponding in-cylinder actual cycle engine model.

scholarly journals Weather Modeling Using Data-Driven Adaptive Rough-Neuro-Fuzzy Approach

2017 ◽  
Vol 12 (2) ◽  
pp. 429-435
Author(s):  
M. Sudha
Keyword(s):  
Intelligent Systems ◽  
Prediction Accuracy ◽  
Intelligent System ◽  
Data Driven ◽  
Fuzzy Approach ◽  
Neuro Fuzzy ◽  
Proposed Model ◽  
Hybrid Data ◽  
Weather Modeling ◽  
Using Data

Recently, hybrid data-driven models have become appropriate predictive patterns in various hydrological forecast scenarios. Especially, meteorology has witnessed that there is a need for a much better approach to handle weather-related parameters intelligently. To handle this challenging issue, this research intends to apply the fuzzy and ANN theories for developing hybridized adaptive rough-neuro-fuzzy intelligent system. . Assimilating the features of ANN and FIS has attracted the rising attention of researchers due to the growing requisite of adaptive intelligent systems to solve the real world requirements. The proposed model is capable of handling soft rule boundaries and linguistic variables to improve the prediction accuracy. The adaptive rough-neuro-fuzzy approach attained an enhanced prediction accuracy of 95.49 % and outperformed the existing techniques.

scholarly journals Modelling and Prediction of Particulate Matter,NOx, and Performance of a Diesel Vehicle Engine under Rare Data Using Relevance Vector Machine

2012 ◽  
Vol 2012 ◽  
pp. 1-9 ◽  
Author(s):  
Ka In Wong ◽  
Pak Kin Wong ◽  
Chun Shun Cheung
Keyword(s):  
Particulate Matter ◽  
Diesel Engine ◽  
Engine Performance ◽  
Optimal Solution ◽  
Relevance Vector Machine ◽  
Training Data ◽  
Coolant Temperature ◽  
Model Accuracy ◽  
Engine Model ◽  
Artificial Neural Network Ann

Traditionally, the performance maps and emissions of a diesel engine are obtained empirically through many testes on the dynamometers because no exact mathematical engine model exists. In the current literature, many artificial-neural-network- (ANN-) based approaches have been developed for diesel engine modelling. However, the drawbacks of ANN would make itself difficult to be put into some practices including multiple local minima, user burden on selection of optimal network structure, large training data size, and overfitting risk. To overcome the drawbacks, this paper proposes to apply one emerging technique, relevance vector machine (RVM), to model the diesel engine, and to predict the emissions and engine performance. With RVM, only a few experimental data sets can train the model due to the property of global optimal solution. In this study, the engine speed, load, and coolant temperature are used as the input parameters, while the brake thermal efficiency, brake-specific fuel consumption, concentrations of nitrogen oxides, and particulate matter are used as the output parameters. Experimental results show the model accuracy is fairly good even the training data is scarce. Moreover, the model accuracy is compared with that using typical ANN. Evaluation results also show that RVM is superior to typical ANN approach.

Prediction of International Stock Markets Based on Hybrid Intelligent Systems

2016 ◽  
pp. 1651-1667
Author(s):  
Salim Lahmiri
Keyword(s):  
Neural Networks ◽  
Time Delay ◽  
Stock Market ◽  
Intelligent Systems ◽  
Fuzzy Inference ◽  
Intelligent System ◽  
Market Price ◽  
Hybrid Intelligent Systems ◽  
Out Of Sample ◽  
Artificial Neural Network Ann

This paper compares the accuracy of three hybrid intelligent systems in forecasting ten international stock market indices; namely the CAC40, DAX, FTSE, Hang Seng, KOSPI, NASDAQ, NIKKEI, S&P500, Taiwan stock market price index, and the Canadian TSE. In particular, genetic algorithms (GA) are used to optimize the topology and parameters of the adaptive time delay neural networks (ATNN) and the time delay neural networks (TDNN). The third intelligent system is the adaptive neuro-fuzzy inference system (ANFIS) that basically integrates fuzzy logic into the artificial neural network (ANN) to better model information and explain decision making process. Based on out-of-sample simulation results, it was found that contrary to the literature GA-TDNN significantly outperforms GA-ATDNN. In addition, ANFIS was found to be more effective in forecasting CAC40, FTSE, Hang Seng, NIKKEI, Taiwan, and TSE price level. In contrary, GA-TDNN and GA-ATDNN were found to be superior to ANFIS in predicting DAX, KOSPI, and NASDAQ future prices.

Sign in / Sign up

Export Citation Format

Share Document