Experiment analysis and computational optimization of the Atkinson cycle gasoline engine through NSGA Ⅱ algorithm using machine learning

2021 ◽  
Vol 238 ◽  
pp. 113871
Author(s):  
Ji Tong ◽  
Yangyang Li ◽  
Jingping Liu ◽  
Ran Cheng ◽  
Jinhuan Guan ◽  
...  
Keyword(s):  
Machine Learning ◽  
Gasoline Engine ◽  
Computational Optimization ◽  
Atkinson Cycle ◽  
Experiment Analysis

scholarly journals Implementation of modified SARSA learning technique in EMCAP

2017 ◽  
Vol 7 (1.5) ◽  
pp. 274
Author(s):  
D. Ganesha ◽  
Vijayakumar Maragal Venkatamuni
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Decision Process ◽  
Learning Algorithm ◽  
Research Work ◽  
Learning System ◽  
State Action ◽  
Learning Technique ◽  
Markov Decision ◽  
Experiment Analysis

This research work presents analysis of Modified Sarsa learning algorithm. Modified Sarsa algorithm.  State-Action-Reward-State-Action (SARSA) is an technique for learning a Markov decision process (MDP) strategy, used in for reinforcement learning int the field of artificial intelligence (AI) and machine learning (ML). The Modified SARSA Algorithm makes better actions to get better rewards.  Experiment are conducted to evaluate the performace for each agent individually. For result comparison among different agent, the same statistics were collected. This work considered varied kind of agents in different level of architecture for experiment analysis. The Fungus world testbed has been considered for experiment which is has been implemented using SwI-Prolog 5.4.6. The fixed obstructs tend to be more versatile, to make a location that is specific to Fungus world testbed environment. The various parameters are introduced in an environment to test a agent’s performance. This modified   SARSA learning algorithm can   be more suitable in EMCAP architecture.  The experiments are conducted the modified   SARSA Learning system gets   more rewards compare to existing  SARSA algorithm.

Investigations of Atkinson Cycle Converted from Conventional Otto Cycle Gasoline Engine

2016 ◽  
Author(s):  
Renhua Feng ◽  
Yangtao Li ◽  
Jing Yang ◽  
Jianqin FU ◽  
Daming Zhang ◽  
...  
Keyword(s):  
Gasoline Engine ◽  
Otto Cycle ◽  
Atkinson Cycle

An Experiment Analysis on Tracking and Detecting the Vehicle Speed using Machine Learning and IOT

2021 ◽  
Author(s):  
Hari Shruthi T K ◽  
Hema Latha A ◽  
Jothi Lakshmi M ◽  
Dinesh Kumar J R ◽  
Ganesh Babu C ◽  
...  
Keyword(s):  
Machine Learning ◽  
Vehicle Speed ◽  
Experiment Analysis

Design, Development, and Evaluation of a Control Framework for an Atkinson Cycle Engine

2017 ◽  
Vol 140 (5) ◽  
Author(s):  
G. Murtaza ◽  
A. I. Bhatti ◽  
Q. Ahmed
Keyword(s):  
Fuel Economy ◽  
Gasoline Engine ◽  
Thermodynamic Cycle ◽  
Mean Value ◽  
Operating Conditions ◽  
Intake Valve ◽  
Design Development ◽  
Engine Model ◽  
Atkinson Cycle ◽  
Control Framework

The efficiency of the spark ignition (SI) engine degrades while working at part loads. It can be optimally dealt with a slightly different thermodynamic cycle termed as an Atkinson cycle. It can be implemented in the conventional SI engines by incorporating advanced mechanisms as variable valve timing (VVT) and variable compression ratio (VCR). In this research, a control framework for the Atkinson cycle engine with flexible intake valve load control strategy is designed and developed. The control framework based on the extended mean value engine model (EMVEM) of the Atkinson cycle engine is evaluated in the view of fuel economy at the medium and higher load operating conditions for the standard new European driving cycle (NEDC), federal urban driving schedule (FUDS), and federal highway driving schedule (FHDS) cycles. In this context, the authors have already proposed a control-oriented EMVEM model of the Atkinson cycle engine with variable intake valve actuation. To demonstrate the potential benefits of the VCR Atkinson cycle VVT engine, for the various driving cycles, in the presence of auxiliary loads and uncertain road loads, its EMVEM model is simulated by using a controller having similar specifications as that of the conventional gasoline engine. The simulation results point toward the significant reduction in engine part load losses and improvement in the thermal efficiency. Consequently, considerable enhancement in the fuel economy of the VCR Atkinson cycle VVT engine is achieved over conventional Otto cycle engine during the NEDC, FUDS, and FHDS cycles.

Research on performance optimization and fuel-saving mechanism of an Atkinson cycle gasoline engine at low speed and part load

Fuel ◽  
2020 ◽  
Vol 265 ◽  
pp. 117010 ◽  
Author(s):  
Qingyu Niu ◽  
Baigang Sun ◽  
Dongsheng Zhang ◽  
Qinghe Luo
Keyword(s):  
Performance Optimization ◽  
Gasoline Engine ◽  
Fuel Saving ◽  
Low Speed ◽  
Part Load ◽  
Atkinson Cycle

scholarly journals Deep Learning on Computational-Resource-Limited Platforms: A Survey

2020 ◽  
Vol 2020 ◽  
pp. 1-19 ◽  
Author(s):  
Chunlei Chen ◽  
Peng Zhang ◽  
Huixiang Zhang ◽  
Jiangyan Dai ◽  
Yugen Yi ◽  
...  
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Pervasive Computing ◽  
Learning Technologies ◽  
Smart Sensors ◽  
Huge Amount ◽  
Computational Optimization ◽  
Computational Overhead ◽  
Resource Limited ◽  
Wide Range

Nowadays, Internet of Things (IoT) gives rise to a huge amount of data. IoT nodes equipped with smart sensors can immediately extract meaningful knowledge from the data through machine learning technologies. Deep learning (DL) is constantly contributing significant progress in smart sensing due to its dramatic superiorities over traditional machine learning. The promising prospect of wide-range applications puts forwards demands on the ubiquitous deployment of DL under various contexts. As a result, performing DL on mobile or embedded platforms is becoming a common requirement. Nevertheless, a typical DL application can easily exhaust an embedded or mobile device owing to a large amount of multiply and accumulate (MAC) operations and memory access operations. Consequently, it is a challenging task to bridge the gap between deep learning and resource-limited platforms. We summarize typical applications of resource-limited deep learning and point out that deep learning is an indispensable impetus of pervasive computing. Subsequently, we explore the underlying reasons for the high computational overhead of DL through reviewing the fundamental concepts including capacity, generalization, and backpropagation of a neural network. Guided by these concepts, we investigate on principles of representative research works, as well as three types of solutions: algorithmic design, computational optimization, and hardware revolution. In pursuant to these solutions, we identify challenges to be addressed.

Enhancement Potential of the Thermal Conversion Efficiency of Ice Cycles by Using of a Real Atkinson Cycle Implementation and (Very) High Pressure Turbo Charging

2010 ◽  
Author(s):  
Victor Gheorghiu
Keyword(s):  
High Pressure ◽  
Conversion Efficiency ◽  
High Efficiency ◽  
Gasoline Engine ◽  
Combustion Engine ◽  
Optimal Solution ◽  
Thermal Conversion ◽  
Point Of View ◽  
Intake Manifold ◽  
Atkinson Cycle

Most recent implementations of the Atkinson cycle are not optimal from the point of view of Thermal Conversion Efficiency (TCE). For example, Toyota has put in its Prius II a gasoline engine which should achieve high efficiency by using a modified Atkinson cycle based on variable intake valve timing management. Firstly, this implementation of the Atkinson cycle is not the optimal solution because some of the air is first sucked from the intake manifold into the cylinder and subsequently returned back there. As a consequence, the oscillating air stream considerably reduces the thermal conversion efficiency of this cycle. Secondly, this implementation of the Atkinson cycle reaches only low levels of Indicated Mean Pressure (IMEP) and, thirdly, it is not suitable for part load Engine Operating Points (EOP) because of the lower TCE. For these reasons, this implementation of the Atkinson cycle is suitable only for hybrid vehicles, where the engine — because it is not directly linked mechanically to the wheels — works only in its best EOP. In this paper the losses in TCE of Internal Combustion Engine (ICE), especially for the Atkinson cycles, are analyzed in detail and a proposal is made for their reduction for aspirated and especially for high pressure supercharged engines.

Modeling the emissions of a gasoline engine during high-transient operation using machine learning approaches

2021 ◽  
pp. 146808742110323
Author(s):  
Mohammad Hossein Moradi ◽  
Alexander Heinz ◽  
Uwe Wagner ◽  
Thomas Koch
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Artificial Neural Network ◽  
Gasoline Engine ◽  
Training Data ◽  
Coefficient Of Determination ◽  
Learning Approaches ◽  
Transient Operation ◽  
Artificial Neural ◽  
Transient Operations

To perform a suitable optimization method in terms of emission and efficiency for an internal combustion engine, first highly accurate and possible real-time capable modeling for the transient operations should be provided. In this work, the modeling of NO x and HC raw emission (before exhaust aftertreatment systems) in a six-cylinder gasoline engine under highly transient operation was performed using machine learning approaches. Three different machine learning methods, namely Artificial Neural Network, Long Short-Term Memory, and Random Forest were used and the results of these models were compared with each other. In general, the results show a significant improvement in accuracy compared to other studies that have modeled transient operations. Furthermore, the shortcoming of Artificial Neural Network for the prediction of the HC emission by the transient operation is observed. The coefficient of determination ( R2) for the best model for NO x prediction is 0.98 and 0.97 for the training data and test data, respectively. This value is 0.9 and 0.89 for the best HC prediction model.

Sign in / Sign up

Export Citation Format

Share Document