The model of compression ignition engine with artificial neural networks

2008 ◽  
Vol 132 (1) ◽  
pp. 44-49
Author(s):  
Krzysztof BRZOZOWSKI ◽  
Jacek NOWAKOWSKI
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Artificial Neural Network ◽  
Compression Ignition ◽  
Control Parameters ◽  
Working Process ◽  
Compression Ignition Engine ◽  
The Neural Networks ◽  
Artificial Neural ◽  
Model Equations

The paper presents an application of artificial neural network in modelling the working process in compression ignition engine. In order to determine the usefulness of proposed method the optimisation task has been formulated. The aim of optimisation process was to find the engine control parameters which enable reduction of the NOx emission. In order to solve the problem, the model equations has to be integrated for values of control parameters whose are given as output from the neural networks implemented.

scholarly journals On the Use of the FuzzyARTMAP Neural Network for Pattern Recognition in Statistical Process Control using a Factorial Design

2010 ◽  
Vol 5 (2) ◽  
pp. 205 ◽  
Author(s):  
J. A. Vazquez-Lopez ◽  
I. Lopez-Juarez ◽  
M. Peña-Cabrera
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Pattern Recognition ◽  
Behaviour Pattern ◽  
Control Parameters ◽  
Network Efficiency ◽  
Statistical Process ◽  
The Neural Network ◽  
Statistical Pattern ◽  
Experimental Design Methodology

Time-series statistical pattern recognition is of prime importance in statistics, especially in quality control techniques for manufacturing processes. A frequent problem in this application is the complexity when trying to determine the behaviour (pattern) from sample data. There have been identified standard patterns which are commonly present when using the X chart; its detection depends on human judgement supported by norms and graphical criteria. In the last few years, it has been demonstrated that Artificial Neural Networks (ANN’s) are useful to predict the type of time-series pattern instead of the use of rules. However, the ANN control parameters have to be fixed to values that maximize its performance. This research proposes an experimental design methodology to determine the most appropriate values for the control parameters of the FuzzyARTMAP ANN such as: learning rate (β ) and network vigilance (ρa, ρb, ρab) in order to increment the neural network efficiency during unnatural pattern recognition.

A 3D Virtual FEM and SA Method to Determining the Optimization Clearance for a Punching Die

2009 ◽  
Vol 419-420 ◽  
pp. 277-280
Author(s):  
Jui Chang Lin ◽  
W.S. Lin ◽  
King Sun Lee
Keyword(s):  
Neural Network ◽  
Satisfactory Result ◽  
Maximum Stress ◽  
Design Method ◽  
Experiment Design ◽  
Virtual Simulation ◽  
Control Parameters ◽  
3D Cad ◽  
Material Thickness ◽  
Simulation And Experiment

This study is subject to 3D virtual simulation and experiment design method application in the optimal clearance design in the 3D shell punched processing. During the simulation stage, the PAM-CRASH and 3D-CAD (Pro/E) system are used to model the punching processing. The results of the punching maximum punched burr from the 3D virtual punching simulation were input to a neural network to establish a model corresponding to the 3D shell punched variables. Once the metal punching control parameters, such as punch/die radius, punch/die clearance, punch cutting angle and different material thickness, were given, the punching processing performance (the punching maximum burr and maximum stress) can be accurately predicted by this developed network. Therefore, in this research, a satisfactory result based on the simulation verification is established.

The Estimation of TP Chromatic Aberration by Using Neural Network

2011 ◽  
Vol 189-193 ◽  
pp. 2211-2214 ◽  
Author(s):  
Du Jou Huang ◽  
Fang Tsung Liu ◽  
Shang Jen Chuang ◽  
Huang Chu Huang ◽  
Rey Chue Hwang
Keyword(s):  
Neural Network ◽  
Chromatic Aberration ◽  
Complex Relationship ◽  
Evaporation Process ◽  
Control Parameters ◽  
Touch Panel ◽  
Decision Mechanism ◽  
Intelligent Decision

In this paper, the chromatic aberration estimator of touch panel (TP) decoration film by using neural network is presented. Through the training of neural network, the complex relationship between the chromatic aberration and the parameters of evaporation process of TP decoration film is expected to be found. Thus, an intelligent decision mechanism for the chromatic aberration of TP film on its evaporation process could be developed. Based on this mechanism, the technician could set the control parameters of evaporation in advance so that the quality of chromatic aberration of TP could meet the customer’s request.

scholarly journals Ship RBF neural network sliding mode PID heading control

2022 ◽  
Vol 355 ◽  
pp. 03064
Author(s):  
Jiaming Yu ◽  
Renxiang Bu ◽  
Liangqi Li
Keyword(s):  
Neural Network ◽  
Pid Control ◽  
Pid Controller ◽  
Sliding Mode ◽  
Rbf Neural Network ◽  
Variable Structure ◽  
Control Parameters ◽  
Mmg Model ◽  
Heading Control ◽  
Online Tuning

In view of the inherent non-linearity, complexity, susceptibility to external wind, wave, and current interference of under-driven ships, and the difficulty of adjusting and adjusting control parameters, to improve the performance of ship’s autopilot, a kind of RBF neural network sliding mode variable structure PID controller is designed. Traditional PID control is sensitive to parameter changes, online tuning is difficult, and easy to overshoot. In order to solve this problem, combining the variable structure characteristics of PID, a differential compensation term is added to the integral term to convert the PID control parameters into three parameters with more obvious physical meanings, and then combined with the RBF neural network learning and identification function to realize online tuning and adaptive control of ship control parameters. Using MATLAB software to simulate the container ship “MV KOTA SEGAR” MMG model shows that the designed RBF neural network sliding mode PID controller can effectively eliminate the ship’s lateral deviation caused by external interference such as wind, waves, currents, etc., with high control accuracy,robustness and strong adaptability.

scholarly journals Design of a New Catheter Operating System for the Surgical Robot

2021 ◽  
Vol 2021 ◽  
pp. 1-9
Author(s):  
Xu Ma ◽  
Jinpeng Zhou ◽  
Xu Zhang ◽  
Yang Qi ◽  
Xiaochen Huang
Keyword(s):  
Neural Network ◽  
Operating System ◽  
Bp Neural Network ◽  
Pid Control ◽  
Pid Controller ◽  
Control Algorithm ◽  
Radiation Injury ◽  
Control Parameters ◽  
Simulation Experiments ◽  
Neural Network Pid

In interventional surgery, the manual operation of the catheter is not accurate. It is necessary to operate the catheter skillfully and effectively to protect the surgeon from radiation injury. The purpose of this paper is to design a new robot catheter operating system, which can help surgeons to complete the operation with high mechanical precision. On the basis of the original mechanical structure—real catheter, the operation information of the main end operator is collected. After the information is collected, the control algorithm of the system is improved, and the BP neural network is combined with the traditional PID controller to adjust the PID control parameters more effectively and intelligently so that the motor can reflect the output of the controller better and faster. The feasibility and superiority of the BP neural network PID controller are verified by simulation experiments.

scholarly journals A Method for Evaluating Chimeric Synchronization of Coupled Oscillators and Its Application for Creating a Neural Network Information Converter

Electronics ◽  
2019 ◽  
Vol 8 (7) ◽  
pp. 756 ◽  
Author(s):  
Velichko
Keyword(s):  
Neural Network ◽  
Coupled Oscillators ◽  
Operating Mode ◽  
Control Parameters ◽  
Network Information ◽  
The Family ◽  
Input Layer ◽  
Generation Mode ◽  
Efficiency Parameter ◽  
Selection Of

This paper presents a new method for evaluating the synchronization of quasi-periodic oscillations of two oscillators, termed “chimeric synchronization”. The family of metrics is proposed to create a neural network information converter based on a network of pulsed oscillators. In addition to transforming input information from digital to analogue, the converter can perform information processing after training the network by selecting control parameters. In the proposed neural network scheme, the data arrives at the input layer in the form of current levels of the oscillators and is converted into a set of non-repeating states of the chimeric synchronization of the output oscillator. By modelling a thermally coupled VO2-oscillator circuit, the network setup is demonstrated through the selection of coupling strength, power supply levels, and the synchronization efficiency parameter. The distribution of solutions depending on the operating mode of the oscillators, sub-threshold mode, or generation mode are revealed. Technological approaches for the implementation of a neural network information converter are proposed, and examples of its application for image filtering are demonstrated. The proposed method helps to significantly expand the capabilities of neuromorphic and logical devices based on synchronization effects.

Sign in / Sign up

Export Citation Format

Share Document