scholarly journals Neural Network Model for Synthesis of Thermally Sprayed (AI/AI2O3) Composite Protective Coatings

2021 ◽  
Vol 2063 (1) ◽  
pp. 012013
Author(s):  
Thamir Abdul-Jabbar Jumah ◽  
Saad Ali Ahmed
Keyword(s):  
Neural Network ◽  
Protective Coatings ◽  
Composite Coatings ◽  
Electrical Potential ◽  
Least Square Method ◽  
Least Square ◽  
Effect Of Temperature ◽  
Hardness Tests ◽  
Al Composite ◽  
Hidden Layer

Abstract Al2O3 and Al2O3–Al composite coatings were deposited on steel specimens using Oxy-acetylene gas thermal spray gun. Alumina was mixed with Aluminum in six groups of concentrations (0, 5, 10,12,15 and 20% ) Al2O3, Specimens were tested for corrosion using Potentiodynamic polarization technique. Further tests were conducted for the effect of temperature on polarization curve and the hardness tests for the coated specimens. At first, Modelling was carried out using MINITAB-19, least square method, as a 2nd degree nonlinear model, bad results were achieved because of the high nonlinearity. Better result was achieved using neural network fitting tool. The network was designed using five neurons in the hidden layer and the input was I input with two layers, the electrical potential and alumina concentration.

Nonlinear Rectification for Capacitance Method Measuring the Moisture of Green Sand Based on Functional Link Neural Network

2013 ◽  
Vol 380-384 ◽  
pp. 806-810
Author(s):  
De Quan Shi ◽  
Gui Li Gao ◽  
Jing Wei Dong ◽  
Li Hua Wang
Keyword(s):  
Neural Network ◽  
Moisture Content ◽  
Least Square Method ◽  
Least Square ◽  
Green Sand ◽  
Functional Link ◽  
Moisture Sensor ◽  
Single Output ◽  
Capacitance Method ◽  
Functional Link Neural Network

In order to solve the nonlinear output/input problem of the capacitance method measuring the moisture content of green sand, a nonlinear compensation is added into the measurement system and the neural network is used for nonlinear rectification. Based on introducing the principle of non-linear compensation, a functional link artificial network with multi-input and single-output is constructed. In the network, the output voltage of capacitance moisture sensor is taken as the input and the moisture content of green sand is taken as the output. The data samples obtained in laboratory are used to train the network, and the dynamic rectification model is got. The experimental results show that the maximum difference and relative error of the moisture content are ±0.09% and ±1.85% after nonlinear rectification by the functional link neural network, and it is significantly better than those of the least square method.

scholarly journals Modelling of the Automatic Depth Control Electrohydraulic System Using RBF Neural Network and Genetic Algorithm

2010 ◽  
Vol 2010 ◽  
pp. 1-16 ◽  
Author(s):  
Xing Zong-yi ◽  
Qin Yong ◽  
Pang Xue-miao ◽  
Jia Li-min ◽  
Zhang Yuan
Keyword(s):  
Neural Network ◽  
Genetic Algorithm ◽  
Distance Measure ◽  
Rbf Neural Network ◽  
Least Square Method ◽  
Least Square ◽  
Nonlinear Characteristics ◽  
Electrohydraulic System ◽  
Comparison Results ◽  
Depth Control

The automatic depth control electrohydraulic system of a certain minesweeping tank is complex nonlinear system, and it is difficult for the linear model obtained by first principle method to represent the intrinsic nonlinear characteristics of such complex system. This paper proposes an approach to construct accurate model of the electrohydraulic system with RBF neural network trained by genetic algorithm-based technique. In order to improve accuracy of the designed model, a genetic algorithm is used to optimize centers of RBF neural network. The maximum distance measure is adopted to determine widths of radial basis functions, and the least square method is utilized to calculate weights of RBF neural network; thus, computational burden of the proposed technique is relieved. The proposed technique is applied to the modelling of the electrohydraulic system, and the results clearly indicate that the obtained RBF neural network can emulate the complex dynamic characteristics of the electrohydraulic system satisfactorily. The comparison results also show that the proposed algorithm performs better than the traditional clustering-based method.

The Layout Measurement Points Prediction and Flatness Calculation for the Antenna Plate After Welding Assembly Based on the RBF Neural Network Model

2016 ◽  
Author(s):  
Minghui Pan ◽  
Wencheng Tang ◽  
Yan Xing ◽  
Jun Ni
Keyword(s):  
Neural Network ◽  
Rbf Neural Network ◽  
Least Square Method ◽  
Least Square ◽  
Measuring Point ◽  
Improve Measurement ◽  
Neural Network Prediction ◽  
Measuring Experiment ◽  
Predicted Height ◽  
Measurement Efficiency

Due to the effect of the antenna plate flatness on the antenna performances, the flatness is one of the key performance indicators for the planar antenna. Before calculating the antenna plate flatness, the support assembly tools are built, and then measuring experiment for height coordinate values is carrying out on the assembly platform. This paper presents a predictive method that is the Radial Basis Function (RBF) neural network method to obtain the height coordinate values based on fewer measurement points on the antenna plate after welding assembly, and the antenna plate flatness is calculated by fitting least square plane using measuring point coordinate value through the least square method (LSM). Simultaneously, before or after welding assembly, comparing with the calculated flatness value, it is shown that the calculated flatness value by the predicted height coordinate values basically agrees well with the initial calculated flatness value. These results reveal that the RBF neural network prediction is adopted to be very correct and valid, which will reduce the measurement cost and improve measurement efficiency in future.

Modeling of Pulp Washing Process Based on Two-Step BP Neural Network

2012 ◽  
Vol 198-199 ◽  
pp. 1712-1715
Author(s):  
Hua Zhong Wang ◽  
Wen Juan Shan
Keyword(s):  
Neural Network ◽  
Bp Neural Network ◽  
Model Simulation ◽  
Least Square Method ◽  
Least Square ◽  
Washing Process ◽  
Optimization Control ◽  
Important Quality ◽  
Simulation Results ◽  
Quality Indexes

The most important quality indexes to evaluate pulp washing performance are residual soda and the Baume degree. But it is difficult to measure the two indexes directly. To solve the problem of optimization control of the washing process, the model of the residual soda and the Baume degree are studied in this paper. Simulating residual soda and the Baume degree via a two-step neural network and modeling them based on least square method and steady-state data obtained by neural network model. Simulation results show that this method can effectively locate the pulp washing process.

scholarly journals A Method of Containment Leakage Rate Estimation Based on Convolution Neural Network

2021 ◽  
Vol 9 ◽  
Author(s):  
Hao Wang ◽  
Jingquan Liu ◽  
Guangyao Xie ◽  
Xianping Zhong ◽  
Xiangqi Fan
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Nuclear Power ◽  
Power Plants ◽  
Least Square Method ◽  
Leakage Rate ◽  
Least Square ◽  
Nonlinear Fitting ◽  
The Third ◽  
Start Up

As the nuclear power plant containment is the third barrier to nuclear safety, real-time monitoring of containment leakage rate is very important in addition to the overall leakage test before an operation. At present, most of the containment leakage rate monitoring systems calculate the standard volume of moist air in the containment through monitoring parameters and calculate the daily leakage rate by the least square method. This method requires several days of data accumulation to accurately calculate. In this article, a new leakage rate modeling technique is proposed using a convolutional neural network based on data of the monitoring system. Use the daily monitoring parameters of nuclear power plants to construct inputs of the model and train the convolutional neural network with daily leakage rates as labels. This model makes use of the powerful nonlinear fitting ability of the convolutional neural network. It can use 1-day data to accurately calculate the containment leakage rate during the reactor start-up phase and can timely determine whether the containment leak has occurred during the start-up phase and deal with it in time, to ensure the integrity of the third barrier.

scholarly journals PEMODELAN PENGARUH SENTIMEN PUBLIK DI TWITTER TERKAIT POLITIK TERHADAP KURS RUPIAH DAN INDEKS HARGA SAHAM DENGAN PENDEKATAN MACHINE LEARNING

2021 ◽  
Vol 2020 (1) ◽  
pp. 989-999
Author(s):  
Epan Mareza Primahendra ◽  
Budi Yuniarto
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Support Vector Machine ◽  
Big Data ◽  
Least Square ◽  
Support Vector ◽  
Hidden Layer ◽  
Hidden Neurons

Kurs Rupiah dan indeks harga saham (IHS) berpengaruh terhadap perekonomian Indonesia. Pergerakan kurs Rupiah dan IHS dipengaruhi oleh, informasi publik, kondisi sosial, dan politik. Kejadian politik banyak menimbulkan sentimen dari masyarakat. Sentimen tersebut banyak disampaikan melalui media sosial terutama Twitter. Twitter merupakan sumber big data yang jika datanya tidak dimanfaatkan akan menjadi sampah. Pengumpulan data dilakukan pada periode 26 September 2019 - 27 Oktober 2019. Pola jumlah tweets harian yang sesuai dengan pergerakan kurs Rupiah dan IHS mengindikasikan bahwa terdapat hubungan antara sentimen di Twitter terkait situasi politik terhadap kurs Rupiah dan IHS. Penelitian ini menggunakan pendekatan machine learning dengan algoritma Neural Network dan Least Square Support Vector Machine. Penelitian ini bertujuan untuk mengetahui pengaruh sentimen terhadap kurs Rupiah dan IHS sekaligus mengkaji kedua algoritmanya. Hasilnya menjelaskan bahwa model terbaik untuk estimasi IHS yaitu NN dengan 1 hidden layer dan 2 hidden neurons. Modelnya menunjukan bahwa terdapat pengaruh antara sentimen tersebut terhadap IHS karena volatilitas estimasi IHS sudah cukup mengikuti pola pergerakan IHS aktual. Model terbaik untuk estimasi kurs Rupiah yaitu LSSVM. Pola pergerakan estimasi kurs Rupiah cenderung stagnan di atas nilai aktual. Ini mengindikasikan bahwa modelnya masih belum memuaskan dalam mengestimasi pengaruh sentimen publik terhadap kurs Rupiah.

Forward Displacement Analysis of the 6-SPS Stewart Mechanism Based on Quaternion and Hyper-Chaotic Damp Least Square Method

2011 ◽  
Vol 230-232 ◽  
pp. 759-763 ◽  
Author(s):  
You Xin Luo ◽  
Qi Yuan Liu ◽  
Xiao Yi Che ◽  
Bin Zeng
Keyword(s):  
Neural Network ◽  
Parallel Mechanism ◽  
Least Square Method ◽  
Least Square ◽  
Chaotic Neural Network ◽  
Forward Displacement ◽  
Displacement Analysis ◽  
Chaotic Sequences ◽  
Chaos System ◽  
Forward Displacement Analysis

The forward displacement analysis of parallel mechanism can be transformed into solving complicated nonlinear equations and it is a very difficult process. Taking chaotic sequences as the initial values of damp least square method, all the solutions of equations can be found and the solving efficiency is related to modeling methods. Making use of existing chaos system and discovering new chaos system to generate chaotic sequences with good properties is the key to the chaos sequences-based damp least square method. Based on the connection topology of chaotic neural network composed of the four chaotic neurons, hyper-chaos exists in the chaotic neural network system. Combining hyper-chaos with damp least square method, a new method to find all solutions of nonlinear questions was proposed, in which initial points are generated by utilizing hyper-chaotic neural network. For the first time, based on quaternion, the model of the forward displacements of 6-SPS parallel mechanism is built up. The result is verified by a numerical example.

NEW METHOD OF NONLINEAR RECTIFICATION OF SENSOR SYSTEMS

2005 ◽  
Vol 02 (01) ◽  
pp. 37-43
Author(s):  
JUNJIE CHEN ◽  
WEIYI HUANG
Keyword(s):  
Neural Network ◽  
Computer Simulations ◽  
Network Model ◽  
Neural Network Model ◽  
Least Square Method ◽  
Least Square ◽  
New Method ◽  
Sensor Systems ◽  
Approximation Accuracy ◽  
Genetic Neural Network

Genetic neural network model of solving the problem of nonlinearity rectification of sensor systems, is put forward in the light of the shortcomings of least square and other conventional methods. And in theory the model is emphatically expounded. Computer simulations are presented to demonstrate that approximation accuracy of the model is far higher than the conventional least square method and the model possesses stronger robustness through adopting the methods in this paper. The research in the paper indicates that the model can also be used to realize nonlinearity rectification in other similar systems.

Forward Displacement Analysis of the 6-SPS Stewart Mechanisms Based on Hyper-Chaotic Damp Least Square Method

2011 ◽  
Vol 55-57 ◽  
pp. 2099-2103
Author(s):  
You Xin Luo ◽  
Qi Yuan Liu ◽  
Xiao Yi Che ◽  
Bin Zeng ◽  
Zhe Ming He
Keyword(s):  
Neural Network ◽  
Direction Cosine ◽  
Least Square Method ◽  
Least Square ◽  
Chaotic Neural Network ◽  
Forward Displacement ◽  
Displacement Analysis ◽  
Chaotic Sequences ◽  
Chaos System ◽  
Forward Displacement Analysis

The forward displacement analysis of the 6-SPS Stewart mechanism can be transformed into solving complicated nonlinear equations and it is a very difficult process. Taking chaotic sequences as the initial values of damp least square method, all the solutions of equations can be found quickly and making use of existing chaos system and discovering new chaos system to generate chaotic sequences with good properties is the key to the Chaos sequences-based damp least square method. Based on the connection topology of chaotic neural network composed of the four chaotic neurons, hyper-chaos exists in the chaotic neural network system. Combining hyper-chaos with damp least square method, a new method to find all solutions of nonlinear questions was proposed, in which initial points are generated by utilizing hyper-chaotic neural network. Based on direction cosine matrix and Euler parameters, the model of the forward displacements of 6-SPS parallel mechanism with seven variables is built up. The result is verified by a numerical example.

Sign in / Sign up

Export Citation Format

Share Document