Process Monitoring and Adjustment Based on Optimal RBF Network

2013 ◽  
Vol 336-338 ◽  
pp. 1286-1291
Author(s):  
Jian Li Yu ◽  
Rui Fang Zhou
Keyword(s):  
Quality Control ◽  
Process Control ◽  
Radial Basis Function ◽  
Control Chart ◽  
Basis Function ◽  
Control Model ◽  
Rbf Network ◽  
Radial Basis ◽  
Process Output ◽  
Residual Control

Modern complex manufacturing process output data showed high autocorrelation, resulting in the output of the process to deviate from the design target , or that false alarms increasd in traditional control chart in monitoring process. Statistical Process Control (SPC) and Automatic process control (APC) are main methods of industrial processes. Study based on the optimization of radial basis (Radial Basis Funtion RBF) neural network integrated SPC/APC quality control model, the forecast MMSE controller based on optimal radial basis function networks were utilized to adjut process of productive process output, and residual control charts were utilized to monitor process output after adjustment. Results show that optimal RBF network can improve forecast accuracy and adjustment effect, eliminate effectively process output autocorrelation. The residual control chart will in steady state and with small fluctuation. Intergrated SPC/APC quality control model based on optimal radial basis function can eliminate process fluctuation effectively and guaranteeproduct stable quality in process quality control.

Radial basis function neural network chaos control of a piezomagnetoelastic energy harvesting system

2019 ◽  
Vol 25 (16) ◽  
pp. 2191-2203 ◽  
Author(s):  
R. Dehghani ◽  
H. M. Khanlo
Keyword(s):  
Energy Harvesting ◽  
Radial Basis Function ◽  
Basis Function ◽  
Output Voltage ◽  
Chaos Control ◽  
Chaotic Behavior ◽  
Rbf Network ◽  
Magnetic Forces ◽  
Radial Basis ◽  
Energy Harvesting System

In this paper, an adaptive chaos control is proposed for a typical vibratory piezomagnetoelastic energy harvesting system to return the chaotic behavior to a periodic one. Piezomagnetoelastic energy harvesting systems show chaotic behaviors in spite of harmonic input. Although, the chaotic behavior of the system gives higher output voltage than the periodic motion, it is preferred to the output voltage as this is periodic for charging a battery or a capacitor efficiently. Therefore, the chaos control is important in this system. The physical model is composed of the upper and lower piezoelectric layers on a cantilever taper beam, one attached tip magnet, and two external magnets (EM). Position of the EM is controlled by inputs. Firstly, chaotic and periodic regions are detected by utilizing the bifurcation diagrams, phase plan portrait, and Poincaré maps. Then an adaptive controller is proposed for controlling of the chaotic behaviors in the presence of uncertainty due to magnetic forces. The control law is derived based on the inverse dynamic method and the uncertainty elements of the controller are estimated using radial basis function (RBF) network. The weights of the RBF network are obtained using an adaptation law. The adaptation laws are derived based on Lyapunov stability theory and a projection operator. The distance of the tip magnet and the EM as well as the gap distance of two EM are used to control the chaotic behavior. Simulation results show that the proposed controller can return the chaotic motion to a periodic one in spite of the uncertainties in the magnetic forces.

scholarly journals Radial Basis Function Network Based Design of Incipient Motion Condition of Alluvial Channels with Seepage

2010 ◽  
Vol 58 (2) ◽  
pp. 102-113 ◽  
Author(s):  
Bimlesh Kumar ◽  
Gopu Sreenivasulu ◽  
Achanta Rao
Keyword(s):  
Radial Basis Function ◽  
Basis Function ◽  
Radial Basis Function Network ◽  
Incipient Motion ◽  
Alluvial Channels ◽  
Rbf Network ◽  
Motion Condition ◽  
Radial Basis ◽  
Alluvial Channel ◽  
Function Network

Radial Basis Function Network Based Design of Incipient Motion Condition of Alluvial Channels with SeepageIncipient motion is the critical condition at which bed particles begin to move. Existing relationships for incipient motion prediction do not consider the effect of seepage. Incipient motion design of an alluvial channel affected from seepage requires the information about five basic parameters, i.e., particle sized, water depthy, energy slopeSf, seepage velocityvsand average velocityu.As the process is extremely complex, getting deterministic or analytical form of process phenomena is too difficult. Data mining technique, which is particularly useful in modeling processes about which adequate knowledge of the physics is limited, is presented here as a tool complimentary to model the incipient motion condition of alluvial channel at seepage. This article describes the radial basis function (RBF) network to predict the seepage velocity vs and average velocityubased on experimental data of incipient condition. The prediction capability of model has been found satisfactory and methodology to use the model is also presented. It has been found that model predicts the phenomena very well. With the help of the RBF network, design curves have been presented for designing the alluvial channel when it is affected by seepage.

Reconstructing cylinder pressure from vibration signals based on radial basis function networks

2001 ◽  
Vol 215 (6) ◽  
pp. 761-767 ◽  
Author(s):  
H Du ◽  
L Zhang ◽  
X Shi
Keyword(s):  
Radial Basis Function ◽  
Network Model ◽  
Basis Function ◽  
Cylinder Head ◽  
Cylinder Pressure ◽  
Vibration Signals ◽  
Rbf Network ◽  
Engine Cylinder ◽  
Wide Range ◽  
Radial Basis

This paper presents an approach to reconstruct internal combustion engine cylinder pressure from the engine cylinder head vibration signals, using radial basis function (RBF) networks. The relationship between the cylinder pressure and the engine cylinder head vibration signals is analysed first. Then, an RBF network is applied to establish the non-parametric mapping model between the cylinder pressure time series and the engine cylinder head vibration signal frequency series. The structure of the RBF network model is presented. The fuzzy c-means clustering method and the gradient descent algorithm are used for selecting the centres and training the output layer weights of the RBF network respectively. Finally, the validation of this approach to cylinder pressure reconstruction from vibration signals is demonstrated on a two-cylinder, four-stroke direct injection diesel engine, with data from a wide range of speed and load settings. The prediction capabilities of the trained RBF network model are validated against measured data.

Approximation by Growing Radial Basis Function Networks Using the Differential-Evolution-Based Algorithm

2005 ◽  
Vol 9 (5) ◽  
pp. 540-548
Author(s):  
Junhong Liu ◽  
◽  
Jouni Lampinen
Keyword(s):  
Differential Evolution ◽  
Radial Basis Function ◽  
Basis Function ◽  
Rbf Network ◽  
Local Tuning ◽  
De Algorithm ◽  
Network Training ◽  
Radial Basis ◽  
Network Output ◽  
Growth Method

The differential evolution (DE) algorithm is a floating-point-encoded evolutionary algorithm for global optimization. We applied a DE-based method to training radial basis function (RBF) networks with variables including centers, weights, and widths. This algorithm consists of three steps – initial tuning focusing on finding the center of a one-node RBF network, local tuning, and global tuning both using cycling schemes to find RBF network parameters. The mean square error from desired output to actual network output is applied as the objective function to be minimized. Network training is shown by approximating a set of functions and reconstructing the spectra of oil samples and classification. Net performance is compared to approaches reported in the literature, and the resulting network generally performs better based on the tests performed. Results show that DE-based Gaussian RBF growth method improves approximation results reported.

Radial Basis Function Network Based MPPT for Photovoltaic System during Shading Condition

2013 ◽  
Vol 448-453 ◽  
pp. 1474-1479
Author(s):  
Mahamad Abd Kadir ◽  
Saon Sharifah
Keyword(s):  
Radial Basis Function ◽  
Basis Function ◽  
Variable Temperature ◽  
Radial Basis Function Network ◽  
Photovoltaic System ◽  
Pv System ◽  
Rbf Network ◽  
Point Tracking ◽  
Radial Basis ◽  
Temperature Constant

The output powers of photovoltaic (PV) system are crucially depending of the two variable factors, which are the cell temperatures and solar irradiances. A method to utilize effectively the PV is known as a maximum power point tracking (MPPT) method. This method is extract the maximum available power from PV module by making them operates at the most efficient output. This paper presents Radial Basis Function (RBF) Network to control the MPPT of PV system. The performances of the controller is analyzed in four conditions with are constant irradiation and temperature, constant irradiation and variable temperature, constant temperature and variable irradiation, and variable temperature and irradiation. The proposed system is simulated by using MATLAB-SIMULINK. According to the results, RBF controller has shown better performance during partially shaded conditions.

scholarly journals Quantum speedup of training radial basis function networks

2019 ◽  
Vol 19 (7&8) ◽  
pp. 609-625
Author(s):  
Changpeng Shao
Keyword(s):  
Radial Basis Function ◽  
Basis Function ◽  
Quantum Computer ◽  
Quantum Algorithms ◽  
Rbf Network ◽  
Training Samples ◽  
Radial Basis ◽  
The Matrix ◽  
Hamiltonian Simulation ◽  
Classical Computer

Radial basis function (RBF) network is a simple but useful neural network model that contains wide applications in machine learning. The training of an RBF network reduces to solve a linear system, which is time consuming classically. Based on HHL algorithm, we propose two quantum algorithms to train RBF networks. To apply the HHL algorithm, we choose using the Hamiltonian simulation algorithm proposed in [P. Rebentrost, A. Steffens, I. Marvian and S. Lloyd, Phys. Rev. A 97, 012327, 2018]. However, to use this result, an oracle to query the entries of the matrix of the network should be constructed. We apply the amplitude estimation technique to build this oracle. The final results indicate that if the centers of the RBF network are the training samples, then the quantum computer achieves exponential speedup at the number and the dimension of training samples over the classical computer; if the centers are determined by the K-means algorithm, then the quantum computer achieves quadratic speedup at the number of samples and exponential speedup at the dimension of samples.

Sign in / Sign up

Export Citation Format

Share Document