scholarly journals Multiaxis Capacitive Force Sensor and its Measurement Principle Using Neural Networks

2006 ◽  
Vol 18 (4) ◽  
pp. 442-449 ◽  
Author(s):  
Seiji Aoyagi ◽  
◽  
Masaru Kawanishi ◽  
Daiichiro Yoshikawa
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Finite Element Method ◽  
Finite Element ◽  
Full Range ◽  
Force Sensor ◽  
The Finite Element Method ◽  
Electrical Field ◽  
The Neural Network ◽  
Measurement Principle

We propose a multiaxis capacitive force sensor consisting of one movable upper electrode on a plate and fixed lower electrodes on a substrate. The plate moves both vertically and horizontally when force is applied, and capacitance between upper and lower electrodes changes. This sensor uses the main electrical field between two directly facing electrodes and the fringe electrical field between diagonally opposed electrodes, making capacitance difficult to analyze. We simulated changes in nonlinear capacitance based on the upper electrode’s movement using the finite element method (FEM) and proved that capacitance is a function of the upper electrode’s displacement. We used a neural network to calculate the upper electrode’s displacement from capacitance. The neural network operates appropriately and calculated displacement error is within 0.5% of the full range. We proposed fabricating a practical force sensor consisting of planar capacitors making it compatible with surface micromachining and not requiring 3-D bulk micromachining, which simplifies fabrication, making it economical.

A Novel Force Sensor Based Multi-Function Take-Off Board

2012 ◽  
Vol 468-471 ◽  
pp. 221-224
Author(s):  
Pei Chen ◽  
Yu Long Zhao ◽  
Bao Jin Wang ◽  
Shan Ping Chen ◽  
Zhen Long Yan
Keyword(s):  
Finite Element Method ◽  
Finite Element ◽  
Force Sensor ◽  
Structural Deformation ◽  
Force Sensors ◽  
The Finite Element Method ◽  
Working Mechanism ◽  
Practical Applications ◽  
Jump Training ◽  
Long Jump

In order to detect the take-off forces of athletes in long jump, a novel force sensor based take-off board is designed. The take-off board consists of a standard take-off board, two novel force sensors, two support plates and a base. The working mechanism of the strain beam in the force sensor is analyzed and the finite element method(FEM) is used to investigate the structural deformation and stress distribution. Then the sensor is tested. The calibration experimental results demonstrate that the sensor has an excellent measurement linearity (0.6%) and can meet the requirements of practical applications. Then the multi-function take-off board based on the force sensors is designed and manufactured which can make the daily long jump training more scientific.

scholarly journals Locating and Classifying Defects with Artificial Neural Networks

2008 ◽  
Vol 13-14 ◽  
pp. 117-123 ◽  
Author(s):  
A. Luna Avilés ◽  
Luis Héctor Hernández-Gómez ◽  
J.F. Durodola ◽  
G. Urriolagoitia-Calderón ◽  
G. Urriolagoitia-Sosa
Keyword(s):  
Neural Networks ◽  
Finite Element Method ◽  
Finite Element ◽  
Parametric Analysis ◽  
Input Data ◽  
Natural Frequencies ◽  
Synthetic Data ◽  
The Finite Element Method ◽  
Backpropagation Algorithm ◽  
Neuro Fuzzy

Locating defects and classifying them by their size was done with an Adaptive Neuro Fuzzy Procedure (ANFIS). Postulated void of three different sizes (1x1 mm, 2x2 mm and 2x1 mm) were introduced in a bar with and without a notch. The size of a defect and its localization in a bar change its natural frequencies. Accordingly, synthetic data was generated with the finite element method. A parametric analysis was carried out. Only one defect was taken into account and the first five natural frequencies were calculated. 495 cases were evaluated. All the input data was classified in three groups. Each one has 165 cases and corresponds to one of the three defects mentioned above. 395 cases were taken randomly and, with this information, the ANN was trained with the backpropagation algorithm. The accuracy of the results was tested with the 100 cases that were left. This procedure was followed in the cases of the plain bar and a bar with a notch. In the next stage of this work, the ANN output was optimized with ANFIS. The accuracy of the localization and classifications of the defects was improved.

Modelling and Optimization of Induction Cooking by the Use of Magneto-Thermal Finite Element Analysis and Neural Network

2014 ◽  
Vol 792 ◽  
pp. 251-259
Author(s):  
F. Allaoui ◽  
A. Kanssab ◽  
M. Matallah ◽  
A. Zoui ◽  
M. Feliachi
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Finite Element Method ◽  
Finite Element Analysis ◽  
Finite Element ◽  
Element Analysis ◽  
Induction Cooking ◽  
Pan Heating ◽  
Homogeneous Temperature ◽  
Modelling And Optimization

The main advantage of induction cooking is the pan heating without thermal inertia.However to obtain best efficiency, it is essential to have an inductor geometry that gives ahomogeneous temperature on the pan bottom. In this paper, we will first model the magnetothermal phenomena of the system by a finite element method (FEM) in order to determine thedistribution of temperature on the pan bottom taking into consideration the nonlinearity of thesystem. This study shows that the temperature is not homogeneously distributed. Then, in the aim tohave homogeneous temperature distribution in the pan bottom, we propose an inductor structurewith four throats containing the coils and we will use Neural Networks to determine the optimalthroats distribution and their dimensions. The optimized structure permits us to achieve our goal.

scholarly journals REVIEW OF AVAILABLE APPROACHES FOR ULTIMATE BEARING CAPACITY OF TWO-LAYERED SOILS

2012 ◽  
Vol 18 (4) ◽  
pp. 469-482 ◽  
Author(s):  
M. Dalili Shoaei ◽  
A. Alkarni ◽  
J. Noorzaei ◽  
M. S. Jaafar ◽  
Bujang B. K. Huat
Keyword(s):  
Neural Network ◽  
Finite Element Method ◽  
Artificial Neural Network ◽  
Finite Element ◽  
Bearing Capacity ◽  
State Of The Art ◽  
Classical Method ◽  
Ultimate Bearing Capacity ◽  
Layered Soils ◽  
The Finite Element Method

This paper presents the state of the art report on available approaches to predicting the ultimate bearing capacity of two-layered soils. The article discusses three most popular methods, including the classical method, application of the finite element method and artificial neural network. Various approaches based on these three powerful tools are studied and their methodologies are discussed.

scholarly journals Artificial Neural Network Modelling for Optimizing the Optical Parameters of Plasmonic Paired Nanostructures

Nanomaterials ◽  
2022 ◽  
Vol 12 (1) ◽  
pp. 170
Author(s):  
Sneha Verma ◽  
Sunny Chugh ◽  
Souvik Ghosh ◽  
B. M. Azizur Rahman
Keyword(s):  
Neural Network ◽  
Finite Element Method ◽  
Artificial Neural Network ◽  
Finite Element ◽  
Plasmonic Nanostructures ◽  
Optical Parameters ◽  
Complex Data ◽  
The Neural Network ◽  
Artificial Neural ◽  
Element Method

The Artificial Neural Network (ANN) has become an attractive approach in Machine Learning (ML) to analyze a complex data-driven problem. Due to its time efficient findings, it has became popular in many scientific fields such as physics, optics, and material science. This paper presents a new approach to design and optimize the electromagnetic plasmonic nanostructures using a computationally efficient method based on the ANN. In this work, the nanostructures have been simulated by using a Finite Element Method (FEM), then Artificial Intelligence (AI) is used for making predictions of associated sensitivity (S), Full Width Half Maximum (FWHM), Figure of Merit (FOM), and Plasmonic Wavelength (PW) for different paired nanostructures. At first, the computational model is developed by using a Finite Element Method (FEM) to prepare the dataset. The input parameters were considered as the Major axis, a, the Minor axis, b, and the separation gap, g, which have been used to calculate the corresponding sensitivity (nm/RIU), FWHM (nm), FOM, and plasmonic wavelength (nm) to prepare the dataset. Secondly, the neural network has been designed where the number of hidden layers and neurons were optimized as part of a comprehensive analysis to improve the efficiency of ML model. After successfully optimizing the neural network, this model is used to make predictions for specific inputs and its corresponding outputs. This article also compares the error between the predicted and simulated results. This approach outperforms the direct numerical simulation methods for predicting output for various input device parameters.

Sign in / Sign up

Export Citation Format

Share Document