scholarly journals Predicting the Frequency Characteristics of Hybrid Meander Systems Using a Feed-Forward Backpropagation Network

Electronics ◽  
2019 ◽  
Vol 8 (1) ◽  
pp. 85 ◽  
Author(s):  
Darius Plonis ◽  
Andrius Katkevičius ◽  
Audrius Krukonis ◽  
Vaiva Šlegerytė ◽  
Rytis Maskeliūnas ◽  
...  
Keyword(s):  
Numerical Methods ◽  
Design Process ◽  
Method Of Moments ◽  
Experimental Results ◽  
Reflection Factor ◽  
Transmission Factor ◽  
Feed Forward ◽  
New Methods ◽  
Backpropagation Network ◽  
Hidden Layer

The process of designing microwave devices is difficult and time-consuming because the analytical and numerical methods used in the design process are complex. Therefore, it is necessary to search for new methods that will allow for an acceleration of synthesis and analytic procedures. This is especially important in cases where the procedures of synthesis and analysis have to be repeated many times, until the correct device configuration is found. Artificial neural networks are one of the possible alternatives for the acceleration of the design process. In this paper we present a procedure for analyzing a hybrid meander system (HMS) using the feed-forward backpropagation network (FFBN). We compared the prediction results of the transmission factor and the reflection factor , obtained using the FFBN, with results obtained using traditional analytical and numerical methods, as well as with experimental results. The comparisons show that prediction results significantly depend on the FFBN structure. In terms of the lowest difference between the characteristics calculated using the method of moments (MoM) and characteristics predicted using the FFBN, the best prediction was achieved using the FFBN with three hidden layers, which included 18 neurons in the first hidden layer, 14 neurons in the second hidden layer, and 2 neurons in the third hidden layer. Differences between the predicted and calculated results did not exceed 7% for the parameter and 5% for the parameter. The prediction of parameters using the FFBN allowed the analysis procedure to be sped up from hours to minutes. The experimental results correlated with the predicted characteristics.

2-D gravity modeling with analytically defined geometry and quadratic polynomial density functions

Geophysics ◽  
1999 ◽  
Vol 64 (6) ◽  
pp. 1730-1734 ◽  
Author(s):  
Beatriz Martín‐Atienza ◽  
Juan García‐Abdeslem
Keyword(s):  
Numerical Methods ◽  
Polynomial Function ◽  
Continuous Functions ◽  
Model Solution ◽  
Gravity Modeling ◽  
Density Functions ◽  
Gravity Effect ◽  
New Methods ◽  
Order Polynomial ◽  
Broad Variety

New methods for 2-D modeling of gravity anomaly data are developed following an approach that uses both analytic and numerical methods of integration. The forward‐model solution developed here is suitable to calculate the gravity effect caused by a 2-D source body bounded either laterally or vertically by continuous functions. In our models, the density contrast is defined by a second‐order polynomial function of depth and distance along the profile. We present several examples to show that our models are capable of accommodating a broad variety of geologic structures.

Yacht Design with Computers: New Methods for New Tools

1983 ◽  
Author(s):  
George S. Hazen ◽  
Steve Killing
Keyword(s):  
Design Process ◽  
Preliminary Design ◽  
Original Design ◽  
New Methods ◽  
Design Office ◽  
Final Design ◽  
Cad Cam

From the perspective of the design office, this paper examines the manner in which computers are streamlining and changing the design process for today's sailing yachts. Starting with preliminary design and progressing through the more detailed aspects of final design, the computer's varying roles in the design process are traced with examples drawn from currently implemented programs. In addition to its customary role as a bookkeeper, the computer's remarkable graphics capabilities are highlighted. The authors offer a glimpse of what programs and hardware tomorrow's yacht designer will use as frequently as his curves and battens. The paper covers such subjects as design follow-up, sailing analysis and feedback into the original design process. Since designers are not the only ones to benefit from the computer revolution, the authors have included sections on computer generated sailing aids for the yachtsman and possible CAD/CAM applications for the boatbuilder.

Optimization Methods for Calculating Design Imprecision

1995 ◽  
Author(s):  
William S. Law ◽  
Erik K. Antonsson
Keyword(s):  
Fuzzy Sets ◽  
Design Process ◽  
Optimization Methods ◽  
Experiment Design ◽  
Design Evaluation ◽  
Preliminary Design ◽  
New Methods ◽  
Evaluation Functions ◽  
Incomplete Design ◽  
Alternative Designs

Abstract The preliminary design process is characterized by imprecision: the vagueness of an incomplete design description. The Method of Imprecision uses the mathematics of fuzzy sets to explicitly represent and manipulate imprecise preliminary design information, enabling the designer to explore the space of alternative designs in the context of the designer and customer’s preferences among alternatives. This paper introduces new methods to perform Method of Imprecision calculations for general non-monotonic design evaluation functions that address the practical necessity to minimize the number of function evaluations. These methods utilize optimization and experiment design.

Verification of the feed-forward control for a piezoelectric actuator using differential flatness approach

2018 ◽  
Vol 30 (3) ◽  
pp. 438-444
Author(s):  
Jomah Alzoubi ◽  
Shadi A Alboon ◽  
Amin Alqudah
Keyword(s):  
Mobile Devices ◽  
Piezoelectric Actuator ◽  
Experimental Results ◽  
Control Voltage ◽  
Differential Flatness ◽  
Digital Cameras ◽  
Precise Positioning ◽  
Feed Forward ◽  
Feed Forward Control ◽  
Micro Technology

In the last decade, the applications of nano- and micro-technology are widely used in many fields. In the modern mobile devices, such as digital cameras, there is an increased demand to achieve fast and precise positioning for some parts such as the recording sensor. Therefore, a smart material (piezoelectric) is used to achieve this requirement. This article discusses the feed-forward control for a piezoelectric actuator using differential flatness approach. The differential flatness approach is used to calculate the required voltage to control the piezoelectric actuator movement. The control voltage will be applied to the real actuator. The simulation and experimental results are compared for the actuator. The aim of this article is to verify the feed-forward control for second eigenfrequency using the differential flatness approach for the piezoelectric actuator.

scholarly journals Engineering Design Driven by Models and Measures: The Case of a Rigid Inflatable Boat

2018 ◽  
Author(s):  
Cristiano Fragassa
Keyword(s):  
Numerical Methods ◽  
Engineering Design ◽  
Design Process ◽  
Experimental Approach ◽  
Numerical Models ◽  
Stress And Strain ◽  
Engineering Design Process ◽  
Hull Slamming ◽  
Available Information ◽  
Special Case

Rigid-hulled inflatable boats are extremely practical and popular nowadays. They offer a effective conciliation among usability and costs. Their stable and seaworthy behaviour is guaranteed by performing hydroplaning hulls coupled with unsinkable inflated tubes. At the same time, their design is often based on tradition and preconceptions. Rarely, the design assumptions are validated by the reality or, even, by deeper investigations. In this article, both numerical methods and experimental mechanics techniques are proposed as an essential way for supporting the designers in their decisive tasks. Three different situations are detailed where a numerical or an experimental approach shows its benefit inside the engineering design process: firstly permitting to investigate the behaviour of materials driving the fiberglass selection; then measuring the levels of stress and strain in the hull during sailing; finally, using all available information as a base for developing numerical models of the hull slamming in waves. Even if the discussion is focused on a rigid inflatable boat, large part of its considerations is relevant beyond this special case.

Roll-Gap Control System of Twin Roll Strip Caster Based on Feed Forward-Feedback

2013 ◽  
Vol 750 ◽  
pp. 64-67
Author(s):  
Wen Yu Zhang ◽  
Dong Ying Ju ◽  
Yao Yao ◽  
Hong Yang Zhao ◽  
Xiao Dong Hu ◽  
...  
Keyword(s):  
Control System ◽  
Control Strategy ◽  
Feedback System ◽  
Experimental Results ◽  
Convergence Time ◽  
Feed Forward ◽  
Gap Control ◽  
Roll Gap ◽  
Twin Roll

In this paper, the established control system and its control algorism of a new twin roll strip caster developed by authors is presented. It is illustrated the roll-gap control strategy of the twin roll strip caster based on a feed forward-feedback system. From the experimental results, the susceptibility of control convergence time, stable and accurate are shown on a higher level than traditional control strategy.

Convergence of a modified gradient-based learning algorithm with penalty for single-hidden-layer feed-forward networks

2018 ◽  
Vol 32 (7) ◽  
pp. 2445-2456 ◽  
Author(s):  
Jian Wang ◽  
Bingjie Zhang ◽  
Zhaoyang Sang ◽  
Yusong Liu ◽  
Shujun Wu ◽  
...  
Keyword(s):  
Learning Algorithm ◽  
Feed Forward ◽  
Gradient Based ◽  
Hidden Layer

Design of diversified teaching platform of college aerobics course based on artificial intelligence

2021 ◽  
pp. 1-13
Author(s):  
Fengping Huang
Keyword(s):  
Artificial Intelligence ◽  
Design Process ◽  
Experimental Results ◽  
Average Score ◽  
Network Teaching ◽  
Teaching Platform ◽  
Student Grouping ◽  
Function Module ◽  
And Function

In order to improve the diversified teaching effect of a college aerobics course, effectively improve the accuracy of student grouping on the teaching platform, a diversified teaching platform of college aerobics course based on artificial intelligence is designed. First of all, it puts forward the construction idea and design process of the network teaching platform, then designs the interface and function module of the teaching platform, and finally designs the grouping function of teaching objects, so as to complete the design of the diversified teaching platform of a college aerobics course based on artificial intelligence. The experimental results show that the grouping accuracy of students on the diversified teaching platform of college aerobics course based on artificial intelligence is greater than 75%, and the average score of students studying on the platform is 74.66. This explains why the designed platform can effectively provide the accuracy of grouping and the students’ performance.

scholarly journals Feed Forward Neural Network Modeling for Rainfall Prediction

2018 ◽  
Vol 73 ◽  
pp. 05017
Author(s):  
Yasin Hasbi ◽  
Warsito Budi ◽  
Santoso Rukun
Keyword(s):  
Neural Network ◽  
Autocorrelation Function ◽  
Seasonal Pattern ◽  
Optimization Method ◽  
Rainfall Data ◽  
Neural Network Modeling ◽  
Least Mean Square ◽  
Feed Forward Neural Network ◽  
Feed Forward ◽  
Hidden Layer

Prediction of rainfall data by using Feed Forward Neural Network (FFNN) model is proposed. FFNN is a class of neural network which has three layers for processing. In time series prediction, including in case of rainfall data, the input layer is the past values of the same series up to certain lag and the output layer is the current value. Beside a few lagged times, the seasonal pattern also considered as an important aspect of choosing the potential input. The autocorrelation function and partial autocorrelation function patterns are used as aid of selecting the input. In the second layer called hidden layer, the logistic sigmoid is used as activation function because of the monotonic and differentiable. Processing is done by the weighted summing of the input variables and transfer process in the hidden layer. Backpropagation algorithm is applied in the training process. Some gradient based optimization methods are used to obtain the connection weights of FFNN model. The prediction is the output resulting of the process in the last layer. In each optimization method, the looping process is performed several times in order to get the most suitable result in various composition of separating data. The best one is chosen by the least mean square error (MSE) criteria. The least of in-sample and out-sample predictions from the repeating results been the base of choosing the best optimization method. In this study, the model is applied in the ten-daily rainfall data of ZOM 136 Cokrotulung Klaten. Simulation results give a consecution that the more complex architecture is not guarantee the better prediction.

scholarly journals Theory and Numerical Analysis of Extreme Learning Machine and Its Application for Different Degrees of Defect Recognition of Hoisting Wire Rope

2018 ◽  
Vol 2018 ◽  
pp. 1-13 ◽  
Author(s):  
Zhike Zhao ◽  
Xiaoguang Zhang
Keyword(s):  
Extreme Learning Machine ◽  
Performance Test ◽  
Research Problem ◽  
Wire Rope ◽  
Nondestructive Method ◽  
Experimental Results ◽  
Feed Forward Neural Network ◽  
Learning Machine ◽  
Hidden Layer ◽  
Hidden Nodes

An improved classification approach is proposed to solve the hot research problem of some complex multiclassification samples based on extreme learning machine (ELM). ELM was proposed based on the single-hidden layer feed-forward neural network (SLFNN). ELM is characterized by the easier parameter selection rules, the faster converge speed, the less human intervention, and so on. In order to further improve the classification precision of ELM, an improved generation method of the network structure of ELM is developed by dynamically adjusting the number of hidden nodes. The number change of the hidden nodes can serve as the computational updated step length of the ELM algorithm. In this paper, the improved algorithm can be called the variable step incremental extreme learning machine (VSI-ELM). In order to verify the effect of the hidden layer nodes on the performance of ELM, an open-source machine learning database (University of California, Irvine (UCI)) is provided by the performance test data sets. The regression and classification experiments are used to study the performance of the VSI-ELM model, respectively. The experimental results show that the VSI-ELM algorithm is valid. The classification of different degrees of broken wires is now still a problem in the nondestructive testing of hoisting wire rope. The magnetic flux leakage (MFL) method of wire rope is an efficient nondestructive method which plays an important role in safety evaluation. Identifying the proposed VSI-ELM model is effective and reliable for actually applying data, and it is used to identify the classification problem of different types of samples from MFL signals. The final experimental results show that the VSI-ELM algorithm is of faster classification speed and higher classification accuracy of different broken wires.

Sign in / Sign up

Export Citation Format

Share Document