scholarly journals A Comparative Study between Regression and Neural Networks for Modeling Al6082-T6 Alloy Drilling

Machines ◽  
2019 ◽  
Vol 7 (1) ◽  
pp. 13 ◽  
Author(s):  
Nikolaos Karkalos ◽  
Nikolaos Efkolidis ◽  
Panagiotis Kyratsis ◽  
Angelos Markopoulos
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Regression Model ◽  
Soft Computing ◽  
Regression Models ◽  
Fuzzy Inference ◽  
Process Conditions ◽  
Neural Network Models ◽  
Inference System ◽  
Computing Models

Apart from experimental research, the development of accurate and efficient models is considerably important in the field of manufacturing processes. Initially, regression models were significantly popular for this purpose, but later, the soft computing models were proven as a viable alternative to the established models. However, the effectiveness of soft computing models can be often dependent on the size of the experimental dataset, and it can be lower compared to that of the regression models for a small-sized dataset. In the present study, it is intended to conduct a comparison of the performance of various neural network models, such as the Multi-layer Perceptron (MLP), the Radial Basis Function Neural Network (RBF-NN), and the Adaptive Neuro-Fuzzy Inference System (ANFIS) models with the performance of a multiple regression model. For the development of the models, data from drilling experiments on an Al6082-T6 workpiece for various process conditions are employed, and the performance of models related to thrust force (Fz) and cutting torque (Mz) is assessed based on several criteria. From the analysis, it was found that the MLP models were superior to the other neural networks model and the regression model, as they were able to achieve a relatively lower prediction error for both models of Fz and Mz.

Artificial neural network and regression models for prediction of sewing thread consumption for multilayered fabric assembly at lockstitch 301 seam

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Md Vaseem Chavhan ◽  
M. Ramesh Naidu ◽  
Hayavadana Jamakhandi
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Regression Model ◽  
Regression Models ◽  
Network Models ◽  
Quadratic Regression ◽  
Neural Network Models ◽  
Content Type ◽  
Sewing Thread ◽  
Artificial Neural

Purpose This paper aims to propose the artificial neural network (ANN) and regression models for the estimation of the thread consumption at multilayered seam assembly stitched with lock stitch 301. Design/methodology/approach In the present study, the generalized regression and neural network models are developed by considering the fabric types: woven, nonwoven and multilayer combination thereof, with basic sewing parameters: sewing thread linear density, stitch density, needle count and fabric assembly thickness. The network with feed-forward backpropagation is considered to build the ANN, and the training function trainlm of MATLAB software is used to adjust weight and basic values according to the optimization of Levenberg Marquardt. The performance of networks measured in terms of the mean squared error and the layer output is set according to the sigmoid transfer function. Findings The proposed ANN and regression model are able to predict the thread consumption with more accuracy for multilayered seam assembly. The predictability of thread consumption from available geometrical models, regression models and industrial empirical techniques are compared with proposed linear regression, quadratic regression and neural network models. The proposed quadratic regression model showed a good correlation with practical thread consumption value and more accuracy in prediction with an overall 4.3% error, as compared to other techniques for given multilayer substrates. Further, the developed ANN network showed good accuracy in the prediction of thread consumption. Originality/value The estimation of thread consumed while stitching is the prerequisite of the garment industry for inventory management especially with the introduction of the costly high-performance sewing thread. In practice, different types of fabrics are stitched at multilayer combinations at different locations of the stitched product. The ANN and regression models are developed for multilayered seam assembly of woven and nonwoven fabric blend composition for better prediction of thread consumption.

scholarly journals Prediction of daily streamflow using artificial neural networks (ANNs), wavelet neural networks (WNNs), and adaptive neuro-fuzzy inference system (ANFIS) models

2020 ◽  
Vol 20 (4) ◽  
pp. 1396-1408
Author(s):  
Hüseyin Yıldırım Dalkiliç ◽  
Said Ali Hashimi
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Water Resources ◽  
Fuzzy Inference System ◽  
Fuzzy Inference ◽  
Hydrological Processes ◽  
Inference System ◽  
Daily Streamflow ◽  
Neuro Fuzzy ◽  
Artificial Neural

Abstract In recent years, the prediction of hydrological processes for the sustainable use of water resources has been a focus of research by scientists in the field of hydrology and water resources. Therefore, in this study, the prediction of daily streamflow using the artificial neural network (ANN), wavelet neural network (WNN) and adaptive neuro-fuzzy inference system (ANFIS) models were taken into account to develop the efficiency and accuracy of the models' performances, compare their results and explain their outcomes for future study or use in hydrological processes. To validate the performance of the models, 70% (1996–2007) of the data were used to train them and 30% (2008–2011) of the data were used to test them. The estimated results of the models were evaluated by the root mean square error (RMSE), determination coefficient (R2), Nash–Sutcliffe (NS), and RMSE-observation standard deviation ratio (RSR) evaluation indexes. Although the outcomes of the models were comparable, the WNN model with RMSE = 0.700, R2 = 0.971, NS = 0.927, and RSR = 0.270 demonstrated the best performance compared to the ANN and ANFIS models.

Thermal Errors Modeling of a CNC Machine’s Axis Using Neural Network and Fuzzy Logic

2011 ◽  
Vol 110-116 ◽  
pp. 2976-2982 ◽  
Author(s):  
Sina Eskandari ◽  
Behrooz Arezoo ◽  
Amir Abdullah
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Fuzzy Logic ◽  
Mean Squared Error ◽  
Fuzzy Inference ◽  
Previous Method ◽  
Data Set ◽  
Inference System ◽  
Thermal Errors ◽  
Squared Error

Thermal errors of CNC machines have significant effects on precision of a workpiece. One of the approaches to reduce these errors is modeling and on-line compensating them. In this study, thermal errors of an axis of the machine are modeled by means of artificial neural networks along with fuzzy logic. Models are created using experimental data. In neural networks modeling, MLP type which has 2 hidden layers is chosen and it is trained by backpropagation algorithm. Finally, the model is validated with the aid of calculating mean squared error and correlation coefficients between outputs of the model and a checking data set. On the other hand, an adaptive neuro-fuzzy inference system is utilized in fuzzy modeling which uses neural network to develop membership functions as fuzzifiers and defuzzifiers. This network is trained by hybrid algorithm. At the end, model validation is done by mean squared error like previous method. The results show that the errors of both modeling techniques are acceptable and models can predict thermal errors reliably.

Fuzzy wavelet neural networks applied as inferential sensors of neonatal incubator dynamics

2020 ◽  
Vol 39 (3) ◽  
pp. 2567-2579
Author(s):  
José M. Araújo Júnior ◽  
Leandro L.S. Linhares ◽  
Fábio M.U. Araújo ◽  
Otacílio M. Almeida
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Fuzzy Inference ◽  
Good Health ◽  
Great Difficulty ◽  
Neural System ◽  
Wavelet Neural Network ◽  
The Body ◽  
Inference System ◽  
Health Complications

Newborns with health complications have great difficulty in regulating the body temperature due to distinct factors, which include the high metabolism rate and low weight. In this context, neonatal incubators help maintaining good health conditions because they provide a thermally-neutral environment, which is adequate to ensure the least energy expenditure by the newborn. In the last decades, artificial neural networks (ANNs) have been established as one of the main tools for the identification of nonlinear systems. Among the various approaches used in the identification process, the fuzzy wavelet neural network (FWNN) can be regarded as a prominent technique, consisting of the combination of wavelet neural network (WNN) and adaptive network-based fuzzy inference system (ANFIS). This work proposes the use of FWNN to infer the temperature and humidity values inside the incubator in order to certify the equipment operation. Results obtained with the analyzed neural system have shown the generalization and inference capacities of FWNNs, thus allowing their application to practical tasks aiming to increase the efficiency of incubators.

EVOLVING RBF NEURAL NETWORKS FOR ADAPTIVE SOFT-SENSOR DESIGN

2013 ◽  
Vol 23 (06) ◽  
pp. 1350029 ◽  
Author(s):  
ALEX ALEXANDRIDIS
Keyword(s):  
Neural Networks ◽  
Fuzzy Inference ◽  
Rbf Neural Network ◽  
Network Models ◽  
Recursive Least Squares ◽  
Rbf Neural Networks ◽  
Soft Sensors ◽  
Neural Network Models ◽  
Inference System ◽  
Rbf Network

This work presents an adaptive framework for building soft-sensors based on radial basis function (RBF) neural network models. The adaptive fuzzy means algorithm is utilized in order to evolve an RBF network, which approximates the unknown system based on input–output data from it. The methodology gradually builds the RBF network model, based on two separate levels of adaptation: On the first level, the structure of the hidden layer is modified by adding or deleting RBF centers, while on the second level, the synaptic weights are adjusted with the recursive least squares with exponential forgetting algorithm. The proposed approach is tested on two different systems, namely a simulated nonlinear DC Motor and a real industrial reactor. The results show that the produced soft-sensors can be successfully applied to model the two nonlinear systems. A comparison with two different adaptive modeling techniques, namely a dynamic evolving neural-fuzzy inference system (DENFIS) and neural networks trained with online backpropagation, highlights the advantages of the proposed methodology.

Soft computing techniques for compressive strength prediction of concrete cylinders strengthened by CFRP composites

2015 ◽  
Vol 22 (1) ◽  
pp. 97-112 ◽  
Author(s):  
Mostafa Jalal
Keyword(s):  
Compressive Strength ◽  
Soft Computing ◽  
Fuzzy Inference ◽  
Concrete Strength ◽  
Experimental Results ◽  
Inference System ◽  
Cfrp Composites ◽  
Soft Computing Techniques ◽  
Concrete Cylinders ◽  
Computing Models

AbstractThis study presents the application of soft computing techniques, namely, as multiple regressions (MRs), neural networks (NNs), genetic programming (GP), and adaptive neuro-fuzzy inference system (ANFIS) for modeling of compressive strength of carbon fiber-reinforced polymer (CFRP) confined concrete cylinders. The proposed soft computing models are based on experimental results collected from literature. They represent the ultimate strength of concrete cylinders after confinement with CFRP composites, which is in terms of diameter and height of the cylindrical specimen, ultimate circumferential strain in the CFRP jacket, elastic modulus of CFRP, unconfined concrete strength, and total thickness of CFRP layer used. The accuracy of the proposed soft computing models is very satisfactory compared to experimental results. Moreover, the results of proposed soft computing models are compared with five models existing in the literature proposed by various researchers so far and are found to be, by far, more accurate.

scholarly journals COVID-19 mortality rate prediction for India using statistical neural networks and gaussian process regression model

2021 ◽  
Vol 21 (1) ◽  
pp. 194-206
Author(s):  
S Dhamodharavadhani ◽  
R Rathipriya
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Mortality Rate ◽  
Regression Model ◽  
Gaussian Process ◽  
Learning Process ◽  
Regression Models ◽  
Gaussian Process Regression ◽  
Statistical Neural Networks ◽  
Death Cases

The primary purpose of this research is to identify the best COVID-19 mortality model for India using regression models and is to estimate the future COVID-19 mortality rate for India. Specifically, Statistical Neural Networks ( Radial Basis Function Neural Network (RBFNN), Generalized Regression Neural Network (GRNN)), and Gaussian Process Regression (GPR) are applied to develop the COVID-19 Mortality Rate Prediction (MRP) model for India. For that purpose, there are two types of dataset used in this study: One is COVID-19 Death cases, a Time Series Data and the other is COVID-19 Confirmed Case and Death Cases where Death case is dependent variable and the Confirmed case is an independent varia- ble. Hyperparameter optimization or tuning is used in these regression models, which is the process of identifying a set of optimal hyperparameters for any learning process with minimal error. Here, sigma (σ) is a hyperparameter whose value is used to constrain the learning process of the above models with minimum Root Mean Squared Error (RMSE). The perfor- mance of the models is evaluated using the RMSE and 'R2 values, which shows that the GRP model performs better than the GRNN and RBFNN. Keywords: Covid-19; India; mortality rate; mortality prediction; regression model; hyperparameter tuning; GPR; GRNN; RBFNN.

scholarly journals A critical review of theoretical models for estimating global so-lar radiation between 2012-2016 in Nigeria

2017 ◽  
Vol 5 (2) ◽  
pp. 60 ◽  
Author(s):  
Samuel Nwokolo ◽  
Julie Ogbulezie
Keyword(s):  
Solar Radiation ◽  
Soft Computing ◽  
Fuzzy Inference ◽  
Theoretical Models ◽  
Global Solar Radiation ◽  
Empirical Models ◽  
Neural Network Models ◽  
Inference System ◽  
Input Parameters ◽  
Functional Forms

A routinely research of solar radiation is of vital requirement for surveys in agronomy, hydrology, ecology and sizing of the photovoltaic or thermal solar systems, solar architecture, molten salt power plant and supplying energy to natural processes like photosynthesis and estimates of their performances. However, measurement of global solar radiation is not available in most locations across in Nigeria. During the past 5 years in order to estimate global solar radiation on the horizontal surface on both daily and monthly mean daily basis, numerous empirical models have been developed for several locations in Nigeria. As a result, various input parameters have been utilized and different functional forms used. In this study aims at comparing, classifying and reviewing the empirical and soft computing models applied for estimating global solar radiation. The empirical models so far utilized were classified into eight main categories and presented based on the input parameters employed. The models were further reclassified into several main sub-classes and finally represented according to their developing year. On the whole, 145 empirical models and 42 functional forms, 8 artificial neural network models, 1 adaptive neural fuzzy inference system approach, and 1 Autoregressive Moving Average methods were recorded in literature for estimating global solar radiation in Nigeria. This review would provide solar-energy researchers in terms of identifying the input parameters and functional forms widely employed up until now as well as recognizing their importance for estimating global solar radiation using soft computing empirical models in several locations in Nigeria.

Selection of the Staff With the Use of Soft Computing

2018 ◽  
Vol 6 (6) ◽  
pp. 61-65
Author(s):  
Михаил Кричевский ◽  
Mihail Krichevskiy
Keyword(s):  
Neural Networks ◽  
Soft Computing ◽  
Fuzzy Systems ◽  
Fuzzy Inference ◽  
Training Methods ◽  
Evolutionary Computations ◽  
Inference System ◽  
Inaccurate Information ◽  
Neural Fuzzy

In a changing environment and inaccurate information, it is difficult to get an unambiguous answer about the quality of the candidate for the position, based only on the results of viewing the applicant’s questionnaires. As a consequence, recently there has been a trend towards the use of soft computing (neural networks, fuzzy logic and evolutionary computations) in tasks personnel’s selection. The article presents the solution of such a problem using the methods of soft computing for a software company. We use a neural-fuzzy system such as the ANFIS (Adaptive Network-Based Fuzzy Inference System) to quantify the candidate’s quality. The idea of neural-fuzzy systems is to determine the parameters of fuzzy systems through training methods used in neural networks. The most important advantage of this system lies in the automatic creation of the rules base. After completing the training, we receive an assessment of the quality of the candidate in the form of a scoring on a 10-point scale. In addition, we derive a regression equation that relates the candidate’s quality with the input variables.

Sign in / Sign up

Export Citation Format

Share Document