Statistically Validated and Optimized Tabu Search Estimation of Cutting Tool Life in Turning

2018 ◽  
Author(s):  
Ré-Mi Hage ◽  
Ilige Hage ◽  
Chady Ghnatios ◽  
Ramsey Hamade
Keyword(s):  
Tabu Search ◽  
Tool Life ◽  
Statistical Significance ◽  
Absolute Error ◽  
Percentage Error ◽  
Depth Of Cut ◽  
Orthogonal Array Method ◽  
Mathematical Expressions ◽  
Experimental Values ◽  
Optimal Set

In machining, tool life is the measure that gives manufacturers fundamental indications on useful tool utilization. In this work, investigated is the influence of turning parameters such as spindle speed, depth of cut, and tool feed on tool life. Literature-reported studies typically utilize Taguchi orthogonal array method for experimental design while tool-wear estimates utilized mathematical expressions by means ofregression analysis. In this work, the authors combine a tabu search (TS) algorithm with the traditional regression analysis (REG) to introduce a combined (TS-REG) scheme that minimizes a weighted sum of the outputs that represent different measures of turning quality. The aim in this paper is to show that the proposed novel combination TS-REG reaches better fitted models in minimal time as compared with other statistical methods. Tool life estimates are plotted versus different turning process parameters. The results that represent optimized tool life of the process are compared to literature reported experimental values. Good correlations confirm desirable efficiency and the ability of the TS-REG method in estimating tool life in turning. In order to determine statistical significance decisions, both p-values and mean absolute percentage error (MAPE: mean of the relative absolute error) were employed. The TS-REG method aids in determining the optimal set of parameters for any combination of the weighting factors resulting in improved tool life.

An Improved Model of Estimation Global Solar Irradiation From in Situ Data: Case of Algerian Oranie’s Region

2020 ◽  
Vol 142 (3) ◽  
Author(s):  
Houcine Naim ◽  
Redouane Fares ◽  
Abed Bouadi ◽  
Abdelatif Hassini ◽  
Benabadji Noureddine
Keyword(s):  
Meteorological Parameter ◽  
Absolute Error ◽  
Solar Irradiation ◽  
Mean Bias Error ◽  
Percentage Error ◽  
Bias Error ◽  
In Situ Data ◽  
Experimental Values ◽  
Improved Model

Abstract The total monthly average of daily radiation on a horizontal surface at the site of Oran (35.38 deg N, 0.37 deg W) is achieved by applying two models. We present a comparison between the first one which is a regression equation of the Angstrom type and the second model, developed by the present authors: Some modifications were recommended using relative humidity as the input meteorological parameter) and longitude, latitude, and altitude as the astronomical parameters. The process of examining similarities is made using root mean square error (RMSE), the mean bias error (MBE), mean absolute error (MAE), and mean absolute percentage error (MAPE). This comparison shows that the second model is closer to the experimental values of the Angstrom model.

Experimental and Numerical Investigation into Residual Stress During Turning Operation for Stainless Steel AISI 316

2020 ◽  
Vol 38 (12A) ◽  
pp. 1862-1870
Author(s):  
Safa M. Lafta ◽  
Maan A. Tawfiq
Keyword(s):  
Stainless Steel ◽  
Residual Stresses ◽  
Orthogonal Cutting ◽  
Cutting Tools ◽  
Cutting Speed ◽  
Percentage Error ◽  
Depth Of Cut ◽  
Main Role ◽  
Turning Operation ◽  
Aisi 316

RS (residual stresses) represent the main role in the performance of structures and machined parts. The main objective of this paper is to investigate the effect of feed rate with constant cutting speed and depth of cut on residual stresses in orthogonal cutting, using Tungsten carbide cutting tools when machining AISI 316 in turning operation. AISI 316 stainless steel was selected in experiments since it is used in many important industries such as chemical, petrochemical industries, power generation, electrical engineering, food and beverage industry. Four feed rates were selected (0.228, 0.16, 0.08 and 0.065) mm/rev when cutting speed is constant 71 mm/min and depth of cutting 2 mm. The experimental results of residual stresses were (-15.75, 12.84, 64.9, 37.74) MPa and the numerical results of residual stresses were (-15, 12, 59, and 37) MPa. The best value of residual stresses is (-15.75 and -15) MPa when it is in a compressive way. The results showed that the percentage error between numerical by using (ABAQUS/ CAE ver. 2017) and experimental work measured by X-ray diffraction is range (2-15) %.

Quantification of tool chatter and metal removal rate using wavelet denoising and statistical approach

2018 ◽  
Vol 49 (2) ◽  
pp. 62-81 ◽  
Author(s):  
Shailendra Kumar ◽  
Bhagat Singh
Keyword(s):  
Response Surface Methodology ◽  
Response Surface ◽  
Metal Removal ◽  
Removal Rate ◽  
Statistical Significance ◽  
Depth Of Cut ◽  
Machining Parameters ◽  
Metal Removal Rate ◽  
Chatter Index ◽  
Tool Chatter

Tool chatter is an unavoidable phenomenon encountered in machining processes. Acquired raw chatter signals are contaminated with various types of ambient noises. Signal processing is an efficient technique to explore chatter as it eliminates unwanted background noise present in the raw signal. In this study, experimentally recorded raw chatter signals have been denoised using wavelet transform in order to eliminate the unwanted noise inclusions. Moreover, effect of machining parameters such as depth of cut ( d), feed rate ( f) and spindle speed ( N) on chatter severity and metal removal rate has been ascertained experimentally. Furthermore, in order to quantify the chatter severity, a new parameter called chatter index has been evaluated considering aforesaid denoised signals. A set of 15 experimental runs have been performed using Box–Behnken design of experiment. These experimental observations have been used to develop mathematical models for chatter index and metal removal rate considering response surface methodology. In order to check the statistical significance of control parameters, analysis of variance has been performed. Furthermore, more experiments are conducted and these results are compared with the theoretical ones in order to validate the developed response surface methodology model.

Tool Life Analysis when Turning Ti-6Al-4V Using Vegetable Oil-Based Cutting Fluid

2017 ◽  
Vol 882 ◽  
pp. 36-40
Author(s):  
Salah Gariani ◽  
Islam Shyha ◽  
Connor Jackson ◽  
Fawad Inam
Keyword(s):  
Tool Wear ◽  
Tool Life ◽  
Vegetable Oil ◽  
Flank Wear ◽  
Cutting Speed ◽  
Fractional Factorial ◽  
Cutting Fluid ◽  
Depth Of Cut ◽  
Tool Flank Wear ◽  
Fluid Concentration

This paper details experimental results when turning Ti-6Al-4V using water-miscible vegetable oil-based cutting fluid. The effects of coolant concentration and working conditions on tool flank wear and tool life were evaluated. L27 fractional factorial Taguchi array was employed. Tool wear (VBB) ranged between 28.8 and 110 µm. The study concluded that a combination of VOs based cutting fluid concentration (10%), low cutting speed (58 m/min), feed rate (0.1mm/rev) and depth of cut (0.75mm) is necessary to minimise VBB. Additionally, it is noted that tool wear was significantly affected by cutting speeds. ANOVA results showed that the cutting fluid concentration is statistically insignificant on tool flank wear. A notable increase in tool life (TL) was recorded when a lower cutting speed was used.

scholarly journals Novel Spatiotemporal Feature Extraction Parallel Deep Neural Network for Forecasting Confirmed Cases of Coronavirus Disease 2019

2020 ◽  
Author(s):  
Chiou-Jye Huang ◽  
Yamin Shen ◽  
Ping-Huan Kuo ◽  
Yung-Hsiang Chen
Keyword(s):  
Neural Network ◽  
Deep Neural Network ◽  
Absolute Error ◽  
Mean Absolute Percentage Error ◽  
The Other ◽  
Percentage Error ◽  
Model Assessment ◽  
Absolute Percentage Error ◽  
Spatiotemporal Feature ◽  
The Mean

AbstractThe coronavirus disease 2019 pandemic continues as of March 26 and spread to Europe on approximately February 24. A report from April 29 revealed 1.26 million confirmed cases and 125 928 deaths in Europe. This study proposed a novel deep neural network framework, COVID-19Net, which parallelly combines a convolutional neural network (CNN) and bidirectional gated recurrent units (GRUs). Three European countries with severe outbreaks were studied—Germany, Italy, and Spain—to extract spatiotemporal feature and predict the number of confirmed cases. The prediction results acquired from COVID-19Net were compared to those obtained using a CNN, GRU, and CNN-GRU. The mean absolute error, mean absolute percentage error, and root mean square error, which are commonly used model assessment indices, were used to compare the accuracy of the models. The results verified that COVID-19Net was notably more accurate than the other models. The mean absolute percentage error generated by COVID-19Net was 1.447 for Germany, 1.801 for Italy, and 2.828 for Spain, which were considerably lower than those of the other models. This indicated that the proposed framework can accurately predict the accumulated number of confirmed cases in the three countries and serve as a crucial reference for devising public health strategies.

scholarly journals Predicting the Istanbul Stock Exchange Index Return using Technical Indicators

2013 ◽  
Vol 2 (3) ◽  
pp. 111-117
Author(s):  
Senol Emir
Keyword(s):  
Stock Exchange ◽  
Absolute Error ◽  
Percentage Error ◽  
Support Vector ◽  
Model Parameters ◽  
Technical Indicators ◽  
Istanbul Stock Exchange ◽  
Vector Machines ◽  
Classical Linear Regression ◽  
Daily Returns

The aim of this study to examine the performance of Support Vector Regression (SVR) which is a novel regression method based on Support Vector Machines (SVM) approach in predicting the Istanbul Stock Exchange (ISE) National 100 Index daily returns. For bechmarking, results given by SVR were compared to those given by classical Linear Regression (LR). Dataset contains 6 technical indicators which were selected as model inputs for 2005-2011 period. Grid search and cross valiadation is used for finding optimal model parameters and evaluating the models. Comparisons were made based on Root Mean Square (RMSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), Theil Inequality Coefficient (TIC) and Mean Mixed Error (MME) metrics. Results indicate that SVR outperforms the LR for all metrics.

A method for predicting the capacity of a lithium-ion battery based on deep neural network

2021 ◽  
Author(s):  
JamesChan
Keyword(s):  
Neural Network ◽  
Deep Neural Network ◽  
Lithium Ion ◽  
Chemical Conversion ◽  
Absolute Error ◽  
Production Costs ◽  
Percentage Error ◽  
Average Percentage ◽  
True Value ◽  
Battery Capacity

This paper proposes a solution to predict the capacity of the lithium-ion battery's capacity division process using deep learning methods. This solution extracts the physical observation records of part of the process steps from the chemical conversion and volumetric processes as features, and trains a Deep Neural Network (DNN) to achieve accurate prediction of battery capacity. According to the test, the average percentage absolute error (Mean Absolute Percentage Error, MAPE) of the battery capacity predicted by this model is only 0.78% compared with the true value. Combining this model with the production line can greatly reduce production time and energy consumption, and reduce battery production costs.

Forecasting Malaysian overnight islamic interbank rate using the Box-Jenkins model

2021 ◽  
Vol 2 (1) ◽  
pp. 38-51
Author(s):  
N.S.M. Radzi ◽  
S.R. Yaziz
Keyword(s):  
Monetary Policy ◽  
Mean Absolute Error ◽  
Absolute Error ◽  
Prediction Intervals ◽  
Percentage Error ◽  
Mean Square ◽  
Islamic Banks ◽  
Financial Instruments ◽  
Policy Makers ◽  
Forecasting Performance

Modelling the overnight Islamic interbank rate (IIR) is imperative to define the IIR performance as it would help the Islamic banks to adjust its costs of funding effectively and facilitate the policy makers to regulate a comprehensive monetary policy in Malaysia. The IIR framework which has been regulated by Bank Negara Malaysia under dual banking and financial system has always been overlooked in most previous studies in modelling the financial instruments rates. Therefore, it is vital to select the appropriate model as it resembles with the features of the IIR. The study assesses the forecasting performance of overnight IIR using the Box-Jenkins model. The suggested Box-Jenkins model has been applied to the Malaysian overnight IIR (in percentage) from 02/01/2001 to 31/12/2020. The empirical results determine that ARIMA (0,1,1) is the most appropriate model in forecasting overnight IIR as the model provides the smallest Mean Absolute Error (MAE), Root Mean Square Error (RMSE) and Mean Absolute Percentage Error (MAPE). In multistep ahead forecasting, it can be summarised that ARIMA (0,1,1) model is able to trail the actual data trend of daily Malaysian overnight IIR up to 5-day ahead within 95% prediction intervals.

scholarly journals A Comparison of Models for Estimating Solar Radiation from Sunshine Duration in Croatia

2020 ◽  
Vol 2020 ◽  
pp. 1-14
Author(s):  
Tihomir Betti ◽  
Ivana Zulim ◽  
Slavica Brkić ◽  
Blanka Tuka
Keyword(s):  
Mean Absolute Error ◽  
Sunshine Duration ◽  
Model Performance ◽  
Absolute Error ◽  
Mean Bias Error ◽  
Percentage Error ◽  
Bias Error ◽  
Mean Square ◽  
Using Data ◽  
Statistical Indicators

The performance of seventeen sunshine-duration-based models has been assessed using data from seven meteorological stations in Croatia. Conventional statistical indicators are used as numerical indicators of the model performance: mean absolute percentage error (MAPE), mean bias error (MBE), mean absolute error (MAE), and root-mean-square error (RMSE). The ranking of the models was done using the combination of all these parameters, all having equal weights. The Rietveld model was found to perform the best overall, followed by Soler and Dogniaux-Lemoine monthly dependent models. For three best-performing models, new adjusted coefficients are calculated, and they are validated using separate dataset. Only the Dogniaux-Lemoine model performed better with adjusted coefficients, but across all analysed locations, the adjusted models showed improvement in reduced maximum percentage error.

ARIMA-Based Time Series Model of Cutting Temperature in Facing Process

2019 ◽  
Vol 18 (03) ◽  
pp. 395-411
Author(s):  
Samya Dahbi ◽  
Latifa Ezzine ◽  
Haj El Moussami
Keyword(s):  
Time Series ◽  
Cutting Temperature ◽  
Numerical Control ◽  
Performance Criteria ◽  
Percentage Error ◽  
Depth Of Cut ◽  
Nose Radius ◽  
Machining Processes ◽  
Adequate Model ◽  
Average Percentage

During machining processes, cutting temperature directly affects cutting performances, such as surface quality, dimensional precision, tool life, etc. Thus, evaluation of cutting temperature rise in the tool–chip interface by reliable techniques can lead to improved cutting performances. In this paper, we present the modeling of cutting temperature during facing process by using time series approach. The experimental data were collected by conducting facing experiments on a Computer Numerical Control lathe and by measuring the cutting temperature by an infrared camera. The collected data were used to test several Autoregressive Integrated Moving Average (ARIMA) models by using Box–Jenkins time series procedure. Then, the adequate model was selected according to four performance criteria: Akaike criterion, Schwarz Bayesian criterion, maximum likelihood, and standard error. The selected model corresponded to the ARIMA (1, 1, 1) and it was tested by conducting a new facing operation under the same cutting conditions (spindle speed, feed rate, depth of cut, and nose radius). It was clearly seen that there is a good agreement between experimental and simulated temperatures, which reveals that this approach simulates the evolution of cutting temperature in facing process with high accuracy (average percentage error [Formula: see text] 0.57%).

Sign in / Sign up

Export Citation Format

Share Document