No full-text available
To read the full-text of this research,
you can request a copy directly from the author.
AISI 1040 ÇELİĞİNİN İŞLENEBİLİRLİĞİ SIRASINDA OLUŞAN YÜZEY PÜRÜZLÜLÜĞÜ DEĞERLERİNİN FARKLI TAHMİN MODELLERİ İLE ARAŞTIRILMASI
Abstract
Bu araştırmada, 45 HRc sertlik değerine sahip AISI 1040 çeliği torna tezgahında işlenmiştir. Kesme hızı, ilerleme ve talaş derinliği parametreleri üçer seviye olarak belirlenmiştir. Deney listesi Taguchi L9 ortagonal dizilim ile oluşturulmuştur. Deneyler CNC kontrollü tornada gerçekleştirilmiştir. Tornalama işlemi sonunda ortalama yüzey pürüzlülüğü (Ra), off-line olarak elde edilmiştir. Elde edilen Ra değerleri Taguchi, çoklu regresyon modeli, yapay sinir ağı ve bulanık mantık ile modellenmiştir. Bu modeller arasındaki yüzdesel fark belirlenmiştir. Taguchi yaklaşık %86,27, çoklu regresyon modeli yaklaşık %85,85, yapay sinir ağı yaklaşık %78,92 ve bulanık mantık yaklaşık %93,86 doğrulukla test sonuçlarını tahmin etmiştir.
... Oluşturdukları YSA yöntemiyle, bileşke kuvvet ve yüzey pürüzlülüğünü başarılı bir şekilde elde etmişlerdir. Akkuş [11], AISI 1040 çeliğinde yüzey pürüzlülüğü tahmininde farklı modeller (regresyon, Taguchi, YSA, bulanık mantık) kullanmıştır. Girdi parametreleri olarak; kesme hızı, ilerleme, talaş derinliği parametrelerini kullanmıştır. ...
Machining is one of the most widely used manufacturing processes in the mold industry and which affects the manufacturing cost significantly. Particularly, the desired surface roughness/quality at a low cost at minimum machining time is the ultimate target. Surface quality depends on many parameters such as cutting speed, feed, depth of cut, vibration, coolant, insert properties/geometry used. In this study, surface roughnesses after turning of hot work tool steel at different parameters are investigated. At the same time, regression, artificial neural network, and fuzzy logic prediction models are developed from the experimental data. Therefore, surface roughness values at the different parameters are determined. The closest estimate with approximately 5% error is obtained by the Sugeno fuzzy logic model when it compared to experimental results.
... Oluşturdukları YSA yöntemiyle, bileşke kuvvet ve yüzey pürüzlülüğünü başarılı bir şekilde elde etmişlerdir. Akkuş [11], AISI 1040 çeliğinde yüzey pürüzlülüğü tahmininde farklı modeller (regresyon, Taguchi, YSA, bulanık mantık) kullanmıştır. Girdi parametreleri olarak; kesme hızı, ilerleme, talaş derinliği parametrelerini kullanmıştır. ...
Machining is one of the most widely used manufacturing processes in the mold industry and which affects the manufacturing cost significantly. Particularly, the desired surface roughness/quality at a low cost at minimum machining time is the ultimate target. Surface quality depends on many parameters such as cutting speed, feed, depth of cut, vibration, coolant, insert properties/geometry used. In this study, surface roughnesses after turning of hot work tool steel at different parameters are investigated. At the same time, regression, artificial neural network, and fuzzy logic prediction models are developed from the experimental data. Therefore, surface roughness values at the different parameters are determined. The closest estimate with approximately 5% error is obtained by the Sugeno fuzzy logic model when it compared to experimental results.
... Parametrelerin kaynak çapı ve maksimum çekme kuvvetine olan etkileri detaylı olarak ANOVA analizi bölümünde ele alınmıştır. Varyans analizlerine (ANOVA) geçmeden önce verilerin normal dağılım eğrisine uygun olup olmadığının araştırılması gerekmektedir (Akkuş 2021). Bu yüzden Şekil 9'da gösterildiği gibi normallik testi gerçekleştirilmiştir. Verilerin normal dağılıma uygun olması normallik varsayımının kabul edilebilir olduğunu göstermektedir. ...
Kaynak prosesi başta otomotiv sektörü olmak üzere, endüstride çelik saçların birleştirilmesinde yaygın olarak kullanılmaktadır. Elektrik direnç kaynağı diğer kaynak yöntemlerine göre kolay uygulanabilirlik, otomasyona uygunluk, dolgu metali gerektirmemesi vb. avantajlar gibi bir çok avantaja sahiptir. Elektrik direnç kaynağı uzun yıllardır bilinen bir işlem olmasına rağmen otomotiv endüstrisinde çok fazla kullanıldığı için üzerinde en çok çalışılan kaynak yöntemlerinden biridir. Bu çalışmada, elektrik direnç kaynağı proses parametrelerinin çekme dayanımı üzerine olan etkisi sonlu elemanlar yöntemi kullanılarak incelenmiştir. Akım, sıkıştırma kuvveti ve kaynak süresi parametreleri değişken olarak ele alınmıştır. Dokuz farklı sonlu elemanlar kaynak analizi sonucunda elde edilen birleştirilmiş sac parçalar çekme analizine girdi olarak tanımlanmıştır. Gerçekleştirilen kaynak ve çekme analizleri sonucunda maksimum punta çapı ve çekme kuvvet değerleri çıktı olarak ele alınmıştır. Elde edilen çıktılar varyans analizi (ANOVA) tabi tutularak hangi parametrenin çekme dayanımı üzerine daha etkili olduğu araştırılmıştır. Sonuç olarak, akım ve zamanın artması ile çekme mukavemet değerlerinin arttığı, sıkıştırma kuvvetinin artması ile mukavemetin azaldığı tespit edilmiştir. Çalışma ayrıca, sonuçların minimum hata ile yaklaşık olarak tahmin edilebildiği ampirik denklemler de önermektedir.
Artan maliyetler ve istenen ürünün kalitesi dikkate alındığında talaşlı imalatta verimli işleme yapmanın önemi artmaktadır. Verimli bir işleme yapabilmek için kesme parametreleri uygun seçilmelidir. Bu çalışmada, nikel esaslı süper alaşımlı malzemelerde delme işlemi yapılmıştır. Delme işleminde farklı kesme parametreleri ve seviyeleri kullanılmıştır. Ayrıca delme işleminde kaplamalı ve kaplamasız olmak üzere iki ayrı matkap ucu seçilmiştir. Taguchi yöntemi ile deney listesi oluşturulmuş ve deneyler sonunda elde dilen yüzeylerin yüzey pürüzlülükleri ölçülmüştür. Sonuçlar, Taguchi ve GİA (Gri İlişkisel Analiz) yöntemleri kullanılarak optimizasyon yapılmıştır. Optimizasyonlar, ortalama yüzey pürüzlülüğünün en küçük değeri istendiği için en küçük en iyi sinyal-gürültü oranı seçilerek yapılmıştır. Deneyler sonunda en düşük ortalama yüzey pürüzlülüğünü elde ettiğimiz kesme parametreleri ve seviyeleri belirlenmiştir. Optimum parametre seviyelerinin dizilimi A2B3C1D3 çıkmıştır. Ortalama yüzey pürüzlülüğüne en çok etki eden parametre belirlenmiş ve çalışmanın güven düzeyi Varyans analizi kullanılarak bulunmuştur. En etkin parametre kesme hızı, çalışmanın güven düzeyi %84,23 olmuştur.
Machining is one of the most widely used manufacturing processes in the mold industry and which affects the manufacturing cost significantly. Particularly, the desired surface roughness/quality at a low cost at minimum machining time is the ultimate target. Surface quality depends on many parameters such as cutting speed, feed, depth of cut, vibration, coolant, insert properties/geometry used. In this study, surface roughnesses after turning of hot work tool steel at different parameters are investigated. At the same time, regression, artificial neural network, and fuzzy logic prediction models are developed from the experimental data. Therefore, surface roughness values at the different parameters are determined. The closest estimate with approximately 5% error is obtained by the Sugeno fuzzy logic model when it compared to experimental results.
Earthquake is one of the most devastating natural calamities that takes thousands of lives and leaves millions more homeless and deprives them of the basic necessities. Earthquake forecasting can minimize the death count and economic loss encountered by the affected region to a great extent. This study presents an earthquake forecasting system by using Artificial Neural Networks (ANN). Two different techniques are used with the first focusing on the accuracy evaluation of multilayer perceptron using different inputs and different set of hyper-parameters. The limitation of earthquake data in the first experiment led us to explore another technique, known as nowcasting of earthquakes. The nowcasting technique determines the current progression of earthquake cycle of higher magnitude earthquakes by taking into account the number of smaller earthquake events in the same region. To implement the nowcasting method, a Long Short Term Memory (LSTM) neural network architecture is considered because such networks are one of the most recent and promising developments in the time-series analysis. Results of different experiments are discussed along with their consequences.
The life of a cutting tool is greatly influenced by the forces acting on it during a cutting operation. A machining operation is a complex process. It is very difficult to develop a comprehensive model involving all the parameters. The present study aims to develop a model to investigate the effects of cutting parameters (speed, depth of cut and feed rate) on the cutting forces during the turning operation of red brass (C23000) using high speed steel (HSS) tool. The experimental results are based on full factorial design methodology to increase the reliability and confidence limit of the data. Artificial neural network and multiple regression approaches were used to model the cutting forces on the basis of cutting parameters. In order to check the adequacy of the regression model, analysis of variance (ANOVA) was used. It was clear from the ANOVA that the regression model is capable to predict the cutting forces with high accuracy. However, ANN model was found to be more accurate than the regression model.
The paper presents the results of the cutting forces research (Ff, Fp, Fc) when machining of sintered carbides WC-Co (25% Co) with tools made of polycrystalline diamond PCD. Inserts with three different nose radii rɛ were used during the study. Each cutting test was carried out on the distance 54 mm at the constant depth of cut 0.2 mm. The biggest increase of passive cutting force component Fp was indicated. In addition, the mathematical models for cutting force value prediction as the cutting path increases are presented. The paper presents also the algorithm of optimization and control of the super hard materials turning process.
This research work focuses on precision turning of Ti6Al4 V material to investigate the machinability of the material. Precision turning is a type of machining where, very low feed rate and depth of cut is being used to machine using a cutting insert with a lower nose radius. The cutting parameters considered for the experiments include the cutting speed, feed rate, depth of cut and nose radius. PVD coated carbide cutting inserts with different nose radius and constant rake and clearance angle are being considered for experimentation. The experimentation was designed based on Taguchi's L 27 orthogonal array. Three different levels of cutting parameters were being considered for the experimentation. The turning experiments were carried out on a conventional variable speed motor lathe under dry working conditions. Based upon the experimental values, Analysis of Variance (ANOVA) was conducted to understand the influence of various cutting parameters on cutting force, surface roughness and cutting tool temperatures during precision turning. There are a number of techniques available for predicting responses using input parameters and the present work uses Fuzzy Inference System (Mamdani Fuzzy logic) to predict the out put parameters.
An artificial neural network (ANN) is an information-processing paradigm that is inspired by the way biological nervous systems, such as the brain, process information. In previous two decades, ANN applications in economics and finance; for such tasks as pattern reorganization, and time series forecasting, have dramatically increased. Many central banks use forecasting models based on ANN methodology for predicting various macroeconomic indicators, like inflation, GDP Growth and currency in circulation etc. In this paper, we have attempted to forecast monthly YoY inflation for Pakistan by using ANN for FY08 on the basis of monthly data of July 1993 to June 2007. We also compare the forecast performance of the ANN model with that of univariate AR(1) model and observed that RMSE of ANN based forecasts is much less than the RMSE of forecasts based on AR(1) model. At least by this criterion forecast based on ANN are more precise.
In ultra-precision machining, diamond turning is widely applied for optical components and die cores. When operating diamond turning, the tool wear is among the most significant concerns, which causes the deterioration of machining quality and the waste of material and time. The tool wear is unable to be assessed by naked eyes, a tedious off line measurement is employed for evaluating the tool wear. In this paper, an optical method using laser-light scattering to evaluate the tool wear is proposed for maintaining the machining quality and determining the appropriate timing for tool change while manufacturing light guide plate. In this optical method, the progress of the tool wear of nose radius is monitored by the scattered light beams from the machined surface. The incident angle between 20 and 30 degrees is found to provide the best results for monitoring the tool wear.
A new cooling technique is proposed to improve effectiveness of the minimum quantity lubrication (MQL) and cryogenic carbon dioxide (CO2) cooling in high performance machining of hard-to-cut materials. The combination of minimum quantity carbon dioxide and oil (CMQL) supplied from the rake face are compared with CO2 and MQL supplied from rake and flank faces, respectively, as well as only CO2 supplied from rake face, in turning of Ti6Al4V and Inconel 718. Tool wear, surface roughness and temperature measurements were performed to quantify the cooling impact of the various methods. Based on the systematical test results, CMQL was identified as the most favorable cooling method considering environmental impact, tool wear, surface finish, chip formation and cutting forces.
The present paper aims to develop the predictive models of average tool-workpiece interface temperature in hard turning of AISI 1060 steels by coated carbide insert. The Response Surface Methodology (RSM) and Artificial Neural Network (ANN) were employed to predict the temperature in respect of cutting speed, feed rate and material hardness. The number and orientation of the experimental trials, conducted in both dry and high pressure coolant (HPC) environments, were planned by using full factorial design. The temperature was measured by using the tool-work thermocouple. In RSM model, two quadratic equations of temperature were derived from experimental data. The analysis of variance (ANOVA) and mean absolute percentage error (MAPE) were performed to suffice the adequacy of the models. In ANN model, 80% data was used to train and 20% data was employed for testing. Like RSM, herein, the error analysis was also conducted. The accuracy of the RSM and ANN model was found to be ≥99%. The ANN models exhibit an error of ~5% MAE for testing data. The regression coefficient was found to be greater than 99.9% for both dry and HPC. Both these models are acceptable, although the ANN model demonstrated a higher accuracy. These models, if employed, are expected to provide a better control of cutting temperature in turning of hardened steel.
The experimental setup and design to develop a multiple regression model for an on-line, real-time surface roughness prediction system was demonstrated. The experiment of collecting data for training and testing was conducted. Accuracy values with vibration information and without vibration information were compared by applying a t-test. Established by using 162 data sets and tested by using 54 data sets for each tool condition, the proposed regression model showed an accuracy of 90% on predicting the in process surface roughness.
In this experimental work, the effect of various cutting fluid levels and cutting parameters on surface roughness and tool wear was studied. Taguchi orthogonal array was employed to minimize the number of experiments. The experiments were carried out on mild steel bar using a TiCN + Al2O3 + TiN coated carbide tool insert in the CNC turning process. The effect of feed rate was found to be the dominant factor contributing 34.3% to surface roughness of the work-piece. The flow rate of the cutting fluid also showed a significant contribution (33.1%). However, cutting speed and depth of cut showed little contribution to surface roughness. On the other hand, cutting speed (43.1%) and depth of cut (35.8%) were the dominant factors influencing tool wear. However, application of cutting fluid (13.7%) showed a considerable contribution, while the feed rate gave the least contribution to tool wear. The optimum cutting conditions for desired surface roughness and tool wear were at a high level of cutting speed, medium level of depth of cut, low level of feed rate and low-flow high-velocity (LFHV) cutting fluid flow from the selected levels.
In this study, the average surface roughness values obtained when turning AISI 4140 grade tempered steel with a hardness of 51 HRC, were modeled using fuzzy logic, artificial neural networks (ANN) and multi-regression equations. Input variables consisted of cutting speed (V), feed rate (f) and depth of cut (a) while output variable was surface roughness (Ra). Fuzzy logic and ANN models were developed using Matlab Toolbox. Variance analysis was conducted using MINITAB. The predicted values of mean squared errors (MSE) were employed to compare the three models. Results showed that the optimum predictive model is the fuzzy logic model. With small errors (e.g MSE = 0.0173166), the model was considered sufficiently accurate.
This paper presents a fuzzy logic artificial intelligence technique for predicting the machining performance of Al-Si-Cu-Fe die casting alloy treated with different additives including strontium, bismuth and antimony to improve surface roughness. The Pareto-ANOVA optimization method was used to obtain the optimum parameter conditions for the machining process. Experiments were carried out using oblique dry CNC turning. The machining parameters of cutting speed, feed rate and depth of cut were optimized according to surface roughness values. The results indicated that a cutting speed of 250 m/min, a feed rate of 0.05 mm/rev, and a depth of cut of 0.15 mm were the optimum CNC dry turning conditions. The results also indicated that Sr and Sb had a negative effect on workpiece machinability. The workpiece containing Bi exhibited the lowest surface roughness value, likely due to the formation of pure Bi that acted as lubricant during turning. A confirmation experiment was performed to check the validity of the model developed in this paper, and the predicted surface roughness came had an error rate of only 5.4%.
This study investigated the optimization of CNC turning operation parameters for SKD11 (JIS) using the Grey relational analysis method. Nine experimental runs based on an orthogonal array of Taguchi method were performed. The surface properties of roughness average and roughness maximum as well as the roundness were selected as the quality targets. An optimal parameter combination of the turning operation was obtained via Grey relational analysis. By analyzing the Grey relational grade matrix, the degree of influence for each controllable process factor onto individual quality targets can be found. The depth of cut was identified to be the most influence on the roughness average and the cutting speed is the most influential factor to the roughness maximum and the roundness. Additionally, the analysis of variance (ANOVA) is also applied to identify the most significant factor; the depth of cut is the most significant controlled factors for the turning operations according to the weighted sum grade of the roughness average, roughness maximum and roundness.
A neural-network-based methodology is proposed for predicting the surface roughness in a turning process by taking the acceleration of the radial vibration of the tool holder as feedback. Upper, most likely and lower estimates of the surface roughness are predicted by this method using very few experimental data for training and testing the network. The network model is trained using the back-propagation algorithm. The learning rate, the number of neurons in the hidden layer, the error goal, as well as the training and the testing dataset size, are found automatically in an adaptive manner. Since the training and testing data are collected from experiments, a data filtration scheme is employed to remove faulty data. The validation of the methodology is carried out for dry and wet turning of steel using high speed steel and carbide tools. It is observed that the present methodology is able to make accurate prediction of surface roughness by utilising small sized training and testing datasets.
Glass fiber reinforced polymer (GFRP) composite materials are finding increased applications in a variety of engineering fields.
Subsequently, the need for accurate, machining of composites has increased enormously. This paper discusses the application
of the Taguchi method with fuzzy logic to optimize the machining parameters for machining of GFRP composites with multiple
characteristics. A multi-response performance index (MRPI) was used for optimization. The machining parameters viz., work
piece (fiber orientation), cutting speed, feed rate, depth of cut and machining time were optimized with consideration of
multiple performance characteristics viz., metal removal rate, tool wear, and surface roughness. The results from confirmation
runs indicated that the determined optimal combination of machining parameters improved the performance of the machining process.
This investigation applied the Taguchi method and designs of experiments (DOE) approach to optimize parameters for magnesium
alloy AZ91D. Tribological properties of wear mass loss and friction coefficients were studied. Planning of experiments was
based on a Taguchi orthogonal array table, and applied signal-to-noise ratios to determine an optimal setting. Furthermore,
as the analysis of variance (ANOVA) was adapted to identify the most influential factors, the fusion slurry pressure was found
to be the most significant factor. By applying regression analysis, a mathematical predictive model of the wear mass loss
was developed in terms of the die casting process parameters. Additional runs were conducted in order to validate the optimal
setting and compare the performance of the Taguchi method and the DOE approach. In this study, the wear mechanisms of adhesive
and delamination for the AZ91D were found through wear tests. A specimen with a low wear mass loss has shown a low friction
coefficient as well as small exfoliates and fractures.
Research during the past several years has established the effectiveness of acoustic emission (AE)-based sensing methodologies for machine condition analysis and process monitoring. AE has been proposed and evaluated for a variety of sensing tasks as well as for use as a technique for quantitative studies of manufacturing processes. This paper reviews briefly the research on AE sensing of tool wear condition in turning. The main contents included are:1.The AE generation in metal cutting processes, AE signal classification, and AE signal correction.2.AE signal processing with various methodologies, including time series analysis, FFT, wavelet transform, etc.3.Estimation of tool wear condition, including pattern classification, GMDH methodology, fuzzy classifier, neural network, and sensor and data fusion.A review of AE-based tool wear monitoring in turning is an important step for improving and developing new tool wear monitoring methodology.
Highly stressed steel components, e.g., gears and bearing parts, are appropriate applications for hard turning. Therefore, the process effects on significant engineering properties of work materials have to be carefully analyzed. Roughness, residual stresses, and white layers as parts of surface integrity, are functions of the machining parameters and of the cuttability of the cutting edge, i.e. of the tool wear.The aim of this work was to study the influence of feed rate, cutting speed, and tool wear on the effects induced by hard turning on case-hardened 27MnCr5 gear conebrakes and to point out the technical limitations in mass production.
About fuzzy logic paradigm
- S Dursun
Dursun, S., (2012). About fuzzy logic paradigm. Batman University Journal of Life Sciences, 1(2), 347-354.