Multi-output fuzzy inference system for modeling cutting temperature and tool life in face milling

This paper proposes a method for cutting parameters identification using the multi-inputs-multi-outputs fuzzy inference system (MIMO-FIS). The fuzzy inference system (FIS) was used to identify the initial values for cutting parameters (cutting speed, feed rate and depth of cut) and flank wear using cutting temperature and tool life as outputs. The objective was to determine the influence of cutting parameters on cutting temperature and tool life. The model for determining the cutting temperature and tool life of steel AISI 1060 was trained (design rules) and tested by using the experimental data. The average deviation of the testing data for tool life was 11.6 %, while that of the cutting temperature was 3.28 %. The parameters used in these testing data were different from the data collected for the design rules. The test results showed that the proposed MIMO-FIS model can be used successfully for machinability data selection. The effect of parameters and their interactions in machining is analyzed in detail and presented in this study.     

Notch wear detection in cutting tools using gradient approach and polynomial fitting

Cutting tool wear is well known to affect the surface finish of a turned part. Various machine vision methods have been developed in the past to measure and quantify tool wear. The two most widely measured parameters in tool wear monitoring are flank wear and crater wear. Works carried out by several researchers recently have shown that notch wear has a more severe effect on the surface roughness compared to flank or crater wear. In this work, a novel gradient detection approach has been developed to detect the presence of micro-scale notches in the nose area of the cutting tool. This method is capable of detecting the location of the notch accurately from a single worn cutting tool image.     

FUZZY CLUSTERING MODELLING FOR SURFACE FINISH PREDICTION IN FINE TURNING PROCESS

ABSTRACT

In this paper, fuzzy subtractive clustering based system identification and Sugeno type fuzzy inference system are used to model the surface finish of the machined surfaces in fine turning process to develop a better understanding of the effect of process parameters on surface quality. Such an understanding can provide insight into the problems of controlling the quality of the machined surface when the process parameters are adjusted to obtain certain characteristics. Surface finish data were generated for aluminum alloy 390 (73 BHN), ductile cast iron (186 BHN), and inconel 718 (BHN 335) for a wide range of machining conditions defined by cutting speed, cutting feed rate and cutting tool nose radius. These data were used to develop a surface finish prediction fuzzy clustering model as a function of hardness of the machined material, cutting speed, cutting feed rate, and cutting tool nose radius. Surface finish of the machined part is the output of the process. The model building process is carried out by using fuzzy subtracting clustering based system identification in both input and output space. Minimum error is obtained through numerous searches of clustering parameters. The fuzzy logic model is capable of predicting the surface finish for a given set of inputs (workpiece hardness, cutting speed, cutting feed rate and nose radius of the cutting tool). As such, the machinist may predict the quality of the surface for a given set of working parameters and may also set the process parameters to achieve a certain surface finish. The model is verified experimentally by further experimentation using different sets of inputs. This study deals with the experimental results obtained during fine turning operation. The findings indicate that while the effects of cutting feed and tool nose radius on surface finish were generally consistent for all materials, the effect of cutting speed was not. The surface finish improved for aluminum alloy and ductile cast iron but it deteriorated with speed for inconel.     

FUZZY CLUSTERING MODELLING FOR SURFACE FINISH PREDICTION IN FINE TURNING PROCESS

In this paper, fuzzy subtractive clustering based system identification and Sugeno type fuzzy inference system are used to model the surface finish of the machined surfaces in fine turning process to develop a better understanding of the effect of process parameters on surface quality. Such an understanding can provide insight into the problems of controlling the quality of the machined surface when the process parameters are adjusted to obtain certain characteristics. Surface finish data were generated for aluminum alloy 390 (73 BHN), ductile cast iron (186 BHN), and inconel 718 (BHN 335) for a wide range of machining conditions defined by cutting speed, cutting feed rate and cutting tool nose radius. These data were used to develop a surface finish prediction fuzzy clustering model as a function of hardness of the machined material, cutting speed, cutting feed rate, and cutting tool nose radius. Surface finish of the machined part is the output of the process. The model building process is carried out by using fuzzy subtracting clustering based system identification in both input and output space. Minimum error is obtained through numerous searches of clustering parameters. The fuzzy logic model is capable of predicting the surface finish for a given set of inputs (workpiece hardness, cutting speed, cutting feed rate and nose radius of the cutting tool). As such, the machinist may predict the quality of the surface for a given set of working parameters and may also set the process parameters to achieve a certain surface finish. The model is verified experimentally by further experimentation using different sets of inputs. This study deals with the experimental results obtained during fine turning operation. The findings indicate that while the effects of cutting feed and tool nose radius on surface finish were generally consistent for all materials, the effect of cutting speed was not. The surface finish improved for aluminum alloy and ductile cast iron but it deteriorated with speed for inconel.     

Experimental investigations on machinability aspects in finish hard turning of AISI 4340 steel using uncoated and multilayer coated carbide inserts

The present work deals with some machinability studies on flank wear, surface roughness, chip morphology and cutting forces in finish hard turning of AISI 4340 steel using uncoated and multilayer TiN and ZrCN coated carbide inserts at higher cutting speed range. The process has also been justified economically for its effective application in hard turning. Experimental results revealed that multilayer TiN/TiCN/Al₂O₃/TiN coated insert performed better than uncoated and TiN/TiCN/Al₂O₃/ZrCN coated carbide insert being steady growth of flank wear and surface roughness. The tool life for TiN and ZrCN coated carbide inserts was found to be approximately 19 min and 8 min at the extreme cutting conditions tested. Uncoated carbide insert used to cut hardened steel fractured prematurely. Abrasion, chipping and catastrophic failure are the principal wear mechanisms observed during machining. The turning forces (cutting force, thrust force and feed force) are observed to be lower using multilayer coated carbide insert in hard turning compared to uncoated carbide insert. From 1st and 2nd order regression model, 2nd order model explains about 98.3% and 86.3% of the variability of responses (flank wear and surface roughness) in predicting new observations compared to 1st order model and indicates the better fitting of the model with the data for multilayer TiN coated carbide insert. For ZrCN coated carbide insert, 2nd order flank wear model fits well compared to surface roughness model as observed from ANOVA study. The savings in machining costs using multilayer TiN coated insert is 93.4% compared to uncoated carbide and 40% to ZrCN coated carbide inserts respectively in hard machining taking flank wear criteria of 0.3 mm. This shows the economical feasibility of utilizing multilayer TiN coated carbide insert in finish hard turning.     

线性回归模型诊断和在线预测刀具磨损量的方法研究

目的是研究诊断端面铣刀磨损量和在线预测铣刀的剩余寿命的方法.采用线性回归模型估计测刀面的磨损量.线性回归模型的输入是从铣刀受力信号提取出的特征和切削条件,比如进给量、转速等.在诊断了刀具的磨损量后,采用双指数平滑方法跟随诊断结果预测铣刀的使用寿命.最后,通过卖验验证了基于线性回归模型得到的刀具的磨损量和基于双指数平滑方法在线预测铣刀的剩余寿命的可行性.     

COMBINED EFFECTS OF FLANK AND CRATER WEAR ON CUTTING FORCE MODELING IN ORTHOGONAL MACHINING—PART II: BAYESIAN APPROACH-BASED MODEL VALIDATION

Flank and crater wear are the primary tool wear patterns during the progressive tool wear in metal cutting. Cutting forces may increase or decrease, depending on the combined contribution from the flank and/or crater wear. A two-dimensional (2D) slip-line field based analytical model has been proposed to model the force contributions from both the flank and crater wear. To validate the proposed force model, the Bayesian linear regression is implemented with credible intervals to evaluate the force model performance in orthogonal cutting of CK45 steels. In this study, the proposed analytical worn tool force model-based predictions fall well within the 75% credible intervals determined by the Bayesian approach, implying a satisfactory modeling capability of the proposed model. Based on the parametric study using the proposed force model, it is found that cutting forces decrease with the increasing crater wear depth but increase with the increasing flank wear length. Also, the predicted cutting forces are affected noticeably by the friction coefficients along the rake and flank faces and the ratio of crater sticking region to sliding region, and better knowledge of such friction coefficients and ratio is expected to further improve worn tool force modeling accuracy. Compared with the finite element approach, the proposed analytical approach is efficient and easy to extend to three-dimensional worn tool cutting configurations.     

Tool wear and its effect on surface roughness in diamond cutting of glass soda-lime

For the technology of diamond cutting of optical glass, the high tool wear rate is a main reason for hindering the practical application of this technology. Many researches on diamond tool wear in glass cutting rest on wear phenomenon describing simply without analyzing the genesis of wear phenomenon and interpreting the formation process of tool wear in mechanics. For in depth understanding of the tool wear and its effect on surface roughness in diamond cutting of glass, experiments of diamond turning with cutting distance increasing gradually are carried out on soda-lime glass. The wear morphology of rake face and flank face, the corresponding surface features of workpiece and the surface roughness, and the material compositions of flank wear area are detected. Experimental results indicate that the flank wear is predominant in diamond cutting glass and the flank wear land is characterized by micro-grooves, some smooth crater on the rake face is also seen. The surface roughness begins to increase rapidly, when the cutting mode changes from ductile to brittle for the aggravation of tool wear with the cutting distance over 150 m. The main mechanisms of inducing tool wear in diamond cutting of glass are diffusion, mechanical friction, thermo-chemical action and abrasive wear. The proposed research makes analysis and research from wear mechanism on the tool wear and its effect on surface roughness in diamond cutting of glass, and provides theoretical basis for minimizing the tool wear in diamond cutting brittle materials, such as optical glass.     

Modeling of tool wear during hard turning with self-propelled rotary tools

In this paper, an attempt is made to evaluate the self-propelled rotary carbide tool performance during machining hardened steel. Although several models were developed and used to evaluate the tool wear in conventional tools, there were no attempts in open literature for modeling the progress of tool wear when using the self-propelled rotary tools. Flank wear model for self-propelled rotary cutting tools is developed based on the work-tool geometric interaction and the empirical function. A set of cutting tests were carried out on the AISI 4340 steel with hardness of 54–56 HRC under different cutting speeds and feeds. The progress of tool wear was recorded under different interval of time. A genetic algorithm was developed to identify the constants in the proposed model. The comparison of measured and predicted flank wear showed that the developed model is capable of predicting the rate of rotary tool flank wear progression.     

APPLICATION OF WAVELET PACKET ANALYSIS IN DRILL WEAR MONITORING

In this work, an attempt has been made to develop a drill wear monitoring system which is independent to cutting conditions of the drilling process. A cost effective Hall-effect current sensor, which does not interfere with the process, has been used for acquiring motor current signature during drilling under different cutting conditions. An advanced signal processing technique, the wavelet packet transform has been used on the acquired current signature to extract features for indirect representation to the amount of drill wear. Experimental sensitivity analysis reveals that in comparison to time domain features, wavelet packet features are more sensitive to flank wear and less sensitive to the cutting conditions. A multilayer neural network model has then been developed to correlate the extracted wavelet packet features with drill flank wear. Experimental results show that the proposed drill wear monitoring system can successfully predict the flank wear with acceptable accuracy.     

APPLICATION OF WAVELET PACKET ANALYSIS IN DRILL WEAR MONITORING

In this work, an attempt has been made to develop a drill wear monitoring system which is independent to cutting conditions of the drilling process. A cost effective Hall-effect current sensor, which does not interfere with the process, has been used for acquiring motor current signature during drilling under different cutting conditions. An advanced signal processing technique, the wavelet packet transform has been used on the acquired current signature to extract features for indirect representation to the amount of drill wear. Experimental sensitivity analysis reveals that in comparison to time domain features, wavelet packet features are more sensitive to flank wear and less sensitive to the cutting conditions. A multilayer neural network model has then been developed to correlate the extracted wavelet packet features with drill flank wear. Experimental results show that the proposed drill wear monitoring system can successfully predict the flank wear with acceptable accuracy.     

Ultraprecision turning of electroless nickel: effects of crystal orientation and origin of diamond tools

This paper deals with (i) the performance of natural and artificial diamond tools and (ii) the effects of crystal orientations at rake face of diamond tool for long distance (>200 km) ultraprecision machining of electroless nickel. The criteria for cutting performance of the diamond tool include flank wear, crater wear, workpiece surface finish, and cutting forces. Experimental results show that the natural diamond tool has superior performance compared to the artificial one as it experienced lower cutting forces and lower flank and crater wears. It was also found that the cutting tool with {110} crystal orientation at rake face performs better than the tool with {100} crystal orientation in terms of amount of wear, surface finish, and cutting forces.     

A New Slip-Line Field Modeling of Orthogonal Machining with a Rounded-Edge Worn Cutting Tool

In this study, a new slip-line field model and its associated hodograph for orthogonal cutting with a rounded-edge worn cutting tool are developed using Dewhurst and Collins's matrix technique. The new model considers the existence of dead metal zone in front of the rounded-edge worn cutting tool. The ploughing force and friction force occurred due to flank wear land, chip up-curl radius, chip thickness, primary shear zone thickness and length of bottom side of the dead metal zone are obtained by solving the model depending on the experimental resultant force data. The effects of flank wear rate, cutting edge radius, uncut chip thickness, cutting speed and rake angle on these outputs are specified.     

涂层刀具前后刀面摩擦下界面应力分析

基于任意拉格朗日欧拉方法(ALE)建立金属正交切削加工的热力耦合的有限元模型,获得不同速度下切削稳定时涂层刀具前后刀面的接触应力、剪应力以及温度场。通过对涂层刀具施加已获得的刀具表面的应力场和温度场,分析了不同速度下摩擦分界点变化的规律以及对涂层基体界面应力的影响。结果表明,随着速度的增大,摩擦分界点逐渐有向前刀面移动的趋势,表明磨损的方式开始从后刀面磨损向前刀面月牙湾磨损转变,这与切削试验结果一致。同时随着速度的增大,涂层界面应力突变更加显著,表明高速条件下涂层更容易破坏,且速度越高,前刀面涂层破坏的几率越大。     

An experimental analysis and measurement of process performances in machining of nimonic C-263 super alloy

Nimonic C-263 alloy is extensively used in the fields of aerospace, gas turbine blades, power generators and heat exchangers because of its unique properties. However, the machining of this alloy is difficult due to low thermal conductivity and work hardening characteristics. This paper presents the experimental investigation and analysis of the machining parameters while turning the nimonic C-263 alloy, using whisker reinforced ceramic inserts. The experiments were designed using Taguchi’s experimental design. The parameters considered for the experiments are cutting speed, feed rate and depth of cut. Process performance indicators, viz., the cutting force, tool wear and surface finish were measured. An empirical model has been created for predicting the cutting force, flank wear and surface roughness through response surface methodology (RSM). The desirability function approach has been used for multi response optimization. The influence of the different parameters and their interactions on the cutting force, flank wear and surface roughness are also studied in detail and presented in this study. Based on the cutting force, flank wear and surface roughness, optimized machining conditions were observed in the region of 210 m/min cutting speed and 0.05 mm/rev feed rate and 0.50 mm depth of cut. The results were confirmed by conducting further confirmation tests.     

Flank Wear Estimation in Face Milling Based on Radial Basis Function Neural Networks

This paper presents an estimation of flank wear in face milling operations using radial basis function (RBF) networks. Various signals such as acoustic emission (AE), surface roughness, and cutting conditions (cutting speed and feed) have been used to estimate the flank wear. The hidden layer RBF units have been fixed randomly from the input data and using batch fuzzy C means algorithm, and a comparative study has been carried out. The results obtained from a fixed RBF network have been compared with those from a resource allocation network (RAN).     

Tool crater wear depth modeling in CBN hard turning

Hard turning has been receiving increased attention because it offers many possible benefits over grinding in machining hardened steel. The wear of cubic boron nitride (CBN) tools, which are commonly used in hard turning, is an important issue that needs to be better understood. For hard turning to be a viable replacement technology, the high cost of CBN cutting tools and the cost of down-time for tool changing must be minimized. In addition to progressive flank wear, microchipping and tool breakage (which lead to early tool failure) are prone to occur under aggressive machining conditions due to significant crater wear and weakening of the cutting edge. The objective of this study is to model the CBN tool crater wear depth (K_T) to guide the design of CBN tool geometry and to optimize cutting parameters in finish hard turning. First, the main wear mechanisms (abrasion, adhesion, and diffusion) in hard turning are discussed and the associated wear volume loss models are developed as functions of cutting temperature, stress, and other process information. Then, the crater wear depth is predicted in terms of tool/work material properties and process information. Finally, the proposed model is experimentally validated in finish turning of hardened 52100 bearing steel using a low CBN content tool. The comparison between model predictions and experimental results shows reasonable agreement, and the results suggest that adhesion is the dominant wear mechanism within the range of conditions that were investigated.     

Experimental research of face mill wear effect to flat surface roughness

In this article, we researched the effect of wear face mills to finish the surface roughness by various conditions of cutting a steel-45 workpiece. The article shows how to affect the feed, cutting speed, and tool wear of a T5K10 carbide tool on the roughness of flat surfaces. The paper analyzes the nature the microprofile of changes in machined surfaces based on increasing the wear surface on the tooth flank.     

Effect of coating layer loss on the wear rate change of coated carbide tools in turning process

This paper reports an experimental study of flank wear on TiN- and TiAlN-coated carbide tools in the turning of AISI 1045, AISI 4135, ductile cast iron, and Inconel 718, and it was conducted with the purpose of showing the relationship between the change in wear rate and the loss of coating layer on the cutting edge. It was found that the relation between cutting distance and flank wear in log-log scale clearly shows the change in wear rate, thus providing a straightforward way to determine the relation between worn out coating layer and increase in wear rate. This relation was confirmed by analyzing the presence of coating layer before and after the inflection point appears by means of scanning electron microscopy (SEM) and energy-dispersive X-ray spectroscopy (EDS) photographs. It was observed that the coating layer on the flank face is worn away and finally is worn out. However, even if the layer on the flank face is worn out, tool wear is suppressed as long as the coating layer on the cutting edge exists. On the other hand, when the coating layer on the cutting edge is worn out, the wear resistance of the tool depends on the substrate; thus, the wear rate increases. According to the results, as the cutting speed increases, the change in wear rate appears in a shorter cutting distance, making flank wear to be high. High pressure and high temperature act on the rake face; thus, thermal stability of the coating layer in the cutting edge is important. A low cutting speed decreases cutting efficiency, but a high cutting speed causes flank wear to be high; therefore, in order to optimize machining cost, an acceptable cutting speed, from the standpoint of tool wear, should be selected.     

Fuzzy-sliding mode control of a polishing robot based on genetic algorithm

This paper proposes a fuzzy-sliding mode control which is designed by a self tuning fuzzy inference method based on a genetic algorithm. Using the method, the number of inference rules and the shape of the membership functions of the proposed fuzzy-sliding mode control are optimized without the aid of an expert in robotics. The fuzzy outputs of the consequent part are updated by the gradient descent method. It is further guaranteed that the selected solution becomes the global optimal solution by optimizing Akaike’s information criterion expressing the quality of the inference rules. In order to evaluate the learning performance of the proposed fuzzy-sliding mode control based on a genetic algorithm, a trajectory tracking simulation of the polishing robot is carried out. Simulation results show that the optimal fuzzy inference rules are automatically selected by the genetic algorithm and the trajectory control result is similar to the result of the fuzzy-sliding mode control which is selected through trial error by an expert. Therefore, a designer who does not have expert knowledge of robot systems can design the fuzzy-sliding mode controller using the proposed self tuning fuzzy inference method based on the genetic algorithm.