Narrow Results

The AISI H11 is widely used for making tools, dies and aircraft landing gears, due to its outstanding mechanical characteristics and superior wear resistance. However, these distinctive properties make it difficult to cut material. Deprived surface characters, high tool wear and higher manufacturing costs are concomitant with the machining of AISI H11. To limit the effects of the mineral oil-based flooding technique which affects the operator’s wellbeing, a vegetable oil-based minimum quantity lubrication (MQL) is represented as an alternative. In this study, graphene nanoplatelets (GNPs)-enhanced green sesame oil-based MQL is chosen for end milling. Initially, the nanofluid characteristics such as density, thermal conductivity, viscosity and surface tension at various concentrations are studied. Later, cutting temperature, surface finish, burr development, chip morphology and crystallographic structure are thoroughly examined. The results indicate that the MQL environment with nanofluid decreases the temperature by 75% and 15% compared with dry condition machining and conventional MQL environments, respectively; whereas the surface roughness reduction is observed to be 73% and 18% as compared with aforementioned atmospheres. Burr formation reduction is seen in the optical microscope examination. The smaller grain size of the machined surface and minimal amount of fibrous and curve chips show the superiority of the proposed cooling environment.

The rising demand for precision and quality in manufacturing necessitates that vast amounts of manufacturing knowledge be incorporated in manufacturing systems. Surface finish in end milling depends upon a number of variables such as cutting speed, feed rate, spindle speed, radial depth of cut, etc. The relative effect of these variables on surface roughness and machining time is quite considerable. A complex relationship exists between these process parameters and hence there is a need to develop models which can capture this complex interrelationship and enable fast computation of the average surface roughness and machining time based on process parameters. Neuro Fuzzy (NF) modeling has gained prominence recently on account of its fast reaction times, improved ease of operation and flexibility to respond to change in process parameters. In the present work, initially a Neuro Fuzzy Model is trained with experimental results of end milling. Subsequently, a generic approach is developed for optimization of end milling where the applicability and effectiveness of Neuro Fuzzy Model for function approximation is used to rapidly estimate average surface roughness and machining time in an integrated framework of Hybrid Stochastic Search Technique (HSST) to form a Neuro Fuzzy Hybrid Stochastic Search Technique (NFHSST). The results indicate that the NFHSST heuristic converges to better solutions rapidly as it provides the values of various process parameters for optimizing the objectives in a single run. Thus, NFHSST assists in the improvement of quality by developing multiple sound parts in an agile manner.

Tool wear of a cutting tool has a significant impact on the tool life and surface quality of the finished product. Tool wear is influenced by many factors such as cutting parameters, tool geometry, coating type, work piece material, chatter, and cutting condition. In the present work, the design of experiments (DOE) technique has been used for four factors at five levels to conduct experiments. Tool wear is taken as the response variable measured during end milling, while helix angle, spindle speed, feed and depth of cut are taken as the input parameters. The material and tool selected for this study are AISI 304 stainless steel and uncoated solid carbide end mill cutter respectively. The tool wear was measured using tool maker's microscope. The experimental values are used in six sigma software for finding the coefficients to develop the regression model. The direct and interaction effect of the machining parameter with tool wear were analyzed using contour graphs, which helped to select process parameters for reducing tool wear and also ensure quality of milling.

The machining of metal matrix composites (MMCs) creates an extra challenge as compared to that of metals and alloys due to their hardness owing to the abrasive reinforcement particles. This paper presents the study on end milling of Al-4032/3% SiC composite considering the cutting speed (CS), feed rate (FR) and depth of cut (DOC) as the process parameters. Surface finish and material removal rate (MRR) have been taken as the response parameters. The Al-4032-based AMC has been prepared using stir casting process. Taguchi’s $L_{27}$ orthogonal array (OA) has been used for experimental trials. The optimum setting of the parameters has been obtained using TGRA. The resulting surface roughness (SR; $R_a$) occurs in the range of 1.18–3.97$\mu$m, with the minimum value corresponding to the CS of 110m/min, FR of 0.05mm/tooth and DOC of 1.2mm. Bayesian regularization (BR), scaled conjugate gradient (SCG) and Levenberg–Marquardt (LM) algorithms have been employed for training, validating and testing the 3–$n$–1 and 3–$n$–2 ANN architectures ($1\le n\le 20$). Minimum root-mean-square error (RMSE) has been taken as the standard for evaluating the model. Neural network toolbox of MATLAB “R2019A” has been used for prediction of the response.

The objective of this work is to compare the machining performance of AISI 1040 Carbon Steel and Ti-6Al-4V alloy for a slot cutting operation using a 3-axis vertical milling machine. A set of 16 experiments was conducted, considering four factors: Feed rate, depth of cut, spindle speed, and coolant concentration, to remove material up to a finite depth. Three multi-objective optimization techniques namely, Grey Relational Analysis (GRA), Multi-Response Signal-to-Noise Ratio (MRSN Ratio), and Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) were employed to determine the optimal machining conditions by maximizing the material removal rate and minimizing surface roughness and material hardness. It has been observed that the response performance index varies with different optimization techniques as well as different workpiece materials. The most significant contributions of each technique were evaluated through ANOVA analysis. A prediction model was developed using linear regression analysis. Finally, comparing the results of the three objective optimization techniques, GRA gives better performance than both TOPSIS and MRSN by effectively satisfying two objectives (i.e., maximizing material removal rate and minimizing surface roughness) for AISI 1040 Carbon Steel. In contrast, the MRSN technique provides better results than GRA and TOPSIS by effectively satisfying two objectives (i.e., maximizing material removal rate and minimizing material hardness) for Ti-6Al-4V alloy.

This chapter introduces a new method for predicting chatter in milling process by a fuzzy neural network. Firstly, a milling experimental setup is built. And a set of the valuable experimental data is obtained under different tool wear states and cutting conditions. Secondly, since it is extremely difficult to construct an exact mathematical model for the setup, a fuzzy neural network model is proposed as a simplified one trained by using the experimental data. Thirdly, some simulation results are obtained based on the model. Finally, the further experiments are done to confirm the validity of predicting chatter in the model. The results show that chatter vibration in high-speed end milling could be exactly predicted via the model. Thus, the method described here is very effective to predict chatter in milling process.