The machinability and the process parameter optimization of turning operation for 15-5 Precipitation Hardening (PH) stainless steel have been investigated based on the Taguchi based grey approach and Technique for Order Preference by Similarity to Ideal Solution (TOPSIS). An L₂₇ orthogonal array was selected for planning the experiment. Cutting speed, depth of cut and feed rate were considered as input process parameters. Cutting force (F_z) and surface roughness (R_a) were considered as the performance measures. These performance measures were optimized for the improvement of machinability quality of product. A comparison is made between the multi-criteria decision making tools. Grey Relational Analysis (GRA) and TOPSIS are used to confirm and prove the similarity. To determine the influence of process parameters, Analysis of Variance (ANOVA) is employed. The end results of experimental investigation proved that the machining performance can be enhanced effectively with the assistance of the proposed approaches.

This research work is focused on examining the turning behavior of Incoloy 800H superalloy by varying important cutting parameters. Incoloy 800H is an Iron- Nickel-Chromium based superalloy; it can withstand high temperature (810°C), high oxidization and corrosion resistance. But, it is difficult to turn in conventional machines and hence the present work was carried out and investigated. Experiments were conducted based on the standard L27 orthogonal array using uncoated tungsten inserts. The cutting force components, namely, feed force (Fx), thrust force (Fy) and cutting force (Fz); surface roughness (Ra) and specific cutting pressure (SCPR) were measured as responses and optimized using Taguchi-Grey approach. The main effects plots and analysis of mean (ANOM) were performed to check the effect of turning parameters and their significance on responses of cutting forces in all the direction (FX, FY, FZ), the surface roughness (Ra) and specific cutting pressure (SCPR). The tool wear and machined surfaces were also investigated using white light interferometer and SEM.

Online saree shopping has become a popular way for adolescents to shop for fashion. Purchasing from e-commerce is a huge time-saver in this situation. Female apparel has many difficult-to-describe qualities, such as texture, form, colour, print, and length. Research involving online shopping often involves studying consumer behaviour and preferences. Fashion image analysis for product search still faces difficulties in detecting textures based on query images. To solve the above problem, a novel deep learning-based SareeNet is presented to quickly classify the tactile sensation of a saree according to the user’s query. The proposed work consists of three phases: i) saree image pre-processing phase, ii) patch generation phase, and iii) texture detection and optimization for efficient classification. The input image is first denoised using a contrast stretching adaptive bilateral (CSAB) filter. The deep learning-based mask region-based convolutional neural network (Mask R-CNN) divides the region of interest into saree patches. A deep learning-based improved EfficientNet-B3 has been introduced which includes an optimized squeeze and excitation block to categorise 25 textures of saree images. The Aquila optimizer is applied within the squeeze and excitation block of the improved EfficientNet to normalise the parameters for improving the accuracy in saree texture classification. The experimental results show that SareeNet is effective in categorising texture in saree images with 98.1% accuracy. From the experimental results, the proposed improved EfficientNet-B3 improves overall accuracy by 2.54%, 0.17%, 2.06%, 1.78%, and 0.63%, for MobileNet, DenseNet201, ResNet152, and InspectionV3, respectively.