Nitinol, a shape-memory alloy (SMA), is gaining popularity for use in various applications. Machining of these SMAs poses a challenge during conventional machining. Henceforth, in the current study, the wire-electric discharge process has been attempted to machine nickel-titanium (Ni55.8Ti) super-elastic SMA. Furthermore, to render the process viable for industry, a systematic approach comprising response surface methodology (RSM) and a heat-transfer search (HTS) algorithm has been strategized for optimization of process parameters. Pulse-on time, pulse-off time and current were considered as input process parameters, whereas material removal rate (MRR), surface roughness, and micro-hardness were considered as output responses. Residual plots were generated to check the robustness of analysis of variance (ANOVA) results and generated mathematical models. A multi-objective HTS algorithm was executed for generating 2-D and 3-D Pareto optimal points indicating the non-dominant feasible solutions. The proposed combined approach proved to be highly effective in predicting and optimizing the wire electrical discharge machining (WEDM) process parameters. Validation trials were carried out and the error between measured and predicted values was negligible. To ensure the existence of a shape-memory effect even after machining, a differential scanning calorimetry (DSC) test was carried out. The optimized parameters were found to machine the alloy appropriately with the intact shape memory effect.

During milling operations, wear of cutting tool is inevitable; therefore, tool condition monitoring is essential. One of the difficulties in detecting the state of milling tools is that they are visually inspected, and due to this, the milling process needs to be interrupted. Intelligent monitoring systems based on accelerometers and algorithms have been developed as a part of Industry 4.0 to monitor the tool wear during milling process. In this paper, acoustic emission (AE) and vibration signals captured through sensors are analyzed and the scalograms were constructed from Morlet wavelets. The relative wavelet energy (RWE) criterion was applied to select suitable wavelet functions. Due to the availability of less experimental data to train the LSTM model for the prediction of tool wear, SinGAN was applied to generate additional scalograms and later several image quality parameters were extracted to construct feature vectors. The feature vector is used to train three long short-term memory network (LSTM) models: vanilla, stacked, and bidirectional. To analyze the performance of LSTM models for tool wear prediction, five performance parameters were computed namelyR², adjustedR², mean absolute error (MAE), root mean square error (RMSE), and mean square error (MSE). The lowest MAE, RMSE, and MSE values were observed as 0.005, 0.016, and 0.0002 and highR²and Adj.R²values as 0.997 are observed from the vibration signal. Results suggest that the stacked LSTM model predicts the tool wear better as compared to other LSTM models. The proposed methodology has given very less errors in tool wear predictions and can be extremely useful for the development of an online deep learning tool condition monitoring system.

Shape-memory alloys such as nitinol are gaining popularity as advanced materials in the aerospace, medical, and automobile sectors. However, nitinol is a difficult-to-cut material because of its versatile specific properties such as the shape-memory effect, superelasticity, high specific strength, high wear and corrosion resistance, and severe strain hardening. Anunconventional machining process like wire-electrical-discharge-machining (WEDM) can be effectively and efficiently used for the machining of such alloys, although the WEDM-induced surface integrity of nitinol hassignificant impact on material performance. Therefore, this work investigated the surface integrity of WEDM-processed nitinol samples using digital microscopy imaging, scanning electron microscopy (SEM), and energy-dispersive X-ray (EDX) analysis. Three-dimensional analysis of the surfaces was carried out in two different patterns (along the periphery and the vertical plane of the machined surface) andrevealed that surface roughness was maximalat the point where the surface was largely exposed to the WEDM dielectric fluid. To attain the desired surface roughness, appropriate discharge energy is required that, in turn, requires the appropriate parameter settings of the WEDM process. Different SEM image analyses showed a reduction in microcracks and pores, and in globule-density size at optimized parameters. EDX analysis revealed the absence of wire material on the machined surface