Government Engineering College, Sheikhpura

In this work, the application of machine learning (ML) models for the prediction of titanium alloy for electrical discharge machining (EDM) was studied. The machining performances (MRR, TWR, Ra , and recast layer thickness) were predicted by SVM, XG Boost and KNN machine learning models. The heatmap highlighted a strong correlation between parameters and a positive effect was observed for MRR (0.96) and Ra-recast layer thickness (0.82). The performance metrics such as Mean Absolute Error (MAE), Mean Squared Error (MSE), and Root Mean Squared Error (RMSE) were also utilized to compare the models. SVM achieved the best prediction results for TWR and recast layer thickness, while KNN produced the lowest MAE on MRR. The XG Boost model had slightly compromised prediction accuracy than the support vector machine for TWR. These results suggested that a hybridized approach could improve prediction accuracy for complex machining parameters, especially in high-precision machining applications such as biomedical and aerospace industries.

The construction of Embankment is a very common structure, used in civil engineering, where a range of materials are used to create a stable foundation for various structures. One such material that has been used is coal ash, which is a by-product of coal combustion; it is an attractive filler material as it is cheap, environment friendly, and available in abundant quantity from thermal power plants. Studies have shown that coal ash which has comparatively similar shear strength than natural soil can be used in embankment constructions. This review covers coal ash’s characteristics as a soil material, including its physical, chemical properties, and its suitability for use in geotechnical applications related to embankment construction. Subsequently, this study discusses several case studies and laboratory experiments that have been conducted to investigate the behavior of embankment using coal ash as a soil material. Additionally, the review highlights the different factors that affect the stability of these embankments, including geotechnical properties, the construction process, and the long-term performance of the embankment. At the end, future research aspects and design considerations by using of bottom ash in embankment construction has been discussed.

The focus of this paper investigates the Wire Electrical Discharge Machining (WEDM) performance of Al-6063/ Fly Ash / ZrO₂ hybrid composite specimens on Material Removal Rate (MRR) and Surface Roughness (SR). The experiments were performed using the three parameters current (60, 70, 80 A), wire feed rate (4,6 and 8 mm/min) and pulse on time (50,75 and 100 µs). ANFIS was employed to minimize predictive error and maximize process optimization by simulating and predicting machining responses. The ANFIS learning curve showed good signs of learning, with a rapid drop of the MRR training error from 9.7 × 10⁻⁶ to about 9.6 × 10⁻⁶ in the first 20 epochs. The experimental results revealed that the highest MRR was attained at high peak current, medium wire feed rate, and medium-high pulse-on time, which supported the combined effect of heat and discharging actions on material removal. On the other hand, an increased current and a longer pulse-on time led to higher surface roughness. The high correlation between actual and expected results, indicated with R² values of 0.95 to 0.98, proves that ANFIS model is a robust tool for the accurate prediction of WEDM performance characteristics. The contribution of this research is a complete guideline for the betterment of Hybrid composites using aluminium in precision machining.

Abstract A major challenge in brushless direct current motor (BLDCM) drives is the dc-link voltage fluctuation arising from the converter and different transition rates of the incoming and outgoing phase currents during commutation, which leads to high commutation torque ripple (CTR), switching-frequency harmonics (SFH), current distortion, vibration, and poor dynamic performance. The main function of the dc–dc converter is to supply the requisite regulated dc-link voltage of the BLDCM drive, although during the commutation, a steady dc-link voltage is required for successful CTR suppression. To address these problems, a quasi-proportional–resonant compensator (QPRC)-fed BLDCM drive with a landsman converter (LMC) is proposed in this study. The LMC supplies the regulated dc-link voltage and the QPRC suppresses the SFH and stabilizes the dc link voltage during commutation. The paper presents a detailed mathematical modeling, steady-state analysis, small-signal modeling, and the QPRC control technique. The proposed drive is verified by using MATLAB/Simulink simulation in steady-state and dynamic operation situations. The recommended control technique reduces the total harmonic distortion from 59.36% to 32.82% and the dc-link voltage ripple by 60%, consequently improving dc-link regulation, reducing CTR, and enhancing the overall performance of the BLDCM drive for electric vehicle (EV) and renewable energy applications.

The proposed monitoring strategy addresses the challenges associated with non-linear process behavior through the application of the Neural Network Fitting (NNF) Model technique, while non-Gaussian process characteristics are effectively managed using the I2 control chart. The study focuses on developing a monitoring strategy that employs statistical techniques while accounting for nonlinear as well as non-normal or non-Gaussian data. The proposed statistical monitoring strategy employs a multivariate I² control chart for non-normal data, while data nonlinearity is addressed using a Neural Network Fitting model. Quality characteristics of steel billets are initially processed through a Neural Network model to mitigate nonlinear patterns. The fully or partially linearized data are then evaluated using the I² control chart, with its control limits determined through the Bootstrap procedure. Observations identified as out-of-control are classified as faults, and their detection prompts the implementation of suitable corrective measures.