Tripura Institute of Technology

This study focuses on performing a dynamic explicit nonlinear finite element simulation to analyze the temperature, residual stress, and strain distribution during the friction stir welding (FSW) process of zirconium (Zr) nanoparticle-reinforced AA2024-T3 (Zr-AA2024-T3) aluminum alloy. The computational modeling of Zr-reinforced FSW (rFSW) process is performed using ABAQUS explicit software. To ensure the development of a reliable and computationally efficient finite element (FE) model, key features such as the arbitrary Lagrangian–Eulerian (ALE) formulation, adaptive meshing, mesh sensitivity analysis, and mass scaling are integrated. The interaction between the tool bottom surface and the plate upper surface is defined using a finite sliding property. The tool–workpiece contact is modeled with a Coulomb friction model that incorporates a temperature-dependent friction coefficient. Additionally, an experimental study is conducted to validate the results obtained numerically. The results demonstrate similar temperature profiles generated across the workpiece, with slightly higher temperatures observed on the advancing side. The mechanical response of the AA2024-T3 aluminum alloy plates is also investigated. A temperature rise of around 20 °C relative to conventional FSW of AA2024-T3 plates is observed in rFSW process. Thermal stresses in Zr-reinforced AA2024-T3 joints show a 38

The 2024 Al-Cu alloy is extensively used in aerospace, automotive, and structural applications due to its remarkable properties, such as a higher strength-to-weight ratio and lightweight nature, making it a popular choice across various industries for various applications. Therefore, in the present study, the effect of varying process parameters, such as tool traverse speed (TTS) and rotational speed (TRS), on force and torque, ripple formation during the joining of surfaces, surface morphology, surface roughness, and hardness of friction stir-welded AA2024 Al-Cu alloy was investigated. The materials were joined at different TRS of 600, 900, and 1200 rpm and TTS of 3, 5, and 7 mm/s using a taper-threaded friction stir tool at a constant tool tilt angle. The results reveal that the low ripple distance occurred at higher TTS. Further, at a constant TRS, it is observed that the TTS is increased, and the ripple distance on the welded samples is also increased. Moreover, the higher surface roughness (SR) values at the weld center (9.82 µm) and 4.38 µm from AS to RS at TRS of 900 rpm and TTS of 3 mm/s and higher micro-hardness values are observed (125HV0.1) at the same process parameters.

Artificial intelligence (AI) has emerged as a key component of modern ophthalmology, enabling highly precise diagnosis of various posterior segment pathologies. Yet, the development of AI technology is inconsistent between subspecialties. Research on AI technology is dominated by studies on retinal diseases, such as diabetic retinopathy (DR) and age-related macular degeneration (AMD), enabled by DL models and datasets like IDRiD. Classification (46.5

The study aims to enhance the seismic stability and cost efficiency of reinforced earth retaining walls by integrating geo-synthetics and employing advanced optimization techniques. Traditional reinforced walls often face structural instability under seismic loading, leading to excessive deformation and high construction costs. Therefore, this work focuses on optimizing the design parameters of geo-synthetic reinforced soil retaining walls (GRS-RW) to achieve improved seismic performance with minimal material and economic expenditure. A novel Hippopotamus Optimization (HO) algorithm is developed and implemented in MATLAB to optimize the size and cost of GRS-RW systems. The proposed approach is evaluated against well-established optimization methods such as Particle Swarm Optimization (PSO), Biogeography-Based Optimization (BBO), and Harmony Search Algorithm (HSA). The analysis considers various seismic acceleration coefficients (kh) ranging from 0 to 0.2 to assess the structural response under dynamic loading. Simulation results indicate that the HO algorithm effectively minimizes construction cost while improving wall stability. The study reveals that extending the anchoring length of the geo-synthetic reinforcement by 28.5

Crop recommendation systems use factors like soil type, climatic conditions, and historical data in recommending suitable crops for a particular place with the help of various machine learning and deep learning models. The paper proposes a novel crop recommendation system using a Deep Convolutional Neural Network (DCNN), in which the weight updation of DCNN is done using an enhanced Honey Badger Optimization Algorithm (LOLSHBA). The conventional HBA may suffer from some drawbacks, including slow convergence speed, unbalanced exploration and exploitation, and stagnation on local optima. Thus, for training the DCNN to perform accurate crop predictions and efficient recommendations, we use an enhanced variant of HBA, namely LOLSHBA. Numerical input features such as nutrients in the soil (N, P, K), pH, temperature, humidity, rainfall, and precipitation are drawn from three publicly available Kaggle datasets. Extensive preprocessing of these datasets has been performed to handle missing values, eliminate duplicate records, and maintain structural consistency, thereby enhancing data quality before model training. Further, crop recommendation is performed using the DCNN–LOLSHBA framework. Experimental results demonstrate that DCNN–LOLSHBA consistently outperforms existing algorithms in terms of accuracy, precision, recall, F1-score, Matthews correlation coefficient (MCC), and execution time across three different crop recommendation datasets. Specifically, the proposed model achieves up to 99.68