IntroductionThis study investigates the influence of duplex surface engineering on the microstructure, mechanical properties, and corrosion resistance of CMT-welded AA6061 aluminum alloy joints.MethodsAA6061 butt joints were fabricated using Cold Metal Transfer (CMT) welding and subsequently treated by shot peening followed by TiN and CrN PVD coatings deposited through reactive magnetron sputtering. Microstructural characterization was performed using SEM and XRD, while mechanical and corrosion properties were evaluated through tensile, hardness, flexural, and electrochemical corrosion tests.ResultsDuplex-treated specimens exhibited improved coating densification, enhanced mechanical interlocking, and refined microstructure. The CrN duplex-treated joint achieved a maximum tensile strength of 325 MPa, microhardness improvement from 78 HV to 110 HV, and approximately 34% enhancement in flexural strength. Corrosion current density decreased significantly from 1 × 10−4 A/cm2 to 5 × 10−4 A/cm2 with nearly 95% reduction in corrosion rate.DiscussionThe combined effect of shot peening and TiN/CrN coatings effectively improved the mechanical integrity and corrosion resistance of welded AA6061 alloy. Duplex surface engineering offers a promising approach for enhancing the service life of lightweight aluminum structures used in marine and automotive applications.

This study presents a comprehensive multiscale comparison of LPBF-fabricated A286 and IN718 lattice structures across three architected topologies (BCC/BCCz, Gyroid/Hexstar and Honeycomb) to elucidate how alloy microstructure and geometry jointly control deformation and failure mechanisms. Quasi-static compression tests revealed a consistent topology-dependent strength hierarchy, with Honeycomb achieving the highest peak stresses (A286: 3.3 GPa; IN718: 2.89 GPa), followed by BCC/BCCz and Gyroid/Hexstar designs. A286 exhibited higher initial stiffness (9.3-11.2 GPa) but experienced early instability due to particle detachment and oxide-assisted cracking, whereas IN718 demonstrated smoother strain hardening and superior energy absorption, with W₆₀ values of 1.71-2.04 MJ/m³ compared to 1.32-1.85 MJ/m³ for A286. XRD analysis showed more compressive residual stresses in A286 (to - 585 MPa) than IN718 (to - 504 MPa), alongside higher microstrain (ε ≈ 5.6 × 10⁻³) and smaller crystallite size (27 nm vs. 43 nm), indicating greater lattice distortion in A286. FTIR spectra revealed stronger carbide- and oxide-related bands in A286, while IN718 displayed predominantly O-H and CO₂ signatures consistent with ductile surface formation. FESEM and EDS analyses confirmed fundamentally different failure pathways: A286 failed via particle pull-out, sinter-neck rupture and oxide-decorated cracking, whereas IN718 deformed through slip-dominated smearing, laminated tearing and blunted microcracks. Collectively, the results establish that topology governs global deformation, while alloy chemistry dictates whether collapse proceeds through brittle-assisted rupture (A286) or ductile, slip-mediated flow (IN718). This framework provides design guidelines for tailoring alloy-topology combinations for lightweight, impact-resistant applications.

The main aim of the present research is to improve the tensile strength of lightweight aluminium alloy 6082, which makes it fit for many advanced engineering applications. Considerable efforts have been made to investigate the tensile characteristics, hardness, microstructural and fractography of AA6082/TiC/graphene composite developed at different reinforcements loadings varying from 1 wt.% to 6 wt. %. The reinforcements used in the current research are TiC and graphene. The aluminium matrix composite fabricated using nanosized particles by stir-casting route. The tensile strength increases with the increase of TiC and graphene particles in the AA6082 matrix up to certain limit i.e. 5 wt.%. Once the reinforcement increases beyond the point at which agglomeration of the particulates starts, the tensile strength and hardness of the developed composites decrease. The x-ray diffraction (XRD) and scanning electron microscopy (SEM) was used for the investigation of elements and morphology. The fractography of the developed composite depicts the morphology of the fractured tensile specimens. The elongated dimples, tear ridges and micro-voids are found during fractography. The failure of the hybrid composites changes from ductile fracture to cleavage failure.

Intermittent demand forecasting remains a persistent challenge in large-scale supply chains due to extreme sparsity, irregular demand occurrence, and highly variable demand magnitudes. While recent studies have increasingly emphasized architectural complexity to address these challenges, comparatively less attention has been directed toward the role of statistically grounded feature representation under sparse-demand conditions. This study introduces the Smoothed Hybrid Occurrence-Size (SHOS) framework as an event-preserving feature-engineering approach for intermittent-demand forecasting. SHOS decomposes demand into latent occurrence probability and conditional demand size components and generates adaptive, series-specific statistical representations using sparsity-aware exponential smoothing. Rather than functioning as a standalone forecasting model, SHOS operates as a feature-generation mechanism that embeds occurrence-size structure directly into supervised learning pipelines. The proposed framework was evaluated using a large-scale automotive aftermarket dataset consisting of approximately 56,000 dealer-part time series and approximately 1.4 million monthly observations generated after preprocessing and zero-padding. Models were evaluated using rolling-window cross-validation, signal-preservation analysis, and robustness studies across heterogeneous demand segments. Under the evaluated sparse-demand setting and model configurations, SHOS-augmented tree-based models substantially improved forecasting accuracy and stability relative to raw-feature baselines. In particular, the SHOS-augmented LightGBM configuration reduced the mean absolute error by approximately 46.3% relative to the baseline model, while the weighted mean absolute percentage error improved by more than 40%. Beyond conventional forecasting accuracy, the study additionally demonstrates that SHOS preserves event timing, peak structure, and frequency-domain characteristics that are often distorted by conventional smoothing approaches. The results further suggest that statistically grounded feature representations can substantially improve sparse-demand learning behaviour under the evaluated automotive aftermarket forecasting environment. Rather than establishing a universal hierarchy between representation and architectural complexity, the findings demonstrate the effectiveness of event-preserving representation-oriented forecasting under highly intermittent demand conditions.

This study investigates the degradation of polyamide 12 (PA12) powder used in Selective Laser Sintering (SLS) technology, focusing on how repeated usage affects powder performance and the quality of printed parts. Multiple printing cycles were carried out using an EOS P396 SLS printer, including pure virgin powder, reused powder, and a 50:50 mixture of new and used powder. The research evaluated powder behavior during the printing process, mechanical properties through tensile testing, and visual surface quality of printed samples. Results showed significant issues in the first and second cycles, such as uneven powder spreading, sintering outside target areas, and part deformation. Tensile tests revealed the lowest strength in parts from the second cycle, while the test cycle with mixed powder showed the highest average stress values and the best visual quality. The findings mostly confirm EOS suggestions, that powder degradation significantly affects mechanical performance and print quality, and that proper mixing and moisture control can mitigate some negative effects. This research highlights the importance of powder management for maintaining part integrity and optimizing the sustainability of SLS production.

The superior mechanical and tribological properties offered by multi-element alloy coatings are drawing significant attention, but choosing the best deposition parameters is still difficult because of several requirements. In this study, the synthesis parameters of CoCrFeNi multi-entropy alloy coatings were optimized using three multi-criteria decision-making techniques: TOPSIS, MOORA, and MARCOS. The impact of criterion importance on the final rankings was evaluated using three weighting schemes: Equal, MEREC, and CRITIC. According to rank stability analysis, alternative A19 continuously obtained the highest rank across all techniques, whereas alternative A16 was consistently found to be the least favorable condition. While MARCOS generated somewhat more variable rankings for mid-performing alternatives, TOPSIS and MOORA showed strong agreement across all weighting schemes, suggesting low sensitivity to weight variation. These trends were further supported by Pearson correlation analysis, which showed somewhat lower correlations with MARCOS but coefficients ≥0.9 for TOPSIS and MOORA variants. In order to speed up performance-driven coating development, the combined approach shows a strong and methodical framework for choosing the best process parameters for HEA coatings. It is also easily adaptable to other material systems.

Abstract Micro Arc Oxidation (MAO) is an advanced electrochemical surface-processing technique capable of producing hard, dense and adherent ceramic coatings on aluminium alloys, exhibiting superior wear and corrosion properties than traditional anodizing. This research project produced MAO coating on CMT-welded AA6082-T6 aluminium alloy joints and the effect of current density, the oxidation time and the distance in between the electrodes on the coating characteristics were systematically studied using Response Surface Methodology (RSM) based parametric mathematical modelling (PMM). The PMMs generated very accurate predictions of the porosity and hardness of the aluminium alloy joints with an error margin less than 2% and 99% confidence level. Detailed characterization was done to test model predictions. The analysis of the SEM showed how the crater-type discharge channels, micropores, and the patterns of molten-oxide resolidification changed, and optimal parameters resulted in homogeneous and compact structures. The thickness variation between about 58 μm to 110 μm with current density was established by cross-sectional SEM. The XRD patterns showed that, γ-Al 2 O 3 , θ-Al 2 O 3 and α- Al 2 O 3 phases existed and were transformed with α- Al 2 O 3 enrichment at moderate current density (0.19 A/cm 2 ) that increased peak hardness. High density of current (0.25 A/cm 2 ) inhibited the formation of α- Al 2 O 3 and high porosity. Optimized MAO conditions of 0.19 A/cm 2 current density, 20 min oxidation time, and 6-cm spacing between electrodes gave minimum porosity (2.07 vol) and maximum hardness (1459.36 HV). The coatings also exhibited positive wear behaviour, and decreased friction coefficient was observed due to high density of ceramic phase. The overall results of modelling and characterization offer a solid system of application of MAO coating on welded aluminium structures in the high-performance engineering applications.

Electrochemical micro-machining (ECMM) enables high-precision fabrication of micro-features in difficult-to-machine materials; however, its strongly nonlinear, multi-physics nature and the high cost of experimentation severely limit reliable data-driven modeling. This study presents a physics-guided machine learning framework for robust multi-response prediction of ECMM performance using polymer graphite electrodes. Controlled experiments were conducted with non-treated and cryogenically treated electrodes, and four critical responses were evaluated: material removal rate (MRR), overcut (Oc), surface roughness (Ra), and taper angle (Ta). Physics-guided descriptors incorporating interaction-driven and severity-based features were constructed to embed mechanistic structure associated with electrochemical excitation and tool-electrolyte-workpiece coupling. Ensemble learning models were trained and rigorously validated using repeated cross-validation. The optimal physics-guided XGBoost models achieved coefficients of determination of 0.817 (MRR), 0.914 (Oc), 0.866 (Ra), and 0.769 (Ta), with corresponding mean absolute errors of 0.013 g/min, 0.026 mm, 0.261 μm, and 0.049°, respectively, consistently outperforming polynomial and purely data-driven baselines. Ablation analysis confirmed that physics-guided feature integration improved both predictive accuracy and cross-validated stability under limited experimental data conditions. Parity and residual diagnostics demonstrated strong generalization without systematic bias. The results establish physics-guided learning as an effective strategy for bridging electrochemical process physics and data-driven modeling, enabling accurate, robust, and interpretable prediction of ECMM responses. The proposed framework provides a scalable foundation for intelligent micro-manufacturing, with potential applications in adaptive process optimization and digital manufacturing workflows.

In manufacturing, the demand is always for better proficiency, less operational costs, and greater effectiveness. The key in achieving these requirements through adept handling is, in fact, maintenance of machines and devices. Combinations of regular maintenance schemes, preventive and curative methods, usually tend to swing between unnecessary maintenance jobs and unexpected equipment failures. This situation calls for a need to develop a more sophisticated approach, which gives rise to Predictive Maintenance (PdM). PdM is different from the rest because it forecasts changes that lead to failure in the equipment even before they seem probable, preparing the ground for pre-emptive measures, thereby reducing downtime, and reducing maintenance costs on a really large scale. However, the introduction of PdM does not come without corresponding challenges, which include: Data compilation and management within PdM systems, difficulty in modeling machinery's nonlinear dynamics, difficulties involved in integrating PdM systems into traditional operational pipelines of manufacturing entities, as well as justification of return on investments. To these issues, this paper adopts sophisticated mathematical models that have been selected carefully for their capabilities to handle bulk data, decipher intricate interrelations, and accurately predict future failures. Examples include Time Series Analysis: ARIMA and SARIMA use sensor temporal patterns; Survival Analysis, using Cox Proportional Hazards model, to measure machinery failure survival horizons; and advanced Machine Learning algorithms such as Stochastic Forests and Gradient Boosting Machines known for their nonlinear data acuity and insight into feature significance levels. Empirical validation of the model across diverse data samples reveals that the proposed model excels on all metric levels by achieving an 8.5% improvement in predictive precision, an 8% increase in accuracy, 4.9% boost in recall, 9.5 times faster velocity, a 4.5 increment in AUC, and an impressive 10.4% shot in specificity over what is available today. The work resolves the tensions between theory and real-life application while setting a new benchmark in predictive maintenance, thereby heralding a paradigm shift in the levels of manufacturing efficiency and reliability sets.

​Abrasive waterjet drilling of polymers is difficult to optimize owing to nonlinear interactions and conflicting performance requirements. This study suggests combining experimental, ML models, multi-objective optimization, and statistical validation to improve polycarbonate drilling performance. A full factorial design was used to vary water pressure (250–350 MPa), standoff distance (1.5–2.5 mm), and traversal rate (300–500 mm/min) in 125 tests. DE and drilling rate were performance responses. Analysis of variance showed water pressure and standoff distance were the principal variables affecting the hole diameter error (DE) and drilling rate (DR).Four machine learning models like XGBoost, Decision Tree, Random forest, and AdaBoost Regressor were built in the Anaconda-based Python environment. The Random forest model demonstrated high reliability in capturing complex process behavior, with R² = 0.92263 for DE and 0.90471 for DR. Random forest was utilized as a stand-in paradigm for multi-objective optimization using the Grey Wolf optimizer, Whale optimization algorithm, and Arithmetic optimization algorithm. With Whale optimization method, Pressure=350 MPa, Standoff distance=2.5 mm, and Traverse rate=300 mm/min produced the highest performance with decreased DE (0.1238) and improved DR (2.0450). The Friedman test (p < 0.001) and post-hoc analysis show that Whale optimization method outperforms Grey Wolf and Arithmetic optimization algorithms.

The advent of designing flexural systems was to provide accurate micro and nano displacement between the assembly members of the mechanism. Applications that used these mechanisms included linear compressors, optomechanical devices, Stirling engines, cryocoolers, microcheck valves, Flexure-based Electromagnetic Linear actuators, and so on. This paper focuses on the machine-tool fabrication of a novel flexural mechanism encased within the spindle head of the microdrilling head. The mechanism cushioned the micro drill and protected it from permanent damage when encountering undeclared resistance in the material matrix. Furthermore, this paper focuses solely on building a 3-axis drilling machine tool in a Product Lifecycle Management environment. The study follows a systematized approach for validating the machine tool design, starting with the hierarchical assembly of components using various kinematic chains. The next phase involves assigning the necessary motions to these components. The final stage utilizes a virtual controller and post-processor to simulate and control machine tool movements. Validation is then performed on the simulated workpiece to ensure design accuracy and functionality. The key findings of the studies indicate that the designed mechanism can move in and out and can also puncture micro-holes in metal. This is the mechanism’s capability, which is the novelty.

This work investigates the effects of fabric weave architecture on the mechanical and tribological properties of sheep wool/epoxy composites manufactured using the hand lay-up technique. Four different weave patterns, namely plain, twill, satin, and basket, were fabricated using a manual handloom and reinforced in an epoxy matrix. The mechanical, interfacial, and wear properties were characterized using tensile, flexural, impact, pull-out, and dry sliding wear tests according to ASTM specifications. Among all the architectures, the satin weave architecture showed the maximum tensile strength of 132.6 MPa, flexural strength, and yield strength due to its lower crimp and higher yarn alignment, which favoured better load transfer. On the other hand, twill architecture offered the best tribological characteristics, and the Taguchi L27 analysis evidenced that the sliding distance is the most dominating parameter that controlling the wear rate. The SEM images showed evidence of good fiber-matrix bonding in satin and twill composites, and the plain and basket architectures revealed higher fiber pull-out and brittle fractures. These observations establish that modifications in weaving architecture could help attain significantly improved stiffness, strength, and wear resistance, and thus wool-reinforced epoxy emerges as a bio-sustainable material for light-weight structural and tribological applications.

Accurate demand forecasting for spare parts under true cold-start conditions remains a fundamental challenge due to extreme demand sparsity, zero inflation, and the complete absence of historical demand information. Conventional time-series methods, single-stage machine learning models, and sequence-based probabilistic forecasters are inherently ill-suited to this setting, as they either rely on historical observations or fail to properly represent zero-demand events and distributional uncertainty. To address this gap, this study proposes a novel Zero-Inflated Gamma Monte Carlo (ZIG MC) framework that explicitly decomposes demand into occurrence and magnitude components and generates fully probabilistic forecasts suitable for risk-aware inventory decision-making. The proposed approach integrates a Bernoulli classifier for demand occurrence with a Gamma-based magnitude model and employs Monte Carlo simulation to construct predictive demand distributions. Model performance is evaluated using a strict part-level nested cold-start validation protocol on an industrial transactional dataset, ensuring genuine generalization to previously unseen parts. Results demonstrate that ZIG MC consistently outperforms strong single-stage regressors, statistical hurdle models, and a state-of-the-art probabilistic deep learning benchmark (DeepAR). The proposed framework achieves the lowest point forecast error (MAE = 5.65), representing a 6.4% improvement over the strongest single-stage baseline, while also delivering superior scale-independent accuracy (MASE = 0.87). Probabilistic evaluation using the Continuous Ranked Probability Score shows an order-of-magnitude improvement over DeepAR (CRPS = 3.27 vs. 15.41), indicating substantially better calibration and sharper predictive distributions under cold-start conditions. Quantile-based reliability analysis confirms that predicted service-level quantiles are well aligned with empirical outcomes, enabling reliable translation of forecasts into inventory policies. Statistical significance testing further confirms that the observed performance gains are robust and not attributable to random variation. Sensitivity analyses demonstrate that forecasting performance is stable with respect to distributional assumptions and Monte Carlo sampling size. Inventory simulations reveal that ZIG MC yields higher fill rates and lower stock-out risk than competing probabilistic models at comparable inventory levels, directly linking improved probabilistic calibration to operational benefits. Collectively, these findings establish ZIG MC as a robust and practical framework for cold-start forecasting of intermittent demand, offering a principled foundation for uncertainty-aware inventory planning in data-scarce environments.

Abrasive Waterjet Machining (AWJM) is a reliable non-traditional technology for machining polymer-based engineered materials with low thermal degradation, dimensional inaccuracy, and surface damage. This study examines polycarbonate hole drilling performance using 125 full-factorial experimental trials using process parameters water pressure, standoff distance, and traverse rate. With a coordinate measuring machine and stylus-based profilometer, kerf angle, entry and exit circularity, and surface roughness were measured in a detailed metrological research. Four ML models were created to develop accurate predicting capabilities, with the Random Forest (RF) model performing best in all responses. RF predicted processes accurately with high coefficient-of-determination R2 values (0.92, 0.82, 0.82, and 0.92) and low error coefficients (RMSE 0.196, 0.045, 0.042, and 0.452). The best drilling settings were found using evolutionary algorithms like Biogeography-Based Optimization (BBO), Particle Swarm Optimization (PSO), Salp Swarm Optimization (SSO), and Tug-of-War Optimization (TWO). Deng's similarity metric ranked SSO as the best optimizer based on many responses. The SSO produced the optimal settings (Wp = 250 MPa, Sd = 1.5, and Tr = 300 mm/min) for reduced kerf deviation, circularity and surface roughness. Under optimal circumstances, anticipated responses matched experimental results, proving the integrated ML-optimization framework's strength.

Ultra-high molecular weight polyethylene (UHMWPE), a thermoplastic, is commonly used as the primary material for plastic spacers in complete knee artificial implants in the biomedical sector. However, holes are required for screwing the plastic spacers to the femoral and tibial components. This material frequently presents problems during conventional drilling, such as burr formation, rapid tool wear, and poor surface finish, resulting in inadequate hole quality. Due to constraints in conventional processes, alternative machining techniques for UHMWPE are being examined. In this work, a full-factorial design was used to drill 10 mm holes into the work material to determine the characteristics of holes produced by abrasive water jet drilling (AWJD). The following process variables: traverse rate (v) (150, 300, 450, and 600 mm/min), abrasive mass flow rate (ma) (250, 300, 350, and 400 g/min), and abrasive water jet pressure (p) (210, 260, 310, and 360 MPa) are considered. Also, a detailed analysis of the geometric characteristics of the drilled holes was conducted, including surface roughness (Ra), roundness errors, and roundness of the entrance and exit diameters. The testing results show that the parameters p and v primarily influence roundness and Ra features. It was found that the higher v of 600 mm/min and p of 360 MPa result in the lowest degree of inaccuracy. Scanning electron microscopy (SEM) examines the roundness deviation in the drilled holes. It was revealed that more abrasives were deposited on the drilled-hole surfaces at 360 MPa, especially at higher magnifications.

More than 80% of the wrist load is applied on the distal radius, and distal radius fractures (DRFs) are the most traumatic wrist injuries. In the development of orthopedic wrist cast, customization, ventilation, weight, and recovery monitoring are the most important design targets. The CAD modelling and finite element analysis (FEA) of the cast using stiff polylactic acid (PLA) and soft thermoplastic polyurethane (TPU) layered composite are applied to develop customized wrist cast model with optimum strength and comfort. The ANSYS CFX-based topology optimization and computational fluid dynamics (CFD) analysis are used to develop optimum ventilation openings to dissipate heat generated at the cast-skin interfaces. The fused filament fabrication (FFF) based additive manufacturing (AM) is used to manufacture the optimized wrist cast model. The force and electromyography (EMG) wearable sensors data-based and genetic algorithm (GA)-tuned artificial neural network (ANN) machine learning modelling is used to determine integrated optimal cast system. The simulation results demonstrated that the cast is loaded with 26.7 MPa peak stress and 4.39 mm maximum deformation during typical wrist motions with a safety margin of 2.25. The optimized cast weighs 148 g and maintain the skin temperature to be below 33.85 degrees C. The GA-tuned ANN model is developed with 3000 datasets divided into (75%) training, (15%) testing, and (10%) validation tests. Finally, the optimal number of straps, and the tightening pressure are determined to be 3, and 11.24 mmHg respectively with R value of 0.9988.

Confined fire environments in marine and industrial compartments present serious safety challenges due to rapid heat accumulation, restricted ventilation, and complex buoyancy-driven flow behavior. Accurate prediction of propagation of heat and development of plume is important for the effective and efficient design of thermal detection and mist-based fire suppression systems. In the present study, a 2D transient Computational Fluid Dynamics analysis has performed to investigate buoyancy-driven heat transfer generated by heat source of 0.5 m diameter maintained at 450 °C inside a closed container of dimensions 2.6 m × 2.6 m. The air was considered as the working fluid, and natural convection was modeled to capture plume rise, entrainment, and thermal stratification effects. The heat source was sequentially positioned at four diagonal locations: D1 (0.65 m, 0.65 m), D2 (1.95 m, 0.65 m), D3 (1.95 m, 1.95 m), and D4 (0.65 m, 1.95 m) to assess the influence of source orientation relative to enclosure (Container) boundaries. The numerical methodology incorporates mesh-independence verification, transient time-step control with Courant numbers maintained below 2, appropriate turbulence modeling, and strict mass conservation to ensure numerical accuracy. The simulation reveals the formation of strong buoyancy-driven thermal plumes with peak velocities in the range of 0.9-1.3 m/s. Lower heat source configurations produce tall vertical plumes, while upper source placements result in early plume impingement and the development of ceiling jets, significantly enhancing lateral heat transport. Temperature and density fields indicate localized high-temperature zones near the heat source, with air density reducing to approximately 0.5-0.7 kg/m3 within plume cores. Turbulent kinetic energy reaches peak values of the order of 10-2 m2/s2 along plume shear layers and ceiling interaction regions, reflecting intense mixing. Pressure and mass imbalance analyses confirm stable transient behavior, with mass imbalance remaining within ± 10-⁷ kg/s. The findings present design trends under idealized enclosed conditions, which may support future development of fire detection and suppression strategies for marine and industrial compartments after further validation under realistic operating conditions.

The present study represents a comprehensive investigation of GTAW Process implemented for ERNiCrMo-10 (Hastelloy C-22) weld overlay on SS 316 L austenitic stainless steel. To assess the weld overlay’s performance, visual testing, hardness testing, bend testing, optical spectroscopy for chemical composition analysis, potentiodynamic polarization technique for corrosion resistance evaluation, as well as macro and microstructural observation were carried out. An average corrosion rate of 0.742 mpy for the overlay was achieved owing to uniform distribution. Microstructural study also observed primary and secondary inter-laminar spacing. These phases contribute to improved structural integrity and adequate hardness characteristics. Dilution of 1.5 mm from the base metal was achieved which can be attributed to precise control and minimal alloy mixing, The average spacings between primary and secondary arms were also measured and values of 4.239 μm and 4.559 μm, were achieved. These findings particularly provide invaluable inputs to the considerate industry of petrochemical and pharmaceutical sectors.

In the small-scale farming, transplantation of tomato is performed manually using hand drilling without considering the standard agronomy practices. To develop innovative products with reduced size and automatic operations, the analysis and design of the feeding, picking, and planting components of the automatic transplanting machine need to be the focus area. The integrated approaches of conceptual design, concepts evaluation and selection, synthesis and numerical modeling of mechanisms, path manipulator design, components and assembly SolidWorks modeling, Matlab and ADAMS software validation simulations, and PLC based control system design are used to develop the target technology. During design and analysis, a 128 cell standard plug tray, 42 mm grid depth, 110 mm average seedling height, 35 cm plant spacing, 40 cm row spacing, and 192 seedlings/min planting capacity were selected as design criteria. The results from kinematics analysis and optimal design of gripper indicated that the clamping and insertion angles should be in the ranges of 16 degrees-22 degrees and 10.6 degrees-14.8 degrees respectively to prevent damage. Furthermore, the optimum clamping angle (beta) and insertion angle (alpha) were found to be 20 degrees and 13.4 degrees respectively for successful clamping and picking of seedlings. A combination of linear and fourth order polynomial models have been developed to provide accurate trajectory plans for the path manipulator. The ADAMS software simulation results are directly fitted with the theoretical results, and the modeling of the seedling pickup mechanisms provides a basis for future bench tests. For a standard 128 cells plug tray, and target frequency of 192 seedlings/min, the pickup device with eight grippers is designed to effectively pick the whole row of tomato seedlings within 2.5 s. Finally, to synchronize the transplanting operations and ensure a continuous supply of signals, photoelectric positioning sensors, magnetic switches, pneumatic components, and PLC control unit are selected and positioned at the optimum locations.

The promotion of Electrical Discharge Machining (EDM) and vibration aided Electric Arc Machining (EAM-V) processes is characterized in the study in terms of their capability for precision manufacture, mainly drawing any performance comparisons from a machine learning approach. The present machine learning study aims to predict some important metrics of machining utility, such as Material Removal Rate (MRR), Tool Wear Rate (TWR), and Surface Roughness (SR), against process parameters like current, pulse-on/off time, etc. Some advanced models like Gradient Boosting and Random Forest are used to analyse the efficacy and effectiveness of EDM and EAM-V, comparing the respective influences these parameters have on honing outcomes. The study describes an elaborate methodology: data collection, preprocessing, feature scaling, and application of multiple regression algorithms for machining performance forecasting. The experimental data for model training and testing were partitioned into 80% and 20%, respectively. The results revealed that Gradient Boosting (GB) performed better than Random Forest (RF) for all parameters. In GB, the R2 values of MRR, TWR, and SR were higher; hence, its degree of accuracy was superior in comparison with RF. For instance, an R2 value of 0.970, 0.994, and 0.999 was achieved by GB for MRR, TWR, and SR, respectively, thus proving its better predictive ability. Moreover, according to average predicted values, EAM-V performs better for MRR; EDM, comparatively, from TWR and SR, is more suitable for precision applications. The performance validation of GB through RMSE and MAE also confirms its efficacious predictions.