Search Results (1,059)

The present study introduces a comprehensive machine-learning framework for modeling, interpretation and optimization of the CNC turning procedure employing coated cutting inserts. The primary novelty of this work lies in the integrated pipeline that leverages a multimodal experimental dataset in order to simultaneously model surface roughness and residual stresses, as well as to interpret these predictions within a unified optimization scheme. Particularly, a deep learning model was developed incorporating a convolutional encoder for analyzing time-series signals and a static encoder for the investigated machining parameters. This fused representation enabled accurate multi-task predictions, capturing the thermo-mechanical interactions that govern surface integrity. Additionally, to ensure interpretability, a surrogate meta-model based on the deep model’s predictions was established and evaluated via Shapley Additive Explanations. This analysis quantified the relative influence of each cutting parameter, linking data-driven insights to contact-mechanical principles. Furthermore, a multi-objective optimization scheme was implemented to derive Pareto optimal trade-offs among the examined parameters that could enhance the machining efficiency. Overall, the integration of deep learning, interpretable modeling and optimization established a coherent framework for data-driven decision making in turning, highlighting the importance of model transparency in advancing intelligent manufacturing systems. Full article

Abrasive water jet machining (AWJM) is a non-traditional machining process that is increasingly employed for shaping hard-to-machine materials, particularly titanium (Ti)-based alloys such as Ti-6Al-4V. Owing to its non-thermal nature, AWJM enables effective material removal while minimising metallurgical damage and preserving subsurface integrity. The process performance is governed by several interacting parameters, including jet pressure, abrasive type and flow rate, nozzle traverse speed, stand-off distance, jet incident angle, and nozzle design. These parameters collectively influence key output responses such as the material removal rate (MRR), surface roughness, kerf geometry, and subsurface quality. The existing studies consistently report that the jet pressure and abrasive flow rate are directly proportional to MRR, whereas the nozzle traverse speed and stand-off distance exhibit inverse relationships. Nozzle geometry plays a critical role in jet acceleration and abrasive entrainment through the Venturi effect, thereby affecting the cutting efficiency and surface finish. Optimisation studies based on the design of the experiments identify jet pressure and traverse speed as the most significant parameters controlling the surface quality in the AWJM of titanium alloys. Recent research demonstrates the effectiveness of artificial neural networks (ANNs) for process modelling and optimisation of AWJM of Ti-6Al-4V, achieving high predictive accuracy with limited experimental data. This review highlights research gaps in artificial intelligence-based fatigue behaviour prediction, computational fluid dynamics analysis of nozzle wear mechanisms and jet behaviour, and the development of hybrid AWJM systems for enhanced machining performance. Full article

The durability of the carbon fiber-reinforced polymer (CFRP)–concrete interface is a critical indicator for assessing the service life of composite structures in cold regions. This study systematically investigates the normal bond behavior under coupled deicing salt and freeze–thaw cycles through single-sided salt-frost tests on 126 specimens. The influence of surface roughness, number of freeze–thaw cycles, concrete strength grade, and CFRP material type was systematically evaluated. The results demonstrate that bond behavior is positively correlated with surface roughness, with the f₂ interface exhibiting optimal performance and increasing the ultimate capacity by up to 76.61% compared to the smooth interface. CFRP cloth showed superior bond retention compared to CFRP plates, which experienced a bond strength loss rate up to 26.90% higher than cloth specimens after six cycles. A critical performance threshold was identified between six and eight cycles, where the failure mode transitioned from cohesive adhesive failure to brittle interfacial debonding. Concrete matrix strength had a negligible effect compared to the dominant environmental damage. A two-parameter prediction model based on cycle count and roughness was established with high accuracy. SEM analysis confirmed that epoxy resin cracking, fiber–matrix debonding, and microcrack propagation in the concrete surface layer were the fundamental causes of macroscopic mechanical degradation. These findings provide a theoretical foundation for optimizing interface treatment and predicting the structural integrity of CFRP-strengthened systems in salt-frost regions. Full article

Dry machining of AISI 1045 steel is attractive for sustainable manufacturing but makes it more challenging to control surface roughness R_a. This work investigates dry turning of AISI 1045 using a 2³ factorial design with three center points (11 runs) and compares a traditional power-law correlation with a quadratic response surface model (RSM). The power-law fit on log-log data explains only about 20% of the variance, whereas the quadratic RSM achieves R² ≈ 0.98 with a root-mean-square error (RMSE) of 0.62–0.77 µm based on leave-one-out cross-validation and bootstrap resampling. Feed rate S is identified as the dominant factor, while cutting speed V and depth of cut t have secondary but non-negligible interactive effects. Sobol global sensitivity indices confirm that S and S² account for more than half of the output variance. The optimized setting within the tested domain (V ≈ 83 m/min, S = 0.60 mm/rev, t = 0.10 mm) yields a predicted R_a ≈ 5.3 µm, appropriate for semi-roughing prior to grinding. The proposed framework combines small-sample RSM, Lasso regularization, uncertainty quantification and Sobol analysis to provide an uncertainty-aware model for optimizing dry-turning parameters of AISI 1045 steel. Full article

Surface roughness is a critical quality attribute in laser cutting, directly influencing edge integrity, dimensional accuracy, and post-processing requirements. While most studies address surface roughness through forward modeling and optimization, practical manufacturing tasks often require solving inverse parameter selection problems, where process parameters must be chosen to satisfy prescribed surface quality requirements. In this study, surface roughness control in laser cutting is formulated within an inverse target-tracking framework based on response surface methodology (RSM). A quadratic response surface model is established using a Box–Behnken experimental design, with cutting speed, laser power, and assist-gas pressure as input factors. The fitted response surface provides an explicit forward mapping within a bounded operating window and serves as a local surrogate for methodological demonstration of target-oriented parameter estimation. Based on this surrogate model, a model-predicted feasible roughness range within the investigated design space is identified as R_a = 1.952–4.212 μm. For prescribed roughness targets within this interval, an inverse least-squares target-tracking formulation is employed to compute model-based parameter estimates. The inverse results are presented as continuous set-point maps and tabulated operating conditions, accompanied by a target-versus-predicted consistency check performed at the model level. Owing to the statistically significant lack-of-fit of the forward response surface, the inverse results presented in this study should be interpreted as theoretical, model-based estimates intended to illustrate the proposed framework rather than as experimentally validated process set-points. The proposed approach highlights both the potential and the limitations of inverse target-tracking strategies based on response surface models and underscores the need for statistically adequate models and independent experimental validation for industrial application. Full article

Tantalum pentoxide (Ta₂O₅) films deposited on fused silica substrates are critical components of high-power laser systems. Ion-assisted electron beam evaporation (IAD-EBE) is the mainstream technique for fabricating Ta₂O₅ films. However, it commonly requires extensive experimental efforts for deposition quality optimization, while each coating cycle is extremely time-consuming. To solve this issue, this work establishes a dataset targeting the surface roughness (Rq) and refractive index (n) of Ta₂O₅ films using atomic force microscopy, as well as ellipsometer and deposition experiments. Influence of assisting ion source beam voltage (V)/current (I) and Ar (Q₁)/O₂ (Q₂) flow rate on the n and Rq of Ta₂O₅ films are analyzed. Combining energy-field mechanism analysis with a Bayesian optimization approach (PI-BO), both deposition quality prediction and feature analysis of process parameters are achieved. The determination coefficient/mean absolute error for the prediction models of n and Rq reach 0.927/0.013 nm and 0.821/0.049 nm, respectively. Based on sensitivity analysis, the weight factors of V, I, Q₁, and Q₂ affecting n/Rq of Ta₂O₅ films are determined to be 0.616/0.274, 0.199/0.144, 0.113/0.582, and 0.072/0.000. V and Q₂ are identified as the core factors for regulating deposition quality. The optimal ranges for V and Q₂ are 600~700 V and 70~80 sccm, respectively. This study proposes a PI-BO method for predicting Rq and n of Ta₂O₅ films under small-data conditions, while determining the preferred parameter ranges and their sensitivity weight factors. These findings provide effective theoretical support and technical guidance for IAD-EBE strategy design and optimization of optical films in high-power laser systems. Full article

Ceramsite foam concrete (CFC), recognized for its lightweight, thermal insulation, and eco-friendly properties, is a promising material for composite structures. The interfacial shear bond behavior between CFC and normal concrete (NC) critically governs the structural integrity of CFC-NC systems. This study investigates the interfacial shear bond strength through direct double shear tests on twelve cubic specimens with controlled interface roughness and casting intervals. Quantitative analysis reveals that increased roughness enhances shear strength by up to 28.6~59.5%, while prolonged casting intervals reduce strength by 22.3~34.6%. Notably, excessive roughness shifts failure modes from interfacial debonding to material failure within CFC, where shear bond strength becomes governed by CFC’s compressive strength. A rigid–plastic model is developed to characterize the shear bond behavior of CFC-NC interface and demonstrates 96% accuracy in predicting experimental results. The findings provide useful insights for improving CFC-NC composite design in engineering applications. Full article

In conventional band sawing, the long-span compression of the flexible saw blade often results in large fluctuations in cutting force, low cutting efficiency, and poor force predictability. To address these issues, this study investigates the dynamic cutting force modeling and experimental validation of ultrasonic vibration-assisted band sawing using 304 stainless steel as the workpiece material. Based on an analysis of the band sawing mechanism, an ultrasonic vibration-assisted approach is proposed to modify the contact conditions between the saw blade and the workpiece. A dynamic model of the saw blade is established using the string vibration equation, and a multi-tooth dynamic cutting force prediction model is further developed by incorporating variable cutting depth characteristics under ultrasonic vibration. Comparative experiments are conducted between conventional sawing and ultrasonic vibration-assisted sawing to validate the proposed model. At feed rates of 0.1–0.4 mm/s and preload values of 0.1–0.5 mm, the proposed model predicts dynamic cutting forces with good agreement to experimental results, achieving an average relative error of 5.44%. Under typical cutting conditions for difficult-to-machine materials, ultrasonic vibration-assisted sawing reduces the average cutting force and feed force by approximately 15% and 18%, respectively, while decreasing surface roughness along the feed direction by about 21%, thereby improving sawing efficiency and surface quality. Full article

This paper analyzes different approaches for the mathematical modeling and optimization of process parameters in the hard turning process of 42CrMo4 steel using a hybrid approach combining response surface methodology (RSM), multi-criteria decision making (MCDM), and machine learning through, support vector regression (SVR) with one-factor-at-a-time (OFAT) sensitivity analysis. Controlled process parameters such as cutting speed, depth of cut, feed, and insert radius are applied to conduct the experiments based on a full factorial experimental design. RSM was used to develop models that describe the effect of controlled parameters on surface roughness and cutting forces. Special emphasis was placed on the analysis of standardized residuals to evaluate the predictive capabilities of the RSM-developed model on an unseen data set. For all four outputs considered, analysis of the standardized residuals shows that over 97% of the points lie within ±3 standard deviations. A multi-criteria optimization technique was applied to establish an optimal combination of input parameters. The SVR model had high performance for all outputs, with coefficient of determination values between 89.91% and 99.39%, except for surface roughness on the test set, with a value of 9.92%. While the SVR model achieved high predictive accuracy for cutting forces, its limited generalization capability for surface roughness highlights the higher complexity and stochastic nature of surface formation mechanisms in the turning process. OFAT analysis showed that feed rate and depth of cut have been shown to be the most important input variables for all analyzed outputs. Full article

This study employs a multi-objective particle swarm optimization (MOPSO) algorithm to address the dual-objective challenge in the robotic polishing of Ti-6Al-4V. The aim is to determine optimal parameters that minimize surface roughness while maximizing the material removal rate (MRR), thereby improving both surface quality and processing efficiency. First, a material removal depth model for end-face polishing is established based on Preston’s equation and theoretical analysis, from which the MRR model is derived. Subsequently, orthogonal experiments are conducted to investigate the influence of process parameters and their interactions on surface roughness, followed by the development of a quadratic polynomial roughness prediction model. Analysis of variance (ANOVA) and model validation confirm the model’s reliability. Finally, the MOPSO algorithm is applied to obtain the Pareto optimal solution set, yielding the optimal parameter combination. Experimental results demonstrate that at a normal contact force of 7.58 N, a feed rate of 4.52 mm/s, and a spindle speed of 5851 rpm, the achieved MRR and Ra values are 0.2197 mm³/s and 0.291 μm, respectively. These results exhibit errors of only 5.64% and 2.65% compared to model predictions, validating the proposed method’s effectiveness. Full article

This paper investigates the impact of lubrication and thermal effects on the performance of single-metal seals in roller cone bits, and it establishes the geometric, material, and operating parameter models for the single-metal seal. Based on the theory of statistics, the Greenwood–Williamson (G–W) model is employed to predict the contact stress of micro-protrusions on the sealing pair surface. This study establishes a Thermal Elastohydrodynamic Lubrication (TEHL) coupling model for single-metal seals, which utilizes the deformation matrix method to characterize the microscopic deformation of the sealing interface. The central difference method is applied to solve the oil film thickness and temperature distribution in the axial and film thickness directions of the sealing surface. The results indicate that the sealing zone is predominantly under rough peak contact pressure, operating in a mixed-lubrication state. Oil film thickness negatively correlates with static contact pressure, and seal pressure and pre-compression displacement significantly influence lubrication performance. Experiments validate the numerical simulation results, with a mean relative error of less than 15%, confirming the model’s effectiveness. This study offers a theoretical basis for optimizing single-metal seal design, enhancing the reliability and lifespan of roller cone bits in harsh conditions. Full article

Remote sensing enables large-scale, image-based assessments of river dynamics, offering new opportunities for hydrological monitoring. We present a publicly available dataset consisting of 281,024 satellite and aerial images of U.S. rivers, constructed using an Application Programming Interface (API) and the U.S. Geological Survey’s National Hydrography Dataset. The dataset includes images, primary keys, and ancillary geospatial information. We use a manually labeled subset of the images to train models for detecting rapids, defined as areas where high velocity and turbulence lead to a wavy, rough, or even broken water surface visible in the imagery. To demonstrate the utility of this dataset, we develop an image segmentation model to identify rivers within images. This model achieved a mean test intersection-over-union ($IoU$) of 0.57, with performance rising to an actual $IoU$ of 0.89 on the subset of predictions with high confidence (predicted $IoU$ > 0.9). Following this initial segmentation of river channels within the images, we trained several convolutional neural network (CNN) architectures to classify the presence or absence of rapids. Our selected model reached an accuracy and F1 score of 0.93, indicating strong performance for the classification of rapids that could support consistent, efficient inventory and monitoring of rapids. These data provide new resources for recreation planning, habitat assessment, and discharge estimation. Overall, the dataset and tools offer a foundation for scalable, automated identification of geomorphic features to support riverine science and resource management. Full article

Seepage–dissolution in carbonate rock fractures serves as the core driver governing the evolution of key engineering projects, including reservoir dam stability, CO₂ geological sequestration, and unstable rock collapse mitigation strategies. While physical heterogeneity (e.g., fracture aperture, mineral distribution) is widely recognized as a critical factor regulating dissolution processes, the specific influence of mineral distribution heterogeneity on dissolution rates still lacks quantitative quantification. To address this gap, this study focuses on limestone fractures and employs multi-component reactive transport numerical simulations to model acidic fluid (pH = 5.0) seepage–dissolution under two Darcy flux conditions (37.8/378 m·yr⁻¹). It investigates the controlling mechanisms of fracture roughness (λ_b = 0.036~0.308) and calcite contents (55%, 75%, 95%) on dissolution dynamics, and analyzes spatial variations in local Darcy velocity, reaction rate, and effective dissolution rate (R_eff,i). Results demonstrate that mineral distribution heterogeneity directly induces pronounced spatial heterogeneity in dissolution behavior: diffusion dominates under low flux (simulation duration: 48.3 days), forming discrete reaction fronts (~15 mm) controlled by mineral clusters; advection prevails under high flux (simulation duration: 4.83 days), generating alternating dissolution–deposition zones (~7.5 mm) with R_eff,i one order of magnitude greater than that under low flux. Notably, 55% calcite content yields the highest R_eff,i (1.87 × 10⁻¹¹ mol·m⁻²·s⁻¹), 0.94 orders of magnitude greater than that at 95% calcite content. A strong linear correlation (R² > 0.98) exists between the Damköhler number (Da_I) and R_eff,i at the same calcite content. Furthermore, the synergistic interaction between fracture aperture and mineral heterogeneity amplifies dissolution complexity, with high roughness (λ_b = 0.308) coupled with 55% calcite content achieving the highest R_eff,i of 2.1 × 10⁻¹¹ mol·m⁻²·s⁻¹. This study provides critical theoretical insights and quantitative data support for fractured rock mass evolution prediction models, geological hazard prevention, and geological carbon sequestration optimization. Full article

This study contributes to the advancement of circular economy practices in polymer manufacturing by applying machine learning algorithms (MLA) to predict the tensile strength of recycled low-density polyethylene (LDPE) building films. As the construction and packaging industries increasingly seek eco-efficient and low-carbon materials, recycled LDPE offers a valuable route toward sustainable resource management. However, ensuring consistent mechanical performance remains a challenge when reusing polymer waste streams. To address this, tensile tests were conducted on LDPE films produced from recycled granules, measuring tensile strength, strain, mass per unit area, thickness, and surface roughness. Three established machine learning algorithms—feed-forward Neural Network (NN), Gradient Boosting Machine (GBM), and Extreme Gradient Boosting (XGBoost)—were implemented, trained, and optimized using the experimental dataset using R statistical software (version 4.4.3). The models achieved high predictive accuracy, with XGBoost providing the most robust performance and the highest level of explainability. Feature importance analysis revealed that mass per unit area and surface roughness have a significant influence on film durability and performance. These insights enable more efficient production planning, reduced raw material usage, and improved quality control, key pillars of sustainable technological innovation. The integration of data-driven methods into polymer recycling workflows demonstrates the potential of artificial intelligence to accelerate circular economy objectives by enhancing process optimization, material performance, and resource efficiency in the plastics sector. Full article

Understanding particle transport in rough-walled fractures is essential for predicting flow behavior, clogging, and permeability evolution in natural and engineered subsurface systems. This study develops a fully coupled CFD–DEM framework to investigate how self-affine fractal roughness, represented by the Joint Roughness Coefficient (JRC), governs fluid–particle interactions across multiple scales. Nine fracture geometries with controlled roughness were generated using a fractal-based surface model, enabling systematic isolation of roughness effects. The results show that increasing JRC introduces a hierarchy of geometric perturbations that reorganize the flow field, amplify shear and velocity-gradient fluctuations, and enhance particle–wall interactions. Particle migration exhibits a nonlinear response to roughness due to the competing influences of disturbance amplification and the formation of preferential high-velocity pathways. Furthermore, roughness-controlled scaling relations are identified for mean particle velocity, residence time, and energy dissipation, revealing JRC as a fundamental parameter linking geometric complexity to transport efficiency. Based on these findings, a unified mechanistic framework is established that conceptualizes fractal roughness as a multiscale geometric forcing mechanism governing hydrodynamic heterogeneity, particle dynamics, and dissipative processes. This framework provides new physical insight into transport behavior in rough fractures and offers a scientific basis for improved prediction of clogging, proppant placement, and transmissivity evolution in subsurface engineering applications. Full article