Wafer map defect pattern classification supports quality monitoring in semiconductor manufacturing, but public benchmark datasets such as WM-811K exhibit extreme class imbalance, where majority classes can dominate standard metrics. This study aims to improve minority class performance while maintaining inference efficiency. Building on an iFormer-based hybrid backbone, we propose the Pattern-Selective Sequential Hybrid Network (PSS-HNet), which redesigns attention blocks to sequentially integrate local interaction (Modulated Convolution) and global interaction (Modulated Axial Attention) and applies sigmoid-based gating to control contextual information injection. Experiments on WM-811K (9 classes) compare iFormer (baseline), Axial-only, Axial+Modulation, and PSS-HNet using macro-averaged metrics as primary indicators, along with class-wise analysis and efficiency evaluation. PSS-HNet improves Macro-Recall by 1.02 percentage points (from 0.8852 to 0.8954) and Macro-F1 by 0.54 percentage points (from 0.9044 to 0.9098) over the baseline while maintaining similar accuracy. It also reduces computational cost and inference latency to 0.754 G FLOPs, 4.381 M parameters, and 7.682 ms, compared with 1.103 G FLOPs, 6.245 M parameters, and 8.666 ms for the baseline. Overall, selective sequential local–global integration provides a favorable balance between minority class performance and efficiency.

Railway bogies are typically engineered with conservative safety margins, which frequently results in the premature disposal of components retaining significant structural integrity. This study proposes a comprehensive 3D modelling framework designed to accurately predict and extend the Remaining Useful Life (RUL) of the bogie structure. To achieve this, a Building Information Modelling (BIM) approach was used, not only for the bogie, but for all train, using a rolling stock in Portugal as a case study. The use of both real and virtual sensors installed in the bogie, with data collected with a sampling rate according to the specificity of each sensor and, next, managed through machine learning tools, allows to implement a predictive maintenance (PdM) policy that aid to extend the RUL. The proposed approach demonstrates that extending the operational life of the bogie is both feasible and safe. This facilitates a strategic transition from the current practices to new approaches that improve the Availability of the Physical Assets, including through the metaverse.

Spent coffee grounds (SCG) are the main by-product generated by the coffee industry, with an estimated annual production of approximately 7 million tons. Although commonly treated as waste, SCG constitute a valuable source of phenolic compounds, particularly chlorogenic acid, which has been associated with antimicrobial, antioxidant, antimutagenic, anti-inflammatory, and cardioprotective properties. These bioactive compounds are of interest as functional ingredients for food, cosmetic, and pharmaceutical applications. However, their recovery by conventional extraction methods often depends on volatile, flammable, or toxic organic solvents. In this context, hydrophobic eutectic solvents (HES) have emerged as a greener and more sustainable alternative. In the present study, phenolic compounds were extracted from SCG using HES combined with microwave-assisted extraction (MAE). Sixteen terpene-based HES formulated with fatty acids and fatty alcohols were evaluated. Among them, camphor:dodecanoic acid and borneol:dodecanoic acid gave the highest total phenolic contents. Process optimization showed that the borneol:dodecanoic acid system, under 12% water content, a 1:10 solid-to-liquid ratio, 57 °C, and 120 min, reached 80.94 ± 4.44 mg GAE g−1 by MAE. HPLC analysis revealed chlorogenic, caffeic, and ferulic acids as the main phenolic compounds, while the extracts also displayed high antioxidant activity. Overall, these findings demonstrate that HES-MAE is a promising and sustainable strategy for the recovery of value-added phenolics from SCG.

As oil and gas development increasingly targets low and ultra-low permeability reservoirs, conventional recovery techniques often prove insufficient for mobilizing residual oil. Surfactant flooding, a key chemical enhanced oil recovery (EOR) technology, thus requires careful system optimization and mechanistic investigation. This study focuses on low-permeability reservoirs in the Changqing Oilfield, evaluating three surfactant systems—YHS-Z1 (a 7:3 mass ratio blend of hydroxypropyl sulfobetaine and cocamide),YHS-Z2 (a polyether carboxylate, a nonionic-anionic composite) and a middle-phase microemulsion system (Heavy alkylbenzene sulfonate and hydroxysulfobetaine were combined with a mass ratio of 7:3)—through a series of experiments including interfacial tension measurement, contact angle analysis, static and dynamic oil displacement tests, as well as emulsion transport/retention index assessments, to comprehensively characterize their oil displacement properties. Based on the experimental data, this study constructed four classical regression models: Ridge Regression, Random Forest (RF), Gradient Boosting Regression (GBR), and Support Vector Regression (SVR), and conducted a comparative analysis of their predictive performance. The results demonstrate that the Random Forest (RF) model achieved the optimal prediction performance, with a Mean Absolute Error (MAE) of 1.8245, a Mean Absolute Percentage Error (MAPE) of 4.78%, and a coefficient of determination (R2) of 0.9428 on the training set. Further analysis using the SHapley Additive exPlanations (SHAP) algorithm revealed that the retention index is the primary global factor (accounting for 49.79% of the variance), while significant intergroup differences exist in the primary factors across different surfactant systems. Concurrently, single-factor and multi-factor sensitivity analyses were conducted to elucidate synergistic effects and threshold behaviors among parameters. The optimal parameter combination, identified via a random search method, achieved a predicted recovery factor of 45.61%, representing a 6.57% improvement over the highest experimental value. This study demonstrates that machine learning methods can effectively identify the dominant factors in oil displacement and enable synergistic parameter optimization, thereby providing a theoretical foundation for the efficient development of surfactant flooding in low-permeability reservoirs.

Hot-air drying is widely adopted for herbs because it is robust and easy to control, yet it is often energy-intensive and may operate far from optimal conditions when industrial dryers rely on fixed airflow paths and large air recirculation rates. This work investigates a conventional basket-type, adiabatic hot-air dryer through an instrumented 30 h drying campaign and a psychrometric energy analysis. The hot-air drier is designed to reduce the relative humidity of herbs from the environmental value (highly variable as a function of the species, the weather conditions, and, mostly, the seasonality) to 20%. Temperature and relative humidity were measured at four positions to characterize the shelf-by-shelf drying sequence and to identify process phases. A mass balance indicated that approximately 3.8 t of water was removed during the trial. Based on the measured thermodynamic states of the moist air and estimated airflow rates (35,000–53,000 m3/h), the baseline configuration was analyzed and an upgrade strategy was proposed to improve dehumidification and overall efficiency while preserving the conventional hot-air-drying concept. The alternative solution integrates a refrigeration-based dehumidification loop (heat pump) to decouple moisture removal from sensible heating; three plant layouts and seasonal boundary conditions (summer/winter) were simulated. For the most favorable configurations, the specific final–primary energy demand and the associated CO2-equivalent emissions were reduced by about 70–85% compared with the baseline, depending on the airflow rate and recirculation strategy. The results highlight practical retrofit options for existing herb dryers and provide a transparent framework for translating measured psychrometric states into energy and emission indicators. The results, achieved and discussed in this study, were used to optimize the utilization of an already existing and operative hot-air dryer. Based on the proposed working configuration, the dryer now allows achieving the fixed target for herb mixtures of the previous configuration and, at the same time, reducing the energy consumption and associated equivalent CO2 emitted, as well as achieving process completion in less time.

Accurate yaw alignment is critical for maximizing power capture in horizontal-axis wind turbines, as even moderate yaw misalignment leads to significant aerodynamic losses, increased actuator usage, and accelerated mechanical wear. This research paper proposes a hybrid smart yaw control system for small-scale wind turbines that combines real-time measurements with short-term wind direction prediction to improve alignment accuracy, operational reliability, and energy efficiency under realistic operating conditions. The system integrates four wind direction information sources, such as physical wind vane sensing, live online weather data, forecast data, and a data-driven prediction module within a structured priority framework (VANE → LIVE → FORECAST → AI), to ensure continuous yaw control during sensor or communication unavailability. The prediction module is based on a long short-term memory (LSTM) neural network trained in MATLAB using live data from an online platform, with sine–cosine encoding employed to address the circular nature of directional data. The yaw controller incorporates a ±15° deadband, dwell-time logic, shortest-path rotation, and cable-safe constraints to reduce unnecessary actuation while maintaining effective alignment. The proposed system is validated through MATLAB/Simulink simulations and real-time microcontroller-based experiments using a stepper motor-driven nacelle. Compared with conventional vane-based yaw control, the hybrid AI-assisted approach reduces the average yaw error by approximately 35–45%, maintains a yaw error within ±15° for more than 90% of the operating time, increases average electrical power output by 3–5%, and reduces yaw motor energy consumption by 10–15%, while decreasing corrective yaw actuation events by 30–40%. These results demonstrate that integrating an LSTM-based wind direction predictor with multi-source wind data provides a robust, low-cost, and practically deployable yaw control solution that enhances energy capture and mechanical durability in small-scale wind turbines.

The large-scale accumulation of steel slag from steelmaking and the over-exploitation of natural aggregates pose significant environmental and resource challenges. Focusing on the arid-cold region of Xinjiang, China, this study proposes the use of steel slag as a substitute for natural aggregates in pavement engineering. Through experimental performance evaluation and regionalized life cycle assessment (LCA), the technical feasibility and carbon reduction potential of this application were comprehensively evaluated. Results indicate that steel slag asphalt mixtures meet or exceed specification requirements in terms of high-temperature stability, water stability, and low-temperature crack resistance. However, volume stability decreases slightly with higher steel slag content and finer particle size, necessitating pretreatment for long-term durability. A local life cycle assessment model considering regional transportation factors was applied to the G30 Luhuo Expressway project. During the materialization stage, steel slag was used to replace 30% of the natural aggregates, reducing approximately 6718 kg of carbon dioxide equivalent emissions (31.4%). This, to some extent, reduced the extraction of natural resources, saved land resources, and alleviated the problems of resource shortage and price fluctuations. Sensitivity analysis reveals a positive correlation between carbon reduction and steel slag content, while transport distance strongly influences overall benefits, with a critical threshold of about 78 km defining the effective utilization range. Furthermore, a multi-objective optimization model balancing service life, cost, and carbon reduction was developed to identify an optimal steel slag content scheme, maximizing comprehensive benefits under constrained conditions. This work confirms the technical viability of steel slag pavement in extreme climates and provides a systematic framework integrating environmental benefits and logistical constraints, supporting regional industrial synergy and promoting circular economy practices in low-carbon infrastructure.

To address the challenges of low accuracy and complex influencing factors in predicting horizontal well fracturing productivity during the development of unconventional oil and gas resources such as tight oil, this paper proposes a productivity prediction framework based on an improved feature selection method and an ensemble learning model. This study employs a fusion analysis using the entropy weight method to combine Pearson correlation analysis and improved gray relational analysis (IGRA) for feature selection. Thirteen machine learning models were tested with six distinct parameter combinations to construct a Stacking-based ensemble learning model, with base models including Random Forest (RF), Ridge Regression (RR), and Artificial Neural Network (ANN). Particle Swarm Optimization (PSO) was employed to optimize hyperparameters, followed by interpretability analysis using SHapley Additive exPlanations (SHAP). The results indicate that the model with fused weights demonstrated optimal performance. The Stacking model achieved significantly improved accuracy after PSO optimization, with the coefficient of determination increasing by 4.9%, outperforming all comparison models. Engineering guidance is provided: Under current geological conditions, sand ratio and displacement fluid volume require fine-tuning to prevent over-treatment. Fracturing design should implement differentiated strategies based on the target sand body thickness. This study not only delivers a high-precision production prediction tool but also offers decision support for efficient unconventional oil and gas field development through its exceptional interpretability.

Rotary kiln-based activated carbon production combines high-temperature operation with flammable/reducing gases, carbonaceous dust, and downstream off-gas treatment and acid/base washing, creating complex escalation pathways. This study prioritizes safety improvements by applying classical failure modes and effects analysis (FMEA) and a transparent Fuzzy-FMEA framework to 18 representative failure modes (six each for kiln/activation, acid/base handling, and atmosphere/control). Five experts evaluated Severity, Occurrence, and Detection on a 10-point scale. The fuzzy model used triangular membership functions (L/M/H), a monotonic 27-rule base, Mamdani max–min inference, and centroid defuzzification to compute a continuous fuzzy risk priority number (FRPN, 0–10). Classical FMEA identified dust explosion (RPN = 405), temperature control failure (RPN = 378), and off-gas leakage (RPN = 324) as the highest-ranked risks. Fuzzy-FMEA preserved the top-risk group while more strongly highlighting barrier-related risks, placing off-gas leakage, instrumentation/interlock failure, and electrostatic ignition control alongside dust explosion (FRPN 9.221–9.332). The rankings were strongly correlated (Spearman ρ = 0.871; Kendall τ = 0.752), yet mid-risk items were rearranged (mean |Δrank| = 2.06; max = 5), improving discrimination within tied RPN clusters. The five highest-priority scenarios were reconstructed into actionable engineering packages, including dust and ignition control, off-gas integrity linked to shutdown logic, interlock proof testing and bypass management, and independent protection layers for kiln temperature control.

The rising demand for sustainable and circular approaches in the agro-industrial sector has generated interest in repurposing herbal tea residues as sources of high-value bioactive compounds. This work focusses on recovering phytochemicals from Rosa canina L. peel and seed dust (by-products of processing of herbal tea in filter tea bags) using green extraction techniques. Two environmentally friendly technologies were used: ultrasound-assisted extraction (UAE) with a sonotrode and subcritical fluid extraction (SBFE). The extracts were qualitatively profiled using (HR) LC-ESI-QToF-MS/MS and quantified using HPLC-PDA. Both by-products contained phenolic substances, including gallic acid derivatives, ellagic acid, and flavonoids such as quercetin and quercetin-3-O-glucoside (only in the peel). Additionally, Folin–Ciocalteu’s assay was used to determine Total Phenolic content (TP). The extraction efficiency was considered in terms of phenolic compound recovery and total phenolic content obtained under the respective experimental conditions. The maximum TP for SBFE was reported in samples extracted with ethanol–water (48:52) at 180 °C, producing 3876.67 GAE mg/L for peel and 1648.57 GAE mg/L for seeds. In the UAE, extraction with ethanol–water (48:52) for 10 min yielded the maximum TP of 2773.81 GAE mg/L for peel and 957.86 GAE mg/L for seeds. These findings highlight the potential of R. canina infusion by-products as long-term sources of bioactive compounds for use in nutraceutical, cosmetic, and pharmaceutical industries.