Kielce University of Technology

Vehicle crush boxes are one of the safety elements used in vehicles to minimize damage that may occur during an accident. The task of crush boxes is to absorb the energy which is generated during an accident. In this study, peak force, energy absorption and specific energy absorption values of cylindrical composite crush boxes, to which 0.25% and 0.50% graphene was added, were experimentally investigated with hydrothermal aging. The composite crush boxes were produced with vacuum infusion method. Glass, aramid and carbon fibers and their hybridizations were used as fibers. During hybridization, the winding order of the fibers was changed from inside to outside. The parameters for hydrothermal aging were selected as 500 h and 1000 h at 60 °C. The highest energy absorption value was obtained in the carbon fiber-reinforced sample CFRPG1H2 with 0.25% graphene-added epoxy resin matrix, aged for 1000 h. The lowest peak strength was observed in the aramid fiber-reinforced sample AFRPG2H2 with 0.50% graphene-added epoxy resin matrix, hydrothermally aged for 1000 h. It was observed that increasing the graphene addition rate reduced the negative effects on aging. It was determined that increasing the graphene ratio by 0.25% had an effect on aging.

Reliable tool-wear monitoring is essential for maintaining machining quality and preventing unscheduled downtime in manufacturing. This investigation presents a sound-based classification framework for identifying wear states in the turning of AISI 316L stainless steel using advanced gradient-boosting models. Acoustic signals were recorded under constant cutting parameters to eliminate process-induced variability, and each recording was divided into standardized 2 s segments. A total of 540 multidomain features-including RMS, ZCR, spectral descriptors, Mel-spectrogram statistics, MFCCs and their derivatives, and discrete wavelet energies-were extracted to capture both stationary and transient characteristics of tool-workpiece interactions. Feature selection was performed using a three-stage pipeline comprising Boruta, LASSO, and SHAP analysis, resulting in a compact subset of highly informative descriptors. LightGBM, XGBoost, and CatBoost classifiers were trained using stratified 10-fold cross-validation across three wear states: Unworn, Slight wear, and Severe wear. LightGBM and XGBoost achieved the best performance, with mean accuracies above 0.96 and strong PRC-AUC and ROC-AUC values (0.98-1.00). Although Slight wear remained the most difficult class due to its transitional acoustic characteristics, all models showed clear separability for Unworn and Severe wear conditions. The results confirm that boosted decision-tree methods combined with SHAP-enhanced feature selection provide an effective, low-cost, and non-contact solution for tool-wear classification in 316L turning.

This study evaluated the performance of four temperate wetland macrophytes (Phragmites australis, Iris pseudacorus, Typha latifolia, and Alisma plantago-aquatica) in floating treatment wetlands (FTWs) exposed to a Cu-Pb-Cd-As mixture. Mesoscale (35 L) batch reactors were operated for 84 days under low (1 mg/L) and high (5 mg/L) metal(loid) loadings, with nutrient-only treatments as controls, enabling assessment of early plant development, nutrient removal, metal(loid) fate, and microbial community responses. Metal(loid) exposure inhibited nitrification and slowed phosphorus removal. Under low loading, FTWs with Typha and Alisma achieved the highest removal efficiencies for Cu (75% and 61%) and Pb (89% and 88%), whereas Phragmites and Iris were more effective for Cd (similar to 30%) and As (similar to 15%). At high loading, removal from solution increased to 86-92% (Cu), 90-95% (Pb), 73-89% (Cd), and 29-34% (As), driven mainly by abiotic and biogeochemical immobilization rather than direct accumulation in biomass or sediments. Metals accumulated predominantly in roots. Mass balance analysis showed that under low loading, plant biomass and sediments together accounted for up to 14.44 mg Cu (48%, Alisma), 8.23 mg Pb (27%, Alisma), and 9.89 mg Cd (33%, Iris), while As was mainly sediment-bound. Under high loading, plant-associated percentages decreased but absolute retention increased (up to 24.45 mg Cu, 37.32 mg Cd, and 14.49 mg As), indicating phytostabilization. Analysis of the developed microbiome revealed that high loading enriched Pseudomonas and Flavobacterium, while Sphingopyxis and Sphingorhabdus persisted under low exposure, indicating their utility as bioindicators.

Ensuring the safety and reliability of wind turbine systems in cold climates requires robust icing detection, as missed events can lead to structural compromise. This study proposes an intelligent information fusion framework that integrates vibration-based structural dynamics with environmental data through a pipeline of automated Operational Modal Analysis (OMA) and temperature compensation. Five classification architectures—Optimized Threshold (OT), Random Forest (RF), XGBoost (XGB), Support Vector Machine (SVM), and Gated Recurrent Unit (GRU)—were rigorously evaluated using rolling-window time-series cross-validation on high-fidelity experimental data from a large-scale climate chamber. To address the safety-critical nature of the application, the framework prioritizes Recall to minimize False Negative (FN) errors and incorporates non-parametric statistical validation (Kruskal-Wallis and Dunn’s post-hoc tests) to quantify model stability. Results reveal a “simplicity paradox” where the physics-informed OT model achieved the highest operational reliability (Recall = 0.9600), outperforming advanced ensemble and deep learning methods in both safety and statistical stability. This work demonstrates that meticulous feature-level fusion and domain-specific engineering enhance system resilience more effectively than increased algorithmic complexity. The proposed methodology provides a scalable foundation for multi-sensor fusion and adaptive predictive maintenance in renewable energy infrastructures.

Ensuring robust railway safety is paramount for efficient and reliable transportation systems, a challenge increasingly addressed through advancements in artificial intelligence (AI). This review paper comprehensively explores the burgeoning role of AI in enhancing the safety of railway operations, focusing on key contributions from machine learning, neural networks, and computer vision. We synthesize current research that leverages these sophisticated AI methodologies to mitigate risks associated with railroad accidents and optimize railroad tracks management. The scope of this review encompasses diverse applications, including real-time monitoring of track conditions, predictive maintenance for infrastructure components, automated defect detection, and intelligent systems for obstacle and intrusion detection. Furthermore, it delves into the use of AI in assessing human factors, improving signaling systems, and analyzing accident/incident reports for proactive risk management. By examining the integration of advanced analytical techniques into various facets of railway operations, this paper highlights how AI is transforming traditional safety paradigms, paving the way for more resilient, efficient, and secure railway networks worldwide.