Search Results (125)

Reliable fault diagnosis of milling machines is essential for maintaining operational stability and cost-effective maintenance; however, it remains challenging due to limited labeled data and the highly non-stationary nature of acoustic emission (AE) signals. This study introduces an optimized Few-Shot Learning framework (FSL) that integrates time–frequency analysis with attention-guided representation learning and distribution-aware classification for data-efficient fault detection. The framework converts AE signals into Continuous Wavelet Transform (CWT) scalograms, which are processed using a self-attention-enhanced ResNet-50 backbone to capture both local texture features and long-range dependencies in the signal. Adaptive prototype computation with learnable importance weighting refines class representations, while Mahalanobis distance-based matching ensures robust alignment between query and prototype embeddings under limited sample conditions. To further strengthen discriminability, contrastive loss with hard negative mining enforces compact intra-class clustering and clear inter-class separation. Comprehensive experiments under 7-way 5-shot settings and 5-fold stratified cross-validation demonstrate consistent and reliable performance, achieving a mean accuracy of 98.86% ± 0.97% (95% CI: [98.01%, 99.71%]). Additional evaluations across multiple spindle speeds (660 rpm and 1440 rpm) confirm that the model generalizes effectively under varying operating conditions. Grad-CAM++ activation maps further illustrate that the network focuses on physically meaningful fault-related regions, enhancing interpretability. The results verify that the proposed framework achieves robust, scalable, and interpretable fault diagnosis using minimal labeled data, offering a practical solution for predictive maintenance in modern intelligent manufacturing environments. Full article

Reliable bearing fault diagnosis is essential for the steady running of mechanical systems. However, existing diagnostic models still face significant limitations in feature extraction, primarily due to the non-stationary and nonlinear characteristics of vibration signals, which lead to a decline in diagnostic performance. To address this issue, this paper proposes a novel diagnostic framework that combines Particle Swarm Optimization-based Variational Mode Decomposition (PSO-VMD) for feature extraction with a deeply integrated Transformer-Convolutional Neural Network-Bidirectional Gated Recurrent Unit (TCB) model for fault classification. Bearing fault diagnosis is crucial for the stable operation of mechanical equipment, yet existing models often suffer from limited feature extraction and low detection accuracy. To address this, PSO-VMD is employed to extract informative, band-limited features from vibration signals, yielding a highly correlated feature set; a composite model TCB, combining a Transformer, a CNN, and a bidirectional GRU (BiGRU), is then used for fault classification. To prevent window-level leakage, the dataset is split before windowing and normalization, and all baselines are aligned under identical preprocessing and training settings. On the CWRU benchmark, the model attains 98.9% accuracy, 98.8% precision, 99.4% recall, 99.1% F1, and macro-F1 = 0.9766 over five runs. The approach offers a favorable accuracy –latency trade-off and yields interpretable, band-limited modes, supporting reproducible deployment in practice. Full article

This study presents a comparative techno-economic and environmental assessment of three leading stationary energy storage technologies: lithium-ion batteries, lead-acid batteries, and hydrogen systems (electrolyzer–tank–fuel cell). The analysis integrates Life Cycle Assessment (LCA) and Levelized Cost of Storage (LCOS) to provide a holistic evaluation. The LCA covers the full cradle-to-grave stages, while LCOS accounts for capital and operational expenditures, efficiency, and cycling frequency. The results indicate that lithium-ion batteries achieve the lowest LCOS (120–180 EUR/MWh) and high round-trip efficiency (90–95%), making them optimal for short- and medium-duration storage. Lead-acid batteries, though characterized by low capital expenditures (CAPEX) and high recyclability (>95%), show limited cycle life and lower efficiency (75–80%). Hydrogen systems remain costly (>250 EUR/MWh) and less efficient (30–40%), yet they demonstrate clear advantages for long-term and seasonal storage, particularly under scenarios with “green” hydrogen production and reduced CAPEX. These findings provide practical guidance for policymakers, investors, and industry stakeholders in selecting appropriate storage solutions aligned with decarbonization and sustainability goals. Full article

Modular process plants represent a promising strategy to address the increasing need for flexibility and accelerated market deployment in the production of fine and specialty chemicals. However, these modular systems are inherently susceptible to wear and fault development, while condition monitoring methods tailored to such systems remain scarce. This study presents a proof of concept for a targeted fault diagnosis approach of the modular hydraulic systems of such modular process plants and reports on its experimental validation. The methodology comprises two stages: First, model-based symptoms are calculated independently for each module and subsequently utilized within a centralized diagnostic system. This rule-based diagnosis incorporates generalized module interactions, quantified fault degrees, and the plant topology. Importantly, uncertainties arising from measurement equipment, model fidelity, and parameter variability are incorporated and systematically propagated throughout the diagnosis. The validation was conducted on a modular test rig specifically designed to simulate a range of single-fault scenarios across more than 1200 stationary operating points. The results underscore the robustness of the proposed approach: the correct fault was consistently identified, with the estimated fault magnitudes closely aligning with the actual values, exhibiting an average discrepancy of 0.029 for internal leakage of a positive displacement pump. The overall discrepancy for the experimental validation of all fault types was 0.12. Notably, no false alarms were observed, and the displayed uncertainty was considered plausible, though there remains potential for refinement. In summary, this study demonstrates the successful application of model-based symptoms for a rule-based diagnosis, representing a significant advancement toward reliable fault detection in modular hydraulic systems. Full article

Accurate forecasting of cellular traffic in non-stationary environments remains a formidable challenge, as real-world traffic patterns dynamically evolve, emerge, and vanish over time. To tackle this, we propose a novel meta-learning framework, GMM-SCM-DCM, which features a Dynamic Component Management (DCM) mechanism. This framework employs a Gaussian Mixture Model (GMM) for probabilistic meta-feature representation. The core innovation, the DCM mechanism, enables online structural evolution of the meta-learner by dynamically splitting, merging, or pruning Gaussian components based on a bimodal similarity metric, ensuring sustained alignment with shifting data distributions. A Single-Component Mechanism (SCM) is utilized for precise base learner initialisation. To ensure a rigorous and realistic validation, we reconstructed the Telecom Italia Milan dataset by applying unsupervised clustering and meta-feature engineering to identify and label four distinct functional zones: residential, commercial, mixed use, and crucially, non-stationary areas. This curated dataset provides a critical testbed for non-stationary forecasting. Comprehensive experiments demonstrate that our model significantly outperforms traditional methods and meta-learning baselines, achieving a 9.3% reduction in MAE and approximately 70% faster convergence. The model’s superiority is further confirmed through extensive ablation studies, robustness tests across base learners and data scales, and successful cross-dataset validation on the Shanghai Telecom dataset, showcasing its exceptional generalization capability and practical utility for real-world network management. Full article

This study investigates the asymmetric effects applying heat transfer as a diagnostic tool in dendritic networks with symmetrical branching, characterized by the geometric property of self-similarity. Using a Computational Fluid Dynamics (CFD) model, we analyze five structural isomers of a three-level dichotomous branching network to evaluate the relationship between fluid dynamics, heat transfer, and geometric configuration. The main constraints are geometrical; that is, the volume at each branching level remains constant, and homothetic relationships respect the Hess–Murray law both for diameters and angles between sister tubes. The model considers an incompressible and stationary Newtonian fluid flow with Reynolds numbers ranging from 10 to 2000 and heat transfer in the range 1 to 1000 W/m². Our results show that significant asymmetries in flow distribution and temperature profiles emerge in these symmetric structures, primarily due to the successive alignment of tubes between different branching levels. We found that the isomer with the lowest pressure drop is not the same as the one providing the most uniform flow distribution. Crucially, thermal analysis proves to be more sensitive than fluid dynamic analysis for detecting flow asymmetries, particularly at low Reynolds numbers less than 50 and q″ = 1000 W/m². While heat transfer does not significantly alter the fluid dynamic asymmetry, its application as a diagnostic tool for identifying flow asymmetries is effective and crucial for such purposes. Full article

The term SHIP (solar heat for industrial processes) or SHIPs (solar heat for industrial plants) refers to the use of collected solar radiation for meeting industrial heat demands, rather than for electricity generation. The global thermal capacity of SHIP systems at the end of 2024 stood slightly above 1 GWth, which is comparable to the electric power capacity of a single power station. Despite this relatively small presence, SHIP systems play an important role in rendering industrial processes sustainable. There are two aims in the current study. The first aim is to cover various types of SHIP systems based on the variety of their collector designs, operational temperatures, applications, radiation concentration options, and solar tracking options. SHIP designs can be as simple as unglazed solar collectors (USCs), having a stationary structure without any radiation concentration. On the other hand, SHIP designs can be as complicated as solar power towers (SPTs), having a two-axis solar tracking mechanism with point-focused concentration of the solar radiation. The second aim is to shed some light on the status of SHIP deployment globally, particularly in 2024. This includes a drop during the COVID-19 pandemic. The findings of the current study show that more than 1300 SHIP systems were commissioned worldwide by the end of 2024 (cumulative number), constituting a cumulative thermal capacity of 1071.4 MWth, with a total collector area of 1,531,600 m². In 2024 alone, 120.3 MWth of thermal capacity was introduced in 106 SHIP systems having a total collector area of 171,874 m². In 2024, 65.9% of the installed global thermal capacity of SHIP systems belonged to the parabolic trough collectors (PTCs), and another 22% of this installed global thermal capacity was attributed to the unevacuated flat plate collectors (FPC-Us). Considering the 106 SHIP systems installed in 2024, the average collector area per system was 1621.4 m²/project. However, this area largely depends on the SHIP category, where it is much higher for parabolic trough collectors (37,740.5 m²/project) but lower for flat plate collectors (805.2 m²/project), and it is lowest for unglazed solar collectors (163.0 m²/project). The study anticipates large deployment in SHIP systems (particularly the PTC type) in 2026 in alignment with gigascale solar-steam utilization in alumina production. Several recommendations are provided with regard to the SHIP sector. Full article

Particulate matter (PM2.5) is a critical indicator of air quality and has significant health implications. This study presents the development and evaluation of a custom-built PM2.5 device, named the P-Tracker, designed to offer an accessible alternative to commercially available air quality monitors. This paper presents the design framework used to address the requirements of a low-cost, accessible device which meets the performance of existing commercial systems. Step-by step build instructions are provided for hardware and software development and connection to the P-tracker open access website which displays the data and interactive map. To demonstrate the performance, the P-Tracker was compared against leading consumer devices, including the AtmoTube Pro by AtmoTech Inc., Flow by Plume Labs, View Plus by Airthings, and the Smart Citizen Kit 2.1 by Fab Lab Barcelona, across four controlled tests. The tests included: (1) a controlled paper combustion test in which all devices were exposed to combustion aerosols in a sealed environment alongside the DustTrak 8530 (TSI Incorporated, Shoreview, MN, USA), used as the gold standard reference, where the P-Tracker achieved a Pearson correlation of 0.99 with DustTrak over the final measurement period; (2) an outdoor test comparing readings with a stationary reference sensor, Osiris (Turnkey Instruments Ltd., Rudheath, UK), where the P-Tracker recorded a mean PM2.5 concentration of 3.08 µg/m³, closely aligning with the Osiris measurement of 3.53 µg/m³ and achieving a Pearson correlation of 0.77; (3) a controlled indoor air quality assessment, where the P-Tracker displayed stable readings with a standard deviation of 0.11 µg/m³, comparable to the AtmoTube Pro; and (4) a real-world kitchen environment test, where the P-Tracker effectively captured fluctuations in PM2.5 levels due to cooking activities, maintaining a consistent response with the DustTrak reference. The results indicate varied degrees of agreement across devices in different conditions, with the P-Tracker demonstrating strong correlation and low error margins in high-pollution and controlled scenarios. This research underscores the potential of open-source, low-cost, custom-built air quality sensors which may be developed and deployed by communities to provide hyperlocal measurements of air pollution. Full article

The Niland Moving Mud Spring, located near the southeastern margin of the Salton Sea, represents a rare and evolving geotechnical hazard. Unlike the typically stationary mud pots of the Salton Trough, this spring is a CO₂-driven mud spring that has migrated southwestward since 2016, at times exceeding 3 m per month, posing threats to critical infrastructure including rail lines, highways, and pipelines. Emergency mitigation efforts initiated in 2018, including decompression wells, containment berms, and route realignments, have since slowed and recently almost halted its movement and growth. This study integrates hydrochemical, temperature, stable isotope, and tritium data to propose a refined conceptual model of the Moving Mud Spring’s origin and migration. Temperature data from the Moving Mud Spring (26.5 °C to 28.3 °C) and elevated but non-geothermal total dissolved solids (~18,000 mg/L) suggest a shallow, thermally buffered groundwater source influenced by interaction with saline lacustrine sediments. Stable water isotope data follow an evaporative trajectory consistent with imported Colorado River water, while tritium concentrations (~5 TU) confirm a modern recharge source. These findings rule out deep geothermal or residual floodwater origins from the great “1906 flood”, and instead implicate more recent irrigation seepage or canal leakage as the primary water source. A key external forcing may be the 4.1 m drop in Salton Sea water level between 2003 and 2025, which has modified regional groundwater hydraulic head gradients. This recession likely enhanced lateral groundwater flow from the Moving Mud Spring area, potentially facilitating the migration of upwelling geothermal gases and contributing to spring movement. No faults or structural features reportedly align with the spring’s trajectory, and most major fault systems trend perpendicular to its movement. The hydrologically driven model proposed in this paper, linked to Salton Sea water level decline and correlated with the direction, rate, and timing of the spring’s migration, offers a new empirical explanation for the observed movement of the Niland Moving Mud Spring. Full article

Learning from demonstration with multiple executions must contend with time warping, sensor noise, and alternating quasi-stationary and transition phases. We propose a label-free pipeline that couples unsupervised segmentation, duration-explicit alignment, and probabilistic encoding. A dimensionless multi-feature saliency (velocity, acceleration, curvature, direction-change rate) yields scale-robust keyframes via persistent peak–valley pairs and non-maximum suppression. A hidden semi-Markov model (HSMM) with explicit duration distributions is jointly trained across demonstrations to align trajectories on a shared semantic time base. Segment-level probabilistic motion models (GMM/GMR or ProMP, optionally combined with DMP) produce mean trajectories with calibrated covariances, directly interfacing with constrained planners. Feature weights are tuned without labels by minimizing cross-demonstration structural dispersion on the simplex via CMA-ES. Across UAV flight, autonomous driving, and robotic manipulation, the method reduces phase-boundary dispersion by 31% on UAV-Sim and by 30–36% under monotone time warps, noise, and missing data (vs. HMM); improves the sparsity–fidelity trade-off (higher time compression at comparable reconstruction error) with lower jerk; and attains nominal 2σ coverage (94–96%), indicating well-calibrated uncertainty. Ablations attribute the gains to persistence plus NMS, weight self-calibration, and duration-explicit alignment. The framework is scale-aware and computationally practical, and its uncertainty outputs feed directly into MPC/OMPL for risk-aware execution. Full article

The experimental study has been carried out using advanced computer vision methods in order to visualize the moment of excitation and further propagation of a non stationary isotropic domain in a hybrid aligned nematic (HAN) microsized volume under the effect of a laser beam focused on a bounding liquid crystal surface. It has been shown that, when the laser power exceeds a certain threshold value, in bulk of the HAN microvolume, an isotropic circular domain is formed. We also observed a structure of alternating concentric rings around the isotropic circular region, which increases with distance from the center of the isotropic domain. The formation of a sequence of rings in a polarizing microscopic image indicates the formation of a complex topology of the director field in the HAN cell under study. The following evolution of the texture can be represented by two modes. Firstly, the “fast” heating mode, which is responsible for the formation and explosive expansion of an isotropic zone in bulk of the HAN microvolume with characteristic time ${\tau }_1$ due to a laser spot heating on the upper indium tin oxide (ITO) layer. Secondly, the “slow” heating mode, when an isotropic zone and concentric rings slowly expand with characteristic time ${\tau }_2$ mainly due to the finite thermoconductivity of ITO layer. When the laser power significantly exceeds the threshold value, damped oscillations of the isotropic domain are observed. We also introduced the metrics that allows quantitatively estimate the behavior of texture observed. The results obtained form an experimental basis for further investigation of thermomechanical force appearing in the LC system with coupled gradients of temperature and director fields. Full article

In automated container terminals (ACTs), rolling bearings of equipment serve as crucial power transmission components, and their performance directly determines the operational efficiency, reliability, and service life of the entire equipment. Rolling bearing fault detection and diagnosis are key means to improve production efficiency, reduce the safety risks, and achieve sustainable development of equipment in ACTs. However, existing rolling-bearing diagnosis models are vulnerable to environmental noise and interference, depressing accuracy and raising misclassification, and they seldom achieve both noise robustness and a lightweight design; robustness usually increases complexity, while compact networks degrade under low signal-to-noise ratios. Therefore, this paper proposes a noise-robust, lightweight, and interpretable deep learning framework for fault detection and diagnosis of rolling bearings in automated container terminal (ACT) equipment. The framework comprises four coordinated components, including Time-Domain Filter, Frequency-Domain Filter, Physical-Feature Extraction module, and Classification module, whose joint optimization yields complementary time–frequency representations and physics-aligned features, and fuses into robust diagnostic decisions under noisy and non-stationary environments. The first component highlights impulsive transients, the second component emphasizes harmonic and sideband modulation, the third module introduces two differentiable and rolling bearing-signal-informed objectives to align learning with characteristic bearing signatures by weighted-average kurtosis and an Lp/Lq-based envelope-spectral concentration index, and the last module integrates multi-layer convolutional neural networks (CNN) and Deep Kolmogorov–Arnold Networks (DeepKAN). Finally, two public datasets are employed to estimate the model’s performance, and results indicate that the proposed method outperforms others. Full article

The relationship between renewable (REN) and non-renewable (NREN) energy and economic growth plays a fundamental role in sustainable development. The number of studies on this relationship in countries with the highest REN consumption is limited. This study analyzes the effects of REN and NREN on economic growth between 1970 and 2023, focusing on the ten leading countries in REN consumption. These countries constitute an appropriate sample for analysis, not only due to their high REN capacity but also because they represent diverse levels of economic development. For this purpose, second-generation panel data methods were employed to investigate the long-run effects, taking into account cross-sectional dependence and heterogeneity in the dataset. The CADF unit root test developed by Pesaran indicated that all variables are stationary at their first differences. The Westerlund panel cointegration test confirmed the existence of a long-run relationship among the variables. Long-run coefficients were estimated using the Common Correlated Effects Mean Group (CCE) approach developed by Pesaran and the Augmented Mean Group (AMG) estimators proposed by Bond & Eberhardt and Eberhardt & Teal. The results revealed that renewable energy consumption has a positive and significant effect on economic growth, while fossil fuel consumption continues to have a favorable effect on growth. However, the negative and significant effect of primary renewable energy production suggests that technological deficiencies and efficiency problems in current production structures may play a role. Overall, this study highlights the necessity of aligning energy policies with both environmental sustainability and economic growth objectives. Full article

Synchronous motors are pivotal to modern industrial systems, particularly those aligned with Industry 4.0 initiatives, due to their high precision, reliability, and energy efficiency. This review systematically examines fault detection and diagnostic techniques for synchronous motors from 2021 to 2025, emphasizing recent methodological innovations. A PRISMA-guided literature survey combined with scientometric analysis via VOSviewer 1.6.20 highlights growing reliance on data-driven approaches, especially deep learning models such as CNNs, RNNs, and hybrid ensembles. Model-based and hybrid techniques are also explored for their interpretability and robustness. Cross-domain methods, including acoustic and flux-based diagnostics, offer non-invasive alternatives with promising diagnostic accuracy. Key challenges persist, including data imbalance, non-stationary operating conditions, and limited real-world generalization. Emerging trends in sensor fusion, digital twins, and explainable AI suggest a shift toward scalable, real-time fault monitoring. This review consolidates theoretical frameworks, comparative analyses, and application-oriented insights, ultimately contributing to the advancement of predictive maintenance and fault-tolerant control in synchronous motor systems. Full article

Wearable systems are increasingly adopted for health monitoring and wellness promotion. Among the most relevant biosignals, the electrocardiogram (ECG) plays a key role; however, in wearable settings (e.g., during physical activity), it is often corrupted by electromyogram (EMG) interference. This study presents a novel adaptive algorithm, template masking (TM), which integrates the stationary wavelet transform (SWT) with template matching for denoising the ECG from EMG. The method identifies the optimal wavelet and decomposition level to maximise detail sparsity. To mitigate EMG interference, after alignment in the SWT domain with a template, the detail coefficients are multiplied by a binary mask and smoothed. TM was compared with soft and hard thresholding on (1) simulations combining clinical ECGs (MIT-BIH database) and synthetic EMGs with different signal-to-noise ratios (SNRs), and (2) experimental signals including ECGs acquired with dry electrodes corrupted by EMGs (SimEMG database, also varying SNRs), as a potential wearable scenario. In both cases, TM yielded significantly lower reconstruction errors at SNRs below 5 dB ($p<0.01$) and significantly outperformed thresholding in the sensitivity of R-peaks estimation ($p<0.001$). These results demonstrate the potential of TM, highlighting the value of adaptive denoising algorithms. Full article