Search Results (685)

Drivetrain systems operate under varying operating conditions (OCs), which often obscure early-stage fault signatures and hinder robust condition monitoring (CM). This work introduces an AI digital platform developed during the EEDRIVEN project, featuring a holistic CM framework that integrates statistical time series methods—using Generalized AutoRegressive (GAR) models in a multiple model fault diagnosis scheme—with deep learning approaches, including autoencoders and convolutional neural networks, enhanced through a dedicated decision fusion methodology. The platform addresses all key CM tasks, including fault detection, fault type identification, fault severity characterization, and remaining useful life (RUL) estimation, which is performed using a dynamics-informed health indicator derived from GAR parameters and a simple linear Wiener process model. Training for the platform relies on a limited set of experimental vibration signals from the physical drivetrain, augmented with high-fidelity multibody dynamics simulations and surrogate-model realizations to ensure coverage of the full space of OCs and fault scenarios. Its performance is validated on hundreds of inspection experiments using confusion matrices, ROC curves, and metric-based plots, while the decision fusion scheme significantly strengthens diagnostic reliability across the CM stages. The results demonstrate near-perfect fault detection (99.8%), 97.8% accuracy in fault type identification, and over 96% in severity characterization. Moreover, the method yields reliable early-stage RUL estimates for the outer gear of the drivetrain, with normalized errors < 20% and consistently narrow confidence bounds, which confirms the platform’s robustness and practicality for real-world drivetrain systems monitoring. Full article

This study introduces a dynamic, multi-output stacking framework for real-time forecasting of HVAC cooling-coil behavior in air-handling units. The dynamic model encodes short-horizon system memory with input/target lags and rolling psychrometric features and enforces leakage-free, time-aware validation. Four base learners—Random Forest, Bagging (DT), XGBoost, and ANN—are each optimized with an Optuna hyperparameter tuner that systematically explores architecture and regularization to identify data-specific, near-optimal configurations. Their out-of-fold predictions are combined through a Ridge-based stacker, yielding state-of-the-art accuracy for supply-air temperature and chilled water leaving temperature (R² up to 0.9995, NRMSE as low as 0.0105), consistently surpassing individual models. Novelty lies in the explicit dynamics encoding aligned with coil heat and mass-transfer behavior, physics-consistent feature prioritization, and a robust multi-target stacking design tailored for HVAC transients. The findings indicate that this hyperparameter-tuned dynamic framework can serve as a high-fidelity surrogate for cooling-coil performance, supporting set-point optimization, supervisory control, and future extensions to virtual sensing or fault-diagnostics workflows in industrial AHUs. Full article

The iron-oxide-copper-gold (IOCG) skarns of the Tatatila-Las Minas mining district in central Mexico represent a structurally-controlled, exhumed fossil geothermal system located in the eastern sector of the Trans-Mexican Volcanic Belt (TMVB). The district was historically exploited for gold and copper mineralization. The emplacement of the ore bodies was controlled by regional Neogene–Quaternary NE- and NW-striking fault systems formed during the extensional evolution of the TMVB. These faults acted as conduits for high-temperature hydrothermal fluids circulating during the cooling of the Neogene magmatic intrusions. By integrating detailed field study with available exploration borehole data, the spatial distribution of the skarn bodies was reconstructed. Three main emplacement geometries were identified: (a) at contacts between magmatic bodies and host rocks, (b) as lenticular or irregular bodies parallel to the host rock foliation, and (c) at the intersections of near-orthogonal faults. Although structural controls on skarn formation represent a key factor in ore emplacement, their analysis remains scarcely explored. This paper therefore contributes to filling this gap by providing a detailed characterization of the structural framework governing IOCG skarn development at Tatatila–Las Minas. The results improve understanding of IOCG systems formation and provide predictive criteria for mineral exploration in similar geological settings, potentially reducing exploration and mining risks. Full article

This paper presents OpS-EWMA-LLM (Operational State Shifts Detection using Exponential Weighted Moving Average and Labeling using Large Language Model), a hybrid framework that combines fleet-normalized statistical shift detection with LLM-assisted diagnostics to identify and interpret operational state changes across heterogeneous fleets. First, we introduce a residual-based EWMA control chart methodology that uses deviations of each component’s sensor reading from its fleet-wide expected value to detect anomalies. This statistical approach yields near-zero false negatives and flags incipient faults earlier than conventional methods, without requiring component-specific tuning. Second, we implement a pipeline that integrates an LLM with retrieval-augmented generation (RAG) architecture. Through a three-phase prompting strategy, the LLM ingests time-series anomalies, domain knowledge, and contextual information to generate human-interpretable diagnostic insights. Finaly, unlike existing approaches that treat anomaly detection and diagnosis as separate steps, we assign to each detected event a criticality label based on both statistical score of the anomaly and semantic score from the LLM analysis. These labels are stored in the OpS-Vector to extend the knowledge base of cases for future retrieval. We demonstrate the framework on SCADA data from a fleet of wind turbines: OpS-EWMA successfully identifies critical temperature deviations in various components that standard alarms missed, and the LLM (augmented with relevant documents) provides rationalized explanations for each anomaly. The framework demonstrated robust performance and outperformed baseline methods in a realistic zero-tuning deployment across thousands of heterogeneous equipment units operating under diverse conditions, without component-specific calibration. By fusing lightweight statistical process control with generative AI, the proposed solution offers a scalable, interpretable tool for condition monitoring and asset management in Industry 4.0/5.0 settings. Beyond its technical contributions, the outcome of this research is aligned with the UN Sustainable Development Goals SDG 7, SDG 9, SDG 12, SDG 13. Full article

Inter-turn short-circuit (ITSC) faults in motor drives can induce substantial circulating currents and localized thermal stress, ultimately degrading winding insulation and compromising torque stability. To enhance the operational reliability of open-winding (OW) five-phase fault-tolerant fractional-slot concentrated-winding interior permanent-magnet (FTFSCW-IPM) motor drive systems, this paper proposes a real-time fault-tolerant control strategy that provides current suppression and torque stabilization under ITSC conditions. Upon fault detection, the affected phase is actively isolated and connected to an external dissipative resistor, thereby limiting the fault-phase current and inhibiting further propagation of insulation damage. This reconfiguration allows the drive system to uniformly accommodate both open-circuit (OC) and ITSC scenarios without modification of the underlying control architecture. For OC operation, an equal-amplitude modulation scheme based on carrier-based pulse-width modulation (CPWM) is formulated to preserve the required magnetomotive-force distribution. Under ITSC conditions, a feedforward compensation mechanism is introduced to counteract the disturbance generated by the short-circuit loop. A principal contribution of this work is the derivation of a compensation term that can be estimated online using zero-sequence voltage (ZSV) together with measured phase currents, enabling accurate adaptation across varying ITSC severities. Simulation and experimental results demonstrate that the proposed method effectively suppresses fault-phase current, maintains near-sinusoidal current waveforms in the remaining healthy phases, and stabilizes torque production over a wide range of fault and load conditions. Full article

Static eccentricity is an important early-stage fault in marine diesel generators, as small air-gap deviations caused by misalignment or mechanical wear can escalate into bearing damage and rotor–stator contact. To address the challenge of detecting such subtle faults, this study proposes a current signal analysis method based on the two-dimensional short-time Fourier transform (2D STFT) for early detection of static eccentricity faults in marine diesel generators. Using three-phase currents measured during normal operation and fault data synthesized with a physics-based electromechanical coupling model (1–5% eccentricity), we construct a two-dimensional phase–time representation rather than treating each phase as an independent one-dimensional time series and then apply 2D STFT. This formulation enables the simultaneous capture of inter-phase relationships and spatial patterns in the time–frequency–phase domain. Experiments indicate a distinct energy rise near 1020 Hz as static eccentricity increases. This trend enables the proposed method to distinguish small faults of approximately 5% eccentricity, which remain difficult to detect using conventional 1D STFT. As a result, the approach improves the diagnostic accuracy of non-contact, current-based monitoring for static eccentricity faults. Future work will include validation using real in-service fault data and extensions to other fault modes such as dynamic eccentricity and bearing defects. Full article

Photovoltaic (PV) systems represent one of the pillars of the global energy transition, yet their reliability and long-term efficiency are constantly threatened by hidden defects and progressive degradation. Early and precise identification of such anomalies is essential for ensuring safety, enhancing performance, and facilitating predictive maintenance plans. Infrared thermography (IRT) is a non-invasive and cost-effective technique for the inspection of PV modules. This study proposes an efficient attentive U-Net architecture for the semantic segmentation of thermographic images, aimed at supporting predictive maintenance and power loss assessment. The model integrates squeeze-and-excitation (SE) and attention gate (AG) modules with atrous spatial pyramid pooling (ASPP), achieving an optimal balance between accuracy and computational complexity. A comprehensive ablation study, including input resolution and module combinations, was conducted on a dataset of 500 thermograms annotated into six defect classes. The proposed configuration (256 × 256 input) achieved a mean Intersection over Union (mIoU) of 81.4% and a macro-F1 score of 87.5%, outperforming U-Net and DeepLabv3+ by over 4 percentage points, with only 5.24 M parameters and an inference time of 118.6 ms per image. These results confirm the suitability of the framework for energy-oriented fault diagnosis and near real-time monitoring of photovoltaic plants. Full article

To study the mechanical properties and displacement evolution of rock masses near coal-seam normal faults under mining disturbances; this paper utilizes fiber optic monitoring and distributed strain measurement techniques to achieve the fine monitoring of the entire process of stress–displacement–strain during mining. The experimental design adopts a stepwise mining approach to systematically reproduce the evolution of fault formation; slip; and instability. The results show that the formation of normal faults can be divided into five stages: compressive deformation; initiation; propagation; slip; and stabilization. The strength of the fault plane is significantly influenced by the dip angle. As the dip angle increases from 30° to 70°, the peak strength decreases by 23%, and the failure mode transitions from tensile failure to shear failure. Under mining disturbances, the stress field in the overlying rock shifts from concentration to dispersion, with a stress mutation zone appearing in the fault-adjacent area. During unloading, vertical stress decreases by 45%, followed by a rebound of 10% as mining progresses. The rock layers above the goaf show significant subsidence, with the maximum vertical displacement reaching 150 mm. The displacement between the hanging wall and footwall differs, with the maximum horizontal displacement reaching 78 mm. The force chain distribution evolves from being dominated by compressive stress to a compressive–tensile stress coupling state. The fault zone eventually enters a stress polarization state and tends toward instability. A large non-uniform high-speed zone forms at the fault cutting point in the velocity field, revealing the mechanisms of fault instability and the initiation of dynamic disasters. These experimental results provide a quantitative understanding of the multi-physics coupling evolution characteristics of coal-seam normal faults under mining disturbances. The findings offer theoretical insights into the instability of coal-seam normal faults and the mechanisms behind the initiation of dynamic disasters. Full article

Based on comprehensive interpretation of three-dimensional seismic data and quantitative analysis of basin-boundary fault activity in the Nanpu Sag, this study employs subsidence history backstripping and equilibrium profile techniques to reconstruct the structural evolution of the main profile. The results indicate that the Cenozoic evolution of the Nanpu Sag can be divided into a syn-rift stage and a post-rift stage, with the syn-rift stage further subdivided into Rift I and Rift II episodes. During Rift I, tectonic activity was primarily controlled by the NE- and NEE-trending Xinanzhuang Fault, Shabei Fault, and No. 2 Fault Zone, which formed under a NW–SE extensional stress regime and governed the development of NE- or NEE-trending faults and associated sedimentary subsidence centers. In Rift II, tectonic activity was dominated by a southward-curved normal fault system, composed of the Xinanzhuang, Gaoliu, and Baigezhuang faults, as well as the Shabei Fault, reflecting the influence of a near N–S ex-tensional stress field. The progressive southward migration of the Sag’s subsidence center over time—from the Linque sub-sag in the third section of the Shahe Formation to the Caofeidian sub-sag in the Dongying Formation—and noting, coupled with the pronounced left-lateral strike-slip characteristics of the Baigezhuang Fault and No. 4 Fault, and regional tectonic evolution analysis of the Bohai Bay Basin, support the proposal that a strike-slip extension mechanism—characterized by lateral strike-slip and forward extension—constitutes the fundamental developmental model of the Nanpu Sag. This study deepens the understanding of the tectonic evolution of the Nanpu Sag and provides new insights in-to the dynamic mechanisms governing the formation of similar Sags in the Bohai Bay Basin. Full article

This paper systematically reviews bridge structural dynamics and pier damage mechanisms under seismic excitation over recent decades, addressing four key aspects: (1) the structural response of simply supported bridges subjected to horizontal seismic forces and corresponding damage in shear keys and piers; (2) the impact of near-fault vertical ground motion on vertical constraint degradation and its contribution to pier damage; (3) the failure mechanisms of piers under bidirectional coupled seismic excitations; (4) recent advances in innovative design concepts, structural configurations, and material applications for seismic-resistant piers. Eventually, the limitations of current research are identified, and potential future research directions and methodologies are proposed. Full article

This study investigates the hydraulic connection of surface karst features within the Northern segment of the Edwards Balcones Fault Zone Aquifer, using a combination of 2D and pseudo-3D Electrical Resistivity Tomography (ERT) at an outcrop near Salado, Texas. The study site features several surface fractures whose hydrological functions are not well understood. Nine ERT profiles and two pseudo-3D models were used to evaluate the connection between surface fractures and subsurface karst conduits. Karst features at the study site were physically evaluated using characteristics such as morphology, which resulted in the identification of three surface fractures (F1, F2, and F3). The ERT results showed several high-resistivity anomalies interpreted as a poorly fractured zone and low-resistivity water-filled conduits within the Edwards Formation. Furthermore, the result reveals that slow hydraulic connectivity exists in F1 and F2; however, F3 presents a low-resistivity zone that extends vertically into the subsurface, which suggests that F3 may serve as a potential recharge feature to the Edwards Aquifer. These findings are corroborated by a water percolation test, as water penetrated more at F3 compared to F1 and F2. This study showed that the combined application of 2D and pseudo-3D ERT can successfully delineate potential recharge pathways in an exposed karst system, thereby constituting a supportive approach providing critical insight into recharge and the vulnerability of karst aquifers to contamination. Full article

This study aims to explore the development characteristics and evolutionary patterns of strike–slip fault zones in carbonate rocks, through quantitative characterization of fault elements and their interrelationships. Taking three strike–slip fault zones in the Daniudi Block of the northeastern Ordos Basin, China, as examples, we analyzed the distribution of fault damage zone width and throw along the strike of the fault zones at equal intervals, based on data derived from 3D seismic interpretation. The relationship between damage zone width and throw was also explored. The results indicate the following: (1) The throw–distance curve of strike–slip fault zones exhibits bimodal or multimodal patterns. As the peak of the curve is located near the overlap zone of the fault, this signifies that the fault is in the independent stage, whereas a peak situated in the middle of a fault segment suggests that the strike–slip fault has achieved integrity through “hard linkage”. (2) The width of the fault damage zone is controlled by the scale of the fault zone and its associated structures. (3) A strong power–law relationship exists between the damage zone width and throw, with a more pronounced positive correlation observed in the Taigemiao Fault Zone. (4) The strike–slip fault zone is primarily composed of a “ternary” structure, including fault core, damage zone, and fracture zone, and has undergone three evolutionary stages. Analyzing the relationships among fault elements contributes to understanding the interaction and evolutionary history of subsurface strike–slip faults in the study area. Full article

Many small-size ore deposits occur in the Lower Paleozoic strata along the ENE-trending imbricate thrust fault in NW Tarim Basin. Based on field investigations and petrographic examinations, sulfur-related deposits mainly occur within the paleo-karst cavities and are composed of elemental sulfur and anhydrite. Elemental sulfur is extensively present, whereas anhydrite is limited to the Topulang area. The over-dispersed δ³⁴S values (−25.2 to +7.4‰ VCDT) suggest that elemental sulfur and anhydrite typically originate from a multi-phase process involving bacterial sulfate reduction (BSR) superimposed stepwise sulfur disproportionation. The source of sulfate most likely derived from the subsurface Cambrian evaporites. The lower δ¹³C (−6.43 to −3.10‰ VPDB) and δ¹⁸O values (−13.49 to −10.30‰ VPDB) and the higher ⁸⁷Sr/⁸⁶Sr ratios (>0.7105) further suggest that the calcite cements precipitated from near surface aquifer with significant meteoric water influx and were associated with southeastward propagation since the Cenozoic in response to the remote effects of the India–Eurasia collision. This regional tectonic uplift and meteoric water influx created favorable anoxic environments (“sulfur springs”) for subsequent BSR and sulfur disproportionation along the Kepingtage overthrust fault front, resulting in the mineralization of sulfur-bearing species. This study provides a useful example for understanding the repeated processes of BSR and sulfur disproportionation for deep-buried evaporites associated with tectonic-driven mineralization within the Tarim Basin and elsewhere. Full article

The drainage network of the Upper Araguari River, Brazil, developed within an intraplate setting characterized by the Brasiliano structural inheritance, Mesozoic magmatism, and marked lithological contrasts. Although these factors strongly influence fluvial organization, gaps remain in how litho-structural controls modulate fluvial transience and divide stability in intraplate regions. We hypothesize that drainage systems constrained by structural controls and resistant lithologies exhibit higher k_sn values, larger χ offsets, greater knickpoint frequency, and less stable divides than systems developed on friable substrates. To test this hypothesis, we applied integrated morphometric metrics (χ parameter, normalized channel steepness index—k_sn, knickpoints, roughness concentration index—Rci, stream frequency—Sf, drainage density—Dd, and lineaments) across 23 sub-basins to assess how the litho-structural conditions influence the drainage patterns, the fluvial gradients, the equilibrium states, and the divide stability. We identified 57 knickpoints and high k_sn values concentrated in quartzitic and basaltic terrains and along fault zones. χ-plot offsets near quartzite–phyllite/schist contacts indicate transient fronts slowed by differential erodibility, whereas catchments developed on friable substrates respond more rapidly to perturbations. Trellis, rectangular, parallel, and radial drainage patterns exhibit greater instability, underscoring the integrated role of lithological contrasts and tectonic reactivations in modulating intraplate fluvial transience. Full article

Groundwater resources in Jordan are under severe stress due to rapidly increasing water demand and over-abstraction that far exceeds natural replenishment. In addition, water quality is threatened by pollution from the misuse of fertilizers and pesticides, leakage from septic tanks, and illegal waste disposal. This study focuses on the Aqeb, Corridor, and Special Economic Zone wellfields, where hydrological and hydrochemical investigations were carried out. A total of 36 groundwater samples were collected and analyzed for hydrochemical composition, stable isotopes of oxygen (δ¹⁸O) and hydrogen (δ²H), and trace elements. In addition, two exploration 2D seismic profiles crossing the study area were interpreted, providing critical insights into the activity of the subsurface Fuluk Fault zone and its relationship with the wellfields. The hydrochemical results reveal elevated total dissolved solids and nitrate concentrations, accompanied by more depleted δ¹⁸O and δ²H values in wells located in the central part of the study area. Three distinct hydrochemical groups were identified within the same aquifer, indicating heterogeneity in groundwater chemistry that reflects variations in recharge conditions, flow paths, and geochemical processes. The first group (high Na/Cl with low salinity) likely represents recently recharged waters with limited rock–water interaction. The second group (intermediate Na/Cl and moderate salinity) may be influenced by evaporation, irrigation return flow, or cation exchange. The third group (low Na/Cl with high salinity) suggests the dissolution of sulfate minerals or mixing with deeper mineralized groundwater, possibly facilitated by structural features such as the Fuluk Fault. Seismic interpretation indicates several active near-surface fault systems that are likely to serve as preferential pathways for salinity and nitrate enrichment, linked to intensive agricultural activities and wastewater leakage from nearby septic tanks. The findings emphasize the combined influence of geochemical processes, excessive groundwater abstraction, and structural features in controlling water quality in the region. Full article