Fault System Research Articles

Wind energy system fault classification using deep CNN and improved PSO‐tuned extreme gradient boosting

AbstractIntelligent fault diagnosis for wind energy systems requires identifying unique characteristics to differentiate various fault types effectively, even when data discrepancy occurs due to the unpredictable and dynamic nature of its environment. This article addresses some of the challenges of fault classification in wind energy systems by proposing an integrated approach that combines deep learning features with a resampled supervisory control and data acquisition (SCADA) dataset. The methodology involves resampling the imbalanced SCADA dataset using synthetic minority oversampling technique (SMOTE) and near‐miss undersampling techniques, extracting deep learning features using deep convolutional neural network, and feeding them into an XGBoost (extreme gradient boosting) classifier with tuned parameters using adaptive elite‐particle swarm optimization (AEPSO). The effectiveness of the proposed method is demonstrated through validation conducted on a different imbalanced dataset showing superior performance metrics in terms of accuracy. Additionally, the study contributes to methodological advancements in wind turbine fault diagnosis by providing a rigorous framework for fault classification. It is confirmed that utilizing the extracted deep learning features into the resampled data can significantly affect the classification performance metrics. Furthermore, the proposed integrated approach shows significance for fault diagnosis enhancement in wind energy systems and advancing the field towards more efficient and reliable operation.

The orientation of intra-arc crustal fault systems influences the copper budget of magmatic-hydrothermal fluids

Some of the largest magmatic-hydrothermal copper ore deposits and deposit clusters are associated with arc-oblique fault systems. Whether this structural context impacts the geochemistry of hydrothermal fluids, including their copper contents, remains unknown. Here, we investigate the copper concentration and helium isotope signature of geothermal fluids as modern analogs of hydrothermal ore deposits in the Andes of central-southern Chile. We show that fault systems broadly parallel to the regional stress field facilitate the early release of fluids from deep primitive magmas. By contrast, fault systems oblique to the regional stress field prevent the early escape of fluids and promote magmatic enrichment in copper, volatiles, and ligands, enhancing the potential to form copper deposits. We conclude that the orientation of fault systems actively influences the copper budget of ascending hydrothermal fluids, explaining the contrasting distribution of metals along distinct structures often observed in porphyry-epithermal systems and other types of magmatic-hydrothermal deposits.

Geoelectric studies in earthquake hazard assessment: the case of the Kozlodui nuclear power plant, Bulgaria

AbstractThe study presents the results of geoelectric research for seismic risk assessment on the example of the Kozlodui nuclear power plant in Bulgaria. The image of the geoelectric structure in the study area was obtained using one-dimensional inverse electrical resistivity modeling of the full five-component magnetotelluric data and quasi-three-dimensional inverse conductivity modeling of the geomagnetic responses recorded during the summer 2021 field campaign. According to the presented results, the geoelectrically anomalous structure is divided into two levels. The near-surface anomalous structure in the immediate reach of human geotechnical activity corresponds to the electrically conductive sedimentary fill. The mid-crustal layer is coincident with the low seismic velocity zone at the brittle and ductile crust interface, revealed in previous studies. The presented results imply that the geological environment is not affected by large faults capable of transmitting seismic energy from tectonically active areas, however, in further studies, attention should be paid to the strike-slip fault systems adjacent to the study area.

Channel parallel virus machine for power system fault diagnosis

Channel parallel virus machine for power system fault diagnosis

Adaptive critic design for safety-optimal FTC of unknown nonlinear systems with asymmetric constrained-input

Safe fault tolerant control is one of the key technologies to improve the reliability of dynamic complex nonlinear systems with limited inputs, which is hard to solve and definitely a great challenge to tackle. Thus the paper presents a novel safety-optimal FTC (Fault Tolerant Control) approach for a category of completely unknown nonlinear systems incorporating actuator fault and asymmetric constrained-input, which can guarantee the system’s operation within a safe range while showcasing optimal performance. Firstly, a CBF (Control Barrier Function) is incorporated into the cost function to penalize unsafe behaviors, and then we translate the intractable safety-optimal FTC problem into a differential ZSG (Zero-Sum Game) problem by defining the control input and the actuator fault as two opposing sides. Secondly, a neural-network-based identifier is employed to reconstruct system dynamics using system data, and the resolution of handling asymmetric constrained-input with the introduced non-quadratic cost function is achieved through the design of an adaptive critic scheme, aiming to reduce computational expenses accordingly. Finally, through the theoretical stability analysis, it is demonstrated that all signals in the closed-loop system are consistently UUB (Uniformly Ultimately Bounded). Furthermore, the proposed method’s effectiveness is also verified in the simulation experiments conducted on a model of a single-link robotic arm system with actuator failure. The result shows that the algorithm can fulfill the safety-optimal demand of fault tolerant control in fault system with asymmetric constrained-input.

Geological and Structural Framework, Inventory, and Quantitative Assessment of Geodiversity: The Case Study of the Lake Faro and Lake Ganzirri Global Geosites (Italy)

The geoconservation policies assumed by the Sicilian Region (Italy) induced to classify as geosites all the geodiversity preserved in the Sicilian natural reserves. In particular, two of these geosites present in the oriented natural reserve of the coastal lagoon of Cape Peloro (Messina, NE Sicily, Italy), denoted “Morpho–tectonic system of Cape Peloro–Lake Faro” and “Morpho–tectonic system of Cape Peloro–Lake Ganzirri”, were considered Global areal geosites on the base of their tectonic origin. Lacking an official scientific report of these sites, the present research was aimed to investigate the lagoon, in order to provide the (i) geological and structural framework, (ii) inventory, and (iii) quantitative assessment of geodiversity. The study geosites resulted to be originated during the post–Wurmian sea–level rise and the strong extensional tectonics affecting the Calabria–Peloritani Arc still active. Indeed, the lagoon depression hosting the Lakes Faro and Ganzirri, developed on low-relief coasts because of different systems of capable faults, NW–SE oriented in the Lake Faro and ENE–WSW oriented in the Lake Ganzirri. The quantitative assessment of geodiversity indicated high scores for the scientific value and the potential educational and touristic uses. On the basis of these results, it was possible to confirm the attribution of Lake Faro’s and Lake Ganzirri’s geodiversity to Global areal geosites, being the study morpho-structures key localities, providing indicators of representativeness, geological diversity, and rarity that ought to be protected as clear and unequivocal examples of the Earth’s geological history and evolution of the Quaternary tectonic coastal lagoons. Actual criticisms that could irreversibly affect the environmental equilibria have been evidenced. Possible actions for the redevelopment of the oriented natural reserve of the coastal lagoon of Cape Peloro and the extension of the geosites were also described.

Energy dissipation methods and protection device synergy strategies for offshore wind power receiving end surplus power

Abstract Firstly, a theoretical analysis of the fault ride-through scheme is carried out based on the land-side AC faults in the offshore wind power delivery system. According to the topological structure of the DC energy consumption device, the working mode and switching of the DC energy consumption device are analyzed and studied. Secondly, the DC protection action of offshore wind power flexible and direct transmission systems was studied, and the switching strategy of energy-consuming devices was determined. Then the impact of the switching of the energy-consuming device on the DC protection function was studied, focusing on the synergy between the DC overvoltage protection and the switching judgment voltage of the energy-consuming device. Finally, based on a typical offshore wind power flexing project, a system model is built in PSCAD/EMTDC to verify the effectiveness of the proposed synergy strategy.

Security Versus Accuracy: Trade-Off Data Modeling to Safe Fault Classification Systems.

While the data-driven fault classification systems have achieved great success and been widely deployed, machine-learning-based models have recently been shown to be unsafe and vulnerable to tiny perturbations, i.e., adversarial attack. For the safety-critical industrial scenarios, the adversarial security (i.e., adversarial robustness) of the fault system should be taken into serious consideration. However, security and accuracy are intrinsically conflicting, which is a trade-off issue. In this article, we first study this new trade-off issue in the design of fault classification models and solve it from a brand new view, hyperparameter optimization (HPO). Meanwhile, to reduce the computational expense of HPO, we propose a new multiobjective (MO), multifidelity (MF) Bayesian optimization (BO) algorithm, MMTPE. The proposed algorithm is evaluated on safety-critical industrial datasets with the mainstream machine learning (ML) models. The results show that the following hold: 1) MMTPE is superior to other advanced optimization algorithms in both efficiency and performance and 2) fault classification models with optimized hyperparameters are competitive with advanced adversarially defensive methods. Moreover, insights into the model security are given, including the model intrinsic security properties and the correlations between hyperparameters and security.

Prescribed Performance Fault-Tolerant Control for Synchronization of Heterogeneous Nonlinear MASs Using Reinforcement Learning.

In this article, a novel approach of prescribed performance synchronization control is developed for heterogeneous nonlinear multiagent systems (MASs) subject to unknown actuator faults. Considering that not all followers are able to access the information of the leader, a distributed auxiliary perception system is proposed to estimate the state information of the leader to guarantee that the estimation errors converge to zero within fixed time. Then, based on the estimated states, a prescribed performance fault-tolerant control (FTC) approach is proposed, which achieves the user-defined performance specifications even in the presence of system faults. Moreover, as accurate system dynamic models are perhaps hard to acquire in practical engineering, a data-based method is proposed by using the reinforcement learning (RL) algorithm to design the fault-tolerant controller, which only needs the off-policy online data and is independent of the model dynamics of followers. The stability and synchronization with the prescribed behavior are guaranteed through the Lyapunov stability theorem. Finally, simulation results are presented to illustrate the effectiveness of the developed controller.

Vertical Deformation Along a Strike‐Slip Plate Boundary: The Uplifted Marine Terraces of the Gulf of Aqaba and Tiran Island, at the Southern End of the Dead Sea Fault

AbstractClose to its southern end where it connects to the Red Sea rift, the Dead Sea strike‐slip fault (DSF) becomes trans‐tensional in the Gulf of Aqaba. Details of this transition, however, remain difficult to unravel as most of the active tectonic structures are located off‐shore. This study focuses on uplifted marine terraces located in the Gulf of Aqaba and on Tiran Island. Using high‐resolution tri‐stereo Pleiades satellite imagery, we build a Digital Surface Model (DSM) at a 0.5‐m resolution of the eastern coast of the gulf and Tiran Island to map 19 levels of marine terraces. The terraces are preserved at elevations from 1 m to almost 500 m above the current sea level. Correlating laterally U‐Th ages obtained along the gulf with the lower levels found on Tiran Island, we build an age model to estimate the ages of the upper terraces on the island. Combining this with the terrace heights from our DSM, we derive the uplift rate affecting the terraces. The geographic extent of the terraces along the gulf suggests that the DSF is responsible for uplift along the entire eastern coastline of the gulf at a rate of about 0.14 ± 0.03 mm/year at least over the Quaternary. The uplift rate of Tiran Island, located closer to the Red Sea rift, is faster at 0.21 ± 0.02 mm/year over the past 2.4 Myr. This faster uplift rate suggests a combined tectonic uplift related to both the Dead Sea strike‐slip fault system and the Red Sea rift.

Detachment and Transfer Fault Systems in the Northern South China Sea, Insights Into 3D Tectonic Segmentation of Rifted Margins

Detachment and Transfer Fault Systems in the Northern South China Sea, Insights Into 3D Tectonic Segmentation of Rifted Margins

South Tibetan Detachment System (STDS), NW Himalaya: A possible Cambro–Ordovician tectonic terrane boundary, and its Cenozoic remobilization

The South Tibetan Detachment System is an important extensional fault zone, separating the Greater Himalayan Sequence from the overlying Tethyan Himalayan Sequence, and is well exposed in the upper reaches of the Dhauliganga valley, NW Himalaya. This fault system is characterized by the occurrence of an extensive Cambro–Ordovician granite belt between Sutlej and Dhauliganga valleys, although only a few small granitoids intrude the high-grade mylonite gneiss of the Greater Himalayan Sequence in its immediate footwall. These bodies yielded U-Pb zircon crystallization ages between 498.92 ± 5.5 Ma and 486.54 ± 2.3 Ma. This work postulates that the South Tibetan Detachment System evolved as a major proto-tectonic marginal extensional terrane boundary during the Cambro–Ordovician Kurgiakh/Bhimphedian Orogeny, when it was the conduit for emplacement of the Cambro–Ordovician granite belt. Denudation of the Neoproterozoic Greater Himalayan Sequence and the Paleozoic granites on its footwall provided approximately ∼ 10 km thick sediments into the Tethyan Basin due to this fault system as a master growth fault. Reactivation of this fault system controlled further melting and emplacement of the Higher Himalayan Leucogranite belt during the Cenozoic. Zircon growth is observed in two distinct modes: pulsative from the Late Eocene to Early Oligocene, with peaks at 33.99 ± 1.07 Ma, 30.53 ± 0.32 Ma and 25.03 ± 0.54 Ma; and in the continuous mode from 23.68 ± 0.94 Ma to 13.30 ± 0.30 Ma, in the Miocene, for nearly 10.0 myr. These datasets reveal some of the oldest pulsative movements in the Late Eocene–Early Oligocene during crustal thickening, thrusting and associated metamorphism, followed by continuous extension during the Miocene. Data from the South Tibetan Detachment System are distinct in character, and do not support either its eastwards younging or diachronous movements along the Dhauliganga valley.

Steady-State Fault Propagation Characteristics and Fault Isolation in Cascade Electro-Hydraulic Control System

Model-based fault diagnosis serves as a powerful technique for addressing fault detection and isolation issues in control systems. However, diagnosing faults in closed-loop control systems is more challenging due to their inherent robustness. This paper aims to detect and isolate actuator and sensor faults in the cascade electro-hydraulic control system of a turbofan engine. Based on the fault characteristics, we design a robust unknown perturbation decoupling residual generator and an optimal fault observer specifically for the inner and outer control loops to detect potential faults. To locate the faults, we analyze the steady-state propagation laws of actuator and sensor faults within the loops using the final value theorem. Based on this, we establish the minimal-dimensional fault influence distribution matrix specific to the cascade turbofan engine control system. Subsequently, we construct the normalized residual vectors and monitor its vector angles against each row of the fault influence distribution matrix to isolate faults. Experiments conducted on an electro-hydraulic test bench demonstrate that our proposed method can accurately locate four typical faults of actuators and sensors within the cascade electro-hydraulic control system. This study enriches the existing fault isolation methods for complex dynamic systems and lays the foundation for guiding component repair and maintenance.

Complex fault system associated with the Molucca Sea Divergent double subduction zone revealed by the 2019 Mw 6.9 and Mw 7.1 Earthquakes

GNSS (Global Navigation Satellite System) data in northern Sulawesi and western Halmahera reveals a pattern of coseismic displacement that was caused by the 7 July 2019 (Mw 6.9) and 14 November 2019 (Mw 7.1) Molucca Sea earthquakes. The coseismic slip of these earthquakes are obtained via inversion on rectangular fault planes of surface GNSS coseismic deformation offsets. The 7 July 2019 earthquake ruptured on an east-dipping fault with a maximum slip of ∼35 cm located at ∼4 km depth and ∼ 100 km north-west of the epicenter. The 14 November 2019 earthquake also ruptured on an east-dipping fault, which has a maximum slip of ∼64 cm located at ∼22 km depth and ∼ 20 km south-west of the epicenter. The coseismic slip distribution of the 14 November earthquake is spatially aligned to that of an earthquake of similar magnitude that took place on 15 November 2014 in the same region. This observation points to the possibility of synchronization, thus raising the prospect of a future earthquake exceeding magnitude 7. If the stress was completely released during the 2014 event, it would have been necessary to reload that portion of the fault at a rate significantly larger than the observed convergence rate of ∼5.8 cm/yr. This suggests that partial ruptures are likely controlling the recurrence time of large earthquakes in the region.

Research on fault diagnosis of multi-mode electromechanical compound transmission system for hybrid electric vehicle based on global analytical redundancy relations

In order to effectively monitor the operational status and detect faults within a hybrid electric vehicle during mode transitions, this study focuses on a specific power-split hybrid electric vehicle model known as the multimode electromechanical composite transmission system (MM-EMCTS HEV). Taking into account the actual occurrence frequency and simulatability of faults in MM-EMCTS HEV, key faults are extracted. Based on the distinctive characteristics and properties of critical system faults, a fault diagnosis framework is constructed by leveraging global analytical redundancy relations (GARRs). This framework encompasses strategies for residual generation across sensors, actuators, and controlled components, alongside residual evaluation techniques employing mode-dependent adaptive thresholds. The detectability and isolatability of the MM-EMCTS are thoroughly analyzed. Subsequently, simulation and verification of the residual responses under typical faults in the MM-EMCTS are implemented in Matlab/Simulink and Simscape. The results demonstrate the efficacy of the fault diagnosis method, rooted in global analytical redundancy relations and mode-dependent adaptive thresholds, in successfully detecting and isolating faults within multimode electromechanical composite transmission systems. Furthermore, compared to conventional fixed threshold residual evaluation approaches, this method significantly mitigates the occurrence of missed detections, thus verifying the effectiveness and superiority of the proposed method.

A fault diagnosis method for hydraulic system based on multi-branch neural networks

As a key part of construction machinery, the hydraulic system is widely used in industrial fields. Due to its complexity and high integration, the fault diagnosis of hydraulic systems has always been a challenging problem. However, existing methods or models mainly focus on individual hydraulic system components while overlooking the interactions between different components, which are limited to specific application scenarios. Therefore, this research aims to develop a multi-task network model to diagnose faults in multiple components of hydraulic systems. Firstly, the initial data was collected from the hydraulic system test bench, in which the extreme gradient boosting (XGBoost) was introduced to evaluate the importance of all features under different fault types. Then, reduction dimensionality is achieved by setting a threshold for feature selection. Subsequently, a novel multi-branch deep neural network (MBDNN), which utilizes multiple branches to extract different information and correlations in the input data, is proposed and established. The multi-level combination of residual block and multi-branch connections enables MBDNN to achieve multiple types of fault diagnosis simultaneously and compensate for the problem of insufficient information representation in single-branch neural networks. The results of multiple rounds of experimental indicate that the MBDNN has higher robustness and accuracy in hydraulic system fault diagnosis than the existing general methods, and the diagnostic accuracy of multi-type faults is improved to 98.5%.

Novel glassbox based explainable boosting machine for fault detection in electrical power transmission system.

The reliable operation of electrical power transmission systems is crucial for ensuring consumer's stable and uninterrupted electricity supply. Faults in electrical power transmission systems can lead to significant disruptions, economic losses, and potential safety hazards. A protective approach is essential for transmission lines to guard against faults caused by natural disturbances, short circuits, and open circuit issues. This study employs an advanced artificial neural network methodology for fault detection and classification, specifically distinguishing between single-phase fault and fault between all three phases and three-phase symmetrical fault. For fault data creation and analysis, we utilized a collection of line currents and voltages for different fault conditions, modelled in the MATLAB environment. Different fault scenarios with varied parameters are simulated to assess the applied method's detection ability. We analyzed the signal data time series analysis based on phase line current and phase line voltage. We employed SMOTE-based data oversampling to balance the dataset. Subsequently, we developed four advanced machine-learning models and one deep-learning model using signal data from line currents and voltage faults. We have proposed an optimized novel glassbox Explainable Boosting (EB) approach for fault detection. The proposed EB method incorporates the strengths of boosting and interpretable tree models. Simulation results affirm the high-efficiency scores of 99% in detecting and categorizing faults on transmission lines compared to traditional fault detection state-of-the-art methods. We conducted hyperparameter optimization and k-fold validations to enhance fault detection performance and validate our approach. We evaluated the computational complexity of fault detection models and augmented it with eXplainable Artificial Intelligence (XAI) analysis to illuminate the decision-making process of the proposed model for fault detection. Our proposed research presents a scalable and adaptable method for advancing smart grid technology, paving the way for more secure and efficient electrical power transmission systems.

Evolution of fluid redox in a fault zone of the Pic de Port Vieux thrust in the Pyrenees Axial Zone (Spain)

Abstract. In mountain ranges, crustal-scale faults localize multiple episodes of deformation. It is therefore common to observe current or past geothermal systems along these structures. Understanding the fluid circulation channelized in fault zones is essential to characterize the thermochemical evolution of associated hydrothermal systems. We present a study of a palaeo-system of the Pic de Port Vieux thrust fault. This fault is a second-order thrust associated with the Gavarnie thrust in the Axial Zone of the Pyrenees. The study focused on phyllosilicates which permit the constraint of the evolution of temperature and redox of fluids at the scale of the fault system. Combined X-ray absorption near-edge structure (XANES) spectroscopy and electron probe microanalysis (EPMA) on synkinematic chlorite, closely linked to microstructural observations, were performed in both the core and damage zones of the fault zone. Regardless of the microstructural position, chlorite from the damage zone contains iron and magnesium (Fetotal / (Fetotal + Mg) about 0.4), with Fe3+ accounting for about 30 % of the total iron. Chlorite in the core zone is enriched in total iron, but individual Fe3+/Fetotal ratios range from 15 % to 40 %, depending on the microstructural position of the grain. Homogeneous temperature conditions about 280–290 °C have been obtained by chlorite thermometry. A scenario is proposed for the evolution of fluid–rock interaction conditions at the scale of the fault zone. It involves the circulation of a single hydrothermal fluid with homogeneous temperature but several redox properties. A highly reducing fluid evolves due to redox reactions involving progressive dissolution of hematite, accompanied by crystallization of Fe2+-rich and Fe3+-rich chlorite in the core zone. This study shows the importance of determining the redox state of iron in chlorite to calculate their temperature of formations and to consider the fluid evolution at the scale of a fault.

Online tree-based planning for active spacecraft fault estimation and collision avoidance.

Autonomous robots operating in uncertain or hazardous environments subject to state safety constraints must be able to identify and isolate faulty components in a time-optimal manner. When the underlying fault is ambiguous and intertwined with the robot's state estimation, motion plans that discriminate between simultaneous actuator and sensor faults are necessary. However, the coupled fault mode and physical state uncertainty creates a constrained optimization problem that is challenging to solve with existing methods. We combined belief-space tree search, marginalized filtering, and concentration inequalities in our method, safe fault estimation via active sensing tree search (s-FEAST), a planner that actively diagnoses system faults by selecting actions that give the most informative observations while simultaneously enforcing probabilistic state constraints. We justify this approach with theoretical analysis showing s-FEAST's convergence to optimal policies. Using our robotic spacecraft simulator, we experimentally validated s-FEAST by safely and successfully performing fault estimation while on a collision course with a model comet. These results were further validated through extensive numerical simulations demonstrating s-FEAST's performance.

Fractal dimension and its implication to mineral exploration: a case study from the Jonnagiri and Gadag gold deposits in India

Fractal dimensions characterize the spatial distribution pattern of mineral deposits, allowing the mineralization processes beneath and at the surface to be understood. This study considered a mineralized vein along the fracture/shear zone near the Dona Temple in the Jonnagiri gold deposit and borehole data from the Sangli Block in the Gadag gold deposit. The above-mentioned zones were considered using fractal dimensional analysis to constrain the fluid-flow pathways. The box-counting technique was used to measure the fractal dimension of the mineralized vein along the surface from a detailed to a regional scale. The fractal correlation integral method was used to provide the fractal dimension values from the gold assay (in g t −1 ). The box-counting fractal dimension values obtained varied from 1.07 to 1.36, whilst the fractal dimensions obtained from the fractal correlation integral method ranged from 0.03 to 1.97. Higher fractal values signify a fully matured interlinked fracture/fault network with steep fluid-flow pathways, while lower values indicate the converse condition. Further, the study showed that the fractal analysis of the mineralized vein along the fracture/shear zone appeared to correlate with the fault system rather than with the litho-contact. Economic gold deposition occurs mainly along a structure with a steep fractal gradient, which is the target area for economic gold exploration.