Fault Conditions Research Articles

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.

Fault Localization in Multi-Terminal DC Distribution Networks Based on PSO Algorithm

Flexible DC power grids are widely recognized as an important component of building smart grids. Compared with traditional AC power grids, flexible DC power grids have strong technical advantages in islanding power supplies, distributed power supplies, regional power supplies, and AC system interconnection. In multi-terminal flexible DC power grids containing renewable energy sources such as solar and wind power, due to the instability and intermittency of renewable energy, it is usually necessary to add energy storage units to pre-regulate the power of the multi-terminal flexible DC power grid in islanded operation. Aiming at the important problem of large current impact and serious consequences when the flexible DC distribution network fails, a combined location method combining an improved impedance method (series current-limiting reactors at both ends of the line to obtain a more accurate current differential value) and a particle swarm optimization algorithm is proposed. Initially, by establishing the enhanced impedance model, the differential variables under the conditions of inter-electrode short-circuit and single-pole grounding fault can be obtained. Then tailor-made fitness functions are designed for these two models to optimize parameter identification. Subsequently, the iterative parameters of the particle swarm optimization algorithm are fine-tuned, giving it dynamic sociality and self-learning ability in the iterative process, which significantly improves the convergence speed and successfully avoids local optimization. Finally, various fault types in a six-terminal DC distribution network are simulated and analyzed by MATLAB, and the results show that this method has good accuracy and robustness. This research provides strong theoretical and methodological support for improving the safety and reliability of DC distribution systems.

Study on the Effect of Starved Lubrication on the Dynamic Characteristics of Locally Failed Roller Bearings

When the lubricant is not enough to maintain the ideal lubrication state of the bearing, the deep groove ball bearing will enter the starved lubrication state, which leads to the change of the vibration response of the deep groove ball bearing with localized defects. Previous bearing dynamics models mainly consider the lubrication state as an ideal lubrication condition, which may not reveal the effect of starved lubrication on the vibration characteristics of defective bearings. In this paper, the internal interaction of the system under starved condition is taken into account, and a dynamic model of defective deep groove ball bearings with insufficient lubricant is established to investigate the effects of different starved lubrication degrees on the contact force, friction force, cage speed, and system vibration characteristics. The results show that the lubricant insufficiency significantly changes the contact force inside the bearing, and the increase in friction caused by the increase in the degree of starved lubrication leads to the suppression of the degree of bearing slipping. The root mean square (RMS) value of the time-domain signal and the outer ring fault frequency both increase with the increase of the starved degree. The results of the study are helpful for fault diagnosis and condition monitoring of related equipment.

Transient Synchronization Stability Analysis and Enhancement Control for Power Self-Synchronization Control Converters

Conventional grid-forming control often destabilizes voltage source converters (VSCs) in stiff grids, and transient synchronization instability will occur in the grid fault condition. Therefore, power self-synchronization control (PSSC) is first introduced for enhancing the small-signal stability of grid-forming control in the case of a short circuit ratio ranging from 1 to infinity. Meanwhile, the transient synchronization instability for the grid-forming converter with PSSC in the grid fault condition is analyzed by the phase portrait, and a transient stability enhancement control (TSEC) scheme is combined with a PSSC-based VSC, which can efficiently eliminate the risk of losing synchronization in the arbitrary SCR. Finally, experimental results are provided to confirm the theoretical analysis.

Concurrent fault diagnosis of small pressurized water reactors based on long-short term memory networks

The control systems of small pressurized water reactors (SPWR) with complex structures, compact layouts, and variable operating environment may be involved in various types of signal and concurrent faults. Concurrent faults can be taken as two or more single faults occurring simultaneously, which usually cause much larger damage to the system and are more difficult to be diagnosed than single faults. However, their fault diagnosis methods are rarely studied because of the numerous fault types and tremendous diagnostic difficulty. This paper explores the concurrent fault diagnosis method for sensors and actuators in SPWR control systems. An intelligent current fault diagnosis model is developed using long short-term memory network with the training and test datasets generated based on a fault simulation platform of the target SPWR. The test results show that both single and concurrent faults of the SPWR can be diagnosed rapidly in an average of 1.06 s after their occurrence with the classification and diagnosis accuracies reaching up to 96.61% and 97.27%, respectively. Moreover, by injecting different noise signals on the faulty dataset for training and validation, it is shown that the proposed LSTM network has strong noise immunity. This demonstrate the excellent diagnosis accuracy and efficiency of the model under both single and concurrent fault conditions. This study provides valuable guidance for the accuracy diagnosis of complex concurrent faults of nuclear power plants.

CNN-ELMNet: fault diagnosis of induction motor bearing based on cross-modal vector fusion

Abstract As the primary driving equipment in industrial, accurate fault diagnosis and condition monitoring of induction motor is crucial for ensuring operational safety. This paper focuses on the bearing faults of induction motors, which have a substantial impact on both the mechanical and electromagnetic systems of the motors. However, in diagnostic tasks, we are faced with the challenges of multi-source, multi-modal data, significant influence from environmental noise, and minimal differentiation between fault data. This paper proposed a novel cross-modal vector fusion fault diagnosis and classification model (CNN-ELMNet), which includes a cross-modal vector fusion network (VF) based on D-S evidence theory, feature extraction layer (FE) and classification layer (CL). Specifically, the VF prioritizes the integration of diagnostic results from individual vibration signals or stator current signals within convolutional neural networks with the features of the input implicit vectors as decision-making evidence, followed by weighted vector fusion through D-S evidence theory at the decision level. The FE focuses on retaining the convolutional, pooling, and fully connected layers of the convolutional network and freezing the final fully connected layer, thus preserving training parameters and fully utilizing the network’s powerful FE capabilities. The CL includes an Extreme Learning Machine optimized for random hyperparameters using the snow ablation optimizer (SAO) algorithm, which offers rapid convergence and high classification recognition rates. The CNN-ELMNet model combines a convolutional network with an extreme learning machine optimized by the SAO algorithm, which not only preserves the model’s FE capability but also enhances the convergence speed and classification recognition rate of the model. Experimental results on real datasets demonstrate that the proposed model exhibits strong stability, generalization, and high accuracy in fault diagnosis, achieving accuracy rate of 99.29% and 98.75%. This provides a more feasible solution for the bearing fault diagnosis of induction motors and holds promising prospects for practical applications.

Fault diagnosis technology overview for lithium‐ion battery energy storage station

AbstractWith an increasing number of lithium‐ion battery (LIB) energy storage station being built globally, safety accidents occur frequently. Diagnosing faults accurately and quickly can effectively avoid safe accidents. However, few studies have provided a detailed summary of lithium‐ion battery energy storage station fault diagnosis methods. In this paper, an overview of topologies, protection equipment, data acquisition and data transmission systems is firstly presented, which is related to the safety of the LIB energy storage power station. Then, existing fault diagnosis technologies are reviewed in detail. Finally, the future developing trends of fault diagnosis technology are discussed.

Dynamic event-triggered prescribed performance disturbance rejection fault-tolerant trajectory tracking for surface vehicles

In this article, a dynamic event-triggered prescribed performance disturbance rejection fault-tolerant scheme is designed for the trajectory tracking of surface vehicles. The external time-varying disturbances and loss-of-effectiveness thruster faults are addressed separately. By constructing the separate observers, the external time-varying disturbances and the loss-of-effectiveness thruster faults are on-line estimated, respectively. The prescribed performance and error transformation functions enable the transient and steady-state performance to settle within pre-specified function values. The dynamic event-triggering is introduced so that commanded control signals are temporarily kept under predefined conditions to reduce wear and tear on the thrusters especially in harsh environmental condition. With the aid of the vectorial backstepping technique, the final control law is derived such that the position and heading of vehicles can be forced to track the reference trajectories in disturbance and fault conditions. Application example on a 1:70 scaled model vessel in the different cases clarify the scheme.

Detection of failures in HV surge arrester using chaos pattern with deep learning neural network

AbstractAs a protective component of HV equipment, the primary function of a surge arrester is to mitigate the impact of surge voltages. When a surge arrester fails, the equipment it protects becomes vulnerable to damage. This study integrates chaotic systems with Convolutional Neural Networks (CNN) to diagnose faults in HV surge arresters. The Partial Discharge (PD) test was initially performed on six HV surge arrester fault models. The Discrete Wavelet Transform (DWT) was performed for filtering the PD signals. Subsequently, the Chen‐Lee chaotic system converted the filtered PD signals into a dynamic error scatter diagram, creating a feature map of various fault states. This feature map was then used as the input layer to train the CNN model. The results demonstrate that the proposed CNN achieved an accuracy of 97.0%, outperforming AlexNet and traditional methods using Histograms of Oriented Gradients (HOG) combined with Support Vector Machine (SVM), Decision Tree (DT), Backpropagation Neural Network (BPNN), and K‐Nearest Neighbor (KNN). This study also incorporates the LabVIEW graphic control software with a fault diagnosis system for HV surge arresters. The PD data can identify the fault type in real‐time, enhancing power equipment maintenance efficiency.

Real-time risk prediction of chemical processes based on attention-based Bi-LSTM

Refined risk prediction must be achieved to guarantee the safe and steady operation of chemical production processes. However, there is high nonlinearity and association coupling among massive, complicated multisource process data, resulting in a low accuracy of existing prediction technology. For that reason, a real-time risk prediction method for chemical processes based on the attention-based bidirectional long short-term memory (Attention-based Bi-LSTM) is proposed in this study. First, multisource process data, such as temperature, pressure, flow rate, and liquid level, are preprocessed for denoising. Data correlation is analyzed in time windows by setting time windows and moving step lengths to explore correlations, thus establishing a complex network model oriented to the chemical production process. Second, network structure entropy is introduced to reduce the dimensions of the multisource process data. Moreover, a 1D relative risk sequence is acquired by max–min deviation standardization to judge whether the chemical process is in a steady state. Finally, an Attention-based Bi-LSTM algorithm is established by integrating the attention mechanism and the Bi-LSTM network to fit and train 1D relative risk sequences. In that way, the proposed algorithm achieves real-time prediction and intelligent perception of risk states during chemical production. A case study based on the Tennessee Eastman process (TEP) is conducted. The validity and reasonability of the proposed method are verified by analyzing distribution laws of relative risks under normal and fault conditions. Also, the proposed algorithm importantly improves the prediction accuracy of chemical process risks relative to that of existing prediction technologies.

Fault rock properties and conditions produce variance in slip during earthquake rupture propagation at the Nankai Trough

Although drilled samples of fault rocks have yielded information on frictional features of shallow subduction zones, the relationship of rupture propagation to the levels of friction and pore-fluid pressure remains uncertain. To investigate this topic, we performed dynamic rupture simulations along the megasplay fault that slipped during the 1944 Mw 8.0 Tonankai earthquake in the Nankai Trough. We used actual data from friction experiments on rocks from the fault segment and pre-existing pore pressures deduced from geophysical surveys for the shallow portion of 0–10 km depth along the fault. Simulations of low friction (friction coefficient ca. 0.04) produced large slip (about 30 m), whereas simulations using higher friction (friction coefficient ca. 0.2) suppressed the rupture. In simulations with low friction in which the pore-fluid pressure was nearly equal to the lithostatic stress, the slip decreased to about 25 m. However, when the simulations included slip-strengthening at shallow depth and higher friction, the slip still reached roughly 20 m. Such variability in slip during rupture propagation is caused by differences in the friction features and fluid pressure conditions of fault rocks, in which the friction features might be related to the mineral composition. Spatiotemporal heterogeneity in fault-rock type and their physical and hydraulic properties may fundamentally produce the complexity and variability of earthquake rupture propagation along the Nankai plate-subduction boundary.

Trajectory tracking control for unmanned amphibious surface vehicles with actuator faults

In this paper, a fixed-time fault-tolerant control strategy is proposed for the trajectory tracking of aquatic–aerial unmanned amphibious vehicles (AquaUAVs) under multiple actuator faults. A switched error system is introduced to describe the AquaUAV trajectory tracking motion under actuator faults in different modes. A switched fixed-time extended state observer (FESO) is developed to observe the tracking errors of the vehicle and the actuator faults, and a fault-tolerant control strategy. The proposed composite controller not only ensures the stability of the system, but also compensates the faults of the actuator. Simulation and experiment results verify that the proposed control strategy can realize the trajectory tracking control of amphibious vehicle under the condition of multiple actuator faults.

Stator fault diagnosis of BLDC motor at varying speed operation using least square support vector machine

Stator fault diagnosis of BLDC motor at varying speed operation using least square support vector machine

Fault Detection of Rotating Machines Using poly-Coherent Composite Spectrum of Measured Vibration Responses with Machine Learning

This study presents an efficient vibration-based fault detection method for rotating machines utilising the poly-coherent composite spectrum (pCCS) and machine learning techniques. pCCS combines vibration measurements from multiple bearing locations into a single spectrum, retaining amplitude and phase information while reducing background noise. The use of pCCS significantly reduces the number of extracted parameters in the frequency domain compared to using individual spectra at each measurement location. This reduction in parameters is crucial, especially for large industrial rotating machines, as processing and analysing extensive datasets demand significant computational resources, increasing the time and cost of fault detection. An artificial neural network (ANN)-based machine learning model is then employed for fault detection using these reduced extracted parameters. The methodology is developed and validated on an experimental rotating machine at three different speeds: below the first critical speed, between the first and second critical speeds, and above the second critical speed. This range of speeds represents the diverse dynamic conditions commonly encountered in industrial settings. This study examines both healthy machine conditions and various simulated fault conditions, including misalignment, rotor-to-stator rub, shaft cracks, and bearing faults. By combining the pCCS technique with machine learning, this study enhances the reliability, efficiency, and practical applicability of fault detection in rotating machines under varying dynamic conditions and different machine conditions.

A new approach to instantaneous power based control of DFIG using active disturbance rejection control

This paper presents the design and control of a wind energy converter system that uses a doubly fed induction generator. It introduces a model that incorporates instantaneous active and reactive power as state variables to represent both the stator and rotor sides of the doubly fed induction generator. Subsequently, a linear active disturbance rejection-based control regulator is proposed for the control loops. The parameters of the linear active disturbance rejection controllers (ADRC) are adjusted by two methods: the single parameter tuning approach and the genetic algorithm (GA) method. The performance of the suggested controller is ultimately compared with a tuned proportional-integral (PI) control regulator in the MATLAB environment. In order to examine the performance of the system, various test scenarios are taken into account. These scenarios include different percentages of load change in both sub-synchronous and super-synchronous modes of operation, faults with different fault periods are considered in both modes of operation. The conventional PI controller-based approach requires 35 control cycles to reach steady state under load change conditions and 50 control cycles under symmetrical fault conditions, regardless of whether the system is operating in sub synchronous or super synchronous mode. The single parameter-based tuned ADRC approach only requires 15 control cycles for load change and 20 control cycles for symmetrical fault scenarios. In contrast, for both the load change and symmetrical fault scenarios, the ADRC with GA-based parameter tuning reaches steady state in just 5 control cycles. Furthermore, a case involving wind speed variation is presented to demonstrate the maximum power point tracking capability of the proposed control structure. Similarly, for the robustness test of the control regulator, variations in resistance and inductance are introduced to observe their impact on the response of the control regulators. Finally, a real-time hardware in loop setup is presented to validate the control strategy during the load change in the sub-synchronous mode of operation of the doubly fed induction generator.

Faulty feeder selection method for high impedance grounding fault in resonant grounding system based on discrete Fréchet distance

Abstract When a high impedance fault (HIF) occurs in a resonant grounding system, the electrical signal is weak and the current distinction between the faulty feeder and non-faulty feeder is inconspicuous. To address this issue, this paper proposes a faulty feeder selection method based on discrete Fréchet distance (DFD). Firstly, the instantaneous value of the zero-sequence current flowing through each sampling point, along with the instantaneous values at its previous sampling moment, is accumulated to enhance the fault signal, and furthermore to magnify the distinction in the amplitude of the accumulated waveforms of zero-sequence current between the faulty feeder and non-faulty feeder. Then, the DFD of the accumulated waveforms of the zero-sequence current for each feeder is calculated, and the Fréchet distance matrix is established to acquire the average DFD (ADFD) value of the accumulated waveform for each feeder. Finally, the relative DFD (RDFD) value is defined as a criterion to distinguish the bus fault from the feeder fault according to the values of the two feeders with the maximum ADFD value and the minimum ADFD value. If the RDFD value is negative, it is identified as a bus fault, otherwise, the feeder corresponding to the maximum ADFD value is identified as a faulty feeder. MATLAB/Simulink simulation results and field measurement data show that the proposed method is not affected by various fault conditions, and the accuracy and reliability in faulty feeder selection are high when detecting an HIF, with good applicability.

Wear characteristics evolution of helical gear with initial defects of bearing inner ring

This study investigated the wear characteristics and operational condition of gears with initial defects of the bearing inner ring. The working states of gears were evaluated through a combination of vibration signal analysis, wear debris concentration analysis, qualitative analysis of the wear debris, and tooth surface analysis. Based on the Hertz contact theory, a dynamic model for the gear drive system was constructed, enabling the simulation and comparison of vibration acceleration signals under normal and fault conditions. The research results revealed that bearing defects induced irregularities in vibration frequency and amplitude, adversely affecting the performance and stability of the gear system. Furthermore, these defects trigger the creation of substantial wear debris, which exacerbates gear wear and reduces the gear lifespan by about 15%. Additionally, bearing defects induced intermittent load spikes and uneven stress distribution across tooth contacts, resulting in localized high shear stresses, material flaking, and surface spalling. Consequently, initial defects of the bearing will accelerate gear wear progression and lead to abnormal wear patterns, potentially resulting in the premature failure of the gear train system. The study investigates the underlying mechanisms of gear wear evolution influenced by these defects and offers practical guidelines for the engineering, manufacturing, and maintenance of gear systems.

A novel fault detection and identification method for complex chemical processes based on OSCAE and CNN

The safety and reliability of chemical processes are of paramount importance. However, due to the complicated heat, mass, and momentum transfer processes coupled with chemical reactions, and the interrelated effects among various equipment units, it is difficult to accurately detect and identify faults occurring in the chemical system. This study proposes an innovative fault diagnosis framework specifically designed for chemical systems. A method based on orthogonal self-attention convolutional autoencoder (OSCAE) is constructed for fault detection. The convolutional autoencoder is combined with an orthogonal attention mechanism to extract time-series characteristic information of the operational state, thereby achieving precise detection of fault conditions. Additionally, a convolutional neural network (CNN) model uses both raw signals and data reconstructed by OSCAE to identify different faults, which enhances the features of the input and enables highly accurate fault identification. The effectiveness and robustness of the propose method is validated with simulation data of our self-established chemical distillation system and the publicly available Tennessee Eastman process system. The diagnosis efficacy in fault detection and identification is validated by applying fault detection metrics, high-dimensional feature visualizations, and confusion matrix analyses across two case studies. This paper not only provides an effective diagnostic framework for chemical systems but also offers a usable benchmark dataset for chemical distillation systems to the academic community, with the hope that the research content can enhance the stability and reliability of chemical processes.

Research on electromagnetic torque and fault parameter identification of pumped storage machine under power generation state based on optimized network parameter method1

Because of the complex and frequent multi-operation conditions of pumped storage machine and the difficulty of its numerical analysis, an optimized network parameter method (ONPM) is given to identify the second harmonic electromagnetic torque of large salient-pole generators. Different from the former research which only considers the positive and negative sequence components, the second harmonic electromagnetic torque of pumped storage machine under power generation state is identified in neutral point grounded system, which are displayed by the lumped parameters. Then, in order to test the validity of the theoretical analysis among power generation salient-pole generators, the finite element model of 300 MVA pumped storage machine under power generation is established. Through the comparison and analysis of the finite element result data with the actual experimental data in the steady state of no-load test and short-circuit test, the correctness of the finite element model is completely verified. Finally, in the case of small current asymmetry and large current asymmetry, the second harmonic electromagnetic torques obtained by ONPM and finite element method (FEM) are found respectively, and their relative errors are elaborately displayed. The results display that ONPM can accurately identify the electromagnetic torque parameters which indicate the specific operation and fault state of pumped storage machine under power generation state. This fault parameter identification has practical significance for monitoring and improving the operation state and stability of large salient-pole generator.

Research on pressure propagation in long-distance water pipelines for fault conditions by VMD and wavelet transform

Long-distance water pipelines in complex geographical environments face potential risks such as leaks. This study uses variational mode decomposition (VMD) and continuous wavelet transform (WT) to analyze pressure fluctuation signals in pipelines for detecting and locating leaks and other anomalies. CFD simulations are conducted to obtain pressure fluctuation data under various fault conditions. The pressure signals are then decomposed into multiple Intrinsic Mode Functions (IMFs) using VMD, and WT is applied to analyze their time–frequency characteristics. The results show significant differences in amplitude and frequency of IMF components between fault and normal conditions, with reduced amplitude and altered frequency under fault conditions, providing a basis for fault detection. Additionally, the IMF characteristics differ at different fault locations, aiding in fault localization. This research offers an effective method for leak detection and localization in long-distance pipelines, crucial for enhancing safety and stability.