Unexpected Faults Research Articles

Digital twin-enabled autonomous fault mitigation in diesel engines: An experimental validation

Due to the growing demand for robust autonomous systems, automating maintenance and fault mitigation activities has become essential. If an unexpected fault occurs during the travel, the system should be able to manage that fault autonomously and continue its mission. Thus, a robust fault mitigation system is needed that can quickly reconfigure itself in an optimal way. This paper presents a novel digital twin-based fault mitigation strategy that uses hierarchical control architecture. Here, a computationally efficient high-fidelity hybrid engine model is developed to simulate actual engine behavior. This hybrid engine model includes a neural network model representing the cylinder combustion process and well-studied physics-based analytical equations describing the remaining subsystems. This architecture uses a feedback controller on top of the control calibration map, generated offline using the hybrid model, to mitigate faults and modeling errors. The fault mitigation strategies are calibrated and validated through model-in-loop (MIL) and hardware-in-loop (HIL) simulations for various operating points using the Navistar 7.6 liters six-cylinder engine. The effectiveness of the proposed architecture in handling injector nozzle clogging, intake manifold leaks, and pressure shift faults is illustrated. The results demonstrate that the proposed architecture can completely overcome faults and maintain the desired torque in a few seconds. Moreover, the average accuracy of 96% is observed for the engine model compared to experimental data. It is anticipated that the proposed end-to-end architecture will be easily deployable on unmanned marine vessels and can be extended to accommodate other component faults.

FAULT DETECTION AND CLASSIFICATION USING DENSENET, SURF-BASED ANN, AND INFRARED THERMOGRAPHY

The reliability and efficiency of electric motors are critical in industrial applications, where unexpected faults can lead to costly downtime and safety hazards. Traditional fault detection methods often require extensive manual inspection and may not capture subtle anomalies in motor behavior. Infrared thermography has emerged as a non-invasive technique to detect temperature variations in motor components, which can indicate potential faults. However, the challenge lies in accurately classifying these faults to prevent failures. Current methods lack the precision needed to classify various motor faults accurately and quickly, especially when dealing with complex thermal patterns. The integration of advanced deep learning architectures with feature extraction techniques presents an opportunity to enhance the detection and classification of motor faults. This study proposes a hybrid model combining DenseNet, a deep learning architecture known for its high performance in image analysis, with a Speeded-Up Robust Features (SURF)-based Artificial Neural Network (ANN) for feature extraction and classification. Infrared thermography images of motors were first processed through DenseNet for initial feature extraction. The SURF algorithm further refined these features, which were then classified using ANN. The model was trained and validated on a dataset of infrared thermography images, representing various motor fault conditions, including bearing wear, misalignment, and insulation failure. The proposed model achieved an overall accuracy of 98.7% in detecting and classifying motor faults, outperforming traditional methods by 5.2%. The model also demonstrated high sensitivity (97.8%) and specificity (99.1%) in identifying subtle temperature variations indicative of early-stage faults. These results highlight the effectiveness of the DenseNet and SURF-based ANN approach in enhancing the reliability of motor fault detection using infrared thermography.

Real-time AIoT anomaly detection for industrial diesel generator based an efficient deep learning CNN-LSTM in industry 4.0

Anomaly detection for industrial diesel generators, in which unexpected faults could lead to severe consequences, is still challenged due to their complex structure and nonstationary operation. Maintenance engineers who manually audit diesel generators for anomaly detection require significant expertise and knowledge. This study proposes a real-time intelligent AIoT system-based convolution neural network long short-term memory (CNN-LSTM) to enhance efficiency and decrease labor costs of industrial diesel generator maintenance service. The AIoT system could autonomously classify abnormal conditions of industrial diesel generators through supervised learning techniques. Several anomaly failure conditions are identified by maintenance experts and are simulated in the laboratory to collect the working parameters based on developed IoT modules. Pearson product-moment coefficients are computed to effectively evaluate the interdependence between collected variables and the target anomaly types. The proposed CNN-LSTM structure is hyperparameter fine-tuning for identifying the most critical configurations in failure-diagnosing applications. The developed approach is comprehensively analyzed and evaluated with other state-of-the-art individual deep learning algorithms, including recurrent neural network (RNN), LSTM, gate-recurrent unit (GRU), and CNN. The experiment results indicate that the proposed hybrid CNN-LSTM could achieve distinguished diagnosis precision of anomaly conditions of industrial diesel generators and significantly improve the classified performance in Industry 4.0.

Research on bearing fault diagnosis based on laser vibrometer

As general components in machinery, rolling bearings are also fault prone components. And unexpected faults will bring immeasurable loss to economy, personnel, etc. Therefore, fault detection and diagnosis are of paramount importance. As the carrier of fault information, component response signal is the most concerned part in fault diagnosis researches. The detection methods for response signal can be divided into contact and non-contact detection. Compared with the contact detection, laser Doppler vibrometer has the advantage of no contact, no damage and dynamic measurement. Thus, this paper progresses theoretical and experimental researches on non-contact detection of bearing wear fault based on laser Doppler vibrometer. Firstly, the vibration measurement principle of laser Doppler vibrometer is analyzed in this paper. On account of the principle, the internal optical path and signal flow of the single point laser vibrometer is established and analyzed. Secondly, in order to carry out the non-contact detection test, an optical measuring system based on a single point laser vibrometer is built to collect signals. Also, a bearing wear fault simulated test rig is built to provide fault response signals. Based on the above built test devices, the detection tests of the intact and faulty bearings are carried out. Lastly, through the analysis of collected signals of bearings with wear of different parts in time domain and frequency domain, the characterizations of the corresponding fault are obtained so as to implement the fault diagnosis, which prove the effectiveness of laser vibration detection method for fault detection.

Using functional decomposition to bridge the design gap between desired emergent multi‐agent‐system resilience and individual agent design

AbstractIncreasing the resilience of modern infrastructure systems is recognized as a priority by both the International Council on Systems Engineering and the National Academy of Engineering. Resilience answers the key stakeholder need for a stable and predictable system by withstanding, adapting to, and recovering from unexpected faults. Increasing resilience in multi‐agent systems is especially challenging because resilience is an emergent system‐level property rather than the sum of individual agent functions. This paper uses biological systems as a source of inspiration for resilient functions, examining the central question How can biologically inspired design be used to increase the emergent property of resilience in multi‐agent systems? The paper uses functional decomposition to break down the individual functions that result in resilience and transfer the properties to generalized systems. Accordingly, the central hypothesis examined in this article is If functional decomposition is performed on eusocial insect colonies, then generalizable approaches to increase the emergent property of multi‐agent system resilience can be identified. The results provide two contributions. The first contribution is the identification of six general functions based on eusocial insect behavior that influence resilience. The second contribution is a description of the process of identifying and transferring insect behaviors into generalized design‐for‐resilience guidance. To support these contributions, a case study applies biologically inspired functions to an emergency power service system and proposes tactics for the power system to improve its resilience. Thus, this article provides a key step towards our goal of using biologically inspired design to influence the emergent property of resilience in multi‐agent systems.

Fault-tolerant controller design based on adaptive backstepping for tower cranes with actuator faults

Due to the widespread application and significant investment required for a single crane, there is an increased emphasis on crane safety and service life. Fault-tolerant control as an effective solution to unexpected faults has been widely studied recently. However, most fault-tolerant control methods require redundant actuators or a complex design process, which is unsuitable for the tower crane. Following these problems, a fault-tolerant controller based on an adaptive backstepping technique is proposed. Firstly, the system states are reconstructed and written as a cascade system. Secondly, a fixed-time convergence optimized backstepping controller is proposed to achieve smooth control of the tower crane without generating sudden or abrupt values. Then, an adaptive approach has been proposed to update fault parameters for the crane system in case of a sudden fault occurrence. Finally, after conducting comparison tests, it has been determined that the proposed controller not only performs exceptionally well in terms of position accuracy and swing elimination, but also maintains a satisfactory control performance when faced with sudden faults.

Accelerated 3D Simulation for Analyzing Electrochemical and Thermal Distribution in Lithium-Ion Batteries

Understanding the spatial and temporal internal behavior of lithium-ion batteries (LIBs) is crucial for ensuring safe operation and preventing unexpected faults during manufacturing and diagnosis processes. Traditional approaches, such as the pseudo-two-dimensional (P2D) model, provide a simplified representation of LIBs but limit the analysis of continuum-scale electrochemical distribution inside the cell.This study proposes an accelerated three-dimensional (3D) simulation methodology, expanding the conventional P2D model into a pseudo-four-dimensional (P4D) model, including three dimensions of cell structure and a pseudo-dimension inside electrode particles based on the porous electrode theory. In this study, the electrochemical model in the pseudo-four-dimension is combined with a thermal model, considering energy balance with ohmic heat, reaction heat, entropic heat, and internal short circuit (ISC) heat generation.To analyze the P4D model, we apply the following numerical strategies: 1) Elimination of nonlinearity inside model equations using Taylor series expansion, 2) Separation of electrochemical and thermal model variables using a staggered time-stepping method, and 3) Determination of time step size based on the gradient of model output. The proposed method is validated by comparing simulation results for an LFP cell with experimental results and a commercial software under constant current discharge operations (1C, 2C, 3C, and 5C).The accelerated 3D simulation methodology offers significant advantages for exploring internal inhomogeneous properties under different materials operating conditions, ensuring battery safety and reliability under various scenarios. We demonstrate that the proposed method enables the investigation of internal distributions of concentration, potential, and temperature inside battery cells, paving the way for designing and managing batteries with various materials. Figure 1

Event-triggered fault-tolerant optimal coordination for multiple Euler–Lagrange systems with semi-Markov jumping networks

ABSTRACT This article explores a distributed optimal coordination control problem for multiple Euler–Lagrange systems with actuator faults. To address this problem, an event-triggered fault-tolerant optimisation algorithm is first proposed to eliminate unexpected faults and reduce the consumption of control resources. In order to further enhance the system's reliability, another algorithm based on the Nussbaum function is proposed to handle faulted systems with uncertain control directions. Note that an auxiliary system with adaptive gains is introduced to eliminate the need for agents to interact with their actual state information, and thus has the effect of protecting privacy. Moreover, the stochastic semi-Markov jumping networks are considered in the algorithms to describe the switching process of uncertain communication graphs. Additionally, the algorithms are fully distributed since it does not require global information of topologies. Finally, numerical simulations are conducted in the article to verify the effectiveness of the proposed algorithms.

A Fault-Tolerant LLC Converter With High Reliability and Low Cost for Two-Stage Converters

The popularity of electric vehicles is getting higher, and a large number of DC-DC converters are deployed. LLC converters have witnessed a rapid deployment due to their remarkable merits, often employed as the isolation stage in two-stage converters. However, the contradiction between the increasing demand for reliability and the limited space is becoming prominent. Therefore, ensuring fault tolerance capacity with fewer devices is highly desired. A fault-tolerant LLC converter, which can keep working after multiple unexpected faults, is designed to take over half-bridge LLC converters. The pre-fault converter behaves like a full-bridge LLC converter and would be reconstructed to retain uninterrupted power output after faults. The reconstructed converter after the first fault behaves like two parallel half-bridge LLC converters and would be further reconstructed into a single half-bridge converter after the second fault. The faults can both be handled, including short-circuit faults and open-circuit faults. The transition processes of reconstruction are extremely short. The spike current during the transition processes is well limited, and the output voltage has slight fluctuation. The proposed converter could drastically reduce the need for redundancy and has obvious cost advantages. Finally, a prototype is developed to verify the superiority of the proposed converter.

A Novel Fault-Tolerant Super-Twisting Control Technique for Chaos Stabilization in Fractional-Order Arch MEMS Resonators

With the increasing demand for high-performance controllers in micro- and nano-systems, it is crucial to account for the effects of unexpected faults in control inputs during the design process. To tackle this challenge, we present a new approach that leverages an estimator-based super-twisting control technique that is capable of regulating chaos in fractional-order arch micro-electro-mechanical system (MEMS) resonators. We begin by studying the governing equation of a fractional-order arch MEMS resonator, followed by a thorough exploration of its chaotic properties. We then outline the design process for our novel control technique. The proposed technique takes into consideration the effects of uncertainty and faults in the control input by utilizing a finite time estimator and a super-twisting algorithm. The proposed technique addresses important challenges in the control of MEMS in real-world applications by providing fault tolerance, which enables the controller to withstand unexpected faults in the control input. We apply our controller to the fractional-order arch MEMS resonator, conducting numerical simulations. The numerical findings reveal that our proposed control technique is capable of stabilizing the system’s dynamics, even in the presence of a time-evolving fault in the control actuator. These results provide compelling evidence of the efficacy of our approach to control, despite the presence of an evolving fault.

Real-Time Sensor Fault Identification and Remediation for Single-Phase Grid-Connected Converters Using Hybrid Observers With Unknown Input Adaptation

Unexpected faults that occur in the sensors of the single-phase grid-connected converter (SGC) may deteriorate the control performance ofthe grid current and dc-link voltage and pose risks to the connected distributed generation system. This article proposes an unknown input sliding mode observer (UI-SMO) based sensor fault identification and remediation strategy. Therein, an UI-SMO is established that integrates the observations of the grid current and dc-link voltage with the reconstruction of the unknown input (i.e., load condition of the SGC). Such an observer-based analytical redundancy generates the residuals that indicate the abnormalities of the sensors for fault identification. An adaptive fault-tolerant control (AFTC) strategy for the SGC is developed, where an automated control system reconfiguration with unknown input adaptation is seamlessly implemented by substituting the data reported by the faulty sensors with their observed values. Extensive simulation and experimental studies validate the effectiveness of the proposed UI-SMO-based sensor fault identification and AFTC strategy of the SGC.

A hybrid deep learning-based approach for rolling bearing fault prognostics

Predictive Maintenance (PdM) has the potential to revolutionize the industry by providing advanced techniques to assess the condition of an industrial system and yield key information that can help optimize maintenance planning and prevent unexpected faults and breakdowns. Nevertheless, PdM is far from being universally applied and it is still the subject of increasing research. Thus, developing new approaches has great relevance to help PdM become a practical reality for the industry. PdM can also bring benefits in terms of sustainability, by reducing human and material resources waste, which is one of the main objectives of Circular Manufacturing initiatives. In this context, rolling bearings are one of the most studied components, as most industrial systems with rotating mechanisms contain bearings, which are prone to a number of faults caused by natural and unnatural wear. In this work, an hybrid Deep Learning (DL) approach is proposed, combining a Convolutional Neural Network (CNN) with a Gated Recurrent Unit (GRU) network to predict Remaining Useful Life (RUL) using rolling bearing vibration data preprocessed with the Short-Time Fourier Transform (STFT). This model was trained and validated using the PRONOSTIA public dataset, which is a popular benchmark for rolling bearing prognostics. The obtained results are satisfactory, providing RUL estimates close to the true values in most test cases, proving the competitiveness of the approach and its potential.

Real-time learning for real-time data: online machine learning for predictive maintenance of railway systems

In the railway, an unexpected fault reduces service availability and may cause fatalities. Therefore, maintenance must be timely. Nowadays, the omnipresence of onboard sensors generates data enormously, thus enabling data-driven predictive maintenance. For this, machine learning has come into prominence. Traditionally, a machine learning model is trained on a batch of data. However, this approach lags behind on fast-paced data streams. For real-time learning on real-time data, we propose a pipeline that employs online machine learning to address predictive maintenance of sensorized railway systems. We showcase the implementation and experimental results of two modules automating data preprocessing to demonstrate the potentials of online learning. We also discuss the intuition of another module using online clustering to monitor the evolution of system health.

Predictive maintenance analytics and implementation for aircraft: Challenges and opportunities

AbstractThe increase in available data from sensors embedded in industrial equipment has led to a recent rise in the use of industrial predictive maintenance. In the aircraft industry, predictive maintenance has become an essential tool for optimizing maintenance schedules, reducing aircraft downtime, and identifying unexpected faults. Despite this, there is currently no comprehensive survey of predictive maintenance applications and techniques solely devoted to the aircraft manufacturing industry. This article is an in‐depth state‐of‐the‐art systematic literature review of the different data types, applications, projects, and opportunities for predictive maintenance in this industry. The goal of this review is to identify, and highlight the challenges and opportunities for future research in this field. This review found that the current focus of research is too biased towards aircraft engines due to a lack of publicly available data sets, and that greater automation is an important step to optimize aircraft maintenance to its full potential.

Methodology for the Identification of Dust Accumulation Levels in Photovoltaic Panels Based in Heuristic-Statistical Techniques

The use of renewable energies is increasing around the world in order to deal with the environmental and economic problems related with conventional generation. In this sense, photovoltaic generation is one of the most promising technologies because of the high availability of sunlight, the easiness of maintenance, and the reduction in the costs of installation and production. However, photovoltaic panels are elements that must be located outside in order to receive the sun radiation and transform it into electricity. Therefore, they are exposed to the weather conditions and many environmental factors that can negatively affect the output delivered by the system. One of the most common issues related to the outside location is the dust accumulation in the surface of the panels. The dust particles obstruct the passage of the sunlight, reducing the efficiency of the generation process and making the system prone to experimental long-term faults. Thus, it is necessary to develop techniques that allow us to assess the level of dust accumulation in the panel surface in order to schedule a proper maintenance and avoid losses associated with the reduction of the delivered power and unexpected faults. In this work, we propose a methodology that uses a machine learning approach to estimate different levels of dust accumulation in photovoltaic panels. The developed method takes the voltage, current, temperature, and sun radiance as inputs to perform a statistical feature extraction that describes the behavior of the photovoltaic system under different dust conditions. In order to retain only the relevant information, a genetic algorithm works along with the principal component analysis technique to perform an optimal feature selection. Next, the linear discrimination analysis is carried out using the optimized dataset to reduce the problem dimensionality, and a multi-layer perceptron neural network is implemented as a classifier for discriminating among three different conditions: clean surface, slight dust accumulation, and severe dust accumulation. The proposed methodology is implemented using real signals from a photovoltaic installation, proving to be effective not only to determine if a dust accumulation condition is present but also when maintenance actions must be performed. Moreover, the results demonstrate that the accuracy of the proposed method is always above 94%.

Probing an intelligent predictive maintenance approach with deep learning and augmented reality for machine tools in IoT-enabled manufacturing

• We solved the fault prediction problem with the combination of CNN and LSTM . • We solved the maintenance decision problem with the deep reinforcement learning. • The enhanced visual guidance of the maintenance process was realized by AR , which could integrate the invisible maintenance information into the machine tools. • The proposed predictive maintenance approach outperforms others in terms of accuracy and effectiveness. In the Industry 4.0 era, the number and complexity of machine tools are both increased, which is prone to cause malfunctions and downtime in the manufacturing process. Predictive Maintenance (PdM), as a pivotal part of Prognostics and Health Management (PHM), plays a vital role in enhancing the reliability of machine tools in the Internet of Things (IoT)-enabled manufacturing. In order to realize a highly reliable maintenance plan integrated with the fault prediction, the maintenance decision-making, and the Augmented Reality (AR)-enabled auxiliary maintenance, an intelligent predictive maintenance approach for machine tools is proposed in this paper via multiple services cooperating within a single framework. The fault prediction service is supported by the combination of Convolutional Neural Network and Long Short-Term Memory (CNN-LSTM). Specified features from massive production data acquired by IoT can be comprehensively extracted using CNN, and their nonlinear relationship can be fitted by LSTM. Based on the fault prediction result, deep reinforcement learning is adopted to achieve the production control and schedule maintenance personnel if a fault code appears. On top of this, the guidance information from the maintenance experience database can be integrated into the faulty machine tools in the form of visibility through AR, which can guide the maintenance personnel to complete maintenance tasks more efficiently. Moreover, the remote expert service is also integrated in the AR-supported auxiliary maintenance, which is activated to solve unexpected faults that are not stored in the maintenance experience database. Comparative experiments are conducted in the IoT-enabled manufacturing workshop with real-world case studies, and the results demonstrate that the proposed predictive maintenance approach is both effective and practical.

Ramanujan Fourier Mode Decomposition and Its Application in Gear Fault Diagnosis

As an important part of rotating machinery, gear is easy to appear some unexpected fault states, and its fault diagnosis is very important. Fourier decomposition method (FDM) is a common method for gear fault diagnosis, but the noise robustness, period recognition, and extraction capabilities of FDM are unsatisfactory. Based on this, in this article, Ramanujan Fourier mode decomposition (RFMD) method is proposed. The RFMD not only has a complete mathematical theory foundation but also has an excellent ability to identify and extract periodic components. Emulational and experimental results of planetary gearbox show that the RFMD method has good noise robustness and can accurately extract gear fault characteristic information. Thus, it is an effective gear fault diagnosis method.

An Overview of Recent Advances of Resilient Consensus for Multiagent Systems under Attacks.

Consensus control of multiagent systems (MASs) has been one of the most extensive research topics in the field of robotics and automation. The information sharing among the agents in the MASs depends upon the communication network because the interaction of agents may affect the consensus performance of the agents in a communication network. An unexpected fault and attack may occur on one agent and can propagate through the communication network into other agents. Thus, this may cause severe degradation of the whole MASs. In this paper, we first discussed MAS technologies. After that available technologies for the modeling of attacks and fundamental issues due to attacks on MAS attacks were discussed. We also introduced cooperative attack methodologies and model-based attack methodology. Objective of this article is to provide comprehensive study on recent advances in consensus control of MASs under attacks covering the published results until 2021. This survey presents different kinds of attacks, their estimation and detection, and resilient control against attacks. At the end, the survey accomplishes some potential recommendations for future direction to solve the key issues and challenges reported for secure consensus control of MASs.

Structural Response of a Prefabricated Utility Tunnel Subject to a Reverse Fault

Prefabricated utility tunnels have drawn much attention in relation to rapid urban development. On this, how to maintain the integrity of an underground lifeline, which is subjected to unexpected fault displacement action, is a concern either from the design or the construction aspect. By applying the commercial software program ABAQUS, this paper presents a systematic numerical simulation of a prefabricated utility tunnel affected by a reverse fault. The critical parameters investigated in this study include fault displacement, burial depth, utility tunnel-soil friction coefficient, and the angle of the utility tunnel crossing the fault plane. Results of the numerical modeling revealed that: (1) both the overall structural deformation and the spliced joints deformation of the prefabricated utility tunnel increase with increasing fault displacement, which greatly reduces the waterproofing ability of the utility tunnel joints; (2) the opening displacement of the joints on the roof of the utility tunnel near the fault plane is positively correlated with burial depth, but the variation is slight; (3) the variations in utility tunnel-soil friction coefficient have little effect on the overall structural deformation and the spliced joints deformation; (4) the opening displacement of the spliced joints of the utility tunnel basically gradually increases with an increase in the crossing angle near the fault plane, which is different than when it is away from the fault plane. The main outcomes obtained from this study can provide reference for the construction of prefabricated utility tunnel in fault active area.

Synthesizing Rolling Bearing Fault Samples in New Conditions: A Framework Based on a Modified CGAN.

Bearings are vital components of rotating machines that are prone to unexpected faults. Therefore, bearing fault diagnosis and condition monitoring are essential for reducing operational costs and downtime in numerous industries. In various production conditions, bearings can be operated under a range of loads and speeds, which causes different vibration patterns associated with each fault type. Normal data are ample as systems usually work in desired conditions. On the other hand, fault data are rare, and in many conditions, there are no data recorded for the fault classes. Accessing fault data is crucial for developing data-driven fault diagnosis tools that can improve both the performance and safety of operations. To this end, a novel algorithm based on conditional generative adversarial networks (CGANs) was introduced. Trained on the normal and fault data on actual fault conditions, this algorithm generates fault data from normal data of target conditions. The proposed method was validated on a real-world bearing dataset, and fault data were generated for different conditions. Several state-of-the-art classifiers and visualization models were implemented to evaluate the quality of the synthesized data. The results demonstrate the efficacy of the proposed algorithm.