Early Fault Detection Research Articles

Anomaly Detection on Small Wind Turbine Blades Using Deep Learning Algorithms

Wind turbine blade maintenance is expensive, dangerous, time-consuming, and prone to misdiagnosis. A potential solution to aid preventative maintenance is using deep learning and drones for inspection and early fault detection. In this research, five base deep learning architectures are investigated for anomaly detection on wind turbine blades, including Xception, Resnet-50, AlexNet, and VGG-19, along with a custom convolutional neural network. For further analysis, transfer learning approaches were also proposed and developed, utilizing these architectures as the feature extraction layers. In order to investigate model performance, a new dataset containing 6000 RGB images was created, making use of indoor and outdoor images of a small wind turbine with healthy and damaged blades. Each model was tuned using different layers, image augmentations, and hyperparameter tuning to achieve optimal performance. The results showed that the proposed Transfer Xception outperformed other architectures by attaining 99.92% accuracy on the test data of this dataset. Furthermore, the performance of the investigated models was compared on a dataset containing faulty and healthy images of large-scale wind turbine blades. In this case, our results indicated that the best-performing model was also the proposed Transfer Xception, which achieved 100% accuracy on the test data. These accuracies show promising results in the adoption of machine learning for wind turbine blade fault identification.

Utilisation pattern of ophthalmic services in Ashanti Region, Ghana.

Best practice in optometry and ophthalmology recommends regular visits to eye care professionals, as routine eye examinations support early detection of ocular defects and associated systemic, sometimes potentially life-threatening, conditions. The study sought to determine the utilisation of ophthalmic services and its associated factors in the Ashanti region of Ghana. Fifty electoral areas in 10 of the 43 districts in the Ashanti region of Ghana. A total of 1615 participants, aged 18 years and above, were randomly selected in the Ashanti region of Ghana for this population-based, cross-sectional survey. The factors associated with having had an eye examination were guided by Andersen's Behavioural Model. The data were analysed using multiple logistic regression, employing the IBM SPSS software, version 25. After statistical adjustments, compared with the 18-29-year-old age group, older participants were found to be more likely to utilise eye care services: In addition, participants with higher formal education had higher odds for eye care utilisation compared with no former education: Being hypertensive, self-reported vision problems and feeling that regular eye examinations are important, were statistically associated with eye care utilisation. There is alarmingly poor utilisation of ophthalmic services in the Ashanti region of Ghana. Effective programmes to promote public health by addressing the socio-economic and individual barriers hindering the uptake of ophthalmic services in the Ashanti region of Ghana are thus necessary.Contribution:The study addresses a gap in the knowledge of factors associated with ophthalmic services utilisation in the Ashanti region of Ghana.

Damage Detection of Gantry Crane with a Moving Mass Using Artificial Neural Network

Gantry cranes play a pivotal role in various industrial applications, and their reliable operation is paramount. While routine inspections are standard practice, certain defects, particularly in less accessible components, remain challenging to detect early. In this study, first a finite element model is presented, and the damage is introduced using random changes in the stiffness of different parts of the structure. Contrary to the assumption of inherent reliability, undetected defects in crucial structural elements can lead to catastrophic failures. Then, the vibration equations of healthy and damaged models are analyzed to find the displacement, velocity, and acceleration of the different crane parts. The learning vector quantization neural network is used to train and detect the defects. The output is the location of the damage and the damage severity. Noisy data are then used to evaluate the network performance robustness. This research also addresses the limitations of traditional inspection methods, providing early detection and classification of defects in gantry cranes. The study’s relevance lies in the need for a comprehensive and efficient damage detection method, especially for components not easily accessible during routine inspections.

Comparative analysis of harmonic sensitivity for stator fault diagnosis in induction motors

Induction motors play a vital role in various industrial applications due to their commendable efficiency and reliability. However, their susceptibility to faults, especially in challenging industrial environments, highlights the need for vigilant fault detection to prevent unforeseen downtimes and reduce subsequent repair costs. Early fault diagnosis is crucial in this context. A systematic approach to diagnosing faults in asynchronous motors involves the application of signal processing techniques, particularly utilizing the Fast Fourier Transform (FFT). The FFT, as a mathematical tool, enables a comprehensive analysis of signals, facilitating the identification and isolation of their frequency components. Monitoring the frequency components within a motor's signal provides a means to determine the existence and severity of faults. FFT analysis allows for the monitoring of four distinct categories of harmonics: time harmonics (TH), rotor slot harmonics (RSH), rotor bar fault harmonics (RBFH), and eccentricity fault harmonics (EFH). Each type of harmonic offers valuable insights into specific fault categories. Empirical evidence, drawn from experimental results, emphasizes the heightened sensitivity of rotor slot harmonics (RSH) in detecting stator faults. Continuous monitoring of the RSH frequency component enables the prompt detection and localization of stator faults, along with an assessment of their severity. Additionally, this diagnostic methodology proves effective in identifying micro short-circuits between stator coils, allowing for a proactive strategy in predictive maintenance. This proactive approach enables anticipatory part replacement before degradation progresses to the point of causing comprehensive failure in the production chain. The combination of FFT-based signal processing and harmonic analysis establishes a robust framework for the early detection and localization of faults in asynchronous motors within industrial settings. This contributes to enhanced operational reliability and efficiency, ultimately ensuring smoother industrial processes.

Development of a Dynamic Semi-empirical Model for Simulation of Copper Electrowinning Processes

Dynamic process models present an opportunity to investigate optimization and control strategies for the energy-intensive copper electrowinning process. In this paper, a dynamic semi-empirical model of the copper electrowinning process was developed to predict the copper yield, current efficiency, and specific energy consumption. The model uses input variables readily measured in industrial tankhouses and incorporates the ability to induce step or pulse disturbances in the electrolyte composition or flow rate. Dynamic bench-scale electrowinning data were used to show how the model may be calibrated and validated for use in predicting electrowinning performance. Overall, the performance of the developed dynamic model lends credence to the application thereof for operator training, process monitoring, and early fault detection. The model also represents a further step towards investigating advanced control strategies for the electrowinning process.

A comprehensive review on enhancing wind turbine applications with advanced SCADA data analytics and practical insights

AbstractThe aim of this study is to explore the potential and economic benefits of utilising Supervisory Control and Data Acquisition (SCADA) data to improve wind turbine operation and maintenance activities. The review identifies a gap in the current understanding of how to effectively use SCADA data in wind turbine applications. It emphasises the need for pre‐processing SCADA data to ensure data integrity by addressing outliers and employing interpolation techniques. Additionally, it highlights the challenges associated with early fault detection methods using SCADA data, including the development of physical models, data‐driven machine learning models, and statistical regression models. The review also recognises the limitations caused by the lack of public data from wind turbine developers and the imbalance between normal operation data samples and abnormal data samples, negatively impacting model accuracy. The key findings of the review demonstrate that SCADA data‐driven techniques can lead to significant improvements in wind turbine operations and maintenance. The application of data‐driven technologies based on SCADA data has proven effective in reducing operation and maintenance costs and enhancing wind power generation. Moreover, the development of robust decision support systems using SCADA data minimises the need for frequent maintenance interventions in offshore wind farms. To bridge the gap and further enhance wind turbine applications using SCADA data, several recommendations are provided. These include encouraging greater openness in sharing SCADA data to improve the robustness and accuracy of AI models, adopting transfer learning techniques to overcome the scarcity of quality datasets, establishing unified standards and taxonomies, and providing specialised resources such as software applications with interactive graphical user interfaces for easier storage, annotation, and analysis of SCADA data.The authors’ review paper identifies a gap in the current understanding of how to effectively utilise SCADA data in wind turbine applications. It emphasises the importance of pre‐processing SCADA data to ensure data integrity by addressing outliers and employing interpolation techniques. Furthermore, the authors highlight the challenges associated with early fault detection methods using SCADA data, including the development of physical models, data‐driven machine learning models, and statistical regression models.

An Embedded Machine Learning Fault Detection System for Electric Fan Drive

Industrial fans are critical components in industrial production, where unexpected damage of important fans can cause serious disruptions and economic costs. One trending market segment in this area is where companies are trying to add value to their products to detect faults and prevent breakdowns, hence saving repair costs before the main product is damaged. This research developed a methodology for early fault detection in a fan system utilizing machine learning techniques to monitor the operational states of the fan. The proposed system monitors the vibration of the fan using an accelerometer and utilizes a machine learning model to assess anomalies. Several of the most widely used algorithms for fault detection were evaluated and their results benchmarked for the vibration monitoring data. It was found that a simple Convolutional Neural Network (CNN) model demonstrated notable accuracy without the need for feature extraction, unlike conventional machine learning (ML)-based models. Additionally, the CNN model achieved optimal accuracy within 30 epochs, demonstrating its efficiency. Evaluating the CNN model performance on a validation dataset, the hyperparameters were updated until the optimal result was achieved. The trained model was then deployed on an embedded system to make real-time predictions. The deployed model demonstrated accuracy rates of 99.8%, 99.9% and 100.0% for Fan-Fault state, Fan-Off state, and Fan-On state, respectively, on the validation data set. Real-time testing further confirmed high accuracy scores ranging from 90% to 100% across all operational states. Challenges addressed in this research include algorithm selection, real-time deployment onto an embedded system, hyperparameter tuning, sensor integration, energy efficiency implementation and practical application considerations. The presented methodology showcases a promising approach for efficient and accurate fan fault detection with implications for broader applications in industrial and smart sensing applications.

Gear fault diagnosis based on complex network theory and error-correcting output codes: Multi class support vector machine

Gearbox failures have a detrimental effect on the machine performance that affects the production capacity and economic benefits of a manufacturing industry in an adverse manner. Early detection of faults in gears helps to prevent sudden machine failures. Previously, many signal processing and artificial intelligence techniques have been successfully applied to diagnose gear faults by analyzing the machine vibrations. These techniques have repeatedly emphasized on the need to extract quality features from gear vibration signals and using artificial intelligence techniques that can identify multiple types of faults simultaneously. As such, in this article, new features called as visibility graph features based on complex network theory have been proposed to extract fault information from vibration signals. In addition, a new artificial intelligence framework for multifault classification known as error-correcting output codes-multiclass support vector machine is proposed to detect gear faults. To the best of authors’ knowledge, these features along with the error-correcting output codes-artificial intelligence framework have been rarely utilized for fault diagnosis purpose. The proposed approach has been applied on experimental gear vibration data to validate its effectiveness. First, the vibration signals are transformed to graphs, and various graph properties are computed to serve as fault features. Then, the fault features are supplied to train the error-correcting output codes-multiclass support vector machine model and learn the fault patterns. Finally, the gear fault classification accuracies are determined for various gear test conditions and compared with those of existing methods. It is observed that the proposed approach provides an average improvement of 4.22%, 9.93% and 11.8% over the time-domain features, time–frequency domain features and voting-based multiclass support vector machine classifier, respectively, for different operating conditions. Furthermore, the suggested technique augments the classification accuracies by 10%, 7.5% and 6.7%, respectively, as compared with the deep-learning models, namely standard stacked sparse autoencoder, deep neural network and convolution neural network.

The Early Detection of Faults for Lithium-Ion Batteries in Energy Storage Systems Using Independent Component Analysis with Mahalanobis Distance

In recent years, battery fires have become more common owing to the increased use of lithium-ion batteries. Therefore, monitoring technology is required to detect battery anomalies because battery fires cause significant damage to systems. We used Mahalanobis distance (MD) and independent component analysis (ICA) to detect early battery faults in a real-world energy storage system (ESS). The fault types included historical data of battery overvoltage and humidity anomaly alarms generated by the system management program. These are typical preliminary symptoms of thermal runaway, the leading cause of lithium-ion battery fires. The alarms were generated by the system management program based on thresholds. If a fire occurs in an ESS, the humidity inside the ESS will increase very quickly, which means that threshold-based alarm generation methods can be risky. In addition, industrial datasets contain many outliers for various reasons, including measurement and communication errors in sensors. These outliers can lead to biased training results for models. Therefore, we used MD to remove outliers and performed fault detection based on ICA. The proposed method determines confidence limits based on statistics derived from normal samples with outliers removed, resulting in well-defined thresholds compared to existing fault detection methods. Moreover, it demonstrated the ability to detect faults earlier than the point at which alarms were generated by the system management program: 15 min earlier for battery overvoltage and 26 min earlier for humidity anomalies.

Synchronous Generator Abnormality and Fault Analysis

The trouble-free operation of alternators is unavoidable to meet the rising demand for electrical energy. Any alternator failure causes overloading of the remainder of the units in a grid, posing a serious threat to network stability. In a stand-alone generation, production is seriously affected. The repairs of large capacity alternators require a trained workforce, which is not always locally available. When an alternator operates under typical fault conditions, it reduces its efficiency and shortens its lifespan. The synchronous generator’s prolonged outage has an adverse impact on network reliability and impacts the economy. As a result, early detection of alternator anomalies significantly reduces fault extension, loss of supply, and maintenance costs, while also improving the alternator’s life. In many cases, the early fault detection scheme for higher capacity alternators cannot be readily applied to a lower capacity one. The article discusses some practical root cause analyses of the commonly occurring faults in turboalternators. The identification, characteristics, and analysis of multiple fault occurrences have been thoroughly addressed. This article would provide utility and protection engineers impetus in determining the urgency, selecting, and implementing the appropriate protective system for various abnormality events.

HVAC early fault detection using a fuzzy logic based approach

The need for improving the energy efficiency of existing buildings has driven to the implementation of building energy management systems (BEMS) that can help facilities manager to discover and identify problems that may cause energy wastage or affect to occupants’ comfort. Modern data-driven fault detection and diagnosis (FDD) make use of the data collected by the building BEMS to provide high accuracy in the revelation of heating, ventilation and air-conditioning (HVAC) system faults. However, these methods need a large amount of faulty data samples during the training, which is an uncommon situation in the real world. The main focus of this paper is to present a methodology to detect faults when the number of faulty samples is low. For this purpose, a regression-based methodology based on an adaptative neuro-fuzzy inference system (ANFIS) chiller model is developed using the data collected from a real use case. The model presents good results, that can be used for benchmarking the machine operation and detect the abnormal operation states.

Bearing fault feature extraction method: stochastic resonance-based negative entropy of square envelope spectrum

The early identification of bearing defects has recently attracted increasing attention in the fields of condition monitoring and predictive maintenance because of the critical role of bearings on the reliability and safety of turbomachines. The weak features representing early faults in the vibration signals are often submerged in the environmental noise, which poses a major challenge for the early fault diagnosis of rolling bearings. This study proposes a negative entropy of the square envelope spectrum approach integrated with optimized stochastic resonance (SR)-based signal enhancement for accurate early defect detection of rolling element bearings. The proposed method considers the cyclostationarity and impulsivity of the raw signal, as well as its similarity with the enhanced signal, thus reinforcing the characteristic frequency while integrating the regularity of the raw signal to evaluate the SR performance. A comparison study with different existing methods using both numerical and experimental data was conducted to illustrate the effectiveness and accuracy of the proposed methodology for early defect detection of rolling element bearings in different locations. The results show that the proposed method improves the fault detection by 3.5 d earlier than other SR methods, and produces the best enhancement results for fault detection in the outer race, inner race, and rolling element of bearings, with the increase of characteristic frequency intensity coefficient by 126.3%, 118.1%, and 100.5% compared to traditional envelope signals, respectively.

Post-2023 Türkiye earthquake risk assessment of cascade dams in upper Euphrates basin

The southeastern region of Türkiye faced two significant earthquakes on February 6, 2023, causing widespread destruction and substantial damage to various infrastructures. Over forty large dams in the region were affected, leading to potential new earthquake-prone areas due to energy accumulation in neighboring regions. This study focuses on the seismic risk of eight cascade dams on the Peri River, a tributary of the Euphrates main river, following these earthquakes. The dams, including Kalecik, Kigi, Konaktepe, Ozluce, Pempelik, Seyrantepe, Tatar, and Uzuncayir, with heights ranging from 31 m to 146 m, are situated in a region influenced by the North Anatolian Fault Zone. The research advocates for a comprehensive re-analysis of certain large dams, considering the updated seismic specifications and seismological maps of Türkiye. The study explores the hazard and overall risk assessment of these dams, emphasizing the cascade system and highlighting the critical seismic vulnerabilities of Kigi and Ozluce dams, with a particular focus on their implications for water security in the region. Our findings underscore the need for tailored safety measures for each dam, focusing on early defect detection. By adopting a proactive stance and implementing our recommendations, the resilience of these dams can be enhanced, contributing to the overall water security of the region.

FPGA implementation of an improved envelope detection approach for bearing fault diagnosis

This study presents an enhanced envelope detection technique implemented on a field-programmable gate array (FPGA) to diagnose bearing faults in rotating machinery. Bearing faults frequently result in machinery breakdowns, incurring substantial downtime and maintenance expenses. In our approach, we employ the Teager energy operator (TEO) to extract the vibration signal envelope. Subsequently, we subject the envelope signal to the fast Fourier transform (FFT) to generate the envelope spectrum of the vibration signal. Finally, we further refine the envelope spectrum using TEO for a second time, resulting in a pronounced fault peak that facilitates early fault detection. We evaluate the effectiveness and performance of the proposed method using two distinct types of bearing vibration signals, one being simulated and the other measured. Our findings reveal that the suggested approach outperforms traditional envelope detection methods, leading to a substantially enhanced fault diagnosis capability. For instance, when we assess the characteristic frequency ratio (FCFR) for faults in the inner and outer rings of the bearing using the proposed method, we observe that the FCFR values are significantly elevated, ranging from 160 to 330% higher compared to the analysis performed by the TEO and HT methods. Consequently, this indicates that the proposed approach has the ability to detect faults at an earlier stage than other methods. Furthermore, the FPGA-based implementation makes it suitable for critical industrial applications where rapid fault detection is essential to prevent catastrophic failures.

RECONSTRUCTION OF BURIED THERMAL SOURCES FROM SURFACE TEMPERATURE FIELDS BY BAYESIAN INFERENCE

Early detection of defects (e.g., cracks, delamination in composites, defects in adhesive bonds) is critical to prevent potential accidents in industrial environments. Traditional nondestructive testing (NDT) methods, such as thermal techniques, can be used to detect and characterize defects buried in the material. In several of these methods, the material is mechanically excited in such a way that the defects behave like heat sources. By studying the resulting thermal fields, inverse methods have been developed to reconstruct these heat sources and, therefore, even more so defects. The reconstruction of volumetric heat sources buried in material is notably ill-posed and requires the use of specific tools, which makes it difficult to reconstruct both the position and, in particular, the source intensity value. In this paper, an algorithm based on a Bayesian approach is proposed. A prior modeling in the form of a mixture of distributions is considered, which promotes spatial sparsity and thereby regularizes the inference problem. This method enables the reconstruction of sources with high fidelity, including the estimation of intensities. Its performance is discussed in relation to noise, and it is compared to other methods, showing favorable potential for NDT applications.

New Harmonics for Early Detection of Inter-turn Faults in Induction Motors During Start-up

New Harmonics for Early Detection of Inter-turn Faults in Induction Motors During Start-up

GearFaultNet: Novel Network for Automatic and Early Detection of Gearbox Faults

GearFaultNet: Novel Network for Automatic and Early Detection of Gearbox Faults

Material management in automobile industry: Era 4.0

Nowadays, a lot of places worldwide are using Industry 4.0 technology. Smart manufacturing, supply chains, warehousing, logistics, and materials are all developed with the usage of these technologies, especially in automobile sector. It can potentially resolve complex production issues from a commercial perspective. Industry 4.0 technologies that are available for enhancing manufacturing procedures and material quality of automobile industry are thoroughly examined in this article. In the upcoming era of vehicles, we have enumerated the several technologies that are currently available, together with their attributes and advantages for efficient management. Automobile businesses may optimise their inventory and material waste with the use of digital technologies, which lowers costs. When necessary, employees who are located on different sites can work together with ease due to remote collaboration. By helping them stay current with knowledge, these tools eventually close communication barriers. Proper equipment monitoring in industries utilising Industry 4.0 technology will be aided by smart predictive analysis. Early detection and resolution of material defects is possible with the help of these advance technologies. Additionally, this meets the customer's expectations and offers transparency in the systems and procedures.

Сегментация дефектов дорожного полотна на основе нейросетевого ансамбля

Early monitoring road conditions and defect detection are an important step in ensuring road safety. The work presents a new road damage segmentation dataset SegmRDD. It contains 4420 images with defects of three classes "cracks", "alligator crack", "potholes" well annotated at the pixel level. The dataset is balanced and covers the roads of five countries, including Russia. Developed ensemble model based on three parallel-trained neural network models YOLOv8, U-Net, Mask R-CNN with combining results, and achieved an F1-score of 70% for all defects.

Stacked AutoEncoder based diagnosis applied on a Solar Photovoltaic System

This paper deals with the modeling of a photovoltaic system connected to a grid for the simulation of normal and faulty operations and the generation of a data-set for learning a fault detection algorithm based on a Stacked Autoencoder. To evaluate the effectiveness of the proposed approach, a Mean Squared Error is used. This method enables early fault detection, enhancing system relability and efficiency while addressing the need for proactive fault management in the system under normal conditions. Obtained results under different radiation and temperature conditions highlight the relevance of the proposed model and the effectiveness of the fault detection algorithm.