Catalogue Search | MBRL
Are you sure you want to remove the book from the shelf?
{{itemTitle}}
27
result(s) for
"System failures (Engineering) Prevention Data processing."
Sort by:
A Review of Artificial Intelligence Methods for Condition Monitoring and Fault Diagnosis of Rolling Element Bearings for Induction Motor
The fault detection and diagnosis (FDD) along with condition monitoring (CM) and of rotating machinery (RM) have critical importance for early diagnosis to prevent severe damage of infrastructure in industrial environments. Importantly, valuable industrial equipment needs continuous monitoring to enhance the safety, reliability, and availability and to decrease the cost of maintenance of modern industrial systems and applications. However, induction motor (IM) has been extensively used in several industrial processes because it is cheap, reliable, and robust. Rolling bearings are considered to be the main component of IM. Undoubtedly, any failure of this basic component can lead to a serious breakdown of IM and for whole industrial system. Thus, many current methods based on different techniques are employed as a fault prognosis and diagnosis of rolling elements bearing of IM. Moreover, these techniques include signal/image processing, intelligent diagnostics, data fusion, data mining, and expert systems for time and frequency as well as time-frequency domains. Artificial intelligence (AI) techniques have proven their significance in every field of digital technology. Industrial machines, automation, and processes are the net frontiers of AI adaptation. There are quite developed literatures that have been approaching the issues using signals and data processing techniques. However, the key contribution of this work is to present an extensive review of CM and FDD of the IM, especially for rolling elements bearings, based on artificial intelligent (AI) methods. This study highlights the advantages and performance limitations of each method. Finally, challenges and future trends are also highlighted.
Journal Article
Disaster mapping and assessment of Pakistan’s 2022 mega-flood based on multi-source data-driven approach
Climate change-induced mega-floods have become increasingly frequent worldwide. The rapid mapping and assessment of flood disasters pose urgent challenges for developing countries with poor data facilities or databases. In this study, the characteristics of the 2022 mega-flood in Pakistan were monitored and analyzed based on multi-resources data. The extent of inundation throughout Pakistan and its impact on farmlands, buildings, and roads were mapped using Synthetic Aperture Radar remote sensing data processing technology. The results showed that a 10-m resolution flooding map could be achieved using the Google Earth Engine platform in a timely manner with reasonable precision. A GIS-based bluespot model was used to evaluate the risk of dam-failure floods. The zone risk distribution map of the dam-failure flood was produced with five risk levels, which contribute to the safety of the key infrastructure for flooding control. The potential influencing factors of snow melting in northern Pakistan induced by heat waves and disasters was detected using Earth observations and long-record historical data. The study provides data-driven approach options for monitoring flood hazards over large areas in emergency using multi-available data sources, where in situ monitoring is difficult. This study not only provided direct data products and risk maps for mega-flooding control in Pakistan, but also proposed five aspects of flood prevention and control recommendations for this region and its neighborhood areas to cope with flood disasters effectively under worsening climate change conditions.
Journal Article
Experimental study on the failure process and modes of loess spoil slope induced by rainfall and engineering disturbance
In this paper, indoor model tests were conducted using image analysis, pore pressure, and displacement measurement methods to investigate the failure evolution process and modes of loess spoil slopes with various components under the influence of rainfall and artificial excavation. The results of the experiments reveal that, under the action of rainfall, there are two types of cracks-to-failure modes for pure loess spoil slopes. One involves the formation of a large gully through the dominant channel, while the other is characterized by step-by-step retreating soil damage between cracks. The failure exhibits three distinct stages, and after failure, the slope angle is relatively large (>45°). The process of rainfall-induced destruction affecting loess spoil containing 25% coarse-grained content similarly unfolds in three stages, ultimately resulting in the formation of a regional landslide. This landslide typically encompasses a broader damage range compared to pure loess spoil, albeit with a shallower depth of damage. After the landslide stops and stabilizes, a tiny slope (45°) is created (<45°). The excavation at the toe of the slope induces loess spoil damage in a progressive multi-stage receding manner. This study provides a reference and basis for disaster prevention and warning of spoiled ground in loess areas.
Journal Article
Data-Driven Deep Learning-Based Attention Mechanism for Remaining Useful Life Prediction: Case Study Application to Turbofan Engine Analysis
Accurately predicting the remaining useful life (RUL) of the turbofan engine is of great significance for improving the reliability and safety of the engine system. Due to the high dimension and complex features of sensor data in RUL prediction, this paper proposes four data-driven prognostic models based on deep neural networks (DNNs) with an attention mechanism. To improve DNN feature extraction, data are prepared using a sliding time window technique. The raw data collected after normalizing is simply fed into the suggested network, requiring no prior knowledge of prognostics or signal processing and simplifying the proposed method’s applicability. In order to verify the RUL prediction ability of the proposed DNN techniques, the C-MAPSS benchmark dataset of the turbofan engine system is validated. The experimental results showed that the developed long short-term memory (LSTM) model with attention mechanism achieved accurate RUL prediction in both scenarios with a high degree of robustness and generalization ability. Furthermore, the proposed model performance outperforms several state-of-the-art prognosis methods, where the LSTM-based model with attention mechanism achieved an RMSE of 12.87 and 11.23 for FD002 and FD003 subset of data, respectively.
Journal Article
Development and validation of warning system of ventricular tachyarrhythmia in patients with heart failure with heart rate variability data
Implantable-cardioverter defibrillators (ICD) detect and terminate life-threatening ventricular tachyarrhythmia with electric shocks after they occur. This puts patients at risk if they are driving or in a situation where they can fall. ICD's shocks are also very painful and affect a patient's quality of life. It would be ideal if ICDs can accurately predict the occurrence of ventricular tachyarrhythmia and then issue a warning or provide preventive therapy. Our study explores the use of ICD data to automatically predict ventricular arrhythmia using heart rate variability (HRV). A 5 minute and a 10 second warning system are both developed and compared. The participants for this study consist of 788 patients who were enrolled in the ICD arm of the Sudden Cardiac Death-Heart Failure Trial (SCD-HeFT). Two groups of patient rhythms, regular heart rhythms and pre-ventricular-tachyarrhythmic rhythms, are analyzed and different HRV features are extracted. Machine learning algorithms, including random forests (RF) and support vector machines (SVM), are trained on these features to classify the two groups of rhythms in a subset of the data comprising the training set. These algorithms are then used to classify rhythms in a separate test set. This performance is quantified by the area under the curve (AUC) of the ROC curve. Both RF and SVM methods achieve a mean AUC of 0.81 for 5-minute prediction and mean AUC of 0.87-0.88 for 10-second prediction; an AUC over 0.8 typically warrants further clinical investigation. Our work shows that moderate classification accuracy can be achieved to predict ventricular tachyarrhythmia with machine learning algorithms using HRV features from ICD data. These results provide a realistic view of the practical challenges facing implementation of machine learning algorithms to predict ventricular tachyarrhythmia using HRV data, motivating continued research on improved algorithms and additional features with higher predictive power.
Journal Article
Gearbox Condition Monitoring and Diagnosis of Unlabeled Vibration Signals Using a Supervised Learning Classifier
Data-based equipment fault detection and diagnosis is an important research area in the smart factory era, which began with the Fourth Industrial Revolution. Steel manufacturing is a typical processing industry, and efficient equipment operation can improve product quality and cost. Steel production systems require precise control of the equipment, which is a complex process. A gearbox transmits power between shafts and is an essential piece of mechanical equipment. A gearbox malfunction can cause serious problems not only in production, quality, and delivery but in safety. Many researchers are developing methods for monitoring gearbox condition and for diagnosing failures in order to resolve problems. In most data-driven methods, the analysis data set is derived from a distribution of identical data with failure mode labels. Industrial sites, however, often collect data without information on the failure type or failure status due to varying operating conditions and periodic repair. Therefore, the data sets not only include frequent false alarms, but they cannot explain the causes of the alarms. In this paper, a framework called the Reduced Lagrange Method (R-LM) periodically assigns pseudolabels to vibration signals collected without labels and creates an input data set. In order to monitor the status of equipment and to diagnose failures, the input data set is fed into a supervised learning classifier. To verify the proposed method, we build a test rig using motors and gearboxes that are used on production sites in order to artificially simulate defects in the gears and to operate them to collect vibration data. Data features are extracted from the frequency domain and time domain, and pseudolabeling is applied. There were fewer false alarms when applying R-LM, and it was possible to explain which features were responsible for equipment status changes, which improved field applicability. It was possible to detect changes in equipment conditions before a catastrophic failure, thus providing meaningful alarm and warning information, as well as further promising research topics.
Journal Article
Automatic detection of earthquake-induced ground failure effects through Faster R-CNN deep learning-based object detection using satellite images
The seismically induced ground failure is defined as any earthquake-generated process that leads to deformations within a soil medium, which in turn results in permanent horizontal or vertical displacements of the ground surface. As a result, relative movements occur on the ground and structures affected by these movements and thus they may be damaged. Determining earthquake-induced ground failure areas is important to carry out damage assessment studies more quickly and reliably and to prevent more destructive damages. Large earthquake-induced ground failure areas or limited access to the areas due to earthquake causes costly and unsafe fieldwork. Using satellite photographs, earthquake-induced ground failure areas can be easily and reliably detected and the fieldwork can be planned quickly. This study aimed at determining the postearthquake-induced ground failure areas and buildings or structures partially ruined (damaged) by using a deep learning-based object detection method, using Google Earth satellite images after an earthquake. The data set obtained after the earthquake occurred in the 2018 Palu region of Indonesia was used. This data set is divided into two parts for training and test areas. A descriptive approach is considered for detecting the earthquake-induced ground failure areas and damaged structures from collected images from Google Earth software using satellite photographs, using a pretrained Faster R-CNN. To demonstrate the effectiveness of the proposed method, the data set was first created with Google Earth Pro software and it was generated with 392 images for the earthquake-induced ground failure area and 223 images for the damaged area with a resolution of 1024 × 600 pixels. The analyses were carried out by taking into account different image scales. As a result of the analyses, it was concluded that the earthquake-induced ground failure effects (liquefied soil) and damaged structures can be detected to a large extent by using object detection-based deep learning methods.
Journal Article
Weibull and Generalized Extreme Value Distributions for Wind Speed Data Analysis of Some Locations in India
Wind velocity data modeling plays a crucial role for the estimation of wind load and wind energy. Apart from these, the same modeling must also be used in the load cycle analysis of fatigue failure in slender structures to address periodic vortex shedding. Most authors fitted the entire available range of wind velocities of various locations using Weibull models. However, they did not check the validity of the model in describing the range of extreme wind velocity. In this work, the validity of Weibull models for describing parent as well as extreme hourly mean wind velocity data for four places on the east coast of India has been checked. While it predicts lower wind speeds accurately, the Weibull model has been found to become inappropriate for describing wind velocity in the range of extremes, i.e., above a certain threshold value. Therefore, this article focuses on the techniques of determining a limiting wind velocity beyond which the Weibull distribution is rendered unsuitable. In the range where the Weibull distribution fails, various extreme value distributions, such as Gumbel, Fréchet and reverse Weibull distributions have been compared, thereby determining the best estimator for each location.
Journal Article
Fault diagnosis and prognosis of steer-by-wire system based on finite state machine and extreme learning machine
In this paper, an integrated condition monitoring method combining model-based fault diagnosis and data-driven prognosis is proposed for steer-by-wire (SBW) system. First, the SBW system is modeled by bond graph (BG) technique and a two-degree-of-freedom (2-DOF) state-space model of the vehicle is built. Based on the 2-DOF model, the estimated self-aligning torque is used for the control of feedback motor. The fault detection is carried out by evaluating the analytical redundancy relations derived from the BG model. Since the fault isolation performance is essential to subsequent fault estimation process, a new fault isolation method based on finite state machine is developed to improve the isolation ability by combining the dependent and independent analytical redundancy relations, where the number of potential faults could be decreased. In order to refine the possible fault set to determine the true fault, a cuckoo search (CS)–particle filter is developed for fault estimation. Based on the estimated true fault, prognosis can be implemented which is important to achieve failure prevention and prolong system lifespan. To this end, an optimized extreme learning machine (OELM) is proposed where the input weights and hidden layer biases are optimized by CS. Based on data representing fault values obtained from the fault identification, the OELM model is trained for remaining useful life prediction of failing component. Finally, the proposed methodologies are validated by simulations.
Journal Article