An Adaptive Modeling Framework for Bearing Failure Prediction

Rolling element bearings are a common component in rotating equipment, a class of machines that is essential in a wide range of industries. Detecting and predicting bearing failures is then vital for reducing maintenance and production costs due to unplanned downtime. In previous literature, significant efforts have been devoted to building data-driven health models from historical bearing data. However, a common limitation is that these methods are typically tailored to specific failure instances and have limited ability to model bearing failures between repairs in the same system. In this paper, we propose a multi-state health model to predict bearing failures before they occur. The model employs a regression-based method to detect health state transition points and applies an exponential random coefficient model with a Bayesian updating process to estimate time-to-failure distributions. A model training framework is also introduced to make our proposed model applicable to more bearing instances in the same system setting. The proposed method has been tested on a publicly available bearing prognostics dataset. Case study results show that the proposed method provides accurate failure predictions across several system failures, and that the training approach can significantly reduce the time necessary to generate an effective, generalized model.

The Business Failure Prediction Using Statistical Approach

The topic of business failure is important because it can be used as a basis for policy making by stakeholders in a company or government. The results of business failure predictions can be used as company managers to take preventive measures for business failure. This study aim is to study the literature regarding the methods and results of predicting business failure from various sectors and regions. We used PRISMA (preferred reporting items for systematic reviews and meta-analyses) for conducting this research. As the result, we found twelve statistical methods for business failure prediction, including Hybrid Failure Prediction (HFP), Altman’s Z-score Model, Data Envelopment Analysis (DEA), Logistic Regression (LR), Neural Networks (NN), Support Vector Machine (SVM), Kernel Fuzzy C-Means (KFCM), IN01, IN05, Ohlson Model, Cart-Based Model and Cash-Flow-Based Measures. The highest result obtained by using cart-based model for dataset of financial indicators of Slovak companies with 92,00% accuracy.

The challenges of predicting pipe failures in clean water networks: a view from current practice

Pipe failure models can aid proactive management decisions and help target pipes in need of preventative repair or replacement. Yet, there are several uncertainties and challenges that arise when developing models, resulting in discord between failure predictions and those observed in the field. This paper aims to raise awareness of the main challenges, uncertainties, and potential advances discussed in key themes, supported by a series of semi-structured interviews undertaken with water professionals. The main discussion topics include data management, data limitations, pre-processing difficulties, model scalability and future opportunities and challenges. Improving data quality and quantity is key in improving pipe failure models. Technological advances in the collection of continuous real-time data from ubiquitous smart networks offer opportunities to improve data collection, whilst machine learning and data analytics methods offer a chance to improve future predictions. In some instances, technological approaches may provide better solutions to tackling short term proactive management. Yet, there remains an opportunity for pipe failure models to provide valuable insights for long-term rehabilitation and replacement planning.

Framework for Predicting Failure in Polymeric Unidirectional Composites through Combined Experimental and Computational Mesoscale Modeling Techniques

As composites continue to be increasingly used, finite element material models that homogenize the composite response become the only logical choice as not only modeling the entire composite microstructure is computationally expensive but obtaining the entire suite of experimental data to characterize deformation and failure may not be possible. The focus of this paper is the development of a modeling framework where plasticity, damage, and failure-related experimental data are obtained for each composite constituent. Mesoscale finite elements models consisting of multiple repeating unit cells are then generated and used to represent a typical carbon fiber/epoxy resin unidirectional composite to generate the complete principal direction stress-strain curves. These models are subjected to various uniaxial states of stress and compared with experimental data. They demonstrate a reasonable match and provide the basic framework to completely define the composite homogenized material model that can be used as a vehicle for failure predictions.

An Ensemble Learning Solution for Predictive Maintenance of Wind Turbines Main Bearing

A novel and innovative solution addressing wind turbines’ main bearing failure predictions using SCADA data is presented. This methodology enables to cut setup times and has more flexible requirements when compared to the current predictive algorithms. The proposed solution is entirely unsupervised as it does not require the labeling of data through work orders logs. Results of interpretable algorithms, which are tailored to capture specific aspects of main bearing failures, are merged into a combined health status indicator making use of Ensemble Learning principles. Based on multiple specialized indicators, the interpretability of the results is greater compared to black-box solutions that try to address the problem with a single complex algorithm. The proposed methodology has been tested on a dataset covering more than two year of operations from two onshore wind farms, counting a total of 84 turbines. All four main bearing failures are anticipated at least one month of time in advance. Combining individual indicators into a composed one proved effective with regard to all the tracked metrics. Accuracy of 95.1%, precision of 24.5% and F1 score of 38.5% are obtained averaging the values across the two windfarms. The encouraging results, the unsupervised nature and the flexibility and scalability of the proposed solution are appealing, making it particularly attractive for any online monitoring system used on single wind farms as well as entire wind turbine fleets.

Calculation of displacements and internal forces of anchored retaining piles

Pile-anchor retaining structures are widely used in excavation engineering. The evaluation of lateral displacements, the internal forces of piles are extremely important for the performance of the structure. Most of the existing methods are empirical, semiempirical or FEM methods, while analytic calculation methods for this evaluation are rare. This paper presents an analytic method to calculate the displacements and internal forces of anchored retaining piles based on the existing design code. In the calculation method, the singular function is applied to evaluate the effect of segmented loading on the deflection of a beam with a nonuniform cross section. The load concentration function, expressed by the singular function, can describe the segmented load and be integrated without a complicated procedure for determining the integral constants. The method is applied to a structure in Wenzhou, China, and the calculation results are compared to the field measurement results. This method is only valid for pre-failure predictions.

Predicting failures in electronic water taps in rural sub-Saharan African communities: an LSTM-based approach

There is a growing need to sustain solar-powered water taps in most parts of the sub-Saharan Africa. The frequent failure of the water taps gives rise to intermittent water supply and poor service delivery by the water service providers. The challenge is to foresee and predict the failure of these water systems before they occur. This study develops a scalable machine-learning model for failure prediction in electronic water taps to ensure timely maintenance of the taps. Specifically, we develop a model based on long short-term memory (LSTM) to efficiently make failure predictions with noisy heterogeneous time-series data from rural water taps. Results from the experiment prove that the proposed model can effectively classify activities and patterns in various time-series datasets. With the proposed model, the failures of the solar-powered taps due to abnormal events can be successfully predicted well in advance, with an accuracy of 78.54%. Based on the data analyses, common causes of failures are presented.

Anisotropic Wellbore Stability Analysis: Impact on Failure Prediction

Shale formations are the main source of borehole stability problems during drilling operations. Suboptimal predictions of borehole failure may partly be caused by neglecting the anisotropic nature of shales: Conventional wellbore stability analysis is based on borehole stresses computed from isotropic linear elasticity (Kirsch solution) with the assumption of no induced pore pressure. This is very convenient for a practical implementation but does not always work for shales. Here, anisotropic wellbore stability analysis was performed targeting an offshore gas field to investigate in particular the impact of elastic anisotropy on borehole failure predictions. Stress concentration around a circular borehole in anisotropic shale was calculated by the Amadei solutions, and induced pore pressure was obtained from the Skempton parameters based on anisotropic poroelasticity. Borehole failure regions and modes were then predicted using the effective stresses and those are apparently consistent with observations. A comparison with the conventional approach suggests the importance of accounting for elastic anisotropy: Predicted failure regions, modes, and also the associated mud weight limits can be completely different. This observation may have significant implications for other fields since shale often show strong elastic anisotropy.

Fracture Behavior of Heavily Cross-Linked Epoxy: Testing, Fractography, and Numerical Modeling

Heavily cross-linked epoxy was characterized under different types of loading. The scope of work involves detailed testing procedures utilizing high-precision digital image correlation (DIC) system for all strain measurements. Fractographic analyses using scanning electron microscopy (SEM) were also provided. Besides, computed tomography (CT) scans were employed to characterize existing manufacturing imperfections, i.e., voids. Numerical modeling using extended finite element method (XFEM) utilizing the actual microstructure is conducted. Testing results and fractographic analyses showed that microvoids led to failure initiation at micro lengths. An unstable fracture behavior dominated the final failure under different types of loading. Global plastic deformation was observed in the case of uniaxial tension, while local plasticity was observed in specimens under three-point loading. It can be concluded that epoxies failure under a combined state of stresses is sophisticated, and straightforward stress/strain-based failure criteria are not well-suited for failure predictions.