Failure Severity Prediction for Protective-Coating Disbondment via the Classification of Acoustic Emission Signals.

Structural health monitoring is a popular inspection method that utilizes acoustic emission (AE) signals for fault detection in engineering infrastructures. Diagnosis based on the propagation of AE signals along any surface material offers an attractive solution for fault identification. However, the classification of AE signals originating from failure events, especially coating failure (coating disbondment), is a challenging task given the AE signature of each material. Thus, different experimental settings and analyses of AE signals are required to classify the various types of coating failures, and they are time-consuming and expensive. Hence, to address these issues, we utilized machine learning (ML) classification models in this work to evaluate epoxy-based-protective-coating disbondment based on the AE principle. A coating disbondment experiment consisting of coated carbon steel test panels for the collection of AE signals was implemented. The obtained AE signals were then processed to construct the final dataset to train various state-of-the-art ML classification models to divide the failure severity of coating disbondment into three classes. Consequently, methods for the extraction of useful features, the handling of data imbalance, and a reduction in the bias of ML models were also effectively utilized in this study. Evaluations of state-of-the-art ML classification models on the AE signal dataset in terms of standard metrics revealed that the decision forest classification model outperformed the other state-of-the-art models, with accuracy, precision, recall, and F1 score values of 99.48%, 98.76%, 97.58%, and 98.17%, respectively. These results demonstrate the effectiveness of utilizing ML classification models for the failure severity prediction of protective-coating defects via AE signals.

Prevalence and Associated Factors of Diabetic Retinopathy among Type 2 Diabetes Mellitus Patients in Brunei Darussalam: A Cross-sectional Study.

PURPOSE: To determine the prevalence of diabetic retinopathy (DR) and the factors associated with retinopathy among type 2 diabetes mellitus (DM) patients in Brunei Darussalam. METHODS: Cross-sectional study of all type 2 DM patients who attended diabetic eye screening over a 3-month period at one of four government hospitals. We assessed association between DR with the following variables: age, sex, glycated hemoglobin (HbA1c), duration of DM, hypertension, hyperlipidemia, and microalbuminuria. RESULTS: There were 341 patients (female, 58.9%; mean age, 55.3 ± 11.9 years) with a mean duration of DM of 9.4 ± 7.4 years and mean serum HbA1c of 8.4% ± 1.9%. The overall prevalence of any DR was 22.6% (95% confidence interval, 18.8-27.1) with prevalence rates of 4.1% (95% confidence interval, 2.1-6.4) for proliferative DR and 9.7% (95% confidence interval, 6.8-13.2) for vision-threatening DR. Multivariate analysis showed that DR was significantly associated with certain age groups (reduced in older age groups), longer duration of DM (11 years or more), poor control (HbA1c >9.0%) and presence of any microalbuminuria. CONCLUSIONS: DR affects one in five patients with DM in Brunei Darussalam, comparable to rates reported for other Asian populations. It is especially worrying that one in ten patients with DM had vision-threatening DR. DR was significantly associated with longer duration of DM, poor control and presence of microalbuminuria but reduced in older age groups. It is important to advocate good control right from the time of diagnosis of DM and institute timely and effective management of retinopathy. DR was significantly associated with longer duration of DM, poor control of diabetes, and presence of microalbuminuria but reduced in older age groups.

Acoustic emission corrosion feature extraction and severity prediction using hybrid wavelet packet transform and linear support vector classifier.

Corrosion in carbon-steel pipelines leads to failure, which is a major cause of breakdown maintenance in the oil and gas industries. The acoustic emission (AE) signal is a reliable method for corrosion detection and classification in the modern Structural Health Monitoring (SHM) system. The efficiency of this system in detection and classification mainly depends on the suitable AE features. Therefore, many feature extraction and classification methods have been developed for corrosion detection and severity assessment. However, the extraction of appropriate AE features and classification of various levels of corrosion utilizing these extracted features are still challenging issues. To overcome these issues, this article proposes a hybrid machine learning approach that combines Wavelet Packet Transform (WPT) integrated with Fast Fourier Transform (FFT) for multiresolution feature extraction and Linear Support Vector Classifier (L-SVC) for predicting corrosion severity levels. A Laboratory-based Linear Polarization Resistance (LPR) test was performed on carbon-steel samples for AE data acquisition over a different time span. AE signals were collected at a high sampling rate with a sound well AE sensor using AEWin software. Simulation results show a linear relationship between the proposed approach-based extracted AE features and the corrosion process. For multi-class problems, three corrosion severity stages have been made based on the corrosion rate over time and AE activity. The ANOVA test results indicate the significance within and between the feature-groups where F-values (F-value>1) rejects the null hypothesis and P-values (P-value<0.05) are less than the significance level. The utilized L-SVC classifier achieves higher prediction accuracy of 99.0% than the accuracy of other benchmarked classifiers. Findings of our proposed machine learning approach confirm that it can be effectively utilized for corrosion detection and severity assessment in SHM applications.

Unsupervised bivariate data clustering for damage assessment of carbon fiber composite laminates.

Damage assessment is a key element in structural health monitoring of various industrial applications to understand well and predict the response of the material. The big uncertainty in carbon fiber composite materials response is because of variability in the initiation and propagation of damage. Developing advanced tools to design with composite materials, methods for characterizing several damage modes during operation are required. While there is a significant amount of work on the analysis of acoustic emission (AE) from different composite materials and many loading cases, this research focuses on applying an unsupervised clustering method for separating AE data into several groups with distinct evolution. In this paper, we develop an adaptive sampling and unsupervised bivariate data clustering techniques to characterize the several damage initiations of a composite structure in different lay-ups. An adaptive sampling technique pre-processes the AE features and eliminates redundant AE data samples. The reduction of unnecessary AE data depends on the requirements of the proposed bivariate data clustering technique. The bivariate data clustering technique groups the AE data (dependent variable) with respect to the mechanical data (independent variable) to assess the damage of the composite structure. Tensile experiments on carbon fiber reinforced composite laminates (CFRP) in different orientations are carried out to collect mechanical and AE data and demonstrate the damage modes. Based on the mechanical stress-strain data, the results show the dominant damage regions in different lay-ups of specimens and the definition of the different states of damage. In addition, the states of the damage are observed using Scanning Electron Microscope (SEM) analysis. Based on the AE data, the results show that the strong linear correlation between AE and mechanical energy, and the classification of various modes of damage in all lay-ups of specimens forming clusters of AE energy with respect to the mechanical energy. Furthermore, the validation of the cluster-based characterization and improvement of the sensitivity of the damage modes classification are observed by the combined knowledge of AE and mechanical energy and time-frequency spectrum analysis.