This paper presents a novel method for diagnosing incipient bearing defects under variable operating speeds using convolutional neural networks (CNNs) trained via the stochastic diagonal Levenberg-Marquardt (S-DLM) algorithm. The CNNs utilize the spectral energy maps (SEMs) of the acoustic emission (AE) signals as inputs and automatically learn the optimal features, which yield the best discriminative models for diagnosing incipient bearing defects under variable operating speeds. The SEMs are two-dimensional maps that show the distribution of energy across different bands of the AE spectrum. It is hypothesized that the variation of a bearing’s speed would not alter the overall shape of the AE spectrum rather, it may only scale and translate it. Thus, at different speeds, the same defect would yield SEMs that are scaled and shifted versions of each other. This hypothesis is confirmed by the experimental results, where CNNs trained using the S-DLM algorithm yield significantly better diagnostic performance under variable operating speeds compared to existing methods. In this work, the performance of different training algorithms is also evaluated to select the best training algorithm for the CNNs. The proposed method is used to diagnose both single and compound defects at six different operating speeds.

Incipient defects in bearings are traditionally diagnosed either by developing discriminative models for features that are extracted from raw acoustic emission (AE) signals, or by detecting peaks at characteristic defect frequencies in the envelope power spectrum of the AE signals. Under variable speed conditions, however, such methods do not yield the best results. This letter proposes a technique for diagnosing incipient bearing defects under variable speed conditions, by extracting features from different sub-bands of the inherently non-stationary AE signal, and then classifying bearing defects using a weighted committee machine, which is an ensemble of support vector machines and artificial neural networks. The proposed method also improves the generalization performance of the neural networks to enhance their classification accuracy, particularly with limited training data.

The purpose of this study is to characterize fracture modes in a concrete structure using an acoustic emission (AE) technique and a data-driven approach. To clarify the damage fracture process, the specimens, which are of reinforced concrete (RC) beams, undergo four-point bending tests. During bending tests, impulses occurring in the AE signals are automatically detected using a constant false-alarm rate (CFAR) algorithm. For each detected impulse, its acoustic emission parameters such as counts, duration, amplitude, risetime, energy, RA, AF are calculated and studied. The mean and standard deviation values of each of these parameters are computed in every 1-s AE signal and are considered as features demonstrating the damage status of concrete structures. The results revealed that as the damage level in concrete structures grows, these features also change accordingly which can be used to categorize the damage fracture stages. The study also carries out experiments to validate the efficiency of the proposed approaches in terms of visual and qualitative evaluations. Experimental results show that the proposed characterizing model is promising and outstanding with the classification performance in the experimental environment of over 82%.

This letter proposes an efficient scheme for the early diagnosis of bearing defects using a convolutional neural network (CNN) and energy distribution maps (EDMs) of acoustic emission spectra. The ...

Incomplete data is the most common but tricky problem for data-driven energy and building solutions. Due to sensor errors or communication failures, raw building data with missing data points are rarely satisfactory for fault detection and diagnosis (FDD) applications. In this paper, a new framework named a deep variational mixture of principal component analyzers (DV-MPPCA) is proposed to address the building FDD problem with incomplete data. DV-MPPCA is the combination of a variational autoencoder (VAE) model for data compression and a mixture of principal component analyzers (MPPCA) for density estimation. To construct an integrated framework comprising both VAE and MPPCA, we introduce a novel methodology that represents the algebraic model of MPPCA within the architecture of a neural network. This innovative architecture undergoes optimization through the minimization of a designated loss function. Subsequently, the refined and optimized framework is harnessed as an unsupervised fault detection model for a real-world air handling unit (AHU) system designed by the ASHRAE research project 1312 (RP-1312). Furthermore, by incorporating the modified evidence lower bound (ELBO) loss function within the VAE, the resulting DV-MPPCA framework exhibits exceptional performance when confronted with incomplete AHU datasets, even with high missing rates. Empirical findings substantiate the supremacy of DV-MPPCA over other contemporary classic and deep models. Impressively, even with a missing rate as modest as 10%, DV-MPPCA consistently delivers outstanding performance, achieving F1-scores of 98.10%, 93.50%, and 81.57% for the Summer, Winter, and Spring datasets, respectively. Note to Practitioners —This article was motivated by the fact that raw building data with missing data points are not qualitative enough for direct use in fault detection and diagnosis (FDD) applications. To resolve this problem, existing studies manipulated imputation algorithms in the preprocessing step to prepare the data for constructing FDD models and impute missing points in test instances during the online monitoring process. However, this step makes an overall FDD framework cumbersome. Therefore, instead of utilizing a data imputation method as a separately operating model, we adopt VAE in our framework to exclude the contribution of missing points during the offline modeling and online monitoring processes. This modification of VAE helps our framework be immune to incomplete data. For reproducibility and future improvement by other researchers, the complete source code of this study is provided in the following repository: https://github.com/viettra-xai/DV-MPPCA.