“…Due to the ability to perform multiresolution analysis of vibration signals, this technique has proven to be a powerful tool for feature extraction [9] A fundamental aspect to be considered in condition monitoring systems based on machine learning is the ability of the adopted method to extract representative features, which may be achieved through multiresolution analysis. In the work of Pham et al [10], WPD was used together with a CNN in a bearing diagnostics system. The method proposed by Tobon-Mejia et al [11] extracts features from bearing signals using WPD, which are then processed through hidden Markov models to estimate the RUL of the machine.…”
The prognosis of rotating machinery has been very prominent in recent years thanks to the advances in digital signal processing and intelligent systems. Unsupervised machine learning methods have been adopted along with signal processing techniques in both time and frequency domain to build indicators that describe the degradation of mechanical systems. This paper proposes a novel method for generating a degradation indicator for estimating the remaining useful life of rotating machinery critical components, based on a beta variational autoencoder neural network that processes statistical distributions in a feature hyperspace whose coordinates mix timedomain analysis and wavelet packet decomposition of vibration signals. Indicators are calculated using bearing vibration signals from a publicly available dataset, aiming to enhance the visibility of monotonic trends, and are used to assess different hyperparameter configurations of the proposed methodology. Based on the comparison with recently published results on the same dataset, the proposed method produced robust indicators capable of detecting early changes in degradation models, generating more accurate RUL estimates.
“…Due to the ability to perform multiresolution analysis of vibration signals, this technique has proven to be a powerful tool for feature extraction [9] A fundamental aspect to be considered in condition monitoring systems based on machine learning is the ability of the adopted method to extract representative features, which may be achieved through multiresolution analysis. In the work of Pham et al [10], WPD was used together with a CNN in a bearing diagnostics system. The method proposed by Tobon-Mejia et al [11] extracts features from bearing signals using WPD, which are then processed through hidden Markov models to estimate the RUL of the machine.…”
The prognosis of rotating machinery has been very prominent in recent years thanks to the advances in digital signal processing and intelligent systems. Unsupervised machine learning methods have been adopted along with signal processing techniques in both time and frequency domain to build indicators that describe the degradation of mechanical systems. This paper proposes a novel method for generating a degradation indicator for estimating the remaining useful life of rotating machinery critical components, based on a beta variational autoencoder neural network that processes statistical distributions in a feature hyperspace whose coordinates mix timedomain analysis and wavelet packet decomposition of vibration signals. Indicators are calculated using bearing vibration signals from a publicly available dataset, aiming to enhance the visibility of monotonic trends, and are used to assess different hyperparameter configurations of the proposed methodology. Based on the comparison with recently published results on the same dataset, the proposed method produced robust indicators capable of detecting early changes in degradation models, generating more accurate RUL estimates.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.