A Bidirectional LSTM-Based Prognostication of Electrolytic Capacitor

Kulevome, Delanyo Kwame Bensah; Wang, Hong; Wang, and Xuegang

doi:10.2528/pierc20120201

Cited by 16 publications

(8 citation statements)

References 24 publications

(28 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The implementation of PHM in radar systems is relatively new and challenging due to system complexities [20]. Most researchers have identified the transmitter [21], power supply [22], cooling system [23], and other electronic parts [24,25] as critical for diagnosis and prognosis. As an essential device of APARs, changes in the working parameters of the transmit/receive (T/R) modules directly affect the operation reliability.…”

Section: Phm Implementation In Radar Systemsmentioning

confidence: 99%

A Hierarchical PHM Framework for Phased Array Radar Systems

Kulevome,

Wang,

Zhao

et al. 2023

PIER M

View full text Add to dashboard Cite

Phased array radar (PAR) systems are critical for modern defense and surveillance applications, but their reliability and availability are affected by various factors, including physical and performance degradation. Furthermore, implementing prognostics and health management (PHM) framework for the whole radar system is challenging. To address these issues, this paper proposes an efficient solution by hierarchically implementing PHM frameworks in an active PAR (APAR) system. The proposed framework subsumes device-level, subsystem-level, and system-level health prediction models to enable comprehensive health monitoring and maintenance decision-making. This approach addresses the unique challenges involved in implementing PHM for the APAR system and facilitates the transition from traditional reactive maintenance practices to a predictive maintenance approach, thereby improving the overall system. Mathematical models that relate the radar's physical degradation to its performance deterioration are formulated, analyzed, and presented. Subsequently, a Bayesian long short-term memory (BayesLSTM) architecture is developed and integrated into the proposed framework for estimating the remaining useful life (RUL) of critical devices/subsystems. The effectiveness of the proposed deep learning-based prognostic framework is evaluated through simulations and experimental studies. The proposed hierarchical framework has the potential to be applied to other radar systems that require effective health monitoring strategy.

show abstract

Section: Phm Implementation In Radar Systemsmentioning

confidence: 99%

A Hierarchical PHM Framework for Phased Array Radar Systems

Kulevome,

Wang,

Zhao

et al. 2023

PIER M

View full text Add to dashboard Cite

show abstract

“…The goal of this phase is to apply the NBR formula by using the proposed deep learning model results to assess the reputation of cloud service providers [34]. It also aims to validate the effectiveness of using the proposed deep learning model for reputation assessment.…”

Section: Reputation Assessment and Model Validation Phasementioning

confidence: 99%

CBiLSTM: A Hybrid Deep Learning Model for Efficient Reputation Assessment of Cloud Services

2022

View full text Add to dashboard Cite

The cloud market is characterized by fierce rivalry among cloud service providers. The availability of various services with identical functionalities on the market complicates the selection decision for service requesters. Although objective trust measurements can be used to evaluate the trustworthiness of services, they are not always available and are static in nature. Subjective approaches are not always viable because they often require repeated service invocations to collect client feedback. To overcome these limitations, we propose, in this paper, a reputation-based trust assessment approach that combines the Net Brand Reputation (NBR) measure with a deep learning-based sentiment analysis model using online user reviews. CBiLSTM is the name of the proposed deep learning model that hybridizes the Convolutional Neural Networks (CNN) and the Bidirectional Long Short-Term Memory (BiLSTM) layers. The CNN layers deal with text inputs' high dimensionality, while the BiLSTM layer explores the context of the extracted features in both forward and backward directions. CBiLSTM was trained on a new dataset named CLOSER-DREAM, containing more than 13,000 reviews relating to several emerging cloud services to classify these reviews and assess the overall reputation of the cloud services providers. The results of the series of experiments that were conducted have shown that CBiLSTM outperforms the classic deep learning models with 98% of precision, 99% of recall, 98% as an F1-score, and 99.7% of accuracy. Also, CBiLSTM offered a reasonable training time of about 519ms with the CLOSER-DREAM dataset. The classification obtained by applying CBiLSTM was proven to be an effective method to calculate the NBR measure used for the reputation assessment of cloud service providers. The proposed technique yielded an NBR score of 98.3% for Google cloud services, which is close to the real/actual NBR of 96.25%.

show abstract

“…In recent years, the advancement and implementation of deep learning (DL) in component diagnostics, prognostics [4,5] and image classifications [6−8] has motivated research in the application of such models in bearing fault diagnostics [9,10]. This research aims to leverage the capabilities of a convolutional neural network (CNN), which comprises sequentially composed layers of convolution and pooling operations, in establishing an effective fault classification model.…”

Section: Introductionmentioning

confidence: 99%

Rolling Bearing Fault Diagnostics Based on Improved Data Augmentation and ConvNet

Kulevome,

Wang,

Wang

2023

J. of Syst. Eng. Electron.

Self Cite

View full text Add to dashboard Cite

Convolutional neural networks (CNNs) are well suited to bearing fault classification due to their ability to learn discriminative spectro-temporal patterns. However, gathering sufficient cases of faulty conditions in real-world engineering scenarios to train an intelligent diagnosis system is challenging. This paper proposes a fault diagnosis method combining several augmentation schemes to alleviate the problem of limited fault data. We begin by identifying relevant parameters that influence the construction of a spectrogram. We leverage the uncertainty principle in processing time-frequency domain signals, making it impossible to simultaneously achieve good time and frequency resolutions. A key determinant of this phenomenon is the window function's choice and length used in implementing the shorttime Fourier transform. The Gaussian, Kaiser, and rectangular windows are selected in the experimentation due to their diverse characteristics. The overlap parameter 's size also influences the outcome and resolution of the spectrogram. A 50% overlap is used in the original data transformation, and ±25% is used in implementing an effective augmentation policy to which two-stage regular CNN can be applied to achieve improved performance. The best model reaches an accuracy of 99.98% and a cross-domain accuracy of 92.54%. When combined with data augmentation, the proposed model yields cutting-edge results.

show abstract

A Bidirectional LSTM-Based Prognostication of Electrolytic Capacitor

Cited by 16 publications

References 24 publications

A Hierarchical PHM Framework for Phased Array Radar Systems

A Hierarchical PHM Framework for Phased Array Radar Systems

CBiLSTM: A Hybrid Deep Learning Model for Efficient Reputation Assessment of Cloud Services

Rolling Bearing Fault Diagnostics Based on Improved Data Augmentation and ConvNet

Contact Info

Product

Resources

About