Fault diagnosis of insulators from ultrasound detection using neural networks

Stefenon, Stéfano Frizzo; Silva, Marcelo Campos; Bertol, Douglas Wildgrube; Meyer, Luiz Henrique; Nied, Ademir

doi:10.3233/jifs-190013

Cited by 35 publications

(18 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The stochastic gradient descent algorithm can oscillate along the steepest descent path towards the optimum, to solve this, a moment term is added to the parameter update to reduce this oscillation [44]. The LSTM with the SGDM optimizer is a promising algorithm and will be compared in this paper [45].…”

Section: Benchmarkingmentioning

confidence: 99%

Hybrid Wavelet Stacking Ensemble Model for Insulators Contamination Forecasting

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

Section: Benchmarkingmentioning

confidence: 99%

Hybrid Wavelet Stacking Ensemble Model for Insulators Contamination Forecasting

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…In addition to electricity price and load forecasting, the use of artificial intelligence is powerful to assess the development of possible failures in the electrical system [29]. As presented by Stefenon et al [30], the use of the wavelet transform reduces signal noise, improving the analysis of chaotic time signals.…”

Section: Related Workmentioning

confidence: 99%

Electricity Price Forecasting Based on Self-Adaptive Decomposition and Heterogeneous Ensemble Learning

et al. 2020

Self Cite

View full text Add to dashboard Cite

Electricity price forecasting plays a vital role in the financial markets. This paper proposes a self-adaptive, decomposed, heterogeneous, and ensemble learning model for short-term electricity price forecasting one, two, and three-months-ahead in the Brazilian market. Exogenous variables, such as supply, lagged prices and demand are considered as inputs signals of the forecasting model. Firstly, the coyote optimization algorithm is adopted to tune the hyperparameters of complementary ensemble empirical mode decomposition in the pre-processing phase. Next, three machine learning models, including extreme learning machine, gradient boosting machine, and support vector regression models, as well as Gaussian process, are designed with the intent of handling the components obtained through the signal decomposition approach with focus on time series forecasting. The individual forecasting models are directly integrated in order to obtain the final forecasting prices one to three-months-ahead. In this case, a grid of forecasting models is obtained. The best forecasting model is the one that has better generalization out-of-sample. The empirical results show the efficiency of the proposed model. Additionally, it can achieve forecasting errors lower than 4.2% in terms of symmetric mean absolute percentage error. The ranking of importance of the variables, from the smallest to the largest is, lagged prices, demand, and supply. This paper provided useful insights for multi-step-ahead forecasting in the electrical market, once the proposed model can enhance forecasting accuracy and stability.

show abstract

“…The scenarios considered the reductions in final energy consumption per capita for a given area of the city, based on intelligent energy measurements [120]. More recent studies have applied the proposed index to 12 cities in Southeastern Europe and 26 global cities, including Rio de Janeiro, to compare the performance related to SDEWES [121,122].…”

Section: Sustainable Development Of Energy Water and Environment Symentioning

confidence: 99%

Tools for Measuring Energy Sustainability: A Comparative Review

et al. 2020

Self Cite

View full text Add to dashboard Cite

This paper is intended to perform a comparative and qualitative review among eight tools to measure energy sustainability. Therefore, it was necessary to create a theoretical and conceptual framework based on four criterias of selection and six categories of comparison. In this work, the conceptual bases that supported the research and the methodology created to carry out the comparative review will be presented. This analysis was based on the intrinsic concepts of energy sustainability of each of the reviewed tools with a critical qualitative analysis. Some conclusions shown through the conceptual framework developed that it was possible to apply an innovative methodology to qualitatively compare different tools to measure sustainability. The importance of this reflects the difficulty of conceptualizing the subjectivity of sustainable development, as shown throughout the paper, where it is often not possible to obtain a measurable result since the measured phenomenon is too complex to reduce it to a numerical value.

show abstract

Fault diagnosis of insulators from ultrasound detection using neural networks

Cited by 35 publications

References 25 publications

Hybrid Wavelet Stacking Ensemble Model for Insulators Contamination Forecasting

Hybrid Wavelet Stacking Ensemble Model for Insulators Contamination Forecasting

Electricity Price Forecasting Based on Self-Adaptive Decomposition and Heterogeneous Ensemble Learning

Tools for Measuring Energy Sustainability: A Comparative Review

Contact Info

Product

Resources

About