Ademir Nied

Dr. Ademir Nied

orcid

Research Focus & Metrics

Academic Career Length

24Years (2003-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
28 April 2021 in IEEE Access
Verified
Journal Article
Open access
Stefano Frizzo StefenonStefano Frizzo Stefenon
Stefano Frizzo Stefenon
Matheus RibeiroMatheus Ribeiro
Matheus Ribeiro
ANAdemir Nied
Ademir Nied
Viviana Cocco MarianiViviana Cocco Mariani
Viviana Cocco Mariani
Leandro dos Santos CoelhoLeandro dos Santos Coelho
Leandro dos Santos Coelho
Laio Oriel SemanLaio Oriel Seman
Laio Oriel Seman
Contaminated insulators can have higher surface conductivity, which can result in irreversible failures in the electrical power system. In this paper, the ultrasound equipment is used to assist in the prediction of failure identification in porcelain insulators of the 13.8 kV, 60 Hz pin profile. To perform the laboratory analysis, insulators from a problematic branch are removed after an inspection of the electrical system and are evaluated in the laboratory under controlled conditions. To perform the time series predictions, the stacking ensemble learning model is applied with the wavelet transform for signal filtering and noise reduction. For a complete analysis of the model, variations in its configuration were evaluated. The results of root mean square error (RMSE), mean absolute percentage error (MAPE), mean absolute error (MAE), and coefficient of determination (R 2 ) are presented. To validate the result, a benchmarking is presented with well-established models, such as an adaptive neuro-fuzzy inference system (ANFIS) and long-term short-term memory (LSTM).

5 October 2020 in Energies
Verified
Journal Article
Open access
PDF file
Matheus RibeiroMatheus Ribeiro
Matheus Ribeiro
Stefano Frizzo StefenonStefano Frizzo Stefenon
Stefano Frizzo Stefenon
JLJosé Donizetti de Lima
José Donizetti de Lima
ANAdemir Nied
Ademir Nied
Viviana Cocco MarianiViviana Cocco Mariani
Viviana Cocco Mariani
Leandro dos Santos CoelhoLeandro dos Santos Coelho
Leandro dos Santos Coelho
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.

14 July 2017 in IEEE Transactions on Energy Conversion
Verified
Journal Article
Closed access
LZLi Zhang
Li Zhang
Ying FanYing Fan
Ying Fan
CLChenxue Li
Chenxue Li
ANAdemir Nied
Ademir Nied
Ming ChengMing Cheng
Ming Cheng
This paper presents a fault-tolerant sensorless control strategy based on a wide-speed strong-robustness sliding mode observer (SMO) for a new five-phase fault-tolerant fractional-slot concentrated-winding interior-permanent-magnet (FTFSCW-IPM) motor, in which the motor drive system has a high reliability. The designed motor possesses a high fault-tolerant capacity. Also, the fault-tolerant space vector pulse width modulation (SVPWM) strategy and the sensorless control are adopted to further improve the fault tolerance of the control system. Moreover, unlike the existing SMO, the proposed SMO algorithm can achieve enhanced low system chattering, estimated accuracy at low speed, as well as strong robustness to motor parameters, fault and load disturbance. Numerical simulations and experiments with a 2-kW five-phase FTFSCW-IPM motor are carried out. The results verify the feasibility and effectiveness of the proposed fault-tolerant sensorless method adopted by the FTFSCW-IPM motor.

11 September 2022 in Electrical Engineering
Verified
Journal Article
Closed access
PDF file
Stefano Frizzo StefenonStefano Frizzo Stefenon
Stefano Frizzo Stefenon
Kin-Choong YowKin-Choong Yow
Kin-Choong Yow
ANAdemir Nied
Ademir Nied
LMLuiz Henrique Meyer
Luiz Henrique Meyer

10 October 2017 in IEEE Transactions on Industry Applications
Verified
Journal Article
Closed access
RERaffael Engleitner
Raffael Engleitner
ANAdemir Nied
Ademir Nied
MCMariana Santos Matos Cavalca
Mariana Santos Matos Cavalca
JCJean Patric da Costa
Jean Patric da Costa
When the wind power accounts for a large portion of the islanded microgrid power, it may need to support the ac bus frequency regulation. The increasing penetration of variable speed wind turbines (WT) in microgrids leads to a lower inertia, as the rotational speed of the turbine and the grid are decoupled by power electronic converters. Lower system inertia results in a larger and faster frequency deviation after occurrence of abrupt variations on generation and load. It is possible to implement control loops in the WT converters to provide a virtual inertia and support frequency regulation in the microgrid. This paper investigates the variables related to the frequency compensation capability of WT, such as kinetic energy, dc-link capacitance, turbine size, wind penetration, number of turbines, operating region along the power curve, power reserve and droop control gain, etc. The analysis is structured as a Design of experiment (DOE) to have a clear and organized comparison of multiple system configurations. An optimal control technique is applied to provide fair comparison among the system variables. A flowchart explaining how the DOE and controllers gains were defined is provided.

9 July 2019 in IEEE Transactions on Industrial Electronics
Verified
Journal Article
Closed access
Stefano Frizzo StefenonStefano Frizzo Stefenon
Stefano Frizzo Stefenon
RGRafael Bartnik Grebogi
Rafael Bartnik Grebogi
RFRoberto Zanetti Freire
Roberto Zanetti Freire
ANAdemir Nied
Ademir Nied
LMLuiz Henrique Meyer
Luiz Henrique Meyer
The classification of distinct problems of insulators in the distribution networks is a task that requires operator's experience. The application of techniques to automate the inspection of electrical systems with the objective of detecting faults in insulators have shown to be reasonable alternatives to improve reliability in power grid. Based on the development of an experimental setup, signals were acquired considering three distinct faults in insulators. In this case, 13.8kV (RMS) was applied in drilled, contaminated, and good insulators considering an ultrasound detector connected to a computer. In the sequence, a multiclass classification method was proposed considering the ensemble of classifiers. The method considered the association of five distinct techniques, Bottom-Up segmentation, Wavelet Energy Coefficient (WEC), Principal Component Analysis (PCA), and Particle Swarm Optimization (PSO) associated to Ensemble Extreme Learning Machine (EN-ELM). Named as Optimized Ensemble Extreme Learning Machine (OEN-ELM), the present approach outperforms the original EN-ELM method. Finally, results showed significant increase in robustness and faster training procedure when compared to classical approaches.