Lucas D. Simões

Universidade Federal de Pelotas

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Trends

Author Order

Document Type

Co-Authors

Rodrigo P. Medeiros

Universidade Federal do Rio Grande do Norte

Flávio B. Costa

Michigan Technological University

Hagi Jakobson Dantas da Costa

Universidade Federal do Rio Grande do Norte

Matheus N. O. Aires

Universidade Federal do Rio Grande do Norte

Bruna Liberato Souza

Universidade Federal do Rio Grande do Norte

Fernanda S. de Sousa

Universidade Federal de São Paulo

Thaís Larré Oliveira

Universidade Federal de Pelotas

Noah Robertson

University of South Carolina

Luke R. Jordan

University of Illinois Chicago

Camila Bonemann Bender

Universidade Federal de Pelotas

Cooperative Institutions

University of Illinois Urbana-Champaign

Universidade Federal de Pelotas

Universidade Federal do Rio Grande do Norte

University of Illinois Chicago

Therapeutics Clinical Research

University of Illinois System

Urbana University

Universidade Federal de São Paulo

Albion College

Universidade Federal Rural do Semi-Árido

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Field

A power transformer differential protection based on support vector machine and wavelet transform

Electric Power Systems Research (2021)

Lucas D. Simões Hagi Jakobson Dantas da Costa Matheus N. O. Aires Rodrigo P. Medeiros Flávio B. Costa

Differential protection

10.1016/j.epsr.2021.107297

Cite

Citations (22)

Evaluation of Restricted Earth-Fault Transformer Differential Protection Schemes Through an Experimental Test Bench

Rodrigo P. Medeiros Lucas D. Simões Flávio B. Costa

This paper presents an experimental test bench for generating events and faults in a three-phase transformer assembled in a laboratory for the purpose of validating performance of two restricted earth-fault (REF) differential protection algorithms: a conventional method, based on phasors; and a high-frequency-components-based algorithm, which uses the wavelet transform. The high-frequency-based method performed well, detecting all faults rapidly, whereas the phasor-based method failed to detect the fault during a transformer energization event, besides to presenting greater delays than wavelet-based one. The results indicate the feasibility of the experimental test bench in generate representative cases to the validation of existing restricted earth-fault transformer differential protection schemes.

Test bench

Differential protection

10.1109/wcnps60622.2023.10345046

Cite

Citations (1)

A Power Transformer Event Classification Technique Based on Support Vector Machine

Lucas D. Simões Bruna Liberato Souza Hagi Jakobson Dantas da Costa Rodrigo P. Medeiros V. S. Orivaldo

Currently, different artificial intelligence techniques have been applied in power transformer protection purposes to discriminate internal faults from inrush currents and other disturbances. This paper proposes the application of a support vector machine (SVM) algorithm, for distinguishing among internal faults, external faults, and transformer energizations in a power transformer. The event classifier is enabled through a disturbance detector, hence receiving as input features the first post-fault boundary wavelet differential energies, which are processed by the classifier during the training and set stages. Simulations of a 100 MVA rated power transformer using the Alternative Transients Program (ATP) were carried out. Hence considering a wide variety of the fault parameters, a performance analysis of the SVM classifier regarding the overall accuracy and the time of operation in discriminating the events was accomplished, and promising results were achieved.

Inrush current

Differential protection

10.1109/wcnps50723.2020.9263773

Cite

Citations (2)

Uma Bancada Experimental para Geração de Eventos em Transformadores de Potência

Congresso Brasileiro de Automática (2022)

Rodrigo P. Medeiros Lucas D. Simões Flávio B. Costa

This work presents an experimental test bench for generating representative distur- bances in a transformer. The experimental configuration uses a 1 kVA three-phase transformer with accessible taps in its windings to generate turn-to-turn and turn-to-ground faults. Further- more, external faults and transformer energizations in the presence and absence of permanent faults were also generated in this experiment. The records of the evaluated events are exported from the oscilloscopes to be evaluated in an offline way in a MATLAB® environment. The performance of the conventional differential protection unit (87T) is evaluated for these real cases. The consistent results highlight the feasibility of using the experimental setup as a valuable step for validating transformer differential protection schemes.

Test bench

10.20906/cba2022/3237

Cite

Citations (0)

A Proposed Methodology for Online Implementation of a Support Vector Machine With Applications in Power Transformers Event Classification

Anais do Congresso Brasileiro de Automática 2020 (2020)

Hagi Jakobson Dantas da Costa Bruna Liberato Souza Lucas D. Simões Matheus N. O. Aires Rodrigo P. Medeiros

The constant evolution of resources in computational processing and machine learning algorithms, combined with the increasing complexity of embedded systems, made the hardware implementation of machine learning models more viable. This paper proposes a methodology for online implementation of a support vector machine classifier through the development of a simple, concise, and easily adapted algorithm for data classification. The system was validated through the development of an application that classifies disturbances in a power transformer, followed by a comparison with the results obtained with the Library for Support Vector Machines (LIBSVM). Besides the very similar results when compared with the LIBSVM, the proposed methodology achieved high overall accuracy and fast classification time.

Relevance vector machine

10.48011/asba.v2i1.1105

Cite

Citations (0)

Oncopig bladder cancer cells recapitulate human bladder cancer treatment responses in vitro

Frontiers in Oncology (2024)

Natália Vieira Segatto Lucas D. Simões Camila Bonemann Bender Fernanda S. de Sousa Thaís Larré Oliveira

Introduction Bladder cancer is a common neoplasia of the urinary tract that holds the highest cost of lifelong treatment per patient, highlighting the need for a continuous search for new therapies for the disease. Current bladder cancer models are either imperfect in their ability to translate results to clinical practice (mouse models), or rare and not inducible (canine models). Swine models are an attractive alternative to model the disease due to their similarities with humans on several levels. The Oncopig Cancer Model has been shown to develop tumors that closely resemble human tumors. However, urothelial carcinoma has not yet been studied in this platform. Methods We aimed to develop novel Oncopig bladder cancer cell line (BCCL) and investigate whether these urothelial swine cells mimic human bladder cancer cell line (5637 and T24) treatment-responses to cisplatin, doxorubicin, and gemcitabine in vitro. Results Results demonstrated consistent treatment responses between Oncopig and human cells in most concentrations tested (p>0.05). Overall, Oncopig cells were more predictive of T24 than 5637 cell therapeutic responses. Microarray analysis also demonstrated similar alterations in expression of apoptotic (GADD45B and TP53INP1) and cytoskeleton-related genes (ZMYM6 and RND1) following gemcitabine exposure between 5637 (human) and Oncopig BCCL cells, indicating apoptosis may be triggered through similar signaling pathways. Molecular docking results indicated that swine and humans had similar Dg values between the chemotherapeutics and their target proteins. Discussion Taken together, these results suggest the Oncopig could be an attractive animal to model urothelial carcinoma due to similarities in in vitro therapeutic responses compared to human cells.

10.3389/fonc.2024.1323422

Cite

Citations (1)

Experimental Test Bench for Power Transformer Differential Protection Testing Methods Evaluation

2021 IEEE Power & Energy Society General Meeting (PESGM) (2023)

Rodrigo P. Medeiros Lucas D. Simões Flávio B. Costa

This paper presents an experimental test bench for generating disturbances in a transformer to validate power transformer differential protection methods. The experimental setup uses a 1 kVA three-phase transformer with accessible taps in its windings to generate challenging inter-turn faults. Moreover, external faults and transformer energizations with and without a permanent fault were also generated in this experiment. This paper evaluates the performance of traditional phasor-based and wavelet-based differential protection methods with representative transformer events obtained in the laboratory. Both methods performed well. However, the wavelet-based method was the fastest, even considering a high level of noise. The coherent results highlight the feasibility of using the experimental setup as a valuable step for validating differential protection methods based on the ampere-turn balance.

Test bench

10.1109/pesgm52003.2023.10253180

Cite

Citations (1)