Wind_turbine_failure_prediction - GitLite

KO | EN

gitlite — search

#javascript #python #react #go #machine-learning #rust #linux #java #cli #awesome-list #vue #security #pytorch #ios

Wind_turbine_failure_prediction

(★ 96)

Machine learning applied to wind turbines incipient fault detection.

파일 탐색기

최종 버전 다운로드 (.zip)

- - v000_SCIG_SC_SENSORC_FOURIER_010-info.txt
  - v000_SCIG_SC_SENSORC_FOURIER_010.csv
  - v000_SCIG_SC_SENSORC_GOERTZEL_001-info.txt
  - v000_SCIG_SC_SENSORC_GOERTZEL_001.csv
  - v000_SCIG_SC_SENSORC_HOS_001-info.txt
  - v000_SCIG_SC_SENSORC_HOS_001.csv
  - v000_SCIG_SC_SENSORC_SCM_001-info.txt
  - v000_SCIG_SC_SENSORC_SCM_001.csv
- - README.md
- workspace-vscode.code-workspace
- - notebook-01-data-inference.ipynb
  - notebook-02-statistical_test.ipynb
- - __init__.py
  - config.py
  - dataset_concat.py
  - example-01.py
  - Pipfile
  - Pipfile.lock
  - README.md
  - requirements.txt
  - run.sh
  - run_experiment_appended.py
  - run_experiment_union.py
  - save_pipeline_sensora_fourier.py
  - save_pipeline_sensora_hos.py
  - save_pipeline_sensora_scm.py
  - save_pipeline_sensorc_fourier.py
  - save_pipeline_sensorc_hos.py
  - save_pipeline_sensorc_scm.py
  - save_pipeline_sensorv_fourier.py
  - save_pipeline_sensorv_hos.py
  - save_pipeline_sensorv_scm.py
  - save_selector_and_scaler.py
  - test_clf_appended.py
  - test_clf_union.py
  - train_clf.py
  - transforms.py
  - utils.py
- .gitignore
- README.md
.gitignore
Dissertation.pdf
README.md

# 설치 가이드

1. 코드 내려받기

git clone https://github.com/lapisco/Wind_turbine_failure_prediction

깃허브에서 프로젝트 코드 전체를 내 컴퓨터로 내려받습니다.

cd Wind_turbine_failure_prediction

방금 내려받은 프로젝트 폴더 안으로 이동합니다.

2. Python

쉬움 추천

사전 준비물

Git GitHub에서 프로젝트 코드를 내려받으려면 필요합니다.
Python 3 설치 시 'Add Python to PATH' 옵션을 꼭 체크하세요 (Windows).

⚠️ 이 프로젝트는 규모가 큰 저장소라, 이 방법이 실제 핵심 제품이 아니라 내부 하위 패키지를 가리키는 것일 수 있습니다. README 전체를 함께 확인해보세요.

pip install -r paper-02-A_multi-sensor_architecture/src/requirements.txt

requirements.txt 등에 명시된 파이썬 라이브러리를 설치합니다.

jupyter notebook

브라우저에서 노트북(.ipynb) 파일들을 열람하고 실행할 수 있는 Jupyter 화면을 켭니다.

✅ 에러 메시지 없이 실행되고 터미널에 안내 문구가 출력되면 정상입니다.

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# The framework for wind turbine failure prediction

Machine learning applied to wind turbines incipient fault detection. This is a project staterd in my Master's degree and it is core. [The full dissertation is available here](Dissertation.pdf).

> The full text is currently being translated to English. Right now only portuguese is available for the dissertation.

There are a few publications that concerns this project. Some are published and some are in still in revision.
I'll post them out here as soon as they are released.

* 1. [Publications](#Publications)
	* 1.1. [Nascimento *et al*, 2019 - A multi-sensor architecture for robust identificationof incipient short-circuits in wind turbine generators](#Nascimentoetal2019-Amulti-sensorarchitectureforrobustidentificationofincipientshort-circuitsinwindturbinegenerators)
	* 1.2. [Reboucas *et al*, 2018 - A reliable approach for detection of incipient faults of short-circuits in induction generators using machine learning](#Reboucasetal2018-Areliableapproachfordetectionofincipientfaultsofshort-circuitsininductiongeneratorsusingmachinelearning)

##  1. <a name='Publications'></a>Publications

If you intend to use the database or the methodology presented in this paper, please cite the following papers:

Paper 1:

XU, YONGZHAO ; NASCIMENTO, NAVAR MEDEIROS M. ; DE SOUSA, PEDRO H. FEIJÓ ; NOGUEIRA, FABRÍCIO G. ; TORRICO, BISMARK C. ; HAN, TAO ; JIA, CHUANYU ; REBOUÇAS FILHO, PEDRO P. Multi-sensor edge computing architecture for identification of failures short-circuits in wind turbine generators. APPLIED SOFT COMPUTING, v. 101, p. 107053, 2021.

Paper 2:

Pedro Pedrosa Rebouças Filho; GOMES, S. L. ; NASCIMENTO, N. M. M. ; MEDEIROS, C. M. S. ; OUTAYC, F. ; ALBUQUERQUE, V. H. C. . Energy production predication via Internet of Thing based machine learning system. Future Generation Computer Systems, p. 180-193, 2019.

Paper 3:

SOUSA, P. H. F. ; NASCIMENTO, N. M. M. ; ALMEIDA, J. S. ; REBOUÇAS FILHO, P. P. ; ALBUQUERQUE, V. H. C. . Intelligent Incipient Fault Detection in Wind Turbines based on Industrial IoT Environment. Journal of Artificial Intelligence and Systems, v. 1, p. 1-19, 2019.

Paper 4:

NASCIMENTO, N. M. M. ; Rebouças Filho, Pedro Pedrosa ; MEDEIROS, C. M. S. . Higher-Order Statistics applied to machine learning as an approach to identify broken rotor bars in induction motors. IEEE Latin America Transactions, v. 16, p. 2267-2274, 2018.

Paper 5:

Pedro Pedrosa Rebouças Filho; NASCIMENTO, N. M. M. ; SOUSA, I. R. ; MEDEIROS, C. M. S. ; ALBUQUERQUE, V. H. C. . A reliable approach for detection of incipient faults of short-circuits in induction generators using machine learning. COMPUTERS & ELECTRICAL ENGINEERING, v. 71, p. 440-451, 2018.

Paper 6:

Nascimento, Navar de Medeiros Mendonça ; Medeiros, Cláudio Marques de Sá ; Rebouças Filho, Pedro Pedrosa . A Comparison of Machine Learning Methods to Identify Broken Bar Failures in Induction Motors Using Statistical Moments. In: ISDA 2017. (Org.). Advances in Intelligent Systems and Computing. 736ed.: Springer International Publishing, 2018, v. , p. 124-133.

Paper 7:

DE SOUSA, PEDRO HENRIQUE FEIJO ; E NASCIMENTO, NAVAR MEDEIROS M. ; FILHO, PEDRO PEDROSA REBOUCAS ; DE MEDEIROS, CLAUDIO MARQUES SA . Detection and classification of faults in induction generator applied into wind turbines through a machine learning approach. In: 2018 International Joint Conference on Neural Networks (IJCNN), 2018, Rio de Janeiro. 2018 International Joint Conference on Neural Networks (IJCNN), 2018. p. 1.

If you desire to use our dataset or replicate our methodology, I would appreacite if you could cite the paper. The bibtex is:

```
@article{xu2021multi,
  title={Multi-sensor edge computing architecture for identification of failures short-circuits in wind turbine generators},
  author={Xu, Yongzhao and Nascimento, Navar Medeiros M and de Sousa, Pedro H Feij{\'o} and Nogueira, Fabr{\'\i}cio G and Torrico, Bismark C and Han, Tao and Jia, Chuanyu and Rebou{\c{c}}as Filho, Pedro P},
  journal={Applied Soft Computing},
  volume={101},
  pages={107053},
  year={2021},
  publisher={Elsevier}
}

@article{rebouccas2019energy,
  title={Energy production predication via Internet of Thing based machine learning system},
  author={Rebou{\c{c}}as Filho, Pedro P and Gomes, Samuel L and e Nascimento, Navar M Mendon{\c{c}}a and Medeiros, Cl{\'a}udio MS and Outay, Fatma and de Albuquerque, Victor Hugo C},
  journal={Future Generation Computer Systems},
  volume={97},
  pages={180--193},
  year={2019},
  publisher={Elsevier}
}

@article{de2019intelligent,
  title={Intelligent Incipient Fault Detection in Wind Turbines based on Industrial IoT Environment},
  author={de Sousa, Pedro H Feij{\'o} and Navar de Medeiros, M and Almeida, Jefferson S and Rebou{\c{c}}as Filho, Pedro P and de Albuquerque, Victor Hugo C and others},
  journal={Journal of Artificial Intelligence and Systems},
  volume={1},
  number={1},
  pages={1--19},
  year={2019},
  publisher={Institute of Electronics and Computer}
}

@article{nascimento2018higher,
  title={Higher-Order Statistics applied to machine learning as an approach to identify broken rotor bars in induction motors},
  author={Nascimento, Navar Medeiros M and Silva, Suane PP and Reboucas Filho, Pedro Pedrosa and Medeiros, Claudio Marques Sa},
  journal={IEEE Latin America Transactions},
  volume={16},
  number={8},
  pages={2267--2274},
  year={2018},
  publisher={IEEE}
}

@article{
  rebouccas2018reliable,
  title={A reliable approach for detection of incipient faults of short-circuits in induction generators using machine learning},
  author={Rebou{\c{c}}as Filho, Pedro Pedrosa and Nascimento, Navar MM and Sousa, Igor R and Medeiros, Cl{\'a}udio MS and de Albuquerque, Victor Hugo C},
  journal={Computers \& Electrical Engineering},
  volume={71},
  pages={440--451},
  year={2018},
  publisher={Elsevier}
}

@inproceedings{e2017comparison,
  title={A Comparison of Machine Learning Methods to Identify Broken Bar Failures in Induction Motors Using Statistical Moments},
  author={e Nascimento, Navar de Medeiros Mendon{\c{c}}a and de S{\'a} Medeiros, Cl{\'a}udio Marques and Rebou{\c{c}}as Filho, Pedro Pedrosa},
  booktitle={International Conference on Intelligent Systems Design and Applications},
  pages={124--133},
  year={2017},
  organization={Springer}
}

@inproceedings{de2018detection,
  title={Detection and classification of faults in induction generator applied into wind turbines through a machine learning approach},
  author={de Sousa, Pedro Henrique Feij{\'o} and e Nascimento, Navar Medeiros M and Rebou{\c{c}}as Filho, Pedro Pedrosa and de Medeiros, Cl{\'a}udio Marques S{\'a}},
  booktitle={2018 International Joint Conference on Neural Networks (IJCNN)},
  pages={1--7},
  year={2018},
  organization={IEEE}
}

```

##  2. <a name='Source code'></a>Source code of Publications

###  2.1. <a name='Nascimentoetal2019-Amulti-sensorarchitectureforrobustidentificationofincipientshort-circuitsinwindturbinegenerators'></a>Multi-sensor edge computing architecture for identification of failures short-circuits in wind turbine generators

This contains a full analyses of the database, employing statistiscal tests and embeeded systems. Its source code is is available [here](paper-02-A_multi-sensor_architecture).

###  2.2. <a name='Reboucasetal2018-Areliableapproachfordetectionofincipientfaultsofshort-circuitsininductiongeneratorsusingmachinelearning'></a>Reboucas *et al*, 2018 - A reliable approach for detection of incipient faults of short-circuits in induction generators using machine learning

The **main** publications about my dissertations is available at the paper entitle as [A reliable approach for detection of incipient faults of short-circuits in induction generators using machine learning☆
](https://www.sciencedirect.com/science/article/pii/S0045790618307584)

The source code for this paper is avaible [here](paper-01-A_reliable_approach).