高頻資料特徵工程與設備健康指標模組
Equipment Health Indicators Module
  ‧ 發明人/PI 李家岩教授
Prof. Chia-Yen Lee
  ‧ 單位 國立臺灣大學資訊管理學系
Department of Information Management, National Taiwan U.
  ‧ 簡歷/Experience http://polab.im.ntu.edu.tw/Bio.html
 
市場需求 / Market Needs:
對於製造業設備健康管理(PHM)與預測保養(PdM)建構人工智慧預測模型能有效提升預測準確度。

Improve prediction accuracy of artificial intelligence models for prognostic & health management (PHM) and predictive maintenance (PdM) of equipment in the manufacturing industry.

 
技術摘要 / Our Technology:
高頻訊號進行特徵工程,透過時域、頻域、頻譜圖的線性與非線性特徵萃,並進行重要特徵挑選後,建構健康指標特徵的相關檢定,以利設備健康指標建構。

Feature engineering for high-frequency signals. Through linear and nonlinear feature extraction in time domain, frequency domain, and spectrogram, the important features are extracted and identified. After statistical testing of these features for equipment health indicator, the selected features benefit the construction of equipment health indicators.

 
優勢 / Strength:
透過大量特徵的轉換,可快速找出真正影響機台設備老化現象的相關特徵。

Through the extraction of a large number of features, identify the relevant features that really affect the aging or degradation of the equipment.

 
競爭產品 / Competing Products:
市面上有許多PHM產品,各家方法與客製化的產業別不一。

There are PHM products in the market and each product is customized for some specific industrial applications.

 
專利簡述 / Intellectual Properties:
(1)本研究團隊具有數十年研究經驗
(2) Lee, Chia-Yen, Huang, Ting-Syun, Liu, M.-K., and Lan, C.-Y., 2019. Data science for vibration heteroscedasticity and predictive maintenance of rotary bearings. Energies, 12 (5), 801.
Lu, Hsuan-Wen, and Lee, Chia-Yen, 2022. Kernel-based dynamic ensemble technique for remaining useful life prediction. IEEE Robotics and Automation Letters, 7 (2), 1142-1149.



 
聯繫方式 / Contact:
臺大產學合作總中心 / Center of Industry-Academia Collaboration, NTU
Email:ordiac@ntu.edu.tw 電話/Tel:02-3366-9945