預測性維護與狀態監控

演講摘要

預測性維護指的是在機台設備故障之前就先預測到其發生,並根據預測結果進行設備的維護保養,因此成為許多企業的首要工作目標,藉此從歷史資料中挖掘出具有價值的商業資訊。有許多新技術,例如機器學習和大數據解析,都已經展現令人信服的成效,不過對在該領域系統專家就能明顯分辨的細微特徵,前述兩項技術可以掌握到的卻仍然有限。

本演講將討論如何將機器學習與大數據解析技術,與傳統的模型化基礎技術結合,建立一個演算法來預測設備的故障並找出根本原因。我們將探索資料的輸入與前處理來設計狀態指標,並訓練以及比較多個機器學習模型。


Predictive Maintenance and Condition Monitorings

Predictive maintenance is the practice of forecasting equipment failures before they occur and is a high priority for many organizations looking to get business value from historical performance data. New technologies such as machine learning and big data show promising results, but they fail to capture nuances that may be obvious to domain experts familiar with these systems.

In this session, see how machine learning and big data techniques can be combined with traditional model-based techniques to build an algorithm for predicting equipment faults and isolating their root cause. We will explore importing and pre-processing data to design condition indicators as well as training and comparing multiple machine learning models.