發明
中華民國
110129929
I 787955
設備溫度異常的線上檢測方法和系統
國立臺灣科技大學
2022/12/21
此次專利的申請是對工業用空調系統進行預測性維護分析,在故障偵測分類系統上,建立大數據與機器學習的架構,找出影響產品品質的關鍵因素,進行設備偵測來發現潛在的問題,防止對產品造成影響。在可使用壽命預測系統上,建立模型,可應用於預測設備失效時間,而如何將重要特徵資料整合成建康指標是很重要的工作,然後以深度學習模型(LSTM)對建康指標進行模型訓練,最後以Python開發應用程式進行機台的故障偵測的分析。此外,在計畫執行過程中,發現”線上設備溫度異常檢測”的相關研究不是很多,因此應用本研究的方法於設備溫度異常檢中,將可以協助業者於工業用空調系統進行預測性維護。進而提升顧客服務水準之能力。 The patent application is to conduct predictive maintenance analysis on industrial air conditioning systems. On the fault detection and classification system, establish a big data and machine learning framework to find out the key factors that affect product quality, and perform equipment detection to find potential problems and prevent impacts on the product. In the service life prediction system, the establishment of a model can be applied to predict the failure time of equipment, and how to integrate important characteristic data into health indicators is a very important task. Then use the deep learning model (LSTM) to conduct model training on health indicators, and finally use Python to develop an application to analyze the machine's fault detection. In addition, during the execution of the plan, there are not many related researches on "detection of abnormal temperature of online equipment". Therefore, applying the method of this research to the abnormal temperature detection of equipment will assist the industry in predictive maintenance of industrial air-conditioning systems. And then improve the ability of customer service level.
技術移轉中心
02-2733-3141#7346
版權所有 © 國家科學及技術委員會 National Science and Technology Council All Rights Reserved.
建議使用IE 11或以上版本瀏覽器,最佳瀏覽解析度為1024x768以上|政府網站資料開放宣告
主辦單位:國家科學及技術委員會 執行單位:台灣經濟研究院 網站維護:台灣經濟研究院