課程概述(系所共同性目標) Course Description
因應先進工業4.0(Industry 4.0)的技術趨勢，我國政府打造以「創新、就業、分配」為核心價值，追求永續發展的經濟新模式，並透過「連結未來、連結全球、連結在地」三大策略，激發產業創新風氣與能量。政府提出「智慧機械」、「亞洲‧矽谷」、「綠能科技」、「生醫產業」、「國防產業」、「新農業」及「循環經濟」等5+2產業創新計畫，作為驅動台灣下世代產業成長的核心，為經濟成長注入新動能。
所謂「智慧機械」就是整合工業4.0技術元素，使其具備故障預測、精度補償、自動參數設定與自動排程等智慧化功能，其中故障預測是指利用各項感測器感知設備關鍵模組之運轉狀態，並設法從中找出設備發生故障前的先期徵兆，提早進行預防保養，降低設備非預期性故障所造成的龐大損失；精度補償則是透過各式感測器監測整個生產過程，並據此調整製程參數、補償加工誤差、推估加工品質等，最終達到生產效能提升、加工品質確保之目的。透過長期的數據收集，將大數據分析概念結合機械振動知識，透過類神經網路的方式建立機台健康指標模型，利用model-base之方式來進行機台全面性的監控，已達到降低無預警故障率、有效排程維修及減少備料問題。
課程規劃(教師個別目標) Course Plan
本課程各主題皆與邁向智慧機械所需的關鍵技術相關，學員透過課程可學習
1. 前言及問題性開題
2. 商用Matlab軟體技術+數據處理+大數據分析技術+AI模型建立技術
3. 設備監測原理+監測系統架構說明與設計流程+如何建置設備狀態監測系統
4. 感測與訊號處理技術(實務操作)
5. 振動原理+機械設備預兆診斷方法與原理
6. 運用訊號處理方法與預兆診斷方法等監控重要機械設備與推估加工品質
7. 透過實例說明強化解決設備異常問題之實務能力
Course Description
Due to the advanced technical trend of Industry 4.0 (Industry 4.0), our government has created a new economic model with "innovation, employment, distribution" as its core value, and pursues a new economic model forever development, and through "connecting the future, connecting the world, connecting the local area" three Big strategy to stimulate the innovation atmosphere and energy of the industry. The government proposed innovative plans for 5+2 industry, including "smart machinery", "Silicon Valley in Asia", "Green Technology", "Bio-medical industry", "National Defense Industry", "New Agriculture" and "Circular Economy" as a driving force The core of Taiwan's next generation of industry growth is to inject new energy into economic growth.
The so-called "smart machinery" is to integrate industrial 4.0 technical elements to provide intelligent functions such as fault prediction, accuracy compensation, automatic parameter setting and automatic scheduling. Among them, fault prediction refers to the use of various sensors to sense the key module of the equipment. Transfer status and design methods to find out the first before the equipment fails For periodic signs, precautionary maintenance is carried out early to reduce the major losses caused by non-expected equipment failures; accuracy compensation is to monitor the entire production process through various sensors, and adjust process parameters, compensate processing errors, and estimate process quality. In the end, we achieve the purpose of improving production efficiency and ensuring processed quality. Through long-term data collection, large data analysis concepts are combined with mechanical vibration knowledge, and the machine health indicator model is established through neural network methods, and comprehensive monitoring of the machine is achieved by reducing no alarm. Failure rate, effective scheduling maintenance and reducing material preparation problems.
Course Plan (Teacher's Special Goal) Course Plan
Each topic of this course is related to the key technologies required for the use of intelligent machinery. Students can learn through the course
1. Preface and questionable questions
2. Commercial Matlab software technology + data processing + large data analysis technology + AI model establishment technology
3. Equipment monitoring principle + monitoring system architecture instructions and design process + how to build a equipment status monitoring system
4. Induction and signal processing technology (actual operation)
5. Vibration principle + mechanical equipment pre-automatic diagnosis method and principle
6. Monitor important mechanical equipment and estimation of processed quality using signal processing methods and pre-visual diagnosis methods
7. Use examples to illustrate the practical ability to solve abnormal equipment problems
教材編選：■自編教材 □教科書作者提供
教學方法：■投影片講述 ■板書講述 ■實例示範 ■操作練習
Textbook selection: ■Self-edited textbook □Provided by the author of the textbook
Teaching method: ■Projection film presentation ■Board presentation ■Practical examples ■Operation practice
| 評分項目 Grading Method | 配分比例 Grading percentage | 說明 Description |
|---|---|---|
| 期中+期末 考期中+期末 考 Midterm + final exam |
20 | |
| 期中小考+期末小考期中小考+期末小考 Primary and secondary exam + final exam |
20 | |
| 點名+專題作業點名+專題作業 Point name + topic action |
20 | |
| 期末專題期末專題 Final topics |
40 |
