平行式類神經網路染整設備用電預測系統模式化之研究

Research on Modeling of Parallel Neural Network Power Consumption Prediction System for Dyeing and Finishing Equipment

廖育佐(Y. Z. Liao) ； 許文正(W. C. Hsu)

《紡織綜合研究期刊》 33卷1期 (2023/01) Pp. 60-64

https://doi.org/10.6439/TTRJ.202301_33(1).0008

摘要

本研究是染整廠設備用電排程優化方法及其系統，以雲林分部廠區為例，通過訓練好的AI模型對廠區設備的感測器參數數據進行預測，可以準確的預測設備將要發生過載的時間，並且將預測結果依據嚴重程度分階反饋給排程系統重新訂定用電排程，讓產線持續運作且不超標。

關鍵字

平行式類神經網路 ； 用電預測 ； 排程

並列摘要

This research is an optimization method and system for power dispatching of equipment in dyeing and finishing plants. Taking the TTRI Yunlin Branch as an example, the trained AI model can predict the sensor parameter data of the equipment in the factory area, can accurately predict the time when the equipment is overloaded, and feed the prediction result back to the dispatching system to reset the electricity consumption schedule in stages according to the severity, so that the production line can continue to run without exceeding specifications.

並列關鍵字

Parallel neural network ； power prediction ； schedule