基於深度神經網路的智慧指套應用於裝配動作辨識;Deep Neural Network-based Smart Finger Sleeve Applying to Assembly Activity Recognition

NCUIR > College of Electrical Engineering & Computer Science > Executive Master of Computer Science and Information Engineering > Electronic Thesis & Dissertation > Item 987654321/83950

Please use this identifier to cite or link to this item: http://ir.lib.ncu.edu.tw/handle/987654321/83950

Title:	基於深度神經網路的智慧指套應用於裝配動作辨識;Deep Neural Network-based Smart Finger Sleeve Applying to Assembly Activity Recognition
Authors:	鍾禮安;Chung, Li-An
Contributors:	資訊工程學系在職專班
Keywords:	九軸控制器;深度學習;CNN;Deep learning
Date:	2020-08-24
Issue Date:	2020-09-02 17:45:04 (UTC+8)
Publisher:	國立中央大學
Abstract:	在工廠量產產品時，依據產品規格與產量指派產線作業員進行產品裝配，但由於產線員工裝配產品時，易發生人為操作失誤導致產品破裂或是產品漏裝，進而導致影響整體產品出貨品質與製造成本。故本篇論文提出以作業員戴上指套且指套上黏附九軸感測器和手握自動螺絲起子，蒐集動作感測數據，再以卡爾曼濾波進行感測數據濾波，以越零率方式進行動作切割，再利用Mahony 濾波計算誤差模型來校正感測器數據後計算出四元數，利用四元數當作特徵後利用一維卷積神經網路來分類 (1) 右上頂螺絲、(2) 右下頂螺絲、(3) 右斜上頂螺絲、(4) 左斜下頂螺絲、(5) 向下鎖螺絲、(6) 抬手放下，共六種作業員裝配基本動作，由此六種裝配動作組合順序以判別裝配產品是否正確。實驗結果發現利用Mahony 濾波校正感測器後再計算出四元數為特徵進行一維卷積神經網路1DCNN 能提升72% 的辨識率，進行長短期記憶模型LSTM 能提升30%辨識率，進行CNN-LSTM 也能提升70%的辨識率，而校正後的數據在1DCNN 有高達94% 的平均辨識率，比使用LSTM 模型高39%辨識率，比使用CNN-LSTM 高3%辨識率，故使用此方法能預防現今作業員鎖螺絲動作出錯與降低作業員動作訓練成本，與改善產線員工管理智能化不足等問題。;When mass-producing products in the factory, the production line operators are assigned to carry out product assembly based on product specifications and product number. However, when the production line employees assemble products, human operation errors are prone to cause product rupture or product miss screw , which in turn affects the overall product quality and manufacturing cost. Therefore, This paper proposes that the operator wears a finger sleeve with a nine-axis sensor attached and holds an automatic screwdriver to collect motion sensing data, and then uses the Kalman filter to filter the sensing data, and performs motion cutting with a zerocrossing rate. Then use Mahony filter to calculate the error model to correct the sensor data and calculate the quaternion, use the quaternion as a feature, and then use a one-dimensional Convolutional neural network to classify (1) upper right screw , (2) lower right screw ,(3) right diagonal screw,(4) Left diagonal screw,(5) down lock screw ,(6) Raise hand and lay down , total of six basic assembly actions for operators, The sequence of six assembly actions is used to judge whether the assembled product is correct. The experimental results found that the use of Mahony filter to calibrate the sensor and then calculate the quaternion as the feature for one-dimensional convolutional neural network 1DCNN can increase the recognition rate by 72%, and the long- and short-term memory model LSTM can increase the recognition rate by 30%. CNN-LSTM can also increase the recognition rate by 70%, and the corrected data has an average recognition rate of 94% in 1DCNN, which is 39% higher than the LSTM model and 3% higher than the CNN-LSTM. Using this method can prevent the current operator from locking screws and reduce the cost of operator training, and improve the lack of intelligent management of production line employees.
Appears in Collections:	[Executive Master of Computer Science and Information Engineering] Electronic Thesis & Dissertation

Files in This Item:

File	Description	Size	Format
index.html		0Kb	HTML	209	View/Open

社群 sharing

Loading...