基於深度學習之工件形狀分類檢測系統

Inspection System for Classifying Workpieces’ Shape Based on Deep Learning

高志偉(ZHI-WEI GAO)

指導教授 ： 陳冠宇

中原大學/工學院/機械工程研究所/碩士(2020年)

https://doi.org/10.6840/cycu202000642

摘要

本文的研究目的為發展一套利用單晶片電腦樹莓派控制機械手臂與輸送裝置，結合深度學習之即時影像辨識功能，完成工件形狀分類之自動化檢測作業。首先，將欲分類的所有工件形狀之影像作成訓練樣本，以基於深度學習之影像分類器進行訓練，完成後可得到模型參數。其次，進行實驗測試，由樹莓派控制之輸送裝置將工件送至檢測位置，此分類器能即時顯示工件形狀的分類結果；最後，再透過樹莓派控制機械手臂分類工件，夾取至設定位置，由輸送設備將工件送達目的地。經由統計並分析實驗數據，本文發展的系統之分類正確率可達95%。

關鍵字

機器視覺 ； 機器學習 ； 深度學習 ； 樹莓派 ； python

並列摘要

The research purpose of this dissertation is to develop a deep learning based automated inspection and classification system for workpiece shape using single-board computer Raspberry Pi, which is used to control conveyor and robotic arm for real-time object detection. First, the images of all workpiece shapes to be classified are made into training samples, and the image classifier based on deep learning is used for training. After completion, the model parameters can be obtained. Secondly, carry out experimental tests. The conveying device controlled by the Raspberry Pi sends the workpiece to the inspection position. This classifier can display the classification results of the workpiece shape in real time. Finally, the Raspberry Pi controls the robotic arm to classify the workpieces, clamp them to the set position, and deliver the workpieces to the destination by the conveying equipment. Through statistics and analysis of experimental data, the classification accuracy rate of the system developed in this dissertation can reach 95%.

並列關鍵字

machine vision ； machine learning ； deep learning ； raspberry pi ； python.

參考文獻

[1] P. J. Werbos. Beyond Regression: New Tools for Prediction and Analysis in the Behavioral Sciences. PhD Thesis, Harvard University, 1974.

[2] D. Rumelhart, G. Hinton, and R. Williams, “Learning representations by back-propagating errors,” Nature, Vol. 323, pp. 533-536, 1986.

[3] D. H. Ackley, G. E. Hinton, and T. J. Sejnowski, “A learning algorithm for Boltzmann machines,” Cognitive Science, Vol. 9, No. 1, pp. 147-169, 1985.

[4] Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner “Gradient-based learning applied to document recognition” Proceedings of the IEEE, Vol. 11, No. 86, pp. 2278-2324, 1998.

[5] U. M. Fayyad, G. Piatetsky-Shapiro, P. Smyth, and R. Uthurusamy, “Advances in knowledge discovery and data mining,” American Association for Artificial Intelligence, ISBN 0262560976. 1996.