| 基于量子卷积神经网络算法的微小零件识别 |
| |
| 引用本文： | 何瑞,丁泽庆.基于量子卷积神经网络算法的微小零件识别[J].食品与机械,2021,37(6):120-125. |
| |
| 作者姓名： | 何瑞 丁泽庆 |
| |
| 作者单位： | 黄河水利职业技术学院，河南 开封 475004;南阳技师学院，河南 南阳 473000 |
| |
| 基金项目： | 河南省教育厅重点项目（编号：2019SJGLX691） |
| |
| 摘 要： | 设计了量子卷积神经网络表示层、隐藏层神经元和输出层神经元模型；采用修正线性激活函数ReLu作为激活函数，并通过训练误差函数优化量子旋转角度和神经连接权值。8种微小零件的仿真试验表明，量子卷积神经网络算法的识别准确率较高，耗时少且识别效果较好。
|
| 关 键 词： | 量子 卷积神经网络 微小零件 识别 |
| 收稿时间： | 2021/2/9 0:00:00 |
Recognition of micro parts based on quantum convolution neural network algorithm |
| |
| HERui,DINGZeqing.Recognition of micro parts based on quantum convolution neural network algorithm[J].Food and Machinery,2021,37(6):120-125. |
| |
| Authors: | HERui DINGZeqing |
| |
| Affiliation: | Yellow River Conservancy Technical College, Kaifeng, Henan 475004, China; Nanyang Technician College, Nanyang, Henan 473000, China |
| |
| Abstract: | The representation layer, hidden layer and output layer neuron models of quantum convolution neural network were designed. Modified linear activation function Relu was used as the activation function, and the quantum rotation angle and neural connection weight were optimized by training error function. The simulation results of eight kinds of micro parts show that the recognition accuracy of quantum convolution neural network algorithm is higher, the time consumption is less and the recognition effect is better than other algorithms. |
| |
| Keywords: | quantum convolution neural network micro part recognition |
|
| 点击此处可从《食品与机械》浏览原始摘要信息 |
|
点击此处可从《食品与机械》下载全文 |
