|
|||||
|
|
| 基于类神经网络模型的电路演化实现方法 | |
| 引用本文： | 崔新风,娄建安,褚杰,原亮,丁国良.基于类神经网络模型的电路演化实现方法[J].计算机工程,2011,37(4):175-177. |
| 作者姓名： | 崔新风 娄建安 褚杰 原亮 丁国良 |
| 作者单位： | 1. 军械工程学院电气工程系,石家庄,050003 2. 军械工程学院静电与电磁防护研究所,石家庄,050003 3. 军械工程学院计算机工程系,石家庄,050003 |
| 基金项目： | 国防科技重点实验室基金 |
| 摘 要： | 为解决目前数字型演化硬件研究中存在的电路编码困难问题,提出一个可用矩阵形式描述组合电路的类神经网络门级电路模型,讨论在此模型上进行电路编码的具体方法.根据编码矩阵特点,对标准遗传算法进行改进,设计遗传操作算子、适应度评估方法等.通过无刷直流电动机电子换相电路的成功演化实例,验证了采用矩阵编码和改进遗传算法实现数字电路演... |
| 关 键 词： | 神经网络 组合电路 演化硬件 |
Implementation Method of Circuit Evolution Based on Artificial Neural Network Model |
|
| CUI Xin-feng,LOU Jian-an,CHU Jie,YUAN Liang,DING Guo-liang.Implementation Method of Circuit Evolution Based on Artificial Neural Network Model[J].Computer Engineering,2011,37(4):175-177. | |
| Authors: | CUI Xin-feng LOU Jian-an CHU Jie YUAN Liang DING Guo-liang |
| Affiliation: | c(a.Department of Electrical Engineering;b.Institute of Electrostatic and Electromagnetic Protection;c.Department of Computer Engineering,Ordnance Engineering College,Shijiazhuang 050003,China) |
| Abstract: | For the purpose of solving the encoding problem harassed the digital Evolvable Hardware（EHW） researchers, a gate-level circuit model which is based on the similarities between combinatorial circuit and neural network is proposed, on which the matrix encoding scheme of combinatorial circuit is discussed. An improved genetic algorithm is used to evolve the encoding matrix, genetic operators and fitness evaluation method are designed according to the characteristics of circuit encoding. The implementation of the commutation circuit of brushless direct current motor proves the feasibility of the implementation method of digital EHW by the using of matrix encoding scheme and the improved genetic algorithm. |
| Keywords: | neural network combinatorial circuit Evolvable Hardware（EHW） |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ | |
| 点击此处可从《计算机工程》浏览原始摘要信息 | |
| 点击此处可从《计算机工程》下载全文 | |