| 引用本文: | 李盼池,宋考平,杨二龙.基于相位编码的混沌量子免疫算法[J].控制理论与应用,2011,28(3):375~380.[点击复制] |
| LI Pan-chi,SONG Kao-ping,YANG Er-long.Chaos quantum immune algorithm based on phase encoding[J].Control Theory and Technology,2011,28(3):375~380.[点击复制] |
|
| 基于相位编码的混沌量子免疫算法 |
| Chaos quantum immune algorithm based on phase encoding |
| 摘要点击 2111 全文点击 1249 投稿时间：2009-12-20 修订日期：2010-02-27 |
| 查看全文 查看/发表评论 下载PDF阅读器 |
| DOI编号 |
| 2011,28(3):375-380 |
| 中文关键词 量子算法 免疫算法 量子免疫算法 相位编码 混沌优化 |
| 英文关键词 quantum algorithm immune algorithm quantum immune algorithm phase encoding chaos optimization |
| 基金项目 国家自然科学基金资助项目(60773065); 中国博士后科学基金资助项目(20090460864, 201003405); 黑龙江省博士后科学基金资助项目(LBH–Z09289); 黑龙江省教育厅科学基金资助项目(11551015). |
|
| 中文摘要 |
| 目前量子群智能优化算法的个体均采用基于量子比特测量的二进制编码方式, 在用于连续问题优化时, 由于频繁的解码运算, 严重降低了优化效率. 针对这一问题, 本文提出一种混沌量子免疫算法. 该方法直接采用量子比特的相位对抗体进行编码; 用量子旋转门实现优良抗体的克隆扩增, 通过在量子旋转门中引入混沌变量动态改变转角大小实现局部搜索; 用基于Pauli-Z门的较差抗体的变异, 实现全局优化. 证明了算法的收敛性. 由于优化过程统一在空间[0, 2π]^n进行, 而与具体问题无关, 因此, 对不同尺度空间的优化问题具有良好的适应性. 实验结果表明该算法能有效改善普通免疫算法的搜索能力和优化效率. |
| 英文摘要 |
| The binary encoding is commonly used based on qubit measures in the current quantum swarm intelligent optimization algorithms. Due to the frequent decoding operations, the efficiency of optimization is greatly reduced when the binary quantum algorithm is applied to continuous optimizations. To deal with this problem, a chaos quantum immune algorithm is proposed, in which individual antibodies are directly encoded by the phase of qubits. The excellent individuals are cloned by quantum rotation gates; and the local search is achieved by employing the chaos variables in the rotation angles of quantum rotation gates. The global search is achieved by the mutations of the inferior individuals based on the quantum Pauli-Z gates. Because the optimization process is performed in [0, 2π]^n which has nothing to do with the specific issues, the proposed method has good adaptability for a variety of optimization problems. The experimental results indicate that the proposed algorithm effectively improves the search capabilities and optimizes the efficiency of the general immune optimization algorithm. |
|
|
|
|
|