{"id":2016,"date":"2024-02-26T16:16:33","date_gmt":"2024-02-26T08:16:33","guid":{"rendered":"https:\/\/luckytian.cn\/?p=2016"},"modified":"2024-03-14T21:43:44","modified_gmt":"2024-03-14T13:43:44","slug":"%e7%b2%92%e5%ad%90%e7%be%a4pso%e6%94%b9%e8%bf%9b%e8%ae%ba%e6%96%87%e9%98%85%e8%af%bb","status":"publish","type":"post","link":"https:\/\/luckytian.cn\/?p=2016","title":{"rendered":"\u7c92\u5b50\u7fa4(PSO)\u6539\u8fdb\u8bba\u6587\u9605\u8bfb"},"content":{"rendered":"\n
1.2023 TNNLS\uff1aA Novel Swarm Exploring Varying Parameter Recurrent Neural Network for Solving Non-Convex Nonlinear Programming.<\/h5>\n\n\n\n

\u672c\u6587\u63d0\u51fa\u4e00\u79cd\u7fa4\u63a2\u7d22\u53d8\u53c2\u6570\u9012\u5f52\u795e\u7ecf\u7f51\u7edc\u975e\u51f8\u975e\u7ebf\u6027\u4f18\u5316\u95ee\u9898\u6c42\u89e3\u65b9\u6cd5(A Novel Swarm Exploring Varying Parameter Recurrent Neural Network for Solving Non-Convex Nonlinear Programming, SE-VPRN). <\/p>\n\n\n\n

\u6838\u5fc3\u601d\u60f3\u4e3a\uff1a\u7531\u53d8\u53c2\u6570\u9012\u5f52\u795e\u7ecf\u7f51\u7edc\u6c42\u89e3\u5c40\u90e8\u6700\u4f18\u95ee\u9898(\u9700\u4f18\u5316\u95ee\u9898\u548c\u7ea6\u675f\u6761\u4ef6\u53ef\u5bfc)\uff1b\u5404\u4e2a\u7f51\u7edc\u6536\u655b\u5230\u5c40\u90e8\u6700\u4f18\u540e\uff0c\u7531\u7c92\u5b50\u7fa4\u8fdb\u884c\u4fe1\u606f\u4ea4\u6362\uff0c\u66f4\u65b0\u901f\u5ea6\u548c\u4f4d\u7f6e\uff1b\u5728\u7c92\u5b50\u7fa4\u5e94\u7528\u8fc7\u7a0b\u4e2d\uff0c\u91c7\u7528\u4e86\u5c0f\u6ce2\u53d8\u5f02\uff0c\u8fdb\u800c\u589e\u52a0\u4e86\u7c92\u5b50\u7684\u591a\u6837\u6027\u3002\u5373\u672c\u6587\u601d\u60f3\u4e3a\uff0c\u5229\u7528\u9012\u5f52\u795e\u7ecf\u7f51\u7edc\u9ad8\u6548\u7cbe\u786e\u7684\u5c40\u90e8\u641c\u7d22\u80fd\u529b\u548c\u5143\u542f\u53d1\u5f0f\u7b97\u6cd5\u5168\u5c40\u641c\u7d22\u80fd\u529b\u76f8\u7ed3\u5408\u6c42\u89e3\u975e\u51f8\u975e\u7ebf\u6027\u95ee\u9898\u3002<\/p>\n\n\n\n

\u53ef\u7528\u53e5\uff1a\uff081\uff09\u7531\u4e8e\u4f17\u591a\u5c40\u90e8\u6700\u5c0f\u70b9\u548c\u9ad8\u6548\u80fd\u7684\u9700\u8981\uff0c\u9ad8\u6548\u6c42\u89e3\u975e\u51f8\u4f18\u5316\u95ee\u9898\u4e3a\u4f18\u5316\u6c42\u89e3\u9886\u57df\u7684\u4e00\u4e2a\u6311\u6218\u3002\uff082\uff09\u7c92\u5b50\u7fa4\u4f18\u5316\u7531Eberhart\u548cKennedy\u57281995\u5e74\u901a\u8fc7\u7814\u7a76\u9e1f\u7c7b\u7684\u6355\u98df\u884c\u4e3a\u63d0\u51fa\uff0c\u8be5\u7b97\u6cd5\u901a\u8fc7\u5728\u6bcf\u4e2a\u4e2a\u4f53\u4e4b\u95f4\u5171\u4eab\u4fe1\u606f\u6765\u83b7\u5f97\u6700\u4f18\u89e3\u3002<\/p>\n\n\n\n

\u6539\u8fdb\u7684\u65b9\u6cd5\uff1a\uff081\uff09\u91c7\u7528\u5c0f\u6ce2\u53d8\u5f02\u65b9\u6cd5\u589e\u52a0\u7c92\u5b50\u7684\u591a\u6837\u6027\u3002\u7c92\u5b50\u7684\u591a\u6837\u6027\u80fd\u591f\u88ab\u8ba1\u7b97\u4e3a\uff1a$s=\\frac{1}{P}\\left|x^{(k+1)}-x^*\\right|_2$, \u5176\u4e2d$P$\u4e3a\u7c92\u5b50\u7684\u6570\u76ee\uff0c$x^{k+1}$\u4e3a\u7c92\u5b50\u7b2c$k+1$\u6b21\u7684\u4f4d\u7f6e\uff0c$x^*$\u4e3a\u5f53\u524d\u7684\u5168\u5c40\u6700\u4f18\u89e3\u3002\u5373\uff0c\u79cd\u7fa4\u7684\u7c92\u5b50\u4eec\u79bb\u5168\u5c40\u6700\u4f18\u70b9\u8d8a\u8fd1\uff0c\u7c92\u5b50\u7fa4\u7684\u591a\u6837\u6027\u8d8a\u5f31\u3002<\/p>\n\n\n\n

\uff082\uff09\u5c0f\u6ce2\u53d8\u5f02\u56e0\u5b50\u8bbe\u8ba1\u4e3a\uff1a$\\tau=\\frac{1}{\\sqrt{v}} \\exp ^{-(\\mu \/ v)^2 \/ 2} \\cos \\left(\\frac{5 \\mu}{v}\\right)$\u3002\u5176\u4e2d\uff0c$v=\\exp (10(k \/ K))$\uff0c$K$\u8868\u793a\u6700\u5927\u8fed\u4ee3\u6b21\u6570\uff0c$\\mu$\u4e3a$[-2.5 v, 2.5 v]$\u7684\u968f\u673a\u6570\u3002\u5373\uff0c\u968f\u7740$k$\u7684\u4e0d\u65ad\u589e\u5927\uff0c$v$\u4e5f\u968f\u4e4b\u4e0d\u65ad\u589e\u5927\uff0c\u800c$\\tau$\u4e2d\u7684$\\mu \/ v$\u7684\u6bd4\u503c\u8303\u56f4\u5e76\u672a\u53d1\u751f\u53d8\u5316\uff0c\u6545\u968f\u7740$v$\u7684\u589e\u5927\uff0c$\\tau$\u4f1a\u8d8a\u6765\u8d8a\u5c0f\u3002<\/p>\n\n\n\n

\uff083\uff09\u7c92\u5b50\u7684\u521d\u59cb\u4f4d\u7f6e\u66f4\u65b0\u5982\u4e0b\uff0c\u5982\u679c$s<\\eta$($\\eta$\u8868\u793a\u7c92\u5b50\u591a\u6837\u6027\u7684\u9608\u503c\uff0c\u9700\u63d0\u524d\u8bbe\u5b9a)\uff0c\u7c92\u5b50\u7684\u4f4d\u7f6e\u88ab\u901a\u8fc7\u4ee5\u4e0b\u516c\u5f0f\u8fdb\u884c\u66f4\u65b0\uff1a$x_i^{(k+1)}=x_i^{(k+1)}+\\tau\\left(\\bar{x}_i-x_i^{(k+1)}\\right), \\quad \\tau>0; x_i^{(k+1)}+\\tau\\left(x_i^{(k+1)}-\\underline{x}_i\\right)$\u3002\u5176\u4e2d\uff0c$\\bar{x}_i$\u548c$\\underline{x}_i$\u5206\u522b\u8868\u793a\u7b2c$i$\u4e2a\u53d8\u91cf\u7684\u4e0a\u7ea6\u675f\u548c\u4e0b\u7ea6\u675f\u3002<\/p>\n\n\n\n

2.2017 PE\uff1aParameter Estimation for VSI-Fed PMSM Based on a Dynamic PSO With Learning Strategies.<\/h5>\n\n\n\n

\u6838\u5fc3\u601d\u60f3\uff1a\u672c\u6587\u63d0\u51fa\u4e00\u79cd\u57fa\u4e8e\u5b66\u4e60\u7684\u52a8\u6001\u7c92\u5b50\u7fa4\u4f18\u5316( dynamic particle swarm optimization with learning strategy, DPSO-LS)\u7528\u4e8e\u6c38\u78c1\u540c\u6b65\u7535\u673a\u7684\u53c2\u6570\u4f30\u8ba1\u3002\u63d0\u51fa\u4e86\u4e24\u70b9\u9488\u5bf9PSO\u5bfb\u4f18\u7684\u6539\u8fdb\uff0c\u9996\u5148\uff0c\u8bbe\u8ba1\u4e86\u4e00\u79cd\u5e26\u6709\u53d8\u63a2\u7d22\u5411\u91cf\u7684\u8fd0\u52a8\u4fee\u6b63\u516c\u5f0f\uff0c\u6709\u52a9\u4e8e\u7c92\u5b50\u7fa4\u641c\u7d22\u66f4\u5927\u7684\u7a7a\u95f4\uff0c\u589e\u5f3a\u5168\u5c40\u641c\u7d22\u80fd\u529b\uff1b\u5176\u6b21\uff0c\u5f00\u53d1\u4e86\u4e00\u79cd\u57fa\u4e8e\u9ad8\u65af\u5206\u5e03\u7684\u52a8\u6001\u5bf9\u7acb\u5b66\u4e60\u7b56\u7565(dynamic opposition-based learning, OBL)\u5e2e\u52a9\u7c92\u5b50\u8df3\u51fa\u5c40\u90e8\u6700\u4f18\u70b9\u3002<\/p>\n\n\n\n

\u6539\u8fdb\u7684\u65b9\u6cd5\uff1a<\/p>\n\n\n\n

\u6240\u4f18\u5316\u7684\u76ee\u6807\u51fd\u6570\u662f\u591a\u6a21\u6001\u7684->\u8981\u6c42\u6240\u63d0\u7684\u53c2\u6570\u4f18\u5316\u5f53\u95ee\u9898\u7684\u6c42\u89e3\u65b9\u6848\u53d1\u751f\u53d8\u5316\u65f6\uff0c\u80fd\u591f\u81ea\u9002\u5e94\u7684\u6539\u53d8\u539f\u59cb\u7684\u8f68\u8ff9\u4ee5\u63a2\u7d22\u65b0\u7684\u7a7a\u95f4<\/p>\n\n\n\n

\uff081\uff09\u5e26\u6709\u53ef\u53d8\u63a2\u7d22\u77e2\u91cf\u7684\u8fd0\u52a8\u66f4\u65b0\u516c\u5f0f\uff1a<\/p>\n\n\n\n

\u5982\u679c\u6536\u655b\u8fc7\u5feb\uff0c\u603b\u662f\u671d\u7740\u5c40\u90e8\u4f4d\u7f6e\u5728\u5c11\u6570\u6b21\u8fed\u4ee3\u540e\u8fc5\u901f\u6536\u7f29\uff0c\u8fd9\u79cd\u884c\u4e3a\u5c06\u5bfc\u81f4\u7c92\u5b50\u7fa4\u591a\u6837\u6027\u7684\u635f\u5931->\u7531\u4e8e\u540c\u8d28\u7684\u641c\u7d22\u884c\u4e3a\u548c\u81ea\u9002\u5e94\u63a2\u7d22\u80fd\u529b\u7684\u7f3a\u5931\uff0c\u5c06\u5bfc\u81f4\u7c92\u5b50\u4eec\u65e0\u6cd5\u8df3\u51fa\u5c40\u90e8\u533a\u57df\u3002<\/p>\n\n\n\n

\u4e00\u79cd\u6539\u8fdb\u7684\u8fd0\u52a8\u4fee\u6b63\u65b9\u7a0b->\u4f7f\u7c92\u5b50\u81ea\u9002\u5e94\u7684\u6539\u53d8\u81ea\u5df1\u7684\u539f\u59cb\u8f68\u8ff9\u4ee5\u63a2\u7d22\u65b0\u7684\u641c\u7d22\u7a7a\u95f4->\u7c92\u5b50\u4eec\u671d\u5411\u4e0d\u540c\u7684\u6709\u524d\u666f\u7684\u533a\u57df\uff0c\u540c\u65f6\u6269\u5bbd\u63a2\u7d22\u7684\u89e3\u7a7a\u95f4\u3002\uff08\u5728\u539f\u7c92\u5b50\u901f\u5ea6\u66f4\u65b0\u7684\u57fa\u7840\u4e0a\uff0c\u589e\u52a0\u4e00\u9879\u968f\u673a\u63a2\u7d22\u9879\uff09<\/p>\n\n\n\n

$V_{\\mathrm{id}}(t+1)=\\phi V_{id}+c_1 rand_1(Pbest(t)-X_{id}(t))+c_2 rand_2(gBest(t)-X_{id}(t))+c_3 rand_3(R(t)-X_{id}(t))$<\/p>\n\n\n\n

$X_{id}(t+1)=X_{id}(t)+V_{id}(t+1)$<\/p>\n\n\n\n

\u5176\u4e2d\uff0c$\\phi$\u4e3a\u60ef\u6027\u56e0\u5b50\uff0c$c_1$\u548c$c_2$\u4e3a\u52a0\u901f\u5ea6\u56e0\u5b50\uff0c$rand_1$\u548c$rand_2$\u4e3a\u4e24\u4e2a\u4f4d\u4e8e\u533a\u95f4[0,1]\u7684\u968f\u673a\u6570\uff0c$t$\u4e3a\u8fed\u4ee3\u6b21\u6570\uff0c$pBest_{id}$\u4e3a\u7b2c$i$\u4e2a\u7c92\u5b50\u5f53\u524d\u53d1\u73b0\u7684\u6700\u4f73\u4f4d\u7f6e\uff08\u4e2a\u4f53\u6700\u4f18\uff09\uff0c$gBest_d$\u4e3a\u6574\u4e2a\u79cd\u7fa4\u53d1\u73b0\u7684\u6700\u4f73\u4f4d\u7f6e\uff08\u5168\u5c40\u6700\u4f18\uff09\u3002<\/p>\n\n\n\n

\u5728\u4e0a\u5f0f\u4e2d\uff0c\u63a2\u7d22\u5411\u91cf$R(t)-X_{id}(t)$\u901a\u8fc7\u4f7f\u7528\u53ef\u53d8\u63a2\u7d22\u534a\u5f84$R(t)$\uff0c\u4e3a\u7c92\u5b50\u63d0\u4f9b\u4e00\u4e2a\u66f4\u5bbd\u7684\u63a2\u7d22\u89e3\u7a7a\u95f4->\u5176\u6709\u5927\u6982\u7387\u5141\u8bb8\u7c92\u5b50\u8986\u76d6\u66f4\u5927\u7684\u641c\u7d22\u7a7a\u95f4\u3002$R(t)$\u7684\u8ba1\u7b97\u516c\u5f0f\u5982\u4e0b\uff1a<\/p>\n\n\n\n

$R(t)=\\frac{\\left(X_{\\max }^d+X_{\\min }^d\\right)}{2}+\\frac{\\left(X_{\\max }^d-X_{\\min }^d\\right)}{2} \\cdot e^{-\\lambda t} \\cdot \\cos (2 \\pi u)$<\/p>\n\n\n\n

\u5176\u4e2d\uff0cu\u4e3a\u533a\u95f4[0,1]\u7684\u968f\u673a\u6570\uff0c$X_{min}^d$\u548c$X_{max}^d$\u5206\u522b\u662f\u6240\u6c42\u89e3\u95ee\u9898\u7684\u4e0a\u7ea6\u675f\u548c\u4e0b\u7ea6\u675f\uff0c$\\lambda$\u4e3a\u5927\u4e8e\u7b49\u4e8e2\u7684\u8c03\u8282\u53c2\u6570\u3002\u516c\u5f0f\u4e2d\uff0c\u5206\u4e3a\u4e86\u4e24\u90e8\u5206\uff0c\u7b2c\u4e00\u90e8\u5206\u83b7\u53d6\u8be5\u4f18\u5316\u53d8\u91cf\u7684\u4e2d\u95f4\u503c\uff0c\u7b2c\u4e8c\u90e8\u5206\u4e3a\u4f18\u5316\u53d8\u91cf\u6240\u53d6\u503c\u534a\u5f84\u4e58\u4e00\u4e2a\u968f\u8fed\u4ee3\u6b21\u6570\u589e\u52a0\u800c\u9010\u6e10\u51cf\u5c0f\u7684\u56e0\u5b50\uff0c\u540c\u65f6cos\u63d0\u4f9b\u4e86\u968f\u673a\u6027\u3002<\/p>\n\n\n\n

\u4fee\u6b63\u7684\u7c92\u5b50\u7fa4\u901f\u5ea6\u5141\u8bb8\u7c92\u5b50\u4eec\u63a2\u7d22\u66f4\u5927\u672a\u8bbf\u95ee\u7684\u533a\u57df\uff0c\u5927\u7684R(t)\u5c06\u4f7f\u7c92\u5b50\u4eec\u79bb\u5f00\u5f53\u524d\u7684\u533a\u57df\uff0c\u641c\u7d22\u53e6\u4e00\u4e2a\u533a\u57df\uff0c\u800c\u5c0f\u7684R(t)\u7cbe\u7ec6\u5316\u4e86\u5f53\u524d\u6700\u4f18\u4f4d\u7f6e\u9644\u8fd1\u7684\u63a2\u7d22\u3002<\/p>\n\n\n\n

\uff082\uff09\u9488\u5bf9\u4e2a\u4f53\u6700\u4f18\u7684\u52a8\u6001\u5bf9\u7acb\u5b66\u4e60\u7b56\u7565<\/p>\n\n\n\n

\u81ea\u9002\u5e94\u9ad8\u65af\u5206\u5e03\u7684\u52a8\u6001OBL\u7b56\u7565->\u5e2e\u52a9\u4e2a\u4f53\u6700\u4f18\u8df3\u51fa\u5c40\u90e8\u6700\u4f18\u89e3\u3002
OBL\u6700\u65e9\u7531\u6587\u732eOpposition based differential evolution<\/em>\u63d0\u51fa\uff0c\u5141\u8bb8\u5f53\u524d\u7684\u7fa4\u4f53\u7b97\u6cd5\u5728\u641c\u7d22\u7684\u53cd\u65b9\u5411\u641c\u7d22\u6700\u4f18\u70b9\u3002\u6587\u732eMathematical and experimental analyses of oppositional algorithms<\/em>\u8bc1\u660e\u76f8\u53cd\u7684\u70b9\u6bd4\u968f\u673a\u70b9\u6536\u76ca\u66f4\u5927\uff0c\u4e14\u80fd\u591f\u52a0\u901f\u5176\u5b83\u6f14\u5316\u7b97\u6cd5\u7684\u6536\u655b\u3002<\/p>\n\n\n\n

OBL\u7684\u57fa\u672c\u601d\u60f3\u662f\u5728\u7c92\u5b50\u5411\u524d\u63a2\u7d22\u65f6\uff0c\u540c\u65f6\u8fdb\u884c\u53cd\u5411\u641c\u7d22\uff1a$\\tilde{x}=a+b-x$\u3002\u5176\u4e2d\uff0c$x$\u662f\u4f4d\u4e8e\u95f4\u9694[a,b]\u4e4b\u95f4\u7684\u5b9e\u6570\uff0c$\\tilde{x}$\u4e3a$x$\u7684\u76f8\u53cd\u6570\u3002\u5bf9\u4e8e$D$\u7ef4\u7a7a\u95f4\u7684\u53c2\u6570\u4f18\u5316\uff0c\u5373$x_1, x_2, \\ldots, x_D \\in R$\uff0c\u4e14$x_i \\in\\left[a_i, b_i\\right]$\uff0c\u6709\uff1a$\\tilde{x}_ i=a_i+b_i-x_i$\u3002<\/p>\n\n\n\n

\u4e3a\u4e86\u514b\u670d\u4f20\u7edfOBL\u7684\u7f3a\u70b9\uff0c\u63d0\u5347pBest\u7684\u6536\u655b\u901f\u5ea6\uff0c\u57fa\u4e8e\u81ea\u9002\u5e94\u9ad8\u65af\u5206\u5e03\u7684\u52a8\u6001OBL\u7b56\u7565\u8bbe\u8ba1\u4e3a\uff1a<\/p>\n\n\n\n

$op\\operatorname{Best}_{id}=a_d(t)+b_d(t)-\\left(1-\\operatorname{Gaussian}\\left(\\mu, \\sigma^2\\right)\\right) \\cdot pBest_{id}$<\/p>\n\n\n\n

\u5176\u4e2d\uff0c$a_d(t)=\\min \\left(p \\operatorname{Best}_{\\mathrm{id}}\\right)$\uff0c$b_d(t)=\\max \\left(p \\operatorname{Best}_{\\mathrm{id}}\\right)$\uff0c\u5373\u5206\u522b\u5bf9\u5e94$pBest_{id}$\u7684\u6700\u5c0f\u503c\u548c\u6700\u5927\u503c\u3002$\\operatorname{Gaussian}\\left(\\mu, \\sigma^2\\right)$\u4e3a\u4e00\u4e2a\u9ad8\u65af\u5206\u5e03\u7684\u968f\u673a\u6570\uff0c\u53d6$\\mu=0$\uff0c\u5373\u4e3a\u96f6\u5747\u503c\u7684\u9ad8\u65af\u5206\u5e03\uff0c$\\sigma$\u4e3a\u9ad8\u65af\u5206\u5e03\u7684\u6807\u51c6\u5dee\u3002<\/p>\n\n\n\n

\u4e3a\u4e86\u83b7\u53d6\u4e00\u4e2a\u66f4\u4f73\u7684$pBest$\u52a8\u6001\u5b66\u4e60\u6027\u80fd\uff0c\u8bbe\u5b9a$\\sigma$\u4ee5\u975e\u7ebf\u6027\u51cf\u5c11\uff0c\u5176\u8ba1\u7b97\u516c\u5f0f\u4e3a\uff1a$\\sigma=\\sigma_{\\min }+\\left(\\sigma_{\\max }-\\sigma_{\\min }\\right)\\left(1-\\frac{t}{T}\\right)^2$<\/p>\n\n\n\n

\u5176\u4e2d\uff0c$\\sigma_{max}$\u5728\u672c\u7814\u7a76\u4e2d\u53d6\u56fa\u5b9a\u503c1\uff0c$\\sigma_{min}$\u53d6\u56fa\u5b9a\u503c0\u3002\u91c7\u7528Box-Muller\u8f6c\u6362$\\sqrt{-2 \\ln \\left(1-u_1\\right)} \\cdot \\cos \\left(2 \\pi \\cdot u_2\\right)$\uff08$u_1$\u548c$u_2$\u662f\u5728\u533a\u95f4[0,1]\u7684\u968f\u673a\u6570\uff09\u83b7\u53d6\u4e00\u4e2a\u9ad8\u65af\u5206\u5e03\u968f\u673a\u503c\uff0c\u8fdb\u800c\u53ef\u4ee5\u5f97\u5230\u4e00\u4e2a\u968f\u8fed\u4ee3\u6b21\u6570\u589e\u52a0\u800c\u4e0d\u65ad\u53d8\u5c0f\u7684\u53d8\u91cf\uff1a<\/p>\n\n\n\n

$\\operatorname{Gaussian}\\left(\\mu, \\sigma^2\\right)=\\mu+\\sigma \\sqrt{-2 \\ln \\left(1-u_1\\right)} \\cdot \\cos \\left(2 \\pi \\cdot u_2\\right)$<\/p>\n\n\n\n

\"\"\/<\/figure>
\n

\u9488\u5bf9pBests\u7684\u52a8\u6001OBL\u7b56\u7565\u539f\u7406\u56fe\u5982\u53f3\u56fe\u6240\u793a\uff0c\u5176\u4e2d$O_c$\u4e3a\u5b66\u4e60\u6982\u7387\uff0c\u7b26\u53f7$d$\u8868\u793a\u4ece\u603b\u7ef4\u5ea6$D$\u4e2d\u968f\u673a\u9009\u62e9\u3002\u7531\u4e8e\u5e76\u975e\u6240\u6709\u7ef4\u5ea6\u7c92\u5b50\u8ba1\u7b97\u76f8\u53cd\u503c\u5e76\u53d1\u751f\u6539\u53d8\uff0c\u6545\u53ef\u4ee5\u4fdd\u7559\u539f\u59cb\u4e2a\u4f53\u4e2d\u7684\u6709\u7528\u4fe1\u606f\u3002<\/p>\n\n\n\n

\u8fdb\u884cOBL\u7684\u70b9\u4e2d\uff0c\u8be5\u70b9\u548c\u5176\u5bf9\u5e94\u7684\u76f8\u53cd\u503c\u88ab\u540c\u65f6\u8fdb\u884c\u8bc4\u4f30\uff0c\u4ee5\u4fbf\u7ee7\u7eed\u4f7f\u7528\u6700\u4f73\u7684\u70b9\uff0c\u5373\uff0c\u5982\u679c$pBest_i{ }^{\\text {new }}$\u7684\u9002\u5e94\u5ea6\u8981\u4f18\u4e8e$pBest$\u7684\u9002\u5e94\u5ea6\uff0c\u5219\u7b2c$i$\u4e2a\u7c92\u5b50\u7684\u4e2a\u4f53\u6700\u4f18$pBest_i$\u5c06\u4f1a\u88ab$opBest_i$\u53d6\u4ee3\u3002\u6b64\u65b9\u6cd5\u4e3apBest\u63d0\u4f9b\u4e86\u4e00\u4e2a\u6270\u52a8\uff0cOBL\u8df3\u51fa\u6781\u503c\u70b9\u7684\u6027\u80fd\u5f97\u4ee5\u63d0\u5347\u3002\u2018<\/p>\n<\/div><\/div>\n\n\n\n

\u53c2\u6570\u8bbe\u5b9a\uff1a\u79cd\u7fa4\u7684\u5927\u5c0f\u8bbe\u7f6e\u4e3a50\uff0c\u60ef\u6027\u6743\u91cd\u8bbe\u5b9a\u4e3a[0.9, 0.4]\uff0c\u4e24\u4e2a\u52a0\u901f\u5ea6\u56e0\u5b50c1\u548cc2\u8bbe\u5b9a\u4e3a1.49445\uff0c\u8c03\u8282\u53c2\u6570$\\lambda$\u8bbe\u5b9a\u4e3a6\uff0c\u5bf9\u7acb\u5b66\u4e60\u6982\u7387$O_c$\u8bbe\u5b9a\u4e3a0.38\u3002\u6240\u6709\u7684PSO\u7b97\u6cd5\uff0c\u53c2\u6570\u8bbe\u5b9a\u5747\u76f8\u540c\uff0c\u8fed\u4ee3\u6b21\u6570300\uff0c\u8fd0\u884c\u6b21\u657030\uff0c\u5728\u76f8\u540c\u7684\u786c\u4ef6\u548c\u8f6f\u4ef6\u5e73\u53f0\u4e0a\u8fd0\u884c\u3002\u6240\u6709\u5b9e\u9a8c\u5747\u5728\u914d\u5907Intel Core i5-2450M\u548c4.0 GB DDR3 RAM\u7684\u76f8\u540c\u8ba1\u7b97\u673a\u4e0a\u8fdb\u884c\u3002<\/p>\n\n\n\n

\"\"\/<\/figure>
\n

\u4ece\u53f3\u56fe\u53ef\u4ee5\u770b\u51fa\uff0cDPSO-LS\u7684\u6536\u655b\u901f\u5ea6\u6bd4\u5176\u4ed6\u6df7\u5408PSOs\u66f4\u5feb\u3002DPSO-LS\u7684\u66f4\u597d\u6027\u80fd\u53ef\u4ee5\u4ece\u4e24\u4e2a\u65b9\u9762\u89e3\u91ca\u3002\u9996\u5148\uff0c\u8bbe\u8ba1\u4e86\u4e00\u79cd\u4f7f\u7528\u53ef\u53d8\u63a2\u7d22\u5411\u91cf\u7684\u65b0\u578b\u79fb\u52a8\u4fee\u6b63\u65b9\u7a0b\u6765\u66f4\u65b0\u7c92\u5b50\u7684\u901f\u5ea6\u3002\u5176\u6b21\uff0c\u5f15\u5165\u4e86\u4e00\u4e2a\u81ea\u9002\u5e94\u9ad8\u65af\u5206\u5e03\u7684\u52a8\u6001OBL\u673a\u5236\uff0c\u4ee5\u514b\u670d\u901a\u8fc7\u968f\u673a\u6f14\u5316\u5bfb\u627e$pBest$\u65f6\u7684\u76f2\u76ee\u6027\uff0c\u5e76\u4f7f\u5176\u8df3\u51fa\u5c40\u90e8\u6700\u4f18\u3002<\/p>\n<\/div><\/div>\n\n\n\n

3. 2022 Expert Systems With Applications: Novel enhanced Salp Swarm Algorithms using opposition-based learning schemes for global optimization problems<\/h5>\n\n\n\n

\u57fa\u4e8e\u5bf9\u7acb\u7684\u5b66\u4e60\u7b56\u7565\uff1a\u5143\u542f\u53d1\u5f0f\u65b9\u6cd5\u5b58\u5728\u7684\u5c40\u90e8\u6700\u4f18\u548c\u6536\u655b\u6027\u95ee\u9898\uff0c\u901a\u8fc7\u751f\u6210\u76f8\u53cd\u7684\u641c\u7d22\u65b9\u6848\uff0c\u4ee5\u63d0\u9ad8\u641c\u7d22\u8fc7\u7a0b\u4e2d\u7684\u7a7a\u95f4\u8986\u76d6\u3001\u51c6\u786e\u6027\u4ee5\u53ca\u6536\u655b\u6027->OBL\u7b56\u7565\u6709\u52a9\u4e8e\u6536\u655b\u3002<\/p>\n\n\n\n

\u542f\u53d1\u5f0f\u6c42\u89e3\u80cc\u666f\uff1a\u82e5\u968f\u673a\u731c\u6d4b\u63a5\u8fd1\u4e8e\u5168\u5c40\u6700\u4f18\u70b9\uff0c\u79cd\u7fa4\u5c06\u5feb\u901f\u6536\u655b\uff1b\u53e6\u4e00\u65b9\u9762\uff0c\u82e5\u968f\u673a\u731c\u6d4b\u79bb\u89e3\u975e\u5e38\u8fdc\uff0c\u5982\u5728\u6700\u574f\u76f8\u53cd\u7684\u60c5\u51b5\uff0c\u4f18\u5316\u5219\u9700\u8981\u76f8\u5f53\u957f\u7684\u65f6\u95f4\u751a\u81f3\u96be\u4ee5\u5904\u7406\u3002\u82e5\u6ca1\u6709\u5148\u9a8c\u77e5\u8bc6\uff0c\u6700\u521d\u65e0\u6cd5\u505a\u51fa\u6700\u4f73\u731c\u6d4b\uff0c\u56e0\u6b64\uff0c\u6211\u4eec\u5e94\u5728\u4f18\u5316\u8fc7\u7a0b\u4e2d\u8fdb\u884c\u53cd\u5411\u641c\u7d22\u3002<\/p>\n\n\n\n

\"\"\/<\/figure>
\n

\u672c\u6587\u6240\u63d0\u7684\u65b9\u6cd5\uff1a1\uff09\u521d\u59cb\u5316\u4e2a\u4f53\u6570\u4e3aN\u7684\u79cd\u7fa4\uff0c\u5206\u522b\u8ba1\u7b97\u5f53\u524d\u7c92\u5b50\u4f4d\u7f6e\u548c\u53cd\u5411\u4f4d\u7f6e\u7684\u9002\u5e94\u5ea6\u3002\u9009\u62e9\u4ece\u521d\u59cb\u4f4d\u7f6e\u548c\u53cd\u5411\u4f4d\u7f6e\u9009\u53d6N\u4e2a\u6700\u4f18\u7684\u503c\uff1b2\uff09\u5bf9\u7c92\u5b50\u7684\u4f4d\u7f6e\u8fdb\u884c\u66f4\u65b0\u8fed\u4ee3\uff0c\u82e5\u6ee1\u8db3\u6761\u4ef6\u5219\u9000\u51fa\u3002\u4e0d\u6ee1\u8db3\u5219\u8ba1\u7b97\u9002\u5e94\u5ea6\uff0c\u4ece\u539f\u59cb\u7684\u89e3\u548c\u53cd\u5411\u7684\u89e3\u4e2d\u9009\u51faN\u4e2a\uff0c\u66f4\u65b0\u7c92\u5b50\u4f4d\u7f6e\uff0c\u7ee7\u7eed\u8fed\u4ee3\uff0c\u76f4\u5230\u8fbe\u5230\u8bbe\u5b9a\u7684\u6761\u4ef6\u3002<\/p>\n\n\n\n

\"\"<\/figure>\n<\/div><\/div>\n\n\n\n

\u8fed\u4ee3\u8fc7\u7a0b\u4e2d\uff0cOBL\u53cd\u5411\u4f4d\u7f6e\u6c42\u53d6\u7b56\u7565\uff1a<\/p>\n\n\n\n

$a_j(t)=\\min_{\\forall i}{x_{i j}(t)}$, $b_j(t)=\\max_{\\forall i}{x_{i j}(t)}$, $\\check{x}_{i j}=a_j(t)+b_j(t)-x_{i j}$<\/p>\n","protected":false},"excerpt":{"rendered":"

1.2023 TNNLS\uff1aA Novel Swarm Exploring Varying Parameter […]<\/p>\n","protected":false},"author":2,"featured_media":0,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":[],"categories":[19,31],"tags":[],"special":[],"_links":{"self":[{"href":"https:\/\/luckytian.cn\/index.php?rest_route=\/wp\/v2\/posts\/2016"}],"collection":[{"href":"https:\/\/luckytian.cn\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/luckytian.cn\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/luckytian.cn\/index.php?rest_route=\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/luckytian.cn\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=2016"}],"version-history":[{"count":68,"href":"https:\/\/luckytian.cn\/index.php?rest_route=\/wp\/v2\/posts\/2016\/revisions"}],"predecessor-version":[{"id":2158,"href":"https:\/\/luckytian.cn\/index.php?rest_route=\/wp\/v2\/posts\/2016\/revisions\/2158"}],"wp:attachment":[{"href":"https:\/\/luckytian.cn\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=2016"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/luckytian.cn\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=2016"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/luckytian.cn\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=2016"},{"taxonomy":"special","embeddable":true,"href":"https:\/\/luckytian.cn\/index.php?rest_route=%2Fwp%2Fv2%2Fspecial&post=2016"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}