变压器油中溶解气体体积分数是表征变压器健康状态及故障特性的重要参量。因此,准确预测变压器油中溶解气体的体积分数,有助于及时把握变压器的状态演化与故障发展趋势。现有对气体体积分数预测的研究多集中在点预测方面,难以全面反映...变压器油中溶解气体体积分数是表征变压器健康状态及故障特性的重要参量。因此,准确预测变压器油中溶解气体的体积分数,有助于及时把握变压器的状态演化与故障发展趋势。现有对气体体积分数预测的研究多集中在点预测方面,难以全面反映气体体积分数的不确定性信息。针对此问题,提出了一种基于灰狼优化长短期记忆网络(long short⁃term memory based on grey wolf optimization,GWO⁃LSTM)与非参数核密度估计(non⁃parametric kernel density estimation,NKDE)的变压器油中溶解气体体积分数点—区间联合预测方法。首先,搭建变压器油中溶解气体体积分数点—区间联合预测模型的整体结构,阐述预测的实现过程;其次,利用自适应噪声完备集合经验模态分解方法将气体体积分数原始序列分解成若干个较为平缓的子序列,再基于GWO⁃LSTM对上述子序列分别进行点预测,并将所有子序列点预测结果叠加合成还原为气体体积分数点预测结果;然后,基于气体体积分数点预测结果及NKDE构造气体体积分数预测误差的概率密度估计函数,进而生成不同置信水平下的区间预测结果;最后,对所提方法进行算例分析,算例结果验证了所提方法的有效性。展开更多
In order to realize the memory cutting of a shearer, made use of the memorizedcutting path and acquisitioned cutting parameters, and realized the teaching and playbackof the cutting path.In order to optimize the memor...In order to realize the memory cutting of a shearer, made use of the memorizedcutting path and acquisitioned cutting parameters, and realized the teaching and playbackof the cutting path.In order to optimize the memory cutting path of a shearer, took intoaccount the constraints of coal mining craft, coal quality and the adaption faculty of coalmining equipments.Genetic algorithm theory was used to optimize the memory cutting ofshearer and simulate with Matlab, and realized the most valuable mining recovery rate.The experimental results show that the optimization of the memory cutting path of ashearer based on the genetic algorithm is feasible and obtains the most valuable memorycutting path, improving the ability of shearer automatic cutting.展开更多
贝叶斯模型平均(Bayesian model averaging,BMA)是最近提出的一种用于多模式集合预报的统计方法.进行贝叶斯模型平均需要准确估算模型集合中每个竞争模型的权重与方差,经常采用的方法是期望最大化(Expectation-Maximization,EM)方法与...贝叶斯模型平均(Bayesian model averaging,BMA)是最近提出的一种用于多模式集合预报的统计方法.进行贝叶斯模型平均需要准确估算模型集合中每个竞争模型的权重与方差,经常采用的方法是期望最大化(Expectation-Maximization,EM)方法与马尔可夫链蒙特卡洛(Markov Chain Monte Carlo,MCMC)方法,两种方法各有优劣.本文首先对BMA的(对数)似然函数进行改进使之无需BMA权重之和为1的显式约束,并利用一种有限记忆的拟牛顿优化算法(LBFGS-B)对其进行极大化,由此提出了一种求解贝叶斯模型平均的新方法(BMA-BFGS).采用三个陆面模式进行的土壤湿度多模式数值模拟试验表明:在计算精度方面,BMA-BFGS的精度与MCMC方法几乎一致,优于EM算法;在计算耗时性方面,BMA-BFGS的计算耗时与EM算法相当,远小于MCMC方法.展开更多
文摘变压器油中溶解气体体积分数是表征变压器健康状态及故障特性的重要参量。因此,准确预测变压器油中溶解气体的体积分数,有助于及时把握变压器的状态演化与故障发展趋势。现有对气体体积分数预测的研究多集中在点预测方面,难以全面反映气体体积分数的不确定性信息。针对此问题,提出了一种基于灰狼优化长短期记忆网络(long short⁃term memory based on grey wolf optimization,GWO⁃LSTM)与非参数核密度估计(non⁃parametric kernel density estimation,NKDE)的变压器油中溶解气体体积分数点—区间联合预测方法。首先,搭建变压器油中溶解气体体积分数点—区间联合预测模型的整体结构,阐述预测的实现过程;其次,利用自适应噪声完备集合经验模态分解方法将气体体积分数原始序列分解成若干个较为平缓的子序列,再基于GWO⁃LSTM对上述子序列分别进行点预测,并将所有子序列点预测结果叠加合成还原为气体体积分数点预测结果;然后,基于气体体积分数点预测结果及NKDE构造气体体积分数预测误差的概率密度估计函数,进而生成不同置信水平下的区间预测结果;最后,对所提方法进行算例分析,算例结果验证了所提方法的有效性。
基金Supported by the High-Tech Research and Development Program of China(2008AA062202)Fok Ying Tung Education Foundation(114003)New Teacher Foundation for the Doctoral Program of Ministry of Education(20070290538)
文摘In order to realize the memory cutting of a shearer, made use of the memorizedcutting path and acquisitioned cutting parameters, and realized the teaching and playbackof the cutting path.In order to optimize the memory cutting path of a shearer, took intoaccount the constraints of coal mining craft, coal quality and the adaption faculty of coalmining equipments.Genetic algorithm theory was used to optimize the memory cutting ofshearer and simulate with Matlab, and realized the most valuable mining recovery rate.The experimental results show that the optimization of the memory cutting path of ashearer based on the genetic algorithm is feasible and obtains the most valuable memorycutting path, improving the ability of shearer automatic cutting.
文摘贝叶斯模型平均(Bayesian model averaging,BMA)是最近提出的一种用于多模式集合预报的统计方法.进行贝叶斯模型平均需要准确估算模型集合中每个竞争模型的权重与方差,经常采用的方法是期望最大化(Expectation-Maximization,EM)方法与马尔可夫链蒙特卡洛(Markov Chain Monte Carlo,MCMC)方法,两种方法各有优劣.本文首先对BMA的(对数)似然函数进行改进使之无需BMA权重之和为1的显式约束,并利用一种有限记忆的拟牛顿优化算法(LBFGS-B)对其进行极大化,由此提出了一种求解贝叶斯模型平均的新方法(BMA-BFGS).采用三个陆面模式进行的土壤湿度多模式数值模拟试验表明:在计算精度方面,BMA-BFGS的精度与MCMC方法几乎一致,优于EM算法;在计算耗时性方面,BMA-BFGS的计算耗时与EM算法相当,远小于MCMC方法.
