针对传统光伏功率预测特征提取不足导致预测精度不高的问题，提出一种双通道网络
模型进行光伏功率预测。首先将光伏功率历史数据进行归一化处理，再将数据送入两个并行的卷积神经网络( Convolutional Neural Network，CNN) 进行特征提取，经融合层融合送入长短期记忆网络( Long Short-Term Memory，LSTM) 进行光伏功率预测。采用地中海气候光伏发电数据集进行测试，结果表明所提出的方法与单通道网络相比平均绝对误差( Mean-Absolute Error，MAE) 减小了 12. 3%，均方根误差( Ｒoot-Mean-Square Error，ＲMSE) 减小了 3%，实现了更高的预测精度。
Aiming at the problem that the traditional PV power prediction feature is insufficiently extracted and the prediction accuracy is not high, a dual-channel network model is proposed for PV power prediction. First, the photovoltaic power historical data is normalized, and then the data is sent to two parallel convolutional neural networks for feature extraction, and the fusion layer is fed to the long-term and short-term memory network for photovoltaic power prediction. Using the Mediterranean climate photovoltaic power generation data set for testing, the results show that the proposed method reduces the average absolute error by 12.3% and the root mean square error by 3% compared with a single channel network, achieving higher prediction accuracy . (2019-12-24, PDF, 200KB, 下载22次)
《算法导论》原书名——《Introduction to Algorithms》，是一本十分经典的计算机算法书籍，与高德纳（Donald E.Knuth）的《计算机程序设计艺术》（《The Art Of Computer Programming》）相媲美。 《算法导论》由Thomas H.Cormen、Charles E.Leiserson、Ronald L.Rivest、Clifford Stein四人合作编著（其中Clifford Stein是第二版开始参与的合著者）。本书的最大特点就是将严谨性和全面性融入在了一起。
"Introduction to Algorithms" original title- "Introduction to Algorithms", is a very classic books computer algorithms, and Gartner (Donald E.Knuth) of the "Art of Computer Programming" ("The Art Of Computer Programming" ) comparable. "Introduction to Algorithms" by the Thomas H.Cormen, Charles E.Leiserson, Ronald L.Rivest, Clifford Stein four co-edited (Clifford Stein is the second edition of which became involved in the co-author). The most important feature of this book is to integrate into the rigor and comprehensiveness in together. (2013-09-24, PDF, 4845KB, 下载4次)
：针对能够采用仿射非线性表示的含有未建模动态的SISO非线性系统，讨论了一种基于神经网络的自适应
控制方法．该方法对受控对象的已知部分．采用反馈线性化方法设计控制器，用神经网络在线补偿未建模动态及
外部干扰等引起的误差，从而实现自适应控制。对具有未建模动态的双车倒立摆设计了输出反馈自适应控制系
统．仿真表明该方法是有效的。
A discussion is devoted to design neural network adaptive control scheme of the SISO (single
input and single output)nonlinear system with unmodeled dynamics．According to the known part of
the plant．feedback Iinearization method iS used to design the controller．The error resulted from the un～
modeled dynamics and the external disturbance is compensated by online neural network．The neural
networks are designed as a five layer fuzzy neural network and its construction is optimized by genetic al—
gorithms．It has been used to approtimate the nonlinear function of system and to compesate the error of
unmodeled dynamic．The design of neural network adaptive controller has better performances．The
method is verified by the digital simulation of tWO—·cart with inverted·-pendulum system and unmodeled
dynamics． (2011-08-01, PDF, 160KB, 下载38次)
新的双基阵纯方位机动目标跟踪算法在目标跟踪的应用
The new bearings two arrays maneuvering target tracking algorithm in the application of target tracking (2011-05-21, PDF, 358KB, 下载4次)
国外论文，关于克里金模型中的均匀拉丁超立方取点方法的研究，通过遗传算法对点点之间的距离进行优化。
International Paper, on the Kriging model in uniform Latin hypercube method of access points, through the genetic algorithm to optimize the distance between the dots. (2011-01-06, PDF, 338KB, 下载56次)
。当各感知用户采用软判决方法,对于2
个感知用户合作和3个感知用户合作的情况,可对最优联合检测算法性能有015dB改善。
. When the user uses soft decision method of perception, perceptual user cooperation for 2 and 3 sensing user cooperation, the joint detection algorithm can best improve the performance of 015dB. (2010-04-26, PDF, 439KB, 下载17次)
混沌时间序列分析以及应用，吕金虎编写的。混沌时间序列比较著名的教材
chaotic time series analysis and applications, Lu Jinhu prepared. Chaotic time series famous teaching (2007-05-03, PDF, 3764KB, 下载129次)