该论文将神经网络应用到烧结终点的预测中，并结合主元分析、灰色理论等人工智能技术，建立了实用有效的预测模型。该方法成功应用于某钢铁企业280m2大型烧结机的在线控制。经过验证，该方法克服了人工判断的随机性，针对不同工况准确预报烧结终点，该预报值可用来指导生产或送控制计算机，为烧结终点智能控制提供操作依据。
In this paper,ANN technology is applied to build the practical and
useful prediction model of BTP,which iS combined with other artificial
intelligent technology such as PCA．gray theory．The method of BTP
intelligent prediction has been successfully applied in on—line control of sintering in 280m2 plant of some iron—steel company．nle result shows．the method Call avoid the randomness of artificial judgment，and providean accurate prediction BTP position under all kinds of state of sintering process，the predict result Can be used to guide the operators or to be used as the dependence o fintelligent control of BTP (2015-11-16, PDF, 2133KB, 下载3次)
DOA估计，OMP算法，算法相关原理，信源方向估计
DOA Estimation OMP algorithm, algorithm principle source direction estimation (2013-04-05, PDF, 8183KB, 下载92次)
DOA估计中MUSIC算法的研究与实现，信源方向估计
Research and Implementation of DOA estimation MUSIC algorithm, the direction of the source estimates (2013-04-05, PDF, 212KB, 下载3次)
齿轮箱早期的故障信号往往十分微弱,信噪比低,这大大限制了已有诊断方法在早期诊断中的应用,因此如何获取真实的振动信号是提高齿轮箱早期故障诊断质量的关键,独立分量分析(ICA)为此提供了一种新的思路。文
中研究了ICA在齿轮箱故障早期诊断中的应用,首先分析了齿轮箱的混合振动信号模型,然后针对具体的轴承故障进行了实验,并使用快速ICA算法分离出轴承的振动信号
The early gearbox fault signal is often very weak, low signal-to-noise ratio, which greatly limits the application of existing diagnostic methods in the early diagnosis, how to obtain the actual vibration signal is to improve the quality of early gearbox fault diagnosis, independent component analysis (ICA) to provide a new way of thinking. In this paper, the application of the ICA in the early diagnosis of gearbox failure, the first analysis of the the mixed vibration signal model of the gearbox, then conducted experiments for specific bearing failure, isolated bearing vibration signal and use the fast ICA algorithm (2013-03-23, PDF, 240KB, 下载23次)
数据
挖掘就是面对海量的存储数据建立数学模型，找出隐含的业务规则和有价值的信
息，在实际应用中发挥作用
Data mining is the face of vast amounts of stored data to a mathematical model to identify the implicit business rules and valuable information to play a role in practical applications (2012-06-16, PDF, 7276KB, 下载2次)
AN ADAPTIVE CONTROLLER BASED ON NEURAL NETWORKS FOR
MOTOR-DRIVE LOAD SIMULATOR
Shen Dongkai Wang Zhanlin
College of Automation Science and Electrical Engineering
Beijing University of Aeronautics and Astronautics Beijing 100083, P.R.China
ridixklh@public3.bta.net.cn
AN ADAPTIVE CONTROLLER BASED ON NEURAL NETWORKS FOR
MOTOR-DRIVE LOAD SIMULATOR
Shen Dongkai Wang Zhanlin
College of Automation Science and Electrical Engineering
Beijing University of Aeronautics and Astronautics Beijing 100083, P.R.China
ridixklh@public3.bta.net.cn (2012-06-16, PDF, 47KB, 下载4次)
〕针对轧钢企业轧机电气设备现有的两类故障诊断系统所存在的实际问题，在企业信息化的大前提下，提出了以
信息集成作为故障诊断的基础，将实时数据报警信息与专家知识相融合，形成一个闭环的故障诊断专家系统。既保证了
故障诊断的实时性、快速性、准确性，获得诊断结果和相应的维修建议，又对轧机设备可能会出现的故障提出了预防性报
警。
a new way to fault diagnosis the mathematics system. (2012-01-31, PDF, 384KB, 下载5次)
针对用户在社区网络中面对海量的信息和资源，如何快速便捷地获得自己感兴趣内容的问题，提出一
种基于社区网络内容的个性化推荐算法。在得到相同兴趣用户聚类的基础上，该算法首先通过用户访问日志信
息挖掘相似内容推荐项，然后根据用户兴趣挖掘新的内容推荐项。实验结果表明，该算法不仅提高了内容推荐
精度，而且扩展了内容覆盖面。
Network for users in the community in the face of a flood of information and resources, how to quickly and easily access content of interest issue, a
Kinds of community-based web content personalized recommendation algorithm. Users get the same interest in the cluster, based on the algorithm begins with the user access log information
Information content of recommended items similar to mining, and mining based on user interest in new content recommended items. Experimental results show that the algorithm not only improve the content recommended
Accuracy, and extend the content coverage. (2011-10-10, PDF, 274KB, 下载28次)
供应链管理实用建模方法及数据挖掘
本书包括：经济全球化及企业竞争优势、供应链管理理论、供应链本流及其定量分析方法、提高供应链管理的运作绩效等内容。
简明目录：
1.经济全球化及企业竞争优势/2.供应链管理理论/3.供应链成本流及其定量分析方法/4.提高供应链管理的运作绩效/5.几种数据驱动型建模方法/6.产品供应链中的数据挖掘技术/7.供应链契约//参考文献
Supply Chain Management Modeling and Data Mining practical book include: Economic Globalization and competitive advantage, supply chain management, supply chain and the quantitative analysis of the flow, improve operational performance in supply chain management and so on. Concise catalog: 1. Economic globalization and competitive advantage/2. Supply chain management theory/3. Supply chain cost stream and its quantitative analysis/4. Improve the operational performance of supply chain management/5. Several data-driven construction model approach/6. product supply chain data mining/7. Supply Chain Contract// References (2010-09-29, PDF, 3067KB, 下载12次)
清华大学胡广书教授《数字信号处理-理论、算法与实现》第二版，可供研究生使用
Tsinghua University Professor Hu Guangshu "Digital Signal Processing- Theory, Algorithm and Implementation of" second edition, available for graduate students to use (2009-01-22, PDF, 13383KB, 下载146次)
文中设计了一个3层径向基神经网络(RBFN)用于对企业的5项评价指标进行聚类分析，并与蚁群算法做了比较分析。RBFN由输入层
到隐含层采用传统的K一均值算法，隐含层到输出层通过“模2递减”学习速率的BP学习；蚁群算法根据信息素的分配能够自动调整收索
路径，从而达到数据自动聚类的目的。结果表明，与蚁群算法相比，改进RBFN具有快速收敛、自动识别奇异样本的优点，而蚁群算法
无须教师学习，并能够达到全局最优。
In this paper, we designed a 3-layer RBF neural network (RBFN) for the 5-to-business evaluation indicators cluster analysis and ant colony algorithm has done a comparative analysis. RBFN from input layer to hidden layer using the traditional K-means algorithm, hidden layer to output layer through the Mode 2 decreasing learning rate of BP learning ant colony algorithm based on pheromone can automatically adjust the allocation of land Faso path, thereby to achieve the purpose of automatic data clustering. The results showed that compared with the ant colony algorithm to improve the RBFN has a fast convergence, automatic identification of singular advantage of the sample, while the ant colony algorithm do not need teachers to learn and be able to reach the global optimum. (2008-09-18, PDF, 162KB, 下载109次)
机器学习 机械工业出版社 中文版
卡耐基梅隆大学教材
machine learning Chinese Machinery Industry Publishing House version of Carnegie Mellon University teaching (2006-10-20, PDF, 9772KB, 下载418次)