基于信息的智能控制理论研究

本文介绍的基于信息的智能控制理论的发展过程，主要分为智能控制的信息指标和智能控制的信息结构分析两部分，文中在最后对这套理论可能的发展方向进行了探讨。     

智能控制的理论和方法

本文简要地回顾了智能控制的发展过程，讨论了智能控制的几个主要理论与方法，最后对智能控制的发展提出了作者的看法。     

Decentralized control design for large-scale systems with strong interconnections using neural networks

We propose a decentralized neural network (NN) controller for a class of large-scale nonlinear systems with the strong interconnections. The NNs are used to approximate the unknown subsystems and interconnections. Due to the functional approximation capabilities of NNs, the additional precautions are not required to be made for avoiding the possible control singularity problems. Semiglobal asymptotic stability results are obtained and the tracking error converges to zero. Furthermore, the issue of transient performance of the subsystems is also addressed under an analytical framework.     

针对任意传感器失效的反馈设计新方法

本文针对任意传感器的失效，给出了一种反馈设计方法，通过解Ｌｙａｐｕｎｏｖ方程及判定一个不等式的成立，即可给出反馈增益阵的设计，最后用这种方法研究了一个例子。     

一种新的时变大系统递阶控制求解方法

研究了一种新的大系统求解方法,利用Taylor级数的性质,将大系统时变递阶控制问题 转化为代数方程的求解问题.该方法简单,易于编成计算机程序.算例表明了它的有效性.     

基于MATLAB的节流阀调速液压回路计算机仿真

以进油节流阀调速液压回路为例,建立了描述液压调速回路动态特性的集中参数数学模型,给出了在MATLAB环境下建立其仿真模型的方法.应用计算机仿真的方法,研究了节流阀开口度的不同和油液体积弹性模量值的改变对进油节流调速回路动态特性的影响,给出了仿真结果.     

PAM/GO复合材料制备及驱油性能研究

利用改进的Hummers法制备氧化石墨烯(Graphene oxide,GO),并利用原位聚合法引入丙烯酰胺(AM),制备PAM/GO复合材料。采用X射线衍射(XRD)、傅里叶红外光谱(FTIR)、激光粒度分析和驱油实验等分析方法对PAM/GO复合材料的官能团和驱油性能进行了研究。X射线衍射(XRD)、傅里叶红外光谱(FTIR)实验结果表明,PAM/GO的谱图中,在2θ=9.4°的氧化石墨的特征峰消失,在2θ=23°出现一个宽的衍射峰,说明PAM/GO为无定形结构,也说明氧化石墨与PAM兼容性良好,没有发生明显的团聚。傅里叶变换红外光谱分析表明,PAM/GO红外谱图中具有很明显的丙烯酰胺特征峰,说明丙烯酰胺成功引入到氧化石墨烯中。激光粒度分析结果表明,石墨烯复合材料的平均粒径范围在0.19~1.45μm。界面张力分析表明,0.3%浓度的石墨烯材料降低油水界面张力的能力较好,与注入水相比,能将油水界面张力从101降低到100数量级左右。PAM/GO复合材料应用于低渗透岩心的动态驱替实验表明,0.3%浓度的石墨烯复合材料对低渗透油藏提高采收率在10%左右,且驱替压力变化平稳,不会对地层造成堵塞伤害。     

A deep learning scheme for mental workload classification based on restricted Boltzmann machines

The mental workload (MWL) classification is a critical problem for quantitative assessment and analysis of operator functional state in many safety-critical situations with indispensable human–machine cooperation. The MWL can be measured by psychophysiological signals. In this work, we propose a novel restricted Boltzmann machine (RBM) architecture for MWL classification. In relation to this architecture, we examine two main issues: the optimal structure of RBM and selection of the most important EEG channels (electrodes) for MWL classification. The trial-and-error and entropy-based pruning methods are compared for the RBM structure identification. The degree of importance of EEG channels is calculated from the weights in a well-trained network in order to select the most relevant channels for classification task. Extensive comparative results showed that the selected EEG channels lead to accurate MWL classification across subjects.     

SVD-based Preisach hysteresis identification and composite control of piezo actuators

In this paper, the singular value decomposition (SVD) based identification and compensation of the hysteretic phenomenon in piezo actuators are addressed using a Preisach model. First, this paper presents an SVD-based least squares algorithm and a revision approach of the identification through updating the SVD. With the identified parameters and a log of the memory curve, a Preisach-based inversion compensator is constructed which is complemented with a feedback controller to address the inevitable and residual modeling errors. Experimental results are furnished for both the identification and compensation approaches. The Preisach-based feedforward controller significantly improves the tracking performance and reduces the root-mean-square (RMS) tracking error of a PID controller by 76.7% and 89% at 1 Hz and 25 Hz, respectively. With the proposed composite controller, the percent-RMS errors at 1 Hz and 25 Hz are reduced to 0.035% and 0.31%, respectively.     

模糊层次分析法对岩溶塌陷易发程度的评估——以广西来宾市吉利村为例

岩溶塌陷是我国主要的地质灾害,其易发程度的评估预测对减少社会损失有重要意义。以岩溶地貌发育的广西来宾市吉利村为研究实例,应用模糊层次分析法,结合研究区地质状况,引入G1S和遥感技术,对研究区的岩溶塌陷易发程度进行评估。首先确定岩溶塌陷评估因子及其权重值;其次划分塌陷等级,将其分为极易发区、易发区、一般区、较稳定区和稳定区;最后对研究区进行评估预测,对评估结果处理后得出研究区岩溶塌陷易发程度分区图。