ACO—BP在神经网络训练中的研究与应用

针对神经网络收敛速度慢、易于陷入局部最优等问题,可将蚁群算法与人工神经网络相融合的方法来解决,但容易出现训练时间与训练精度、泛化能力之间的矛盾.为解决上述矛盾,提出将蚁群优化算法与反向传播算法相融合共同完成神经网络训练的方法.算法首先采用蚁群优化算法对网络权值进行整体寻优,克服反向传播算法容易陷入局部最优的不足再以找到的较优的权值为初值,采用反向传播算法做进一步的寻优,克服单一训练网络时间较长、精度不高的缺点.最后对ACO-BP与反向传播算法进行了比较,给出两种算法在不同隐结点数目下的检验误差值和两种网络在矿选指标中的应用效果.通过对实验结果的分析.表明ACO-BP算法要优于反向传播算法.     

网络化控制系统中状态估计策略的进展

在网络化控制系统(Networked Control Systems,简记为NCSs)中,由于网络的介入使控制系统的规模和复杂性显著增加,且产生了各种新问题,为了使控制更加容易,需要设计合理的估计策略.主要从控制和通信2个角度出发,集中考虑了在量化影响、时延与丢包、不确定性等通信受限因素下状态估计策略的研究与进展.一直以来,状态估计都是诸如过程监控、故障诊断等控制领域中不可缺少的重要部分,当前已成为网络化控制系统研究的热点和准点,为抵消网络环境不确定性对闭环系统性能的影响,设计最优的状态估计策略必将成为不可缺少的因素之一.     

Amine Coordinated Electron-Rich Palladium Nanoparticles for Electrochemical Hydrogenation of Benzaldehyde

Electrocatalytic hydrogenation (ECH) is a burgeoning strategy for the sustainable utilization of hydrogen. However, how to effectively suppress the competitive hydrogen evolution reaction (HER) is a big challenge to ECH catalysis. In this study, amine (NH₂ R)-coordinated Pd nanoparticles loaded on carbon felt (Pd@CF) as a catalyst is successfully synthesized by a one-step solvothermal reduction method using oleylamine as the reducing agent. An exceptional ECH reactivity on benzaldehyde is achieved on the optimal Pd@CF catalyst in terms of a high conversion (89.7%) and selectivity toward benzyl alcohol (89.8%) at −0.4 V in 60 min. Notably, the Faradaic efficiency for producing benzyl alcohol is up to 90.2%, much higher than that catalyzed by Pd@CF-without N-group (41.1%) and thecommercial Pd/C (20.9%). The excellent ECH performance of Pd@CF can be attributed to the enriched electrons on Pd surface resulted from the introduction of NH₂ R groups, which strengthens both the adsorption of benzaldehyde and the adsorbed hydrogen (H_ads) on Pd, preventing the combination of H_ads to form H₂, that is, inhibiting the HER. This study gives a new insight into design principles of highly efficient electrocatalysts for the hydrogenation of unsaturated aldehydes molecules.     

Neural-network-based fuzzy logic control of a 3D rigid pendulum

International Journal of Control, Automation and Systems - This paper concerns the attitude control problem of a 3D rigid pendulum based on dynamic T-S fuzzy neural model. A generalized 3D rigid...     

Toxicoproteomics and its application to human health risk assessment

Toxicoproteomics is the use of proteomic technologies to better understand environmental and genetic factors, toxic mechanisms, and modes of action in response to acute exposure to toxicants and in the long-term development of diseases caused or influenced by these exposures. Use of toxicoproteomic technologies to identify key biochemical pathways, mechanisms, and biomarkers of exposure and toxicity will decrease the uncertainties that are associated with human health risk assessments. This review provides an overview of toxicoproteomics from human health risk assessment perspectives. Key toxicoproteomic technologies such as 2-D gel-based proteomic methods and toxicoproteomic approaches are described, and examples of applications of these technologies and methodologies in the risk assessment context are presented. The discussion includes a focus on challenges and future directions.     

Interfacing industrial R&A equipment using Matlab

We present a toolbox that enables access to real robotics and automation (R&A) equipment from the MATLAB shell. If used in conjunction with a robotics toolbox, it will extend significantly their application, i.e., besides robotic simulation and data analysis, the user can interact online with the equipment he or she is using. This article briefly presents the software architecture adopted and how it was used to generate the MATLAB MEX files presented. It then exemplifies application to two types of equipment, complemented with a generic manipulation example using a robotic gripper. The utilization of this tool with force control experiments is also briefly explored