Short-term load forecasting using bayesian neural networks learned by Hybrid Monte Carlo algorithm

This paper presents a short term load forecasting model based on Bayesian neural network (shorted as BNN) learned by the Hybrid Monte Carlo (shorted as HMC) algorithm. The weight vector parameter of the Bayesian neural network is a multi-dimensional random variable. In learning process, the Bayesian neural network is considered as a special Hamiltonian dynamical system, and the weights vector as the system position variable. The HMC algorithm is used to learn the weight vector parameter with respect to Normal prior distribution and Cauchy prior distribution, respectively. The Bayesian neural networks learned by Laplace algorithm and HMC algorithm and the artificial neural network (ANN) learned by the BP algorithm were used to forecast the hourly load of 25 days of April (Spring), August (Summer), October (Autumn) and January (Winter), respectively. The roots mean squared error (RMSE) and the mean absolute percent errors (MAPE) were used to measured the forecasting performance. The experimental result shows that the BNNs learned by HMC algorithm have far better performance than the BNN learned by Laplace algorithm and the neural network learned BP algorithm and the BNN learned by HMC has powerful generalizing capability, it can welly solve the overfitting problem.     

Robust H ∞ control of uncertain nonlinear switched systems using constructive method

This paper focuses on the problem of robust H _?? control of nonlinear switched systems with parameter uncertainty via the multiple Lyapunov functions (MLFs) approach. The uncertain parameters are assumed to be in a known compact set and are allowed to enter the system nonlinearly. Based on the explicit construction of Lyapunov functions, which avoids solving the Hamilton-Jacobi-Isaacs (HJI) inequalities, sufficient conditions for the solvability of the robust H _?? control problem of cascade nonlinear switched systems are derived under some switching signal. Then, the result is extended to solve the robust H _?? control problem of nonlinear switched systems in strict feedback form. Finally, the effectiveness of the proposed results is illustrated through a simulation example.     

FD—140型高灵敏测氡仪及其应用

FD—140型高灵敏测氡仪用于测量氡的浓度,测氡灵敏度可达15mBq/m~3 min。该仪器可用于普查与勘探铀矿床,也可用于找石油、煤、金、地下水和地震预报以及地质构造调查等方面。     

项目管理在IT企业中的推广与应用

现阶段传统的管理模式还是一些中小型IT企业的主要管理方式。这种方式导致很多中小型IT企业发展的新旧项目成功率都很小。所以,在当前情况下,要大大加强项目管理的涉及度,使之进入中小IT企业。从而,提高中小企业的核心竞争力。那么什么IT企业,何为项目管理,项目管理在IT企业中的推广应用,以及二者之间的相互关系就是我们研究的重要课题。     

天然沸石与纳滤组合工艺处理铜突发污染的应用

纳滤工艺被广泛应用于分散式饮用水深度处理,能解决饮用水苦咸化,盐碱化或微污染等常规水处理工艺无法规避的用水风险,在长时间运行过程中还能有效应对重金属等突发污染风险。但重金属污染易加重纳滤膜污染,需要增设预处理装置加以缓冲,实现纳滤装置的长久稳定运行。而天然沸石具有良好的筛分性能和吸附性能,能够有效缓冲重金属对纳滤装置的冲击。试验以重金属铜为例,证明水中铜离子会造成纳滤不可逆污染比例增加,不利于系统稳定运行;天然沸石对铜离子有很好的吸附效果,静态吸附试验表明天然沸石对水中铜离子的最大吸附量为3.03 mg/g,通过正交试验合理设计吸附预处理,能够有效为纳滤工艺提供安全进水,保证纳滤进水铜离子浓度低于10 mg/L。实践工艺中,吸附预处理能有效缓解纳滤膜不可逆污染,而且吸附-纳滤组合工艺对铜离子及部分其他重金属离子表现出良好的处理效果。     

Damping forced oscillations in power system via interline power flow controller with additional repetitive control

With the continuous expansion of power systems and the application of power electronic equipment, forced oscillation has become one of the key problems in terms of system safety and stability. In this paper, an interline power flow controller (IPFC) is used as a power suppression carrier and its mechanism is analyzed using the linearized state-space method to improve the system damping ratio. It is shown that although the IPFC can suppress forced oscillation with well-designed parameters, its capability of improving the system damping ratio is limited. Thus, combined with the repetitive control method, an additional repetitive controller (ARC) is proposed to further dampen the forced power oscillation. The ARC control scheme is characterized by outstanding tracking performance to a system steady reference value, and the main IPFC controller with the ARC can provide higher damping, and further reduce the amplitude of oscillations to zero compared with a supplementary damping controller (SDC). Simulation results show that the IPFC with an ARC can not only greatly reduce the oscillation amplitude, but also actively output the compensation power according to the reference value of the ARC tracking system.     

关键目标选择问题模型研究

现代信息化战争多使用打击精度高的中远程武器,保证了稳准狠的条件,但目标体系往往有多个目标单元,具体打击哪些目标单元就成了首要问题。构建了目标体系网络,运用场理论中势函数的概念对目标体系的作战能力进行量化,通过定义三元组(打击行动结果、目标单元状态和目标单元间失效影响关系)来描述目标体系网络级联失效关系,以效费比最优为目标函数,建立了关键目标选择模型。举例说明了该方法的合理性和有效性,为指挥员进行关键目标选择提供有效的解决思路。     

表面工程技术在导弹武器装备维修中的应用

本文主要介绍铝/F_(46),协合涂层新技术、复合电刷镀Ni—PTFE新工艺、DJB—823电接触保护剂及三防电子器件绝缘清漆在二炮导弹武器装备维修中的应用。     

充放电过程液相锂离子浓度变化及机理

采用三电极电池实时监测不同倍率充放电过程中全电池、正极对锂、负极对锂以及浓差电池电压变化,得到不同倍率下充放电过程中正负极之间液相锂离子浓度变化规律,与此同时还研究了不同层数隔膜三电极电池正负极之间液相锂离子浓度的变化趋势.本工作通过恒电流间歇滴定法(GITT)测试了三电极电池中正极Li(Ni0.65Co0.2Mn0.15)O2(NCM65)电极表观化学扩散系数和负极石墨电极表观化学扩散系数.结果表明,充放电过程中正负极之间液相锂离子浓度变化与负极对锂电位有关,且充电过程正负极之间液相锂离子浓度大于放电过程正负极之间液相锂离子浓度.充电过程中,倍率越大,正负极之间液相锂离子浓度越大,放电过程则相反.通过增加正负极之间隔膜层数以此增加扩散路径,隔膜层数增加正负极之间液相锂离子浓度有所降低,总体锂离子浓度变化趋势保持不变,但靠近正负极侧液相锂离子浓度有一定差异.GITT测试正极NCM65电极表观化学扩散系数(3.57×10-9～5.63×10-8cm2/s)大于负极石墨电极表观化学扩散系数(1.16×10-10～8.21×10-8cm2/s),且负极石墨表观化学扩散系数的变化趋势也与负极对锂电位有关,因此得出正极脱嵌锂速度大于负极,液相锂离子浓度变化受负极扩散的影响.     

330 kV变电站35 kV侧经小电阻接地改造技术可行性分析

330 kV变电站35 kV高压设备及电缆单相接地故障,因短路电流无法达到保护动作条件而导致事故进一步扩大。为了提高330 kV变电站35 kV系统运行可靠性,提出了35 kV侧经接地变压器和小电阻接地的方式。提出了小电阻接入方案,并通过仿真系统建立了基于实际变电站的建模,分析了小电阻接地前后短路电流变化情况,论证了接地电阻、电容器投退对短路零序电流的影响,从而证实了小电阻接地的可行性。