Predictive active control of building structures using LQR and artificial intelligence

This study presents a neural network-based model for predicting linear quadratic regulator(LQR)weighting matrices for achieving a target response reduction.Based on the expected weighting matrices,the LQR algorithm is used to determine the various responses of the structure.The responses are determined by numerically analyzing the governing equation of motion using the state-space approach.For training a neural network,four input parameters are considered:the time history of the ground motion,the percentage reduction in lateral displacement,lateral velocity,and lateral acceleration,Output parameters are LQR weighting matrices.To study the effectiveness of an LQR-based neural network(LQRNN),the actual percentage reduction in the responses obtained from using LQRNN is compared with the target percentage reductions.Furthermore,to investigate the efficacy of an active control system using LQRNN,the controlled responses of a system are compared to the corresponding uncontrolled responses.The trained neural network effectively predicts weighting parameters that can provide a percentage reduction in displacement,velocity,and acceleration close to the target percentage reduction.Based on the simulation study,it can be concluded that significant response reductions are observed in the active-controlled system using LQRNN.Moreover,the LQRNN algorithm can replace conventional LQR control with the use of an active control system.

Stochastic Differential Game Model for Decentralized Power Control with Wisdom Regulation Factor in Wearable Audio-Oriented BodyNets

In this study,aiming at the characteristics of randomness and dynamics in Wearable Audio-oriented BodyNets(WA-BodyNets),stochastic differential game theory is applied to the investigation of the problem of transmitted power control inconsumer electronic devices.First,astochastic differential game model is proposed for non-cooperative decentralized uplink power control with a wisdom regulation factor over WA-BodyNets with a one-hop star topology.This model aims to minimize the cost associated with the novel payoff function of a player,for which two cost functions are defined:functions of inherent power radiation and accumulated power radiation damage.Second,the feedback Nash equilibrium solution of the proposed model and the constraint of the Quality of Service(QoS) requirement of the player based on the SIR threshold are derived by solving the Fleming-Bellman-Isaacs partial differential equations.Furthermore,the Markov property of the optimal feedback strategies in this model is verified.The simulation results show that the proposed game model is effective and feasible for controlling the transmitted power of WA-BodyNets.

Design and analysis of control system using neural network for regulated DC power supply

Conventional control systems used for regulated power supplies,including the proportional integral and derivation(PID)controller,have some serious disadvantages.The PID controller has a delayed feedback associated with the control action and requires a lot of mathematical derivations.This paper presents a novel controlling system based on the artificial neural network(ANN),which can be used to regulate the output voltage of the DC power supply.Using MATLABTM,the designed control system was tested and analyzed with two types of back-propagation algorithms.This paper presents the results of the simulation that includes sum-squared error(SSE)and mean-squared error(MSE),and gives a detailed comparison of these values for the two algorithms.Hardware verification of the new system,using RS232 interface and Microsoft Visual Basic 6.0,was implemented,showing very good consistency with the simulation results.The proposed control system,compared to PID and other conventional controllers,requires less mathematical derivation in design and it is easier to implement.

Learning Reactive Power Control Polices in Distribution Networks Using Conditional Value-at-Risk and Artificial Neural Networks

Scalable coordination of photovoltaic(PV)inverters,considering the uncertainty in PV and load in distribution networks(DNs),is challenging due to the lack of real-time communications.Decentralized PV inverter setpoints can be achieved to address this issue by capitalizing on the abundance of data from smart utility meters and the scalable architecture of artificial neural networks(ANNs).To this end,we first use an offline,centralized data-driven conservative convex approximation of chance-constrained optimal power flow(CVaR-OPF)in which conditional value-at-risk(CVaR)is used to compute reactive power setpoints of PV inverter,taking into account PV and load uncertainties in DNs.Following that,an artificial neural network(ANN)controller is trained for each PV inverter to emulate the optimal behavior of the centralized control setpoints of PV inverter in a decentralized fashion.Additionally,the voltage regulation performance of the developed ANN controllers is compared with other decentralized designs(local controllers)developed using model-based learning(regressionbased controller),optimization(affine feedback controller),and case-based learning(mapping)approaches.Numerical tests using real-world feeders corroborate the effectiveness of ANN controllers in voltage regulation and loss minimization.

Distributed Control of Thermostatically Controlled Loads in Distribution Network with High Penetration of Solar PV

High penetration of solar energy can result in voltage rise in midday,while growth in residential air conditioning is the main contributor of overloading and voltage drop issues during peak demand time.This paper provides a hierarchical control scheme to coordinate multiple groups of aggregated thermostatically controlled loads to regulate network loading and voltage in a distribution network.Considering the limited number of messages that can be exchanged in a realistic communication environment,an event-triggered distributed control strategy is proposed in this paper.Through intermittent on and off toggling of air conditioners,the required active power adjustment is shared among participating aggregators to solve the issue.A case study is conducted and simulation results are presented to demonstrate the performance of the proposed control scheme.

Coordinated Control Strategy for Operation Mode Switching of DC Distribution Networks

Due to the advantages such as low line cost,low transmission loss,and high power supply reliability,DC distribution networks have become the main development trend for future distribution networks.In this paper,a typical DC distribution network with multiple voltage levels is considered as a research object.It is proposed that the interface converters between DC buses with different voltage levels be implemented through the series-parallel combination of full-bridge LLC resonant converters.To realize the decentralized self-discipline control of DC voltage under various working conditions,different slack buses are prepared according to the voltage ranges of the DC buses,and the voltage regulation modes of the DC distribution network are divided into main voltage regulation mode,backup voltage regulation mode,and off-grid voltage droop regulation mode.By introducing a voltage coefficient related to DC voltage deviation as a basis for mode switching,the voltage fluctuations caused by slow switching between control modes in the method of traditional voltage margin control is reduced,facilitating fast and smooth switching between different voltage regulation modes.Finally,a simulation model for DC distribution networks is constructed utilizing MATLAB/Simulink.Simulation results verify the effectiveness and feasibility of the proposed voltage regulation modes and switching methods for DC distribution networks.Finally,an experimental platform is also constructed to verify the feasibility of the mode switching method proposed in this paper.

基于模糊神经网络的氢液化氦气压力PID控制

为了解决氢液化装置氦气压力调节系统超调量大、响应速度慢、调节时间长、控制参数无法在线整定等问题,针对系统具有非线性和时变性的特点,设计了基于模糊神经网络的PID控制器以及基于双曲正切函数的改进型激活函数。仿真结果表明:相比传统PID控制或模糊PID控制,采用模糊神经网络PID控制的系统动态性能显著改善,使得氢液化装置的氦气压力调节更加稳定可靠。

基于IPSO-SVC的含风电配电网稳压控制策略

当配电网含风电接入时,电能质量会受到较大的影响。为解决不同风速下风力机出力不同影响配电网电压稳定性的问题,利用静止无功补偿器提高含风电配电网电压稳定性。在考虑不同风速场景下,引入改进粒子群算法并以配电网系统有功损耗最小为目标函数,优化SVC控制参数,改善SVC对电压的控制性能。以含风电IEEE 33节点算例进行仿真计算,验证了该算法的正确性和可行性。

基于光伏逆变器调节的中低压配电网电压分层协调控制策略

针对高比例分布式光伏接入配电网引起的电压质量问题,提出一种基于光伏逆变器调节的中低压配电网电压分层协调控制策略。首先分析了中低压有源配电网电压控制方式,提出一种光伏逆变器电压区间分区控制方法;然后,提出了中低压配电网2阶段分层控制架构,构建以网络损耗最小、电压偏差最小和分布式电源消纳最大为目标的优化控制模型;最后,结合IEEE 33节点算例以及某实际配电网算例对有源配电网分层控制策略进行验证。IEEE33节点算例表明,优化方法可使配电网整体损耗降低3.79%,电压偏差率降低27.29%;实际配电网算例结果表明,优化方法可使配电网整体损耗降低36.33%,电压偏差率降低62.59%,并可有效提高光伏消纳平衡能力,保障有源配电网安全稳定运行。

基于物联网的船舶通信信道负载率调控

船舶物联网是船舶自动化控制系统的重要组成部分,Mesh无线网络在物联网中承担着数据传输的任务。本文对船舶通信信道负载率调控方案进行研究,数据在Mesh无线网络传输时,有静态信道分配、动态信道分配和混合信道分配3种方案,混合信道分配更加适用于船舶物联网数据传输,提出了船舶物联网通信信道负载率估计方法,设计了DACA-LB信道负载率调控算法,分析了算法实现流程,并从数据传输时延和吞吐量比较了DACA-LB算法和ORPTD算法的优劣,结果发现DACA-LB算法更优。

10 Gbit/s PON系统突发模式前置放大器设计(英文)

针对无源光网络(PON)设计了10 Gbit/s的突发模式前置放大器. 为了获取大动态范围和快速响应,电路采用DC耦合结构,并设计了一种反馈型峰值检测单元以实现自动增益控制与阈值提取功能. 利用调节型共源共栅(RGC)结构的输入级单元减小了电路的输入电阻,使得包括光检测器电容在内的大寄生电容与电路的主极点相隔离,从而提高了带宽. 该前置放大器采用低成本的0.13 μm CMOS工艺实现,芯片面积为425μm×475μm,总功耗为23.4mW. 测试结果表明,电路的工作速率范围在1.25 ～10.312 5Gbit/s,可提供64.0 dBΩ的高跨阻增益与54. 6 dBΩ的低跨阻增益,输入动态范围大于22.9 dB. 等效输入噪声电流为23.4 pA/Hz1/2. 该放大器可满足10G-EPON与XG-PON的相关指标.

配网抢修智慧指挥全流程管控系统设计

为了扩大配网抢修过程中的管控规模、降低风险和损失,设计了配网抢修智慧指挥全流程管控系统。在硬件部分,针对系统实际应用功能设计硬件整体结构,根据IEC 61850标准,利用电缆和三轴磁传感模块优化电子互感器的接口电路,以提升电流与电压信号的传输性能。在软件部分,基于多维数据云调控技术进行数据采集与融合,完成配网抢修智慧指挥全流程管控系统设计,以实现抢修看板可视化管控。测试结果表明,所提方法与理想方法之间的关联度指标优于其他对比方法。该设计可降低配网抢修风险。

基于二网均温调节曲线的全网自控系统应用

通过控制换热站一次侧电调阀开度调整二次侧温度是站点调控的主要手段。根据站点不同节能等级建筑、不同采暖方式制定对应的二次侧供、回水平均温度,作为电调阀控制器设定值,二网供、回水平均温度实际值温度作为返回值,根据两者的偏差进行调节。基于不同类别的二网均温调节曲线实现了一种快速响应式全网自动控制系统,并进行实际案例应用。研究表明,该调控系统可根据供热负荷变化实现各站点热量按需快速响应式调整,从而达到系统整体节能目的。

6 500t/d水泥生产线余热发电孤网运行技术改进

某6500t/d水泥生产线配套132kV/6kV总降压变电站和12MW余热发电机组,当外部电网故障时,余热发电机组将进行孤网供电运行。分析了现有配电系统无法自动判别改变并网、孤网运行方式,缺乏外部电网故障时的自我保护等问题,提出了构建“电源、电网、负荷”机网协调控制系统解决方案,介绍了其功能构成和结构组件。当外部电网故障时,机网协调控制系统能够迅速切换至适当的电网运行模式,自动实施二次调频调压控制,保障配电系统的稳定运行。

亚健康脾肾病机与NIE网络调控失衡

从探讨以肾命为中心的脾肾调节机制及其与NIE调节网络的关系入手,阐明亚健康的脾肾阴阳气血失调病机与NIE调节网络调控失衡的同质性,为中医调适亚健康状态提供现代医学理论依据。

Synergistic control of dual cross-linking strategy toward tailor-made hydrogels

Simple, efficient and accurate controllable systems for materials are becoming more essential, in response to the explosively growing demands in the fields of chemistry and material science. Herein, tailored hydrogels are explored depending on synergistic regulation of p H-responsive chemical networks with an "on/off" function and physical networks with dynamic selfoptimized arrangement. Thiol-disulfide exchange reaction endows hydrogels with controlled architectures while hydrogen bondstrengthened 2-ureido-4[1H]-pyrimidinone(UPy) moieties contributes a significant increase in mechanical strengths. The integration of that dual cross-linking(DC) network ensures the hydrogels with customized structure and enhanced mechanical property. Such controllably strategy is universally applicable and will open a new avenue to flexibly fabricate desired hybrid hydrogels with distinctive features and functions for their potential applications.

一种配电网多线路混合式统一潮流控制器

为适应配电网多线路的潮流调节需求,进一步提高潮流调控能力和响应速度,文中提出一种新型配电网多线路混合式统一潮流控制器(multi-line hybrid unified power flow controller for distribution network, D-MHUPFC)。D-MHUPFC由Sen变压器、统一潮流控制器(unified power flow controller, UPFC)和混合式有载分接开关组成,能够快速调节配电网多线路潮流。相较于传统调节方式,D-MHUPFC具有结构紧凑、响应快速、经济性好和可靠性高等优点。文中结合ZIP负荷模型,推导计及D-MHUPFC的多线路潮流方程,优化其协同控制策略,并搭建10 kV配电网仿真平台验证其可行性。结果显示,D-MHUPFC及其控制策略能在0.15 s内快速调节多线路潮流,转移过载功率,提高断面输电极限。D-MHUPFC能够解耦控制有功功率和无功功率,补偿误差小于1%,具有和UPFC相当的潮流调节能力。

基于转速自适应控制的旋转潮流控制器功率调节方法研究

针对分布式电源接入引起的功率波动与潮流不均衡问题,旋转潮流控制器(rotary power flow controller,RPFC)通过伺服电机调节旋转角的大小,输出幅值与相位连续可调的串联电压,实现有源配电网的功率调控,具有控制方式灵活、调节精度高和可靠性强等优点。该文首先根据RPFC的工作原理建立其数学模型。其次,提出RPFC功率解耦控制方法,即根据线路有功与无功功率的目标值分别计算出RPFC输出电压的dq轴分量设定值,实现输出电压对线路功率的闭环解耦控制。接着,针对RPFC接入后存在输出功率周期性震荡的问题,采用旋转角转速自适应的调节方式,即将输出电压dq轴分量合成并转换为两个旋转角的参考值,并根据旋转角偏差,对RPFC伺服电机的占空比进行量化计算,从而对两个旋转角的转速进行协调控制。最后,通过仿真验证该控制方法的正确性,并研制一台40kVA的RPFC装置样机,通过在单回与并行线路场景下的实验验证RPFC在不同工况下功率精确控制和潮流均衡调控的可行性与有效性。