Model-Free control performance improvement using virtual reference feedback tuning and reinforcement Q-learning

This paper proposes the combination of two model-free controller tuning techniques, namely linear virtual reference feedback tuning (VRFT) and nonlinear state-feedback Q-learning, referred to as a new mixed VRFT-Q learning approach. VRFT is first used to find stabilising feedback controller using input-output experimental data from the process in a model reference tracking setting. Reinforcement Q-learning is next applied in the same setting using input-state experimental data collected under perturbed VRFT to ensure good exploration. The Q-learning controller learned with a batch fitted Q iteration algorithm uses two neural networks, one for the Q-function estimator and one for the controller, respectively. The VRFT-Q learning approach is validated on position control of a two-degrees-of-motion open-loop stable multi input-multi output (MIMO) aerodynamic system (AS). Extensive simulations for the two independent control channels of the MIMO AS show that the Q-learning controllers clearly improve performance over the VRFT controllers.     

真实数据驱动下的变电站三维智能仿真技术研究

随着大数据技术的发展,面向变电站三维虚拟场景,考虑变电站三维仿真模型的准确性和仿真环境的真实性,融合色彩、声音、图像等真实数据高效模拟变电站的各种操作和设备拆装。从数据层、系统设计层、功能应用层等3方面详细分析了变电站多维多媒体仿真系统架构,以变压器为例分析了变电站主设备结构建模与精准拆装设计流程,最后引入顶点纹理技术,考虑变电站不同运行状态下的动态色差,融合变电站真实数据驱动,实现动态色彩渲染与声效模拟。基于主场景漫游、GIS漏气与主设备着火等事故示例验证本文仿真渲染技术的有效性。     

基于最小二次支持向量机数据驱动的Hammerstein系统故障诊断与分离方法

本文在最小二乘支持向量机(LS-SVM)框架,针对Hammerstein非线性系统,设计了一种数据驱动故障诊断与分离(FDI)方法。具体内容包括:构造单适当的输出系统设计基于等价空间的残差生成器,进一步将残差生成器扩展至多输出情况。为了解决实时监控问题,通过低阶和稀疏逼近理论构造半参数残差生成器,此残差生成器带有参数动力学方程和非参数静态函数。在半参数框架下,通过设计参数化矩阵重构实现对传感器/执行器故障的检测与分离。最后,本文给出一个仿真实例验证了所提方法的有效性和实用性。     

台风灾害下配网用户停电数量预测最优数据驱动模型选择

严重的台风灾害可能导致配网用户停电,有效的配网用户停电数量预测可为电网应急抢修提供辅助指导。综合考虑气象因素、电网因素及地理因素,提出了基于机器学习回归算法的配网用户停电数量预测方法。分析比较了线性回归、支持向量回归(SupportVectorRegression,SVR)、分类回归树(ClassificationandRegressionTree,CART)、梯度提升树(Gradient Boosting Decision Tree, GBDT)及随机森林(Random Forest, RF)等5种机器学习回归算法对配网用户停电数量预测的应用效果。对比结果表明,LR在进行配网用户停电数量预测时表现较差,SVR及CART模型效果次之,RF及GBDT效果相对较好,其中GBDT算法与RF算法误差较为接近。但考虑到GBDT算法为串行计算,而RF算法为并行计算,使用时RF算法效率更高。因此最终选取了RF进行停电数量预测效果的进一步分析。结果表明其误差在±30%以内的准确率可达70%以上,可为配网用户停电抢修提供有力指导。     

基于机理与数据驱动的热连轧板凸度组合预测

针对传统热连轧出口板凸度预测方法存在的模型精度低、解释性差等缺陷,提出了一种将机理与数据驱动相结合的热连轧板凸度组合预测模型。通过热连轧板凸度机理预测模型得到热连轧板凸度基准值,将该基准值与实际值之间的偏差量作为机器学习模型的预测变量,再将偏差量预测值与基准值进行求和得出组合预测模型的板凸度预测值,并将该组合预测策略应用至多个神经网络进行方法验证。研究结果表明,提出的热连轧板凸度组合预测模型相较于传统预测模型具有更好的预测性能,其中有97%以上预测数据的绝对误差小于0.02 mm,82%以上预测数据的绝对误差小于0.01 mm,同时该组合预测方法具有较好的可行性与普适性,所提出的模型能够实现机理模型与数据驱动模型的优势互补,使得模型更加符合实际物理意义,该组合模型既缓解了神经网络预测结果由于过程黑箱导致解释性差、可信度低的问题,又弥补了机理模型预测结果偏离生产工况、无法实时修正的缺陷,对热连轧板带钢的板形控制以及热连轧产品质量的改善具有重要意义。     

基于长短期记忆循环神经网络的AGC实时控制策略

大量新能源的接入以及电网中冲击负荷数量的剧增,使得电网对自动发电控制(AGC)策略提出了新的要求.简化AGC的一般控制流程,对比不同AGC策略的控制特性,在每个考核周期内选择控制效果更优的控制策略,并充分发挥多种控制策略在各自优势工况下的性能,以得到优秀控制数据集;在此基础上,以长短期记忆(LSTM)循环神经网络为神经...     

数据驱动的能源互联网建模与仿真关键技术

针对能源互联网面临的多能流运行复杂性、源荷不确定性等日益突出的问题,基于能源生产、传输与消费各环节数据信息,文章设计了一种包含物理层、感知网络层、模型层、算法层、应用层的数据驱动能源互联网建模与仿真框架,并提出能源互联网数据与物理融合统一建模、分布式能源及负荷概率预测、典型运行场景生成以及多能流优化运行等关键技术,最后展望典型应用场景。以数据驱动为核心,为能源互联网建设提供技术支撑。     

Evaluation,Prediction, and Feedback of Blast Furnace Hearth Activity Based on Data-Driven Analysis and Process Metallurgy

For complex, difficult-to-control, and hour-delay blast furnace (BF) systems, the quantitative characterization, prediction, and adjustment of the BF hearth activity are significant in improving the furnace status. In this study, data including raw fuel, process operation, smelting state, and slag and iron discharge during the entire BF process are analyzed, with a total of 171 variables and 5033 groups of data. Based on the knowledge of BF technology, a comprehensive index of hearth activity is then proposed to quantitatively characterize and grade the activity level of the BF hearth; the rationality of this method is verified from the two aspects of furnace heat level and furnace status coincidence. Compared with the traditional single-machine learning algorithm, the performance of the proposed method that combines genetic algorithm and stacking exhibits significant improvement. The hit rates for 10% and 5% errors in the prediction and estimation of hearth activity are 94.64% and 80.36%, respectively. To enhance the BF hearth activity, quantized and dynamic actions and suggestions are also simultaneously pushed. The model of BF hearth activity is successfully applied in practical online production. During the application period, the average furnace hearth activity increases by 10% compared to the historical value.     

More data-driven processing at retrieval reduces age-related memory deficits.

The environmental support hypothesis postulates that it may be possible to reduce older adults' deficits in episodic memory by providing environmental support at the encoding and/or retrieval phases. To examine the validity of this hypothesis, we varied the amount of retrieval support by manipulating data-driven processes. Young and older adults performed a word-stem cued recall task under a low data-driven condition (LDDC) in which the retrieval cue comprised 3 letters, and a higher data-driven condition (HDDC) in which the cue comprised 4 letters. Older adults benefitted more than younger adults from the additional support. Older adults exhibited a large deficit relative to younger adults in the LDDC condition but no age differences were found in the HDDC condition. These findings demonstrate that age-related memory deficits can be reduced by increasing the environmental support at retrieval associated with the data-driven component of retrieval processing. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

化工过程软测量建模方法研究进展

软测量仪表是解决化工过程中质量变量难以实时测量的重要手段。软测量仪表的核心问题是软测量建模。阐述了软测量建模与辨识和非线性建模的关系:质量变量和易测变量的动态关系存在于增量之间,辨识模型依赖于增量数据,软测量建模则是依赖于实测变量数据来获取这个动态关系;非线性建模建立了变量间的静态关系,忽略了对象动态特性,而软测量建模要兼顾对动态特性的表征。随着人们对过程特性的认识加深,软测量建模方法不断发展,经历了从机理建模到数据驱动建模,从线性建模到非线性建模,从静态建模到动态建模的过程。详细讨论了软测量建模的发展过程,众多建模方法的优缺点及适用情况和现在建模的热点,最后对软测量建模方法进行了总体展望。