意大利专家的多年模型预测控制算法总结,共有9章,2021年更新,可用于BMS SOC估计,PMSM估计等
2021-02-27 09:03:42 9.05MB 模型预测控制 MPC QP 数据驱动
1
数据驱动的寿命预测和健康管理技术研究进展
2021-02-26 18:07:58 1.55MB 研究论文
1
在长流程浮选过程中,生产指标难以在线检测,造成操作不及时,影响系统的稳定运行.本文提出了一种基于多源数据的铝土矿浮选过程生产指标集成建模方法.首先结合浮选机理和现场工人经验,分析影响和反映生产指标的多源数据(生产数据和泡沫图像特征数据);然后分别建立各生产指标预测子模型和同步误差补偿子模型;最后采用信息熵和智能协调策略分别构建精矿品位和尾矿品位的集成预测模型.工业验证和工况分析表明,本文集成建模方法具有良好的预测性能和较强的泛化性,为基于生产指标的浮选过程操作参数控制和全流程优化奠定基础.
1
采用激光诱导击穿光谱(LIBS)技术结合偏最小二乘判别分析(PLS-DA)对新疆、青海和俄罗斯的白色软玉进行产地研究。选取产自新疆(和田、于田、且末)、青海(格尔木)、俄罗斯(贝加尔湖)的146个白色软玉样品作为样品集,从样品集中随机抽取111个样品作为校正集,用于建立PLS-DA识别模型,剩余35个样品作为验证集,用于检验PLS-DA识别模型的预测效果。采用LIBS对三个产地的软玉样品进行成分分析,选择Na、K、Al、Li、Be、Mn、Sr、Zr、Ba、Y、Ce作为目标元素,并选取589.995,766.490,396.152,670.793,313.042,257.610,407.771,389.138,455.403,437.493,401.239 nm处的谱线作为目标元素的分析谱线,选取Si元素作为内标元素,以其在 288.158 nm处的谱线作为内标元素分析谱线,分别计算各目标元素与内标元素的谱线强度的比值Rx,由Rx组成自变量矩阵,用于模型的建立与预测。实验结果表明,采用LIBS结合PLS-DA建立的产地识别模型,其校正自变量和验证自变量与实际分类变量的相关系数都大于0.9
2021-02-24 14:04:19 5.55MB 光谱学 激光诱导 产地识别 偏最小二
1
新一代工业互联网发展模式与成功实践:数据驱动的新价值网络
2021-02-06 10:02:36 1.45MB 网络互联
1
铸造2D Foundry是一个实时的多合一游戏引擎。 目标是性能,易用性和可移植性。 对于本地构建和引擎开发,请查看。
2021-02-04 18:12:43 325KB game-engine haxe GameengineHaxe
1
基于数据驱动鲁棒优化的高比例清洁能源高速充电站规划,采用数据驱动鲁棒优化算法量化可再生能源、充电负荷的不确定性问题,从而百分百可再生比例下实现最优充电站配置
主题:Clojure的递归,数据驱动的模式匹配
2021-01-28 22:15:48 24KB clojure matching pattern ClojureClojure
1
自己整理的关于偏最小二乘方面的资料,包括迭代偏最小二乘法NIPALS,高斯核变换,交叉有效性等
2020-12-07 16:59:11 586KB PLS 偏最小二乘
1
Digital technology has not only revolutionized the way designers work, but also the kinds of designs they produce. The development of the computer as a design environment has encouraged a new breed of digital designer; keen to explore the unique creative potential of the computer as an input/output device. Data-driven Graphic Design introduces the creative potential of computational data and how it can be used to inform and create everything from typography, print and moving graphics to interactive design and physical installations. Using code as a creative environment allows designers to step outside the boundaries of commercial software tools, and create a set of unique, digitally informed pieces of work. The use of code offers a new way of thinking about and creating design for the digital environment. Each chapter outlines key concepts and techniques, before exploring a range of innovative projects through case studies and interviews with the artists and designers who created them. These provide an inspirational, real-world context for every technique. Finally each chapter concludes with a Code section, guiding you through the process of experimenting with each technique yourself (with sample projects and code examples using the popular Processing language supplied online to get you started).
2020-01-29 03:10:52 34MB 数据驱动 data-driven 可视化
1