【摘 要】
：
Automated flowsheet synthesis is an important field in computer-aided process engineering.The present work demonstrates how reinforcement learning can be used for automated flowsheet synthesis without any heuristics or prior knowledge of conceptual design
【机 构】
：
Technical University of Munich,Campus Straubing for Biotechnology and Sustainability,Laboratory of C
论文部分内容阅读
Automated flowsheet synthesis is an important field in computer-aided process engineering.The present work demonstrates how reinforcement learning can be used for automated flowsheet synthesis without any heuristics or prior knowledge of conceptual design.The environment consists of a steady-state flowsheet simulator that contains all physical knowledge.An agent is trained to take discrete actions and sequentially build up flowsheets that solve a given process problem.A novel method named SynGameZero is developed to ensure good exploration schemes in the complex problem.Therein,flowsheet synthesis is modelled as a game of two competing players.The agent plays this game against itself during training and consists of an artificial neural network and a tree search for forward planning.The method is applied successfully to a reaction-distillation process in a quaternary system.
其他文献
With the development of the Internet of Things(IoT) and the popularization of commercial WiFi,researchers have begun to use commercial WiFi for human activity recog-nition in the past decade.However,cross-scene activity recog-nition is still difficult due
Data aggregation has been widely researched to ad-dress the privacy concern when data is published,meanwhile,data aggregation only obtains the sum or average in an area.In reality,more fine-grained data brings more value for data consumers,such as more ac
A (t,n) threshold secret sharing scheme is a funda-mental tool in many security applications such as cloud com-puting and multiparty computing.In conventional threshold se-cret sharing schemes,like Shamir\'s scheme based on a univari-ate polynomial,addi
电动汽车充放电对配电网具有重要的无功支撑能力,为此提出一种考虑电动汽车充放电的无功优化方法.首先,分析充电机无功调节原理,建立充电机状态约束模型,通过修正充电机状态来满足电池容量和用户目标电量对功率因数角的约束;其次,提出用户无功优化补贴的量化方法,分别建立网侧和用户侧需求指标,综合双方利益提出配用电系统综合无功优化目标函数;然后,以双向充电机的功率因数角作为优化变量,基于粒子群优化算法提出充电机功率因数角优化方法,从而建立计及有序充放电的无功优化模型,以实现配电网和电动汽车用户之间的有功和无功功率调控;
备用的配置是为了应对系统中可能的设备故障、负荷与可再生能源出力的不确定性.系统配置充足的备用是保证电力系统安全经济运行的必要条件.在传统的备用决策方法中,不同程度上忽略了故障概率的不确定性.为此提出了一种统筹考虑设备故障概率和净负荷不确定性的备用优化模型.其中,风电与负荷造成的净负荷不确定性以及设备故障概率不确定性统一采用区间描述,并采用对偶理论、上境界转化和KKT(Karush-Kuhn-Tucker)条件等方法进行求解.最后,基于IEEE-RTS 24节点系统验证了所提模型和方法的有效性.
Copper(Ⅰ) selenide-nanocrystalline semicon-ductor was synthesized via one-step mechanochemical synthesis after 5 min milling in a planetary ball mill.The kinetics of synthesis was followed by X-ray powder diffraction analysis and specific surface area mea
1 IntroductionrnPublic key infrastructure (PKI) is an integral part of the net-work communication system.Relying on the certificate author-ity,it provides security policies for the systems,which enables users to communicate or conduct e-commerce transacti
针对城区不规则高层建筑目标三维成像算法进行研究,基于Attributed Scattering Center(ASC)模型,优化不规则复杂体高层建筑的GEO SAR重构算法.利用北斗GEO卫星作为辐射源,机载接收机作为信号接收平台,成像场景反射GNSS信号作为回波信号,建立以稀疏表示系数和字典为凸优化变量的优化模型,提出一种基于变量分裂和增广拉格朗日技术的迭代方法.基于GEO SAR系统进行回波仿真和成像处理,利用TeslaK20 C显卡仿真平台,生成建筑物图像并应用于目标成像仿真.仿真结果表明,生成的图
The conceptual process design of novel bioprocesses in biorefinery setups is an important task,which remains yet challenging due to several limitations.We propose a novel framework incorporating super-structure optimization and simulation-based optimizati
Direct application ofbio-oil from fast pyrolysis as a fuel has remained a challenge due to its undesirable attributes such as low heating value,high viscosity,high corrosiveness and storage instability.Solvent addition is a simple method for circumventing