Alcohol oxidation is a widely used green chemical reaction.The reaction process produces flammable and explosive hydrogen,so the design of the reactor must meet stringent safety requirements.Based on the limited exper...Alcohol oxidation is a widely used green chemical reaction.The reaction process produces flammable and explosive hydrogen,so the design of the reactor must meet stringent safety requirements.Based on the limited experimental data,utilizing the traditional numerical method of computational fluid dynamics(CFD)to simulate the gas-liquid two-phase flow reactor can mitigate the risk of danger under varying working conditions.However,the calculation process is highly time-consuming.Therefore,by integrating process simulation,computational fluid dynamics,and deep learning technologies,an intelligent hybrid chemical model based on machine learning was proposed to expedite CFD calculations,enhance the prediction of flow fields,conversion rates,and concentrations inside the reactor,and offer insights for designing and optimizing the reactor for the alcohol oxidation system.The results show that the hybrid model based on the long and short-term memory neural network achieves 99.8%accuracy in conversion rate prediction and 99.9%accuracy in product concentration prediction.Through validation,the hybrid model is accelerated by about 360 times compared with instrumental analysis in conversion rate prediction and about 45 times compared with CFD calculation in concentration distribution prediction.This hybrid model can quickly predict the conversion rate and product concentration distribution in the gas-liquid two-phase flow reactor and provide a model reference for fast prediction and accurate control in the actual chemical production process.展开更多
An adaptive fast multipole higher order boundary element method combining fast multipole （FM） with a higher order boundary element method is studied to solve the power frequency electric field （PFEF） of substation...An adaptive fast multipole higher order boundary element method combining fast multipole （FM） with a higher order boundary element method is studied to solve the power frequency electric field （PFEF） of substations. In this new technique, the iterative equation solver GMRES is used in the FM, where matrix-vector multiplications are calculated using fast multipole expansions. The coefficients in the preconditioner for GMRES are stored and are used repeatedly in the direct evaluations of the near-field contributions. Then a 500kV outdoor substation is modeled and the PFEF of the substation is analyzed by the novel algorithm and other conventional methods. The results show that, in computational cost and the storages capability aspects, the algorithm proposed in this study has obvious advantages. It is suitable for the calculation of the large-scale PFEF in complex substations and the design of electromagnetic compatibility.展开更多
The rapid rise of artificial intelligence(AI)has catalyzed advancements across various trades and professions.Developing large-scale AI models is now widely regarded as one of the most viable approaches to achieving g...The rapid rise of artificial intelligence(AI)has catalyzed advancements across various trades and professions.Developing large-scale AI models is now widely regarded as one of the most viable approaches to achieving general-purpose intelligent agents.This pressing demand has made the development of more advanced computing accelerators an enduring goal for the rapid realization of large-scale AI models.However,as transistor scaling approaches physical limits,traditional digital electronic accelerators based on the von Neumann architecture face significant bottlenecks in energy consumption and latency.Optical computing accelerators,leveraging the high bandwidth,low latency,low heat dissipation,and high parallelism of optical devices and transmission over waveguides or free space,offer promising potential to overcome these challenges.In this paper,inspired by the generic architectures of digital electronic accelerators,we conduct a bottom-up review of the principles and applications of optical computing accelerators based on the basic element of computing accelerators–the multiply-accumulate(MAC)unit.Then,we describe how to solve matrix multiplication by composing calculator arrays from different MAC units in diverse architectures,followed by a discussion on the two main applications where optical computing accelerators are reported to have advantages over electronic computing.Finally,the challenges of optical computing and our perspective on its future development are presented.Moreover,we also survey the current state of optical computing in the industry and provide insights into the future commercialization of optical computing.展开更多
基金the support from the National Natural Science Foundation of China(22478429)the Special Project Fund of Taishan-Scholars(tsqn202408101)+3 种基金the Natural Science Foundation of Shandong Province(ZR2023YQ009)CNPC Innovation Found(2024DQ02-0504)Fundamental Research Funds for the Central Universities,Ocean University of China(202364004)the State Key Laboratory of Heavy Oil Processing(SKLHOP202403003)。
文摘Alcohol oxidation is a widely used green chemical reaction.The reaction process produces flammable and explosive hydrogen,so the design of the reactor must meet stringent safety requirements.Based on the limited experimental data,utilizing the traditional numerical method of computational fluid dynamics(CFD)to simulate the gas-liquid two-phase flow reactor can mitigate the risk of danger under varying working conditions.However,the calculation process is highly time-consuming.Therefore,by integrating process simulation,computational fluid dynamics,and deep learning technologies,an intelligent hybrid chemical model based on machine learning was proposed to expedite CFD calculations,enhance the prediction of flow fields,conversion rates,and concentrations inside the reactor,and offer insights for designing and optimizing the reactor for the alcohol oxidation system.The results show that the hybrid model based on the long and short-term memory neural network achieves 99.8%accuracy in conversion rate prediction and 99.9%accuracy in product concentration prediction.Through validation,the hybrid model is accelerated by about 360 times compared with instrumental analysis in conversion rate prediction and about 45 times compared with CFD calculation in concentration distribution prediction.This hybrid model can quickly predict the conversion rate and product concentration distribution in the gas-liquid two-phase flow reactor and provide a model reference for fast prediction and accurate control in the actual chemical production process.
基金Supported by the National Natural Science Foundations of China under Grant No 50877082, the National Basic Research Program of China under Grant No 2009CB724506, and the Specialized Research Fund for State Key Laboratory of Power Transmission Equipment ＆ System Security and New Technology under Grant No 2007DA10512708304.
文摘An adaptive fast multipole higher order boundary element method combining fast multipole （FM） with a higher order boundary element method is studied to solve the power frequency electric field （PFEF） of substations. In this new technique, the iterative equation solver GMRES is used in the FM, where matrix-vector multiplications are calculated using fast multipole expansions. The coefficients in the preconditioner for GMRES are stored and are used repeatedly in the direct evaluations of the near-field contributions. Then a 500kV outdoor substation is modeled and the PFEF of the substation is analyzed by the novel algorithm and other conventional methods. The results show that, in computational cost and the storages capability aspects, the algorithm proposed in this study has obvious advantages. It is suitable for the calculation of the large-scale PFEF in complex substations and the design of electromagnetic compatibility.
基金supported by Shanghai Municipal Science and Technology Major Project.
文摘The rapid rise of artificial intelligence(AI)has catalyzed advancements across various trades and professions.Developing large-scale AI models is now widely regarded as one of the most viable approaches to achieving general-purpose intelligent agents.This pressing demand has made the development of more advanced computing accelerators an enduring goal for the rapid realization of large-scale AI models.However,as transistor scaling approaches physical limits,traditional digital electronic accelerators based on the von Neumann architecture face significant bottlenecks in energy consumption and latency.Optical computing accelerators,leveraging the high bandwidth,low latency,low heat dissipation,and high parallelism of optical devices and transmission over waveguides or free space,offer promising potential to overcome these challenges.In this paper,inspired by the generic architectures of digital electronic accelerators,we conduct a bottom-up review of the principles and applications of optical computing accelerators based on the basic element of computing accelerators–the multiply-accumulate(MAC)unit.Then,we describe how to solve matrix multiplication by composing calculator arrays from different MAC units in diverse architectures,followed by a discussion on the two main applications where optical computing accelerators are reported to have advantages over electronic computing.Finally,the challenges of optical computing and our perspective on its future development are presented.Moreover,we also survey the current state of optical computing in the industry and provide insights into the future commercialization of optical computing.
