- 著者
- Michihisa KOYAMA Seiichiro KIMURA Yasunori KIKUCHI Takao NAKAGAKI Kenshi ITAOKA
- 出版者
- 公益社団法人 化学工学会
- 雑誌
- JOURNAL OF CHEMICAL ENGINEERING OF JAPAN (ISSN:00219592)
- 巻号頁・発行日
- pp.13we345, (Released:2014-06-26)
- 被引用文献数
- 6 28
It has been an important target to realize a sustainable energy usage in the future, regardless of the country. Japan is now compelled to consider a new paradigm of energy policy due to the nuclear power plant failures after March 11, 2011. To discuss the ideal or a favorable future of Japan’s energy, understanding the present status as well as the available energy options in the future will be an initial step, followed by discussion of the issues related to each option. The aim of this article is to summarize the present status of Japan’s energy systems and to clarify the major points of discussions for the realization of future sustainable energy systems. In addition, the major options of both energy supply and demand sides are summarized. The issues for realizing the future energy systems are discussed from the large-scale penetration of renewable systems, the demand side energy management and savings, the mobility, and the centralized electricity grid viewpoints, to provide a common basis for the discussion of future energy systems in Japan.
- 著者
- Corey Adam Myers Takao Nakagaki
- 出版者
- The Iron and Steel Institute of Japan
- 雑誌
- ISIJ International (ISSN:09151559)
- 巻号頁・発行日
- vol.59, no.4, pp.687-696, 2019-04-15 (Released:2019-04-17)
- 参考文献数
- 105
- 被引用文献数
- 1 9
A prediction of the nucleation lag time of iron and steelmaking melts solely from elemental composition and temperature was produced via deep neural networks trained on data available in the literature. To the best of our knowledge, this constitutes the first published instance of prediction of nucleation lag time that does not require composition specific empirical data. Control of the nucleation process is critical for the production of ground granulated blast furnace slag, control of slag properties for heat recovery or utilization, and the optimization of slag for CO2 mineralization. The deep neural network achieved an average absolute scaled error (AASE) over a testing set of 947 points covering 7 orders of magnitude of 39.9%. Performance was further improved by bootstrapping with a prediction of liquidus temperature from a separate deep neural network (AASE = 33.4%). Bootstrapping using DNN-generated viscosity data did not increase prediction accuracy. The negligible calculation load of the trained deep neural networks allows for rapid design, analysis, and optimization of novel slag compositions and treatment methods. This ability was demonstrated by calculating the necessary continuous cooling rate to generate amorphous slag across all CaO–Al2O3–SiO2 and CaO–FeO–SiO2 compositions and the potential to use additives to alter said cooling rate.