US 12,078,344 B2
Learning device and boiler control system
Masato Tamura, Tokyo (JP); Shinji Watanabe, Tokyo (JP); Shun Inoue, Tokyo (JP); Isao Umoto, Tokyo (JP); Tomonori Matsubara, Tokyo (JP); and Shinobu Nakamura, Tokyo (JP)
Assigned to IHI Corporation, Koto-ku (JP)
Appl. No. 17/426,966
Filed by IHI Corporation, Koto-ku (JP)
PCT Filed Feb. 7, 2020, PCT No. PCT/JP2020/004864
§ 371(c)(1), (2) Date Jul. 29, 2021,
PCT Pub. No. WO2020/162607, PCT Pub. Date Aug. 13, 2020.
Claims priority of application No. 2019-021712 (JP), filed on Feb. 8, 2019.
Prior Publication US 2022/0099289 A1, Mar. 31, 2022
Int. Cl. F22B 35/18 (2006.01); F22B 35/06 (2006.01); G06N 20/00 (2019.01); H02J 3/00 (2006.01)
CPC F22B 35/18 (2013.01) [F22B 35/06 (2013.01); G06N 20/00 (2019.01); H02J 3/004 (2020.01)] 8 Claims
OG exemplary drawing
 
1. A learning device for constructing a learning model for generating a prior acceleration command value for controlling a control target in advance of the time a load on a boiler used for thermal power generation changes, the learning device comprising:
a microprocessor or a microcontroller configured to generate the learning model by mechanically learning, as learning data, a data set including a power generation command value for the thermal power generation and the prior acceleration command value which have been used in a previous operation of the boiler,
wherein the microprocessor or the microcontroller constructs, based on the learning data, the learning model which, by at least the power generation command value being input, outputs the prior acceleration command value in which a tracking characteristic of a power generation quantity with respect to the power generation command value exceeds a given standard.