US 12,093,024 B2
Operation evaluation device, operation evaluation method, and program
Hisashi Nishiki, Tokyo (JP); Tomoyuki Enomoto, Tokyo (JP); and Hikaru Sawada, Komaki (JP)
Assigned to MITSUBISHI HEAVY INDUSTRIES, LTD., Tokyo (JP)
Appl. No. 17/432,592
Filed by MITSUBISHI HEAVY INDUSTRIES, LTD., Tokyo (JP)
PCT Filed Feb. 7, 2020, PCT No. PCT/JP2020/004710
§ 371(c)(1), (2) Date Aug. 20, 2021,
PCT Pub. No. WO2020/175084, PCT Pub. Date Sep. 3, 2020.
Claims priority of application No. 2019-033275 (JP), filed on Feb. 26, 2019.
Prior Publication US 2022/0121182 A1, Apr. 21, 2022
Int. Cl. G05B 19/418 (2006.01); G06Q 50/04 (2012.01)
CPC G05B 19/41885 (2013.01) [G06Q 50/04 (2013.01); G05B 2219/43112 (2013.01)] 5 Claims
OG exemplary drawing
 
1. An operation evaluation device comprising:
an acquisition unit configured to acquire a plurality of kinds of data related to the operation of a factory;
an evaluation value prediction unit configured to predict an evaluation value related to an operation of the factory at a time point after a given time passes from a predetermined evaluation time based on input data related to the operation of the factory at the evaluation time using a prediction model which is a learned model learned so that the evaluation value at a time point after the given time passes from one time point is output by inputting the plurality of kinds of data related to the operation of the factory at the one timepoint; and an evaluation value output unit configured to output information related to the evaluation value,
wherein the prediction model outputs, as the evaluation value, an energy evaluation value related to energy consumption of the factory and a running ratio evaluation value related to a running ratio of the factory,
the operation evaluation device, further comprising:
an importance specifying unit configured to specify importance by a kind of the input data in the prediction model;
wherein the evaluation value output unit outputs the importance by the kind of input data;
wherein the importance specifying unit specifies the importance in a case where the prediction model is updated;
wherein the evaluation value output unit outputs time-series importance by the kind of input data;
a changing unit configured to accept a change in a value of the input data from a user based on the importance by the kind of input data outputted by the evaluation value output unit; and
a simulation unit configured to predict a changed evaluation value which is the evaluation value at the time point after the given time passes from the evaluation time based on the changed data using the prediction model,
wherein the factory is operated based on the changed evaluation value.