Air Conditioning Load Learning and Prediction Apparatus Using Machine Learning

ChangeBridge: Patent Grants - AI & Computing (G06N)

Published March 31st, 2026

Detected March 31st, 2026

Summary

The USPTO granted patent US12590726B2 to Daikin Industries for an air conditioning load learning and prediction apparatus using machine learning. The patent covers a system that acquires actual AC load data and building operation information to generate predictive models. The patent contains 23 claims.

View original document View source feed page

What changed

The USPTO issued patent grant US12590726B2 to Daikin Industries for an AI-based air conditioning load learning and prediction apparatus. The patent includes claims covering a learning apparatus with an actual load acquisition unit, a first information acquisition unit for building operation data, and a learning unit that generates a model using building operation information as explanatory variables and AC load data as objective variables. The patent is classified under G06N 20/00 (machine learning) and related HVAC control categories.

This is a routine patent grant and creates no compliance obligations. Entities developing AI-based HVAC or building energy management systems should review the patent claims to assess potential licensing needs or design-around considerations for their own machine learning-based load prediction systems. The filing date was September 7, 2021, with Application No. 18023599.

Source document (simplified)

← USPTO Patent Grants

Air conditioning load learning apparatus and air conditioning load prediction apparatus

Grant US12590726B2 Kind: B2 Mar 31, 2026

Assignee

DAIKIN INDUSTRIES, LTD.

Inventors

Hiroyuki Murayama, Yoshiyuki Shimoda

Abstract

An air conditioning load learning apparatus includes an actual load acquisition unit, a first information acquisition unit, and a learning unit. The actual load acquisition unit acquires an actual air conditioning load in a target space inside a target building. The first information acquisition unit acquires first information about an operation of the target building. The learning unit generates a learning model using at least the first information as an explanatory variable and a value regarding the actual air conditioning load as an objective variable. An air conditioning load prediction apparatus includes the air conditioning load learning apparatus.

CPC Classifications

F24F 11/64 F24F 2140/50 F24F 2140/60 F24F 2110/10 F24F 2120/10 F24F 11/62 G05B 2219/2614 G05B 15/02 G05B 19/042 G05B 13/0265 G05B 13/04 G05B 13/048 G05B 2219/2642 G06N 20/00 G06N 3/084