Search

EP-4741726-A1 - CONTROL DEVICE, CONTROL METHOD, AND PROGRAM

EP4741726A1EP 4741726 A1EP4741726 A1EP 4741726A1EP-4741726-A1

Abstract

This control device comprises: an extraction unit that extracts, from time-series data obtained by measuring the indoor temperature of an air-conditioned space, an element included in a monitoring section stretching from a prescribed start condition for air-conditioning control by an air conditioner to an end condition therefor; an estimation unit that estimates, on the basis of the time-series data of the monitoring section, a time constant estimation value and a dead time estimation value of a primary delay response of the air-conditioning control; and a learning unit that learns a lookup table in which an explanatory variable, which is a condition affecting the air conditioning of the air-conditioned space, is associated with the dead time estimation value and the time constant estimation value.

Inventors

  • NISHIKAWA, NAOKI
  • MORIKAWA, JUNJI
  • ARAI, KENTA

Assignees

  • MITSUBISHI HEAVY INDUSTRIES THERMAL SYSTEMS, LTD.

Dates

Publication Date
20260513
Application Date
20240823

Claims (6)

  1. A control device comprising: an extraction unit that extracts an element included in a monitoring interval from a predetermined start condition to a predetermined end condition of air conditioning control by an air conditioner from time-series data obtained by measuring an indoor temperature of an air-conditioning target space; an estimation unit that estimates a time constant estimation value and a dead time estimation value of a first-order delay response of the air conditioning control based on the time-series data of the monitoring interval; and a learning unit that learns a lookup table in which an explanatory variable that is a condition affecting air conditioning of the air-conditioning target space is associated with the dead time estimation value and the time constant estimation value.
  2. The control device according to Claim 1, wherein the learning unit determines a storage destination cell corresponding to the explanatory variable from the lookup table, and updates the dead time estimation value and the time constant estimation value in the lookup table by calculating a weighted average of a new estimation value obtained by the estimation unit and a past estimation value recorded in the storage destination cell.
  3. The control device according to Claim 2, wherein the learning unit determines at least one target cell around the storage destination cell, and updates the dead time estimation value and the time constant estimation value in the lookup table by calculating a weighted average of the new estimation value obtained by the estimation unit and a past estimation value recorded in the target cell.
  4. The control device according to any one of Claims 1 to 3, further comprising: a prediction unit that predicts a predicted arrival time for the air-conditioning target space to reach a target temperature based on the lookup table and a current explanatory variable.
  5. A control method comprising: a step of extracting an element included in a monitoring interval from a predetermined start condition to a predetermined end condition of air conditioning control by an air conditioner from time-series data obtained by measuring an indoor temperature of an air-conditioning target space; a step of estimating a time constant estimation value and a dead time estimation value of a first-order delay response of the air conditioning control based on the time-series data of the monitoring interval; and a step of learning a lookup table in which an explanatory variable that is a condition affecting air conditioning of the air-conditioning target space is associated with the dead time estimation value and the time constant estimation value.
  6. A program causing a control device to execute a process comprising: a step of extracting an element included in a monitoring interval from a predetermined start condition to a predetermined end condition of air conditioning control by an air conditioner from time-series data obtained by measuring an indoor temperature of an air-conditioning target space; a step of estimating a time constant estimation value and a dead time estimation value of a first-order delay response of the air conditioning control based on the time-series data of the monitoring interval; and a step of learning a lookup table in which an explanatory variable that is a condition affecting air conditioning of the air-conditioning target space is associated with the dead time estimation value and the time constant estimation value.

Description

Technical Field The present disclosure relates to a control device, a control method, and a program. Priority is claimed on Japanese Patent Application No. 2023-142859, filed on September 4, 2023, the content of which is incorporated herein by reference. Background Art For example, in a case where an air conditioner performs a cooling operation, it takes time for an indoor temperature to reach a target temperature set by a user after the power is turned on, and the indoor temperature during this period is not comfortable for an occupant (user). Therefore, in order to make the room comfortable when the user occupies the room, the user uses a function (warming-up operation) of manually turning on the power of the air conditioner (indoor unit) before the time when the user is expected to start occupying the room and automatically starts precooling a certain period of time in advance (for example, 15 minutes or 30 minutes before). An appropriate precooling time varies not only depending on an air-conditioned space such as a room but also depending on conditions such as an outside air temperature. Therefore, in a case where the time when the precooling is automatically started is fixed as in the warming-up operation described above, the precooling time may be excessive or insufficient. In a case where the precooling time of the air conditioner is excessive, energy is wasted, which leads to an increase in electricity bills. In a case where the precooling time is insufficient, the comfort is impaired. In addition, it is considered that the air conditioner performs control in response to a change in conditions such as the outside air temperature by taking into consideration thermal response parameters including a dead time between an operation and the appearance of results, as well as a first-order delay (for example, see PTL 1 and PTL 2). Citation List Patent Literature [PTL 1] Japanese Unexamined Patent Application Publication No. 2001-350503[PTL 2] Japanese Unexamined Patent Application Publication No. 2002-054837 Summary of Invention Technical Problem In order to calculate the thermal response parameters in real time in response to constantly changing conditions and to calculate the precooling time, sufficient computational resources (memory and CPU) are required. However, in most cases, a control device (microcomputer) of a general air conditioner is equipped with only limited computational resources. An object of the present disclosure is to provide a control device, a control method, and a program capable of learning a lookup table that can predict thermal response parameters to a set temperature with low load and at high speed even when only limited computational resources are installed. Solution to Problem One aspect of the present disclosure relates to a control device including: an extraction unit that extracts an element included in a monitoring interval from a predetermined start condition to a predetermined end condition of air conditioning control by an air conditioner from time-series data obtained by measuring an indoor temperature of an air-conditioning target space; an estimation unit that estimates a time constant estimation value and a dead time estimation value of a first-order delay response of the air conditioning control based on the time-series data of the monitoring interval; and a learning unit that learns a lookup table in which an explanatory variable that is a condition affecting air conditioning of the air-conditioning target space is associated with the dead time estimation value and the time constant estimation value. Another aspect of the present disclosure relates to a control method including: a step of extracting an element included in a monitoring interval from a predetermined start condition to a predetermined end condition of air conditioning control by an air conditioner from time-series data obtained by measuring an indoor temperature of an air-conditioning target space; a step of estimating a time constant estimation value and a dead time estimation value of a first-order delay response of the air conditioning control based on the time-series data of the monitoring interval; and a step of learning a lookup table in which an explanatory variable that is a condition affecting air conditioning of the air-conditioning target space is associated with the dead time estimation value and the time constant estimation value. Still another aspect of the present disclosure relates to a program causing a control device to execute a process including: a step of extracting an element included in a monitoring interval from a predetermined start condition to a predetermined end condition of air conditioning control by an air conditioner from time-series data obtained by measuring an indoor temperature of an air-conditioning target space; a step of estimating a time constant estimation value and a dead time estimation value of a first-order delay response of the air conditioning control ba