# US 12,601,519 B2 · Learning device and inference device for state of air conditioning system > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,601,519 B2 - Document ID: US12601519B2 - Status: Granted - Kind: B2 - Application number: 18/245,015 - Filed: 2020-12-11 - Published: 2023-11-09 - Granted: 2026-04-14 - Earliest claimed: 2020-12-11 - Assignees: Mitsubishi Electric Corporation - Applicants: Mitsubishi Electric Corporation - Inventors: Mitsuhiro Ishigaki; Hiroaki Hokari; Takahiro Hashikawa - Web page: https://patentgrep.com/patent/US12601519B2 ## CPC - F24F 11/64: using pre-stored data - F24F 11/32: Responding to malfunctions or emergencies - F24F 11/38: Failure diagnosis - F24F 11/49: ensuring correct operation, e.g. by trial operation or configuration checks - F24F 11/54: using one central controller connected to several sub-controllers - F24F 11/63: Electronic processing - F25B 13/00: Compression machines, plants or systems, with reversible cycle (defrosting cycles F25B47/02) - F25B 49/02: for compression type machines, plants or systems - F24F 2110/10: Temperature - F24F 2110/12: of the outside air - F24F 2140/20: Heat-exchange fluid temperature - F25B 2313/0233: in parallel arrangements - F25B 2700/1931: Discharge pressures - F25B 2700/1933: Suction pressures - F25B 2700/21151: at the suction side of the compressor - F25B 2700/21152: at the discharge side of the compressor - F24F: AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING (removing dirt or fumes from areas where they are produced B08B15/00; vertical ducts for carrying away waste gases from buildings E04F17/02; tops for chimneys or ventilating shafts, terminals for flues F23L17/02) - F25B: REFRIGERATION MACHINES, PLANTS OR SYSTEMS; COMBINED HEATING AND REFRIGERATION SYSTEMS; HEAT PUMP SYSTEMS ## Abstract A learning device includes: a first data acquisition unit; and a model generation unit. The first data acquisition unit is configured to acquire operation data of an air conditioning system. The model generation unit is configured to convert a specific model into a trained model using the operation data. The operation data includes a specific parameter and at least one of a temperature of air passing through the second heat exchanger, a temperature and a pressure of refrigerant, and a temperature outside a space where each of at least one indoor unit is arranged. The specific model estimates the specific parameter from the operation data other than the specific parameter. The specific parameter includes at least one of an operating frequency of the compressor, a degree of opening of the expansion valve, and an amount of air blown per unit time by the blower. ## Claims ### Claim 1 A learning device that learns a state of an air conditioning system in which refrigerant circulates, wherein the air conditioning system includes an outdoor unit and at least one indoor unit, the outdoor unit includes a compressor, a first heat exchanger, and a blower configured to blow air to the first heat exchanger, the at least one indoor unit includes an expansion valve and a second heat exchanger, the refrigerant circulates in order of the compressor, the first heat exchanger, the expansion valve, and the second heat exchanger, or circulates in order of the compressor, the second heat exchanger, the expansion valve, and the first heat exchanger, the learning device comprises circuitry configured to: acquire operation data of the air conditioning system; and convert a specific model into a trained model by using the operation data, wherein the operation data includes a specific parameter and at least one of a temperature of air passing through the second heat exchanger, a temperature and a pressure of the refrigerant, a temperature outside a space where each of the at least one indoor unit is arranged, and at least one of a current value and a voltage value of an inverter of the compressor, a temperature of a heat sink included in the outdoor unit, and a temperature of a liquid pipe that connects the outdoor unit and each of the at least one indoor unit, the specific model estimates the specific parameter from the operation data other than the specific parameter, and the specific parameter includes at least one of a degree of opening of the expansion valve and an amount of air blown per unit time by the blower. ### Claim 2 (depends on 1) The learning device according to claim 1, wherein the circuitry is configured to perform supervised learning on the specific model by using, as ground truth data, the operation data when the air conditioning system is in a normal state. ### Claim 3 (depends on 1) An inference device comprising: circuitry configured to: acquire the operation data; and use the trained model generated by the learning device according to claim 1, wherein the circuitry is further configured to estimate the specific parameter from the operation data which is acquired, by using the trained model. ### Claim 4 (depends on 1) The learning device according to claim 1, wherein the specific model have been trained by machine learning, wherein the machine learning includes supervised learning. ### Claim 5 (depends on 1) The learning device according to claim 1, wherein the specific model includes a neural network. ### Claim 6 (depends on 1) The learning device according to claim 1, wherein the circuitry is further configured to acquire, as time passes, the operation data from the air conditioning system, which is used to convert the specific model into the trained model, wherein the at least one of the temperature of air passing through the second heat exchanger, the temperature and the pressure of the refrigerant, and the temperature outside the space where each of the at least one indoor unit is arranged, are associated with each other. ### Claim 7 (depends on 1) The learning device according to claim 1, further comprising a memory configured to store the specific model. ### Claim 8 (depends on 1) The learning device according to claim 1, wherein the circuitry is further configured to cluster and weight parameters in the operation data. ### Claim 9 (depends on 1) The learning device according to claim 1, wherein the circuitry is further configured to update a weight and bias of the specific model using back propagation with respect to an error between an output result of the specific model and ground truth data. ### Claim 10 An inference device that infers a state of an air conditioning system in which refrigerant circulates, by using a specific model which is trained, wherein the air conditioning system includes an outdoor unit and at least one indoor unit, the outdoor unit includes a compressor, a first heat exchanger, and a blower configured to blow air to the first heat exchanger, the at least one indoor unit includes an expansion valve and a second heat exchanger, the refrigerant circulates in order of the compressor, the first heat exchanger, the expansion valve, and the second heat exchanger, or circulates in order of the compressor, the second heat exchanger, the expansion valve, and the first heat exchanger, the inference device comprises circuitry configured to: acquire operation data of the air conditioning system; and estimate a specific parameter from the operation data by using the specific model, wherein the operation data includes at least one of a temperature of air subjected to heat exchange with the second heat exchanger, a temperature and a pressure of the refrigerant, a temperature outside a space where each of the at least one indoor unit is arranged, and at least one of a current value and a voltage value of an inverter of the compressor, a temperature of a heat sink included in the outdoor unit, and a temperature of a liquid pipe that connects the outdoor unit and each of the at least one indoor unit, and the specific parameter includes at least one of a degree of opening of the expansion valve and an amount of air blown per unit time by the blower. ### Claim 11 (depends on 10) The inference device according to claim 10, wherein the specific model is generated by supervised learning. ### Claim 12 (depends on 10) The inference device according to claim 10, wherein the circuitry is further configured to make a determination as to whether the air conditioning system is normal or abnormal, by using the specific parameter which is estimated and actual operation data corresponding to the specific parameter, and to output a result of the determination. ### Claim 13 (depends on 10) The inference device according to claim 10, wherein the specific model has been trained by machine learning, wherein the machine learning includes supervised learning. ### Claim 14 (depends on 10) The inference device according to claim 10, wherein the specific model includes a neural network. ### Claim 15 (depends on 10) The inference device according to claim 10, wherein the circuitry is configured to acquire, as time passes, the operation data from the air conditioning system, which is used to convert the specific model into a trained model, wherein the at least one of the temperature of air passing through the second heat exchanger, the temperature and the pressure of the refrigerant, and the temperature outside the space where each of the at least one indoor unit is arranged, are associated with each other. ### Claim 16 (depends on 10) The inference device according to claim 10, further comprising a memory configured to store the specific model. ### Claim 17 (depends on 10) The inference device according to claim 10, wherein the circuitry is further configured to cluster and weight parameters in the operation data. ### Claim 18 (depends on 10) The inference device according to claim 10, wherein the circuitry is further configured to update a weight and bias of the specific model using back propagation with respect to an error between an output result of the specific model and ground truth data.