# US 11,305,395 B2 · Thermal displacement compensation system > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,305,395 B2 - Document ID: US11305395B2 - Status: Granted - Kind: B2 - Application number: 16/143,467 - Filed: 2018-09-27 - Published: 2019-04-04 - Granted: 2022-04-19 - Earliest claimed: 2017-10-04 - Assignees: Fanuc Corporation - Applicants: Fanuc Corporation - Inventors: Keita Hada; Kazunori Iijima - Web page: https://patentgrep.com/patent/US11305395B2 ## CPC - B23Q 15/18: Compensation of tool-deflection due to temperature or force - B23Q 11/0007: {by compensating occurring thermal dilations (B23Q15/18 takes precedence)} - G05B 19/404: characterised by control arrangements for compensation, e.g. for backlash, overshoot, tool offset, tool wear, temperature, machine construction errors, load, inertia (G05B19/19, G05B19/41 take precedence) - B23Q 2220/006: Spindle heads - G05B 2219/49206: Compensation temperature, thermal displacement, use measured temperature - G05B 2219/49219: Compensation temperature, thermal displacement - B23Q: DETAILS, COMPONENTS, OR ACCESSORIES FOR MACHINE TOOLS, e.g. ARRANGEMENTS FOR COPYING OR CONTROLLING (tools of the kind used in lathes or boring machines B23B27/00); MACHINE TOOLS IN GENERAL CHARACTERISED BY THE CONSTRUCTION OF PARTICULAR DETAILS OR COMPONENTS; COMBINATIONS OR ASSOCIATIONS OF METAL-WORKING MACHINES, NOT DIRECTED TO A PARTICULAR RESULT - G05B: CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS (systems for controlling or regulating non-electric variables G05D; systems for regulating electric or magnetic variables G05F; control devices or systems insofar as characterised by mechanical features only G05G) ## Abstract A thermal displacement compensation system detects a state quantity indicating a state of a machine, infers a thermal displacement compensation amount of the machine from the detected state quantity, and performs a thermal displacement compensation of the machine based on the inferred thermal displacement compensation amount of the machine. The thermal displacement compensation system generates a learning model by machine learning that uses a feature quantity, and stores the generated learning model in association with a combination of specified conditions of individual difference of the machine. ## Claims ### Claim 1 A thermal displacement compensation system for performing a thermal displacement compensation of a machine, the thermal displacement compensation system comprising: a processor configured to specify a condition of individual difference of the machine, detect a state quantity indicating a state of the machine, infer a thermal displacement compensation amount of the machine from the state quantity, perform the thermal displacement compensation of the machine based on the thermal displacement compensation amount of the machine, and generate or update at least one learning model among a plurality of learning models by machine learning that uses the state quantity under the condition of individual difference of the machine; and a memory configured to store the plurality of learning models, including the at least one learning model generated or updated by the processor, in association with a combination of conditions including the condition of individual difference of the machine, wherein the processor is configured to among the plurality of learning models stored in the memory, switch to a learning model corresponding to the condition of individual difference of the machine, and infer the thermal displacement compensation amount of the machine by selectively using, among the plurality of learning models stored in the memory, the learning model corresponding to the condition of individual difference of the machine, the condition of individual difference of the machine includes a production lot, a frequency of use, or a maintenance history, and the individual difference includes a difference of the machine compared to other machines controlled by the processor. ### Claim 2 (depends on 1) The thermal displacement compensation system according to claim 1, wherein the processor is configured to create a feature quantity characterizing a thermal state of the machine, from the state quantity, infer the thermal displacement compensation amount of the machine from the feature quantity, and generate or update the at least one learning model by machine learning that uses the feature quantity. ### Claim 3 (depends on 1) The thermal displacement compensation system according to claim 1, wherein the at least one learning model comprises a new learning model, and the processor is configured to generate the new learning model by performing a modification of an existing learning model of the plurality of learning models stored in the memory. ### Claim 4 (depends on 1) The thermal displacement compensation system according to claim 1, wherein the processor is configured to encrypt the plurality of learning models for storing the plurality of learning models in the memory, and decrypt the encrypted learning model corresponding to the condition of individual difference of the machine for reading and using the learning model corresponding to the condition of individual difference of the machine to infer the thermal displacement compensation amount of the machine. ### Claim 5 A thermal displacement compensation system for performing a thermal displacement compensation of a machine, the thermal displacement compensation system comprising: a processor configured to specify a condition of individual difference of the machine, detect a state quantity indicating a state of the machine, infer a thermal displacement compensation amount of the machine from the state quantity, and perform a thermal displacement compensation of the machine based on the thermal displacement compensation amount of the machine; and a memory configured to store a plurality of learning models associated in advance with a combination of conditions including the condition of individual difference of the machine, wherein the processor is configured to among the plurality of learning models stored in the memory, switch to a learning model corresponding to the condition of individual difference of the machine, and infer the thermal displacement compensation amount of the machine by selectively using, among the plurality of learning models stored in the memory, the learning model corresponding to the condition of individual difference of the machine, the condition of individual difference of the machine includes a production lot, a frequency of use, or a maintenance history, and the individual difference includes a difference of the machine compared to other machines controlled by the processor. ### Claim 6 (depends on 5) The thermal displacement compensation system according to claim 5, wherein the processor is configured to create a feature quantity characterizing a thermal state of the machine, from the state quantity, and infer the thermal displacement compensation amount of the machine from the feature quantity. ### Claim 7 A thermal displacement compensation method, comprising: specifying a condition of individual difference of a machine; detecting a state quantity indicating a state of the machine; inferring a thermal displacement compensation amount of the machine from the state quantity; performing a thermal displacement compensation of the machine based on the thermal displacement compensation amount; and generating or updating at least one learning model among a plurality of learning models by machine learning that uses the state quantity under the condition of individual difference of the machine, wherein the inferring comprises: among the plurality of learning models associated in advance with a combination of conditions including the condition of individual difference of the machine, switching to a learning model corresponding to the condition of individual difference of the machine, and using the learning model corresponding to the condition of individual difference of the machine to infer the thermal displacement compensation amount of the machine, the condition of individual difference of the machine includes a production lot, a frequency of use, or a maintenance history, and the individual difference includes a difference of the machine compared to other machines controlled by the processor. ### Claim 8 (depends on 7) The thermal displacement compensation method according to claim 7, further comprising: creating a feature quantity characterizing a thermal state of the machine, from the state quantity, wherein in the inferring, the thermal displacement compensation amount of the machine is inferred from the feature quantity, and in the generating or updating, the at least one learning model is generated or updated by machine learning that uses the feature quantity. ### Claim 9 A thermal displacement compensation method, comprising: specifying a condition of individual difference of a machine; detecting a state quantity indicating a state of the machine; inferring a thermal displacement compensation amount of the machine from the state quantity; and performing a thermal displacement compensation of the machine based on the thermal displacement compensation amount, wherein the inferring comprises: among a plurality of learning models associated in advance with a combination of conditions including the condition of individual difference of the machine, switching to a learning model corresponding to the condition of individual difference of the machine, and using the learning model corresponding to the condition of individual difference of the machine to infer the thermal displacement compensation amount of the machine, the condition of individual difference of the machine includes a production lot, a frequency of use, or a maintenance history, and the individual difference includes a difference of the machine compared to other machines controlled by the processor. ### Claim 10 (depends on 9) The thermal displacement compensation method according to claim 9, further comprising: creating a feature quantity characterizing a thermal state of the machine, from the state quantity, wherein in the inferring, the thermal displacement compensation amount of the machine is inferred from the feature quantity. ### Claim 11 (depends on 1) The thermal displacement compensation system according to claim 1, wherein the plurality of learning models includes another learning model using two or more different learning algorithms in association with the combination of conditions. ### Claim 12 (depends on 5) The thermal displacement compensation system according to claim 5, wherein the plurality of learning models includes another learning model using two or more different learning algorithms in association with the combination of conditions. ### Claim 13 (depends on 7) The thermal displacement compensation method according to claim 7, wherein the plurality of learning models includes another learning model using two or more different learning algorithms in association with the combination of conditions. ### Claim 14 (depends on 9) The thermal displacement compensation method according to claim 9, wherein the plurality of learning models includes another learning model using two or more different learning algorithms in association with the combination of conditions.