MACHINE LEARNING DEVICE AND MAGNETIZATION DEVICE FOR ELECTRIC MOTOR

• Main Author: FUNAKUBO MAKOTO
• Format: Patent
• Language: English; Japanese
• Published: 06.04.2017
• Subjects: BASIC ELECTRIC ELEMENTS; CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; ELECTRICITY; INDUCTANCES; MAGNETS; PHYSICS; SELECTION OF MATERIALS FOR THEIR MAGNETIC PROPERTIES; TRANSFORMERS

PROBLEM TO BE SOLVED: To provide a magnetizer enhancing the stability of manufacturing quality of a rotor, while enhancing the stability of torque of an electric motor.SOLUTION: A machine learning device includes a state observation unit for observing the winding temperature, winding resistance value, current value, and rotor magnetic flux density of a magnetizer having a magnetization yoke and a winding part, a compensation calculation unit for calculating the compensation from the rotor magnetic flux density acquired by the state observation unit, and a learning unit for updating an action value table based on a magnetization rate calculated from the rotor magnetic flux density and the target magnetic flux density, winding temperature, and winding resistance value.SELECTED DRAWING: Figure 2 【課題】本発明は、ロータの製造品質の安定性を向上させるとともに、電動機のトルクの安定性を向上させる着磁器を提供することを目的とする。【解決手段】本発明の一実施例に係る機械学習装置は、着磁ヨーク及び巻線部を有する着磁器の巻線温度、巻線抵抗値、電流値、及びロータ磁束密度を観測する状態観測部と、状態観測部より取得したロータ磁束密度から報酬を計算する報酬計算部と、ロータ磁束密度と目標とする磁束密度から計算される着磁率、巻線温度、及び巻線抵抗値に基づいて行動価値テーブルを更新する学習部と、を有することを特徴とする。【選択図】図２