Prediction of faulty behaviour of a converter based on temperature estimation with machine learning algorithm

    公开(公告)号:US11853046B2

    公开(公告)日:2023-12-26

    申请号:US17772553

    申请日:2020-10-15

    Applicant: ABB Schweiz AG

    CPC classification number: G05B23/0229 G05B23/024 G05B23/0283

    Abstract: Disclosed herein is a method for predicting a faulty behaviour of an electrical converter. The method includes receiving an operation point indicator of the electrical converter indicative of an actual operation point of the electrical converter, where the electrical converter is connected to a rotating electrical machine; receiving a measured device temperature of a power semiconductor device of the electrical converter indicative of an actual temperature of the power semiconductor device; inputting the operation point indicator as input data into a machine learning algorithm trained with historical data comprising operation point indicators and associated device temperatures, where the historical data was recorded during normal operation of a power semiconductor device; estimating an estimated device temperature with the machine learning algorithm, where the estimated device temperature represents a device temperature during a normal operation; and predicting the faulty behaviour by comparing the estimated device temperature with the measured device temperature.

    ARRANGEMENT FOR MONITORING ANTIFRICTION BEARING OF ROTATING SHAFT OF ROTATING ELECTRIC MACHINE

    公开(公告)号:US20200256763A1

    公开(公告)日:2020-08-13

    申请号:US16864208

    申请日:2020-05-01

    Applicant: ABB Schweiz AG

    Abstract: An arrangement for monitoring an antifriction bearing of a rotating shaft of a rotating electric machine. The arrangement includes: one or more capacitor electrodes to measure a capacitive shaft displacement parameter; one or more of the following additional measurement sensors; a microphone to measure a bearing noise parameter, a voltage sensor to measure a bearing current parameter, and/or an optical pyrometer to measure a shaft heat parameter; and one or more processors configured to evaluate a condition of the antifriction bearing based on the capacitive shaft displacement parameter and one or more of the following: the bearing noise parameter, the bearing current parameter, and/or the shaft heat parameter.

    Collecting Data on an Industrial Automation Device

    公开(公告)号:US20220397883A1

    公开(公告)日:2022-12-15

    申请号:US17806195

    申请日:2022-06-09

    Applicant: ABB Schweiz AG

    Abstract: To provide adaptiveness to data collected on an industrial automation device, a test is used for a specific need. A set of parameter values to be used during the test are temporary and send to the industrial automation device with an indication of a test. Before the test is run, existing parameter values are backed up, and they are restored after the test.

    PREDICTION OF FAULTY BEHAVIOUR OF A CONVERTER BASED ON TEMPERATURE ESTIMATION WITH MACHINE LEARNING ALGORITHM

    公开(公告)号:US20220382269A1

    公开(公告)日:2022-12-01

    申请号:US17772553

    申请日:2020-10-15

    Applicant: ABB Schweiz AG

    Abstract: Disclosed herein is a method for predicting a faulty behaviour of an electrical converter. The method includes receiving an operation point indicator of the electrical converter indicative of an actual operation point of the electrical converter, where the electrical converter is connected to a rotating electrical machine; receiving a measured device temperature of a power semiconductor device of the electrical converter indicative of an actual temperature of the power semiconductor device; inputting the operation point indicator as input data into a machine learning algorithm trained with historical data comprising operation point indicators and associated device temperatures, where the historical data was recorded during normal operation of a power semiconductor device; estimating an estimated device temperature with the machine learning algorithm, where the estimated device temperature represents a device temperature during a normal operation; and predicting the faulty behaviour by comparing the estimated device temperature with the measured device temperature.

Patent Agency Ranking