Abb Schweiz Ag

Joni Siimesjärvi

Teemu Tanila

Olli Alkkiomäki

Ville Särkimäki

Olli Alkkiomáki

Disclosed is a method comprising obtaining a set of process data associated with an industrial process, wherein the set of process data includes measured values associated with the industrial process over a time period; estimating at least an energy consumption of each motor of a plurality motors over the time period based at least partly on the set of process data and a plurality of digital twins associated with the plurality of motors, wherein the plurality of digital twins includes at least a first digital twin of a first motor and a second digital twin of a second motor different to the first motor; extrapolating at least the energy consumption of each motor of the plurality of motors over an expected total useful lifetime of each motor; and indicating at least the extrapolated energy consumption of each motor of the plurality of motors.

Extrapolating motor energy consumption based on digital twin

An electric power train includes an electric drive, an electric motor driven by the electric drive, and a meshing pair of a drive gear and a driven gear. The drive gear is coupled to the electric motor and the driven gear is coupled to a mechanical load. The backlash of the meshing pair of the drive gear and the driven gear is measured and estimated based on a time until a contact of teeth of the rotating drive gear and the driven gear during a startup of the electric motor. Wear of the meshing pair of the drive gear and the driven gear based on a change in the measured backlash over time during the operation of the electric power train.

Monitoring a gear wear in an electric power train

To provide a status information also to one or more industrial devices for which no process data is available, a machine learning model is trained by using process data of a subset of industrial devices, corresponding product data, and statuses obtained by performing remote monitoring analysis to the process data. When user input including first information, which at least indicate at least one industrial device type is received, product data of one or more industrial automation devices, which are of the same indicated industrial device type is retrieved and inputted to the trained model, which outputs one or more estimated statuses.

Remote monitoring

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.

Growing community of inventors

Helsinki, Finland

Joni Siimesjärvi