Back to results
US 11,341,395 B2Granted
Device and method for determining the status of a spindle of a machine tool
AssigneeSiemens Aktiengesellschaft
InventorsFlorian Büttner, Felix Buggenthin, Felix Butz, Georg Domaschke, Michael Helbig, Philipp Siegel, Werner Vom Eyser
Life of this patent
Estimating the term…
Abstract
A device for determining a spindle status of a spindle of a machine tool includes a detector for detecting sensor data of the spindle for a defined time window. A processing unit analyses the sensor data through artificial intelligence by calculating a defined feature of the sensor data for the defined time window and determining a spindle status from the sensor data. An output member outputs the determined spindle status.
Claims14
A device for determining a spindle status of a spindle of a machine tool, said device comprising:
- a detector detecting continuous sensor data of the spindle;
- a processing unit configured to analyze the detected sensor data through artificial intelligence by
- dividing the continuous sensor data into a plurality of time windows having each a predetermined duration to obtain for each of the plurality of time windows a signal associated with the time window,
- analyzing, with a second AI-module based on a CNN (convolutional neural network), raw continuous sensor data to determine a first value representative of a load of the spindle,
- analyzing, with a second AI-module based on an ensemble of regularized decision trees or boosted classification trees, characterized sensor data a second value representative the load of the spindle for the time window,
- calculating with the second AI-module for each signal defined features and transferring the defined features to the ensemble of regularized decision trees or boosted classification trees to determine a second value representative of the load of the spindle,
- based on the first value and on the second value, determining with the processing unit a category of the load of the spindle;
- determining the spindle status based on the category of the load of the spindle for each of the plurality of signals, and
- an output member outputting the determined spindle status.
6 more elements
A machine tool, comprising:
- a spindle;
- and
- a device for determining a spindle status of the spindle, said device including a detector detecting continuous sensor data of the spindle, a processing unit configured to analyze the detected sensor data through artificial intelligence by
- dividing the continuous sensor data into a plurality of time windows having each a predetermined duration to obtain for each of the plurality of time windows a signal associated with the time window,
- analyzing, with a first AI-module based on a CNN (convolutional neural network), raw continuous sensor data to determine a first value representative of a load of the spindle,
- analyzing, with a second AI-module based on an ensemble of regularized decision trees or boosted classification trees, characterized sensor data a second value representative of the load of the spindle for the time window,
- calculating with the second AI-module for each signal defined features and transferring the defined features to the ensemble of regularized decision trees or boosted classification trees to determine a second value representative of the load of the spindle,
- based on the first value and on the second value, determining with the processing unit a category of the load of the spindle;
- determining the spindle status based on the category of the load of the spindle for each of the plurality of signals, and
- an output member outputting the determined spindle status.
7 more elements
A method for determining a spindle status of a spindle of a machine tool, comprising:
- detecting with a detector continuous sensor data of the spindle;
- analyzing the detected sensor data with a processing unit using artificial intelligence (AI), by:
- dividing the continuous sensor data into a plurality of time windows having each a predetermined duration to obtain for each of the plurality of time windows a signal associated with the time window,
- analyzing, with a first AI-module based on CNN (convolutional neural network), raw continuous sensor data to determine a first value representative of a load of the spindle,
- analyzing, with a second AI-module based on an ensemble of regularized decision trees or boosted classification trees, characterized sensor data a second value representative of the load of the spindle for the time window,
- calculating with the second AI-module for each signal defined features and transferring the defined features to the ensemble of regularized decision trees or boosted classification trees to determine a second value representative of the load of the spindle,
- based on the first value and, on the second value, determining with the processing unit a category of the load of the spindle;
- determining the spindle status based on the category of the load of the spindle for each of the plurality of signals;
- and
- outputting the determined spindle status.
7 more elements
Dependencies are inferred from the claim text.