Method and controller for deciding whether a bearing is faulty or not
AssigneeABB Schweiz AG
InventorKari Saarinen
Life of this patent
Estimating the term…
Abstract
There is provided mechanisms for deciding whether a bearing is faulty or not. A method is performed by a controller. The method comprises obtaining, as a measurement signal, metal particles counting data, where the metal particles counting data indicates number of metal particles present in lubrication oil of the bearing per time unit. The method comprises differentiating the measurement signal, resulting in a differentiated measurement signal. The method comprises deciding, depending on how large share of a probability density estimate of the differentiated measurement signal is above a threshold value, whether the bearing is faulty or not.
Claims16
A computer program for deciding whether a bearing is faulty or not, the computer program comprising computer code which, when run on processing circuitry of a controller, causes the controller to:
- obtain, as a measurement signal, metal particles counting data, where the metal particles counting data indicates number of metal particles present in lubrication oil of the bearing per time unit;
- differentiate the measurement signal, resulting in a differentiated measurement signal;
- and
- decide, depending on how large share of a probability density estimate of the differentiated measurement signal is above a threshold value, whether the bearing is faulty or not, wherein the probability density estimate of the differentiated measurement signal is represented by a histogram of the differentiated measurement signal.
A controller for deciding whether a bearing is faulty or not, the controller comprising processing circuitry, the processing circuitry being configured to cause the controller to:
- obtain, as a measurement signal, metal particles counting data, where the metal particles counting data indicates number of metal particles present in lubrication oil of the bearing per time unit;
- differentiate the measurement signal, resulting in a differentiated measurement signal;
- and
- decide, depending on how large share of a probability density estimate of the differentiated measurement signal is above a threshold value, whether the bearing is faulty or not, wherein the probability density estimate of the differentiated measurement signal is represented by a histogram of the differentiated measurement signal.
Dependencies are inferred from the claim text.