Computer system and method for monitoring the status of a technical system

A monitoring system for monitoring the technical status of a technical system, the monitoring system comprising:

• one or more sensors configured to generate, in a low precision mode on the monitoring system, sensor data reflecting technical parameters of the technical system, the low precision mode being defined by status data generated from the one or more sensors complying with a first precision level associated with low precision parameters including at least one of:
• a number of sensors associated with the low precision mode for providing status data in the low precision mode, a sampling frequency associated with the low precision mode for providing status data in the low precision mode, a transmission frequency associated with the low precision mode for providing status data in the low precision mode, and one of a data pre-processing or data aggregation level associated with status data in the low precision mode, the one or more sensors configured to change, in response to received instructions, at least one low precision parameter to generate further status data complying with a second precision level;
• and
• a communication module configured to:
• provide the status data generated in the low precision mode to a first machine learning model of a computer system trained to identify one or more indicators of an abnormal technical status of the technical system;
• receive, from the computer system, instructions for the one or more sensors to generate sensor data for the further status data complying with the second precision level if the provided status data indicates an abnormal technical status, the second precision level being associated with changes of a selection of the low precision parameters in response to a detection of an abnormal status of the technical system, the second precision level being associated with higher data accuracy than the first precision level;
• and
• provide the further status data to a second machine learning model of the computer system trained on training data complying with the second precision level.

A computer-implemented method for monitoring the technical status of a technical system, the method comprising:

• receiving, by a computer system while operated in a low-precision mode, status data generated by or more sensors recorded by a monitoring system while operated in the low-precision mode, the status data reflecting technical parameters of the technical system, the low-precision mode being defined by the received status data complying with a first precision level associated with low-precision parameters including at least one of:
• a number of sensors associated with the low-precision mode for providing status data in the low-precision mode, a sampling frequency associated with the low-precision mode for providing status data in the low-precision mode, a transmission frequency associated with the low-precision mode for providing status data in the low-precision mode, and one of a data pre-processing or data aggregation level associated with status data in the low-precision mode;
• applying a first machine learning model to the received status data, the first machine learning model having been trained on training data complying with the first precision level to analyze the received status data for one or more indicators of an abnormal technical status;
• if an abnormality indicator is detected, sending instructions to one or more sensors of the monitoring system to generate sensor data for further status data complying with a second precision level, the second precision level being associated with higher data accuracy than the first precision level, the second precision level being associated with changes applied to a selection of the low-precision parameters in response to the detection of the abnormality indicator;
• in response to sending instructions, receiving the further status data complying with the second precision level from the monitoring system;
• providing the further status data to a data analyzer having a second machine learning model trained on training data complying with the second precision level,
• wherein the first machine learning model and the second machine learning model comprise predictive machine learning models based on a predictive classification algorithm or a prediction regression algorithm.

A computer-implemented method, executed by a monitoring system, for monitoring the technical status of a technical system, the method comprising:

• generating, in a low precision mode, sensor data by one or more sensors for status data reflecting technical parameters of the technical system, the low precision mode being defined by the status data complying with a first precision level associated with low precision parameters including at least one of:
• a number of sensors associated with the low precision mode for providing status data in the low precision mode, a sampling frequency associated with the low precision mode for providing status data in the low precision mode, a transmission frequency associated with the low precision mode for providing status data in the low precision mode, and one of a data pre-processing or data aggregation level associated with status data in the low-precision mode;
• providing the status data to a first machine learning model of a computer system trained to identify one or more indicators of an abnormal technical status of the technical system;
• receiving from the computer system one or more instructions for one or more sensors to generate sensor data for further status data complying with a second precision level associated with changes of a selection of the low precision parameters in response to the detection of an abnormal status of the technical system, the second precision level being associated with higher data accuracy than the first precision level;
• in response to the received instructions, changing at least one low precision parameter to generate the further status data complying with the second precision level;
• and
• providing the further status data to a second machine learning model of the computer system trained on training data complying with the second precision level.