Called ‘KI-Predict’ it has come out of the German Federal Ministry of Education and Research (BMBF) and has seven partners including the Fraunhofer Institute for Integrated Circuits (IIS).
Part of the project is to create a low-power data acquisition and processing asic that will integrate with the sensors that monitor the condition of equipment. The hardware will not be tailored to any specific applications, and wll be able to be trained for new use cases.
“Today’s electronic data acquisition and signal processing systems have yet to be optimised for this application,” according to Fraunhofer IIS. “The cost, space requirements and power consumption of DSPs and FPGAs are too high for many frequently used Industry 4.0 sensors, so manufacturers seeking to digitalise their processes cannot simply swap sensors in a one-to-one replacement scheme.”
The aim is low-latency decentralised analysis and prediction. with machine learning algorithms running on the asic inside the sensor providing local signal processing and feature extraction for the measurement of parameters such as electrical current, position, vibration, acoustics, pressure, force and temperature.
“It delivers these features to the control level for sensor data fusion, or uses them directly for classification, clustering or anomaly detection.” said Fraunhofer IIS. “Aggregated features are extracted from the data stream at the sensor to reduce the amount of data – this reduction is necessary to connect to standard industrial interfaces and networks.”
When forwarded to process control or enterprise resource planning (ERP) software, this pre-processed data can help determine the equipment’s status, assess product quality and track trends using sophisticated AI and ML methods, said IIS.
Fraunhofer IIS is one of the many Fraunhofer institutes in Germany that bridge the gap between academic research and manufacturing. IIS developes microelectronics and IT systems. Its Integrated Sensor Systems focuses on defining, developing, simulating and assessing integrated circuits for sensor applications.