AiSight develops a product that uses artificial intelligence algorithms to determine the state of a machine in real time, predict errors and dynamically regulate the machine parameters based on sensor data. The solution consists of both hardware and software components.
The hardware includes an easy-to-install device based on vibration sensors and is optimized to allow Plug & Play installation within minutes without specialized expertise.
The software uses machine learning models to learn machine states, identify anomalies and determine causes of errors in sensor data. The key algorithm is "acoustic fingerprinting", in which physical parameters are extracted from the sensor data to learn behaviors of normal conditions and deviations from it. The algorithm is optimized to operate on low-power hardware to perform all calculations and data processing on the edge.