The VibroSense chip extracts patterns from a sensor’s raw signal and passes only valuable data for classification at the next computing point. It can integrate into existing systems.
“Predictive maintenance solutions usually require cloud services and are resource-hungry,” explains Eugene Zetserov, Polyn’s vice-president of marketing. “The sensor node consumes a lot of electricity on vibration data transmission. Collecting data from many sensors requires considerable resources such as the sensor node itself, radio bandwidth, data processing and storage in the cloud.
“VibroSense reduces the need for these resources through a thousand-fold reduction of sensor data to be sent for analysis in the central cloud or at the edge.”
“VibroSense is the only analogue neuromorphic solution on the market today that extracts vibration signal patterns at the sensor level,” he adds. “It not only saves IIoT network bandwidth and reduces total cost of ownership, it enables faster adaptation of predictive maintenance solutions, better performance and sustainability.”
Polyn specialises in application-specific Neuromorphic Analog Signal Processing (NASP) technology and Neuromorphic Front End (NFE) chips for always-on sensor systems. NFE chips have ultra-low power consumption, low latency, and high resiliency for novel AI-based products.
Polyn supports a hybrid architecture where patterns are extracted from the analogue portion of signals, leaving classification for the digital element. In this way, VibroSense offers flexibility as well as cutting power consumption, and chips that adapt to applications, allowing different deployments for the same chip.
Polyn’s AI chips analyse vibration data locally, cutting the amount of information that needs to be passed on
Polyn Technology: Twitter LinkedIn
