The solution enables industrial-equipment vendors to quickly evaluate embedded AI models running on device and learning
Octonion SA, a deep tech software company specialising in Artificial Intelligence (AI) at the Edge for industrial-equipment diagnosis has announced a STM32Cube expansion package optimised for STM32L4+ microcontroller-based industrial-application development boards from STMicroelectronics.
Octonion’s new software package supports ST’s efforts to develop Artificial Intelligence-based applications running on STM32 microcontrollers and microprocessors in the fast-growing condition-based-monitoring and predictive-maintenance segments. The Octonion I-CUBE-OCTMI package delivers a self-care system running on STM32 ultra-low power MCUs and powered by Octonion’s Edge AI engine that automatically learns, inspects and monitors the health of industrial equipment throughout its operating life.
The expansion pack is optimised for the STM32L4+ development boards which include a range of ST’s industrial-grade sensors and connectivity features, starting from the STWIN SensorTile Wireless Industrial Node. It embeds Octonion’s AI engine operating in an unsupervised mode, continuously analysing data from an accelerometer to handle vibration analysis for condition monitoring and predictive maintenance. The engine does not require any prior knowledge of the equipment or existing dataset. It learns operational modes locally on the microcontroller to fine-tune the embedded Octonion Machine Intelligence algorithm. With all the computation done at the Edge, there are no data sent outside, eliminating possible privacy issues.
Industrial machine behaviour coverage
The I-CUBE-OCTMI expansion pack gives developers access to two ready-to-use algorithms: Instant Analyser for fast-response equipment-health analysis and Wize Analyser designed for equipment with frequent operational-mode changes. The expansion pack covers a wide range of industrial machines’ behaviours allowing it to detect spike anomalies and extended dynamic state anomalies on motors of various power classes, including small BLDC, PMSM motors, or huge turbines.
“Developers can customise different parameters to adapt the embedded AI engine for their specific use case, balancing the quality of equipment-state recognition, its computational complexity, and the response speed,” said Andrei Sheleh, CTO of Octonion.
“Octonion Edge AI engine coupled with ST’s STM32 MCUs allows any industrial organization to reduce its maintenance cost and downtime by easing and accelerating the implementation of predictive-maintenance solutions with real-time machine-health monitoring on all STM32 build-in systems or ultra-low power STM32 MCUs,” said Jacky Perdrigeat, EMEA Marketing & Application VP, STMicroelectronics.
The I-CUBE-OCTMI is available under commercial license with free usage for evaluation and non-commercial purposes.
ST’s solutions for embedded AI, including a customer-tailored machine-health monitoring application developed in collaboration with Octonion was presented at ST Live Days, during the IoT&5G session held last month.