ROHM has released the industry-first AI MCUs capable of standalone learning and inference specifically designed to enable predictive maintenance.
The new ML63Q253x-NNNxx and ML63Q255x-NNNxx series leverage real-time sensor data to detect anomalies, predict failures, and anticipate equipment degradation across a broad spectrum of industrial applications. As industrial machinery becomes more intelligent and efficient, the ability to perform early fault detection and predictive maintenance offers significant operational and economic advantages.
In an exclusive interview with electropages, Kenichi Morioka, Technical Marketing Manager at ROHM Semiconductor USA, emphasized that these devices are the first in the industry capable of performing both AI learning and inference entirely on the device, eliminating the need for network connectivity.
AI Learning and Inference
“Solist-AI™ digitizes and learns the normal operating state of target equipment on-site using sensor input, then detects deviations from this baseline as an ‘anomaly score’ – a numerical indicator used to predict potential failures or performance degradation,” explained Morioka.
By conducting learning directly at the deployment site, the system can accurately capture the specific characteristics of each device, including environmental factors such as noise, vibration, and humidity, as well as individual unit variations, enabling high accuracy failure prediction. Morioka added, “This technology simplifies deployment through on-site learning without relying on the cloud. Operating without a network connection ensures faster response times, minimizes information security risks, and reduces communication costs.”
Industrial Motor Applications
Solist-AI™ captures and learns normal operating parameters—such as motor current, temperature, and rotational speed, using data collected from sensors. “If abnormalities like bearing wear or load misalignment occur, they manifest as subtle changes current and vibration patterns. Solist-AI™ identifies these deviations and raises the anomaly score accordingly,” Morioka explained.
In a typical implementation, this elevated anomaly score is transmitted to a host microcontroller, which interprets this signal as an indication that maintenance is required.
Predictive Maintenance
“Equipment failures can lead directly to line stoppages and increased maintenance costs,” noted Morioka. Proactively addressing potential issues before a complete failure occurs is essential to minimizing downtime and reducing overall maintenance expenses—making predictive maintenance a critical and widely adopted practice. Morioka further commented, “In some countries, regions, or installation sites, it can be challenging to secure inspection personnel or conduct frequent checks. We believe this solution offers a practical and effective alternative in such cases.”
Solist-AI™ Solution
Solist-AI™ incorporates a compact 3-layer neural network algorithm that enables both learning and inference directly at the endpoint, such as motors, without requiring cloud connectivity, host computers, or network networks. “To support smooth evaluation and implementation, we offer development tools such as Solist-AI™ Sim, a simulator for verifying AI behavior, and Solist-AI™ Scope, a real-time visualization tool that illustrates AI performance,” Morioka explained. Solist-AI™ Sim, in particular, allows users to assess the suitability and effectiveness of Solist-AI™ for their specific application on a PC before deploying the hardware.
No Cloud Dependency Required
Solist-AITM performs both learning and inference directly on the microcontroller, eliminating the need for cloud services or large-scale data transmission. “Anomalies can be easily communicated to a host microcontroller via standard serial interfaces, making it easy to retrofit Solist-AI™ into existing systems,” Morioka noted. Traditional AI models often rely on network access and powerful processors, introducing challenges like latency, higher costs, and cybersecurity risks.
In contrast, Solist-AI™ achieves processing speeds up to 1,000 times faster than traditional software-based approaches while consuming only a few tens of milliwatts.
Key Features
“This FLASH microcontroller is built around an Arm Cortex-M0+ core and comes equipped with a range of peripherals, including multiple serial interfaces, an A/D converter, CAN controller, multifunction timers (i.e. PWM and capture), and an analog comparator,” Morioka emphasized. Beyond these standard features, integrating Solist-AI™ enables both on-site learning and inference. Unlike conventional endpoint AI solutions that rely on cloud-based training and local CPUs or GPUs for inference, ROHM’s approach incorporates the AxlCORE-ODL AI accelerator to handle both processes efficiently on-device. “As no communication with the cloud or external host is required for inference, and given its high processing speed, the system can detect anomalies and deviations from normal behavior in real time,” Morioka added.
Expansion Plans
Solist-AI™ is a fully standalone AI capable of performing both learning and inference independently, with the need for cloud connectivity. “Its versatility allows it to be applied in ways we hadn’t initially envisioned,” noted Morioka. “We plan to expand the product lineup to meet emerging needs.” Solist-AITM is available for purchase from major global online distributors such as DigiKey, Mouser, and Farnell. Evaluation boards (RB-D63Q2537TB48, RB-D63Q2557TB64) are also offered to support rapid software development and standalone evaluation.
Morioka added, “We are also advancing our ‘Ecosystem Partner’ program, which involves collaboration with companies (currently concentrated in Japan) that specialize in PCB design, manufacturing, assembly, software development and AI system integration.” This program is designed to help customers implement Solist-AI™ quickly and efficiently, even those without expertise in AI.
Click here to learn more about ROHM’s Solist-AI™ Solution. For technical support or purchasing inquiries regarding this solution, please contact ROHM engineers at [email protected].
