Cameras, sensors, multi-modal data and on-device AI come together in one adaptable architecture — built to observe, understand and respond to the physical world in real time.
Multi-modal sensing
Edge AI on-device
Multi-signal fusion · real-time inference
Actionable intelligence
Detection · prediction · automation · integration
Conventional monitoring watches for a single value to cross a line. That's too late and too blunt — it misses the early build-up, and it can't tell a real event from noise.
AIOTOMATE analyzes the sequence and magnitude of sensor events over time. A rolling window of multi-channel sensor data is fed to a machine-learning model that recognizes the pattern of an emerging failure — the order in which signals appear, how they escalate, how they relate to each other — against patterns learned from recorded event data.
The output isn't a binary alarm. It's a probability of the event — graded, early, and continuously updated. That's what lets us warn before a threshold would ever trip, and distinguish a genuine event from an environmental false alarm.
Signal over time
Inference runs locally on the device, close to the sensors and cameras that generate the data. Models process incoming signals in real time, without requiring a cloud round-trip for every decision.
Depending on the application, edge models can detect patterns, classify events, combine multiple sensing modalities, or trigger local actions directly on the device.
Models are trained offline and deployed to dedicated edge-AI hardware for inference. Keeping intelligence close to the physical process reduces latency, limits unnecessary data transfer, and allows systems to continue operating when connectivity is unavailable or unreliable.
On-device inference
Sensor window
Rolling multi-channel time series
1D‑CNN NPU
Convolutional feature extraction, accelerated
Dense
Classification layer
Event probability
Graded, real-time, on-device
Extend to a new sensor
The method doesn't care what produces the data. Because it operates on time-series signals, the platform ingests any analog or digital sensor — gas, thermal, electrical, vibration, acoustic, vision, and more.
Stopyr applies this to a specific gas-sensor array for battery thermal-runaway detection. The same architecture extends to condition monitoring, visual inspection, and process safety — the model changes, the platform doesn't.
AIOTOMATE speaks the protocols industrial sites already run — RS485 / Modbus, CAN, and dry-contact I/O into existing BMS, SCADA, fire-and-gas panels, inverters, and access control. Manufacturer-agnostic, retrofit-ready, no rip-and-replace.
RS485 industrial fieldbus
Battery & inverter comms
Building & EMS integration
Relay · dry-contact I/O
Hybrid & storage inverters
SCADA · cloud edge
The edge makes the decision; the platform gives you the picture — across every site.
Device provisioning, configuration, live monitoring, and reporting across sites — one pane for the whole fleet.
Data and status exposed for integration into your own systems — pull results into the tools your operators already use.
Results stream to the cloud for cross-site trends — an optional visibility layer, never a dependency for local operation.
Honest status, layer by layer — what's in testing, what's proven, what's operational today, and what's in build. Nothing overclaimed.
Detection approach tested against real battery packs — targeting BESS deployments from residential to grid-scale.
Hardware integration verified on the current generation in lab conditions.
The management platform and API are operational.
Edge vision built on the same principles runs in production with a UK manufacturing partner.
The STM32N6 edge platform is in active development — bringing advanced sensing and AI inference fully on-device.