Sensor Fusion x Physical AI: Enabling Fusion and Decision-Making at the Edge
On industrial sites, equipment data comes from sensors with different protocols, different formats, and different frequencies. NeoFlow instantly aggregates, cleans, and transforms this heterogeneous data at the edge, and cross-references it with Edge AI model inference results to form a cross-modal intelligent decision-making process—completing the perception-to-action loop on-site without uploading to the cloud or waiting for a response.
Through NeoFlow's innovative and secure process orchestration and synchronization technology, enterprises can uniformly manage the lifecycle of OT data and AI models, truly bridging the information gap between OT and IT, and realizing the implementation of Physical AI on the factory floor.
The humanized workflow orchestration tool NeoFlow, customize enterprise-exclusive Physical AI
No-code graphical interface
A node-based No-Code logic engine built on a containerized architecture, allowing OT engineers to connect data flows by dragging and dropping nodes, bid farewell to complex development processes and terminal commands. Each node can be configured with processing logic such as conditional judgments, data merging, type conversion, and time window calculations. The system provides real-time prompts when data formats do not match, significantly reducing the risk of configuration errors. For advanced logic, custom applications (Custom Apps) can also be deployed, balancing ease of use with flexibility.
Scalable open architecture
Users can develop custom containers (Custom APP) through the SDK (supporting Python, Go) to create exclusive applications that meet their specific site requirements. The platform supports custom nodes, allowing developers to package their self-developed programs into containerized applications for direct deployment and operation at the edge.
100% Containerization Support
Users can deploy different inference environments on the edge according to their needs, such as NVIDIA TensorRT, Intel OpenVINO, ONNX Runtime, PyTorch, TensorFlow, or third-party AI inference environments, to establish a management mechanism for edge inference environment and AI model iterative integration, and quickly deploy AI applications.
Flexible cross-plant deployment with unified scheduling
The same NeoFlow process can simultaneously connect tens to hundreds of industrial gateways. Through parameterized design, each device is applied with its respective credentials, usernames, passwords, and connection information. Engineers do not need to reconfigure for each site, nor do they need to worry about human errors during the configuration process.
When a successful process can be validated on the first production line and only requires parameter adjustments to be quickly replicated across the second and third factories, your industrial AI deployment can move from single-point validation to group-wide implementation.
Application cases
Multinational equipment manufacturer enhances service efficiency by integrating AI agents
The client is a multinational equipment manufacturer with products distributed nationwide. In addition to selling products, they also sign maintenance contracts with clients and provide 24/7 round-the-clock service. However, when dispatching repair personnel, they are unable to obtain real-time equipment status on-site. They must send personnel to the location to assess the situation before they can evaluate how to perform repairs, leading to many ineffective dispatches and increased operational costs.
