A full-stack self-controllable software foundation for PLC, DCS, and intelligent controllers, providing 1ms hard real-time control, multi-protocol SOA industrial communication, and native edge AI support, validated on domestic processor platforms.
The vast majority of domestic PLC manufacturers rely on overseas vendors for runtime and programming environments. Self-developed logic compilation software for medium and large PLCs is extremely rare. Embedded software costs account for 20%~40% of total PLC costs, and software licensing fees continue to rise, making domestic replacement imperative.
Traditional PLC control logic, communication protocols, and underlying hardware are highly coupled. Replacing a chip means rewriting the entire upper-layer software. In the current context of increasing supply chain uncertainty, software-hardware decoupling has become an industry necessity.
As Industry 4.0 advances, OT/IT convergence has shifted from trend to necessity. Traditional PLCs focus solely on real-time control, lacking native interoperability with MES, ERP, and cloud platforms, resulting in widespread data silos. The industry urgently needs a unified software platform to create an end-to-end data pipeline from the shop floor to enterprise management.
AI applications such as visual quality inspection and predictive maintenance are moving from pilots to routine deployment. However, traditional controllers lack both the computing power for edge AI inference and the software framework for large model interaction. Next-generation domestic SoCs integrate NPU power, but lack a software foundation to safely fuse AI with real-time control.
Three real-time levels cover all scenarios from μs-level hard real-time to upper-layer applications, with unified execution management providing complete lifecycle control.
Hard Real-Time Control
Closed-loop control tasks within 1ms, deployed on a dedicated hard real-time control plane, providing microsecond-level scheduling precision
Periodic Control
Periodic control and acquisition tasks, supporting phase alignment and cross-plane data consistency management
Upper-Layer Applications
HMI, data analysis and other upper-layer applications, with four-tier fault recovery (thread-level, process-level, service-level, node-level)
Unified Protocol Abstraction
Control Plane / Information Plane Separation
Cross-Domain Protocol Bridging
Interface Version Management
Compatible with existing PLC ecosystem, retaining SoftPLC Runtime engineering assets while gaining comprehensive enhancements.
Supports SoftPLC Runtime configuration and runtime monitoring, providing runtime status queries, log collection, and exception restart interfaces
Supports SoftPLC Runtime data integration with platform persistence framework
Supports SoftPLC Runtime and platform state machine linkage for unified lifecycle management
For dual-machine redundancy scenarios, supports integration with SoftPLC Redundancy SL or equivalent redundancy framework
Dual-domain architecture natively supports edge AI inference and large model deployment, with hard real-time control and intelligence operating without interference.
Fully leverages NPU computing power built into domestic SoCs, supporting vision inspection, predictive maintenance, process parameter optimization, and other AI inference tasks on the controller locally, achieving edge intelligence with data never leaving the site.
AI/Large model tasks run in the general application domain, so even if anomalies occur they will not affect hard real-time control task execution. AI analysis results are delivered to the control domain as "recommendations" for final decision-making by control logic.
The platform pre-deploys AutoForge™, an intelligence agent platform created by AutoCore, evolving traditional pre-programmed controllers into intelligent devices capable of long-term upgrades and services.
Persistence and Configuration Management
Supports atomic commits, power failure protection, versioning, checksums and rollback, ensuring critical data does not enter "half-written" state from a single power failure. Startup parameters, device configurations, and application configurations are managed in layers.
Four-Tier Watchdog Chain
Task watchdog, service watchdog, system watchdog, and hardware watchdog, supporting abnormal exit, deadlock, livelock, resource leak, and cycle timeout detection.
High Availability Architecture
Supports single-node self-recovery and dual-machine hot/warm/cold standby, with fault-safe state and controlled degradation mechanisms.
Fault Diagnostics
Crash snapshots, core dumps, and recent fault window data preservation capabilities ensure single-point software faults do not cause irrecoverable machine failures.
Platform Internal Interfaces
Unified service registration/discovery, unified message bus, shared memory process data, unified clock and timestamp, unified health status and fault code interfaces
Controller to Device Interfaces
Unified device model, unified abstraction of local I/O, remote I/O and fieldbus devices, supporting multi-protocol plugin access and redundant link definitions
Controller to Upper-Layer Application Interfaces
OPC UA Server/Client and MQTT interfaces, supporting log queries, status queries, and alarm subscriptions, with built-in authentication, authorization, and audit capabilities
Systematic validation completed on domestic ARM processor platform, with all key metrics meeting or exceeding design requirements.
