Abstract
IEC 61499 is a reference architecture for constructing Industrial Cyber-Physical Systems (ICPS). However, current function block development environments only provide limited fault-finding capabilities. There is a need for comprehensive diagnostic tools that help engineers identify faults, both during development and after deployment. This article presents the software architecture for an agent-based fault diagnostic engine that equips agents with domain-knowledge of IEC 61499. The engine encourages a Model-Driven Development with Diagnostics methodology where agents work alongside engineers during iterative cycles of design, development, diagnosis and refinement. Attribute-Driven Design (ADD) was used to propose the architecture to capture fault telemetry directly from the ICPS. A Views and Beyond Software Architecture Document presents the architecture. The Architecturally-Significant Requirement (ASRs) were used to design the views while an Architectural Trade-off Analysis Method (ATAM) evaluated critical parts of the architecture. The agents locate faults during both early-stage development and later provide long-term fault management. The architecture introduces dynamic, low-latency software-in-loop Diagnostic Points (DPs) that operate under the control of an agent to capture fault telemetry. Using sound architectural design approaches and documentation methods, coupled with rigorous evaluation and prototyping, the article demonstrates how quality attributes, risks and architectural trade-offs were identified and mitigated early before the construction of the engine commenced.
Highlights
Embedded Control Systems (ECSs), augmented with communications and sophisticated sensors, have led to the development of powerful new mechanisms known as Industrial-scale Cyber-Physical Systems (ICPS)
Design resources created in the Integrated Development Environments (IDEs) during the creation of the Function Blocks (FBs) application are available to the agents
The use of domain-specific agents in the GORITE framework provides a scope for implementing model-free or machine-learning approaches during subsequent research
Summary
Embedded Control Systems (ECSs), augmented with communications and sophisticated sensors, have led to the development of powerful new mechanisms known as Industrial-scale Cyber-Physical Systems (ICPS). This paper focuses primarily on the architectural design of the software agents and the way in which they have been provided with domain-specific knowledge of IEC 61499 This equips them with the abilities they need to interact with FB applications that are operating nominally, are failing, or have failed. The primary contribution of this paper is its presentation of the architecture for a fault detection engine in a well-structured Software Architecture Document that draws on recognized industry standards It describes the way the agents apply domain-specific knowledge during fault finding for ICPS. When agents are deployed by the engine, they first explore the IEC 61499 application definition files of the ICPS that will be diagnosed They build sets of beliefs about the FBs and how they are connected to each other. The agents are responsible for managing the fault-finding activities while the primary role of the DPs is to gather telemetry and inject test values into function blocks
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have