Legacy PLC Replacement Using ML Behavior Cloning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Legacy programmable logic controllers (PLCs) pose challenges due to the lack of spare parts, proprietary protocols, and the loss of engineering skills, making it difficult and costly to replace them without incurring significant hardware and software engineering costs, and resulting in production downtime and vendor lock-in.
Innovation Solution
The implementation of machine learning techniques, such as deep neural networks and deep reinforcement learning, to train a replacement PLC (ML-PLC) to learn and imitate the behavior of the legacy PLC, allowing it to understand and improve the automation environment's operations without requiring extensive programming, and enabling virtualization for efficient replacement.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of time
If traditional PLC replacement methods are used, then hardware and software engineering costs are reduced, but production downtime increases and vendor lock-in persists
Solution Approach 1:
The patent creates a digital twin (virtual replica) of the legacy PLC that captures its behavior, state, and operational characteristics. This digital twin can be analyzed, replicated, and transferred to new hardware platforms without requiring deep understanding of the legacy system's proprietary internals, thereby reducing both downtime and engineering complexity.
Solution Approach 2:
The patent introduces an intermediary layer (the digital twin and behavior capture system) between the legacy PLC and the replacement system. This intermediary captures the essential behavior and state of the legacy system, allowing replacement without direct access to proprietary programming or internal structures, thus reducing vendor lock-in and engineering barriers.
2Reliability
If legacy PLCs are kept in operation, then operational continuity is maintained, but spare parts availability decreases and engineering skills are lost
Solution Approach 1:
The digital twin captures and preserves the operational knowledge, behavior patterns, and state information of the legacy PLC in a format that can be stored, analyzed, and transferred. This prevents loss of engineering knowledge even when the original hardware becomes obsolete or when specialists retire.
Solution Approach 2:
The system enables self-documentation and self-analysis of PLC behavior through automated state capture and behavior modeling. This reduces dependence on human experts who remember legacy system quirks and programming nuances, as the system itself generates and preserves this knowledge.
3Adaptability or versatility
If proprietary protocols are used, then vendor lock-in is avoided, but adaptability to new systems decreases
Solution Approach 1:
The digital twin acts as an intermediary that translates and captures protocol behavior without requiring the replacement system to directly implement or understand the proprietary protocols. This enables adaptability to new systems while preserving the essential communication patterns and behavioral characteristics of the legacy system.
Data Source
AI summary
Over the past several decades, rapid advances in semiconductors, automation, and control systems have resulted in the adoption of programmable logic controllers (PLCs) in an immense variety of environments. Machine learning techniques help train replacement PLCs when a legacy PLC must be replaced, e.g., due to aging or failure. The techniques facilitate the efficient adoption and correct operation of replacement PLCs in the industrial environment.