Industrial Controller AI Multicore Adaptive Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current industrial controllers rely on deterministic control programs that are inflexible and require pre-anticipation of all possible system states, leading to potential malfunctions when unanticipated conditions arise and may not yield optimal performance across all operating conditions.
Innovation Solution
An industrial controller that integrates a program execution component for deterministic control and an AI engine for executing non-deterministic search algorithms to dynamically update the control program based on current operating conditions, improving control performance metrics.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If deterministic control programs are used, then predictable control outputs are generated, but the system lacks adaptability when unanticipated conditions arise
Solution Approach 1:
The patent implements a multi-core processor architecture where one core executes deterministic control programs for reliable predictable outputs, while another core executes non-deterministic search algorithms that dynamically adapt to unanticipated conditions. The system dynamically switches between deterministic and adaptive control modes based on operating conditions, resolving the contradiction between reliability and adaptability.
2Productivity
If pre-developed deterministic control code is executed, then high frequency execution cycles are achieved, but control performance is not optimal across all operating conditions
Solution Approach 1:
The patent segments the control system into two functional parts: a deterministic control program executed at high frequency for basic control operations, and a separate non-deterministic search algorithm executed periodically for optimization. This segmentation allows the system to maintain high execution frequency while periodically improving control performance metrics through adaptive optimization.
Solution Approach 2:
The non-deterministic search algorithm analyzes current operating conditions and control performance metrics, then generates optimized control strategies that are fed back to update the deterministic control program. This feedback loop enables continuous improvement of control performance while maintaining high execution frequency through the deterministic core.
3Device complexity
If deterministic control programs are used, then device complexity is reduced, but adaptability to changing operating conditions deteriorates
Solution Approach 1:
The patent merges deterministic and non-deterministic control approaches into a unified multi-core processor system. The deterministic control program maintains simple structure for ease of implementation, while the integrated non-deterministic search algorithm provides adaptive capabilities. The merging of these two approaches in a single hardware platform enables both structural simplicity and operational adaptability.
Data Source
AI summary
An industrial controller supports deterministic execution of control programs (e.g., ladder logic, function block diagrams, structured text, or other such control code) and is also capable of executing non-deterministic execution cycles, including mathematical optimization algorithms—in which a systematic search in a solution space is performed to identify a desired solution—or machine learning algorithms, either of which can be used by the controller to dynamically update the deterministic control program or code based on current or predicted states of the automation system being controlled by the controller.