AI PLC Control Agent for Automatic Set Point Optimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional Programmable Logic Controllers (PLCs) lack the ability to automatically optimize set points and process inputs in industrial environments using advanced data analytics, leading to suboptimal performance and requiring human intervention for adjustments.
Innovation Solution
An artificially intelligent control system that queries data from PLCs, generates multiple potential solution sets using machine-learning models, assesses these sets, and automatically updates PLC set points to alter physical behavior in the environment, thereby optimizing industrial processes without human intervention.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If conventional PLCs with HMI are used for controlling industrial processes, then human operators can manually adjust set points, but the system lacks automatic optimization capability and requires continuous human intervention
Solution Approach 1:
The system enables self-service by implementing an AI agent that automatically queries PLC data, generates solution sets using machine learning models, assesses potential solutions, and updates PLC set points without human intervention. The AI agent autonomously optimizes process parameters by leveraging historical and real-time data, eliminating the need for continuous manual adjustment while maintaining system performance
Solution Approach 2:
The patent replaces the mechanical human-operator intervention system with an intelligent automated system. Instead of human operators manually analyzing data and adjusting set points through HMI interfaces, an AI-based control agent automatically performs data querying, analysis, solution generation, and PLC configuration updates, substituting human cognitive and manual operations with intelligent algorithms
2Productivity
If manual adjustment of PLC set points is used, then operators can change operational parameters, but the process efficiency is reduced and time-consuming adjustments are required
Solution Approach 1:
The system applies preliminary action by continuously analyzing historical and real-time PLC data to predict optimal set points before performance degradation occurs. The AI agent proactively generates and implements solution sets that prevent efficiency losses, rather than reacting to problems after they manifest. This anticipatory optimization reduces the time needed for corrective adjustments and maintains higher overall productivity
Solution Approach 2:
The patent implements continuity of useful action by establishing an ongoing automated optimization cycle where the AI agent continuously queries PLC data, analyzes performance trends, generates solution sets, and updates set points without interruption. This continuous operation eliminates the periodic downtime associated with manual adjustments and maintains uninterrupted productive operation
3Reliability
If conventional PLC control systems are used, then basic automation is achieved, but advanced data analytics and machine learning optimization are not utilized
Solution Approach 1:
The patent introduces an intermediary AI agent layer between the PLC control system and the optimization algorithms. This intermediary component handles data querying from the PLC, coordinates with machine learning models for solution generation, manages assessment of potential solutions, and interfaces with PLC configuration for updates. This intermediary architecture enables advanced analytics integration while maintaining compatibility with existing PLC systems and managing overall system complexity
Data Source
AI summary
A computer-implemented method including querying, from data sources including a data historian associated with performance of an automated environment controlled by one or more programmable logic controllers (PLCs), data for the automated environment controlled by the one or more PLCs. The method also can include validating and error-correcting the data, and generating multiple potential solution sets based on the data and multiple machine-learning models. The method additionally can include assessing the multiple potential solution sets to select one or more solution sets. The method further can include outputting at least one solution set of the one or more solution sets to cause (i) set points and process inputs of the one or more PLCs to be automatically updated based at least in part on the at least one solution set, and (ii) physical devices of the automated environment controlled by the one or more PLCs to alter behavior of the automated environment. Other embodiments are described.