Chiller And Air Handler AI Control for KPI-Constrained Optimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Smaller entities and those lacking expertise or infrastructure struggle to effectively apply AI systems to optimize industrial processes due to a lack of domain-level knowledge integration and effective AI system configuration.
Innovation Solution
An AI system that aggregates system-defining information, including KPIs, process variables, and equipment constraints, using an interactive interface to query users and optimize KPIs through an AI agent, enabling domain experts to input their knowledge and generate actionable plans.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If AI systems are implemented to optimize industrial processes, then productivity and KPI optimization improve, but device complexity and implementation difficulty increase
Solution Approach 1:
The patent introduces an intermediary AI system that acts as a mediator between domain experts and the optimization process. This intermediary translates domain knowledge into actionable optimization strategies, reducing the complexity burden on end users while maintaining high productivity benefits. The AI system serves as a bridge that converts expert knowledge into automated decision-making capabilities.
Solution Approach 2:
The AI system is designed to autonomously optimize KPIs by itself, requiring minimal human intervention once configured. The system self-manages the complex AI algorithms, data processing, and optimization routines, freeing domain experts from the burden of managing system complexity while still achieving significant productivity improvements.
2Reliability
If domain experts configure AI systems directly, then optimization effectiveness improves, but ease of operation deteriorates due to lack of AI expertise
Solution Approach 1:
The patent employs an intermediary AI system that translates domain expert knowledge into optimization configurations automatically. Domain experts provide their knowledge through natural interaction, and the AI intermediary handles the complex translation and configuration tasks, maintaining optimization effectiveness while dramatically improving ease of operation.
Solution Approach 2:
The patent replaces the manual mechanical process of AI system configuration with an automated AI-driven process. Instead of requiring domain experts to manually configure complex AI parameters, the system uses AI agents to automatically interpret domain knowledge and configure optimization strategies, making the process accessible to non-experts while maintaining high effectiveness.
3Ease of operation
If existing AI systems are used without domain knowledge integration, then implementation ease improves, but optimization effectiveness deteriorates
Solution Approach 1:
The patent implements feedback loops where the AI system continuously learns from domain expert inputs and optimization outcomes. Domain knowledge is fed into the system, which then applies it to optimize KPIs and provides feedback on results. This iterative feedback process maintains ease of implementation while progressively improving optimization effectiveness through learned domain insights.
Solution Approach 2:
The patent performs preliminary integration of domain knowledge into the AI system during the configuration phase. By pre-loading domain expertise and constraints into the AI system before deployment, the system achieves both ease of operation and high optimization effectiveness from the outset, eliminating the need for complex post-deployment adjustments.
Data Source
AI summary
Methods and systems are disclosed for determining a plan to optimize key performance indicators (KPIs) of an industrial process using a trained artificial intelligence agent and a custom objective function determined based on process information from the industrial system.