Industrial AI Model Aggregation for Hierarchical Process Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional enterprise systems face challenges in optimizing operations due to complex mathematical programming, dependency on intricate metadata models, and the overwhelming volume of data generated across automated processes, leading to inefficiencies and unachievable objectives.
Innovation Solution
The system employs graphical representations of industrial processes using models and supermodels, allowing for real-time monitoring and control through intelligent devices with on-board processing capabilities. This enables the adjustment of operations based on changing conditions and the incorporation of AI for data analysis and decision-making.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If conventional enterprise systems use complex mathematical programming and metadata models to optimize operations, then system optimization capability is improved, but device complexity and operational burden increase significantly
Solution Approach 1:
The patent segments the complex enterprise system into multiple hierarchical levels (enterprise level, plant level, area level, device level), with each level having its own simplified model and optimization capabilities. This segmentation allows complex optimization problems to be broken down into manageable sub-problems at each hierarchical level, reducing overall system complexity while maintaining optimization effectiveness.
Solution Approach 2:
The patent introduces intermediate control systems at each hierarchical level that act as mediators between the enterprise-level optimization goals and the actual device operations. These intermediate systems translate high-level optimization objectives into device-specific control parameters, reducing the complexity burden on individual devices while maintaining system-wide optimization capability.
2Loss of information
If conventional systems process large volumes of sensor data through higher-level devices, then data processing capability is improved, but operational burden on higher-level devices increases
Solution Approach 1:
The patent segments data processing responsibilities across multiple hierarchical levels. Device-level systems perform initial data filtering and preprocessing, area-level systems perform intermediate processing, and enterprise-level systems perform high-level analysis. This segmentation distributes the operational burden of data processing across multiple systems rather than concentrating it at the higher level, reducing the burden on any single device while maintaining comprehensive data processing capability.
3Adaptability or versatility
If conventional enterprise systems use highly complex metadata models from disparate sources, then system comprehensiveness is improved, but model explainability and achievability of objectives deteriorate
Solution Approach 1:
The patent segments the comprehensive metadata model into hierarchical layers, with each layer maintaining explainability for its specific level while collectively providing system-wide comprehensiveness. Device-level models explain device-specific behavior, area-level models explain regional patterns, and enterprise-level models explain overall system objectives. This segmentation preserves explainability at each level while maintaining comprehensive system coverage through the hierarchical structure.
4Loss of information
If conventional systems rely on higher-level devices to process and format all data, then data centralization is improved, but response time and real-time control capability deteriorate
Solution Approach 1:
The patent segments data processing and control functions across hierarchical levels, enabling real-time responses at device and area levels without requiring all decisions to be centralized at the enterprise level. This segmentation allows critical real-time control actions to be executed locally with minimal delay, while still maintaining centralized data collection and high-level coordination for non-critical functions.
Solution Approach 2:
The patent implements dynamic control where the level at which processing occurs can adapt based on the urgency and importance of the task. Critical real-time control functions are dynamically handled at lower hierarchical levels for immediate response, while less time-sensitive functions are handled at higher levels for centralized coordination. This dynamic allocation of processing functions optimizes both response time and data centralization.
Data Source
AI summary
Various systems and methods are presented regarding monitoring and controlling operation of a process. A visual representation of the process can be created based on a supermodel comprising models (representing one or more devices) and nodes (representing respective device variables and constraints). Further, the process can be represented by levels, wherein devices at each level can be self-aware and have onboard artificial intelligence, such that a device at any level can auto-configure itself in accordance with a requirement placed upon it. Field-level devices (IFLDs) can be smart devices which auto-configure based upon a requirement from a higher-level device. Accordingly, system awareness can be incorporated across all levels of the process enabling overall and device-specific optimization of the process. IFLDs can auto-configure to collect and transmit data in accordance with an instruction from a higher-level device, leading to efficient data collection, reduced data bandwidth/processing, and expedited system optimization.