Industrial AI Model Graphs for Hierarchical Process Optimization
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 in industrial processes, which can lead to unachievable objectives and inefficient data processing.
Innovation Solution
The system employs a configuration component to construct graphical representations of industrial processes using models and nodes, an AI component to monitor and adjust these models in real-time, and a visualization component to present the data on a human-machine interface, enabling efficient data processing and model updates.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If conventional enterprise systems use complex mathematical programming and intricate metadata models to optimize operations, then the system can handle sophisticated optimization requirements, but the system complexity and difficulty of operation 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 sophisticated optimization to be achieved through coordinated simple models at each level, rather than requiring one monolithic complex model.
Solution Approach 2:
The patent introduces simplified intermediate models at each hierarchical level that act as mediators between the complex real-world processes and the optimization algorithms. These intermediate models translate complex operational requirements into manageable optimization problems, reducing overall system complexity while maintaining optimization capability.
2Reliability
If conventional systems process large volumes of sensor data through higher-level devices, then comprehensive monitoring is achieved, but the operational burden on higher-level devices increases significantly
Solution Approach 1:
The patent divides data processing responsibilities across multiple hierarchical levels, with each level processing only the data relevant to its scope. Lower levels (device, area, plant) perform initial data processing and filtering, so that higher enterprise levels receive pre-processed, relevant data rather than raw sensor streams, reducing operational burden while maintaining monitoring completeness.
Solution Approach 2:
The patent implements preliminary data processing and filtering at lower hierarchical levels before data reaches higher levels. Each level performs preliminary aggregation, validation, and relevance filtering of data, so that higher-level devices receive pre-prepared data in the appropriate format, reducing their operational burden.
3Loss of information
If conventional systems generate and transmit extensive sensor data across the enterprise, then comprehensive process information is available, but data transmission and processing become unwieldy
Solution Approach 1:
The patent extracts and processes data locally at each hierarchical level, taking out only the essential information needed for each level's decision-making. Rather than transmitting all raw sensor data to the enterprise level, each level extracts relevant features and insights locally, reducing data transmission volume while preserving necessary information.
Solution Approach 2:
The patent segments data processing into hierarchical layers, with each layer processing data appropriate to its scope. This segmentation allows comprehensive information to be maintained through distributed processing while improving productivity by avoiding the transmission and processing of unnecessary data at higher levels.
4Loss of information
If conventional systems use highly complex metadata models from disparate sources, then comprehensive system representation is achieved, but the models become non-explainable and difficult to interpret
Solution Approach 1:
The patent segments the complex metadata model into hierarchical layers, with each layer representing a specific scope (enterprise, plant, area, device). This segmentation maintains comprehensive system representation through the hierarchy while improving interpretability by allowing users to understand and interact with models at appropriate granularities without being overwhelmed by overall system complexity.
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.