Industrial AI Data Navigation for Hierarchical Process Monitoring
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, which can lead to unachievable objectives and operational burdens.
Innovation Solution
A system comprising a processor and memory that executes computer-executable components to construct a graphical representation of an industrial process using interconnected models, allowing for visualization and navigation across multiple levels of information, including operational details of devices, and enabling detection of changes in process operations.
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 increases and becomes difficult to manage and explain
Solution Approach 1:
The patent segments the complex enterprise system into multiple hierarchical levels (enterprise level, plant level, area level, device level). Each level has its own simplified model and optimization capabilities, avoiding the need for a single monolithic complex model. This allows sophisticated optimization at each level while keeping individual models manageable and explainable.
Solution Approach 2:
The patent introduces a hierarchical dimension to the system architecture, organizing models and data across multiple levels from enterprise-wide to device-specific. This dimensional organization transforms the problem from managing one complex model to managing multiple simpler models at different hierarchical levels, each with focused scope and purpose.
2Loss of information
If conventional systems process all sensor data from automated processes, then complete operational information is available, but the data volume becomes overwhelming and places significant operational burden on higher-level devices
Solution Approach 1:
The patent segments data processing across hierarchical levels, with each level processing only the data relevant to its scope. Lower levels process device-specific sensor data, intermediate levels aggregate area-level data, and higher levels handle plant-wide and enterprise-level data. This segmentation reduces the data volume at each processing level while maintaining information completeness through hierarchical aggregation.
Solution Approach 2:
Each hierarchical level processes data with quality and detail appropriate to its level. Lower levels handle high-frequency, high-volume sensor data with fine granularity, while higher levels process aggregated, lower-volume data with broader context. This local quality approach ensures information completeness without overwhelming any single processing level.
3Loss of information
If conventional systems transmit all generated data to higher-level devices for processing, then all operational data is available for analysis, but the transmission and processing burden increases significantly
Solution Approach 1:
The patent extracts and processes data locally at each hierarchical level before transmission to higher levels. Each level extracts only the essential aggregated information needed for its decision-making, leaving detailed raw data processing to the local level. This extraction approach maintains data availability for local optimization while reducing transmission and processing burden at higher levels.
Solution Approach 2:
Data aggregation, filtering, and preliminary analysis are performed in advance at lower hierarchical levels before data reaches higher levels. This preliminary action ensures that higher-level devices receive pre-processed, relevant information rather than raw sensor data, improving operational efficiency while maintaining comprehensive data availability through the hierarchical structure.
4Loss of information
If conventional systems use highly complex metadata models to represent enterprise processes, then the models can capture detailed process relationships, but the models become non-explainable and difficult to interpret
Solution Approach 1:
The patent segments the enterprise process model into hierarchical levels, with each level having its own simplified metadata model focused on its specific scope. Enterprise-level models capture high-level process relationships, while device-level models capture detailed operational relationships. This segmentation maintains process representation accuracy within each level while improving interpretability by limiting model scope and complexity.
Solution Approach 2:
The patent adds a hierarchical dimension to process representation, organizing process models across multiple levels from enterprise-wide to device-specific. This dimensional organization allows accurate process representation through hierarchical aggregation while maintaining interpretability at each level, as users can understand and navigate the process model at the appropriate level of detail rather than being overwhelmed by a single monolithic model.
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.