Hierarchical AI Configuration for Industrial 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 across automated processes, leading to inefficiencies and unachievable objectives.
Innovation Solution
The system employs on-board intelligence in devices to monitor and control equipment in real-time, using a configuration component to construct graphical representations of industrial processes, an AI component to adjust models based on output data, and smart devices to process and transmit relevant data, thereby optimizing operations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If conventional enterprise systems use complex mathematical programming and metadata models to optimize operations, then the system can handle enterprise-wide optimization requirements, but the system complexity and difficulty of implementation increase significantly
Solution Approach 1:
The patent segments the enterprise system into multiple hierarchical levels (enterprise level, plant level, area level, device level), with each level handling optimization independently through simplified models. This divides the complex enterprise-wide optimization problem into manageable sub-problems that can be solved with less computational complexity at each level.
Solution Approach 2:
The patent introduces simplified intermediate models and data representations that act as mediators between complex enterprise requirements and device-level operations. These intermediate representations translate complex optimization objectives into simpler, actionable parameters for individual devices and processes.
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 distributes data processing responsibilities across multiple hierarchical levels, with lower-level devices performing initial data filtering and preprocessing. This segmentation reduces the volume of raw data that must be processed by higher-level devices, while maintaining comprehensive monitoring through coordinated processing at all levels.
Solution Approach 2:
The patent implements preliminary data processing and filtering at device and area levels before data reaches higher-level systems. This preliminary action reduces the data burden on enterprise and plant level systems, allowing them to focus on strategic optimization rather than raw data processing.
3Loss of information
If conventional systems transmit all generated data to higher-level devices for processing, then complete data availability is achieved, but data transmission and processing overhead increases
Solution Approach 1:
The patent applies local quality by allowing different data processing strategies at different hierarchical levels and for different types of data. Critical real-time data is processed locally with high priority, while less time-sensitive data is aggregated and processed at higher levels, optimizing both data completeness and processing efficiency.
Solution Approach 2:
The patent implements partial data transmission where only relevant and necessary data is transmitted to higher levels, rather than all generated data. This selective transmission maintains sufficient data completeness for optimization decisions while significantly reducing transmission and processing overhead.
4Adaptability or versatility
If conventional enterprise systems use highly complex metadata models, then the system can represent diverse enterprise processes, but the models become non-explainable and difficult to interpret
Solution Approach 1:
The patent segments complex metadata models into hierarchical layers with standardized, interpretable representations at each level. This segmentation maintains the ability to represent diverse processes while ensuring that each layer uses explainable, domain-specific terminology and structures that can be understood by operators and engineers.
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.