Intent-Based Automation Engineering for Production Control Strategy
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current automation engineering processes struggle to capture and utilize the expert knowledge of chemical or process engineers, leading to inefficiencies and suboptimal production processes. This results in issues such as lost information, inefficient optimization, and increased costs due to alarm floods and inadequate sensor planning.
Innovation Solution
An intent-based automation engineering method that receives an intent model representing process intent and a process model representing process knowledge, and determines a machine-readable production model linking these two. This model is used to develop a control strategy for the production process, optimizing it based on key performance indicators.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If traditional automation engineering processes are used to control production processes, then equipment-level control is achieved, but expert knowledge is lost and production optimization is delayed
Solution Approach 1:
The system performs preliminary capture and integration of expert knowledge from process engineers during the design phase, storing it in a knowledge base before operational issues arise. This allows the system to have optimization capabilities ready in advance rather than waiting for problems to occur during operation.
Solution Approach 2:
The patent introduces an intermediary layer (the knowledge integration system) that bridges process engineers and automation engineers. This intermediary captures expert knowledge, translates it into formal representations, and integrates it with automation systems, preventing knowledge loss between these two groups.
2Productivity
If iterative optimization is performed after plant start-up, then production efficiency is improved, but costs increase due to alarm floods and case-by-case problem solving
Solution Approach 1:
The system performs optimization preparations in advance by integrating expert knowledge and defining control strategies during the engineering phase. This preliminary optimization reduces the need for costly iterative adjustments and alarm management during operation, as the system is already configured for efficient production.
Solution Approach 2:
The patent implements feedback mechanisms where the system continuously monitors production processes and automatically adjusts operations based on integrated expert knowledge. This closed-loop control reduces the need for manual intervention and case-by-case problem solving, thereby lowering operational costs while maintaining high productivity.
3Loss of information
If sensors are added during operational phase for optimization, then process information is improved, but economic feasibility decreases
Solution Approach 1:
The system performs sensor planning and information requirements analysis during the design phase, identifying exactly what process information is needed for optimization. This preliminary planning ensures that sensors are specified and integrated cost-effectively from the beginning, avoiding the need to add sensors during operation when it becomes economically less feasible.
4Reliability
If alarm systems are implemented to monitor KPI-critical conditions, then operational awareness is improved, but alarm floods occur reducing operator effectiveness
Solution Approach 1:
The patent extracts and separates critical information from the general alarm stream by using integrated expert knowledge to identify and highlight only the most relevant KPI-critical conditions. This extraction process filters out non-essential alarms, reducing alarm floods while maintaining operational awareness of truly critical situations.
Solution Approach 2:
The system introduces an intermediary intelligence layer that processes alarm information using integrated expert knowledge before presenting it to operators. This intermediary filters, prioritizes, and contextualizes alarms, transforming raw alarm data into actionable insights that improve operator effectiveness rather than overwhelming them.
Data Source
AI summary
An intent-based automation engineering method for automation of a production process includes: receiving an intent model, correlating to process intent, including production process functions, constraints on measurable properties on the production process functions, and/or production process function sequences required for the production process, as a received intent model; receiving a process model, correlating to process knowledge including a production process behavior, as a received process model; determining a machine-readable production model linking the received intent model to the received process model as a provided production model; and determining a control strategy for controlling the production process dependent on the provided production model as a determined control strategy.