Intent-Based Automation Modeling for Vendor-Independent Process Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current automation engineering processes fail to effectively capture and utilize the expert knowledge of chemical or process engineers, leading to inefficiencies and increased costs due to lost information, particularly in the operational phase of production, where optimization is necessary for product quality, throughput, and energy consumption, and existing control strategies are not adaptable across different automation systems.
Innovation Solution
An intent-based automation engineering method that uses an intent-language to formulate quantifiable expectations on production process behavior, linking process intent and knowledge through a process model, which abstracts complex process knowledge into a medium complexity model for resource-efficient control strategies, and automatically generates engineering data and alarm systems to improve production process control.
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 operational optimization cannot be performed
Solution Approach 1:
The system performs preliminary capture and formalization of expert knowledge during the engineering phase through intent-based specifications. Process experts define their knowledge and intent in a formal language before operation begins, creating a knowledge base that will be used for operational optimization. This prevents knowledge loss by capturing it in advance rather than trying to retrieve it during operations.
Solution Approach 2:
The patent introduces an intent-based formal language and process model as an intermediary between expert knowledge and automation control. This intermediary translates informal expert knowledge into structured representations that can be processed by control systems, enabling operational optimization without requiring experts to be directly involved in real-time operations.
2Productivity
If process optimization is implemented during operational phase, then production efficiency improves, but it requires expert knowledge that was lost during engineering
Solution Approach 1:
The system captures and formalizes expert knowledge during the engineering phase before operation begins. Process experts define their knowledge, constraints, and optimization goals in a formal intent-based language, creating a reusable knowledge base that enables operational optimization without requiring knowledge to be rediscovered during operations.
Solution Approach 2:
The system establishes feedback loops where operational data is continuously compared against the formalized expert knowledge and intent specifications. This feedback mechanism enables automatic detection of optimization opportunities and triggers appropriate control actions, allowing continuous improvement while maintaining alignment with expert intent.
3Ease of manufacture
If vendor-specific automation tools are used, then device configuration is simplified, but the engineering process becomes tied to particular vendor portfolios and technologies
Solution Approach 1:
The patent introduces a vendor-independent intent-based formal language and process model that can represent automation requirements universally. This universal representation layer sits above vendor-specific tools, allowing the same expert knowledge to be used across different vendor portfolios and technology platforms without being locked into a single ecosystem.
Solution Approach 2:
The intent-based formal specification serves as an intermediary between vendor-independent expert knowledge and vendor-specific implementation tools. This intermediary enables translation of universal process intent into various vendor-specific configurations, maintaining adaptability while leveraging the ease of use of proprietary tools.
4Measurement precision
If alarm systems provide detailed process information, then operators can monitor KPIs, but alarm floods occur that diminish operator ability to react
Solution Approach 1:
The system extracts and separates critical alarm information from the general process data stream based on the formalized expert knowledge. Alarms are selectively generated only when process deviations match patterns defined in the intent specifications, filtering out non-critical information and presenting only the most relevant alerts to operators.
Solution Approach 2:
The patent introduces an intelligent alarm management layer that acts as an intermediary between raw process data and operator alerts. This layer uses the formalized process model to interpret sensor data, determine significance based on expert knowledge, and generate meaningful alarm messages with suggested actions, reducing alarm floods while maintaining monitoring precision.
Data Source
Figure 1~2
Figure 3
AI summary
The present invention is concerned with an intent-based automation engineering method for automation of a production process, comprising the steps: receiving an intent model (I), correlating to process intent, comprising production process functions, constraints on measurable properties on the production process functions and/or production process function sequences required for the production process; receiving a process model (P), correlating to process knowledge comprising a production process behaviour; determining a machine-readable production model (M) linking the received intent model (I) to the received process model (P); and determining a control strategy (S) for controlling the production process dependent on the provided production model (M).