Production Intent Validation Using a Protected Safety Library
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Intent-based production processes face challenges in detecting harmful intent, which can lead to accidents or malicious actions compromising functional safety and productivity, as they rely on automated reconfiguration without adequate security measures.
Innovation Solution
A method involving a machine-readable production model linking intent and process models, with a safety library protected by security mechanisms, validates process intent using key performance indicators and safety rules, evaluates changes for potentially harmful intent, and provides a report for auditing, ensuring adjustments are made only if approved by experts.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If intent-based automated reconfiguration is implemented, then productivity and efficiency are improved, but vulnerability to harmful intent and functional safety risks increase
Solution Approach 1:
The system segments the intent-based production process into distinct components: a production model with intent model and process model, a separate safety library with safety process intents, and an evaluation mechanism. This segmentation allows the safety functions to be independently validated and protected from harmful intent while maintaining productivity benefits of automated reconfiguration.
Solution Approach 2:
The safety library is determined in advance and protected by security mechanisms before regular intent-based engineering mechanisms operate. Changes to process intent are pre-evaluated against the safety library to detect potentially harmful intent before implementation, preventing safety incidents while allowing productive automation.
2Reliability
If security mechanisms are added to protect against harmful intent, then functional safety is improved, but device complexity increases
Solution Approach 1:
The safety library acts as an intermediary layer between the intent model and the production process execution. It provides a standardized set of safety process intents that mediate between automated reconfiguration requests and actual process changes, simplifying the security architecture by using a centralized reference rather than distributed complex validation logic.
Solution Approach 2:
The system changes the parameter of process intent by evaluating it against the safety library and detecting potentially harmful intent. This parameter transformation converts raw intent changes into validated, safety-checked intent configurations, enabling automated security verification without requiring complex real-time monitoring systems.
3Reliability
If manual auditing of process intent changes is required, then detection of harmful intent is improved, but productivity decreases
Solution Approach 1:
The system applies partial manual action by requiring expert auditing only for changes that are potentially harmful according to the safety library evaluation. Routine changes that pass safety checks can proceed through automated mechanisms, while only suspicious changes require manual review, balancing detection capability with productivity preservation.
Solution Approach 2:
The evaluation of changes against the safety library provides feedback on whether process intent modifications are potentially harmful. This feedback mechanism guides the auditing process by highlighting only those changes that require expert review, enabling efficient targeted manual verification rather than blanket manual approval for all changes.
Data Source
Figure 1~2
AI summary
Method for detection of harmful process intent in an intent-based production process, comprising the steps: providing (S10) a machine-readable production model (M) linking an intent model (I), correlating to process intent (Ip), comprising production process functions, constraints on measurable properties on the production process functions and/or production process function sequences required for the production process, and a process model (P), correlating to process knowledge comprising a production process behaviour; determining (S20) a safety library (L) of at least one safety process intent (Is), wherein the safety library (L) is protected by security mechanisms to be maintained outside of regular intent-based engineering mechanisms and operation mechanisms; evaluating (S30) changes of process intent (Ip) in view of potentially harmful process intent (Ih) dependent on the at least one safety process intent (Is); and providing (S40) a report of potentially harmful process intent (Ih) for auditing based on the potentially harmful process intent (Ih).