Model-Based Production Control Integrating Diagnostics
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional production system diagnostics are ineffective in providing adequate diagnostic information without halting production and incurring significant costs, especially when dealing with limited sensor deployment and recurring intermittent system component failures.
Innovation Solution
A model-based production control system that includes a planner and a diagnosis engine, which constructs plans to achieve production goals while incorporating diagnostic objectives and expected information gain data, allowing for online pervasive diagnostics that integrate production and diagnostic objectives without requiring complete sensor coverage.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If dedicated diagnostic operation is performed to obtain better diagnostic information, then measurement precision is improved, but productivity decreases due to system downtime
Solution Approach 1:
The system performs preliminary diagnostic actions by incorporating diagnostic objectives into production plan construction. The planner generates plans that simultaneously achieve production goals and gather diagnostic information about suspected faulty resources, eliminating the need for separate diagnostic operations that would halt production.
Solution Approach 2:
The invention merges production operations with diagnostic operations into a unified plan execution process. The diagnosis engine and planner work together to construct plans that achieve both production objectives and diagnostic objectives simultaneously, allowing the system to gather diagnostic information during normal production without downtime.
2Productivity
If passive diagnostics are used to avoid system downtime, then productivity is maintained, but diagnostic information quality is insufficient
Solution Approach 1:
The system dynamically adjusts plan construction based on diagnostic needs. When faults are detected or suspected, the planner modifies production plans to include diagnostic actions that actively exercise the suspected faulty resources, transforming passive observation into active diagnostic gathering while maintaining production continuity.
Solution Approach 2:
The diagnosis engine continuously monitors system performance and provides feedback to the planner about suspected faulty resources. This feedback loop enables the system to adaptively construct plans that target specific diagnostic objectives based on real-time system conditions, improving diagnostic information quality during ongoing production.
3Measurement precision
If complete sensor coverage is deployed to capture all system faults, then measurement precision is improved, but device complexity and cost increase
Solution Approach 1:
The system introduces an intermediary diagnostic layer consisting of the diagnosis engine and planner that processes limited sensor readings and infers the state of unmonitored resources. This intermediary layer enables comprehensive fault detection capabilities without requiring physical sensors at every possible fault location, reducing device complexity while maintaining diagnostic precision.
Data Source
AI summary
Model-based production control systems and methods are presented for constructing plans for controlling operation of a production system with a plant having a plurality of resources to achieve one or more production goals, in which a planner constructs plans for execution in the plant based on production goals while balancing both production objectives (e.g., production cost, production time) and diagnostic objectives (e.g., diagnostic cost, information gained, repair cost), and a diagnosis engine determines a current plant condition based on a previously executed plan and corresponding observations from the plant, and provides expected information gain data to the planner, with the planner generating a plan that will achieve a given production goal and is improved for one or more diagnostic objectives and the expected information gain data.