Neural Network DRC Error Classification for Design Reliability
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The process of performing a design rule check (DRC) on electronic device designs is overwhelmed by numerous errors, leading to increased design time and potential overlooking of critical errors, as it is challenging to determine which errors to ignore or address during the early stages of the design process.
Innovation Solution
A neural network is used to classify DRC errors based on whether they should be ignored, taking into account the design rule and component information from the DRC result, producing a final report that indicates which errors require attention, and allowing for updates and retraining based on feedback to improve accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual evaluation of all DRC errors is performed, then design reliability is improved, but design time and complexity increase significantly
Solution Approach 1:
An automated classification system acts as an intermediary between DRC error generation and manual review, filtering errors by priority and type to guide designer attention to critical issues while automatically handling routine classifications
Solution Approach 2:
The manual mechanical process of reviewing all DRC errors is replaced with an automated electronic classification system that uses algorithms to categorize and prioritize errors, significantly reducing the time required while maintaining reliability
2Manufacturing precision
If all DRC errors are addressed, then manufacturing precision is improved, but design complexity and resource expenditure increase
Solution Approach 1:
Different classification rules and evaluation criteria are applied to different types of DRC errors based on their location, type, and potential impact on manufacturing, allowing targeted attention to critical errors while tolerating minor violations
3Reliability
If comprehensive DRC error analysis is performed, then design quality is improved, but the process becomes overwhelming and errors may be overlooked
Solution Approach 1:
The comprehensive DRC error analysis process is segmented into automated classification stages and manual review stages, with clear demarcation of which errors require human attention and which can be automatically handled, making the overall process more manageable
Data Source
AI summary
A process for performing a design rule check (DRC) by a computer may comprise receiving a DRC result comprising a plurality of DRC errors, the DRC result corresponding to a DRC deck comprising a plurality of rules and a design layout database comprising a plurality of components; classifying, using a neural network, each of the plurality of DRC errors according to whether that DRC should be ignored; and producing a final report including a plurality of respective indications of whether the plurality of DRC errors should be ignored. Performing the process may further include the receiving mistake feedback regarding the final report; updating, using the mistake feedback, a DRC result dataset comprising a plurality of dataset entries; and re-training the neural network using the updated DRC result dataset.