Wirebond Inspection Using ML to Predict RF Package Performance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The existing semiconductor package manufacturing process involves time-consuming and costly testing for RF performance after wirebond assembly, often requiring rework and additional testing, which can lead to delays and increased costs.
Innovation Solution
A method and system for semiconductor package inspection using machine learning to predict RF performance based on wirebond interconnection features, allowing for real-time evaluation and decision-making during wirebond assembly.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If testing is performed after wirebond assembly to detect RF performance issues, then manufacturing precision is improved, but loss of time and productivity decrease significantly
Solution Approach 1:
The patent applies preliminary action by performing optical inspection and machine learning-based RF performance prediction during the wirebond assembly process itself, rather than after completion. The system captures images of wirebond interconnections in real-time and uses trained neural networks to predict RF performance, enabling quality assessment before the assembly is finalized and eliminating the need for separate post-assembly testing phases.
2Reliability
If comprehensive RF performance testing is conducted after assembly, then reliability is improved, but device complexity and cost increase
Solution Approach 1:
The patent replaces complex physical RF testing equipment and procedures with an optical inspection system coupled with machine learning algorithms. Instead of using sophisticated RF measurement instruments to assess performance, the system uses standard optical imaging combined with neural network analysis to predict RF performance, thereby reducing device complexity while maintaining reliability assessment capability.
3Manufacturing precision
If post-assembly testing is performed to ensure quality, then manufacturing precision is improved, but productivity decreases due to rework requirements
Solution Approach 1:
The system performs self-service quality control by automatically capturing images of wirebond interconnections during assembly, processing them through machine learning models, and providing real-time RF performance predictions. This automated self-assessment eliminates the need for separate manual testing operations and enables immediate detection of defects, allowing defective packages to be identified and removed from the production line without requiring rework or additional testing cycles.
Data Source
AI summary
Methods, systems and devices for use in semiconductor package manufacture of a package having a die and die substrate are provided. A method for use in semiconductor package manufacture includes steps of forming one or more wirebond interconnections between the die and the die substrate, capturing input data representative of wirebond interconnection features during inspection of the formed wirebond interconnections, and passing the captured input data to a machine learning (ML) engine. The method further includes processing the captured input data with the machine learning engine using a trained model to obtain an output array of data, evaluating the output array of data to determine a predicted radio-frequency (RF) performance rating, and outputting the predicted RF performance rating. Training data set processing may include applying image data and parameters to a multi-layer neural network to obtain a set of candidate ML models, and selecting an optimal ML model.