ACS EASY™: ACS Engineering AI Studio for Yield Improvement
AI-powered, user-friendly software solution
Advantest's ACS EASY™ is a unique AI-powered, user-friendly software solution that automates the analysis of yield issues, reducing engineers' workloads and speeding correction turnaround time.
Device yields are key performance indicators in semiconductor production, requiring continuous engineering efforts to debug and fine-tune.
The "ACS Engineering AI Studio for Yield Improvement" - ACS EASY™ - is offering a new low-cost yield-improvement solution that leverages Artificial Intelligence (AI) to expedite identifying the root causes of yield loss and increase the efficiency of analyzing test results.
Test conditions and inferences are automatically monitored using AI to isolate and analyze the causes of yield degradation. This resolves production issues quickly, slashes troubleshooting time, and dramatically reduces test workloads for data analytics.
Our proprietary machine learning algorithm expedites and complements human judgment, based on experience, and can categorize any new yield-related issues for future monitoring and analysis. These machine learning capabilities extend the system’s stored knowledge base, allowing inferencing applications to present bigger values.
ACS EASY™ is capable of handling vast volumes of data to compare new lots' test results with previous lots to identify abnormal bin trends quickly. The solution's GUI facilitates the online sharing of test results, eliminating the need to create separate reports.
ACS EASY™ accommodates a wide range of users, from chip designers to outsourced semiconductor assembly and test (OSAT) companies. It represents a low-cost system that is simple to install and easy to use. ACS EASY™ does not require users to have familiarity with AI, machine learning, data analysis, or statistics. It enables test engineers to master data management without being data scientists.
Advantest's latest innovation provides a solution that can dramatically increase the productivity of both device engineering and production operations.
- High speed data integration from standard test data format (STDF) and databases.
- Machine learning features including reason isolation and wafer pattern analysis.
- HTML-based graphical user interface including basic data visualization, i.e., wafer maps, histogram of measurements, etc.
- Server front-end model architecture which enables seamless team collaboration.
- APIs to allow simple integration with other programs.
- Provided as web-based application on containerization technology which enables easy installation.
- Low-cost yield-improvement solution.
- Identifying the root causes of yield loss.
- Increase the efficiency of analyzing test results.
- Capability of handling huge volumes, learn and identify abnormal bin trends.
- Easy installment and intuitive user interface.