Loading...
News Article

ASMPT expands SMT analytics with AI-driven line balance and yield analysis

News

ASMPT SMT Solutions has expanded the analytics capabilities of its SMT Analytics software, introducing new tools aimed at improving line utilisation, throughput, and yield in complex electronics and advanced manufacturing environments.

A key addition is Line Balance Analysis, which enables station-level evaluation of cycle times across entire SMT lines.

By comparing actual performance against reference values generated by ASMPT’s WORKS Programming software, manufacturers can quickly identify bottlenecks, imbalanced processes, and throughput-limiting steps at the line level.

Existing analytics functions have also been enhanced. The Theoretical Cycle Time Comparison now provides deeper insight into deviations caused by programming parameters such as waiting times and acceleration settings, highlighting optimisation opportunities that can have a significant impact across high-volume placement cycles.

Meanwhile, Reject Analysis has been expanded to include cost-based evaluations, allowing manufacturers to better quantify the financial impact of yield losses.

Through integration with ASMPT’s Factory Equipment Centre, maintenance-related data, including feeder status, cycle counts, and service intervals, can now be incorporated directly into analytics workflows, supporting more informed production and maintenance decisions.

The latest release also introduces AI-supported reporting, with an integrated assistant that automatically analyses production data and delivers prioritised recommendations to improve performance, component efficiency, and equipment availability.

In addition, SMT Analytics now supports the integration of third-party equipment via the IPC-2591 Connected Factory Exchange (CFX) standard, enabling consistent analysis across heterogeneous production lines.

ASMPT says the enhanced platform is designed to support data-driven optimisation in increasingly complex manufacturing environments, including high-mix and high-value production scenarios.