USPTO Patent US12583122B2: Automated cavity filter tuning using machine learning

ChangeBridge: Patent Grants - AI & Computing (G06N)

Published March 24th, 2026

Detected March 24th, 2026

Summary

The USPTO has granted patent US12583122B2 to Tektronix, Inc. for an automated cavity filter tuning system utilizing machine learning. The patent describes a method for optimizing tuning screws on devices under test using robotic control and AI-driven parameter prediction.

View original document View source feed page

What changed

The United States Patent and Trademark Office (USPTO) has granted patent US12583122B2 to Tektronix, Inc. This patent covers an automated system for tuning cavity filters, which are critical components in electronic devices. The system employs machine learning to command a robot to adjust tuning screws on devices under test (DUTs), acquire operating parameters, generate images of these parameters, and use a machine learning system to predict optimal screw positions. The goal is to achieve tuned operating parameters and validate DUT operation.

This patent grant is primarily an intellectual property event and does not impose direct compliance obligations on regulated entities. However, it signifies innovation in the field of automated testing and manufacturing, potentially impacting companies involved in the design, manufacturing, or testing of electronic components and systems. Companies in the electronics manufacturing and test equipment sectors may need to be aware of this patented technology to avoid potential infringement issues.

Source document (simplified)

← USPTO Patent Grants

Automated cavity filter tuning using machine learning

Grant US12583122B2 Kind: B2 Mar 24, 2026

Assignee

Tektronix, Inc.

Inventors

John J. Pickerd, Ajaiey Kumar Sharma, Kan Tan

Abstract

A test and measurement instrument connects to one or more devices under test (DUT) having tuning screws, and to a robot, and has one or more processors to: command the robot to position the tuning screws on the DUTs to one or more sets of positions, each set of positions being a parameter set for the tuning screws, acquire a set of operating parameters for each parameter set from the DUTs, generate a parameter set image for each set, create a combined image of the parameter set images, provide the combined image to a machine learning system to obtain a predicted set of values, adjust the predicted set of values to produce a set of predicted positions, command the robot to position the tuning screws to positions in the set of predicted positions, obtain a set of tuned operating parameters from the DUTs, and validate operation of the DUTs.

CPC Classifications

B25J 9/1697 G06T 7/70 G06T 11/001 G06T 11/206 G06T 2207/10024 G06T 2207/20081 G06T 2207/20084 G06T 2207/20212 G06T 2207/30108 G06N 3/096 G01R 27/32 H04B 17/0085 H04W 24/06