Back to results
US 2022/0016847 A1Published application
Material phase detection
AssigneeHewlett-Packard Development Company, L.P.
InventorsHe Luan, Jun Zeng
Life of this patent
Estimating the term…
Abstract
Examples of methods for detecting a material phase are described herein. In some examples, a kernel is predicted based on an input corresponding to an object and based on a machine learning model. In some examples, the machine learning model is constrained with a physical model. In some examples, a material phase is detected based on the kernel.
Claims15
A method, comprising:
- predicting a kernel based on an input corresponding to an object and based on a machine learning model that is constrained with a physical model;
- and
- detecting a material phase based on the kernel.
A three-dimensional (3D) printing device, comprising:
- a print head;
- a thermal projector;
- a thermal sensor to capture a thermal image;
- and
- a controller, wherein the controller is to:
- produce a kernel based on a portion of the thermal image;
- and
- determine a phase condition score based on the kernel.
5 more elements
A non-transitory tangible computer-readable medium storing executable code, comprising:
- code to cause a processor to determine a kernel matrix based on an input;
- and
- code to cause the processor to calculate a statistic metric of parameters of the kernel matrix to determine a material phase.
Dependencies are inferred from the claim text.