RELIABILITY ASSESSMENT OF AN ELECTRONIC COMPONENT CARRIER OR A PACKAGE COMPRISING IT USING AI-SUPPORTED FINITE ELEMENT ANALYSIS

A method for a reliability assessment of an electronic component carrier or a package comprising an electronic component carrier (1). The method comprises: providing a global simulation model of the component carrier or package (1), wherein a predetermined number of geometric properties of the compo...

Full description

Saved in:
Bibliographic Details
Main Authors Krivec, Thomas, Zuendel, Julia, Tao, Qi
Format Patent
LanguageEnglish
French
German
Published 24.04.2024
Subjects
Online AccessGet full text

Cover

Loading…
More Information
Summary:A method for a reliability assessment of an electronic component carrier or a package comprising an electronic component carrier (1). The method comprises: providing a global simulation model of the component carrier or package (1), wherein a predetermined number of geometric properties of the component carrier or package (1) and of its constituent parts made of different materials and of physical properties of materials used in said constituent parts are defined as independent variables in a parameter space of the global simulation model; and wherein the global simulation model is configured to receive input data including a point in the parameter space and is configured to output data indicative of resulting geometric and/or physical properties within a global volume of the resulting component carrier or package (1). The method comprises running a simulation of the global simulation model and identifying, in its output data, boundary conditions for a plurality of local sub-portions (2) of the component carrier or package (1). The method further comprises providing at least one data-based local model for said local sub-portions (2), each data-based local model being trained to receive said boundary conditions as input data and provide a criticality value indicative of a reliability of the respective local sub-portion (2) as output data; running the at least one local data-based model for each of said local sub-portions (2) and identifying, in the respective output data, those local sub-portions (2) whose criticality value is above at least one predetermined threshold.
Bibliography:Application Number: EP20220201845