Nitride LED Light Output Prediction Using Growth Temperature
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The long time required to produce finished nitride semiconductor light-emitting elements due to the need for chip cutting and packaging after film deposition, and the difficulty in predicting light output due to the large number of parameters involved, makes it challenging to revise designs and evaluate prototypes efficiently.
Innovation Solution
A method and device that create a trained model using correlations between composition, physical property, and manufacturing condition parameters to predict light output, specifically incorporating growth temperature as a manufacturing condition parameter, allowing for accurate prediction without extensive prototyping.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If traditional prototyping and evaluation processes are used for nitride semiconductor light-emitting elements, then design revisions can be made, but it takes a very long time due to chip cutting and packaging requirements
Solution Approach 1:
The patent applies preliminary action by performing light output prediction through machine learning before actual chip fabrication and packaging. The system predicts light output characteristics based on film deposition parameters and layer structure data, allowing design evaluation to occur in advance. This enables design revisions to be made based on predicted performance without waiting for the complete manufacturing cycle, thus reducing development time while maintaining design adaptability
Solution Approach 2:
The patent creates a virtual model (copy) of the light-emitting element's light output characteristics using machine learning. Instead of physically manufacturing chips to evaluate performance, the system generates predictive data that replicates expected light output based on input parameters. This virtual copying allows rapid design iteration without the time-consuming physical prototyping process
2Loss of time
If light output prediction is attempted before prototyping, then development time can be reduced, but it is unclear what parameters should be used due to the large number of parameters involved
Solution Approach 1:
The patent extracts and identifies the specific parameters that have the greatest influence on light output characteristics from the large set of available parameters. The machine learning system analyzes which film deposition parameters and layer structure parameters most significantly affect light output, and focuses the prediction model on these key parameters. This extraction process simplifies parameter management by distinguishing between critical parameters that require precise control and less influential parameters
Solution Approach 2:
The patent applies parameter changes by using machine learning to automatically determine the optimal set of parameters for prediction based on training data. The system learns which parameter combinations yield the most accurate light output predictions and adjusts the parameter selection accordingly. This dynamic parameter optimization reduces the complexity of manual parameter selection while improving prediction accuracy
Data Source
AI summary
A light output prediction method for nitride semiconductor light-emitting element that is a method for predicting light output of a nitride semiconductor light-emitting element, the method including a model creation step of creating a trained model by learning at least a correlation of at least one of a composition parameter or a physical property parameter of a layer constituting the nitride semiconductor light-emitting element and a manufacturing condition parameter, relative to light output of the nitride semiconductor light-emitting element; and a light output prediction step of predicting light output using the trained model. In the model creation step, at least one of the composition parameter or the physical property parameter of a predetermined layer of the nitride semiconductor light-emitting element is used for the learning, and a growth temperature of the predetermined layer is used as the manufacturing condition parameter for the learning.