Machine learning program, method and device for estimating the electromagnetic wave radiation situation of an electronic circuit
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods struggle to accurately estimate the electromagnetic wave radiation situation, particularly the near field, due to the complexity of elements like inductors, capacitors, and resistors, which affects the accuracy of far field estimation.
Innovation Solution
A machine learning approach that identifies the resonance frequency and spatial distribution of current in an electronic circuit, using a training dataset to generate a model that estimates electromagnetic wave radiation by inputting resonance frequency and current distribution data into a deep learning model.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If machine learning estimation is performed using conventional methods, then the estimation process can be automated, but the accuracy of near field approximation deteriorates when LCR element values are small
Solution Approach 1:
The patent changes the input parameters from conventional geometric parameters to resonance frequency and current spatial distribution. This transformation allows the machine learning model to capture the essential electromagnetic characteristics of the circuit regardless of LCR element values, resolving the accuracy deterioration when element values are small while maintaining automation.
2Ease of manufacture
If the circuit is approximated as two lines cut at the LCR element, then the near field can be estimated based on total line length, but the approximation becomes inaccurate when reflection is small
Solution Approach 1:
The patent replaces the mechanical/geometric approximation method (treating circuits as simple lines based on length) with an electromagnetic field-based approach using resonance frequency and current distribution. This substitution maintains computational simplicity while dramatically improving accuracy across all LCR element value ranges.
3Productivity
If conventional machine learning models are used for EMI estimation, then the far field can be predicted, but the near field complexity from various LCR elements cannot be accurately captured
Solution Approach 1:
The patent performs preliminary calculation of resonance frequency and current spatial distribution before feeding data to the machine learning model. This preliminary action extracts the essential electromagnetic characteristics that capture near field complexity, enabling the model to accurately predict far field EMI while accounting for near field effects.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A machine learning estimation program causes a computer to execute a process, the process comprising identifying, for an electronic circuit to be analyzed, a resonance frequency of a current and a spatial distribution of the current that flows through the electronic circuit to be analyzed at the resonance frequency, generating a machine learning model using a training data set in which arrangements of circuit elements in respective electronic circuits differ from each other, the training data set being a set of training data in each of which a specific value of a resonance frequency for a specific electronic circuit and information of a spatial distribution of a current that flows through the specific electronic circuit at the resonance frequency of the specific value are used as input data and an electromagnetic wave radiation situation of the specific electronic circuit is set as a label, inputting, as input data, a frequency value of the identified resonance frequency and information of the identified spatial distribution to the generated machine learning model, and estimating an electromagnetic wave radiation situation of the electronic circuit to be analyzed, based on an output from the machine learning model according to the inputting.