Machine learning for complex EMI prediction, optimization and localization

Jin, Hailin; Zhang, Le; Ma, Hanzhi; Yang, Sichen; Yang, Xiaoli; Li, Er‐Ping

doi:10.1109/edaps.2017.8276967

Cited by 14 publications

(4 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The maximum CM current was found in the portion of the power cable close to the outlet in the wall of the chamber (Fig. (23)f) due to the noisy electronic load placed outside the chamber. A radiated emission full scan was performed, and the results are presented in Fig.…”

Section: B Power Cable Radiation: Conversion Modementioning

confidence: 99%

See 1 more Smart Citation

Prediction of Radiated Emissions From a Fuel Cell Power Converter by Measuring the Common-Mode Current in the Attached Cable

2023

View full text Add to dashboard Cite

Being able to predict radiated emissions before using an accredited laboratory can be both time-effective and cost-effective. This study presents a model for predicting radiated emissions from power converters by measuring the common-mode current in the attached cable. When power converters are tested for radiated emissions, in semi-anechoic chambers, the attached cables tend to be thick because of the high currents they carry. Ideally, these cables leave the chamber through connectors in an opening positioned precisely at the middle of the bottom of the turntable in keeping with CISPR 32. However, the turntable-connectors are typically not intended for currents higher than 16 A. Consequently, such cables are usually inserted through the side wall of the chamber and are therefore laid horizontally on the chamber floor. When the turntable is to be rotated with a device on it during a test, the length of the cable attached to the device can exceed 10 meters. The proposed model in this study is based on the transmission line model of a cable loaded with reactive impedance and the assumption that the current distribution along the cable follows a sinusoidal distribution law, much like in dipole antenna theory. The analytic equation of the radiation pattern is derived, and a simplified approximation equation is also presented. The proposed model also works with short, attached cables and is thus universal. The Maxima software code for automated calculation of the radiated field from measurement data is supplied as supplemental material. The proposed model was experimentally validated by running the fuel cell converter module at 5 kW output power.INDEX TERMS CM current, EMC, EMI prediction, power converters, radiated emissions.

show abstract

Section: B Power Cable Radiation: Conversion Modementioning

confidence: 99%

“…Thus, this method may be expensive and time consuming. A similar approach is used in references [22] and [23] in which deep neural networks were implemented to predict the azimuth position with maximum radiation from a DUT.…”

Section: Introductionmentioning

confidence: 99%

Prediction of Radiated Emissions From a Fuel Cell Power Converter by Measuring the Common-Mode Current in the Attached Cable

2023

View full text Add to dashboard Cite

show abstract

“…One of the areas that is gaining attention is the use of Artificial intelligence (AI) techniques to predict/classify EMI [3], [4], or to address problems in electromagnetic compatibility (EMC) [5]. These techniques include using neural networks to model EMI and predict its impact on electronic systems [6], or using genetic algorithms to optimize electronic device design to improve EMC performance [7].…”

Section: Introductionmentioning

confidence: 99%

Decision Algorithm Based on the Modified Bellman Equation to Deal With EMI-Induced Errors in Hamming-Based Communications

Gonzalez-Atienza

Vanoost

Verbeke

et al. 2023

IEEE Trans. Electromagn. Compat.

View full text Add to dashboard Cite

This paper presents a decision-making algorithm based on a modified version of the Bellman Equation to deal with Electromagnetic Interference errors in a communication channel inside a harsh electromagnetic reverberant environment.The Bellman equation is a fundamental concept in decisionmaking problems such as Markov Decision Processes. Such processes model decision-making in situations where the outcomes are partly random and partly controlled by an agent (decisionmaker).Recent studies have implemented Markov Decision Processes as a tool for risk assessment in areas such as robotics or aviation. However, so far, no research has been reported that uses the Bellman Equation or Markov Decision Processes to deal with risks related to electromagnetic disturbances.In our study, a wired communication channel that uses Non-Return-to-Zero-Level data encoding and Hamming code for error detection and correction is disturbed. First, the packet error rate is calculated and compared with and without the proposed algorithm for different electromagnetic disturbance frequencies and bit rates. The gain is compared at different packet error rates when the algorithm's parameters (called rewards) are optimized and when these are set as random. Last, the influence of the rewards and the maximum number of resends on the algorithm's performance is also studied.

show abstract

“…On the other hand, with the rapid development of artificial intelligence, neural network modelling methods have been applied in many fields [1–5], greatly improving computational efficiency. In [4], a deep convolutional neural network is trained to predict the electric potential with different excitations and permittivity distribution in 2D and 3D models.…”

Section: Introductionmentioning

confidence: 99%

Fast multi‐physics simulation approach in underwater exploration via deep learning technique

Zhu

Zhou

Javaid

et al. 2021

Electronics Letters

View full text Add to dashboard Cite

When underwater pressure wave is generated, moving water particles cut off the geomagnetic field and produce induced currents, which will simultaneously induce electromagnetic field in the whole space. Due to the large distribution range and slow attenuation of this pseudo‐radiation, it is possible to observe above the sea surface. In this work, we introduce a novel long‐ and short‐term memory neural network and the corresponding training algorithm, to model the multi‐physics process instead of solving magneto‐hydrodynamics equations via numerical methods. Compared with commercial software, the proposed approach is much faster and easier to apply, which puts forward a feasible alternative for predicting the electromagnetic field distribution excited by underwater pressure wave.

show abstract

Machine learning for complex EMI prediction, optimization and localization

Cited by 14 publications

References 13 publications

Prediction of Radiated Emissions From a Fuel Cell Power Converter by Measuring the Common-Mode Current in the Attached Cable

Prediction of Radiated Emissions From a Fuel Cell Power Converter by Measuring the Common-Mode Current in the Attached Cable

Decision Algorithm Based on the Modified Bellman Equation to Deal With EMI-Induced Errors in Hamming-Based Communications

Fast multi‐physics simulation approach in underwater exploration via deep learning technique

Contact Info

Product

Resources

About