A Novel Method for Intelligent EMC Management Using a “Knowledge Base”

Management of electromagnetic compatibility (EMC) is a key aspect of product manufacturing. The fierce industry competition and numerous regulations (guidelines) make EMC architects, engineers, and manufacturers increasingly anxious to apply EMC management in each phase (design, validation, development, production, deployment, and monitoring) by depending mainly on their experience. To organize the knowledge, regulations, and implementations of EMC management, this study introduces a new knowledge base with a collection of entities, their properties, and a rich set of relationships among them. Then, a machine learning-based framework for EMC management automation and intelligence is proposed. Convolutional neural network is applied to establish and classify the entities, and the knowledge-based question-answering approach is used for question answering. Finally, the EMC management plan is generated automatically. Two experiments were designed to evaluate the proposed method, and results show that both good recall and precision are achieved in the comprehensive EMC management scenarios. This method is useful for the practical EMC management of industrial products and can enhance product quality, shorten the production cycle, and reduce production cost.

[1]  Zhiyuan Liu,et al.  Learning Entity and Relation Embeddings for Knowledge Graph Completion , 2015, AAAI.

[2]  Keith Armstrong.  Cost-effective Risk Management of EMC without special EMC design expertise or testing , 2013, 2013 IEEE International Symposium on Electromagnetic Compatibility.

[3]  E. Garcia.  Electromagnetic Compatibility Uncertainty, Risk, and Margin Management , 2010, IEEE Transactions on Electromagnetic Compatibility.

[4]  Victor C. M. Leung,et al.  Deep-Reinforcement-Learning-Based Optimization for Cache-Enabled Opportunistic Interference Alignment Wireless Networks , 2017, IEEE Transactions on Vehicular Technology.

[5]  Zhang Yujie,et al.  Electromagnetic compatibility (EMC) management challenges on Tuas West Extension (TWE) project , 2016, 2016 Asia-Pacific International Symposium on Electromagnetic Compatibility (APEMC).

[6]  Lionel Pichon,et al.  The Use of Equivalent Model and Numerical Simulation for EMC Analysis in Hospital Environments , 2016, IEEE Transactions on Electromagnetic Compatibility.

[7]  Lei Huang,et al.  A multiclass classification method based on deep learning for named entity recognition in electronic medical records , 2016, 2016 New York Scientific Data Summit (NYSDS).

[8]  Philipp Cimiano,et al.  Corpus-based Pattern Induction for a Knowledge-based Question Answering Approach , 2007, International Conference on Semantic Computing (ICSC 2007).

[9]  Nicola Fanizzi,et al.  Scalable Learning of Entity and Predicate Embeddings for Knowledge Graph Completion , 2015, 2015 IEEE 14th International Conference on Machine Learning and Applications (ICMLA).

[10]  Ming-Wei Chang,et al.  Semantic Parsing via Staged Query Graph Generation: Question Answering with Knowledge Base , 2015, ACL.

[11]  Tao Hu,et al.  The design method of the radiation source parameter-database based on C/S structure , 2016, 2016 11th International Symposium on Antennas, Propagation and EM Theory (ISAPE).

[12]  Satoshi Sekine,et al.  A survey of named entity recognition and classification , 2007 .

[13]  Jaehoon Choi,et al.  Optimization of EMC management plan for BOP(Balance of Plant) of fuel cell electric vehicle(FCEV) , 2010, 2010 Asia-Pacific International Symposium on Electromagnetic Compatibility.

[14]  M. Mishra,et al.  Leveraging knowledge based question answer technology to address user-interactive short domain question in natural language , 2012, 2012 2nd National Conference on Computational Intelligence and Signal Processing (CISP).

[15]  Mark Steedman,et al.  Large-scale Semantic Parsing without Question-Answer Pairs , 2014, TACL.

[16]  Jason Weston,et al.  Question Answering with Subgraph Embeddings , 2014, EMNLP.

[17]  Shihong Du,et al.  Spectral–Spatial Feature Extraction for Hyperspectral Image Classification: A Dimension Reduction and Deep Learning Approach , 2016, IEEE Transactions on Geoscience and Remote Sensing.

[18]  A. Jackson,et al.  EMC Design Feedback and Analysis Data Management Program , 1983, 1983 IEEE International Symposium on Electromagnetic Compatibility.

[19]  Xianpei Han,et al.  A Generative Entity-Mention Model for Linking Entities with Knowledge Base , 2011, ACL.

[20]  J. Ross Heverly,et al.  Improved EMC Management , 1975, 1975 IEEE International Symposium on Electromagnetic Compatibility.

[21]  Erik F. Tjong Kim Sang,et al.  Introduction to the CoNLL-2003 Shared Task: Language-Independent Named Entity Recognition , 2003, CoNLL.

[22]  Ralph Grishman,et al.  Exploiting Diverse Knowledge Sources via Maximum Entropy in Named Entity Recognition , 1998, VLC@COLING/ACL.

[23]  Q. Balzano,et al.  Electromagnetic compatibility management of wireless transceivers in electromagnetic-interference-sensitive medical environments. , 2007, Annali dell'Istituto superiore di sanita.

[24]  D. H. Simons.  Electromagnetic Compatibility Management in the 1980s , 1982, 1982 IEEE International Symposium on Electromagnetic Compatibility.

[25]  Xu-Guang Wan,et al.  EMC design and management and grounding practice of field communication equipment , 2015 .

[26]  Jing Liu,et al.  A Hierarchical Entity-Based Approach to Structuralize User Generated Content in Social Media: A Case of Yahoo! Answers , 2013, EMNLP.