A novel method for Analog Circuit Faults Diagnosis Based on CSA
DOI:
https://doi.org/10.22385/jctecs.v13i0.216Abstract
The paper emphasizes the way to the analog circuit fault diagnosis. The extreme learning machine(ELM) is used as classifier optimized by cuckoo search algorithm(CSA) and discussed in detail in the novel. The feasibility and effectiveness of the proposed method will be verified by the simulations of Sallen-Key low-pass filter circuit. Compared with other methods, the proposed method is more effective to identify and classify mistakes.
Downloads
References
Aihua Zhang, Chen Chen, Baoshan Jiang, Analog circuit fault diagnosis based UCISVM, Neurocomputing, Volume 173, Part 3, 15 January 2016, Pages 1752-1760.
A. Zhang and C. Chen, "Fault diagnosis based semi-supervised global LSSVM for analog circuit," Mechatronics and Control (ICMC), 2014 International Conference on, Jinzhou, 2014, pp. 744-748.
Mei Hu, Hong Wang, Geng Hu, Shiyuan Yang, Soft Fault Diagnosis for Analog Circuits Based on Slope Fault Feature and BP Neural Networks, Tsinghua Science & Technology, Volume 12, Supplement 1, July 2007, Pages 26-31.
Huang, G.-B., Zhu, Q.-Y., & Siew, C.-K.Extreme learning machine: a new learning scheme of feedforward neural networks. In IEEE international conference on neural networks. 2004,Vol. 2,pp. 985–990.
Huang, G.-B., Zhu, Q.-Y., & Siew, C.-K. (2006). Extreme learning machine: theory and applications. Neurocomputing, 70(1–3), 489–501
Y. Xin-She, S. Deb, Cuckoo Search via Levy flights, Nature & Biologically Inspired Computing, 2009. NaBIC 2009. World Congress on, 2009, pp. 210–214.
X.-S. Yang, S. Deb, Multi-objective cuckoo search for design optimization, Comput. Oper. Res 40 (2013) 1616–1624.
Hojjat Rakhshani, Effat Dehghanian, Amin Rahati, Hierarchy cuckoo search algorithm for parameter estimation in biological systems, Chemometrics and Intelligent Laboratory Systems, Volume 159, 15 December 2016, Pages 97-107.
X.-S. Yang, S. Deb, Cuckoo search: recent advances and applications, Neural Comput. Appl. 24 (2014) 169–174.
Yong-Ping Zhao, Parsimonious kernel extreme learning machine in primal via Cholesky factorization, Neural Networks, Volume 80, August 2016, Pages 95-109.
F. Aminian, M. Aminian and H. W. Collins, "Analog fault diagnosis of actual circuits using neural networks," in IEEE Transactions on Instrumentation and Measurement, vol. 51, no. 3, pp. 544-550, Jun 2002.doi: 10.1109/TIM.2002.1017726
S. Guoming, W. Houjun, J. Shuyan and L. Hong, "Fault Diagnosis Approach of Analog Circuits Based on Genetic Wavelet Neural Network," Electronic Measurement and Instruments, 2007. ICEMI '07. 8th International Conference on, Xi'an, 2007, pp. 3-675-3-679.doi: 10.1109/ICEMI.2007.4351007
Yanghong Tan, Yichuang Sun, Xin Yin, Analog fault diagnosis using S-transform preprocessor and a QNN classifier, Measurement, Volume 46, Issue 7, August 2013, Pages 2174-2183.
Downloads
Published
Issue
Section
License
The journal is currently an open access journal.
The articles receive both rigorous peer-review and expedited online publication.
The journal encourages young researchers to submit their unpublished papers.
The authors retain their article’s copyright.
The authors retain publishing rights without restrictions.
Thus, authors may use their own articles for the following non-commercial purposes without asking our permission (and subject only to acknowledging first publication in Journal of Communications Technology, Electronics and Computer Science and giving a full reference or web link, as appropriate).
Authors cannot submit a manuscript for publication to other journals simultaneously. It is a waste of valuable resources because editors and referees spent a great deal of time processing submitted manuscripts. It is also unethical to republish similar research articles (text/figures/tables) again because journals have limited page space and it most likely violates copyrights which have already been transferred to the first journal. Therefore, all journals require a signed author's copyright transfer agreement stating the originality of the research work submitted through a manuscript. As stated above that authors should submit original, new and unpublished research work to the journal. The ethical issues such as plagiarism, fraudulent and duplicate publication, violation of copyrights, authorship and conflict of interest are serious issues concerning ethical integrity when submitting a manuscript to a journal for publication.
The contents of papers are the sole responsibility of the authors, and publication shall not imply the concurrence of the Editors or Publisher.