Artificial Intelligent Systems and Machine Learning

Open Access Open Access  Restricted Access Subscription Access
Open Access Open Access Open Access  Restricted Access Restricted Access Subscription Access

Empirical Investigation of Genetic Algorithm Parameters on Neural Network based Fault Diagnosis in Analog Circuits


Affiliations
1 Depatment of Electronics and Communication, Shri Shankracharya Institute of Technology and Management, CSVTU, Chhattisgarh, India
     

   Subscribe/Renew Journal


Fault analysis in analog circuit is matter of research since last few decades because of the complexity in diagnosis of fault models. This paper proposes fault diagnosis approach for analog circuit using hybrid evolutionary techniques and neural network. Neural network is used because of its good robustness and adaptability and genetic algorithm is used as evolutionary technique for optimization and learning of neural network. The proposed method is validated through state variable filter circuit and all possible parametric variations are taken for faulty and non-faulty condition and experimental results are presented to show that hybrid scheme is more efficient than neural network method.


Keywords

Artificial Neural Network, Fault Detection, Genetic Algorithm, Analog Circuits, Soft Faults, MATLAB, Fault Location.
User
Subscription Login to verify subscription
Notifications
Font Size

  • A. Kavithamani, V. Manikandan and N. Devarajan, “Soft Fault Classification of Analog Circuits Using Network Parameters and Neural Networks” Springer Science+Business Media New York 2013, Received: 30 April 2012, Accepted: 8 March 2013, Published online: 11 April 2013, Pp. 237-240.

  • Sheikhan, Mansour, and Amir Ali Sha’bani. "PSO-optimized modular neural network trained by OWO-HWO algorithm for fault location in analog circuits." Neural computing & applications (2013): 1-12.

  • Randall, S., Sexton, R., & Dorsey, E. (2000). Reliable classification using neural networks: A genetic algorithm and back propagation comparison. Decision Support Systems, 30, 11–22.

  • Palaniswamy, Arun, Anura Jayasumana, and Yashwant K. Malaiya. "A Neural Network based Approach for Testing Analog Circuits with Frequency Domain Classification and Time Domain Testing." Proc. IEEE Int'l System Test Diagnosis Workshop. 1999.

  • Ashwani Kumar and A.P.Singh, “Neural Network based Fault Diagnosis in Analog Electronic Circuit using Polynomial Curve Fitting” International Journal of Computer Applications (0975 – 8887), Volume 61– No.16, January 2013, Pp. 28-34.

  • Mohd Ayub Khan, Divya Rawat, Mahima Singh, Meghna Acharya and Monika Garg, “Fault Detection In Analog Circuit Using Neural Network” International Journal of Advance Research In Science And Engineering, Vol. No.4, Issue 05, May 2015, Pp. 250-254.

  • Ashwani Kumar, Narula and Amar Partap Singh, “Fault Diagnosis of Mixed-Signal Analog Circuit using Artificial Neural Networks” I.J. Intelligent Systems and Applications, 2015, Volume-07, Published Online June 2015 in MECS, Pp. 11-17.

  • P. Kalpana, K. Gunavathi, “A Novel Implicit Parametric

  • Fault Detection Method for Analog/Mixed Signal Circuits

  • Using Wavelets” ICGST-PDCS Journal, Volume 7, Issue

  • , pp. 43-48, May, 2007.

  • Peng Wang, Shiyuan Yang, “ A New Diagnosis Approach

  • for Handling Tolerence in Analog and Mixed-Signal

  • Circuits by Using Fuzzy Math” IEEE Transactions on

  • Circuits and Systems-I: Regular Papers, Vol. 52, No.10, pp.

  • -2127, 2005.

  • Sheikhan, M., Ali, A., & Sha’bani, (2012). PSO-optimized

  • modular neural network trained by OWO-HWO algorithm for

  • fault location in analog circuits (pp. 1–14). New York: springer.

  • Guo, Zhen, and Jacob Savir. "Coefficient-based test of parametric faults in analog circuits." IEEE Transactions on Instrumentation and Measurement55.1 (2006): 150-157.

  • Mahdieh Jahangiri and Farhad Razaghian," Fault detection in analogue circuits using hybrid evolutionary algorithm and neural network" Springer Science+Business Media New York 2014, Received: 2 December 2013, Revised: 11 March 2014, Accepted: 19 May 2014, Published online: 4 July 2014, Pp. 155-156.

  • Kaur, Taranjit. "Implementation of Back Propagation algorithm: A Neural Network approach for pattern recognition." International Journal of Engineering Research and Development 1.5 (2012): 30-7.

  • D. Montana and L. Davis, “Training feedforward neural networks using genetic algorithms”, published in “IJCAI'89 Proceedings of the 11th international joint conference on Artificial intelligence”, pp 762-767 vol. 1, 1989.

  • Rahman, Md Mijanur, and T. Akter Setu. "An implementation for combining neural networks and genetic algorithms." Int. J. Comput. Sci. Technol 6.3 (2015).


Abstract Views: 266

PDF Views: 4




  • Empirical Investigation of Genetic Algorithm Parameters on Neural Network based Fault Diagnosis in Analog Circuits

Abstract Views: 266  |  PDF Views: 4

Authors

Divya Bisen
Depatment of Electronics and Communication, Shri Shankracharya Institute of Technology and Management, CSVTU, Chhattisgarh, India
Yogesh Sharma
Depatment of Electronics and Communication, Shri Shankracharya Institute of Technology and Management, CSVTU, Chhattisgarh, India

Abstract


Fault analysis in analog circuit is matter of research since last few decades because of the complexity in diagnosis of fault models. This paper proposes fault diagnosis approach for analog circuit using hybrid evolutionary techniques and neural network. Neural network is used because of its good robustness and adaptability and genetic algorithm is used as evolutionary technique for optimization and learning of neural network. The proposed method is validated through state variable filter circuit and all possible parametric variations are taken for faulty and non-faulty condition and experimental results are presented to show that hybrid scheme is more efficient than neural network method.


Keywords


Artificial Neural Network, Fault Detection, Genetic Algorithm, Analog Circuits, Soft Faults, MATLAB, Fault Location.

References