Category Archives: Electronic circuit modelling

Black-box modelling of electronic circuits and systems

Circuit simulations at the system level are one of the most complex tasks that engineers encounter in the field of electronics and microelectronics due to two main reasons: the low speed and limited accuracy of circuit simulations. The black-box approach to behavioural modelling of electronic circuits, although very challenging, is particularly interesting for fast and relatively accurate simulations of analogue and mixed-signal integrated circuits. Today’s most prevalent approach is manual generation of the black-box models, which is heuristic, inconvenient, computationally expensive and error-prone. Automated model-building has many potential benefits. It is however very difficult to develop a fully automated model generation procedure because the model has to cover a wide range of circuits and devices. In this research several methods are proposed that can be regarded as essential blocks needed for the automated generation of black-box models. The new methods of functional approximation (ALSVR, TASVR and MK-ALSVR) suitable for the black-box modelling of electronic circuits are proposed. The new algorithm FTSR is proposed for model inputs selection and ranking as well as training data points selection and ranking, designed specifically for black-box modelling of electronic circuits. Also, a new method for checking and improving the stability of black-box electronic circuit models (CISB) is presented. It enables models built from the proposed behavioural modelling procedures to be effectively implemented in common circuit simulation tools. A new machine learning approach to modelling of conducted electromagnetic emissions and conducted electromagnetic immunity is proposed. Finally, the framework for behavioural modelling of electronic circuits based on the methods proposed is proposed.


Journal papers

  1. ​​V. Ceperic, G. Gielen, and A. Baric. “Recurrent sparse support vector regression machines trained by active learning in the time-domain”. In: Expert Systems with Applications 39.12 (2012), pp. 10933—10942. Corresponding author.
  2. V. Ceperic, G. Gielen, and A. Baric. “Sparse multikernel support vector regression machines trained by active learning”. In: Expert Systems with Applications 39.12 (2012), pp. 11029—11035. Corresponding author. 
  3. V. Ceperic, G. Gielen, and A. Baric. “Sparse e-tube Support Vector Regression by Active Learning”. In: Soft Computing (2013).  Accepted for publication. Corresponding author.

​Submitted journal papers

  1. V. Ceperic, N. Bako, and A. Baric. “Symbolic regression based modelling strategy of AC/DC rectifiers for RFID applications”. In: IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems​  (2013). Under review. Corresponding author. Journal impact factor: 1.038.​

Patent applications

  1. V. Ceperic and A. Baric. “System, Method and Computer Program Product for Modelling Electronic Circuits”. Patent application 13,353,701 (US). Jan. 2012.

​Conference papers

  1. V. Ceperic, G. Gielen, and A. Baric. “Black-Box Modelling of AC-DC Rectifiers for RFID Applications Using Support Vector Regression Machines”. In: 15th International Conference on Computer Modelling and Simulation (UKSim). Apr. 2013, pp. 815—820.
  2. V. Ceperic, G. Gielen, and A. Baric. “Black-box modelling of conducted electromagnetic immunity by support vector machines”. In: International Symposium on Electromagnetic Compatibility (EMC EUROPE), 2012. Sept. 2012, pp. 1—6.
  3. V. Ceperic, G. Gielen, and A. Baric. “Black-box modelling of conducted electromagnetic emissions by adjustable complexity support vector regression machines”. In: Asia-Pacific Symposium on Electromagnetic Compatibility (APEMC), 2012. May 2012, pp. 17—20.
  4. V. Ceperic and A. Baric. “A brief overview of the black-box behavioural modelling of electronic circuits for transient simulations”. In: Proceedings of the 35th International Convention MIPRC 2012. May 2012, pp. 72—77.
  5. V. Ceperic and A. Baric. “Modelling of Electromagnetic Immunity of Integrated Circuits by Artificial Neural Networks”. In: 20th International Zurich Symposium on Electromagnetic Compatibility, 200.9. Jan. 2009, pp. 373—376.
  6. V. Ceperic and A. Baric. “Conducted electromagnetic emission current source modelling by artificial neural networks”. In: 16th International Conference on Software, Telecommunications and Computer Networks, SoftCOM 2008. Sept. 2008, pp. 55—59.
  7. V. Ceperic, E. Ceperic, and A. Baric. “Behavioural Modelling of Circuits that Exhibit Chaotic Behaviour”. In: Proceedings of the 31th International Convention MIPRC 2008. Vol. 1. May 2008, pp. 167-171.
  8. V. Ceperic, A. Baric, and B. Pejcinovic. “Artificial neural network in modelling of voltage controlled oscillators with jitter”. In: Proceedings of the 12th IEEE Mediterranean Electrotechnical Conference, MELECON2004. Vol. 1. 2004, pp. 347—350.
  9. V. Ceperic and A. Baric. “Modeling of analog circuits by using support vector regression machines”. In: Proceedings of the 11th IEEE International Conference on Electronics, Circuits and Systems, ICECS 2004. 2004, pp. 391—394.
  10. V. Ceperic and A. Baric. “Modelling of SCFL circuits”. In: Proceedings of the 27th International Convention MIPRC 2004: conferences Microelectronics, Electronics and Electronics Technologies (MEET) and Hypermedia and Grid System (HGS). May 2004, pp. 72—77.