IGBT junction temperature prediction method based on improved artificial bee colony algorithm for optimizing SVR

Aiming at the low precision of IGBT thermal parameter junction temperature prediction method and the need to extract multiple parameters and being vulnerable to load, the improved artificial bee colony algorithm optimized support vector regression machine (ABC- SVR) is used to predict the IGBT junction temperature. Firstly, the formula for updating the honey source in the artificial bee colony algorithm (ABC) is improved, and the fitness probability of Follower bee select honey source is introduced to construct the weight function; Then the problem of support vector regression (SVR) parameter selection is transformed into the parameter combination optimization problem, then establish an optimal SVR model; Finally, the data from the IGBT accelerated aging test provided by the National Aeronautics and Space Administration (NASA) is taken as a sample, the predicted results of the improved ABC-SVR model and the common ABC-SVR model were compared and analyzed. Through the simulation results, the prediction effect of improved ABC-SVR model is better than the common model, and the running time is greatly reduced, it has greater precision in junction temperature prediction.

[1]  Dervis Karaboga,et al.  A powerful and efficient algorithm for numerical function optimization: artificial bee colony (ABC) algorithm , 2007, J. Glob. Optim..

[2]  T. McNutt,et al.  Inverter Dynamic Electro-Thermal Modeling and Simulation with Experimental Verification , 2005, 2005 IEEE 36th Power Electronics Specialists Conference.

[3]  KarabogaDervis,et al.  A powerful and efficient algorithm for numerical function optimization , 2007 .

[4]  Sayan Mukherjee,et al.  Choosing Multiple Parameters for Support Vector Machines , 2002, Machine Learning.

[5]  P.M. Fabis,et al.  Thermal modeling of diamond-based power electronics packaging , 1999, Fifteenth Annual IEEE Semiconductor Thermal Measurement and Management Symposium (Cat. No.99CH36306).

[6]  T. Seeley.  The Wisdom of the Hive: The Social Physiology of Honey Bee Colonies , 1995 .

[7]  Michel Mermet-Guyennet,et al.  Temperature measurement on series resistance and devices in power packs based on on-state voltage drop monitoring at high current , 2006, Microelectron. Reliab..

[8]  Bernhard Schölkopf,et al.  A tutorial on support vector regression , 2004, Stat. Comput..

[9]  Josef Lutz,et al.  Semiconductor Power Devices , 2011 .

[10]  Hui Huang,et al.  A Lifetime Estimation Technique for Voltage Source Inverters , 2013, IEEE Transactions on Power Electronics.

[11]  A.T. Bryant,et al.  Exploration of Power Device Reliability Using Compact Device Models and Fast Electrothermal Simulation , 2006, IEEE Transactions on Industry Applications.

[12]  D. Karaboga,et al.  On the performance of artificial bee colony (ABC) algorithm , 2008, Appl. Soft Comput..

[13]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[14]  Ivan Bahun,et al.  Real-Time Measurement of IGBT's Operating Temperature , 2011 .

[15]  Jeyraj Selvaraj,et al.  A Fiber Bragg Grating—Bimetal Temperature Sensor for Solar Panel Inverters , 2011, Sensors.