中高压功率IGBT模块开关特性测试及建模
|
摘要
绝缘栅双极型晶体管(IGBT)广泛应用于中大功率变流器中,其开关特性决定了器件的开关损耗、电气应力、装置最高可应用的开关频率、功率密度、电磁兼容性以及散热结构设计等,直接影响设备的性能和寿命。IGBT在实际工况下的开关特性与工作环境参数密切相关,研究功率开关器件的开关特性是正确设计变流器、改善变流器性能、提高变流器变换效率和确保功率器件及电力设备安全的重要前提。
中高压IGBT功率器件开关时间短,电压、电流变化率大,上升和下降沿产生大量电磁干扰,给开关特性的测量带来很大挑战。本文首先对中高压大功率IGBT模块的开关特性测试展开研究,提出了一种全电压等级的功率器件开关特性测试系统的设计准则,在该准则指导下设计和研制了一台通用型中高压大功率IGBT器件开关特性自动测试平台。该测试平台可用于多种拓扑和封装结构的功率IGBT模块开关特性测试,最高测试电压为5000V,最大测试电流为1500A,实现了：①根据用户需求自动调节IGBT的工作环境参数；②精确记录功率IGBT模块开关特性瞬态波形；③自动完成示波器设置、多组工作点重复测试和测试数据的自动保存；④获得器件定制的开关特性资料和器件开关特性随多维环境参数的变化趋势,为变换器设计、变换器性能优化和评估,以及器件的损耗计算提供实验基础和指导；⑤记录器件故障瞬态,为失效分析提供依据。
利用测试平台,本文进一步测试和研究了不同拓扑、技术和容量的IGBT功率模块,获得了功率模块各开关特性参数随环境参数的多维分布趋势。通过对不同技术和容量的IGBT功率模块进行测试：①分析了环路寄生电感对IGBT开关过程的影响；②提出了一种通过实验波形提取功率模块内部寄生电感的方法；③分析了IGBT的一种失效机理,发现反向恢复引起的二极管过压失效比IGBT关断过压失效更容易发生,应给予特别关注；④对不同公司相同IGBT结构的半桥功率模块进行测试和比较,为器件选型提供指导；⑤研究了一种新型拓扑的三电平IGBT功率模块(optimized A(T-type)-3level circuit),结合准在线分析方法,比较了新型三电平电路和NPC三电平电路的器件损耗,结果显示T型三电平电路的总导通损耗比NPC型三电平小,开关损耗比NPC型三电平大,在一定的开关频率范围内T型三电平电路具有器件损耗小的优势。
由于精确的IGBT物理解析模型很难实现,本文避开IGBT的工作物理机理,结合测试平台的大量实验建立了一种IGBT开关特性的实验模型——基于误差反向传播算法(backpropagation, BP)的IGBT开关特性神经网络预测模型,实现了对IGBT在实际工况下的开关特性参数如器件电气应力、开关损耗等的精确预测。与物理解析模型相比,基于实验数据的开关特性预测模型容易建立且使用方便,可以对用户购买的器件做定制的预测模型,具有较高的预测精度。
针对BP神经网络隐含层的节点数、网络的目标期望误差和神经网络的初始权值与阈值矩阵对网络性能影响大、凭经验和试凑法设计网络结构对性能的影响不可控、寻优容易陷入局部极小值且无法逃离极值点等局限性,本文进一步引入全局优化算法对开关特性的BP神经网络预测模型进行改进：采用遗传优化算法对隐层节点数和目标期望误差进行混合整数规划；分别采用遗传算法、模拟退火算法和粒子群算法对神经网络的初始权值和阈值矩阵进行优化,大大改善了BP神经网络模型的预测性能。
经过大量实验数据的训练,用改进的BP神经网络预测模型能以较高精度预测IGBT在不同的环路寄生电感、集电极电压、集电极电流、器件结温、驱动电阻和驱动电压下硬开关状态的开关特性参数。通过对开关特性的高精度预测,可以对器件进行模拟实际工况的准在线分析,计算器件损耗和系统效率,评估器件的电压、电流过冲和系统可靠性,优化硬件电路的寄生参数,合理设计死区时间,对工程师进行散热设计、电路设计、结构设计和装置性能评估具有很大的指导意义。
Insulated-gate bipolar transistors (IGBTs) are widely used in medium and high power converter. Switching characteristics determine the switching losses, device voltage and current stresses, converter maximum switching frequency, power density and electromagnetic compatibility as well as thermal design, therefore the switching characteristics directly determine the performance and reliability of the converter. IGBT switching characteristics under actual operating conditions are closely related to their working environments. The switching characteristics of IGBTs are critical for power converter design, performance, efficiency and reliability.
Because of the short switching time, high dv/dt and di/dt as well as serious electromagnetic interference, the measurement of high-voltage IGBT switching characteristics meets great challenges. The design criteria for the switching characteristics test system of IGBT voltage ratings from1200V to6500V have been proposed. With the criteria, a universal off-line switching characteristics test bench for medium and high voltage IGBTs has been developed. The test bench covers voltage ratings from1200V to6500V and wide current range of40A to1500A, applicable to a variety of topologies and package structures. The test bench realizes:1.adjusting working environmental parameters automatically according to user's need;2.recording IGBT switching transients accurately;3.completing oscilloscope settings, repeated measurement and data preservation automatically;4.extracting comprehensive information of switching characteristics far more than the vendor-supplied datasheet;5.acquiring IGBT switching characteristics trends with environmental parameters for converter design, optimization and performance evaluation as well as device loss calculation;6.recording device fault transients and providing evidence for failure analysis.
IGBT modules of different topologies, technologies and capacities have been tested on the test bench. Distribution trends of switching characteristics parameters with environmental parameters have been acquired. Based on experimental data:1.The influence of loop parasitic inductance on IGBT switching characteristics has been explored.2.An extraction method for parasitic inductance within the package has been proposed.3.The mechanism for IGBT dynamic failure during test has been analyzed.4.A comparison of IGBTs with the same capacity but different technologies has been presented.5.A new type of ANPC power module realized by reverse blocking IGBT has been tested and analyzed, and the device losses ANPC of and NPC3-level topologies have been calculated and compared. The result shows that the conduction losses of ANPC is lower than NPC while its switching losses is higher. This indicates that it has device losses advantage in a certain frequency range.
The prediction and simulation of switching characteristics and device losses are extremely important for device manufacturers and users. Physical modeling is extremely complex while its accuracy is difficult to guarantee and device structure and process parameters can hardly be obtained, therefore it is not easy for device users. An error back-propagation multi-layer feed-forward neural network model has been established in this paper based on the experimental data from the test bench, realizing reliable prediction of IGBT switching characteristics as device stresses and switching losses under actual working conditions. Compared to physical modeling, the specified BP neural network prediction model for purchased IGBTs is convenient to use and easy to build. Environmental influences and IGBT physical mechanisms can be uniformly considered, avoiding explicit description of physical mechanisms.
In this paper, an optimized switching characteristics artificial neural network prediction model has been further proposed. BP neural network algorithm has certain limitations. The number of hidden neurons, training goal, initial network weights and biases have great impacts on neural network performance, and designing network structure by using trial and error method may make the impacts uncontrollable. The optimizing process of BP algorithm is vulnerable to local minima, and when falling into local minima, the BP algorithm cannot escape from the pole. Global optimization algorithms are introduced:genetic algorithm has been used for hidden neuron number and training goal optimization; genetic algorithm, simulated annealing algorithm and particle swarm optimization algorithm have been applied for network initial weights and biases optimization. The global optimization algorithms have improved the performance of the BP neural network prediction model greatly.
After training, the improved BP neural network prediction model has realized accurate predictions of IGBT hard switching performance such as switching time, switching losses, voltage overshoot and current spike under different environmental parameters:parasitic inductance, junction temperature, driving voltage and resistance, collector voltage and current. By high precision forecast, quasi-online analysis for actual working conditions as device losses and system efficiency calculation, device voltage and current stress evaluation, circuit parasitic parameter optimization, and reasonable dead-time design can be performed. It is convenient and has great guiding significance for engineers to design heat sink, circuit, structure and assess device and system performance.
中高压IGBT功率器件开关时间短,电压、电流变化率大,上升和下降沿产生大量电磁干扰,给开关特性的测量带来很大挑战。本文首先对中高压大功率IGBT模块的开关特性测试展开研究,提出了一种全电压等级的功率器件开关特性测试系统的设计准则,在该准则指导下设计和研制了一台通用型中高压大功率IGBT器件开关特性自动测试平台。该测试平台可用于多种拓扑和封装结构的功率IGBT模块开关特性测试,最高测试电压为5000V,最大测试电流为1500A,实现了：①根据用户需求自动调节IGBT的工作环境参数；②精确记录功率IGBT模块开关特性瞬态波形；③自动完成示波器设置、多组工作点重复测试和测试数据的自动保存；④获得器件定制的开关特性资料和器件开关特性随多维环境参数的变化趋势,为变换器设计、变换器性能优化和评估,以及器件的损耗计算提供实验基础和指导；⑤记录器件故障瞬态,为失效分析提供依据。
利用测试平台,本文进一步测试和研究了不同拓扑、技术和容量的IGBT功率模块,获得了功率模块各开关特性参数随环境参数的多维分布趋势。通过对不同技术和容量的IGBT功率模块进行测试：①分析了环路寄生电感对IGBT开关过程的影响；②提出了一种通过实验波形提取功率模块内部寄生电感的方法；③分析了IGBT的一种失效机理,发现反向恢复引起的二极管过压失效比IGBT关断过压失效更容易发生,应给予特别关注；④对不同公司相同IGBT结构的半桥功率模块进行测试和比较,为器件选型提供指导；⑤研究了一种新型拓扑的三电平IGBT功率模块(optimized A(T-type)-3level circuit),结合准在线分析方法,比较了新型三电平电路和NPC三电平电路的器件损耗,结果显示T型三电平电路的总导通损耗比NPC型三电平小,开关损耗比NPC型三电平大,在一定的开关频率范围内T型三电平电路具有器件损耗小的优势。
由于精确的IGBT物理解析模型很难实现,本文避开IGBT的工作物理机理,结合测试平台的大量实验建立了一种IGBT开关特性的实验模型——基于误差反向传播算法(backpropagation, BP)的IGBT开关特性神经网络预测模型,实现了对IGBT在实际工况下的开关特性参数如器件电气应力、开关损耗等的精确预测。与物理解析模型相比,基于实验数据的开关特性预测模型容易建立且使用方便,可以对用户购买的器件做定制的预测模型,具有较高的预测精度。
针对BP神经网络隐含层的节点数、网络的目标期望误差和神经网络的初始权值与阈值矩阵对网络性能影响大、凭经验和试凑法设计网络结构对性能的影响不可控、寻优容易陷入局部极小值且无法逃离极值点等局限性,本文进一步引入全局优化算法对开关特性的BP神经网络预测模型进行改进：采用遗传优化算法对隐层节点数和目标期望误差进行混合整数规划；分别采用遗传算法、模拟退火算法和粒子群算法对神经网络的初始权值和阈值矩阵进行优化,大大改善了BP神经网络模型的预测性能。
经过大量实验数据的训练,用改进的BP神经网络预测模型能以较高精度预测IGBT在不同的环路寄生电感、集电极电压、集电极电流、器件结温、驱动电阻和驱动电压下硬开关状态的开关特性参数。通过对开关特性的高精度预测,可以对器件进行模拟实际工况的准在线分析,计算器件损耗和系统效率,评估器件的电压、电流过冲和系统可靠性,优化硬件电路的寄生参数,合理设计死区时间,对工程师进行散热设计、电路设计、结构设计和装置性能评估具有很大的指导意义。
Insulated-gate bipolar transistors (IGBTs) are widely used in medium and high power converter. Switching characteristics determine the switching losses, device voltage and current stresses, converter maximum switching frequency, power density and electromagnetic compatibility as well as thermal design, therefore the switching characteristics directly determine the performance and reliability of the converter. IGBT switching characteristics under actual operating conditions are closely related to their working environments. The switching characteristics of IGBTs are critical for power converter design, performance, efficiency and reliability.
Because of the short switching time, high dv/dt and di/dt as well as serious electromagnetic interference, the measurement of high-voltage IGBT switching characteristics meets great challenges. The design criteria for the switching characteristics test system of IGBT voltage ratings from1200V to6500V have been proposed. With the criteria, a universal off-line switching characteristics test bench for medium and high voltage IGBTs has been developed. The test bench covers voltage ratings from1200V to6500V and wide current range of40A to1500A, applicable to a variety of topologies and package structures. The test bench realizes:1.adjusting working environmental parameters automatically according to user's need;2.recording IGBT switching transients accurately;3.completing oscilloscope settings, repeated measurement and data preservation automatically;4.extracting comprehensive information of switching characteristics far more than the vendor-supplied datasheet;5.acquiring IGBT switching characteristics trends with environmental parameters for converter design, optimization and performance evaluation as well as device loss calculation;6.recording device fault transients and providing evidence for failure analysis.
IGBT modules of different topologies, technologies and capacities have been tested on the test bench. Distribution trends of switching characteristics parameters with environmental parameters have been acquired. Based on experimental data:1.The influence of loop parasitic inductance on IGBT switching characteristics has been explored.2.An extraction method for parasitic inductance within the package has been proposed.3.The mechanism for IGBT dynamic failure during test has been analyzed.4.A comparison of IGBTs with the same capacity but different technologies has been presented.5.A new type of ANPC power module realized by reverse blocking IGBT has been tested and analyzed, and the device losses ANPC of and NPC3-level topologies have been calculated and compared. The result shows that the conduction losses of ANPC is lower than NPC while its switching losses is higher. This indicates that it has device losses advantage in a certain frequency range.
The prediction and simulation of switching characteristics and device losses are extremely important for device manufacturers and users. Physical modeling is extremely complex while its accuracy is difficult to guarantee and device structure and process parameters can hardly be obtained, therefore it is not easy for device users. An error back-propagation multi-layer feed-forward neural network model has been established in this paper based on the experimental data from the test bench, realizing reliable prediction of IGBT switching characteristics as device stresses and switching losses under actual working conditions. Compared to physical modeling, the specified BP neural network prediction model for purchased IGBTs is convenient to use and easy to build. Environmental influences and IGBT physical mechanisms can be uniformly considered, avoiding explicit description of physical mechanisms.
In this paper, an optimized switching characteristics artificial neural network prediction model has been further proposed. BP neural network algorithm has certain limitations. The number of hidden neurons, training goal, initial network weights and biases have great impacts on neural network performance, and designing network structure by using trial and error method may make the impacts uncontrollable. The optimizing process of BP algorithm is vulnerable to local minima, and when falling into local minima, the BP algorithm cannot escape from the pole. Global optimization algorithms are introduced:genetic algorithm has been used for hidden neuron number and training goal optimization; genetic algorithm, simulated annealing algorithm and particle swarm optimization algorithm have been applied for network initial weights and biases optimization. The global optimization algorithms have improved the performance of the BP neural network prediction model greatly.
After training, the improved BP neural network prediction model has realized accurate predictions of IGBT hard switching performance such as switching time, switching losses, voltage overshoot and current spike under different environmental parameters:parasitic inductance, junction temperature, driving voltage and resistance, collector voltage and current. By high precision forecast, quasi-online analysis for actual working conditions as device losses and system efficiency calculation, device voltage and current stress evaluation, circuit parasitic parameter optimization, and reasonable dead-time design can be performed. It is convenient and has great guiding significance for engineers to design heat sink, circuit, structure and assess device and system performance.
引文
[1]Baliga B J. Fundamentals of Power Semiconductor Devices. New York:Springer Science+ Business Media,2008.
[2]Kharitonov S A, Petrov M A, Korobkov D V, et al. A principle of calculation dynamic and static power losses with hard-switching IGBT[C]. In Proceedings of the 6th Annual Meeting of the International Siberian Workshop and Tutorials on Electron Devices and Materials. 2005,147-149.
[3]IGBT Power Losses Calculation Using the Data-Sheet Parameters. Available: http://www.infineon.com/cms/en/product/index.html
[4]Kurnia A, Cherradi H, Divan D M, Impact of IGBT behavior on design optimization of soft switching inverter topologies [J]. IEEE Transactions on Industry Applications,1995,31: 280-286.
[5]熊妍.绝缘栅晶体管和大功率二极管损耗建模方法的研究：[学位论文].杭州：浙江大学,2006.
[6]Ammous K, Allard B, Brevet O, et al. Error in estimation of power switching losses based on electrical measurements[C]. In Proceedings of the IEEE 31st PESC.2000,1:286-291.
[7]XYZs of Oscilloscopes:Operating the Oscilloscope. Available:www.tek.com/Measurement
[8]ABCs of Probes Primer. Available:www.tek.com/measurement
[9]Witcher J B. Methodology for Switching Characterization of Power Devices and Modules: [dissertation]. USA:Virginia Polytechnic Institute and State University,2002.
[10]BΦrge P. Modelling and Test of Power Semiconductors:[dissertation]. Denmark:Aalborg University,2004.
[11]Xu D, Huang L, Azuma S, et al. Power Loss and Junction Temperature Analysis of Power Semiconductor Devices[J]. IEEE Transactions on Industrial Application,2002, 38:1426-1431.
[12]Azuma S, Jiang X, Lu H, et al. Research on the Power Loss and Junction Temperature of Power Semiconductor Devices for Inverter[C]. In Proceedings of the IEEE IVEC'99 conference,1999,183-187.
[13]Munk-Nielsen S, Blaabjerg F, Pedersen J K. An advanced measurement system for verification of models and datasheets[C]. In Proceedings of the IEEE 4th Workshop on Computers in Power Electronics.1994,209～214.
[14]Li Y. Unified Zero-Current-Transition Techniques for High-Power Three-Phase PWM Inverters:[dissertation]. USA:Virginia Polytechnic Institute and State University,2002.
[15]Azzopardi S. A Systematic Hard-and Soft-Switching Performances Evaluation of 1200V Punchthrough IGBT Structures[J]. IEEE Transactions on Power Electronics,2004,19: 231-241.
[16]Petterteig A, Lode J, Undeland T M. IGBT Turn-off Losses for Hard Switching and with Capacitive Snubbers[C]. In Conference Record of the 1991 IEEE Industry Applications Society Annual Meeting,1991,1501～1507.
[17]Bernet S, Carroll E, Streit P, et al. Design, test and characteristics of 10 kV IGCTs[C]. In Conference Record of the 38th IAS Annual Meeting,2003,2:1012～1019.
[18]Yuan L, Zhao Z, Bai H, Li Chongjian, et al. The IGCT test platform for voltage source inverters[C]. In Proceedings of the IEEE 5th PEDS,2003,2:1291～1294.
[19]Ladoux P, Blaquiere J M, Alvarez S, et al. Test bench for the characterisation of experimental low voltage IGCTs[C]. In Proceedings of the IEEE 35th PESC,2004,4: 2937-2942.
[20]Lai J S, Leslie L, Ferrell J, et al. Characterization of HV-IGBT for High-Power Inverter Applications[C]. In Conference Record of the IEEE 40th IAS Annual Meeting,2005,1: 377-382.
[21]Yuan L, Zhao Z, Liu J, et al. Experiment and Analysis for Single IGCT Equipped in MV Three-level Inverter[C]. In Proc. of the IEEE 40th IAS Annual Meeting,2005,2:825～829.
[22]Munk N S, Blaabjerg F, Pedersen J K, An advanced measurement system for verification of models and datasheets[C]. In Proceedings of the IEEE 4th Workshop on Computers in Power Electronics,1994,209～214.
[23]Petterteig A, Lode J, Undeland T M. IGBT Turn-off Losses for Hard Switching and with Capacitive Snubbers[C]. In Conference Record of the IEEE IAS Annual Meeting,1991, 2:1501-1507.
[24]Lai J S, Leslie L, Ferrell J, et al. Characterization of HV-IGBT for High-Power Inverter Applications[C]. In Conference Record of the IEEE 40th IAS Annual Meeting,2005,1: 377～382.
[25]Wang K, Lee F C, Hua G. A Comparative Study of Switching Losses of IGBTs under Hard switching, Zero-voltage-switching and Zero-Current-Switching[C]. In Proceedings of the IEEE 25th PESC,1994,2:1196～1204.
[26]Yuan L, Zhao Z, Liu J, et al. Experiment and Analysis for Single IGCT Equipped in MV Three-level Inverter, in Industry Applications Conference [C]. In Conference Record of the IEEE 40th IAS Annual Meeting,2005,2:825～829.
[27]Yu Q, Li L, Jiang Q. High power electronic device measurements of four IGCTs (4.5 kV/4.0 kA) in series connection[C]. In Proceedings of the Fifth World Congress on Intelligent Control and Automation,2004,5:4446～4449.
[28]Kim S C, Kim H W, Seo K S, et al. Static and dynamic characteristics of the 2.5kV/500A IGCTs[C]. In Proceedings of the 24th International Conference on Microelectronics,2004, 1:171～173.
[29]Wang X, Lu L, Pytel S, et al. Multilevel device models developed for the virtual test bed (VTB)[C]. In Conference Record of the IEEE 39th IAS Annual Meeting,2004, 4:2528～2535.
[30]Yuan L, Zhao Z, Li C. The optimization of snubbers for IGCT-based voltage source inverters[C]. In Proceedings of the IEEE 29th IECON,2003,1:679～682.
[31]Wang J, Yang B, Zhao J, et al. Development of a compact 750KVA three-phase NPC three-level universal inverter module with specifically designed busbar[C]. In Proceedings of the IEEE 25th APEC,2010:1266～1271.
[32]杨兵建.基于IGBT的大功率三电平逆变器控制与测试方法等相关问题研究：[学位论文].杭州：浙江大学,2011.
[33]汪望.基于IGBT的750kVA三相二极管箝位型三电平通用变流模块设计：[学位论文].杭州：浙江大学,2010.
[34]Kuang S, Williams B W, Finney S J. A review of IGBT models[J]. IEEE Transactions on Power Electronics,2000,15:1250～1266.
[35]Hefner A R. Characterization and Modeling of the Power Insulated Gate Bipolar Transistor [dissertation]. Maryland:The University of Maryland,1987.
[36]Hefner A R, Jr., An improved understanding for the transient operation of the power insulated gate bipolar transistor (IGBT)[J]. IEEE Transactions on Power Electronics,1990, 5:459-468.
[37]Cavalcanti M C, da Silva E R, Boroyevich D, et al. A feasible loss model for IGBT in soft-switching inverters[C]. In Proceedings of the IEEE 34th PESC.2003,4:1845～1850.
[38]Cavalcanti M C, da Silva E R, Jacobina C B, et al. Comparative evaluation of losses in soft and hard-switched inverters[C]. In Conference Record of the IEEE 38th IAS Annual Meeting,2003,3:1912～1917.
[39]Claudio-Sanchez A, Li J M, Lafore D. Behaviour analysis of the IGBT in hard and soft switching modes by a soft modelling concept[C]. In Technical Proceedings of the 3rd International CIEP Power Electronics Congress,1994,101～107.
[40]Berning D W, Hefner A R. IGBT model validation for soft-switching applications[J]. IEEE Transactions on Industry Applications,2001,37:650～660.
[41]Stier S H, Mutschler P. An investigation of a reliable behavioral IGBT model in comparison to PSpice and measurement in hard and soft switching applications[C]. In Technical Proceedings of the 2005 European Conference on Power Electronics and Applications,2005,10 pp.-P.10.
[42]Trivedi M, Shenai K.Modeling the turn-off of IGBT's in hard- and soft-switching applications[J]. IEEE Transactions on Electron Devices,1997,44:887～893.
[43]Jinrong Q, Khan A, Batarseh I. Turn-off switching loss model and analysis of IGBT under different switching operation modes[C]. In Proceedings of the IEEE 21st IECON,1995,1: 240～245.
[44]Hefner A R. A dynamic electro-thermal model for the IGBT[C]. In Conference Record of the IEEE 1992 IAS Annual Meeting,1992,1:1094～1104.
[45]Hefner A R, Diebolt D M. An experimentally verified IGBT model implemented in the Saber circuit simulator[J]. IEEE Transactions on Power Electronics,1994,9:532～542.
[46]Hefner A R. Modeling buffer layer IGBTs for circuit simulation[J]. IEEE Transactions on Power Electronics,1995,10:111～123.
[47]Hefner A R, Diebolt D M. An experimentally verified IGBT model implemented in the Saber circuit simulator[C]. In Proceedings of the IEEE 22nd PESC,1991,10～19.
[48]Artamonov A, Nelayev V, Shelibak I, et al. IGBT technology design and device optimization[C]. In Proceedings of the 9th East-West Design & Test Symposium (EWDTS),2011,233～236.
[49]Shelibak I, Nelayev V, Artamonov A. Technology and electrical design of IGBT[C]. In Proceedings of the 18th International Conference in Mixed Design of Integrated Circuits and Systems (MIXDES),2011,562～564.
[50]Ammous A, Ammous K, Morel H, et al. Electrothermal modeling of IGBTs:application to short-circuit conditions[J]. IEEE Transactions on Power Electronics,2000,15:778-790.
[51]Elmazria O, Hoffmann A, Lepley B, et al. Simulation of electrons irradiation damages to optimize the performance of IGBT[J]. IEEE Transactions on Nuclear Science,1997,44: 14～19.
[52]Kang X, Santi E, Hudgins J L, et al. Parameter extraction for a physics-based circuit simulator IGBT model[C]. In Proceedings of the IEEE 18th APEC,2003,2:946～952.
[53]Cotorogea M, Claudio A, Rodriguez M A. Parameter extraction method for the Pspice model of the PT- and NPT-IGBT's by electrical measurements[C]. In Technical Proceedings of the IEEE International CIEP 2002 Power Electronics Congress,2002, 101-106.
[54]Musumeci S, Raciti A, Sardo M, et al. PT-IGBT PSpice model with new parameter extraction for life-time and epy dependent behaviour simulation[C]. In Proceedings of the IEEE 27th PESC,1996,2:1682～1688.
[55]Kang X, Caiafa A, Santi E, et al. Characterization and modeling of high-voltage field-stop IGBTs[C]. In Conference Record of the IEEE 37th IAS Annual Meeting,2002,3: 2175～2181.
[56]Tang Y, Chen M, Wang B. New methods for extracting field-stop IGBT model parameters by electrical measurements[C]. In Proceedings of the IEEE International Symposium on Industrial Electronics,2009,1546～1551.
[57]Kang X, Lu L, Wang X, et al. Characterization and modeling of the LPT CSTBT-the 5th generation IGBT[C]. In Conference Record of the IEEE 38th IAS Annual Meeting,2003,2: 982-987.
[58]Blaabjerg F, Pedersen J K, Sigurjonsson S, et al. An extended model of power losses in hard-switched IGBT-inverters[C]. In Conference Record of the IEEE 1996 IAS Annual Meeting,1996,3:1454～1463.
[59]Castellazzi A, Ciappa M, Fichtner W, et al. Comprehensive Electro-Thermal Compact Model of a 3.3kV-1200A IGBT-module[C]. In Proceedings of the International Conference on Power Engineering, Energy and Electrical Drives,2007,405～410.
[60]Hefner A R. A dynamic electro-thermal model for the IGBT[J]. IEEE Transactions on Industry Applications,1994,30:394～405.
[61]Lu B, Hudgins J L, Bryant A T, et al. Expanded Thermal Model for IGBT Modules[C]. In Conference Record of the IEEE 41st IAS Annual Meeting,2006,2:777～784.
[62]Bonsbaine A, Trigkidis G, Benamrouche N. An integrated electro-thermal model of IGBT devices (experimental validation) [C]. In Proceedings of the 44th International Universities Power Engineering Conference (UPEC),2009,1～5.
[63]Sigg J, Turkes P, Kraus R. Parameter extraction methodology and validation for an electro-thermal physics-based NPT IGBT model [C]. In Conference Record of the IEEE 1997 IAS Annual Meeting,1997,2:1166～1173.
[64]Igic P M, Mawby P A, Towers M S. Physics-based dynamic electro-thermal models of power bipolar devices (PiN diode and IGBT) [C]. In Proceedings of the 13th International Symposium on Power Semiconductor Devices and ICs,2001,381～384.
[65]Reichl J, Berning D, Hefner A R, et al. Six-pack IGBT dynamic electro-thermal model: parameter extraction and validation[C]. In Proceedings of the IEEE 19th APEC,2004,1: 246～251.
[66]Chan-Su Y, Malberti P, Ciappa M, et al. Thermal component model for electrothermal analysis of IGBT module systems[J]. IEEE Transactions on Advanced Packaging,2001,24: 401～406.
[67]Fatemizadeh B, Silber D. A versatile electrical model for IGBT including thermal effects[C]. In Proceedings of the IEEE 24th PESC,1993,85～92.
[68]Forsyth A J, Yang S Y, Mawby P A, et al. Measurement and modelling of power electronic devices at cryogenic temperatures[C]. In IEE Proceedings of Circuits, Devices and Systems, 2006,407～415.
[69]Caiafa A, Snezhko A, Hudgins J L, et al. Physics-based modeling of NPT and PT IGBTs at deep cryogenic temperatures[C]. In Conference Record of the IEEE 39th IAS Annual Meeting,2004,4:2536～2541.
[70]Caiafa A, Wang X, Hudgins J L, et al. Cryogenic study and modeling of IGBTs[C]. In Proceedings of the IEEE 34th PESC,2003,4:1897～1903.
[71]Shen Y, Xiong Y, Jiang J, et al. Switching Loss Analysis and Modeling of Power Semiconductor Devices Base on an Automatic Measurement System[C]. In Proceedings of the 2006 IEEE International Symposium on Industrial Electronics,2006,853～858.
[72]Monti A. A fuzzy-based black-box approach to IGBT modelling, in Electronics[C]. In Proceedings of the Third IEEE International Conference on Circuits, and Systems,1996,2: 1147～1150.
[73]Baraia I, Galarza J, Barrena J A, et al. An IGBT behavioural model based on curve fitting methods[C]. In Proceedings of the IEEE 39th PESC,2008,1971～1977.
[74]刘恩科.半导体物理学.北京：电子工业出版社,2011.
[75]尼曼.半导体物理与器件.北京：电子工业出版社,2010.
[76]Jian C, Bharathan D, Emadi A. Efficiency and Loss Models for Key Electronic Components of Hybrid and Plug-in Hybrid Electric Vehicles' Electrical Propulsion Systems[C]. In Proceedings of the IEEE 2007 Vehicle Power and Propulsion Conference (VPPC),2007,477～482.
[77]Consoli A, Cacciato M, Testa A, et al. A SPICE behavioural model of PowerMESH IGBTs[C]. In Proceedings of the IEEE 35th PESC,2004,4:2983～2989.
[78]Cacciato M, Consoli A, Tagliavia D, et al. A Neural Network Based Behavioral Model of a Monolithic Cascode Power Switch[J]. Transactions of the Institute of Electrical Engineers of Japan,2001,27:764～769.
[79]Mitsubishi Electric IGBT Modules Application Note. Available:http://www.mitsubishielectric.com/cn
[80]富士IGBT模块应用手册.Available:http://www.fujielectric.com.cn/products/
[81]沈燕群.绝缘栅晶体管和功率二极管开关特性测试系统的研制：[学位论文].杭州：浙江大学,2006.
[82]王群京,陈权,姜卫东等.中点钳位型三电平逆变器通态损耗分析[J].电工技术学报,2007,22：66-90.
[83]Hagan M T, Demuth H B, Beale M H.神经网络设计(Neural Network Design).北京：机械工业出版社,2002.
[84]Haykin S神经网络原理(Neural Networks:A Comprehensive Foundation).北京：机械工业出版社,2004.
[85]飞思科技产品研发中心MATLAB辅助神经网络设计.北京：电子工业出版社,2003.
[86]王耀南.智能控制系统-模糊逻辑,专家系统,神经网络控制.湖南：湖南大学出版社,1996.
[87]蒋宗礼.人工神经网络导论.北京：高等教育出版社,2001.
[88]陈允平,王旭蕊,韩宝亮.人工神经网络原理及其应用.北京：中国电力出版社,2002.
[89]夏玫.BP神经网络泛化能力改进研究：[学位论文].太原：太原科技大学,2009.
[90]江学军,唐焕文.前馈神经网络泛化性能力的系统分析[J].系统工程理论与实践,2000,36-40.
[91]雷英杰,张善文,李续武等MATLAB遗传算法工具箱及应用.西安：西安电子科技大学出版社,2005.
[92]Kusum D, Singh K P, Kansal M L, et al. A real coded genetic algorithm for solving integer and mixed integer optimization problems[J]. Applied Mathematics and Computation,2009, 212:505～518.
[93]李勇平.基于改进粒子群神经网络的电信业务预测模型研究：[学位论文].广州：华南理工大学,2009.
[94]Ratnaweera A, Halgamuge S K,Watson H C. Self-organizing hierarchical particle swarm optimizer with time-vary ing acceleration coefficients [J]. IEEE Transactions on Evolutionary Computation,2004,8:240～255.
[95]Eberhart R C, Shi Y. Comparing inertia weights and constriction factors in particle swarm optimization[C]. In Proceedings of the 2000 Congress on Evolutionary Computation,2000, 1:84～88.
[96]Shi Y, Eberhart R C. Fuzzy adaptive particle swarm optimization[C]. In Proceedings of the 2001 Congress on Evolutionary Computation,2001,1:101～106.
[2]Kharitonov S A, Petrov M A, Korobkov D V, et al. A principle of calculation dynamic and static power losses with hard-switching IGBT[C]. In Proceedings of the 6th Annual Meeting of the International Siberian Workshop and Tutorials on Electron Devices and Materials. 2005,147-149.
[3]IGBT Power Losses Calculation Using the Data-Sheet Parameters. Available: http://www.infineon.com/cms/en/product/index.html
[4]Kurnia A, Cherradi H, Divan D M, Impact of IGBT behavior on design optimization of soft switching inverter topologies [J]. IEEE Transactions on Industry Applications,1995,31: 280-286.
[5]熊妍.绝缘栅晶体管和大功率二极管损耗建模方法的研究：[学位论文].杭州：浙江大学,2006.
[6]Ammous K, Allard B, Brevet O, et al. Error in estimation of power switching losses based on electrical measurements[C]. In Proceedings of the IEEE 31st PESC.2000,1:286-291.
[7]XYZs of Oscilloscopes:Operating the Oscilloscope. Available:www.tek.com/Measurement
[8]ABCs of Probes Primer. Available:www.tek.com/measurement
[9]Witcher J B. Methodology for Switching Characterization of Power Devices and Modules: [dissertation]. USA:Virginia Polytechnic Institute and State University,2002.
[10]BΦrge P. Modelling and Test of Power Semiconductors:[dissertation]. Denmark:Aalborg University,2004.
[11]Xu D, Huang L, Azuma S, et al. Power Loss and Junction Temperature Analysis of Power Semiconductor Devices[J]. IEEE Transactions on Industrial Application,2002, 38:1426-1431.
[12]Azuma S, Jiang X, Lu H, et al. Research on the Power Loss and Junction Temperature of Power Semiconductor Devices for Inverter[C]. In Proceedings of the IEEE IVEC'99 conference,1999,183-187.
[13]Munk-Nielsen S, Blaabjerg F, Pedersen J K. An advanced measurement system for verification of models and datasheets[C]. In Proceedings of the IEEE 4th Workshop on Computers in Power Electronics.1994,209～214.
[14]Li Y. Unified Zero-Current-Transition Techniques for High-Power Three-Phase PWM Inverters:[dissertation]. USA:Virginia Polytechnic Institute and State University,2002.
[15]Azzopardi S. A Systematic Hard-and Soft-Switching Performances Evaluation of 1200V Punchthrough IGBT Structures[J]. IEEE Transactions on Power Electronics,2004,19: 231-241.
[16]Petterteig A, Lode J, Undeland T M. IGBT Turn-off Losses for Hard Switching and with Capacitive Snubbers[C]. In Conference Record of the 1991 IEEE Industry Applications Society Annual Meeting,1991,1501～1507.
[17]Bernet S, Carroll E, Streit P, et al. Design, test and characteristics of 10 kV IGCTs[C]. In Conference Record of the 38th IAS Annual Meeting,2003,2:1012～1019.
[18]Yuan L, Zhao Z, Bai H, Li Chongjian, et al. The IGCT test platform for voltage source inverters[C]. In Proceedings of the IEEE 5th PEDS,2003,2:1291～1294.
[19]Ladoux P, Blaquiere J M, Alvarez S, et al. Test bench for the characterisation of experimental low voltage IGCTs[C]. In Proceedings of the IEEE 35th PESC,2004,4: 2937-2942.
[20]Lai J S, Leslie L, Ferrell J, et al. Characterization of HV-IGBT for High-Power Inverter Applications[C]. In Conference Record of the IEEE 40th IAS Annual Meeting,2005,1: 377-382.
[21]Yuan L, Zhao Z, Liu J, et al. Experiment and Analysis for Single IGCT Equipped in MV Three-level Inverter[C]. In Proc. of the IEEE 40th IAS Annual Meeting,2005,2:825～829.
[22]Munk N S, Blaabjerg F, Pedersen J K, An advanced measurement system for verification of models and datasheets[C]. In Proceedings of the IEEE 4th Workshop on Computers in Power Electronics,1994,209～214.
[23]Petterteig A, Lode J, Undeland T M. IGBT Turn-off Losses for Hard Switching and with Capacitive Snubbers[C]. In Conference Record of the IEEE IAS Annual Meeting,1991, 2:1501-1507.
[24]Lai J S, Leslie L, Ferrell J, et al. Characterization of HV-IGBT for High-Power Inverter Applications[C]. In Conference Record of the IEEE 40th IAS Annual Meeting,2005,1: 377～382.
[25]Wang K, Lee F C, Hua G. A Comparative Study of Switching Losses of IGBTs under Hard switching, Zero-voltage-switching and Zero-Current-Switching[C]. In Proceedings of the IEEE 25th PESC,1994,2:1196～1204.
[26]Yuan L, Zhao Z, Liu J, et al. Experiment and Analysis for Single IGCT Equipped in MV Three-level Inverter, in Industry Applications Conference [C]. In Conference Record of the IEEE 40th IAS Annual Meeting,2005,2:825～829.
[27]Yu Q, Li L, Jiang Q. High power electronic device measurements of four IGCTs (4.5 kV/4.0 kA) in series connection[C]. In Proceedings of the Fifth World Congress on Intelligent Control and Automation,2004,5:4446～4449.
[28]Kim S C, Kim H W, Seo K S, et al. Static and dynamic characteristics of the 2.5kV/500A IGCTs[C]. In Proceedings of the 24th International Conference on Microelectronics,2004, 1:171～173.
[29]Wang X, Lu L, Pytel S, et al. Multilevel device models developed for the virtual test bed (VTB)[C]. In Conference Record of the IEEE 39th IAS Annual Meeting,2004, 4:2528～2535.
[30]Yuan L, Zhao Z, Li C. The optimization of snubbers for IGCT-based voltage source inverters[C]. In Proceedings of the IEEE 29th IECON,2003,1:679～682.
[31]Wang J, Yang B, Zhao J, et al. Development of a compact 750KVA three-phase NPC three-level universal inverter module with specifically designed busbar[C]. In Proceedings of the IEEE 25th APEC,2010:1266～1271.
[32]杨兵建.基于IGBT的大功率三电平逆变器控制与测试方法等相关问题研究：[学位论文].杭州：浙江大学,2011.
[33]汪望.基于IGBT的750kVA三相二极管箝位型三电平通用变流模块设计：[学位论文].杭州：浙江大学,2010.
[34]Kuang S, Williams B W, Finney S J. A review of IGBT models[J]. IEEE Transactions on Power Electronics,2000,15:1250～1266.
[35]Hefner A R. Characterization and Modeling of the Power Insulated Gate Bipolar Transistor [dissertation]. Maryland:The University of Maryland,1987.
[36]Hefner A R, Jr., An improved understanding for the transient operation of the power insulated gate bipolar transistor (IGBT)[J]. IEEE Transactions on Power Electronics,1990, 5:459-468.
[37]Cavalcanti M C, da Silva E R, Boroyevich D, et al. A feasible loss model for IGBT in soft-switching inverters[C]. In Proceedings of the IEEE 34th PESC.2003,4:1845～1850.
[38]Cavalcanti M C, da Silva E R, Jacobina C B, et al. Comparative evaluation of losses in soft and hard-switched inverters[C]. In Conference Record of the IEEE 38th IAS Annual Meeting,2003,3:1912～1917.
[39]Claudio-Sanchez A, Li J M, Lafore D. Behaviour analysis of the IGBT in hard and soft switching modes by a soft modelling concept[C]. In Technical Proceedings of the 3rd International CIEP Power Electronics Congress,1994,101～107.
[40]Berning D W, Hefner A R. IGBT model validation for soft-switching applications[J]. IEEE Transactions on Industry Applications,2001,37:650～660.
[41]Stier S H, Mutschler P. An investigation of a reliable behavioral IGBT model in comparison to PSpice and measurement in hard and soft switching applications[C]. In Technical Proceedings of the 2005 European Conference on Power Electronics and Applications,2005,10 pp.-P.10.
[42]Trivedi M, Shenai K.Modeling the turn-off of IGBT's in hard- and soft-switching applications[J]. IEEE Transactions on Electron Devices,1997,44:887～893.
[43]Jinrong Q, Khan A, Batarseh I. Turn-off switching loss model and analysis of IGBT under different switching operation modes[C]. In Proceedings of the IEEE 21st IECON,1995,1: 240～245.
[44]Hefner A R. A dynamic electro-thermal model for the IGBT[C]. In Conference Record of the IEEE 1992 IAS Annual Meeting,1992,1:1094～1104.
[45]Hefner A R, Diebolt D M. An experimentally verified IGBT model implemented in the Saber circuit simulator[J]. IEEE Transactions on Power Electronics,1994,9:532～542.
[46]Hefner A R. Modeling buffer layer IGBTs for circuit simulation[J]. IEEE Transactions on Power Electronics,1995,10:111～123.
[47]Hefner A R, Diebolt D M. An experimentally verified IGBT model implemented in the Saber circuit simulator[C]. In Proceedings of the IEEE 22nd PESC,1991,10～19.
[48]Artamonov A, Nelayev V, Shelibak I, et al. IGBT technology design and device optimization[C]. In Proceedings of the 9th East-West Design & Test Symposium (EWDTS),2011,233～236.
[49]Shelibak I, Nelayev V, Artamonov A. Technology and electrical design of IGBT[C]. In Proceedings of the 18th International Conference in Mixed Design of Integrated Circuits and Systems (MIXDES),2011,562～564.
[50]Ammous A, Ammous K, Morel H, et al. Electrothermal modeling of IGBTs:application to short-circuit conditions[J]. IEEE Transactions on Power Electronics,2000,15:778-790.
[51]Elmazria O, Hoffmann A, Lepley B, et al. Simulation of electrons irradiation damages to optimize the performance of IGBT[J]. IEEE Transactions on Nuclear Science,1997,44: 14～19.
[52]Kang X, Santi E, Hudgins J L, et al. Parameter extraction for a physics-based circuit simulator IGBT model[C]. In Proceedings of the IEEE 18th APEC,2003,2:946～952.
[53]Cotorogea M, Claudio A, Rodriguez M A. Parameter extraction method for the Pspice model of the PT- and NPT-IGBT's by electrical measurements[C]. In Technical Proceedings of the IEEE International CIEP 2002 Power Electronics Congress,2002, 101-106.
[54]Musumeci S, Raciti A, Sardo M, et al. PT-IGBT PSpice model with new parameter extraction for life-time and epy dependent behaviour simulation[C]. In Proceedings of the IEEE 27th PESC,1996,2:1682～1688.
[55]Kang X, Caiafa A, Santi E, et al. Characterization and modeling of high-voltage field-stop IGBTs[C]. In Conference Record of the IEEE 37th IAS Annual Meeting,2002,3: 2175～2181.
[56]Tang Y, Chen M, Wang B. New methods for extracting field-stop IGBT model parameters by electrical measurements[C]. In Proceedings of the IEEE International Symposium on Industrial Electronics,2009,1546～1551.
[57]Kang X, Lu L, Wang X, et al. Characterization and modeling of the LPT CSTBT-the 5th generation IGBT[C]. In Conference Record of the IEEE 38th IAS Annual Meeting,2003,2: 982-987.
[58]Blaabjerg F, Pedersen J K, Sigurjonsson S, et al. An extended model of power losses in hard-switched IGBT-inverters[C]. In Conference Record of the IEEE 1996 IAS Annual Meeting,1996,3:1454～1463.
[59]Castellazzi A, Ciappa M, Fichtner W, et al. Comprehensive Electro-Thermal Compact Model of a 3.3kV-1200A IGBT-module[C]. In Proceedings of the International Conference on Power Engineering, Energy and Electrical Drives,2007,405～410.
[60]Hefner A R. A dynamic electro-thermal model for the IGBT[J]. IEEE Transactions on Industry Applications,1994,30:394～405.
[61]Lu B, Hudgins J L, Bryant A T, et al. Expanded Thermal Model for IGBT Modules[C]. In Conference Record of the IEEE 41st IAS Annual Meeting,2006,2:777～784.
[62]Bonsbaine A, Trigkidis G, Benamrouche N. An integrated electro-thermal model of IGBT devices (experimental validation) [C]. In Proceedings of the 44th International Universities Power Engineering Conference (UPEC),2009,1～5.
[63]Sigg J, Turkes P, Kraus R. Parameter extraction methodology and validation for an electro-thermal physics-based NPT IGBT model [C]. In Conference Record of the IEEE 1997 IAS Annual Meeting,1997,2:1166～1173.
[64]Igic P M, Mawby P A, Towers M S. Physics-based dynamic electro-thermal models of power bipolar devices (PiN diode and IGBT) [C]. In Proceedings of the 13th International Symposium on Power Semiconductor Devices and ICs,2001,381～384.
[65]Reichl J, Berning D, Hefner A R, et al. Six-pack IGBT dynamic electro-thermal model: parameter extraction and validation[C]. In Proceedings of the IEEE 19th APEC,2004,1: 246～251.
[66]Chan-Su Y, Malberti P, Ciappa M, et al. Thermal component model for electrothermal analysis of IGBT module systems[J]. IEEE Transactions on Advanced Packaging,2001,24: 401～406.
[67]Fatemizadeh B, Silber D. A versatile electrical model for IGBT including thermal effects[C]. In Proceedings of the IEEE 24th PESC,1993,85～92.
[68]Forsyth A J, Yang S Y, Mawby P A, et al. Measurement and modelling of power electronic devices at cryogenic temperatures[C]. In IEE Proceedings of Circuits, Devices and Systems, 2006,407～415.
[69]Caiafa A, Snezhko A, Hudgins J L, et al. Physics-based modeling of NPT and PT IGBTs at deep cryogenic temperatures[C]. In Conference Record of the IEEE 39th IAS Annual Meeting,2004,4:2536～2541.
[70]Caiafa A, Wang X, Hudgins J L, et al. Cryogenic study and modeling of IGBTs[C]. In Proceedings of the IEEE 34th PESC,2003,4:1897～1903.
[71]Shen Y, Xiong Y, Jiang J, et al. Switching Loss Analysis and Modeling of Power Semiconductor Devices Base on an Automatic Measurement System[C]. In Proceedings of the 2006 IEEE International Symposium on Industrial Electronics,2006,853～858.
[72]Monti A. A fuzzy-based black-box approach to IGBT modelling, in Electronics[C]. In Proceedings of the Third IEEE International Conference on Circuits, and Systems,1996,2: 1147～1150.
[73]Baraia I, Galarza J, Barrena J A, et al. An IGBT behavioural model based on curve fitting methods[C]. In Proceedings of the IEEE 39th PESC,2008,1971～1977.
[74]刘恩科.半导体物理学.北京：电子工业出版社,2011.
[75]尼曼.半导体物理与器件.北京：电子工业出版社,2010.
[76]Jian C, Bharathan D, Emadi A. Efficiency and Loss Models for Key Electronic Components of Hybrid and Plug-in Hybrid Electric Vehicles' Electrical Propulsion Systems[C]. In Proceedings of the IEEE 2007 Vehicle Power and Propulsion Conference (VPPC),2007,477～482.
[77]Consoli A, Cacciato M, Testa A, et al. A SPICE behavioural model of PowerMESH IGBTs[C]. In Proceedings of the IEEE 35th PESC,2004,4:2983～2989.
[78]Cacciato M, Consoli A, Tagliavia D, et al. A Neural Network Based Behavioral Model of a Monolithic Cascode Power Switch[J]. Transactions of the Institute of Electrical Engineers of Japan,2001,27:764～769.
[79]Mitsubishi Electric IGBT Modules Application Note. Available:http://www.mitsubishielectric.com/cn
[80]富士IGBT模块应用手册.Available:http://www.fujielectric.com.cn/products/
[81]沈燕群.绝缘栅晶体管和功率二极管开关特性测试系统的研制：[学位论文].杭州：浙江大学,2006.
[82]王群京,陈权,姜卫东等.中点钳位型三电平逆变器通态损耗分析[J].电工技术学报,2007,22：66-90.
[83]Hagan M T, Demuth H B, Beale M H.神经网络设计(Neural Network Design).北京：机械工业出版社,2002.
[84]Haykin S神经网络原理(Neural Networks:A Comprehensive Foundation).北京：机械工业出版社,2004.
[85]飞思科技产品研发中心MATLAB辅助神经网络设计.北京：电子工业出版社,2003.
[86]王耀南.智能控制系统-模糊逻辑,专家系统,神经网络控制.湖南：湖南大学出版社,1996.
[87]蒋宗礼.人工神经网络导论.北京：高等教育出版社,2001.
[88]陈允平,王旭蕊,韩宝亮.人工神经网络原理及其应用.北京：中国电力出版社,2002.
[89]夏玫.BP神经网络泛化能力改进研究：[学位论文].太原：太原科技大学,2009.
[90]江学军,唐焕文.前馈神经网络泛化性能力的系统分析[J].系统工程理论与实践,2000,36-40.
[91]雷英杰,张善文,李续武等MATLAB遗传算法工具箱及应用.西安：西安电子科技大学出版社,2005.
[92]Kusum D, Singh K P, Kansal M L, et al. A real coded genetic algorithm for solving integer and mixed integer optimization problems[J]. Applied Mathematics and Computation,2009, 212:505～518.
[93]李勇平.基于改进粒子群神经网络的电信业务预测模型研究：[学位论文].广州：华南理工大学,2009.
[94]Ratnaweera A, Halgamuge S K,Watson H C. Self-organizing hierarchical particle swarm optimizer with time-vary ing acceleration coefficients [J]. IEEE Transactions on Evolutionary Computation,2004,8:240～255.
[95]Eberhart R C, Shi Y. Comparing inertia weights and constriction factors in particle swarm optimization[C]. In Proceedings of the 2000 Congress on Evolutionary Computation,2000, 1:84～88.
[96]Shi Y, Eberhart R C. Fuzzy adaptive particle swarm optimization[C]. In Proceedings of the 2001 Congress on Evolutionary Computation,2001,1:101～106.