Modeling method for predicting switching loss in dynamic process of IGBT

Abstract

The invention relates to a modeling method for predicting switching loss in an IGBT dynamic process. The method is an IGBT switching loss prediction method based on an optimal krill swarm optimization extreme learning machine, and comprises the following steps: firstly, acquiring IGBT dynamic characteristic test data; secondly, after test data processing and basic parameter setting of the extreme learning machine and the krill swarm algorithm are completed, optimizing an initial krill swarm through a good point set algorithm to serve as a weight threshold value of the extreme learning machine, and calculating good point krill fitness; in the optimizing process, continuously updating the positions of the krill by taking Levy flight and cosine control factors as wings, and calculating the fitness of the krill until the optimization is finished; and finally, according to the optimal weight threshold value of the extreme learning machine found by the optimal krill, predicting and outputting IGBT on-off loss values. Dynamic adjustment is carried out on algorithm optimization, so that the prediction precision of the prediction model is high, the prediction speed is high, and the prediction result has good guiding significance for an engineer to improve a heat dissipation system of the IGBT module and the like.

Description

technical field [0001] The technical scheme of the invention belongs to the technical field of IGBT reliability of power electronic devices, specifically a modeling method for switching loss prediction in the dynamic process of IGBT. Background technique [0002] With the continuous aggravation of the energy crisis, the continuous development of power electronic technology has effectively promoted the progress and development of society. IGBT, as a modern power electronic switch, is widely used in power systems, electric vehicles and high-speed traction and other fields. However, the faults of photovoltaic inverters with IGBT as the core account for about 37% of the total faults. Among the failures of power electronic systems, the failures caused by temperature account for about 55% of the total failures, and there is a negative correlation between the temperature of the device and its safety margin and thermal cycle life. The occurrence of faults seriously affects the nor...

AI Technical Summary

Problems solved by technology

First of all, the switching loss calculation based on the physical model is to use the simulation software to simulate the dynamic characteristics of the IGBT, and then calculate the switching loss of the IGBT. The calculation result is more accurate, but the process of building the model is more complicated and the simulation speed is slower; the second is The switching loss calculation based on the mathematical model, the common method is to consult the IGBT technical manual to calculate the switching loss, but the calculated value is very different from the actual value, and although the polynomial model has improved the prediction accuracy, the prediction speed is relatively slow; finally, based on The switching loss prediction of the intelligent model has improved the prediction accuracy and prediction speed compared with the former two. However, in terms of parameter selection of the intelligent model, if the parameter selection is improper, the intelligent model will fall into the local optimal solution, which is not conducive to the model to find the global optimal solution. Excellent solution

[0005] Therefore, the prediction accuracy of existing measurement methods is not high, and the selection of optimal intelligent model parameters to predict IGBT switching loss and other issues

Images