Intelligent Prediction Method for Heat Dissipation State of Converter Heatsink

Currently, the offline manual periodic detection method is a well-established practice in detecting thermal state of converter heatsink. This method, however, huge maintenance costs. To lower costs and improve efficiency dissipation state, this paper proposes an intelligent online prediction scheme based on Gauss-Newton iteration method. Firstly, power loss model module established according to characteristics IGBT FWD. The device then calculated real time with voltage current parameters converter. Next, transient heatsink thermodynamics theory. And calculation steady resistance proposed model. impedance data allow for timely characterize Finally, help DSP28377D, experimental platform built verify scheme. Results show that can realize online.