Condition monitoring for solder layer degradation in multi‐device system based on neural network
| Autor: | Sylvia Konaklieva, Olayiwola Alatise, Shengyou Xu, Paul McKeever, Borong Hu, Jose Ortiz-Gonzalez, Chong Ng, Li Ran |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
power module
multidevice system Computer science condition monitoring Energy Engineering and Power Technology 02 engineering and technology 01 natural sciences different constant current values power semiconductor devices temperature distribution condition monitoring method Reliability (semiconductor) multidevice systems uneven degradation 0103 physical sciences power losses 0202 electrical engineering electronic engineering information engineering Electronic engineering health condition parallel devices power rating solders stage NN 010302 applied physics reliability uneven solder layer degradation thermal resistance high power applications 020208 electrical & electronic engineering General Engineering Condition monitoring Semiconductor device multichip power modules Converters parallel chips translates failure analysis renewable energy Power (physics) neural nets current sharing Power rating lcsh:TA1-2040 degraded chips Power module multichip modules Constant current lcsh:Engineering (General). Civil engineering (General) higher thermal resistances two-stage neural network approach Software |
| Zdroj: | The Journal of Engineering (2019) |
| ISSN: | 2051-3305 |
| Popis: | Power semiconductor devices (chips) are usually arranged in parallel to increase the power rating of the modules for high power applications like renewable energy. In multi-device systems uneven degradation of the devices is inevitable. The uneven solder layer degradation of the parallel chips translates into higher thermal resistances for the degraded chips and, according to the electrothermal properties of the devices, the current sharing and temperature distribution between the devices will be affected. This phenomenon will have implications on the global reliability of the power module. In this study, a two-stage neural network (NN) approach is proposed for the diagnosis of the degradation: the first stage NN estimates the power losses of the parallel devices, whose deviations from the reference values are then applied to the NN in the second stage to classify the health condition. This condition monitoring method has been evaluated in on-state experiments at different constant current values, indicating that it could be a suitable strategy for improving the operational reliability of converters employing multi-chip power modules. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Plný text