Researchers at SDLE use machine learning to better gauge failure of solar panels

A team of researchers at Case Western Reserve University's Solar Durability and Lifetime Extension (SDLE) Research Center has recently developed a new method towards increasing the lifetime of photovoltaic solar panels. Through the use of machine learning, the team was able to develop an algorithm that quickly processes thousands of images of solar panels that detail their wear over time and identify the issues that lead to failure.

Once the algorithm has been adequately trained, it can be used to predict when certain points of degradation will occur. This capability gives manufacturers the opportunity to improve the design of solar panels, allowing for longer use and, ultimately, lower costs. With the collaboration of various manufacturers and support from the Department of Energy (DOE), this is the first time that scientists are able to see the complete lifespan of the photovoltaic cells composing a solar panel. The DOE's Solar Energy Technologies Office has also highlighted this work as one of its "Success Stories".

Read more about the work being done at The Daily