pv magazine spoke with Fan Bin, founder of GCL Optoelectronics, about how high-throughput experimentation and AI-driven optimization are accelerating perovskite development, and why stability, and not efficiency, remains the key challenge on the path to mass production
According to GCL Optoelectronics, these perovskite modules have been tested over a two-year period and have shown no measurable degradation. The next step is to ensure comparable stability under scaled-up production conditions and higher manufacturing capacity.
Image: GCL Optoelectronics
Over the past decade, perovskite solar technology has seen remarkable progress both in terms of stability and efficiency, yet challenges remain on the path to commercialization. GCL Optoelectronics is now ramping up its first gigawatt-scale production line using the same technology, with initial capacity of 500 MW.
According to Fan Bin, founder of China’s GCL Optoelectronics, efficiency is no longer the primary hurdle. “Our best tandem modules have reached 29.5% in the lab, and we are targeting around 27% on the mass-production line. That is already very competitive compared to silicon,” he told pv magazine. “The main remaining challenge is stability.”
Even with meticulous manufacturing, achieving consistent stability at scale remains difficult. “Our modules can already pass the IEC 61215 standard, even at three times the test duration. But when we move to full-scale production, with one module produced every ten seconds, it is still a challenge to make sure that every module performs equally well,” Fan explained.
To tackle this, GCL Optoelectronics has turned to high-throughput experimentation and AI-based optimization. In their Singapore laboratory, the team operates a system capable of fabricating roughly 1,800 small one-inch cells per day and measuring their performance. This generates thousands of data points daily, which are then fed into AI models in a process known as active learning. Fan Bin describes the goal: “We hope that the AI can become predictive and eventually propose and test its own material changes. This is possible today because automation tools are much more advanced than they were 20 years ago,” Fan said.
The company collaborates with undisclosed partners from France, Germany, and China, integrating AI models like ChatGPT and Gemini into their workflow. While such tools are largely unnecessary in the silicon industry, they are proving invaluable for perovskite solar development, particularly in optimizing absorber materials, buffer layers, and passivation techniques.
GCL Optoelectronics also distinguishes itself through its four-terminal (4T) tandem approach. Unlike most solar manufacturers companies, which reportedly fabricate perovskite directly on top of silicon in a two-terminal (2T) configuration, Fan Bin’s team first produces large-area perovskite modules on glass and then combines them with silicon. “At an early stage, many people believed that producing square-meter-scale perovskite modules would be extremely difficult. Now we proved that it is possible. I think it is more complicated to fabricate perovskite directly on the texture of a silicon wafer,” he said. “For example, CATL is following a similar strategy, as are some Chinese display panel manufacturers entering the perovskite field.”
In terms of fabrication methods, small cells are produced using spin coating, but this method cannot be scaled for larger modules. Instead, GCL Optoelectronics relies on slot-die coating based entirely on solution processing. “Some groups are trying vacuum or sublimation methods, but perovskite formulations are very complex. Different components evaporate at different rates, which makes precise control extremely difficult. That is why we continue to rely on solution processing,” Fan concluded.
This content is protected by copyright and may not be reused. If you want to cooperate with us and would like to reuse some of our content, please contact: editors@pv-magazine.com.
More articles from Michael Fuhs
Please be mindful of our community standards.
Your email address will not be published. Required fields are marked *
Comment *
Name *
Email *
Website
Save my name, email, and website in this browser for the next time I comment.


Δ
By submitting this form you agree to pv magazine using your data for the purposes of publishing your comment.
Your personal data will only be disclosed or otherwise transmitted to third parties for the purposes of spam filtering or if this is necessary for technical maintenance of the website. Any other transfer to third parties will not take place unless this is justified on the basis of applicable data protection regulations or if pv magazine is legally obliged to do so.
You may revoke this consent at any time with effect for the future, in which case your personal data will be deleted immediately. Otherwise, your data will be deleted if pv magazine has processed your request or the purpose of data storage is fulfilled.
Further information on data privacy can be found in our Data Protection Policy.
Legal Notice Terms and Conditions Data Privacy © pv magazine 2026
Δ
This website uses cookies to anonymously count visitor numbers. View our privacy policy. ×
The cookie settings on this website are set to “allow cookies” to give you the best browsing experience possible. If you continue to use this website without changing your cookie settings or you click “Accept” below then you are consenting to this.
Close

source