Close Menu
  • News
  • Industry
  • Solar Panels
  • Commercial
  • Residential
  • Finance
  • Technology
  • Carbon Credit
  • More
    • Policy
    • Energy Storage
    • Utility
    • Cummunity
What's Hot

Mitsubishi Electric Trane announces new heat pump line for hydronic heating – SPE

March 6, 2026

Origis is developing a 413 MW solar portfolio in West Texas

March 6, 2026

New Jersey expands state community solar program by 3 GW

March 6, 2026
Facebook X (Twitter) Instagram
Facebook X (Twitter) Instagram
Solar Energy News
Friday, March 6
  • News
  • Industry
  • Solar Panels
  • Commercial
  • Residential
  • Finance
  • Technology
  • Carbon Credit
  • More
    • Policy
    • Energy Storage
    • Utility
    • Cummunity
Solar Energy News
Home - Solar Industry - Improvement of roll-to-roll slot-die coating via machine learning
Solar Industry

Improvement of roll-to-roll slot-die coating via machine learning

solarenergyBy solarenergyAugust 14, 2025No Comments4 Mins Read
Facebook Twitter Pinterest LinkedIn Tumblr Email
Share
Facebook Twitter LinkedIn Pinterest Email

Researchers from the University of Sheffield developed a machine learning framework to improve the coating properties in a roll-to-roll slot that coating process. The work is seen as a first step in the direction of wider use of machine learning and related technologies to help with optimization.

August 14, 2025
Valerie Thompson

Researchers from the University of Sheffield in the United Kingdom have developed a machine learning framework to improve the coating properties in a roll-to-roll slot that coating process.

“Insofar as we know, this work is the first optimization of machine learning of roll-to-roll slot that coating, looking at changing fundamental coating parameters to improve coating performance,” said Christopher Passmore, corresponding author of the research, said PV -Magazine.

Glot that coating is used for the precise deposition of slurry fluids on different substrate materials to make thin films. The slurries used in the experiment, according to the researchers, were similar to those used to make thin films for solar energy, such as perovskite solar cells, as well as thin films for lithium-ion batteries and polymeer electrolytemmebran fuel cells.

The team selected radial basic function Neural Network (RBFNN) as the surrogate model, combined with a reference sector guided evolutionary algorithm (RVEA) to help with optimization.

Surrogate models are particularly effective when analytical models are not available, the scientists explained, which further indicates that surrogate optimization is “well suited” for slot-coating, because of the complexity of the process and the many interacting inputs and outputs.

The model was trained on a small experimental data set to be able to predict new optimal parameter sets. The slot die coating parameters in the model were as follows: substrate speed, pump speed, coating gap, shadow thickness and composition of coating solution.

See also  Oleic acid anti-pollution coating for solar panels – SPE

“When these new sets were tested experimental, they gave substantial improvements in coating properties. We also used predicted trends for machine learning to emphasize the impact of individual parameters on coating properties; something that was historically a challenge for complex coating formulases, often an extensive required in solar, PVVERAGEER.

The team discovered that the models predict coating thickness and uniformity with average absolute errors under 11.5 %.

It noted that the thick thickness and substrate speed had the greatest impact on the uniformity of the coating, while the Coating Gap played a lesser role. They said that the evolutionary algorithm “identified new business parameters, which led to improved coating properties.”

In comparison with traditional approaches of trial and error optimization, the surrogate model-assisted optimization offers a better understanding of closing that coating behavior in addition to offering fast and large improvements in coating properties, the researchers said.

The group regards the work as a “first step” in the direction of the “broader integration” of machine learning guidelines in a metrology and data-driven approach for optimizing slot-die-coating.

It also suggested a list of model improvements, such as the use of larger and more diverse training data sets, the use of other sampling technology to manage multivariate parameters and the possibility to repeat or replicate measurements in the event of selected parameter institutions to make “more accurate assessment” of process and measuring variety.

The researchers have the potential to record other coating properties, provided that the reliable metrology is available, the researchers said: “In addition, integration of additional parameters, such as substrate pre-treatment, concentration of surfactive substances and lock that sprout design in the algorithm and the use of Fundamentele Princesele Leren on the basis of Fundamentele-Lerenen based be improved by machine. “

See also  Hybrid Deep Learning Model for PV prediction in scenarios with considerable fluctuations - PV Magazine International

Users of both industrial and R&D-Slot-DIE coating equipment can benefit from the new methods to optimize coatings and a reliable way to quantify how good the coating is, according to Passmore.

The study is described in “Surrogate-assisted optimization of roll-to-roll slot that coating“In Natural science reports.

Looking at the upcoming research work, Passmore said that the team is investigating the production of colloidal crystals with large area and mesos scale structured thin films, with potential applications in photovoltaic and other opto-electronic devices.

This content is protected by copyright and may not be reused. If you want to work with us and reuse part of our content, please contact: editors@pv-magazine.com.

Popular content

Source link

coating Improvement learning machine rolltoroll slotdie
Share. Facebook Twitter Pinterest LinkedIn Tumblr Email
solarenergy
  • Website

Related Posts

How to address imbalance datasets in solar panel dust detection

March 5, 2026

Oleic acid anti-pollution coating for solar panels – SPE

March 5, 2026

Zelestra continues construction of two Texas projects

March 5, 2026
Leave A Reply Cancel Reply

Don't Miss
News

DCO decision on 500 MW solar park postponed until 2025

By solarenergyOctober 15, 20240

A map of the proposed development. Image: Ecotricity The Department for Energy Security and Net…

What happens when Type-C cracks affect photovoltaic modules?

February 17, 2026

Vertical floating PV installation comes online in Germany – SPE

October 13, 2025

Baywa.re receives planning permission for Ireland’s first solar park

September 2, 2024
Stay In Touch
  • Facebook
  • Twitter
  • Pinterest
  • Instagram
  • YouTube
  • Vimeo
Our Picks

Mitsubishi Electric Trane announces new heat pump line for hydronic heating – SPE

March 6, 2026

Origis is developing a 413 MW solar portfolio in West Texas

March 6, 2026

New Jersey expands state community solar program by 3 GW

March 6, 2026

How to address imbalance datasets in solar panel dust detection

March 5, 2026
Our Picks

Mitsubishi Electric Trane announces new heat pump line for hydronic heating – SPE

March 6, 2026

Origis is developing a 413 MW solar portfolio in West Texas

March 6, 2026

New Jersey expands state community solar program by 3 GW

March 6, 2026
About
About

Stay updated with the latest in solar energy. Discover innovations, trends, policies, and market insights driving the future of sustainable power worldwide.

Subscribe to Updates

Get the latest creative news and updates about Solar industry directly in your inbox!

Facebook X (Twitter) Instagram Pinterest
  • Contact
  • Privacy Policy
  • Terms & Conditions
© 2026 Tsolarenergynews.co - All rights reserved.

Type above and press Enter to search. Press Esc to cancel.