According to POSCO, the technology relies on an artificial intelligence that precisely controls zinc coating weights, even under changing operating conditions. It does so by predicting what the coating weight will be based on real-time operating variables and then adjusting those variables to ensure that the target coating weight is being met at any given moment.  

POSCO said that through a recently concluded production trial, the system demonstrated that it could keep coating weights to within 0.5 grams per square meter of the target weight. For comparison, the typical deviation when manually operating the production line used in the trial is around 7 grams per square meter, the company said.  

The technology was developed in conjunction with its mills, its research lab and Sungkyunkwan University professor Jon-seok Lee, a member of the university’s systems management engineering department. 

He is an expert in statistics, data mining, machine learning and optimization methodologies, POSCO said. Collaborating with company researchers, he created the coating weight model and algorithm that lies at the heart of the system. 

“This method operates in real time allowing the AI program to stay up-to-date by analyzing hundreds of different types of data generated during the plating process. It can accurately predict and control coating weight in real time, even if equipment has been replaced or operating conditions have changed,” POSCO said in a statement. 

The company ran a two-month beta test that began in July 2016, and once completed, company researchers incorporated additional quality control measures into the system and installed it on the No. 3 continuous galvanizing line at POSCO’s Gwangyang works for a production trial. 

The trial ended successfully, and POSCO has now fully integrated the technology into the line.  It’s planning to apply the technology to other galvanizing lines, and it’s looking for places that it can deploy artificial intelligence.   

“POSCO is also taking steps to introduce artificial intelligence technology to the manufacturing processes of other steel products while also continuing to build smart factories that can help POSCO continue to be a leader in the steel industry,” the company said. 

For instance, POSCO said the plate mill at the Gwangyang works plans to connect all of the components in the production process to a data integration system that can analyze operations and preemptively detect or predict abnormalities. Meanwhile, one of the hot strip mills at its Pohang works is incorporating smart technology relying on laser sensors and artificial intelligence.