top of page




More steel manufacturers are shifting their focus from quantitative expansion to innovation in their manufacturing process to build an intelligent factory. They monitor the entire process from a manufacturing plan all the way to shipment not only to analyze the process but also to optimize the process based on the information by big data and AI. The technologies are used also to decrease product defective rate and enhance the flexibility in the production cycle. Thanks to the technologies, they are succeeding in establishing manufacturing environments that are very adaptive to the market needs.

BISTelligence optimizes the manufacturing system to alter the factory DNA. The AI technology supports our customers to adapt to the market changes in a preemptive manner. 

AI can learn many parameters and conditions in such stages of the process as hot rolling, cold rolling, and plating to control the product specifications and operation environments. Meaning, less quality fluctuation, and production loss.

Enhancing smart manufacturing by data analysis: With the help of data-based root cause analysis, engineers can respond to equipment and quality anomalies preemptively. The accumulated analysis information can enhance the production system. 


Use Case 1

AI-based root cause analysis of plate width shrinkage 

One of the most important inspection items for plate quality is product dimensions against the standards. For example, an inspector checks the plate width to determine if the plate shrunk or expanded. If a plate shrunk out of specifications, it cannot be shipped, many of which cases can critically impact the bottom line. When a width shrinkage case occurred in the rolling or annealing stage in the cold rolling process, the engineers must inspect the whole batch of products and analyze the root cause of the problem to properly respond to it. This takes the engineer team a significant period of time.

A plate that shows a big difference from the width standard due to shrinkage during the manufacturing process is considered a defective product. With big data technology, the engineers analyzed the root cause of this type of fault to get to decision-making fast, which enabled a proper response to the process fault in a timely manner.

Use Case 2

Root cause analysis of plate surface defects with big data

One of the most important inspection items for plate quality is defects on the plate surface. The goal of coil production is to yield products with consistent thickness, width, and especially with a smooth surface. No matter if the defects originate from environmental factors such as external particles or the process factors such as faults in the process, design data, and surface defects, the factors have a significant impact on the production of plates where consistent quality is necessary.

When a surface defect comes from the annealing stage of a cold rolling process, it is not only hard to detect but also to track the cause of it. The fact that a surface defect’s data lack the coordinates information makes the process analysis from various perspectives harder.

Big data analysis can detect patterns in surface defects. Based on these patterns shared by multiple defect cases, the engineer can find the root cause faster and reach a decision fast to execute a corrective action against the defects promptly.

Ask an Expert!

수채화 새 2
bottom of page