Predicting Power Requirement In Steel Manufacturing (EAF)

Problem

In the steel manufacturing industry, Electric Arc Furnace (EAF) and Ladle Refining Furnace (LRF) processes require substantial electrical power, supplied by captive power plants (CPPs). Striking a balance between power supply and the manufacturing demand is a complex task due to the variable nature of manufacturing processes and environmental factors. This often leads to surplus power generation, also known as “infirm power”.​

The challenge lies in aligning the power production of CPP with the fluctuating power demand of EAF and LRF. Factors such as the mix of raw materials, atmospheric conditions, and availability of material and assets for subsequent processes complicate this task. Additionally, the limited ramp-up or ramp-down time for power production in CPP can be longer than the 5-minute lead signal provided by the steel plant.

Approach

• Creating a 2-D digital map of the production process​
• Developing data connectors and pipelines for real-time and historical data integration​
• Creating a real-time dashboard for monitoring KPIs & material and equipment availability​
• Developing an AI based dynamic scheduling tool and  demand forecasting​
• Real time alerts by predicting power consumption and risks of schedule delays​

Benefits

• Improved Forecasting: Predict heat start and end times with a lead time of up to 10 minutes
• Reduced Surplus Power​: Reduced surplus infirm power production from 15 MW to 5 MW, leading towards zero​
• Cost Savings​: Savings of approx. $2 Million per year due to reduced infirm power​
• Power Production Alignment​: With improved forecasting, power production aligns with power demand​
• Operational Efficiency: Predictive insights reduced reactive decision-making causing inefficiencies​

Real-Time Visual Inspection of Ingot Defects for the World’s Second Largest Integrated Zinc-Lead Producer

Problem

The world’s second-largest integrated zinc-lead producer faced significant challenges with its ingot production process. With a high production rate of 600 ingots per hour, manual quality control (QC) became impractical and hazardous for workers. The company needed a solution to efficiently and safely inspect ingots for defects in real-time. 

Approach

To overcome the challenges, the company implemented an automated system using cutting-edge computer vision technology. The system was designed to capture defects at high speed, enabling real-time tracking of ingots. Leveraging SAP Business Technology Platform (BTP), a cloud-based deployment, the company ensured seamless scalability and integration with its existing infrastructure. 

Benefits

• Real-Time Defect Tracking: The implementation of the automated system allowed for real-time defect tracking, enabling immediate corrective actions to be taken. 
• Improved Insights: The system provided enhanced insights into raw material quality and production processes, leading to better control over operations and improved efficiency. 
• Live Link with Finished Goods: The solution established a live link with finished goods issuance, optimizing supply chain management and ensuring timely delivery of high-quality products to customers. 
• Enhanced Safety: By eliminating the need for manual quality control, the company improved worker safety in the ingot production process. 
• Increased Productivity: The automated system streamlined the inspection process, resulting in increased productivity and reduced inspection time. 

Overall, the implementation of the automated system with computer vision technology brought significant improvements in ingot quality control, safety, and production efficiency for the zinc-lead producer.