Successes to date
In terms of reimagining processes, one metals company is working with SAP to develop solutions in areas including process analysis, machine learning, predictive analytics and production planning. Another company is using machine learning and data analysis to optimize materials consumption during steel production. Yet another created an analytics center of excellence to encourage data-driven decision-making.
Barriers and how AI can help
With just 5 percent of metals companies pursuing breakthroughs across all three AI-related dimensions simultaneously, the barriers to progress loom large. Two challenges stand out. First, still widely misperceived as heavy, low-tech and environmentally unfriendly, it’s hard for the metals industry to attract innovative young talent. In reality, it is a highly complex and automated industry where precision is paramount. But this message isn’t getting across. Another challenge is the industry’s aging workforce and how to capture and retain these employees’ learning and knowledge before they retire.
AI and machine learning can help overcome these barriers. In the book, Human + Machine, the authors highlight the opportunity to empower people and machines to work together in new ways in the “missing middle”—the human/machine alliances and collaboration where each enhances and augments the capabilities of the other.
By getting experienced workers to teach smart machines, companies can capture their knowledge and apply it to improve processes. The missing middle also offers scope for machines to augment humans—making metals a safer and more fulfilling industry to work in by taking away the strain of physically hazardous and repetitive tasks.
Opportunities across the business
The focus of AI in metals will differ from other manufacturing industries. As a process-based industry, asset availability is critical, and the biggest risk is variability of production. The core focus of AI in metals will therefore be on managing continuous production processes to ensure equipment reliability and consistency. This means using AI in areas like tracking, predicting and managing quality, and eliminating variability by learning from historical data.
The opportunities for AI also extend into customer service—reimagining these processes, for example, by videoing a defect and using intelligent machines to identify the problem before the customer does. AI could also transform R&D for new products.
Finally, AI could reduce the need for crisis management by capturing and combining data and decades of experience to help humans make better decisions faster.