Leveraging Real-Time Data Analysis and Multiple Kernel Learning for Manufacturing of Innovative Steels

2025-05-16

AI Summary

In steel manufacturing, thermal spray coating quality is difficult to control, and existing rework standardization fails to align with dynamic process requirements. Method: This paper proposes a real-time, data-driven predictive quality control method tailored for the Thermal Spray Coating Surface Manufacturing (TCCSM) process. It innovatively integrates a lightweight multi-kernel learning (MKL) quality predictor with a sensor–flow-control co-designed data aggregator, incorporating real-time sensor networks, edge-based data processing, MKL modeling, and millisecond-scale anomaly alerting. Contribution/Results: Small-scale validation demonstrates significantly improved coating quality prediction accuracy and critical process deviation detection latency under 10 ms, enabling timely operator intervention. To our knowledge, this is the first system to realize a lightweight, real-time closed-loop of “perception–analysis–alerting–regulation” in thermal spray coating processes, establishing a novel paradigm for surface engineering quality management under high-dynamic conditions in smart manufacturing.

Technology Category

• Machine Learning: Time-Series/Data Streams
• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Multiagent Systems: Coordination and Collaboration

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Data management and stream processing for Web, mobile and wireless applications
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

The implementation of thermally sprayed components in steel manufacturing presents challenges for production and plant maintenance. While enhancing performance through specialized surface properties, these components may encounter difficulties in meeting modified requirements due to standardization in the refurbishment process. This article proposes updating the established coating process for thermally spray coated components for steel manufacturing (TCCSM) by integrating real-time data analytics and predictive quality management. Two essential components--the data aggregator and the quality predictor--are designed through continuous process monitoring and the application of data-driven methodologies to meet the dynamic demands of the evolving steel landscape. The quality predictor is powered by the simple and effective multiple kernel learning strategy with the goal of realizing predictive quality. The data aggregator, designed with sensors, flow meters, and intelligent data processing for the thermal spray coating process, is proposed to facilitate real-time analytics. The performance of this combination was verified using small-scale tests that enabled not only the accurate prediction of coating quality based on the collected data but also proactive notification to the operator as soon as significant deviations are identified.

Problem

• Challenges in thermally sprayed steel component production and maintenance
• Standardized refurbishment limits meeting modified performance requirements
• Real-time data analytics for predictive quality management in coatings

Innovation

• Real-time data analytics for thermal spray coating
• Multiple kernel learning for predictive quality
• Sensor-based data aggregator for process monitoring