Identifying Best Practice Melting Patterns in Induction Furnaces: A Data-Driven Approach Using Time Series KMeans Clustering and Multi-Criteria Decision Making
This addresses energy efficiency and cost reduction for foundries, but it is incremental as it applies existing data-driven methods to a specific industrial domain.
The paper tackled the problem of improving energy efficiency in induction furnaces by identifying optimal melting patterns, resulting in an 8.6% reduction in electricity costs through implementation of the best practice.
Improving energy efficiency in industrial production processes is crucial for competitiveness, and compliance with climate policies. This paper introduces a data-driven approach to identify optimal melting patterns in induction furnaces. Through time-series K-means clustering the melting patterns could be classified into distinct clusters based on temperature profiles. Using the elbow method, 12 clusters were identified, representing the range of melting patterns. Performance parameters such as melting time, energy-specific performance, and carbon cost were established for each cluster, indicating furnace efficiency and environmental impact. Multiple criteria decision-making methods including Simple Additive Weighting, Multiplicative Exponential Weighting, Technique for Order of Preference by Similarity to Ideal Solution, modified TOPSIS, and VlseKriterijumska Optimizacija I Kompromisno Resenje were utilized to determine the best-practice cluster. The study successfully identified the cluster with the best performance. Implementing the best practice operation resulted in an 8.6 % reduction in electricity costs, highlighting the potential energy savings in the foundry.