Towards Deep Industrial Transfer Learning: Clustering for Transfer Case Selection

TL;DR

This paper proposes a clustering-based method, specifically using BIRCH, for selecting transfer cases in industrial transfer learning, demonstrating its effectiveness on manufacturing time series data.

Contribution

It introduces a novel clustering approach for transfer case selection in industrial transfer learning, validated with reproducible results on real-world data.

Findings

BIRCH clustering is effective for transfer case selection.

The method is robust to dataset sequence, size, and dimensionality.

Results show improved transfer learning performance in industrial scenarios.

Abstract

Industrial transfer learning increases the adaptability of deep learning algorithms towards heterogenous and dynamic industrial use cases without high manual efforts. The appropriate selection of what to transfer can vastly improve a transfer's results. In this paper, a transfer case selection based upon clustering is presented. Founded on a survey of clustering algorithms, the BIRCH algorithm is selected for this purpose. It is evaluated on an industrial time series dataset from a discrete manufacturing scenario. Results underline the approaches' applicability caused by its results' reproducibility and practical indifference to sequence, size and dimensionality of (sub-)datasets to be clustered sequentially.