Industrial Data Denoising via Low-Rank and Sparse Representations and Its Application in Tunnel Boring Machine

Abstract

The operation data of a tunnel boring machine (TBM) reflects its geological conditions and working status, which can provide critical references and essential information for TBM designers and operators. However, in practice, operation data may get corrupted due to equipment failures or data management errors. Moreover, the working state of a TBM system usually changes, which results in patterns of operation data that vary comparatively. This paper proposes a denoising approach to process the corrupted data. This approach is combined with low-rank matrix recovery (LRMR) and sparse representation (SR) theory. The classical LRMR model requires that the noise must be sparse, but the sparsity of noise cannot be fully guaranteed. In the proposed model, a weighted nuclear norm is utilized to enhance the sparsity of sparse components, and a constraint of condition number is applied to ensure the stability of the model solution. The approach is coupled with a fuzzy c-means algorithm (FCM) to find the natural partitioning using the TBM operation data as input. The performances of the proposed approach are illustrated through an application to the Shenzhen metro. Experimental results show that the proposed approach performs well in corrupted TBM data denoising. The different excavation status of the TBM recognition accuracy is improved remarkably after denoising.