Prognostic classification based on random convolutional kernel

TL;DR

This paper introduces the use of random convolutional kernel transforms, specifically ROCKET and MiniROCKET, for efficient and accurate health status classification of turbine engines using multi-sensor time-series data, outperforming deep learning methods.

Contribution

The paper presents a novel application of random convolutional kernels for health status classification, demonstrating high accuracy and efficiency on real-world datasets, and combining these features with traditional classifiers.

Findings

ROCKET and MiniROCKET achieve high accuracy in HS assessment.

The methods are significantly more efficient than deep learning models.

Feature combination with SVM and LDA enhances classification performance.

Abstract

Assessing the health status (HS) of system/component has long been a challenging task in the prognostic and health management (PHM) study. Differed from other regression based prognostic task such as predicting the remaining useful life, the HS assessment is essentially a multi class classificatIon problem. To address this issue, we introduced the random convolutional kernel-based approach, the RandOm Convolutional KErnel Transforms (ROCKET) and its latest variant MiniROCKET, in the paper. We implement ROCKET and MiniROCKET on the NASA's CMPASS dataset and assess the turbine fan engine's HS with the multi-sensor time-series data. Both methods show great accuracy when tackling the HS assessment task. More importantly, they demonstrate considerably efficiency especially compare with the deep learning-based method. We further reveal that the feature generated by random convolutional kernel can be combined with other classifiers such as support vector machine (SVM) and linear discriminant analysis (LDA). The newly constructed method maintains the high efficiency and outperforms all the other deop neutal network models in classification accuracy.