Autoencoder-Based Iterative Modeling and Multivariate Time-Series Subsequence Clustering Algorithm
This paper introduces an algorithm for the detection of change-points and the identification of the corresponding subsequences in transient multivariate time-series data (MTSD). The analysis of such data has become increasingly important due to growing availability in many industrial fields. Labelin...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10049550/ |
| _version_ | 1811161976415453184 |
|---|---|
| author | Jonas Kohne Lars Henning Clemens Guhmann |
| author_facet | Jonas Kohne Lars Henning Clemens Guhmann |
| author_sort | Jonas Kohne |
| collection | DOAJ |
| description | This paper introduces an algorithm for the detection of change-points and the identification of the corresponding subsequences in transient multivariate time-series data (MTSD). The analysis of such data has become increasingly important due to growing availability in many industrial fields. Labeling, sorting or filtering highly transient measurement data for training Condition-based Maintenance (CbM) models is cumbersome and error-prone. For some applications it can be sufficient to filter measurements by simple thresholds or finding change-points based on changes in mean value and variation. But a robust diagnosis of a component within a component group for example, which has a complex non-linear correlation between multiple sensor values, a simple approach would not be feasible. No meaningful and coherent measurement data, which could be used for training a CbM model, would emerge. Therefore, we introduce an algorithm that uses a recurrent neural network (RNN) based Autoencoder (AE) which is iteratively trained on incoming data. The scoring function uses the reconstruction error and latent space information. A model of the identified subsequence is saved and used for recognition of repeating subsequences as well as fast offline clustering. For evaluation, we propose a new similarity measure based on the curvature for a more intuitive time-series subsequence clustering metric. A comparison with seven other state-of-the-art algorithms and eight datasets shows the capability and the increased performance of our algorithm to cluster MTSD online and offline in conjunction with mechatronic systems. |
| first_indexed | 2024-04-10T06:22:35Z |
| format | Article |
| id | doaj.art-4016c38050e146c3afa628ce1b891944 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-10T06:22:35Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-4016c38050e146c3afa628ce1b8919442023-03-02T00:00:39ZengIEEEIEEE Access2169-35362023-01-0111188681888610.1109/ACCESS.2023.324756410049550Autoencoder-Based Iterative Modeling and Multivariate Time-Series Subsequence Clustering AlgorithmJonas Kohne0https://orcid.org/0000-0001-5536-9604Lars Henning1https://orcid.org/0000-0001-6724-9781Clemens Guhmann2https://orcid.org/0000-0002-2865-0078Chair of Electronic Measurement and Diagnostic Technology, Technische Universität Berlin, Berlin, GermanyIAV GmbH, Berlin, GermanyChair of Electronic Measurement and Diagnostic Technology, Technische Universität Berlin, Berlin, GermanyThis paper introduces an algorithm for the detection of change-points and the identification of the corresponding subsequences in transient multivariate time-series data (MTSD). The analysis of such data has become increasingly important due to growing availability in many industrial fields. Labeling, sorting or filtering highly transient measurement data for training Condition-based Maintenance (CbM) models is cumbersome and error-prone. For some applications it can be sufficient to filter measurements by simple thresholds or finding change-points based on changes in mean value and variation. But a robust diagnosis of a component within a component group for example, which has a complex non-linear correlation between multiple sensor values, a simple approach would not be feasible. No meaningful and coherent measurement data, which could be used for training a CbM model, would emerge. Therefore, we introduce an algorithm that uses a recurrent neural network (RNN) based Autoencoder (AE) which is iteratively trained on incoming data. The scoring function uses the reconstruction error and latent space information. A model of the identified subsequence is saved and used for recognition of repeating subsequences as well as fast offline clustering. For evaluation, we propose a new similarity measure based on the curvature for a more intuitive time-series subsequence clustering metric. A comparison with seven other state-of-the-art algorithms and eight datasets shows the capability and the increased performance of our algorithm to cluster MTSD online and offline in conjunction with mechatronic systems.https://ieeexplore.ieee.org/document/10049550/Condition-based maintenancemultivariate time-series datachange point detectionunsupervised clusteringautoencodersegmentation |
| spellingShingle | Jonas Kohne Lars Henning Clemens Guhmann Autoencoder-Based Iterative Modeling and Multivariate Time-Series Subsequence Clustering Algorithm IEEE Access Condition-based maintenance multivariate time-series data change point detection unsupervised clustering autoencoder segmentation |
| title | Autoencoder-Based Iterative Modeling and Multivariate Time-Series Subsequence Clustering Algorithm |
| title_full | Autoencoder-Based Iterative Modeling and Multivariate Time-Series Subsequence Clustering Algorithm |
| title_fullStr | Autoencoder-Based Iterative Modeling and Multivariate Time-Series Subsequence Clustering Algorithm |
| title_full_unstemmed | Autoencoder-Based Iterative Modeling and Multivariate Time-Series Subsequence Clustering Algorithm |
| title_short | Autoencoder-Based Iterative Modeling and Multivariate Time-Series Subsequence Clustering Algorithm |
| title_sort | autoencoder based iterative modeling and multivariate time series subsequence clustering algorithm |
| topic | Condition-based maintenance multivariate time-series data change point detection unsupervised clustering autoencoder segmentation |
| url | https://ieeexplore.ieee.org/document/10049550/ |
| work_keys_str_mv | AT jonaskohne autoencoderbasediterativemodelingandmultivariatetimeseriessubsequenceclusteringalgorithm AT larshenning autoencoderbasediterativemodelingandmultivariatetimeseriessubsequenceclusteringalgorithm AT clemensguhmann autoencoderbasediterativemodelingandmultivariatetimeseriessubsequenceclusteringalgorithm |