Anomaly Detection Based on Time Series Data of Hydraulic Accumulator
Although hydraulic accumulators play a vital role in the hydraulic system, they face the challenges of being broken by continuous abnormal pulsating pressure which occurs due to the malfunction of hydraulic systems. Hence, this study develops anomaly detection algorithms to detect abnormalities of p...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-12-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/23/9428 |
| _version_ | 1797462145137377280 |
|---|---|
| author | Min-Ho Park Sabyasachi Chakraborty Quang Dao Vuong Dong-Hyeon Noh Ji-Woong Lee Jae-Ung Lee Jae-Hyuk Choi Won-Ju Lee |
| author_facet | Min-Ho Park Sabyasachi Chakraborty Quang Dao Vuong Dong-Hyeon Noh Ji-Woong Lee Jae-Ung Lee Jae-Hyuk Choi Won-Ju Lee |
| author_sort | Min-Ho Park |
| collection | DOAJ |
| description | Although hydraulic accumulators play a vital role in the hydraulic system, they face the challenges of being broken by continuous abnormal pulsating pressure which occurs due to the malfunction of hydraulic systems. Hence, this study develops anomaly detection algorithms to detect abnormalities of pulsating pressure for hydraulic accumulators. A digital pressure sensor was installed in a hydraulic accumulator to acquire the pulsating pressure data. Six anomaly detection algorithms were developed based on the acquired data. A threshold averaging algorithm over a period based on the averaged maximum/minimum thresholds detected anomalies 2.5 h before the hydraulic accumulator failure. In the support vector machine (SVM) and XGBoost model that distinguish normal and abnormal pulsating pressure data, the SVM model had an accuracy of 0.8571 on the test set and the XGBoost model had an accuracy of 0.8857. In a convolutional neural network (CNN) and CNN autoencoder model trained with normal and abnormal pulsating pressure images, the CNN model had an accuracy of 0.9714, and the CNN autoencoder model correctly detected the 8 abnormal images out of 11 abnormal images. The long short-term memory (LSTM) autoencoder model detected 36 abnormal data points in the test set. |
| first_indexed | 2024-03-09T17:32:19Z |
| format | Article |
| id | doaj.art-df61360ae912460cb332f0c22dc0bd12 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T17:32:19Z |
| publishDate | 2022-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-df61360ae912460cb332f0c22dc0bd122023-11-24T12:14:32ZengMDPI AGSensors1424-82202022-12-012223942810.3390/s22239428Anomaly Detection Based on Time Series Data of Hydraulic AccumulatorMin-Ho Park0Sabyasachi Chakraborty1Quang Dao Vuong2Dong-Hyeon Noh3Ji-Woong Lee4Jae-Ung Lee5Jae-Hyuk Choi6Won-Ju Lee7Division of Marine Engineering, Korea Maritime and Ocean University, Busan 49112, Republic of KoreaTerenz Co., Ltd., Busan 48060, Republic of KoreaDivision of Marine System Engineering, Korea Maritime and Ocean University, Busan 49112, Republic of KoreaHwajin Enterprise Co., Ltd., 25, Mieumsandan 2-ro, Gangseo-gu, Busan 46748, Republic of KoreaDivision of Marine System Engineering, Korea Maritime and Ocean University, Busan 49112, Republic of KoreaDivision of Marine System Engineering, Korea Maritime and Ocean University, Busan 49112, Republic of KoreaDivision of Marine System Engineering, Korea Maritime and Ocean University, Busan 49112, Republic of KoreaInterdisciplinary Major of Maritime and AI Convergence, Korea Maritime and Ocean University, Busan 49112, Republic of KoreaAlthough hydraulic accumulators play a vital role in the hydraulic system, they face the challenges of being broken by continuous abnormal pulsating pressure which occurs due to the malfunction of hydraulic systems. Hence, this study develops anomaly detection algorithms to detect abnormalities of pulsating pressure for hydraulic accumulators. A digital pressure sensor was installed in a hydraulic accumulator to acquire the pulsating pressure data. Six anomaly detection algorithms were developed based on the acquired data. A threshold averaging algorithm over a period based on the averaged maximum/minimum thresholds detected anomalies 2.5 h before the hydraulic accumulator failure. In the support vector machine (SVM) and XGBoost model that distinguish normal and abnormal pulsating pressure data, the SVM model had an accuracy of 0.8571 on the test set and the XGBoost model had an accuracy of 0.8857. In a convolutional neural network (CNN) and CNN autoencoder model trained with normal and abnormal pulsating pressure images, the CNN model had an accuracy of 0.9714, and the CNN autoencoder model correctly detected the 8 abnormal images out of 11 abnormal images. The long short-term memory (LSTM) autoencoder model detected 36 abnormal data points in the test set.https://www.mdpi.com/1424-8220/22/23/9428accumulatorpulsating pressure dataCNNautoencoderanomaly detection |
| spellingShingle | Min-Ho Park Sabyasachi Chakraborty Quang Dao Vuong Dong-Hyeon Noh Ji-Woong Lee Jae-Ung Lee Jae-Hyuk Choi Won-Ju Lee Anomaly Detection Based on Time Series Data of Hydraulic Accumulator Sensors accumulator pulsating pressure data CNN autoencoder anomaly detection |
| title | Anomaly Detection Based on Time Series Data of Hydraulic Accumulator |
| title_full | Anomaly Detection Based on Time Series Data of Hydraulic Accumulator |
| title_fullStr | Anomaly Detection Based on Time Series Data of Hydraulic Accumulator |
| title_full_unstemmed | Anomaly Detection Based on Time Series Data of Hydraulic Accumulator |
| title_short | Anomaly Detection Based on Time Series Data of Hydraulic Accumulator |
| title_sort | anomaly detection based on time series data of hydraulic accumulator |
| topic | accumulator pulsating pressure data CNN autoencoder anomaly detection |
| url | https://www.mdpi.com/1424-8220/22/23/9428 |
| work_keys_str_mv | AT minhopark anomalydetectionbasedontimeseriesdataofhydraulicaccumulator AT sabyasachichakraborty anomalydetectionbasedontimeseriesdataofhydraulicaccumulator AT quangdaovuong anomalydetectionbasedontimeseriesdataofhydraulicaccumulator AT donghyeonnoh anomalydetectionbasedontimeseriesdataofhydraulicaccumulator AT jiwoonglee anomalydetectionbasedontimeseriesdataofhydraulicaccumulator AT jaeunglee anomalydetectionbasedontimeseriesdataofhydraulicaccumulator AT jaehyukchoi anomalydetectionbasedontimeseriesdataofhydraulicaccumulator AT wonjulee anomalydetectionbasedontimeseriesdataofhydraulicaccumulator |