SAVSDN: A Scene-Aware Video Spark Detection Network for Aero Engine Intelligent Test
Due to carbon deposits, lean flames, or damaged metal parts, sparks can occur in aero engine chambers. At present, the detection of such sparks deeply depends on laborious manual work. Considering that interference has the same features as sparks, almost all existing object detectors cannot replace...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-06-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/13/4453 |
| _version_ | 1827688539911880704 |
|---|---|
| author | Jie Kou Xinman Zhang Yuxuan Huang Cong Zhang |
| author_facet | Jie Kou Xinman Zhang Yuxuan Huang Cong Zhang |
| author_sort | Jie Kou |
| collection | DOAJ |
| description | Due to carbon deposits, lean flames, or damaged metal parts, sparks can occur in aero engine chambers. At present, the detection of such sparks deeply depends on laborious manual work. Considering that interference has the same features as sparks, almost all existing object detectors cannot replace humans in carrying out high-precision spark detection. In this paper, we propose a scene-aware spark detection network, consisting of an information fusion-based cascading video codec-image object detector structure, which we name SAVSDN. Unlike video object detectors utilizing candidate boxes from adjacent frames to assist in the current prediction, we find that efforts should be made to extract the spatio-temporal features of adjacent frames to reduce over-detection. Visualization experiments show that SAVSDN can learn the difference in spatio-temporal features between sparks and interference. To solve the problem of a lack of aero engine anomalous spark data, we introduce a method to generate simulated spark images based on the Gaussian function. In addition, we publish the first simulated aero engine spark data set, which we name SAES. In our experiments, SAVSDN far outperformed state-of-the-art detection models for spark detection in terms of five metrics. |
| first_indexed | 2024-03-10T09:57:11Z |
| format | Article |
| id | doaj.art-e9e77d43c0ac4179ae58efb8519de13d |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T09:57:11Z |
| publishDate | 2021-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-e9e77d43c0ac4179ae58efb8519de13d2023-11-22T02:14:59ZengMDPI AGSensors1424-82202021-06-012113445310.3390/s21134453SAVSDN: A Scene-Aware Video Spark Detection Network for Aero Engine Intelligent TestJie Kou0Xinman Zhang1Yuxuan Huang2Cong Zhang3School of Electronic and Information Engineering, MOE Key Lab for Intelligent Networks and Network Security, Xi’an Jiaotong University, Xi’an 710049, ChinaSchool of Electronic and Information Engineering, MOE Key Lab for Intelligent Networks and Network Security, Xi’an Jiaotong University, Xi’an 710049, ChinaSchool of Electronic and Information Engineering, MOE Key Lab for Intelligent Networks and Network Security, Xi’an Jiaotong University, Xi’an 710049, ChinaAECC Sichuan Gas Turbine Establishment, Mianyang 621000, ChinaDue to carbon deposits, lean flames, or damaged metal parts, sparks can occur in aero engine chambers. At present, the detection of such sparks deeply depends on laborious manual work. Considering that interference has the same features as sparks, almost all existing object detectors cannot replace humans in carrying out high-precision spark detection. In this paper, we propose a scene-aware spark detection network, consisting of an information fusion-based cascading video codec-image object detector structure, which we name SAVSDN. Unlike video object detectors utilizing candidate boxes from adjacent frames to assist in the current prediction, we find that efforts should be made to extract the spatio-temporal features of adjacent frames to reduce over-detection. Visualization experiments show that SAVSDN can learn the difference in spatio-temporal features between sparks and interference. To solve the problem of a lack of aero engine anomalous spark data, we introduce a method to generate simulated spark images based on the Gaussian function. In addition, we publish the first simulated aero engine spark data set, which we name SAES. In our experiments, SAVSDN far outperformed state-of-the-art detection models for spark detection in terms of five metrics.https://www.mdpi.com/1424-8220/21/13/4453video object detectionsmall object detectionspark detectionvideo codecdeep ConvLSTM networkaero engine intelligent test |
| spellingShingle | Jie Kou Xinman Zhang Yuxuan Huang Cong Zhang SAVSDN: A Scene-Aware Video Spark Detection Network for Aero Engine Intelligent Test Sensors video object detection small object detection spark detection video codec deep ConvLSTM network aero engine intelligent test |
| title | SAVSDN: A Scene-Aware Video Spark Detection Network for Aero Engine Intelligent Test |
| title_full | SAVSDN: A Scene-Aware Video Spark Detection Network for Aero Engine Intelligent Test |
| title_fullStr | SAVSDN: A Scene-Aware Video Spark Detection Network for Aero Engine Intelligent Test |
| title_full_unstemmed | SAVSDN: A Scene-Aware Video Spark Detection Network for Aero Engine Intelligent Test |
| title_short | SAVSDN: A Scene-Aware Video Spark Detection Network for Aero Engine Intelligent Test |
| title_sort | savsdn a scene aware video spark detection network for aero engine intelligent test |
| topic | video object detection small object detection spark detection video codec deep ConvLSTM network aero engine intelligent test |
| url | https://www.mdpi.com/1424-8220/21/13/4453 |
| work_keys_str_mv | AT jiekou savsdnasceneawarevideosparkdetectionnetworkforaeroengineintelligenttest AT xinmanzhang savsdnasceneawarevideosparkdetectionnetworkforaeroengineintelligenttest AT yuxuanhuang savsdnasceneawarevideosparkdetectionnetworkforaeroengineintelligenttest AT congzhang savsdnasceneawarevideosparkdetectionnetworkforaeroengineintelligenttest |