Automated groove identification and measurement using long short-term memory unit. (July 2019)
- Record Type:
- Journal Article
- Title:
- Automated groove identification and measurement using long short-term memory unit. (July 2019)
- Main Title:
- Automated groove identification and measurement using long short-term memory unit
- Authors:
- Zhixing Cai, A.
Lin Li, B.
Yuping Hu, C.
Wenting Luo, D.
Chunmian Lin, E. - Abstract:
- Highlights: GrooveNet model is initiated to identify out potential dips on airport runways. Moving bounding box is proposed to locate the two endpoints of each identified dip. Naïve Bayes classifier is modified to separate out runway grooves and slab joints. GrooveNet and modified Naïve Bayes classifier are better than the existing methods. Abstract: Transverse grooves have been widely used on airport runways to improve their drainage capacity and skid resistance. Therefore, regular measurement and evaluation of groove dimensions on airport runways are significant for runways to improve skid resistance and eliminate hydroplaning risks. However, there are few effective methods that are able to automatically and accurately measure groove dimension. This study introduces a new method for automated groove identification and measurement using Long Short-term Memory (LSTM). The GrooveNet is designed to identify the potential dip and determine two endpoints of the identified dip. Subsequently, dip dimension is calculated according to FAA AC No. 150/5320-12C. Finally, the modified Naïve Bayes classifier is proposed to distinguish grooves and slab joints. Results indicate that the proposed methodology (including GrooveNet and modified Naïve Bayes classifier) is more robust and accurate in runway groove identification and measurement. With the proposed approach, operators of airfield runway pavements have a robust tool to conduct groove safety evaluation and further provide correctiveHighlights: GrooveNet model is initiated to identify out potential dips on airport runways. Moving bounding box is proposed to locate the two endpoints of each identified dip. Naïve Bayes classifier is modified to separate out runway grooves and slab joints. GrooveNet and modified Naïve Bayes classifier are better than the existing methods. Abstract: Transverse grooves have been widely used on airport runways to improve their drainage capacity and skid resistance. Therefore, regular measurement and evaluation of groove dimensions on airport runways are significant for runways to improve skid resistance and eliminate hydroplaning risks. However, there are few effective methods that are able to automatically and accurately measure groove dimension. This study introduces a new method for automated groove identification and measurement using Long Short-term Memory (LSTM). The GrooveNet is designed to identify the potential dip and determine two endpoints of the identified dip. Subsequently, dip dimension is calculated according to FAA AC No. 150/5320-12C. Finally, the modified Naïve Bayes classifier is proposed to distinguish grooves and slab joints. Results indicate that the proposed methodology (including GrooveNet and modified Naïve Bayes classifier) is more robust and accurate in runway groove identification and measurement. With the proposed approach, operators of airfield runway pavements have a robust tool to conduct groove safety evaluation and further provide corrective maintenance actions for the unsafe runway grooves. … (more)
- Is Part Of:
- Measurement. Volume 141(2019)
- Journal:
- Measurement
- Issue:
- Volume 141(2019)
- Issue Display:
- Volume 141, Issue 2019 (2019)
- Year:
- 2019
- Volume:
- 141
- Issue:
- 2019
- Issue Sort Value:
- 2019-0141-2019-0000
- Page Start:
- 152
- Page End:
- 161
- Publication Date:
- 2019-07
- Subjects:
- LSTM -- Runway groove -- Slab joint -- Naïve Bayes classifier -- GrooveNet
Weights and measures -- Periodicals
Measurement -- Periodicals
Measurement
Weights and measures
Periodicals
530.8 - Journal URLs:
- http://www.sciencedirect.com/science/journal/02632241 ↗
http://www.elsevier.com/journals ↗ - DOI:
- 10.1016/j.measurement.2019.03.071 ↗
- Languages:
- English
- ISSNs:
- 0263-2241
- Deposit Type:
- Legaldeposit
- View Content:
- Available online (eLD content is only available in our Reading Rooms) ↗
- Physical Locations:
- British Library DSC - 5413.544700
British Library DSC - BLDSS-3PM
British Library HMNTS - ELD Digital store - Ingest File:
- 10533.xml