{"@type": "dcat:Dataset", "accessLevel": "public", "accrualPeriodicity": "irregular", "bureauCode": ["026:00"], "contactPoint": {"@type": "vcard:Contact", "fn": "Ashok Srivastava", "hasEmail": "mailto:ashok.n.srivastava@gmail.com"}, "description": "The environmental impact of aviation is enormous given the fact that\r\nin the US alone there are nearly 6 million flights per year of commercial aircraft.\r\nThis situation has driven numerous policy and procedural measures to help develop\r\nenvironmentally friendly technologies which are safe and affordable and reduce the\r\nenvironmental impact of aviation. However, many of these technologies require significant\r\ninitial investment in newer aircraft fleets and modifications to existing regulations\r\nwhich are both long and costly enterprises. We propose to use an anomaly\r\ndetection method based on Virtual Sensors to help detect overconsumption of fuel in\r\naircraft which relies only on the data recorded during flight of most existing commercial\r\naircraft, thus significantly reducing the cost and complexity of implementing this\r\nmethod. The Virtual Sensors developed here are ensemble-learning regression models\r\nfor detecting the overconsumption of fuel based on instantaneous measurements\r\nof the aircraft state. This approach requires no additional information about standard\r\noperating procedures or other encoded domain knowledge. We present experimental\r\nresults on three data sets and compare five different Virtual Sensors algorithms. The\r\nfirst two data sets are publicly available and consist of a simulated data set from a\r\nflight simulator and a real-world turbine disk.We show the ability to detect anomalies\r\nwith high accuracy on these data sets. These sets contain seeded faults, meaning that\r\nthey have been deliberately injected into the system. The second data set is from realworld\r\nfleet of 84 jet aircraft where we show the ability to detect fuel overconsumption\r\nwhich can have a significant environmental and economic impact. To the best of our\r\nknowledge, this is the first study of its kind in the aviation domain.", "distribution": [{"@type": "dcat:Distribution", "description": "Greener Aviation", "downloadURL": "https://c3.nasa.gov/dashlink/static/media/publication/Srivastava_DMKD_2012.pdf", "format": "PDF", "mediaType": "application/pdf", "title": "Srivastava DMKD 2012.pdf"}], "identifier": "DASHLINK_510", "issued": "2012-01-19", "keyword": ["ames", "dashlink", "nasa"], "landingPage": "https://c3.nasa.gov/dashlink/resources/510/", "modified": "2025-03-31", "programCode": ["026:029"], "publisher": {"@type": "org:Organization", "name": "Dashlink"}, "title": "Greener Aviation with Virtual Sensors:  A Case Study"}