Reducing False Alarms with Multi-modal Sensing for Pipeline Blockage (extended)

Reducing False Alarms with Multi-modal Sensing for Pipeline Blockage (extended). Zhang, C. & Heidemann, J. Technical Report ISI-TR-2013-686b, USC/Information Sciences Institute, June, 2013. (revised July 2013)

Paper abstract bibtex

Industrial sensing applications place a premium on cost-effectiveness and accuracy. Traditional approaches often use expensive, invasive sensors, because inexpensive sensors suffer from false positive detections. Sensor cost means automation is sparse or avoided when the value of specific sites cannot be justified. In this paper, we show combining different types of sensors can allow low-cost sensors to avoid false positives, enable much greater levels of automation in some applications. We explore this problem by studying a specific application: blockages in oil pipelines common in cold weather. We use pipe skin temperature to infer changes in fluid flow, and combine readings with acoustic data to avoid false positives and be robust to environmental changes. We demonstrate that our approach is effective with field experiments. Finally, suggest that this approach generalizes to other classes of problems where false positives from one sensing modality can be resolved by multi-modal sensing.

@TechReport{Zhang13b,
	author = 	"Chengjie Zhang and John Heidemann",
	title = 	"Reducing False Alarms with Multi-modal
                  Sensing for Pipeline Blockage (extended)",
	institution = 	"USC/Information Sciences Institute",
	year = 		2013,
	sortdate = "2013-06-01",
	project = "ilense, cisoft",
	jsubject = "sensornet_fusion",
	number =	"ISI-TR-2013-686b",
	month =		jun,
	note = "(revised July 2013)",
	location =	"johnh: pafile",
	keywords =	"sensornet, multi-sensor fusion, cold oil blockage, cisoft",
	url =		"http://www.isi.edu/%7ejohnh/PAPERS/Zhang13b.html",
	pdfurl =	"http://www.isi.edu/%7ejohnh/PAPERS/Zhang13b.pdf",
	myorganization =	"USC/Information Sciences Institute",
	copyrightholder = "authors",
	abstract = "Industrial sensing applications place a premium on cost-effectiveness
and accuracy.  Traditional approaches often use expensive, invasive
sensors, because inexpensive sensors suffer from false positive
detections.  Sensor cost means automation is sparse or avoided when
the value of specific sites cannot be justified.  In this paper, we
show combining different types of sensors can allow low-cost sensors
to avoid false positives, enable much greater levels of automation in
some applications.  We explore this problem by studying a specific
application:  blockages in oil pipelines common in cold weather.  We
use pipe skin temperature to infer changes in fluid flow, and combine
readings with acoustic data to avoid false positives and be robust to
environmental changes.  We demonstrate that our approach is effective
with field experiments.  Finally, suggest that this approach
generalizes to other classes of problems where false positives from
one sensing modality can be resolved by multi-modal sensing.",
}

Downloads: 0

{"_id":"cyn6FAFhhp9hXsyKG","bibbaseid":"zhang-heidemann-reducingfalsealarmswithmultimodalsensingforpipelineblockageextended-2013","author_short":["Zhang, C.","Heidemann, J."],"bibdata":{"bibtype":"techreport","type":"techreport","author":[{"firstnames":["Chengjie"],"propositions":[],"lastnames":["Zhang"],"suffixes":[]},{"firstnames":["John"],"propositions":[],"lastnames":["Heidemann"],"suffixes":[]}],"title":"Reducing False Alarms with Multi-modal Sensing for Pipeline Blockage (extended)","institution":"USC/Information Sciences Institute","year":"2013","sortdate":"2013-06-01","project":"ilense, cisoft","jsubject":"sensornet_fusion","number":"ISI-TR-2013-686b","month":"June","note":"(revised July 2013)","location":"johnh: pafile","keywords":"sensornet, multi-sensor fusion, cold oil blockage, cisoft","url":"http://www.isi.edu/%7ejohnh/PAPERS/Zhang13b.html","pdfurl":"http://www.isi.edu/%7ejohnh/PAPERS/Zhang13b.pdf","myorganization":"USC/Information Sciences Institute","copyrightholder":"authors","abstract":"Industrial sensing applications place a premium on cost-effectiveness and accuracy. Traditional approaches often use expensive, invasive sensors, because inexpensive sensors suffer from false positive detections. Sensor cost means automation is sparse or avoided when the value of specific sites cannot be justified. In this paper, we show combining different types of sensors can allow low-cost sensors to avoid false positives, enable much greater levels of automation in some applications. We explore this problem by studying a specific application: blockages in oil pipelines common in cold weather. We use pipe skin temperature to infer changes in fluid flow, and combine readings with acoustic data to avoid false positives and be robust to environmental changes. We demonstrate that our approach is effective with field experiments. Finally, suggest that this approach generalizes to other classes of problems where false positives from one sensing modality can be resolved by multi-modal sensing.","bibtex":"@TechReport{Zhang13b,\n\tauthor = \t\"Chengjie Zhang and John Heidemann\",\n\ttitle = \t\"Reducing False Alarms with Multi-modal\n Sensing for Pipeline Blockage (extended)\",\n\tinstitution = \t\"USC/Information Sciences Institute\",\n\tyear = \t\t2013,\n\tsortdate = \"2013-06-01\",\n\tproject = \"ilense, cisoft\",\n\tjsubject = \"sensornet_fusion\",\n\tnumber =\t\"ISI-TR-2013-686b\",\n\tmonth =\t\tjun,\n\tnote = \"(revised July 2013)\",\n\tlocation =\t\"johnh: pafile\",\n\tkeywords =\t\"sensornet, multi-sensor fusion, cold oil blockage, cisoft\",\n\turl =\t\t\"http://www.isi.edu/%7ejohnh/PAPERS/Zhang13b.html\",\n\tpdfurl =\t\"http://www.isi.edu/%7ejohnh/PAPERS/Zhang13b.pdf\",\n\tmyorganization =\t\"USC/Information Sciences Institute\",\n\tcopyrightholder = \"authors\",\n\tabstract = \"Industrial sensing applications place a premium on cost-effectiveness\nand accuracy. Traditional approaches often use expensive, invasive\nsensors, because inexpensive sensors suffer from false positive\ndetections. Sensor cost means automation is sparse or avoided when\nthe value of specific sites cannot be justified. In this paper, we\nshow combining different types of sensors can allow low-cost sensors\nto avoid false positives, enable much greater levels of automation in\nsome applications. We explore this problem by studying a specific\napplication: blockages in oil pipelines common in cold weather. We\nuse pipe skin temperature to infer changes in fluid flow, and combine\nreadings with acoustic data to avoid false positives and be robust to\nenvironmental changes. We demonstrate that our approach is effective\nwith field experiments. Finally, suggest that this approach\ngeneralizes to other classes of problems where false positives from\none sensing modality can be resolved by multi-modal sensing.\",\n}\n\n","author_short":["Zhang, C.","Heidemann, J."],"bibbaseid":"zhang-heidemann-reducingfalsealarmswithmultimodalsensingforpipelineblockageextended-2013","role":"author","urls":{"Paper":"http://www.isi.edu/%7ejohnh/PAPERS/Zhang13b.html"},"keyword":["sensornet","multi-sensor fusion","cold oil blockage","cisoft"],"metadata":{"authorlinks":{}}},"bibtype":"techreport","biburl":"https://bibbase.org/f/dHevizJoWEhWowz8q/johnh-2023-2.bib","dataSources":["YLyu3mj3xsBeoqiHK","fLZcDgNSoSuatv6aX","fxEParwu2ZfurScPY","7nuQvtHTqKrLmgu99"],"keywords":["sensornet","multi-sensor fusion","cold oil blockage","cisoft"],"search_terms":["reducing","false","alarms","multi","modal","sensing","pipeline","blockage","extended","zhang","heidemann"],"title":"Reducing False Alarms with Multi-modal Sensing for Pipeline Blockage (extended)","year":2013}