{"id":21057,"date":"2023-05-08T13:02:34","date_gmt":"2023-05-08T11:02:34","guid":{"rendered":"https:\/\/nr.no\/en\/?post_type=bc_project&#038;p=21057"},"modified":"2024-04-11T09:55:19","modified_gmt":"2024-04-11T07:55:19","slug":"tilstandsovervakning-i-vind-og-vannkraftverk","status":"publish","type":"bc_project","link":"https:\/\/nr.no\/en\/projects\/tilstandsovervakning-i-vind-og-vannkraftverk\/","title":{"rendered":"Anomaly detection in wind and hydropower plants\u00a0\u00a0"},"content":{"rendered":"\n<div class=\"wp-block-columns is-layout-flex wp-container-core-columns-is-layout-28f84493 wp-block-columns-is-layout-flex\">\n<div class=\"wp-block-column is-layout-flow wp-block-column-is-layout-flow\" style=\"flex-basis:66.66%\">\n<p><\/p>\n\n\n\n<p class=\"has-sizing-large\"><strong>Wind and hydropower plants can become more efficient by minimizing downtime due to wear and maintenance.<\/strong>&nbsp;<\/p>\n\n\n\n<p><\/p>\n\n\n\n<div class=\"wp-block-media-text alignwide is-stacked-on-mobile\" style=\"grid-template-columns:32% auto\"><figure class=\"wp-block-media-text__media\"><img loading=\"lazy\" decoding=\"async\" width=\"683\" height=\"1024\" src=\"https:\/\/nr.no\/en\/content\/uploads\/sites\/2\/2023\/05\/Wind_turbine_maintenance-683x1024.jpg\" alt=\"Hydro and wind power plants can become more efficient by minimizing downtime due to wear and maintenance \" class=\"wp-image-21082 size-full\" srcset=\"https:\/\/nr.no\/content\/uploads\/sites\/2\/2023\/05\/Wind_turbine_maintenance-683x1024.jpg 683w, https:\/\/nr.no\/content\/uploads\/sites\/2\/2023\/05\/Wind_turbine_maintenance-200x300.jpg 200w, https:\/\/nr.no\/content\/uploads\/sites\/2\/2023\/05\/Wind_turbine_maintenance-768x1152.jpg 768w, https:\/\/nr.no\/content\/uploads\/sites\/2\/2023\/05\/Wind_turbine_maintenance-1024x1536.jpg 1024w, https:\/\/nr.no\/content\/uploads\/sites\/2\/2023\/05\/Wind_turbine_maintenance-scaled.jpg 1366w\" sizes=\"auto, (max-width: 683px) 100vw, 683px\" \/><\/figure><div class=\"wp-block-media-text__content\">\n<p>In this project we are developing methods for condition monitoring of hydro and wind turbines, based on sensors that measure temperature, pressure, and vibration, among other things. This way, serious and costly faults in the facilities can be detected before they occur and corrected within weeks rather than years.&nbsp;<\/p>\n\n\n\n\n\n<p class=\"has-sizing-small\"><em>Hydro and wind power plants can become more efficient by minimizing downtime due to wear and maintenance (Photo: Harald Danielsen).&nbsp;<\/em><\/p>\n<\/div><\/div>\n\n\n\n\n\n<h2 class=\"wp-block-heading\">The anomaly detection method consists of two basic steps:&nbsp;<\/h2>\n\n\n\n<div class=\"wp-block-group\">\n<ul class=\"wp-block-list\">\n<li>A prediction model for how the sensor measurements should behave given information about how the turbine is operated at any given time (e.g., the amount of guide vane opening).\u00a0<\/li>\n\n\n\n<li>A model for detecting deviations from the estimated normal behavior.&nbsp;<\/li>\n<\/ul>\n<\/div>\n\n\n\n<p><\/p>\n\n\n\n<figure class=\"wp-block-image size-large is-resized\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"537\" src=\"https:\/\/nr.no\/content\/uploads\/sites\/2\/2023\/05\/anomaly_illustration-1024x537.png\" alt=\"Anomalies are detected as large differences between predicted and observed sensor measurements.\" class=\"wp-image-21080\" style=\"aspect-ratio:1.9068901303538175;width:666px;height:auto\" srcset=\"https:\/\/nr.no\/content\/uploads\/sites\/2\/2023\/05\/anomaly_illustration-1024x537.png 1024w, https:\/\/nr.no\/content\/uploads\/sites\/2\/2023\/05\/anomaly_illustration-300x157.png 300w, https:\/\/nr.no\/content\/uploads\/sites\/2\/2023\/05\/anomaly_illustration-768x402.png 768w, https:\/\/nr.no\/content\/uploads\/sites\/2\/2023\/05\/anomaly_illustration-1536x805.png 1536w, https:\/\/nr.no\/content\/uploads\/sites\/2\/2023\/05\/anomaly_illustration.png 2048w\" sizes=\"auto, (max-width: 1024px) 100vw, 1024px\" \/><figcaption class=\"wp-element-caption\">Anomalies are detected as large differences between predicted and observed sensor measurements. <\/figcaption><\/figure>\n\n\n\n<p class=\"has-sizing-small\"><em>Anomalies are detected as large differences between predicted and observed sensor measurements.\u00a0<\/em><\/p>\n\n\n\n\n\n<p>Calibrating the method to detect only what is interesting is a central research challenge. If the operators of the power plant receive too many false alarms, they will lose trust in the system, and it becomes practically worthless. <\/p>\n\n\n\n<p>It is also crucial that the operators can understand why an alarm has occurred, without being experts in machine learning or statistics.&nbsp;<\/p>\n<\/div>\n\n\n\n<div class=\"wp-block-column is-layout-flow wp-block-column-is-layout-flow\" style=\"flex-basis:33.33%\">\t\t<div id=\"post-type-multi-block_574a758b4b388e444ea9190b515b362a\" class=\"wp-block-post-type-multi type-manual style-card-bc_employee t2-grid\">\n\t\t\t\t\t\t\t<div class=\"t2-grid-item-col-12\">\n\t\t\t\t\t\t<a href=\"https:\/\/nr.no\/en\/employees\/martin-tveten\/\" class='card-employee'>\n\t\t\t\t\t<figure>\n\t\t\t\t<img decoding=\"async\" src=\"https:\/\/nr.no\/content\/uploads\/sites\/2\/2024\/05\/martin-tveten-3.jpg\" alt=\"\">\n\t\t\t<\/figure>\n\t\t\t\t<div class=\"card-employee__content\">\n\t\t\t<p class=\"card-employee__name\">Martin Tveten<\/p>\n\t\t\t\t\t\t\t<p class=\"card-employee__position\">Senior Research Scientist<\/p>\n\t\t\t\t\t\t<svg xmlns=\"http:\/\/www.w3.org\/2000\/svg\" viewBox=\"0 0 24 24\" height=\"24\" width=\"24\" class=\"t2-icon t2-icon-arrowforward\" aria-hidden=\"true\" focusable=\"false\"><path d=\"M15.9 4.259a1.438 1.438 0 0 1-.147.037c-.139.031-.339.201-.421.359-.084.161-.084.529-.001.685.035.066 1.361 1.416 2.947 3l2.882 2.88-10.19.02c-8.543.017-10.206.029-10.29.075-.282.155-.413.372-.413.685 0 .313.131.53.413.685.084.046 1.747.058 10.29.075l10.19.02-2.882 2.88c-1.586 1.584-2.912 2.934-2.947 3-.077.145-.085.521-.013.66a.849.849 0 0 0 .342.35c.156.082.526.081.68-.001.066-.035 1.735-1.681 3.709-3.656 2.526-2.53 3.606-3.637 3.65-3.742A.892.892 0 0 0 23.76 12a.892.892 0 0 0-.061-.271c-.044-.105-1.124-1.212-3.65-3.742-1.974-1.975-3.634-3.616-3.689-3.645-.105-.055-.392-.107-.46-.083\"\/><\/svg>\n\t\t<\/div>\n\t<\/a>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\n\n\n<div class=\"wp-block-group has-nr-dark-yellow-background-color has-background\">\n<p>Name: Anomaly detection in wind and hydropower plants&nbsp;&nbsp;<\/p>\n\n\n\n<p>Partner: Statkraft<\/p>\n\n\n\n<p>Period: 2022 &#8211; 2023<\/p>\n<\/div>\n<\/div>\n<\/div>\n","protected":false},"featured_media":21083,"template":"","meta":{"_acf_changed":false,"_trash_the_other_posts":false,"editor_notices":[],"footnotes":""},"class_list":["post-21057","bc_project","type-bc_project","status-publish","has-post-thumbnail"],"acf":[],"_links":{"self":[{"href":"https:\/\/nr.no\/en\/wp-json\/wp\/v2\/bc_project\/21057","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/nr.no\/en\/wp-json\/wp\/v2\/bc_project"}],"about":[{"href":"https:\/\/nr.no\/en\/wp-json\/wp\/v2\/types\/bc_project"}],"version-history":[{"count":4,"href":"https:\/\/nr.no\/en\/wp-json\/wp\/v2\/bc_project\/21057\/revisions"}],"predecessor-version":[{"id":29103,"href":"https:\/\/nr.no\/en\/wp-json\/wp\/v2\/bc_project\/21057\/revisions\/29103"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/nr.no\/en\/wp-json\/wp\/v2\/media\/21083"}],"wp:attachment":[{"href":"https:\/\/nr.no\/en\/wp-json\/wp\/v2\/media?parent=21057"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}