![\"\"](\"https:\/\/vikinganalytics.se\/wp-content\/uploads\/2023\/04\/smart-industry-robot-arms-digital-factory-production-technology-2-2048x1536-1.jpg\")
<\/p>\n<\/p>\n
Predictive maintenance<\/span>, despite<\/span>\u00a0its measurable results and successes,\u00a0<\/span>has\u00a0<\/span>been suffering<\/span>\u00a0from\u00a0<\/span>lack of scalability.\u00a0<\/span>Models designed and trained for a given machine with a particular set of sensors often had to be retrained before being used with other similar machines.<\/span>\u00a0In addition, t<\/span>he\u00a0<\/span>quantity and variety<\/span>\u00a0of machines i<\/span>n a factory\u00a0<\/span>makes developing, training, and maintaining models\u00a0<\/span>for each machine a challenge.\u00a0<\/span>Therefore, it<\/span>\u2018<\/span>s natural that\u00a0<\/span>predictive maintenance\u00a0<\/span>became limited to the most valuable assets<\/span>\u00a0in a plant.<\/span>\u00a0<\/span><\/p>\n But that is<\/span>\u00a0quickly changing.<\/span>\u00a0<\/span><\/p>\n Technological advances have increased the availability of affordable vibration<\/span>\u00a0sensors<\/span>, offered\u00a0<\/span>either with\u00a0<\/span>or<\/span>\u00a0without\u00a0<\/span>analytics solutions.\u00a0<\/span>New products come out\u00a0<\/span>often<\/span>\u00a0and i<\/span>n late 2020<\/span>,<\/span>\u00a0the market heated up with the entrance of Amazon in the\u00a0<\/span>condition monitoring<\/span>\u00a0arena<\/span>,<\/span>\u00a0with the launch of\u00a0<\/span>Amazon\u00a0<\/span>Monitron<\/span>\u00a0sensors.\u00a0<\/span>A<\/span>ccording to a research by\u00a0<\/span>T<\/span>echnavio,\u00a0<\/span>\u201cthe industrial vibration sensor market size is expected to grow by USD 2.83 billion during 2021-2025.\u201d<\/span>\u00a0<\/span><\/p>\n And t<\/span>his is great news<\/span>!<\/span>\u00a0With sensors being added<\/span>\u00a0to more machines<\/span>, industries will be able to\u00a0<\/span>scale up predictive maintenance to entire plants<\/span>\u00a0and reap even more benefits. However,\u00a0<\/span>no change comes without<\/span>\u00a0challenges:\u00a0<\/span>the\u00a0<\/span>more machines are\u00a0<\/span>monitored<\/span>,\u00a0<\/span>the stronger the<\/span>\u00a0pressure to collect<\/span>\u00a0data, analyze it,<\/span>\u00a0and quickly\u00a0<\/span>show<\/span>\u00a0a<\/span>s<\/span>sets<\/span>\u00a0that need closer inspection.<\/span>\u00a0To remain competitive,\u00a0<\/span>OEMs<\/span>,\u00a0<\/span>p<\/span>lant<\/span>\u00a0maintenance companies<\/span>, and sensor distributors<\/span>\u00a0will\u00a0<\/span>need to adapt by adding<\/span>\u00a0more analytics\u00a0<\/span>capabilities\u00a0<\/span>to their solutions.<\/span>\u00a0<\/span><\/p>\n That is why we are launching\u00a0<\/span>MultiViz<\/span>\u00a0Vibration. To enable\u00a0<\/span>companies<\/span>\u00a0and professionals<\/span>\u00a0that deliver machine\u00a0<\/span>diagnostics\u00a0<\/span>to\u00a0<\/span>add value to their offer\u00a0<\/span>through<\/span>\u00a0analytics features<\/span>, powered by Machine Learning algorithms<\/span>.<\/span>\u00a0<\/span><\/p>\n Traditionally, vibration\u00a0<\/span>analysis\u00a0<\/span>requires a vibration expert, detailed knowledge of the machines, and significant contribution from domain experts. This also contributes to the lack of scalability,\u00a0<\/span>especially<\/span>\u00a0in a situation in which all machines\u00a0<\/span>would\u00a0<\/span>have their own sensor.\u00a0<\/span>\u00a0<\/span><\/p>\n Machine Learning becomes the solution to that, by allowing large-scale\u00a0<\/span>unsupervised\u00a0<\/span>analysis of the history of an asset or a population of assets.<\/span>\u00a0Additionally, o<\/span>ur\u00a0<\/span>API makes it easy for asset health management, condition monitoring, and maintenance providers to build their own solution on top of it<\/span>.<\/span>\u00a0Just\u00a0<\/span>connect data from vibration sensors or upload their own historic data and\u00a0<\/span>let our engine help with:<\/span>\u00a0<\/span><\/p>\n And more features are\u00a0<\/span>in the pipeline<\/span>!\u00a0<\/span>We\u00a0<\/span>also provide<\/span>\u00a0a\u00a0<\/span>P<\/span>ython package for those who are not familiar with a REST API<\/span>\u00a0or would like to integrate it in their data analysis routine in Jupyter<\/span>\u00a0Notebook<\/span>, for example.\u00a0<\/span>\u00a0<\/span>\u00a0<\/span><\/p>\n Like<\/span>\u00a0the<\/span>\u00a0Bob Dylan<\/span>\u00a0song that inspired the title of this text says<\/span>,\u00a0times\u00a0<\/em><\/span>they are a-changin<\/em>\u2018<\/em>.\u00a0<\/span>Don\u2019t wait for the walls to start rattling, click below to request<\/span>\u00a0your free trial of\u00a0<\/span>MultiViz<\/span>\u00a0Vibration<\/span>\u00a0and start making the most out of vibration data.<\/span>\u00a0<\/span><\/p>\n","protected":false},"excerpt":{"rendered":" Predictive maintenance, despite\u00a0its measurable results and successes,\u00a0has\u00a0been suffering\u00a0from\u00a0lack of scalability.\u00a0Models designed and trained for a given machine with a particular set of sensors often had to be retrained before being used with other similar machines.\u00a0In addition, the\u00a0quantity and variety\u00a0of machines in a factory\u00a0makes developing, training, and maintaining models\u00a0for each machine a challenge.\u00a0Therefore, it\u2018s natural that\u00a0predictive […]<\/p>\n","protected":false},"author":9,"featured_media":6765,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"inline_featured_image":false,"footnotes":""},"categories":[24],"tags":[],"class_list":["post-6755","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-news"],"yoast_head":"\n\n
\n\u00a0<\/span><\/li>\n