{"id":6094,"date":"2025-04-15T16:37:35","date_gmt":"2025-04-15T14:37:35","guid":{"rendered":"https:\/\/dbis.rwth-aachen.de\/dbis\/?p=6094"},"modified":"2025-10-20T23:59:45","modified_gmt":"2025-10-20T21:59:45","slug":"smart-llm-sensor-based-maintenance-bot-for-analysis-and-retrieval-of-time-series-data-using-llms","status":"publish","type":"post","link":"https:\/\/dbis.rwth-aachen.de\/dbis\/index.php\/2025\/smart-llm-sensor-based-maintenance-bot-for-analysis-and-retrieval-of-time-series-data-using-llms\/","title":{"rendered":"SMART-LLM: Sensor-based Maintenance bot for Analysis and Retrieval of Time Series data using LLMs"},"content":{"rendered":"\n<p>The goal of this thesis is to design, implement, and evaluate a <strong>sensor-based maintenance bot<\/strong> that uses <strong>Large Language Models (LLMs)<\/strong> to support <strong>predictive maintenance<\/strong> and <strong>decision-making<\/strong>. The bot should be capable of retrieving, analyzing, and reasoning over <strong>time series sensor data<\/strong> as well as <strong>unstructured maintenance-related documentation<\/strong> (e.g., technical manuals, incident reports). The result is a unified system that assists technicians and engineers in diagnosing issues, suggesting preventive actions, and retrieving relevant information in natural language.<\/p>\n\n\n\n<p>This work is conducted in collaboration with the <strong>Fraunhofer Institute for Production Technology (IPT)<\/strong> as part of the research initiative <strong>&#8220;<a href=\"https:\/\/icnap_digital_services.web.fec.ipt.fraunhofer.de\/service\/66\">Generative AI for Production and Business Operations<\/a>&#8220;<\/strong>, aiming to explore practical applications of generative models in manufacturing and industrial operations.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>The goal of this thesis is to design, implement, and evaluate a sensor-based maintenance bot that uses Large Language Models (LLMs) to support predictive maintenance and decision-making. The bot should be capable of retrieving, analyzing, and reasoning over time series sensor data as well as unstructured maintenance-related documentation (e.g., technical manuals, incident reports). The result [&hellip;]<\/p>\n","protected":false},"author":16,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"footnotes":""},"categories":[21],"tags":[],"class_list":["post-6094","post","type-post","status-publish","format-standard","hentry","category-thesis"],"acf":[],"_links":{"self":[{"href":"https:\/\/dbis.rwth-aachen.de\/dbis\/index.php\/wp-json\/wp\/v2\/posts\/6094","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/dbis.rwth-aachen.de\/dbis\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/dbis.rwth-aachen.de\/dbis\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/dbis.rwth-aachen.de\/dbis\/index.php\/wp-json\/wp\/v2\/users\/16"}],"replies":[{"embeddable":true,"href":"https:\/\/dbis.rwth-aachen.de\/dbis\/index.php\/wp-json\/wp\/v2\/comments?post=6094"}],"version-history":[{"count":2,"href":"https:\/\/dbis.rwth-aachen.de\/dbis\/index.php\/wp-json\/wp\/v2\/posts\/6094\/revisions"}],"predecessor-version":[{"id":6646,"href":"https:\/\/dbis.rwth-aachen.de\/dbis\/index.php\/wp-json\/wp\/v2\/posts\/6094\/revisions\/6646"}],"wp:attachment":[{"href":"https:\/\/dbis.rwth-aachen.de\/dbis\/index.php\/wp-json\/wp\/v2\/media?parent=6094"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/dbis.rwth-aachen.de\/dbis\/index.php\/wp-json\/wp\/v2\/categories?post=6094"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/dbis.rwth-aachen.de\/dbis\/index.php\/wp-json\/wp\/v2\/tags?post=6094"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}