The customer needs to equip himself with an advanced system capable not only of detecting operating anomalies and leaks of one of his district heating networks, but also of foreseeing future problems. This can be done through analysis of the thermographs that are acquired annually with aerial flyovers and integrate them with other features\/data sources in an anomaly detection and predictive analysis tool. The goal is to understand the evolution of the network and its anomalies over time, so as to intelligently plan maintenance interventions and contain waste. <\/p>\n
Exprivia is accompanying the partner in the industrialization of a digital platform based on artificial intelligence models (deep learning) for anomaly detection.
\nThrough the collection and mosaic of thermal images of annual flyovers, the system builds a progressive dataset in which anomalies are compared with leak cases verified in the field. Neural networks thus learn to distinguish what is physiological or disturbing elements from what constitutes a significant anomaly.
\nThe result is an intelligent map, capable of sorting and prioritising anomalies according to criteria of severity, extent and potential impact: a useful strategic decision-making tool for the multi-utility. In addition, diachronic monitoring allows you to observe how anomalies evolve, transforming a traditionally reactive approach into a predictive and proactive model. <\/p>\n
The platform will make it possible to identify critical points in the network potentially exposed to anomalies or failures in advance and to optimize the planning of interventions, with a positive impact on the economic and environmental level. The multi-utility can thus contain energy losses and improve the overall efficiency of the grid, strengthening its role as a key player in the energy transition of the areas served. <\/p>\n","protected":false},"excerpt":{"rendered":"
Industrialization of a digital platform based on deep learning artificial intelligence models for anomaly detection<\/p>\n","protected":false},"author":2,"featured_media":8652,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"content-type":"","footnotes":""},"categories":[134],"tags":[141,155,136],"class_list":["post-8649","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-case-history","tag-artificial-intelligence","tag-cloud","tag-energy-utilities"],"acf":[],"yoast_head":"\n