A long-tailed distribution time-series dataset in boiler equipment

Abstract Industrial boilers are critical in various industries, transforming fuel’s chemical energy into heat energy in the form of steam. These equipment primarily serve sectors such as power generation, chemicals, metallurgy, and paper production, providing essential heat and steam. Time-series an...

Full description

Saved in:
Bibliographic Details
Main Authors: Weijun Hu, Anze Jiang, Kaihong Chen, Jie Zheng, Wenli Shang, Zhong Cao
Format: Article
Language:English
Published: Nature Portfolio 2025-05-01
Series:Scientific Data
Online Access:https://doi.org/10.1038/s41597-025-05096-4
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Abstract Industrial boilers are critical in various industries, transforming fuel’s chemical energy into heat energy in the form of steam. These equipment primarily serve sectors such as power generation, chemicals, metallurgy, and paper production, providing essential heat and steam. Time-series analysis of boiler parameters offers valuable insights into the interactions of various operational factors, enabling optimization of settings and extending the equipment’s service life. However, due to the challenging operational environments and data transmission issues, sensors often record incomplete or erroneous data. This study focuses on collecting operational data from a coal-fired boiler at a chemical plant in Zhejiang. By preprocessing this flawed data, we generate a high-dimensional time-series dataset that includes key operational parameters like pressure, temperature, flow rate, and oxygen levels. Using the boiler outlet steam temperature as a key indicator of equipment condition, the dataset also reveals long-tailed distribution, offering a foundation for addressing long-tailed issues in industrial equipment analytics.
ISSN:2052-4463