Industrial heat sources serve as crucial indicators of energy consumption levels and air pollution. Energy-intensive industries are facing substantial challenges in transforming and upgrading in China. Therefore, accurately identifying industrial heat source locations and monitoring their temporal patterns are becoming utmost importance. In this study, a long-term industrial heat source datasets between 2012 and 2021 in China using long-term Active Fire/Hotspots (ACF) data has been constructed to monitor and analyze large-scale industrial heat sources. Firstly, density segmentation method based on an improved k-means algorithm using long-term ACF data and spatial topological correlation analysis was conducted to build industrial heat sources. Then, 4410 industrial heat sources were obtained between 2012 and 2021 in China, with an identification accuracy of 95.08% by manual verification using high-resolution remote sensing images and point of interest (POI) data. Finally, the trend in the spatio-temporal variation of industrial heat sources was analyzed using long-term series. The results from 2012 to 2021 showed that the spatial distribution of industrial heat sources in China exhibits local aggregation and a gradual shift from east to west.And,the number of industrial heat sources in China has followed a trend of an initial increase from 2012 to 2014, followed by a decrease since 2014, consistent with national energy reform-related policies.The result of this study indicated the temporal variation of industrial heat sources, enhanced the accuracy of fire points category identification, and demonstrated potential for advancing energy efficiency, emission reduction, and sustainable development in China.