High concentration of PM 2.5 has seriously affected people's daily lives in recent years. It is necessary to analyze PM 2.5 and the correlations with other pollutants in winter. Data presented in this paper were obtained from monitoring stations from 2016 to 2018. Attention was fixed on PM 2.5 and its monthly and daily variations in winter. Furthermore, the correlations between PM 2.5 and CO, SO 2 , NO 2 , O 3 and PM 10 were studied. The results showed concentrating PM 2.5 was roughly consistent with the monthly and daily trends. It was January>December>February>November>March. The mass concentration ranges of PM 2.5 before and after the adjustment of heating energy structures were 64.5-184.1 μg/m 3 , and 86.4-140.1 μg/m 3 , respectively. The average concentrations of PM 2.5 were 135.5 μg/m 3 , and 109.1 μg/m 3 , decreased by 26.4 μg/m 3. PM 2.5 /PM 10 was changed from 64.6% to 62.6%, reduced by 2%. The linear correlation analysis revealed a strong correlation between PM 2.5 and CO, SO 2 , NO 2 , and PM 10 , but a negative correlation between PM 2.5 and O 3. Two multiple linear regression models on the pollutants were established, respectively. This study helps understand the concentrating distribution of PM 2.5 and other pollutants in winter. It will provide some useful references to control air pollution for some cities, which have a similar type of heating energy structure.