Aiming at the problems of tower inclination,cable fracture caused by geological collapse in goaf,and the existing transmission line sag and temperature monitoring rely too much on sensors,a transmission line sag temperature estimation method based on improved machine learning is proposed. Firstly,the sag temperature image data of the line is obtained by using the intelligent camera and sensor installed on the line. Secondly,the data is transmitted to the supervisory control and data acquisition (SCADA) based on remote wireless communication. The sag of the transmission line is estimated based on genetic support vector machine (GA-SVM) algorithm,while the temperature of the transmission line is estimated by genetic Elman (GA-Elman) neural network algorithm to accurately track the state of the transmission line. Finally,the simulation platform is built to analyze and verify the proposed method. The experimental results show that the proposed method can quickly obtain the monitoring data in complex environment. The accuracy of sag temperature estimation is better than the comparison methods.