Abstract: Straightness control is one of the key technologies to ensure stable and efficient advancement of coal mining face, and at present, most of the wise mining face is controlled by inertial guidance to measure the travelling trajectory of the coal mining machine, but the inertial guidance system has the problems of expensive and fragile, high maintenance difficulty, which is easy to affect the normal production efficiency of coal mining. While the coal mining system installed a large number of travel, pressure and other conventional sensors and electro-hydraulic control generated by the massive detection and operation data contains the working face straightness control decision-making information, so this paper proposes the use of massive travel and other conventional data mining modelling technology, to achieve the working face straightness intelligent control decision-making. First of all, using data cleaning and smoothing filtering technology to process the hydraulic support travel data, combined with pressure data and coal mining machine position data to calculate the working face scraper conveyor propulsion distance and manual control distance, composed of straightness analysis matrix. Then use big data mining technology to analyse the straightness analysis matrix in combination with the actual production situation, clarify the minimum pushing unit of the working face, and form the straightness control decision-making feature matrix of the working face. The straightness control decision-making model is constructed by the classification algorithm of machine learning, and the accuracy rate of Random Forest algorithm is 91.41% better than other classification algorithms. The web page of the system application is developed by using internet technology and deployed in the production site for 30d normal operation, the prediction result adoption rate is 81.4%, and good results are achieved. It makes full use of the massive production data generated by the coal mining face, and at the same time reduces the labour intensity of the workers in the wise mining face.