Abstract: There are currently problems with the intelligent gas extraction system in coal mines. ① The system's functions are limited to a certain process control, resulting in incomplete coverage of gas extraction business management and inadequate implementation of measures. ② Based on the traditional "chimney style" IT architecture, subsystems are scattered, data utilization is low, collaborative capabilities are poor. The cost of later subsystem integration is high, making system expansion inconvenient. ③ There are still many manual links in the gas extraction process, and the system's intelligence and automation capabilities still need to be further improved. In order to solve the above problems, a coal mine gas intelligent extraction control system based on industrial Internet architecture is designed. A multi-source heterogeneous data collection process for gas extraction has been developed based on the publish/subscribe model. It promotes data decoupling and sharing, reduces system complexity, and achieves unified collection of multi-source heterogeneous data such as gas extraction pipeline network data, drilling operation and trajectory data, equipment working condition data, and meeting standard evaluation data. Based on digital twin technology, a three-dimensional extraction system model is constructed, achieving a three-dimensional display of the up and down extraction system. Based on rule engine technology, sensor data processed by the message center can be judged based on subscribed Topic. The processed sensor data is stored in the database to realize the automation and process operation of gas extraction standard evaluation. By using machine vision video analysis technology to identify the number of drill pipes, automatic counting of drill pipe numbers (drilling depth) during the drilling process and information management of drilling engineering are achieved. Combined with drilling measurement instruments, analysis and visualization of drilling trajectory left and right, upper and lower deviations are achieved. The on-site application results show that gas extraction management personnel can quickly and in real time understand the extraction situation, extraction evaluation, drilling engineering construction, and system failure of each extraction face by viewing the intelligent control system software for gas extraction. It improves the level of gas extraction information and intelligent management.