Abstract: The intelligent operation of underground coal mine tunneling workfaces relies on the multi-factor coordination of personnel, equipment, and environment. To address the issue that traditional cloud-edge collaborative architectures struggle to balance efficient processing and in-depth mining of operational status data for tunneling equipment, this paper proposes a Cloud-Edge-End collaborative computing model for online monitoring and analysis of equipment operational status in coal mine tunneling workfaces. This model leverages the advantages of high-performance cloud computing and real-time device-side computing to achieve efficient aggregation and organization of operational status data at the edge side of the tunneling workface, thereby ensuring the accuracy and reliability of online equipment status monitoring. To address the abnormal cutting rotation caused by mechanical jamming in the hydraulic cylinders of a boom-type roadheader, an online equipment status monitoring platform based on Cloud-Edge-End collaborative computing is established. At the device end, moving average filtering is applied to smooth raw data, and timestamps are used for multi-device data synchronization, while a lightweight transmission channel is constructed via the MQTT protocol to enable real-time data transmission. At the cloud platform layer, based on the collected historical operational status data of coal mining tunneling equipment, a device state data relationship graph is constructed using prior knowledge. Mutual information is employed to quantify and rank the correlations within the historical data of the boom-type roadheader’s swing section, uncovering strong coupling relationships among the data, which are then explicitly represented using Neo4j. At the edge side of the tunneling workface, real-time multi-dimensional data filtering is performed based on the strong coupling relationships mined from the cloud platform. Through real-time aggregation and computation of operational status characteristic data, including cylinder extension displacement, rotation angle, and cutting head lateral displacement, online monitoring and anomaly analysis of the equipment cutting status are achieved. Through collaborative computation across the three tiers—cloud platform, edge side, and device end—the proposed Cloud-Edge-End collaborative computing model realizes efficient aggregation and organization of multi-dimensional operational status data at the edge side of the tunneling workface. It effectively balances the response speed for abnormal equipment status identification with the reliability of operational status monitoring, providing a reliable analytical and decision-making foundation for intelligent control and predictive maintenance of coal mine tunneling workface equipment.