With the development of information technology, the application of machine learning in automatic structure monitoring has been increasing gradually. Data analysis and prediction, as an important component of automatic structure monitoring, play a key role in ensuring structural safety. To address the issues of current structural monitoring data prediction methods, which may not fully leverage data characteristics and can be time-consuming, we propose a monitoring data prediction model based on the gated broad learning system (G-BLS). G-BLS can control feature nodes to extract highly relevant information by adding forgetting gates and cyclic feedback gates to feature nodes of BLS. Compared to the deep learning models, the network structure of G-BLS model is much simpler, leading to significantly reduced training times. Test results using measured subsidence data from a subway foundation pit demonstrate that G-BLS effectively achieves both reliability and real-time performance in prediction and monitoring data. This model proves to be an accurate and efficient method for structural monitoring data prediction.