The heat transfer characteristics of vacuum degree and the influence of the vacuum degree of vacuum glass on unit operations for predicting the vacuum degree were investigated. In this study, we designed and developed a set of intelligent detection systems using intelligent algorithms that comprised a model for predicting the vacuum degree of vacuum glass. Using wireless temperature detection in an intelligent detection system was convenient for measuring temperature data. First, the model utilized a backpropagation neural network (BPNN) to predict and infer temperature data. Furthermore, we developed a software package implementing the proposed BPNN-based model in MATLAB and verified that it could predict the vacuum degree of vacuum glass. The proposed system created a precedent for using intelligent algorithms to establish a model to predict the vacuum degree of vacuum glass with additional computer software to improve its convenience for users. Using the core theoretical module of the system, BPNN, and the appropriate intelligent algorithms, we obtained an absolute error within 1.5 Pa using the model and learnt that it was good for quick vacuum prediction.