数据和知识双驱动下的土压平衡盾构结泥饼事件预警模型

针对施工中结泥饼事件成因机制复杂、预判难度大的问题，从数据建模和知识推理2种角度综合判断盾构结泥饼事件概率。从数据建模角度，采用无阈值递归图转换和极限学习机自编码器技术建立基于施工多维时序数据的结泥饼异常诊断子模型；从知识推理角度，提取土压平衡盾构结泥饼事件规则，形成事件诊断知识库，建立基于历史施工经验的结泥饼事件诊断子模型。基于2个子模型输出结果，采用综合概率法，建立数据和知识双驱动的结泥饼事件预警模型。实际工程应用表明： 数据和知识双驱动的预警模型能够有效预测结泥饼事件，且预警效果优于单一形式的子模型，较子模型的误报率更低，预警时间早于人工发现的结泥饼事件，为工程安全提供了技术保障。

Mud Cake Event Early Warning Model for Earth Pressure Balance Shield Driven by Data and Knowledge

The mud cake incidents would significantly reduce the effectiveness of shield building and jeopardize worker safety when an earth pressure balance (EPB) shield is being built. To overcome the challenge of recognizing mud cake events in shields, a method is proposed to diagnose mud cake events from two perspectives of data modeling and knowledge inference. Then, the mud cake diagnosis sub model based on unthresholded recurrence plot transformation and extreme learning machine autoencoder technology in data modeling is established. The mud cake event rules are also retrieved from a knowledge reasoning standpoint to create an event diagnostic knowledge base and choose a mud cake event diagnosis submodel based on prior construction experience. Finally, based on the two sub model output results and the comprehensive probability method, a mud cake event early warning model powered by data and knowledge is built. The use of the early warning model demonstrates that the mud cake event early warning model driven by both data and knowledge model can accurately predict the mud cake event with better performance and lower false positive rate than single sub models. Furthermore, the warning time is earlier than the manual discovery time, providing technical help for project safety.