摘要
针对人工检查盾构施工故障存在施工安全等问题,提出一种基于盾构掘进参数神经网络信息融合的盾构施工故障诊断方法。将多个盾构掘进参数信息引入各子神经网络进行局部融合诊断,再将各局部诊断信息引入决策融合网络进行全局融合,最终诊断出各种施工故障并给出可信度评价。研究结果表明:所建立的诊断系统结构合理,融合方法有效,诊断结果可靠。研究结论可为设计基于盾构掘进参数的盾构施工故障实时诊断系统提供有益指导。
In order to avoid the potential operation harms caused by manual checking shield construction faults,a diagnosis method of shield construction faults based on neural network information fusion is proposed in this study.The shield excavation parameters data are inputted into each neural network to perform partial fusion.Subsequently.the results of partial fusion are sent to decision-making fusion network to complete total fusion.As a result,the shield construction faults are diagnosed.A case study shows that the structure of diagnosis system is rational,the method of decision-making fusion is feasible and the diagnosis result is credible.This provides a beneficial guidance for the design of the online diagnosis system of construction faults based on shield excavation parameters data.
出处
《辽宁工程技术大学学报（自然科学版）》
CAS
北大核心
2010年第3期472-474,共3页
Journal of Liaoning Technical University (Natural Science)
基金
广东省自然科学基金资助项目(32484)
关键词
盾构
施工故障
信息融合
神经网络
shield
construction faults
information fusion
neural network
