Hydraulic system has been the mainstream choice in large engineering equipment due to its smooth transmission, large bearing capacity, and small volume. However, because of the tightness and invisibility in hydraulic equipment, it is difficult to check and predict its faults. Common fault diagnosis and maintenance methods for the hydraulic system can be divided into two types: a signal analysis based on the mathematical model and a machine learning algorithm based on artificial intelligence. The first method can only diagnose specific faults based on the mathematical model, which is not universal, and the second one must rely on abundant history fault data, which is impossible to obtain in the early running stage. In order to address these questions, a digital twin framework is proposed which combines the virtual model with the real part to solve practical problems. As a concrete realization form of a five-dimension digital twin model, this framework provides a more feasible solution mode for fault diagnosis in the hydraulic system. Meanwhile, it expands the functions of faults prediction and digital model display. A case study of a hydraulic cylinder is used to illustrate the effectiveness of the proposed framework. The experimental result shows that this method can improve diagnosis accuracy for a hydraulic cylinder greatly compared with the non-interactive simulation model. Meanwhile, with the supplement of actual fault data, the diagnosis accuracy can be further improved, which has a certain growth ability and good applicability.

This paper is focused on developing an effective method to optimize the performance (e.g., advance rate and energy consumption) of a tunnel boring machine (TBM) by determining reasonable operating and structural parameters according to geological conditions. The TBM is a complex mechatronic system consisting of closely coupled subsystems. The changing of an operating or structural parameter can significantly influence the performances of several subsystems simultaneously in different manners. In addition, most of the subsystems of the TBM are subject to rock loads with server uncertainties, as a result of the probabilistic natures of rock characteristics. To overcome these challenges, multidisciplinary modeling of the subsystems of the TBM is performed to derive the performance functions and limit state functions of the whole machine. Based on design of experiment, sensitive analysis (SA) is carried out to detect the significant factors and their influences on the performances of the whole machine and the subsystems. Based on the SA results, the optimization efficiency can be improved by disregarding insignificant factors. Taking the stochastic properties of rocks into account, a reliability-based performance optimization strategy is proposed. Case studies are carried out and proved that with the proposed method, the performances of the TBM can be greatly improved while the system reliability is kept at high level.