The complicated geological conditions and unreasonable tunneling parameters will cause the abnormalities or damage of the TBM tools and increase the tool consumption, which are adverse to the tunneling efficiency of TBM and the construction cost control. Based on the systematic description of the common failure modes of the TBM tool, we have studied and analyzed such tunneling parameters as total thrust, cutterhead speed and tool penetration, such geological parameters of different surrounding rocks as uniaxial compressive strength and quartz content, as well as the influence rule for the wear, abnormalities or damage of the tool. Taking Zhongtianshan Tunnel as an example, we have made statistics for and analyzed the tool consumption and failure modes, and proposed the specific optimization methods in terms of tool selection, inspection and maintenance. Finally, we have proposed that the configuration technology for the tools with adjustable clearance shall be further developed, to ensure the rock-breaking efficiency of tools under different geological conditions. In the meantime, we will intensify the R&D and application of the new tool condition monitoring system strongly adaptive to the work environment of TBM. © 2024 The Author(s).

With the Gaoligong Mountain Tunnel of Dali-Ruili Railway, Qinling Tunnel of Hanjiang to Weihe River Project, Xianglu Mountain Tunnel commenced successively in China, the TBM entrapment in water-rich fragmentation in extreme soft stratum and rockburst in extremely hard rock under high ground stress have been increasingly prominent problems in TBM construction. On the basis of the summary analysis on the cases of partial tunnel collapse and TBM entrapment and their contributory factors in the projects, we conduct systematic investigation of the key technologies for TBM tunneling: (1) For now there is no way to make accurate quantitative forecast of the geological conditions in medium or long distances ahead; for the soft and broken stratums with joint development, carbonaceous slate and fault fracture zone, special measures against machine entrapment must be taken and proper rescue solutions can be devised based on the length of the segment with unfavorable geological conditions; (2) The anomalies in the tunneling parameters are important indicators that reveal the geological conditions ahead of heading face. Before TBM tunneling, proper tunneling parameters should be chosen based on the preliminarily anticipated surrounding rock conditions such as fullsection hard rock and weak and broken rock. In the boring process of TBM, it is necessary to correct the preestimation of geological conditions and take corresponding regulatory measures based on the abnormal changes of boring parameters; (3) Aiming at the situation that the existing TBMs are difficult to adapt to the existing geological conditions, the transformation technology of TBMs is analyzed and discussed with the engineering cases of Tao River Water Diversion Tunnel, Hongyan River to Shitou River Water Diversion Tunnel, and Hanjiang to Weihe River Water Diversion Tunnel. Finally, the new problems of TBM tunnel construction under extremely complex geological conditions and their countermeasures are prospected and discussed. © 2024 The Author(s).

Time-series waveform data widely exist in various industrial fields, such as equipment monitoring and fault diagnosis. The current time series representation methods have limitations when dealing with industrial abnormal time-series waveforms, such as limited applicability, semantic ambiguity, and time distortion. This work proposes a novel shape reference-based representation method for industrial abnormal time-series waveform (ShapeRef), which takes the shape of the standard waveform as a reference to represent the anomaly deviation. Specifically, ShapeRef first establishes a time-series shape reference frame, then proposes the minimum shape difference-based mapping method to describe the mapping process of coordinates, and finally reduces multi-intersection points in the mapping process to achieve uniform mapping of the abnormal time-series waveform. Experimental results show that ShapeRef can effectively represent abnormal time-series waveforms and outperforms several baseline methods in the clustering task of a real industrial equipment waveform dataset. This work enhances the accuracy and reliability of industrial equipment monitoring and fault diagnosis, which could have significant practical implications. © 2023 IEEE.

Rolling bearing of rotating machinery's key component will inevitably fail due to the complex and changeable operating environment such as variable speed, large disturbance, high and low temperature. It is quite challenging to obtain abundant labeled bearing fault samples because the rotating machinery is typically in a healthy and operational state. For addressing the issue, an intelligent fault diagnosis method based on a deep transfer learning network is proposed. First, a bidirectional gated recurrent unit (Bi-GRU) network is utilized to mine the latent relationship between labeled source domain samples and few labeled target domain samples, the parameters of Bi-GRU are trained to obtain the instance transfer bidirectional gated recurrent unit model (ITBi-GRU), and auxiliary samples are generated based on the ITBi-GRU. Second, as a feature transfer learning method, joint distribution adaptation is used to simultaneously decrease the distribution discrepancies between the generated auxiliary samples and the unlabeled target domain samples. Finally, extensive experiments are employed to evaluate the effectiveness of the proposed method in the case of scarce labeled samples. © 2023 IEEE.