Machine learning-based identification of segment joint failure in underground tunnels.

Shield tunnels that reside deep within soft soil are subject to longitudinal differential settlement and structural deformation during long-term operation. Longitudinal deformation can be classified into two modes: bending and dislocation deformation. The failure of bolts and engineering treatment techniques differ between these two modes. Therefore, it is imperative to accurately identify the tunnel's longitudinal deformation mode to determine the validity of the segment joint and implement appropriate engineering treatment. Traditional methods for detecting dislocation or opening suffer from high labour costs. To address this issue, this study presents an innovative identification method using a back-propagation neural network (BPNN) to detect segment joint failure in underground tunnels. First, this study collects the tunnel settlement curves of various subways located in the East China soft soil area, and it calculates tunnel settlement-dislocation and settlement-opening datasets using the equivalent axial stiffness model. A corresponding BPNN regression model is subsequently established, and the new settlement curve is the input to this regression model to predict the dislocation and opening, thereby determining the validity of the segment joint. The efficiency of this method is demonstrated through its successful application to the Hangzhou Metro Tunnel. This article is part of the theme issue 'Artificial intelligence in failure analysis of transportation infrastructure and materials'.

Influences of operational practices on municipal solid waste landfill storage capacity.

The quantitative effects of three operational factors, that is initial compaction, decomposition condition and leachate level, on municipal solid waste (MSW) landfill settlement and storage capacity are investigated in this article via consideration of a hypothetical case. The implemented model for calculating landfill compression displacement is able to consider decreases in compressibility induced by biological decomposition and load dependence of decomposition compression for the MSW. According to the investigation, a significant increase in storage capacity can be achieved by intensive initial compaction, adjustment of decomposition condition and lowering of leachate levels. The quantitative investigation presented aims to encourage landfill operators to improve management to enhance storage capacity. Furthermore, improving initial compaction and creating a preferential decomposition condition can also significantly reduce operational and post-closure settlements, respectively, which helps protect leachate and gas management infrastructure and monitoring equipment in modern landfills.

An equivalent-time-lines model for municipal solid waste based on its compression characteristics.

Municipal solid waste (MSW) demonstrates a noticeable time-dependent stress-strain behavior, which contributes greatly to the settlement of landfills and therefore influences both the storage capacity of landfills and the integrity of internal structures. The long-term compression tests for MSW under different biodegradation conditions were analyzed. It showed that the primary compression can affect the secondary compression due to the biodegradation and mechanical creep. Based on the time-lines model for clays and the compression characteristics of MSW, relationships between MSW's viscous strain rate and equivalent time were established, and then the viscous strain functions of MSW under different biodegradation conditions were deduced, and an equivalent-time-lines model for MSW settlement for two biodegradation conditions was developed, including the Type I model for the enhanced biodegradation condition and the Type II model for the normal biodegradation condition. The simulated compression results of laboratory and field compression tests under different biodegradation conditions were consistent with the measured data, which showed the reliability of both types of the equivalent-time-lines model for MSW. In addition, investigations of the long-term settlement of landfills from the literature indicated that the Type I model is suitable for predicting settlement in MSW landfills with a distinct biodegradation progress of MSW, a high content of organics in MSW, a short fill age or under an enhanced biodegradation environment; while the Type II model is good at predicting settlement in MSW landfills with a distinct progress of mechanical creep compression, a low content of organics in MSW, a long fill age or under a normal biodegradation condition. Furthermore, relationships between model parameters and the fill age of landfills were summarized. Finally, the similarities and differences between the equivalent-time-lines model for MSW and the stress-biodegradation model for MSW were discussed.

A practical approach for calculating the settlement and storage capacity of landfills based on the space and time discretization of the landfilling process.

The settlement of any position of the municipal solid waste (MSW) body during the landfilling process and after its closure has effects on the integrity of the internal structure and storage capacity of the landfill. This paper proposes a practical approach for calculating the settlement and storage capacity of landfills based on the space and time discretization of the landfilling process. The MSW body in the landfill was divided into independent column units, and the filling process of each column unit was determined by a simplified complete landfilling process. The settlement of a position in the landfill was calculated with the compression of each MSW layer in every column unit. Then, the simultaneous settlement of all the column units was integrated to obtain the settlement of the landfill and storage capacity of all the column units; this allowed to obtain the storage capacity of the landfill based on the layer-wise summation method. When the compression of each MSW layer was calculated, the effects of the fluctuation of the main leachate level and variation in the unit weight of the MSW on the overburdened effective stress were taken into consideration by introducing the main leachate level's proportion and the unit weight and buried depth curve. This approach is especially significant for MSW with a high kitchen waste content and landfills in developing countries. The stress-biodegradation compression model was used to calculate the compression of each MSW layer. A software program, Settlement and Storage Capacity Calculation System for Landfills, was developed by integrating the space and time discretization of the landfilling process and the settlement and storage capacity algorithms. The landfilling process of the phase IV of Shanghai Laogang Landfill was simulated using this software. The maximum geometric volume of the landfill error between the calculated and measured values is only 2.02%, and the accumulated filling weight error between the calculated value and measured value is less than 5%. These results show that this approach is practical for satisfactorily and reliably calculating the settlement and storage capacity. In addition, the development of the elevation lines in the landfill sections created with the software demonstrates that the optimization of the design of the structures should be based on the settlement of the landfill. Since this practical approach can reasonably calculate the storage capacity of landfills and efficiently provide the development of the settlement of each landfilling stage, it can be used for the optimizations of landfilling schemes and structural designs.