Search

Objective Grouting treatment of karst caves is a challenge in metro tunnel engineering, as improper handling of karst caves during construction can easily lead to accidents. Therefore, it is necessary to study the relationship between the quantity of cracks and grouting pressure in small karst caves. Method To address the uncertainty regarding the quantity of cracks in urban small unconnected karst caves (with a volume not exceeding 8 m3) that requires grouting filling, numerical simulations of cave grouting with different crack quantities are conducted using multiphase flow Mixture model in Fluent numerical simulation software. The variation of grouting pressure in the test area during simulated grouting is calculated over time and compared with karst caves grouting pressure data from practical engineering. Result & Conclusion For small unconnected karst caves with a volume not exceeding 8 m3, the grouting pressure in the simulated test area shows an inverse square relationship with the quantity of cracks, and decreasing as the crack quantity increases. When the crack area reaches 0.048 m2, the grouting pressure no longer decreases. The grouting pressure decreases with the increase in the elevation of crack locations. In practical engineering, comparing grouting pressure data among the same type of small unconnected karst caves with volumes not exceeding 8 m3 can serve as a basis for judging the relative quantity of cracks in karst caves, thereby adjusting and optimizing subsequent grouting schemes.

In real-time onboard hyperspectral-image(HSI) anomalous targets detection, processing speed and accuracy are equivalently desirable which is hard to satisfy at the same time. To improve detection accuracy, deep learning based HSI anomaly detectors (ADs) are widely studied. However, their large scale network results in a massive computational burden. In this paper, to improve the detection throughput without sacrificing the accuracy, a pruning–quantization–anomaly–detector (P-Q-AD) is proposed by building an underlying constraint formulation to make a trade-off between accuracy and throughput. To solve this formulation, multi-objective optimization with nondominated sorting genetic algorithm II (NSGA-II) is employed to shrink the network. As a result, the redundant neurons are removed. A mixed precision network is implemented with a delicate customized fixed-point data expression to further improve the efficiency. In the experiments, the proposed P-Q-AD is implemented on two real HSI data sets and compared with three types of detectors. The results show that the performance of the proposed approach is no worse than those comparison detectors in terms of the receiver operating characteristic curve (ROC) and area under curve (AUC) value. For the onboard mission, the proposed P-Q-AD reaches over 4.5 × speedup with less than 0.5 % AUC loss compared with the floating-based detector. The pruning and the quantization approach in this paper can be referenced for designing the anomalous targets detectors for high efficiency. [ABSTRACT FROM AUTHOR]