Mingfei Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Mingfei Li has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Yan Wang
School of Civil Engineering, Qingdao University of Technology, Qingdao 266520, China
5 shared publications - Yongjun Zhang
School of Civil Engineering, Qingdao University of Technology, Qingdao 266520, China
3 shared publications - Fei Liu
State Key Laboratory of Water Resource Protection and Utilization in Coal Mining, Beijing 102209, China
1 shared publication - Miaomiao Kou
State Key Laboratory of Water Resource Protection and Utilization in Coal Mining, Beijing 102209, China
1 shared publication - Tianhui Ma
State Key Laboratory of Coastal and Offshore Engineering, Dalian University of Technology, Dalian, China
1 shared publication Yi Qi
Postdoctoral Workstation
1 shared publication
Latest Publications
- Open Access
A Review of Machine Learning Applications in Monitoring Data Processing for Underground Engineering
With the acceleration of global urbanization and the large-scale development of underground spaces, underground engineering faces extremely complex and variable geological environments and high-risk construction disturbances. The widespread application of the Internet of Things and novel sensing technologies has given rise to structural health monitoring data increasingly characterized by massive volume, high dimensionality, multi-source heterogeneity, and strong spatiotemporal coupling. Traditional data processing methods based on mechanical analysis, empirical formulas, or numerical simulation have increasingly exposed limitations of insufficient accuracy, lengthy computation times, and weak generalization capability when confronted with such engineering big data. Machine learning and deep learning technologies, by virtue of their superior nonlinear mapping capability, advantages in feature extraction from massive data, and flexible architectural design, provide solutions for efficient knowledge extraction and intelligent assessment of underground engineering monitoring data. This paper reviews the current application status and frontier advances of machine learning technologies in the field of underground engineering monitoring data processing in recent years. First, the development trajectory of analytical algorithms evolving from classical shallow machine learning, through temporal and spatial deep learning, to physics-data dual-driven approaches is delineated. Second, targeting the critical challenges of missing field data and sparse sensor deployment, spatiotemporal fusion imputation techniques and spatial reconstruction methods incorporating mechanical prior knowledge are thoroughly evaluated, elucidating the paradigm shift in monitoring philosophy from discrete point-based alarming to inference-augmented sparse sensing that approximates full-field state awareness through model-dependent estimation rather than direct measurement. Third, the applications of machine learning in underground structural deformation mechanism interpretation, key influencing factor identification based on explainable artificial intelligence (AI), and rapid back-analysis of geomechanical parameters are summarized. Finally, composite network architectures and physics-constrained guidance strategies for non-stationary deformation time series prediction under complex and variable working conditions are discussed. A methodological audit of the 73 included studies—of which 33 enter the quantitative comparison tables—reveals that 26 of the 33 audited studies (78.8%) validate exclusively on single-project data, only 1 study conducts rigorous out-of-distribution generalization testing, and none of the 33 studies (0%) provides uncertainty quantification. These findings highlight cross-project generalization and probabilistic prediction as important methodological challenges. This paper aims to provide theoretical references and methodological guidance for safety early warning, intelligent construction, and full life-cycle health management of underground engineering.
Open AccessA Review of Machine Learning Applications in Monitoring Data Processing for Underground Engineering
With the acceleration of global urbanization and the large-scale development of underground spaces, underground engineering faces extremely complex and variable geological environments and high-risk construction disturbances. The widespread application of the Internet of Things and novel sensing technologies has given rise to structural health monitoring data increasingly characterized by massive volume, high dimensionality, multi-source heterogeneity, and strong spatiotemporal coupling. Traditional data processing methods based on mechanical analysis, empirical formulas, or numerical simulation have increasingly exposed limitations of insufficient accuracy, lengthy computation times, and weak generalization capability when confronted with such engineering big data. Machine learning and deep learning technologies, by virtue of their superior nonlinear mapping capability, advantages in feature extraction from massive data, and flexible architectural design, provide solutions for efficient knowledge extraction and intelligent assessment of underground engineering monitoring data. This paper reviews the current application status and frontier advances of machine learning technologies in the field of underground engineering monitoring data processing in recent years. First, the development trajectory of analytical algorithms evolving from classical shallow machine learning, through temporal and spatial deep learning, to physics-data dual-driven approaches is delineated. Second, targeting the critical challenges of missing field data and sparse sensor deployment, spatiotemporal fusion imputation techniques and spatial reconstruction methods incorporating mechanical prior knowledge are thoroughly evaluated, elucidating the paradigm shift in monitoring philosophy from discrete point-based alarming to inference-augmented sparse sensing that approximates full-field state awareness through model-dependent estimation rather than direct measurement. Third, the applications of machine learning in underground structural deformation mechanism interpretation, key influencing factor identification based on explainable artificial intelligence (AI), and rapid back-analysis of geomechanical parameters are summarized. Finally, composite network architectures and physics-constrained guidance strategies for non-stationary deformation time series prediction under complex and variable working conditions are discussed. A methodological audit of the 73 included studies—of which 33 enter the quantitative comparison tables—reveals that 26 of the 33 audited studies (78.8%) validate exclusively on single-project data, only 1 study conducts rigorous out-of-distribution generalization testing, and none of the 33 studies (0%) provides uncertainty quantification. These findings highlight cross-project generalization and probabilistic prediction as important methodological challenges. This paper aims to provide theoretical references and methodological guidance for safety early warning, intelligent construction, and full life-cycle health management of underground engineering.
- Open Access
Evaluation of the Consistency of Rock Joint Surface Morphology Based on Grayscale Surface-Differential Box Counting and Mechanical Tests
The accurate evaluation of the geometric morphology of rock and rock-like material joint surfaces was considered crucial for studying the mechanical properties of joint surfaces. A method based on grayscale surface and differential box-counting for evaluating the consistency of rock joint surface morphology was proposed in this study. The fractal dimensions of natural red sandstone joint surfaces and 3D printed restored joint surfaces were quantitatively identified. The consistency of the joint surface morphology of the samples was validated on both the image scale and the macroscopic mechanical scale using two approaches: CNN feature extraction and variable-angle shear tests. The validation results demonstrated a high degree of convergence, thereby confirming the accuracy of the proposed method. This study could provide a reference for the determination of the fractal dimension of joint surface morphology and the consistency research.
Open AccessEvaluation of the Consistency of Rock Joint Surface Morphology Based on Grayscale Surface-Differential Box Counting and Mechanical Tests
The accurate evaluation of the geometric morphology of rock and rock-like material joint surfaces was considered crucial for studying the mechanical properties of joint surfaces. A method based on grayscale surface and differential box-counting for evaluating the consistency of rock joint surface morphology was proposed in this study. The fractal dimensions of natural red sandstone joint surfaces and 3D printed restored joint surfaces were quantitatively identified. The consistency of the joint surface morphology of the samples was validated on both the image scale and the macroscopic mechanical scale using two approaches: CNN feature extraction and variable-angle shear tests. The validation results demonstrated a high degree of convergence, thereby confirming the accuracy of the proposed method. This study could provide a reference for the determination of the fractal dimension of joint surface morphology and the consistency research.
- Open Access
A Review of Stability of Dam Structures in Coal Mine Underground Reservoirs
Coal has remained the primary component of China’s energy structure, and high-intensity extraction has continued in the central and western coal-producing regions of China. In contrast to the abundant coal resources, water resources have become extremely scarce in these regions, creating a conflict between coal resource extraction and water resource conservation. The coal mine underground reservoir (CMUR), as a typical technology for combined coal and water extraction and water-preserving coal mining, has been applied in numerous mines in central and western China. This effectively alleviates water resource shortages and achieves the goal of water resource conservation. The CMURs utilizes the goaf created by longwall mining as the water storage space. The reservoir dam structure comprises coal pillars, which serve as protective coal pillars in the mining area, and artificial dam structures that filled the gaps between these coal pillars. The stability of the dam structure under the complex stress effects of hydraulic coupling has been identified as the key to maintaining the safe operation of the CMUR. The mechanical properties, stress field, fracture field, and seepage field (“three fields”) change mechanisms, as well as the research results on size optimization of coal pillar dams and artificial dams in CMURs, were systematically reviewed. The core content included the instability and failure mechanisms of dam structures under the comprehensive coupling effects of factors such as dry–wet cycles of mine water, long-term immersion, chemical effects of high-salinity water, dynamic and static loads, and cyclic loads. This paper is considered to have certain reference value for the study of the stability of dam structures in CMURs and to provide some guidance for the safe operation of CMURs.
Open AccessA Review of Stability of Dam Structures in Coal Mine Underground Reservoirs
Coal has remained the primary component of China’s energy structure, and high-intensity extraction has continued in the central and western coal-producing regions of China. In contrast to the abundant coal resources, water resources have become extremely scarce in these regions, creating a conflict between coal resource extraction and water resource conservation. The coal mine underground reservoir (CMUR), as a typical technology for combined coal and water extraction and water-preserving coal mining, has been applied in numerous mines in central and western China. This effectively alleviates water resource shortages and achieves the goal of water resource conservation. The CMURs utilizes the goaf created by longwall mining as the water storage space. The reservoir dam structure comprises coal pillars, which serve as protective coal pillars in the mining area, and artificial dam structures that filled the gaps between these coal pillars. The stability of the dam structure under the complex stress effects of hydraulic coupling has been identified as the key to maintaining the safe operation of the CMUR. The mechanical properties, stress field, fracture field, and seepage field (“three fields”) change mechanisms, as well as the research results on size optimization of coal pillar dams and artificial dams in CMURs, were systematically reviewed. The core content included the instability and failure mechanisms of dam structures under the comprehensive coupling effects of factors such as dry–wet cycles of mine water, long-term immersion, chemical effects of high-salinity water, dynamic and static loads, and cyclic loads. This paper is considered to have certain reference value for the study of the stability of dam structures in CMURs and to provide some guidance for the safe operation of CMURs.
- Open Access
- 17 March 2021
- Published by Hindawi Limited in Geofluids
- Vol. 2021, 1-13
Research on the Deformation Law of Jointed Surrounding Rock during Tunnel Excavation Based on Hydromechanical Coupling
The coupling of the joint network and groundwater in rock under bias conditions has a significant impact on the deformation and failure of the surrounding rock due to tunnel excavation. This paper studies the deformation and failure of surrounding rock after tunnel excavation under different joint network and groundwater conditions. A finite element-based composite joint network modeling method is proposed in this paper, and the typical parameters of the surrounding rock, such as the plastic zone size, vertical displacement, and lateral displacement, are analyzed and compared through numerical calculations. According to the different stratum and hydraulic conditions considered, four numerical models under four different working conditions are established and studied. The deformation and failure laws of the surrounding rock during tunnel excavation are obtained. The results show that with a single joint network, when there is no influence of groundwater, the surrounding rock mainly undergoes shear failure at the arch crown after tunnel excavation. When the influence of groundwater is considered, there are differences in the mode of damage between the left and right sides of the tunnel. The stratum approximately 1m from the invert breaks, and the right sidewall fails approximately 1m from the measuring point. In rock with a composite joint network, when groundwater is not considered, two kinds of failures occur in the surrounding rock near the tunnel; however, the surrounding rock far from the tunnel is dominated by shear failure. The stratum approximately 3.5m from the arch crown fractures and the surrounding rock within approximately 5.5m from the measurement point on the right sidewall undergoes separation failure. Under the dual effects of joints and groundwater, soft rock deforms considerably. The total hydraulic gradient decreases from left to right before and after tunnel excavation. The total hydraulic gradient of the composite joint network strata is generally smaller than that of the single joint network. In the composite joint network strata, the total hydraulic gradient near the tunnel changes dramatically. This research can provide a reference for tunnel engineering under similar conditions.
- 17 March 2021
- Published by Hindawi Limited in Geofluids
- Vol. 2021, 1-13
Open AccessResearch on the Deformation Law of Jointed Surrounding Rock during Tunnel Excavation Based on Hydromechanical Coupling
The coupling of the joint network and groundwater in rock under bias conditions has a significant impact on the deformation and failure of the surrounding rock due to tunnel excavation. This paper studies the deformation and failure of surrounding rock after tunnel excavation under different joint network and groundwater conditions. A finite element-based composite joint network modeling method is proposed in this paper, and the typical parameters of the surrounding rock, such as the plastic zone size, vertical displacement, and lateral displacement, are analyzed and compared through numerical calculations. According to the different stratum and hydraulic conditions considered, four numerical models under four different working conditions are established and studied. The deformation and failure laws of the surrounding rock during tunnel excavation are obtained. The results show that with a single joint network, when there is no influence of groundwater, the surrounding rock mainly undergoes shear failure at the arch crown after tunnel excavation. When the influence of groundwater is considered, there are differences in the mode of damage between the left and right sides of the tunnel. The stratum approximately 1m from the invert breaks, and the right sidewall fails approximately 1m from the measuring point. In rock with a composite joint network, when groundwater is not considered, two kinds of failures occur in the surrounding rock near the tunnel; however, the surrounding rock far from the tunnel is dominated by shear failure. The stratum approximately 3.5m from the arch crown fractures and the surrounding rock within approximately 5.5m from the measurement point on the right sidewall undergoes separation failure. Under the dual effects of joints and groundwater, soft rock deforms considerably. The total hydraulic gradient decreases from left to right before and after tunnel excavation. The total hydraulic gradient of the composite joint network strata is generally smaller than that of the single joint network. In the composite joint network strata, the total hydraulic gradient near the tunnel changes dramatically. This research can provide a reference for tunnel engineering under similar conditions.
- Open Access
A Numerical Investigation of the Deformation Mechanism of a Large Metro Station Foundation Pit under the Influence of Hydromechanical Processes
Considering the unique conditions of deep and large subway foundation pit excavation affected by heavy rainfall in soil-rock composite strata, this paper employs finite element numerical simulation methods to study foundation pit instability under the influence of heavy rainfall. According to the hydraulic coupling conditions caused by rainfall, a fluid-solid coupling numerical model for a deep and large subway foundation pit in soil-rock composite strata is established in this paper. By selecting the Anshan road station of Qingdao subway line 4 as the engineering background, various parameters related to foundation pit excavation affected by heavy rainfall at different excavation depths were analyzed. The study found that after the foundation pit was excavated, the surrounding pore water pressure decreased and the pore water pressure near the ground surface increased rapidly due to rainfall. As the horizontal distance from the foundation pit increased, the pore water pressure at the same depth also increased. The excavation of the foundation pit caused uplift of the bottom of the pit. After rainfall, the uplift value decreased compared with that before rainfall. With increasing excavation depth, the decreased value of the bottom uplift decreased and then increased. The rainfall caused the horizontal displacement of the pit walls on both sides of the pit to increase. When the excavation depth was 10 m, the horizontal displacements on both sides of the pit were equivalent. When the excavation depth was 20 m, the horizontal displacement was concentrated in the first 10 m; when the excavation depths were 30 m and 40 m, the horizontal displacement was concentrated in the first 13 m. This finding shows that when the foundation pit was affected by rainfall, the sidewall collapsed at a distance of 13 meters from the ground. As the excavation depth increased, the depth of excavation instability was closer to the bottom of the pit. The research in this paper can provide a reference for the construction of deep and large foundation pits in similar composite ground conditions that are affected by rainfall.
Open AccessA Numerical Investigation of the Deformation Mechanism of a Large Metro Station Foundation Pit under the Influence of Hydromechanical Processes
Considering the unique conditions of deep and large subway foundation pit excavation affected by heavy rainfall in soil-rock composite strata, this paper employs finite element numerical simulation methods to study foundation pit instability under the influence of heavy rainfall. According to the hydraulic coupling conditions caused by rainfall, a fluid-solid coupling numerical model for a deep and large subway foundation pit in soil-rock composite strata is established in this paper. By selecting the Anshan road station of Qingdao subway line 4 as the engineering background, various parameters related to foundation pit excavation affected by heavy rainfall at different excavation depths were analyzed. The study found that after the foundation pit was excavated, the surrounding pore water pressure decreased and the pore water pressure near the ground surface increased rapidly due to rainfall. As the horizontal distance from the foundation pit increased, the pore water pressure at the same depth also increased. The excavation of the foundation pit caused uplift of the bottom of the pit. After rainfall, the uplift value decreased compared with that before rainfall. With increasing excavation depth, the decreased value of the bottom uplift decreased and then increased. The rainfall caused the horizontal displacement of the pit walls on both sides of the pit to increase. When the excavation depth was 10 m, the horizontal displacements on both sides of the pit were equivalent. When the excavation depth was 20 m, the horizontal displacement was concentrated in the first 10 m; when the excavation depths were 30 m and 40 m, the horizontal displacement was concentrated in the first 13 m. This finding shows that when the foundation pit was affected by rainfall, the sidewall collapsed at a distance of 13 meters from the ground. As the excavation depth increased, the depth of excavation instability was closer to the bottom of the pit. The research in this paper can provide a reference for the construction of deep and large foundation pits in similar composite ground conditions that are affected by rainfall.