Complex Underground Environment Research Articles

Research on Path Planning of a Mining Inspection Robot in an Unstructured Environment Based on an Improved Rapidly Exploring Random Tree Algorithm

To ensure the safe production of mines, the intelligent trend of underground mining operations is gradually advancing. However, the operational environment of subterranean mining is intricate, making the conventional path-planning algorithm used by mining inspection robots frequently inadequate for real requirements. To safeguard the mining inspection robot, targeting the problem of low search efficiency and path redundancy in the path planning of the existing rapidly exploring random tree (RRT) algorithm in the narrow and complex unstructured environment, a path-planning algorithm combining improved RRT and a probabilistic road map (PRM) is proposed. Initially, the target area is efficiently searched according to the fan-shaped goal orientation strategy and the adaptive step size expansion strategy. Subsequently, the PRM algorithm and the improved RRT algorithm are combined to reduce the redundant points of the planning path. Ultimately, considering the kinematics of the vehicle, the path is optimized by the third-order Bessel curve. The experimental simulation results show that the proposed path-planning algorithm has a higher success rate, smoother path, and shorter path length than other algorithms in complex underground mining environments, which proves the effectiveness of the proposed algorithm.

Insulation life prediction of stacking multi-model fusion motors based on Conv1d-LSTM

Abstract The insulation system of the mine motor is key to ensuring its stable operation, which affects the efficiency of mine production and transportation and the benefit of enterprises. The prediction of motor insulation life can effectively prevent the deterioration of motor performance. Due to the complex underground environment, many factors affect the insulation of coal mine motors, which are not conducive to the selection of feature parameters. The insulation life prediction efficiency and accuracy of motors need to be improved. To solve this problem, this paper proposes a prediction method based on Conv1d (one-dimensional convolve) and LSTM (long short-term memory neural network), which integrates multiple models and the Stacking integrated algorithms. The operating data and environmental parameters of a coal mine motor under different conditions are analyzed. Three Conv1d-LSTM hybrid models with batch normalization, residual network, and dense number are used as the base learner, and the results are weighted by K-fold to verify the accuracy of the three models. The linear regression model is used as a meta-learner to prevent overfitting of the model and effectively improve the speed and accuracy of single network optimization. Compared with the traditional method, the results show that the optimization of the LSTM neural network by the multi-feature model has a higher accuracy in predicting the remaining life of motor insulation, which provides a new way for the prediction of motor insulation life.

Three-dimensional modelling of artificial caves for geomechanical analysis

Abstract. Accurate cave surveying is crucial for understanding their genesis, current state, and potential hazards, especially in challenging environments marked by limited accessibility and poor visibility. This study applies geomatics techniques, including Terrestrial Laser Scanning (TLS), SLAM-based Mobile Mapping Systems (MMS), and digital photogrammetry, to create three-dimensional models of artificial caves in Gravina in Puglia, Apulia region, southern Italy. The research aims to assess these methodologies' accuracy, reliability, and performance for structural monitoring and hazard assessment. Despite challenges such as rough conditions, limited accessibility and poor visibility, the study reveals promising insights into the capabilities of these techniques for efficient surveying in complex underground environments. While highlighting the potential of MMS for cost-effective and rapid data acquisition, digital photogrammetry using spherical cameras also emerges as a viable alternative, offering comprehensive data collection capabilities with minimal capture time. Further research is warranted to optimize these techniques for enhanced hazard assessment and structural monitoring in challenging underground environments.

Prediction of external corrosion rate for buried oil and gas pipelines: A novel deep learning method with DNN and attention mechanism

Buried pipelines is easily subjected to external corrosion affected by complex underground environment, such as soil resistivity, pH, dissolved ion concentration, water content and coatings condition. Therefore, external corrosion rate prediction is essential to ensure pipelines intrinsic safety. Generally numerous researches focused on mathematical models and degradation analysis are limited to considering comprehensive corrosion factors. In this work, a novel proposed deep learning method involves a deep neural network (DNN) and attention mechanism which has good robust generalization ability. DNN was used to predict external corrosion rate of buried pipelines with extracting corrosion characteristics data, and attention mechanism is carried on weighting operations of corrosion factors furtherly. The results show that main controlling factors are pipeline age and soil bulk density, sulfate ion concentration and redox potential have less effect by analyzing external corrosion factors dataset, and data reduction and standardization of DNN-attention mechanism model are carried out. The external corrosion rate value predicted by the DNN-attention mechanism model is the closest prediction with the real truth, which the evaluation index root mean square error (RMSE) is 0.0064, and prediction accuracy is 91.91 % compared with convolutional neural network (CNN), CNN-residual, DNN. It proves that it is reasonable to predict pipeline external corrosion rate using DNN-attention mechanism based on publicly pipeline corrosion dataset.

A study on the application of building information modeling technology in geotechnical engineering

Building information modeling (BIM) technology has brought significant changes to the construction industry, but its application in geotechnical engineering is still in its early stages. Despite challenges, an increasing number of professionals recognize the potential of BIM in geotechnical engineering. This paper studies the application of BIM technology in geotechnical engineering, including an analysis of BIMs characteristics, advantages, and challenges. It can be concluded that while facing complex underground environments, data acquisition difficulties, and compromised model accuracy, the integration of geological and soil data requires tools and standards, and subsurface and surface interactions demand intricate simulations. However, through secondary development, functional optimization, and advancements in exploration techniques, BIM still holds promise in geotechnical engineering. It aids assistant engineers in understanding subterranean environments, refining foundational designs, predicting issues, and facilitating construction management. Despite present hurdles, the application of BIM in geotechnical engineering is anticipated to grow gradually with the progress of technology, bringing forth more advantages and transformation.

Multi-Scale Adaptive Feature Network Drainage Pipe Image Dehazing Method Based on Multiple Attention

Drainage pipes are a critical component of urban infrastructure, and their safety and proper functioning are vital. However, haze problems caused by humid environments and temperature differences seriously affect the quality and detection accuracy of drainage pipe images. Traditional repair methods are difficult to meet the requirements when dealing with complex underground environments. To solve this problem, we researched and proposed a dehazing method for drainage pipe images based on multi-attention multi-scale adaptive feature networks. By designing multiple attention and adaptive modules, the network is able to capture global features with multi-scale resolution in complex underground environments, thereby achieving end-to-end dehazing processing. In addition, we also constructed a large drainage pipe dataset containing tens of thousands of clear/hazy image pairs of drainage pipes for network training and testing. Experimental results show that our network exhibits excellent dehazing performance in various complex underground environments, especially in the real scene of urban underground drainage pipes. The contributions of this paper are mainly reflected in the following aspects: first, a novel multi-scale adaptive feature network based on multiple attention is proposed to effectively solve the problem of dehazing drainage pipe images; second, a large-scale drainage pipe data is constructed. The collection provides valuable resources for related research work; finally, the effectiveness and superiority of the proposed method are verified through experiments, and it provides an efficient solution for dehazing work in scenes such as urban underground drainage pipes.

Analysis of strength failure in gangue-based cementitious backfill body from a microscopic perspective.

Backfill mining is an effective way to solve environment pollute, surface subsidence, and groundwater system damage which caused by coal mining. However, the complex underground environment may change the physical and mechanical properties of the backfill body, which poses a risk of strength failure. This paper analyzed the failure of gangue-based cemented backfill body which made up of gangue and fly ash. The results show that physicochemical reactions will generate quartz, kaolinite, and other high-strength substances; hydration reaction between the fine particles will generate hydrocalcium silicate and other C-S-H gels, they wrapped gangues as a whole, which provide a high strength of the cemented backfill body. Several experiments were carried out in order to find the reason for failure in samples under loads. The conclusion drawn as following: (1) When the load is large, the cracks extend from the surface of the samples to the interior, at the same time, the length and width of the cracks increasing obviously and connecting as net. Especially the external load exceeds the peak intensity. (2) The relationship between sample failure and pores is weak, but obvious with crack development, especially the cracks connected as a net. (3) The interface structure formed by gangue is an important source of crack development and, thus, will stimulate the development of cracks.

Intelligent management of carbon emissions of urban domestic sewage based on the Internet of Things

Domestic wastewater is one of the major carbon sources that cannot be ignored by human society. Against the background of carbon peaking & carbon neutrality (Double Carbon) goals, the continuous urbanization has put heavy pressure on urban drainage systems. Nevertheless, the complex subjective and objective conditions of drainage systems restrict the field monitoring, measurement, and analysis of drainage systems, which has become a great obstacle to the study of carbon emissions from drainage system. In this paper, 3389 sensor terminals of Internet of Things (IoT) are used to build a field monitoring IoT for urban domestic wastewater methane (CH4) carbon emission, with 21 main districts of Chongqing Municipality in China as the study area. Incorporating Fick's law of diffusion, this field monitoring IoT derives a measurement model for methane carbon emissions based on measured concentrations, and solves the problems of long-term and stable monitoring and measurement of methane gas in complex underground environment. With GIS spatio-temporal analysis used to analyze the spatial and temporal evolution patterns of carbon emissions from septic tanks in drainage systems, it successfully reveals the spatial and temporal distribution of methane carbon emissions from drainage systems in different seasons, as well as the relationship between methane carbon emissions from drainage systems and the latitude of direct sunlight. Applying the DTW method, it quantifies the stability of methane monitoring in drainage systems and evaluates the effects of Sampling Frequency (SF) and Number of Devices Terminal (NDT) on the stability of methane monitoring. Consequently, an intelligent management system for carbon emissions from urban domestic wastewater is constructed on the base of IoT, which integrates methane monitoring, measurement and analysis in septic tanks of drainage systems.

A high resolution detection approach combining probe drilling and horizontal cross-hole resistivity tomography to interpret water conducting channels ahead of the tunnel: A case study in Yunnan, China

The geological conditions in Yunnan Province, China, are intricate, and numerous challenges are anticipated during tunnel excavation. The goal of this study was to develop a high resolution detection approach combining probe drilling and horizontal cross-hole resistivity tomography to interpret water conducting channels ahead of the tunnel. A complex section of the Xianglu Mountain tunnel was taken as an example. Drilling data from 10 boreholes are used to establish the initial resistivity model ahead of the tunnel face. The utilization of drilling data as a priori information refines the horizontal cross-borehole resistivity tomography imaging results, providing a more accurate depiction of the subsurface conditions. In practical applications, the use of multiple boreholes for high resolution detection via probe drilling analysis and horizontal cross-hole resistivity tomography is relatively uncommon in complex underground environments and represents an engineering innovation. At the Xianglu Mountain tunnel site, 13 electrical resistivity tomography (ERT) profiles were executed to thoroughly assess the geological conditions. A 3-D resistivity model was constructed via interpolation of this dataset. The 3-D resistivity model not only facilitated precise estimation of the 3-D hydrogeological environment at the Xianglu Mountain tunnel site but also enhanced the accuracy of identifying the water conducting channels by revealing low-resistivity interconnected zones. This approach offers a precise guide for determining the location of the critical water conducting channels and for optimizing grouting treatment strategies based on the characterization, geometry, resistivity spatial distribution, and hydrogeological conditions of the studied zones. The acquired results, which are in good accordance with the reality of the studied area in terms of locating the water conducting channels, can be utilized to develop preventative techniques for water and mud inrush disasters during tunnel construction.

Simulation and Application of Windowing for High-Grade Steel Thick-Wall Casing in Ultradeep Wells: A Case Study of ST102 Well

Windowing processes in ultradeep wells (> 7000 m) with high steel grade (TP155V) and thick-wall (15.83 mm) casing not only face complex underground environments with high temperature and pressure but also have the difficulty of long operation time and high cost. To improve the success rate and operational efficiency, CAE software was used to establish the casing windowing side-drilling simulation model and optimize the windowing milling cone. Field applications were used to further demonstrate the simulation results. The main conclusions are as follows. The simulation shows that the milling shoulder and the outer circle of the cone top are the main working faces in window opening and window repair. The conical milling cone has the largest windowing stress, highest windowing efficiency, and regular shape of the window. A casing with a depth of 7473 m, wall thickness of 15.83 mm, and steel grade TP155V was successfully windowing using six conical milling cone in the ST102 well, taking 51.76 h, and generating 94 kg iron chips in total; the average milling speed was 0.06 m/h; The casing windowing progress can be determined by observing the return state of the cuttings. ST102 well set three records in China for the deepest drilling depth, highest steel grade, and thickest wall thickness.

The Application of SLAM in Life and Scientific Research

This article mainly focuses on the application of SLAM in technology and provides a literature review on the following aspects: 1) The application of SLAM in automatic parking of automobiles. This includes using AVP-SLAM for high-precision automatic parking in outdoor parking lots using convolutional neural networks, and using MOFISLM for high-precision automatic parking when indoor GPS signals are poor. 2) The application of SLAM in robotics. It includes three aspects. The first is using the GMapping algorithm to construct and locate maps with high accuracy, low computational complexity, and high robustness, enabling robots to plan the shortest path in unknown environments. The second is to use ORB-SLAM2, which can handle more complex situations, to navigate medical institution robots to improve hospital efficiency and reduce disease transmission rates. The third is for robots that perform tasks in complex and unknown terrains. The improved version of LAMP1.0, LAMP2.0, which is suitable for complex underground environments, can achieve multi robot collaborative cooperation with high accuracy and robustness. 3) Application of SLAM in the field of unmanned aerial vehicles. This article mainly elaborates on four aspects. The first is to use visual SLAM to achieve collaborative work between ground robots and drones, and to utilize the high camera advantage of drones to quickly build maps for ground robots, improve accuracy, and save time. The second is to utilize the application of VSLAM on unmanned aerial vehicles to contribute to agriculture. The third is ORB-SLAM3 to provide rapid and high-precision landing on deck for unmanned aerial vehicles in maritime missions. The fourth is using SLAM to assist unmanned aerial vehicles in landing in emergency or position situations (such, when GPS signals are lost).

A framework for GPR‐based water leakage detection by integrating hydromechanical modelling into electromagnetic modelling

AbstractTimely and accurate detection of water pipe leakage is critical to preventing the loss of freshwater and predicting potential hazards induced by the change in underground water conditions, thereby developing mitigation strategies to improve the resilience of pipeline infrastructure. Ground‐penetrating radar (GPR) has been widely applied to investigating ground conditions and detecting pipe leakage. However, due to uncertainties of complex underground environments and time‐lapse change, a proper interpretation of GPR data has been a challenging task. This paper aims to leverage hydromechanical (HM) modelling to predict electromagnetic (EM) responses of water leakage detection in diverse leakage cases. A high‐fidelity 3D digital model of an actual pipeline network, hosting pipes with various sizes and materials, was reconstructed to represent the complex geometry and various mediums. The interoperability between the digital model and the numerical models utilized in HM and EM simulations was improved to better capture the irregular pipelines. Based on Kriging interpolation and the volumetric complex refractive index model, a linking technique was employed to replicate material heterogeneity caused by water intrusion. Thus, a framework was developed to accommodate the interoperability among digital modelling, HM modelling and finite‐difference time‐domain forward modelling. Moreover, sensitivity studies were conducted to evaluate the influences of different time stages, leak positions and pipe types on GPR responses. In GPR B‐scans, the presence of hyperbolic motion and horizontal reflections serve as indicators to estimate the location and scale of water leakage. Specifically, a downward‐shifting hyperbola indicates that the pipeline is submerged by leaked water, whereas the emergence of horizontal reflection is linked to the wetting front of saturated areas. The developed framework can be expanded for complicated applications, such as unknown locations and unforeseen failure modes of pipelines. It will increase the efficiency and accuracy of traditional interpretations of GPR‐based water leakage detection and thus enable automated interpretations by data‐driven methods.

Experimental Investigation on the Anchorage Performance of a Tension–Compression-Dispersed Composite Anti-Floating Anchor

Rapid advancements in construction technologies have accelerated the development of complex and deep underground structures, raising concerns about the impact of groundwater on structures, particularly anti-floating measures. Traditional tensioned anchors, commonly used for preventing flotation, suffer from limitations like low pull-out bearing capacity, shallow critical anchoring depth, and localized stress concentration. To overcome these limitations, this paper introduces a tension–compression dispersed composite anchor, which combines casing, load-bearing plates, and tensioned anchors. Comparative tests were conducted between these composite anchors and traditional tensioned anchors to analyze their anchoring behavior. Our results show that tensioned anchors exhibit a stable axial force distribution as anchoring length increases. By identifying abrupt changes in the axial force curve, optimal anchoring lengths for load-dispersed anchors can be determined, thereby enhancing rock and soil strength utilization. The tension–compression-dispersed composite anchor outperforms tensioned anchors, with 1.44 times the ultimate bearing capacity for equivalent anchoring lengths and 1.1 times the capacity for an additional 1 m length. It also displays superior deformation adaptability and structural ductility under high-bearing loads compared to tensioned anchors with extended anchoring lengths. Effectively mobilizing the strength of the lower anchoring segment within the rock and soil results in a lower critical anchoring depth and a more uniform distribution of lateral friction resistance. In conclusion, the tension–compression-dispersed composite anchor offers significant advantages, making it a promising engineering solution for anti-floating anchor systems in complex underground environments.

E. coli phage transport in porous media: Response to colloid types and water saturation

Because of its long survival time, high migration ability and high pathogenicity, the migration of the virus in the subsurface environment deserves in-depth exploration and research. In this study we investigated the migration behavior of E. coli phage (VI) with organic colloids (HA) or inorganic colloids (SiO2) in the saturated or unsaturated bands and compared the differences in their migration mechanisms.The effects of different colloids on the surface characteristics of VI were analyzed according to particle size and zeta potential. Column experiments were conducted to simulate their migration in the subsurface environment. The results show that HA enhances the stability of VI-HA, promotes VI migration and plays a dominant role in its migration process under both saturated and unsaturated conditions. In contrast, SiO2 puts VI-SiO2 in an unstable state and is easily separated in the unsaturated state, thus promoting VI migration. Based on migration experiments, the extent of influence factors on VI migration was quantified and compared. The effect of colloids on VI migration is greater than that of moisture content, where the effect of HA is greater than that of SiO2. This study provides an experimental research idea to determine the dominant factors affecting virus migration, and provides a general direction and theoretical basis for the biological risk assessment of pathogenic microorganisms in complex underground environments, in order to enable the decision makers to make a response in time, accurately, and efficiently.

A method to predict rockburst using temporal trend test and its application

Rockbursts have become a significant hazard in underground mining, underscoring the need for a robust early warning model to ensure safety management. This study presents a novel approach for rockburst prediction, integrating the Mann-Kendall trend test (MKT) and multi-indices fusion to enable real-time and quantitative assessment of rockburst hazards. The methodology employed in this study involves the development of a comprehensive precursory index library for rockbursts. The MKT is then applied to analyze the real-time trend of each index, with adherence to rockburst characterization laws serving as the warning criterion. By employing a confusion matrix, the warning effectiveness of each index is assessed, enabling index preference determination. Ultimately, the integrated rockburst hazard index Q is derived through data fusion. The results demonstrate that the proposed model achieves a warning effectiveness of 0.563 for Q, surpassing the performance of any individual index. Moreover, the model's adaptability and scalability are enhanced through periodic updates driven by actual field monitoring data, making it suitable for complex underground working environments. By providing an efficient and accurate basis for decision-making, the proposed model holds great potential for the prevention and control of rockbursts. It offers a valuable tool for enhancing safety measures in underground mining operations.

Water-Adaptive Microcapsules with a Brittle-Ductile-Brittle Transition Based on an O/W/O Emulsion for the Self-Healing of Cementitious Materials.

Cementitious materials inevitably develop cracks, posing a serious threat to the long-term security of infrastructure, especially in the complex underground environment of cementing engineering. Microcapsules are facing the problem of encapsulated structure damage during the mixing and breaking difficultly during self-healing when applied in cementitious materials, resulting in the decline of self-healing efficiency. Herein, the calcium alginate water-adaptive microcapsules (CaAlg-NS/E-51) were prepared via an O/W/O emulsion, and the water adaptability of the shell was applied to achieve a rapid brittle-ductile transition by absorbing water. The water adaptability of the microcapsule is conducive to resisting shear stress during stirring due to the decreased elastic modulus and the increased ductility of the shell when it absorbs water. Meanwhile, the water-bearing shell loses water and becomes brittle during dry curing, making it prone to fracture when self-healing. In the self-healing measurement, the self-healing efficiency of cementitious specimens with microcapsules absorbing water for 10 min improved by 234.9 and 60.0% at 1 and 7 days, respectively, compared with those containing dry microcapsules, owing to the water adaptability of the shell.

An Improved Fault Diagnosis Approach for Pumps Based on Neural Networks with Improved Adaptive Activation Function

Due to the complex underground environment, pumping machines are prone to producing numerous failures. The indicator diagrams of faults are similar to a certain degree, which produces indistinguishable samples. As the samples increase, manual diagnosis becomes difficult, which decreases the accuracy of fault diagnosis. To accurately and quickly judge the fault type, we propose an improved adaptive activation function and apply it to five types of neural networks. The adaptive activation function improves the negative semi-axis slope of the Rectifying linear unit activation function by combining the gated channel conversion unit to improve the performance of the deep learning model. The proposed adaptive activation function is compared to the traditional activation function through the fault diagnosis data set and the public data set. The results show that the activation function has better nonlinearity and can improve the generalization performance of the deep learning model and the accuracy of fault diagnosis. In addition, the proposed adaptive activation function can also be well-embedded into other neural networks.

H2S-responsive zwitterionic hydrogel as a self–healing agent for plugging microcracks in oil-well cement

During cementing construction, H2S gas leak from micro-cracks of cement ring or cementing interface, seriously damaging wellbore integrity and shortening the life of wells. Therefore, microcrack self-healing cement technology is of great significance for oil wells to maintain the durability of cement rings and adapt to complex underground environments. Herein, acrylamide (AM), acrylonitrile (AN) and N-vinylformamide (NVF) were used as functional monomers, and laponite was added to prepare Laponite-poly(acrylamide-acrylonitrile-n-vinylformamide) nanocomposite hydrogel (L-PMAN) with excellent mechanical strength as micro-crack repair agent for gas-triggered cementing cement sheath. Considering the difference of chemical environment in the process of wellbore cement slurry sealing and subsequent micro-fracture plugging, different structural units were selected to design amphoteric structure. The construction of zwitterionic structure makes it exhibit excellent swelling behavior in salt solution while maintaining 80% of the original mechanical strength. More importantly, after adding L-PMAN powder,cement stone (C1) can achieve good repair of microcracks under the trigger of H2S within 3 days, and the maximum gas breakthrough pressure can reach 2.5 MPa, indicating the great potentials of the L-PMAN for plugging microcracks in cement sheath.

Numerical investigation of seismic wavefield characteristics induced by a tensile source in a heterogeneous mining environment

Mining-induced tremors serve as the main dynamic stress source of coal bursts which represent one type of the most critical mining disasters in underground coal mines. To evaluate coal burst risks and comprehend the response of the coal-rock mass to seismic waves, microseismic monitoring stands as the principal method. By inferring the zones with elevated coal burst risks based on the seismic event clusters, valuable insights can be gained. However, because of limited seismic monitoring results generated from an individual seismic event, the recognition of the corresponding dynamic disturbance process remains ambiguous. The dynamic disturbance process presents immense complexity due to the focal mechanism and heterogeneous medium, particularly under the effect of structural heterogeneity induced by large-scale mining operations. In this study, forward numerical modelling was employed to gain the comprehension of seismic wave propagation affected by extraction zones. The findings revealed heightened intricacy of the wavefields and increased displacement concentrations around the working face. The characteristics of peak particle velocity (PPV) and displacement spectra were investigated in the near- and far-field zones, respectively. Owing to the existence of the extraction zone, both a significant amplification effect and the redistribution of PPV were observed around the near-field zone. The intricate wavefield caused by the focal mechanism and extraction zones resulted in more scattered distributions of the low-frequency spectral level, which can potentially cause an overestimation of source intensity. However, the impact of the complex wavefield on the corner frequency was limited. Through the analysis of the PPV attenuation law, as well as the distribution of both seismic moment and source radius, this study offered valuable insights for seismic risk assessment. The forward modelling approach facilitated the identification of high-risk potential areas resulting from seismic events, which deepened our comprehension of the dynamic disturbance process in the complex underground mine environment.

Automatic recognition of effective and interference signals based on machine learning: A case study of acoustic emission and electromagnetic radiation

Integrated monitoring technology using acoustic emission (AE) and electromagnetic radiation (EMR) is a promising mean for monitoring coal and rock dynamic disasters. However, due to the complex underground environment, blasting, drilling and mechanical operations may generate interference signals that affect the accuracy of early warning. It is essential to study the automatic recognition of effective and interference signals for AE and EMR. For this reason, a field test of synchronous AE-EMR monitoring was conducted in a coal mine. Further, the time domain, frequency domain and fractal characteristics of effective and interference signals for AE and EMR were analyzed, and sensitive characteristics were obtained by the Relief algorithm. Based on this, automatic recognition models of effective and interference signals were established by Fisher's linear discriminant method, support vector machine and ensemble learning method, respectively. Field application showed that support vector machine performed higher recognition accuracy. The AE and EMR warning indicators were obtained based on the signal recognition model, and the results show that the indicators reflect the risk of rock burst more accurately and earlier than the original indicators before the removal of interference signals.