36results about How to "Efficient mining" patented technology

The invention discloses a medical data processing method and system combining big data and smart medical treatment, and relates to the technical field of data processing, and the method comprises the steps: obtaining a historical anatomical record based on the big data, and carrying out the analysis to obtain an anatomical data set; calling a preset data processing mechanism for processing and analyzing to establish an anatomical medical database; calling a predetermined association analysis strategy to perform association analysis to obtain an association list; performing multi-dimensional feature collection on a target user of smart medical treatment to obtain target feature data; collaboratively forming target input data; and activating the intelligent prediction model for analysis to obtain a target output result and performing early warning intervention processing. The technical problems of low medical data processing efficiency, insufficient association between anatomical knowledge and patient individual features and limited intelligent early warning ability in the prior art are solved, and the technical effects of efficiently mining anatomical data values, accurately associating patient multi-dimensional features and improving intelligent medical prediction and intervention ability are achieved.

The invention provides a rapid pollutant detection method based on spectral feature analysis, and relates to the technical field of environmental pollutant spectral detection, and the method comprises the following steps: obtaining an original absorption spectrum of a sample, and preprocessing and reconstructing an intrinsic spectral signal; extracting three types of features of morphology, frequency domain energy distribution and phase disturbance, and splicing to obtain a multi-dimensional joint feature tensor; pollutant classification and confidence judgment are completed through an improved CNN, and concentration is predicted through a linear regression model synchronously; in combination with a Mahalanobis distance verification result, deep residual network secondary feature mining is triggered for a low-confidence sample, a final type is determined according to a fusion result, and the concentration is corrected; and generating a detection report and dynamically updating the spectral feature intrinsic library. The method is adaptive to a portable ultraviolet-visible spectrophotometer, the single sample detection time consumption is less than 10min, the classification accuracy is greater than or equal to 90%, the unknown pollutant judgment accuracy is greater than or equal to 89%, and the method is suitable for on-site rapid detection.

The present application provides a kind of coal mine with the integrated equipment of digging anchor, it includes body, supporting device and adjustment component;Supporting device includes support frame and guard plate component, support frame is connected with body and can be rotated around the straight line of the width direction of body relative to body, support frame includes the first frame body and second frame body connected, second frame body can be rotated around the straight line of the length direction of body relative to first frame body, guard plate component is arranged in second frame body;Adjustment component includes first driver, the output end of first driver is drivingly connected with second frame body, first driver is used to drive second frame body to rotate relative to first frame body, so that guard plate component adapts to the inclination angle of roadway roof.The present application can realize the efficient integration of tunneling and supporting by the cooperative work of body, supporting device and adjustment component, so that the equipment can flexibly adapt to various complex conditions of coal mine roadway, provide a safer and more efficient solution for coal mining.

The application provides a ship-vehicle-person virtual image establishment method and system, which comprises the following steps: obtaining ship, personnel and vehicle data as source data for preprocessing, calculating and mining labels according to the preprocessed source data, and producing ship, personnel and vehicle labels; defining hierarchical labels; defining group labels; extracting basic attributes of the ship, personnel and vehicle; defining personalized labels, adding personalized labels to the ship, personnel and vehicle according to their basic attributes and respective source data; defining correlation relationship labels among the ship, personnel and vehicle; creating a label table in a database, adding the calculated labels into the label table, and then performing correlation analysis on the respective source data of the ship, personnel and vehicle and the label table according to business requirements to obtain index data; and providing the index data to a ship-vehicle-person virtual image system for drawing charts. The application can improve traffic operation efficiency, safety and risk prediction.

The application is a medical image segmentation method based on multi-modal self-supervision. First, the multi-modal medical image of the lesion tissue is obtained, including A-mode image and B-mode image, and the image is preprocessed. Then, a cycle-consistent modal contrast domain translation network is constructed, including two generators and two discriminators. The generator is used to convert the image of one mode into the image of another mode, including an encoder, an intermediate shared module and a decoder. The discriminator is used to judge the source of the input. Then, the cycle-consistent modal contrast domain translation network is pre-trained, the training loss is calculated, and the loss function includes multi-modal semantic consistency loss, adversarial loss, cross-domain translation loss and cycle consistency loss. Finally, the A-mode segmentation network and the B-mode segmentation network are constructed, the pre-trained weights are migrated to the two segmentation networks, and the trained two segmentation networks are respectively used for medical image segmentation of the corresponding mode. The contrast cross-domain translation is used as a multi-modal self-supervised pre-training task to learn more comprehensive modal features, promote the network to better learn modal characteristics and common knowledge, and improve the segmentation ability.

The invention relates to a semi-supervised semantic segmentation method based on adaptive pseudo label generation, which realizes adaptive control of pseudo label quality by constructing category prototype representation containing a feature mean value and a standard deviation and introducing standard deviation information into a pseudo label screening and prototype consistency learning process. The method comprises a class prototype generation module, an adaptive pseudo-label generation module and a prototype consistency learning module, dynamically adjusts a pseudo-label screening threshold by combining prediction probability distribution and class prototype similarity, and introduces a prototype-based feature consistency constraint in a training process. Therefore, the segmentation precision and the training stability of the semantic segmentation model are remarkably improved under the condition of a small amount of annotated data.

The present application belongs to the technical field of speech analysis, and discloses an English oral pronunciation quality evaluation method based on multi-modal speech feature analysis, which comprises the following steps: obtaining the speech signal of the target user's English oral speech, and performing multi-domain decomposition on the speech signal to obtain multi-modal speech features; performing time-frequency domain corresponding relationship analysis and feature extraction on the multi-modal speech features to obtain a pronunciation detail feature sequence; performing multi-scale matching on the pronunciation detail feature sequence and a preset standard pronunciation template, and constructing a multi-dimensional representation model based on the multi-scale matching result; calculating the fine-grained quality score of the phoneme unit in each multi-dimensional representation model in combination with the prosody rhythm parameters in the multi-modal speech features; and fusing the prosody coherence score and the overall fluency score to generate a comprehensive pronunciation quality evaluation result and a visual diagnostic report of pronunciation deviation; the present application realizes comprehensive and refined evaluation of English oral pronunciation, and provides scientific guidance basis for personalized language learning.

The invention discloses a flood classification and identification method based on flood feature analysis, and belongs to the technical field of hydrological forecasting and flood control and disaster reduction. According to the method, for the problem that a traditional hydrological model is unstable in performance when processing different types of floods, feature indexes of historical flood events are extracted through a system, advanced dimension reduction, clustering and recognition technologies are combined, accurate classification and real-time recognition of the flood events are achieved, and therefore differentiated parameter sets are provided for the hydrological model; and the accuracy and adaptability of flood forecasting are remarkably improved. The method not only reduces the influence of hydrological process heterogeneity on forecasting precision, but also provides more reliable technical support for flood control and disaster reduction decision-making. And taking M basin flood forecasting application as an example, the reasonability and effectiveness of the method are verified.

The invention provides a femoral neck fracture image analysis method and system based on preoperative double-view X-rays, and belongs to the technical field of medical image processing. The method comprises the following steps: acquiring anterior and lateral X-ray images of the hip joint of a patient before an operation; performing geometric constraint-based standardized preprocessing on the image to obtain a normal position ROI and a lateral position ROI; performing contrast enhancement on the ROI by adopting a dark channel prior algorithm; inputting the enhanced double-view ROI into a weight-shared feature fusion neural network model for deep feature extraction and fusion; and finally generating an analysis value for evaluating the state of the femoral head based on the fusion features. According to the femoral neck fracture image analysis method and system based on the preoperative double-view X-rays, the defects that an existing analysis method is high in subjectivity and insufficient in feature utilization are overcome through the double-view information fusion and deep learning technology, and objective, accurate and automatic analysis of the femoral head postoperative state is achieved.

This invention provides a method for constructing and reasoning a ship navigation knowledge graph based on multi-source heterogeneous data, involving the intersection of artificial intelligence and maritime technology. The method includes: Step S1, establishing a ship navigation knowledge model; Step S2, acquiring and preprocessing multi-source heterogeneous data; Step S3, performing named entity recognition on the preprocessed data based on a BiLSTM-CRF hybrid model incorporating domain dictionary features; Step S4, extracting entity relationships from the entities identified in Step S3 using a pre-trained BiLSTM hybrid model incorporating interactive attention mechanisms; Step S5, fusing knowledge from the entities and entity relationships extracted in Steps S3 and S4 to construct a preliminary knowledge graph; Step S6, performing link prediction on the preliminary knowledge graph based on an RGCN model incorporating temporal constraints and rule logic to achieve knowledge completion and reasoning. This invention improves the ability to respond to risks in complex navigation scenarios.

The present application relates to the technical field of coal mine underground transportation equipment, and particularly relates to a fully mechanized coal mining face crossheading single rail train system and advancing method, wherein the fully mechanized coal mining face crossheading single rail train system comprises a trailer, a train set and a pipe cable telescopic device connected in sequence, the tail of the pipe cable telescopic device is connected with a reversed loader, a track is laid under the train set, the train set travels along the track, the trailer is connected with the track through a cross connector and drags the track to advance; the advancing method comprises the steps of pulling and moving the track, pulling and moving the train set, advancing the working face and cyclically advancing. The present application realizes the rapid and continuous movement of the train through the long-distance alternate movement of the track and the train, without the need of frequently disassembling and laying tracks and the need of winch steel wire rope traction, can effectively reduce the labor intensity and operation time of workers and improve the safety of train operation.

The application provides a SAR image target recognition method based on a saliency map guide, comprising: generating a corresponding target saliency map according to an original SAR image, wherein the target saliency map contains target key information; extracting deep features and shallow features in the original SAR image based on the target saliency map, and guiding the deep features and the shallow features to be fused; refining the fused image features by using a multi-layer hollow convolution to obtain target features; and performing type recognition on the target features by using a full connection layer to obtain a target recognition result. The application avoids noise interference in a background image, improves in-class consistency of target features, can efficiently and robustly realize mining of basic features of a target, and improves precision and efficiency of SAR image target recognition.

This invention belongs to the field of computer vision technology, specifically relating to a skin lesion image segmentation method based on a Transformer dual-branch model. The method constructs and trains a Transformer dual-branch model, inputting the image to be processed into the trained Transformer dual-branch model to obtain the segmentation result. The Transformer dual-branch model includes a main branch network, an auxiliary branch network, and an information aggregation module. This invention proposes a novel skin lesion image segmentation method that addresses the shortcomings of traditional deep learning methods in extracting global contextual information. It utilizes an efficient multi-scale visual Transformer as an encoder to extract more powerful and robust features. Simultaneously, it introduces low-level feature modules and high-level feature fusion modules to effectively improve the network's feature learning ability and segmentation performance.

A deep learning-based method for reconstructing the two-dimensional vector vibration direction of a multi-core optical fiber includes: constructing simulated noise-free data; selecting the same multi-core fiber grating sensor as the simulation, providing the same two-dimensional vibration excitation parameters as the simulation, and collecting measured sensor data; preprocessing the measured sensor dataset to achieve standardized alignment between the measured data and the simulation data; constructing a deep learning model for two-dimensional vibration direction reconstruction; optimizing the deep learning model through a phased training and transfer learning strategy; and reconstructing the two-dimensional vector vibration direction based on the trained deep learning model. This invention automatically extracts complex temporal features from wavelength drift signals by constructing a deep learning model, learns the temporal variation patterns and inter-channel coupling relationships in the signal, effectively mining vibration direction-related information, and overcomes the limitations of traditional geometric models that rely on the assumption of an ideal optical fiber structure, significantly improving the accuracy and precision of vibration direction reconstruction.

This invention belongs to the field of power system technology, specifically relating to a method and system for mining rules for electricity price and fee consistency verification. The method includes: acquiring a verification dataset and calculating the equivalence partitions of quantity, price, and fee data; using a depth-first spatial search strategy to mine data consistency relationships, obtaining a set of consistency relationships in the data; using the obtained set of consistency relationships to perform rule parsing on the quantity, price, and fee consistency relationships; and identifying rare data in the quantity, price, and fee data through rule parsing. This invention applies a novel consistency rule mining method for categorized data to the verification of electricity price and fee data. It can proactively mine potential rules in the data, effectively overcoming the shortcomings of previous manual rule definition methods, such as high workload, long time consumption, insufficient rule coverage, and the ability to only discover abnormal business data covered by defined rules. This assists business personnel in completing the verification of electricity marketing quantity, price, and fee data more intelligently and comprehensively.

The present specification provides a determination method and device of a multi-task inversion model and a multi-task elastic parameter inversion method. The determination method of the multi-task inversion model comprises: inputting pre-stack seismic data samples into the multi-task inversion model to obtain a plurality of different elastic parameter data; inputting the plurality of different elastic parameter data into a forward model to obtain predicted pre-stack seismic data; determining a pre-stack seismic loss according to the pre-stack seismic data samples and the predicted pre-stack seismic data; determining an elastic parameter loss according to label data corresponding to the plurality of different elastic parameter data and the pre-stack seismic data samples; adjusting parameters of the multi-task inversion model and the forward model according to the pre-stack seismic loss and the elastic parameter loss; wherein the adjusted multi-task inversion model is used to determine a plurality of different target elastic parameter data according to target pre-stack seismic data. The above method can improve the prediction accuracy and efficiency of different elastic parameter data.

The application provides a multi-modal bias detection method based on style features, which first constructs a multi-modal data set containing news text, pictures and political bias labels and extracts statistical multi-level style features; then extracts deep semantic information of text and image respectively to obtain multi-modal semantic feature representation; then constructs text style, image style and cross-modal consistency features; then takes multi-modal semantic features as the main representation and multi-level style features as the adjustment signal, realizes style-guided feature fusion through a structured fusion mechanism and outputs the prediction result; then based on a multi-modal large language model, generates an explanation text by taking news content, the prediction result and a preset prompt template as input and encodes the explanation text into an explanation representation; finally, takes the explanation representation as an intermediate variable, constructs the causal relationship among multi-modal hidden variables, the explanation representation and the prediction result through variational causal reasoning, and introduces a consistency constraint loss. The application improves the detection accuracy, stability and explainability.

The invention discloses a hyperspectral anomaly detection method based on spatial spectrum attention enhancement and a blind spot U-Net network, the overall architecture of the network is in a U-Net form, and interference of an abnormal target on subsequent feature extraction is eliminated through mask convolution and down-sampling operation. Firstly, in order to effectively capture global information, a spectrum-space self-attention module is embedded in a network; particularly, for a spatial self-attention module, in order to prevent blind spot information from interfering subsequent feature extraction, a mask is added to an attention map to meet blind spot requirements. In addition, in order to perceive the multi-class attributes of the background, an attention module based on a sequence dictionary is designed in the potential layer space. The multi-class attributes of the background are perceived through an additional dictionary, so that the background expression is effectively enhanced, and the anomaly detection precision is improved. And after the network converges, obtaining an anomaly detection result through a reconstruction error. According to the method, target features can be enhanced for interference of small targets, complex backgrounds and the like, so that a relatively good detection effect is achieved.

The application provides a tower fatigue life prediction method and system, which is suitable for the technical field of data processing. The method comprises the following steps: based on a preset communication tower stress monitoring information cutting model, a plurality of communication tower stress monitoring information cutting segment quantity information is obtained by cutting calculation on the plurality of communication tower stress monitoring information, and a plurality of communication tower stress monitoring cutting information is obtained; and based on a preset tower fatigue life prediction model, a plurality of tower fatigue life prediction information is obtained by calculation according to the plurality of communication tower stress monitoring cutting information. The application greatly improves the accuracy and timeliness of tower fatigue life prediction, helps operation and maintenance personnel to discover potential safety risks of tower structure in advance, timely formulates targeted maintenance and reinforcement scheme, thereby prolongs the service cycle of the communication tower, reduces the operation and maintenance cost, and guarantees the long-term stable operation of the communication network.

The invention relates to a risk rechecking method and device and a storage medium. The method comprises the steps that feature extraction is carried out based on at least one document sample, multiple types of feature vectors are obtained, the multiple types of feature vectors comprise at least two of text feature vectors, numerical feature vectors and graph feature vectors, and the at least one document sample does not comprise known misinformation samples or comprises part of the known misinformation samples; determining a risk review model based on the multiple types of feature vectors corresponding to each document sample; and processing the to-be-discriminated document based on the risk review model to obtain a risk review result, the risk review result being used for indicating whether the to-be-discriminated document has a false alarm. According to the embodiment of the disclosure, a large amount of structured and non-structured information contained in the receipt data can be fully utilized in a scene lacking the labeled sample, and context semantics, statistical laws and entity association relationships contained in the express receipt information can be comprehensively and deeply understood, so that the false alarm rate is effectively reduced.

The application discloses a point cloud segmentation method based on feature deviation values and an attention mechanism, relates to the technical field of three-dimensional point cloud classification, and utilizes the farthest sampling method to perform down-sampling on point clouds; a threshold radius is set with a sampling point as a center to extract feature points in the range by using a KNN algorithm; after the feature points are extracted, feature deviation values are calculated for each spherical neighborhood with the sampling center point, and then local features of the spherical neighborhood are obtained; residual multilayer perceptron shared weight parameters are utilized to fuse the local features by using attention pooling, and then global features of the point cloud are obtained; and the point cloud is segmented by utilizing the local features and the global features of the spliced point cloud. The application can effectively extract deep geometric features of the point cloud in a complex point cloud scene, fully excavate semantic information of the point cloud, avoid the problem of feature loss in a scene segmentation task, improve the segmentation capability of the model in a complex scene, effectively excavate deep information, and effectively realize scene segmentation of the point cloud.

The application provides a "7" shape shield support for mining, which comprises a top beam parallel to the roof in the ore body, a support shield beam vertical to the roof, a balance hydraulic cylinder connected between the top beam and the support shield beam, a support walking mechanism arranged on the top beam, a support sliding mechanism, and an extension shield mechanism arranged on the support shield beam, one end of the top beam and the support shield beam is hinged, the support walking mechanism is arranged on the inner side of the top beam away from the support shield beam, and has the freedom of extension relative to the top beam; the inner side of the top beam is provided with a sliding track extending along the support walking mechanism, the support sliding mechanism is arranged on the inner side of the top beam, is clamped in the sliding track, and has the freedom of sliding along the sliding track relative to the top beam; one end of the balance hydraulic cylinder is hinged with the support sliding mechanism, the other end is hinged with the inner side of the support shield beam, and the top beam has the freedom of swinging around the hinged shaft with the support shield beam under the driving of the balance hydraulic cylinder.

A method for dynamic beam optimization in satellite communication and a satellite communication terminal are disclosed. The terminal has a locally pre-installed hybrid architecture deep learning model. The specific steps are as follows: The terminal collects spatiotemporal feature data such as space, time, orbit, interference, and position in real time and stores it in a local historical database; it calculates the instantaneous phase angle of the satellite based on the position features and satellite ephemeris, identifies the scene type, and adapts the interference features to obtain optimized features; it extracts historical multi-frame spatiotemporal position features that match the current phase angle, combines them with the optimized features to construct a multi-dimensional feature matrix, inputs it into the model, and outputs spatial and temporal feature scores; it calculates dynamic weights by combining real-time interference and scene, balances the spatiotemporal score decision ratio, integrates historical reputation scores to calculate a comprehensive beam score, selects the optimal beam, and stores the decision result back into the local historical database. This invention integrates spatiotemporal multi-dimensional features, scene-based signal processing, and local deep learning inference to achieve beam optimization, improving the reliability of satellite communication and the efficiency of beam decision-making.

This invention relates to a hyperspectral band selection method based on spectral-spatial hypergraph regularized sparse self-representation. To address the insufficient utilization of band adjacency relationships in traditional sparse self-representation models, this method first integrates spectral similarity and spatial proximity to design a comprehensive index for evaluating band correlation. It explores and evaluates adjacency relationships between bands from multiple perspectives, constructing a hypergraph to generate a more complete inter-spectral local structure. Second, based on the aforementioned local band constraints, it supplements this with global band characteristics to jointly guide the optimization process of the sparse self-representation band selection model, obtaining the optimal low-dimensional representation of high-dimensional data and achieving band selection. This method overcomes the limitations of using a single similarity metric for decision-making and fully explores the multi-faceted adjacency relationships between bands, effectively reducing band redundancy, improving the quality of band subsets, and contributing to improved analytical accuracy in subsequent tasks.

The application discloses a method for reinforcing the well wall of a hydrate exploitation well in a sea area by using mineralization deposition, and comprises the following steps: arranging a spray hole on the pipeline of the exploitation well and extending the spray hole to the outside of the well wall; arranging a plurality of pipelines along the well wall inside the well wall for conveying branched polyethylene imine (BPEI) solution and modified nano calcium carbonate dispersion; before hydrate exploitation, conveying the reagents from an exploitation platform to a specified reinforcement depth, and spraying the two reagents from the spray hole by using a high-pressure pump at a certain time interval and pressure; the two reagents are fully reacted in the soil layer around the well wall to generate mineralization deposits and improve the strength of the soil layer; the method can be repeated according to requirements to form multiple mineralization deposits to achieve the required reinforcement strength; the method is convenient to operate, the reinforcement process is clear, and the effect is remarkable, and the method fills the blank in the field of real-time reinforcement of the well wall of a hydrate exploitation well, and helps long-term, safe and efficient exploitation of hydrate energy, and has remarkable technical advantages.

The invention provides a meta-universe content generation method and platform based on a multi-modal large model, and relates to the technical field of meta-universe content generation, and the method comprises the steps: carrying out the demand analysis through the multi-modal large model in response to the original multi-modal input of a target user, and generating an initial structured content list; based on the initial structured content list, retrieval matching is carried out in a historical task experience library, a heterogeneous approximate task set is obtained, and generation modal paths of the heterogeneous approximate task set and the initial structured content list are configured in a differentiated mode; analyzing the heterogeneous approximate task set through a multi-modal large model, extracting heterogeneous generality information, and constructing the heterogeneous generality information into a structured heterogeneous generality knowledge graph; and according to the initial structured content list and the heterogeneous common knowledge graph, in combination with a multi-modal large model, carrying out meta-universe content generation and merging output. And the generation efficiency and the generation quality of the element universe content are improved.

The application relates to a multi-modal vehicle re-identification method and system based on flow generation type multi-expert fusion, which comprises the following steps: acquiring a vehicle image and extracting input features, and classifying available modalities and missing modalities according to the availability of modalities; modeling a multi-modal joint latent distribution based on normalized flow, inferring the conditional distribution parameters of the missing modalities in the latent space under the condition of the available modalities, and generating semantic consistent missing modality features through reversible transformation; combining missing mode perception routing and modality level uncertainty weighting strategies to perform semantic enhancement and deviation compensation on the restored missing modality features, and obtaining vehicle identity embedding representation; and realizing vehicle re-identification based on the vehicle identity embedding representation. Compared with the prior art, the application has the advantages of effectively processing various missing modality conditions and maintaining the complementary relationship between modalities.

This invention relates to the field of artificial intelligence technology and discloses a method for identifying marine environmental risks based on big data. The method includes: standardizing marine environmental monitoring data to obtain a standardized dataset of the ocean; performing correlation analysis on the standardized dataset based on a pre-set risk knowledge base to obtain risk correlation features of the ocean; constructing a topology of the risk correlation features based on historical risk events of the ocean to obtain an environmental risk feature map of the ocean; tracking the trajectory of the environmental risk feature map to obtain the spatiotemporal evolution path of the ocean; simulating the spatiotemporal evolution path to obtain a risk evolution trajectory report of the ocean; and comprehensively evaluating the risk evolution trajectory report to obtain the risk level and early warning information of the ocean. This invention can improve the efficiency of marine environmental risk identification based on big data.

This invention discloses a wind condition prediction method and system based on a time-series evolution graph, solving the technical problem of insufficient accuracy in wind condition prediction results caused by existing methods. The method includes acquiring and preprocessing nacelle data and meteorological data for a single wind turbine to obtain a preprocessed wind turbine time series; then, based on predefined local and global time factors, mining key time series segments to determine a time-aware key time series segment set; subsequently, combining this set with the preprocessed sequence to calculate the matching probability and construct a time-series evolution graph; next, based on a deep walk algorithm, generating structured embedding vectors through a skip character model; finally, based on a multi-layer multi-head self-attention mechanism, using a multilayer perceptron network to perform wind condition prediction, outputting ultra-short-term wind speed prediction values ​​and wind direction angle prediction values.

This invention provides a physical simulation experimental device and method for fine exploration of water-bearing sections in underground rock strata. The device includes a water storage tank connected to a water pump. The water pump is connected to one end of multiple water supply valves via a one-way valve. Each water supply valve has a corresponding rock chamber at its other end. These rock chambers are vertically mounted on the sidewall of a simulated borehole pipe. Flange end caps are installed at both ends of the simulated borehole pipe. A return water inlet sealing head is installed on the flange end cap at the tail end of the simulated borehole pipe. The return water inlet sealing head is connected to the water storage tank via a return water valve. An energy storage and voltage regulator is also installed between the water storage tank and one end of the multiple water supply valves. An armored optical fiber cable for acoustic wave sensing is coaxially installed inside the simulated borehole pipe. This invention can effectively simulate various geological and hydrological conditions in actual underground rock strata environments. By analyzing the variation patterns of acoustic signals, it improves the accuracy of exploration of water-bearing sections, providing reliable technical support for coal mine water hazard prevention and safe production.