76 results about "Rock classification" patented technology

The invention relates to the technical field of tunnel engineering, in particular to a tunnel surrounding rock grading method and system, comprising intelligent sensing and data acquisition, multi-source data fusion and modeling, hybrid model dynamic grading, real-time decision and support optimization, online learning and dynamic feedback, and risk early warning and emergency response. Compared with the prior art that a geological data acquisition mode combining manual drilling coring and low-resolution geophysical prospecting is adopted, efficiency is low, subjective errors are large, and a complex geological structure is difficult to cover, unmanned aerial vehicle LiDAR scanning, intelligent rock core image analysis and a high-density IoT sensor network work cooperatively, and the working efficiency is greatly improved. Real-time dynamic acquisition of full-section geological information is achieved, manual intervention errors are eliminated in combination with a multi-source data fusion algorithm, the automation level and three-dimensional space representation precision of data acquisition are remarkably improved, and a high-resolution holographic data base is provided for surrounding rock classification.

The invention belongs to the technical field of tunnel and underground engineering intelligent construction and geotechnical engineering informatization, and discloses a high-energy geological environment surrounding rock classification and decision-making method based on digital twinning and multi-source feedback. The problems caused by difficulty in realizing surrounding rock state dynamic sensing, multi-source data fusion classification and construction decision closed-loop linkage in the prior art in a high-energy geological environment are solved. The method comprises the following steps: firstly, constructing a tunnel three-dimensional geology-structure digital twinborn body based on initial survey data; in the construction process, multi-source data such as geology, construction disturbance and surrounding rock response are collected in real time through the Internet of Things technology and mapped to the digital twinborn body, and virtual-real synchronous updating is achieved. And then, constructing a deep learning-parameter inversion hybrid model on the basis of the multi-source fusion data, outputting a dynamic surrounding rock classification index DRCI and key mechanical parameters, inputting the DRCI and the key mechanical parameters into a multi-objective optimization module, and giving a self-adaptive drilling and blasting scheme. And finally, reversely correcting the model through a construction feedback result to realize closed-loop self-learning.

The invention mainly relates to the technical field of tunnel engineering, and provides a tunnel surrounding rock grading dynamic correction method based on image texture features in order to improve the accuracy and real-time performance of surrounding rock grading under complex geological conditions. An improved deep residual network model integrated with an attention mechanism is input and introduced, the model improves the precision of single-point surrounding rock grade identification based on key textures, an initial prediction value of the surrounding rock grade is obtained, and meanwhile a time sequence prediction model is introduced; the whole excavation process is regarded as a continuous geological sequence based on the multi-source surrounding rock feature vectors of the current excavation cycle and at least one previous historical cycle, a time sequence trend value of the surrounding rock grade is obtained, a self-adaptive weight is set, the surrounding rock grade initial prediction value and the time sequence trend value of the surrounding rock grade are smoothed and corrected, and the surrounding rock grade is obtained. Therefore, the accuracy and the stability of the surrounding rock grading result are improved.

The invention, which belongs to the technical field of tunnel engineering, discloses a tunnel surrounding rock pressure arch calculation system comprising a multi-source data fusion acquisition module, a surrounding rock grade intelligent identification module, a self-adaptive pressure arch parameter calculation module and a dynamic load prediction and optimization module. The multi-source data fusion acquisition module acquires geological parameters, drilling monitoring data and case data and generates fusion feature vectors; the surrounding rock grade intelligent identification module outputs a surrounding rock classification result based on a deep residual network and an attention mechanism; the self-adaptive pressure arch parameter calculation module calculates pressure arch parameters by adopting an improved Prscherski theory and a stress release time-varying function; the dynamic load prediction and optimization module predicts the load through the space-time collaborative network and feeds the deviation back to the calculation module to form closed-loop optimization, precise dynamic calculation of the surrounding rock pressure arch parameters is achieved, and the calculation precision is improved by 20% or above compared with a traditional method.

The invention discloses an asymmetric and uncoupled tunnel smooth blasting method. The method comprises the steps that surrounding rock grading data and initial ground stress distribution of a target area are obtained, and a low-damage trial blasting scheme is optimized; drilling operation is conducted on the basis of the low-damage trial explosion scheme, a specific pre-charging place is selected to assemble an asymmetric non-coupling refined charging sleeve device, and a peripheral hole pre-charging sleeve device is further assembled; the peripheral holes are filled through a peripheral hole pre-charging sleeve device, other blast holes are filled in a continuous charging mode, and blocking is conducted after filling is completed; and constructing a detonating network, ventilating after detonating, checking the detonating effect, and iteratively optimizing a trial detonating scheme according to a damage judgment result. According to the method, the acting direction and the acting range of energy during blasting of explosives in peripheral holes can be accurately controlled, so that the disturbance influence of the blasting effect on surrounding rocks is relieved, the blasting damage degree of the surrounding rocks is reduced, construction safety is guaranteed, the occurrence frequency of back break phenomena is reduced, and the construction efficiency can be greatly improved.

The invention discloses a rock identification method and equipment based on geological semantic guidance, and a medium, belongs to the technical field of geological rock detection and identification, and is used for solving the problems that blindness and redundancy exist in a feature fusion process, and the efficiency is high due to lack of effective modeling of geoscience features in existing rock target detection. And the identification requirements of complex geological images are difficult to adapt. The method comprises the following steps: performing semantic analysis on effective data in multi-source geological original data under related rock characteristics to generate a geological semantic map; performing feature fusion processing under related feature mapping between the geological semantic map and the feature pyramid to obtain a target fusion feature under the current rock image; performing collaborative recognition based on visual features on rock physical attributes in the current multi-source geological data, and outputting target detection features under the current rock image; outputting a geological rock classification result of the current rock image; and carrying out visualization processing on the geological rock classification result under the integrated platform.

The invention relates to a tunnel surrounding rock grading method and system based on multi-source data fusion, and the method comprises the following steps: obtaining image data and point cloud data of a tunnel face, carrying out the preprocessing and data enhancement, obtaining image features and point cloud features reflecting the shape, structure, texture and roughness of the tunnel face, and carrying out the classification of the image features and the point cloud features; carrying out fusion processing on the obtained features; during feature fusion, according to the joint density in the image, determining the image block granularity, and projecting the image block granularity to the image features; determining a geological weight according to geological information acquired in advance, and embedding the geological weight into the image features; fusing the surrounding rock roughness and the rock quality index in the point cloud features with the image features through a cross-modal attention mechanism to obtain fused features; and the fused features learn geological structure laws through a pre-trained main network and a pre-trained slave network to obtain a comprehensive score, and a surrounding rock grading result is determined in combination with a threshold value of a set geological parameter.

The invention belongs to the technical field of deep hole blasting parameter optimization, and discloses a hole site parameter optimization analysis method based on open-air deep hole blasting. According to the method, the rock type is judged through multi-index cooperation, and a dynamic threshold adjustment mechanism is combined, so that the rock classification accuracy is improved, and accurate matching of hole site parameters and geological conditions is ensured. According to the method, through geological parameter-rock type-mapping relation three-level correlation determination, limitation of an empirical formula is avoided, and the parameter range better fits actual geological features. And meanwhile, a historical blasting data set is introduced for similar case matching, a potential risk parameter set is removed through experience screening, the deviation between theoretical simulation and actual engineering is reduced, and the parameter reliability is improved. According to the method, the multi-objective optimization model is adopted, the crushing quality, the safety control and the economical efficiency are synchronously considered, the parameter set for balancing all the objectives is output through the Pareto optimal algorithm, and high-quality, low-risk and low-cost collaborative optimization is achieved.

The invention discloses a tunnel slotting blasting parameter intelligent design method and system based on while-drilling sensing and dynamic optimization, and the method comprises the steps: S1, carrying out the real-time inversion of geological parameters based on a while-drilling signal frequency spectrum, and evaluating the rock mass quality; s2, determining slotting hole arrangement through a slotting mode decision tree according to the evaluated rock mass quality and a dynamic surrounding rock classification result; s3, based on the rock mechanics parameter library, the explosive loading amount of a single slotting hole is calculated through an explosive loading amount dynamic equation; and S4, through vibration propagation numerical simulation and three-dimensional scanning, the slotting hole arrangement and the explosive loading amount of a single slotting hole are verified, blasting parameters are corrected according to the verification result, and design is completed. According to the method, through a collaborative mechanism of rock mass parameter real-time sensing, blasting energy dynamic distribution and safety effect closed-loop verification, the core purposes of reducing the over-excavation condition, improving the construction efficiency and reducing the construction cost are achieved. According to the method, the blasting precision and the construction efficiency are remarkably improved, the over-excavation and under-excavation phenomena are reduced, and the safety risk is reduced.

The application provides a TBM tunnel face surrounding rock grade real-time intelligent sensing method and system, the method comprises the following steps: collecting rock-machine related multi-source information in the TBM tunneling process; establishing a TBM tunnel face surrounding rock classification standard; based on the TBM tunnel face surrounding rock classification standard, a database for training a rock-machine composite score cascade prediction model is constructed; taking the constructed database as a training sample, a rock-machine composite score cascade prediction model is constructed based on a ridge regression model and an artificial neural network; inputting the rock-machine related multi-source information into the rock-machine composite score cascade prediction model, obtaining the current TBM tunnel face composite rock-machine score, and then obtaining the TBM tunnel face surrounding rock grade according to the TBM tunnel face surrounding rock classification standard. The application realizes real-time intelligent prediction of the TBM tunnel face surrounding rock grade, improves the TBM tunneling environment perception level, and lays a solid foundation for underground engineering intelligent construction.

The invention relates to a shield tunnel surrounding rock classification method based on multi-task learning and adversarial training, and the method comprises the steps: collecting different tunnel engineering data, carrying out the signal decomposition and structural processing, and constructing a database, wherein the parameters comprise surrounding rock categories at different duct pieces of the tunnel, corresponding corrected BQ values and time sequence data of shield tunneling machine operation parameters recorded by a shield tunneling machine PLC system during construction of each duct piece; constructing a transfer learning model by using a multi-task learning framework and an adversarial training mechanism, and training and verifying the transfer learning model based on the database to obtain a final transfer learning model; and obtaining target tunnel engineering data, inputting the target tunnel engineering data into the final transfer learning model, and outputting a predicted surrounding rock category and a corresponding corrected BQ value. According to the method, common features among different engineering data are extracted through a transfer learning model architecture combining a multi-task learning framework and adversarial training, so that the model generalization ability is improved, and the surrounding rock classification problem in a target engineering data scarcity scene is solved.

The invention discloses an intelligent grading method and system for tunnel face surrounding rock. According to the method, a two-dimensional image, a three-dimensional point cloud and environmental mechanics data of a tunnel face are synchronously collected through a sensor array integrated on tunneling equipment; after space-time registration fusion is carried out on the multi-source data, pixel-level identification and quantitative extraction of geological features are carried out by using a deep learning model, and three-dimensional reconstruction is carried out based on a motion recovery structure algorithm to obtain rock mass structural plane occurrence parameters; visual, geometric and environmental characteristics are fused, and accurate prediction of the surrounding rock grade is realized through an integrated learning model; and finally, dynamic excavation numerical simulation is carried out by combining the three-dimensional geologic model and a prediction result, the surrounding rock stability is analyzed, and safety early warning is generated. According to the method, automation and quantification of the whole process of surrounding rock grading are achieved, and the accuracy and timeliness of tunnel construction safety decision making are effectively improved.

The invention provides a tunnel surrounding rock identification method and system, and relates to the technical field of tunnel construction, and the method comprises the steps: obtaining a mixed frequency sound wave reflection signal collected by a sensor array disposed on a tunnel face, synchronously acquiring the hyperspectral image data of the tunnel face rock mass from the visible light to the short wave infrared band through a portable spectrometer; topological mode construction is carried out according to the mixed frequency sound wave reflection signals, and topological invariant features are obtained; performing cross-modal fusion according to the topology invariant features and the hyperspectral image data to obtain a fused topology-spectrum association graph; hidden manifold structure learning is carried out according to the fusion topology-spectrum correlation graph, and a low-dimensional feature vector is obtained; performing dynamic surrounding rock category division according to the low-dimensional feature vector to obtain a surrounding rock dynamic classification label; and performing identification result decision according to the surrounding rock dynamic classification label to obtain a tunnel surrounding rock identification result. According to the invention, high-precision and high-robustness dynamic identification of the tunnel surrounding rock state is realized.

The invention discloses an underground engineering surrounding rock while-drilling intelligent sensing and in-situ classification method, and relates to the technical field of underground engineering, and the method comprises the steps: building a rock mass mechanical parameter while-drilling inversion model, carrying out the dynamic prediction of the equivalent compressive strength of a rock mass, and generating a strength curve changing with the drilling depth; according to the sudden change characteristics of the strength curve, recognizing the position of the structural plane, constructing a rock mass structural plane response-while-drilling model, obtaining structural plane parameters according to the position of the structural plane, and further calculating rock mass quality indexes; after the testing while drilling is completed, an underground water state testing while drilling model is constructed, and underground water state characterization parameters are obtained; based on a surrounding rock classification method, performing underground engineering surrounding rock intelligent while-drilling in-situ classification evaluation by integrating rock mass equivalent compressive strength, structural plane width, structural plane spacing, rock mass quality indexes and underground water state characterization parameters; according to the invention, real-time detection and in-situ while-drilling classification of underground engineering surrounding rock properties can be realized, and the test accuracy and timeliness are improved.

The application discloses a kind of highway super large section tunnel intelligent construction method and system, method includes: in the drilling process of highway super large section tunnel, the drilling parameter set of working face is collected;According to the drilling parameter set, determine multiple groups of matching drilling parameters, and determine the drilling parameters of different sections;Based on the drilling parameter set and the drilling parameters of different sections, utilize the pre-trained surrounding rock classification model based on machine learning, determine the overall surrounding rock grade of tunnel and the surrounding rock grade of different sections;According to the overall surrounding rock grade and the surrounding rock grade of different sections, corresponding tunnel support scheme is generated, to realize the intelligent construction of tunnel.Utilize the embodiment of the application, can be combined with artificial intelligence to realize the rapid evaluation of surrounding rock grade, generate corresponding support scheme, improve the safety and efficiency of construction.

The invention discloses a zone division method, device and equipment for multi-type coal rock gas in a complex structure deformation zone, a storage medium and a program product. The method comprises the following steps: determining a coal rock classification result according to sedimentary environment description information and geochemical index information; generating a geological model of the target exploration area in a coal rock development geological period, and determining a coal rock distribution range in the geological model according to a coal rock classification result; according to the core data, the logging data and the seismic data, establishing a sequence stratigraphic framework in the coal rock distribution range; determining a coal rock seismic image according to the seismic data; according to the coal rock seismic imaging, determining coal rock space-time distribution information of the target exploration area; and determining a zone division result of the coal rock gas according to the spatial and temporal distribution information of the coal rock. According to the technical scheme, the problem that a coal rock gas zone of a complex structure deformation zone is difficult to reliably divide is solved, multiple types of coal rocks can be effectively identified through layer-by-layer coal rock distribution depiction, and the coal rock gas exploration efficiency is improved.

The invention provides a real-time TBM (Tunnel Boring Machine) cross-tunnel-diameter surrounding rock category distinguishing method and system based on a rock breaking mechanism. The method comprises the following steps: acquiring tunneling data of different TBM construction tunnels, forming a sample data set, extracting tunneling parameters and equipment parameters of each engineering TBM, and forming a refining data set; extracting stable tunneling section data from the refined data set by adopting an MMD method, calculating DFPI and DTPI rock breaking characteristic indexes, and enabling the rock breaking characteristic indexes to correspond to surrounding rock category labels through pile numbers and tunneling time to obtain a surrounding rock grade data set; taking two standardized indexes of DFPI and DTPI as two-dimensional input variables, and constructing a two-dimensional Bayesian surrounding rock classification model; carrying out weighted fusion on [DFPI, DTPI] to obtain an index R, and constructing a one-dimensional surrounding rock discrimination model and a threshold identification method; and inputting the acquired TBM tunneling data into the one-dimensional surrounding rock discrimination model to obtain the surrounding rock grade of the current TBM tunnel face. According to the method, the model generalization ability is improved, and the problem that a current surrounding rock classification method is insufficient in physical interpretation is solved.

The present application mainly relates to the technical field of tunnel engineering, in order to improve the accuracy and real-time of surrounding rock classification under complex geological conditions, the present application provides a kind of dynamic correction method of surrounding rock classification of tunnel based on image texture feature, the texture feature of surrounding rock image is fused with geological parameters, form multi-source feature vector, input improved deep residual network model with integrated attention mechanism is introduced, model is based on key texture improves the precision of single-point surrounding rock grade identification, obtains the initial prediction value of surrounding rock grade, simultaneously introduces time series prediction model, based on the multi-source surrounding rock feature vector of current excavation cycle and at least one historical cycle, the entire excavation process is regarded as a continuous geological sequence, the time trend value of surrounding rock grade is obtained, and the adaptive weight is set, the initial prediction value of surrounding rock grade and the time trend value of surrounding rock grade are smoothed and corrected, and the dynamic classification result of surrounding rock is obtained, the accuracy and stability of surrounding rock classification result are improved.

The invention discloses a rock slice image classification method based on domain self-adaption, and the method comprises the steps: collecting rock slice image data, the method comprises the following steps: acquiring a rock slice image, performing multi-scale data preprocessing and geological field data enhancement, extracting multi-level visual features of the rock slice image by utilizing a pre-trained DINOv3 model, performing field specialized adaptation on general visual features through a geological field adaptive Adapter module, and enhancing rock slice discriminative feature representation by adopting a double-path attention mechanism. Constructing a progressive hierarchical classification head to realize coarse-to-fine rock classification; and designing a multi-stage progressive training strategy to optimize the overall performance of the model. According to the method, mineral composition and structural features of the rock slices under different scales can be accurately captured, and multi-scale features and an attention mechanism are fully utilized, so that accurate classification of the rock slices is realized, and the accuracy and reliability of rock slice identification are remarkably improved.

The invention discloses a single well rock classification method and device and application, and the method comprises the steps: obtaining a single well saturation curve of a target well through the calculation of an Archie formula; constructing a saturation height function based on the core data; a height curve above a free water interface and a single well porosity curve of the target well are obtained; through the height curve above the free water interface, the single well porosity curve and the saturation height function, a single well saturation curve of different rock types is obtained through calculation; and determining the rock type of the target well based on the different rock type saturation curves of the single well and the single well saturation curve. By applying the method to a core well and comparing with core well rock classification, the coincidence rate of the rock type of the method reaches 85%, and the coincidence rate of the original method is improved by 12% while the coincidence rate of the original method is 73%. According to the method, the accuracy rate of single well rock classification is improved, a foundation is laid for subsequent rock type three-dimensional modeling, and the method can be continuously used for other similar oil reservoirs in the Middle East.

The invention belongs to the technical field of oil and gas geological exploration, and particularly relates to a lacustrine facies carbonate rock division method which comprises the following specific steps: selecting a research area with remarkable lacustrine facies mixed deposition characteristics, determining a target interval, and combining a structure location map and a stratigraphic histogram to obtain a lacustrine facies carbonate rock division model; and determining that the sample collection range covers different sedimentary facies zones such as a southern slope zone, a nose-shaped tectonic zone and a northern slope zone. The classification scheme not only has a clear facies indicating significance and can effectively indicate a sedimentary environment, but also provides a reliable lithofacies basis for evaluation of a lacustrine facies carbonate reservoir; the method is especially suitable for oil-gas exploration target optimization under the multi-layer-series and multi-object-source background, and has important practical application value for guiding exploration deployment of similar regions.

The present application belongs to the technical field of deep hole blasting parameter optimization, and discloses a hole site parameter optimization analysis method based on open pit deep hole blasting. The present application determines rock types through multi-index coordination, improves the accuracy of rock classification by combining a dynamic threshold adjustment mechanism, and ensures the accurate matching of hole site parameters and geological conditions. The present application determines through three-level correlation of geological parameters-rock types-mapping relationship, avoids the limitations of empirical formulas, and makes the parameter range more in line with actual geological characteristics. At the same time, historical blasting data sets are introduced for similar case matching, potential risk parameter sets are removed through experience screening, the deviation between theoretical simulation and actual engineering is reduced, and the parameter reliability is improved. The present application adopts a multi-objective optimization model, simultaneously considers fragmentation quality, safety control and economy, outputs a parameter set balancing each target through a Pareto optimal algorithm, and realizes the coordinated optimization of high quality, low risk and low cost.

This invention proposes a method and system for determining the classification of tunnel surrounding rock based on a dual-modal fusion model, relating to the field of tunnel engineering technology. Addressing the problems of poor accuracy and applicability in existing surrounding rock classification technologies, this invention collects drilling parameters, tunnel face images, and level labels, and performs preprocessing. Based on the drilling parameters, a multi-dimensional initial feature set is constructed and key drilling parameter feature sets are obtained through screening. Dimensionality reduction processing of the tunnel face images yields key image feature sets, which are then used to determine the fusion feature set. Using the fusion feature set as input and the level labels as output, a feature-level fusion classification model is trained. Using the key drilling parameter feature set and key image feature set as input, combined with the level labels, two single-modal classification models are trained and then co-validated and fused to obtain a decision-level fusion classification model. The tunnel data to be classified is then input into either the feature-level or decision-level fusion classification model to determine the classification result. This invention offers high classification accuracy and applicability.

The present invention discloses a spatial registration method for multi-source heterogeneous data of a tunnel, the method comprising: constructing a lightweight digital twin model based on a design parameter library, a construction log library and a real-time monitoring library; mapping the multi-source sensor data in the real-time monitoring library to the spatial nodes of the digital twin model through a spatiotemporal synchronization algorithm; eliminating outliers based on a probability distribution model for geological exploration data, drilling parameters and geological sketches, and generating a three-dimensional distribution field of surrounding rock mechanical parameters using a discrete smooth interpolation algorithm; using the three-dimensional distribution field of surrounding rock mechanical parameters as input, dynamically predicting the probability distribution of surrounding rock classification ahead through a machine learning model optimized by transfer learning; extracting structural surface geometric parameters and constructing a normal vector constrained fracture network model based on the three-dimensional point cloud data of the tunnel face in the digital twin model; the present invention accurately locates the surrounding rock risk area based on dual threshold triggering, and realizes seamless fusion of multi-scale models through gradient constrained topological fusion.

The invention provides a surrounding rock grading method and system based on a TBM rock slag image, and belongs to the field of TBM surrounding rock grading. The method comprises the steps that a TBM rock slag image is collected and preprocessed, and rock slag in the rock slag image is extracted through the image segmentation technology; fractures of the rock slag are extracted based on a target recognition algorithm, and binary images of the fractures and the background are output; calculating an index breakage rate based on the binarized image; calculating an index fractal dimension by adopting a box counting method, and determining box distribution and division of the box counting method based on an image segmentation result; and projecting the breakage rate and the fractal dimension into a feature space, respectively obtaining feature vectors of the breakage rate and the fractal dimension, and inputting the feature vectors into a classifier to obtain a grading result of the TBM surrounding rock quality. The index breakage rate and the index fractal dimension are used for surrounding rock quality grading, the image surrounding rock grading calculation amount can be remarkably reduced, and the recognition accuracy and interpretability are improved. The problem that the classification result depends on the advantages and disadvantages of the algorithm and the quality of the picture in the traditional method is solved.

This invention relates to an optimized processing method for monitoring surrounding rock displacement during the excavation of a cavern complex. The method includes: determining the rock mass strength parameters and establishing a three-dimensional geological model by combining topographic information of the target area and on-site geological survey data; calculating the corresponding three-dimensional geostress field; determining the approximate range of surrounding rock strength and deformation parameters according to specifications and rock mechanics handbooks based on the surrounding rock category determined by surrounding rock classification and surrounding rock parameters obtained from laboratory tests; calculating the relative deformation of different measurement sections and inverting the optimized surrounding rock parameters using the relative deformation of different measurement sections monitored by multi-point displacement gauges; and verifying the reliability of the inverted surrounding rock parameters by comparing them with the measured relative deformation characteristics of the surrounding rock. The beneficial effects of this invention are: by optimizing the surrounding rock parameters to obtain the excavation response characteristics of the surrounding rock, the on-site monitoring data is corrected and analyzed to correct the multi-point displacement gauge monitoring data, making the monitoring data obtained by the multi-point displacement gauges more accurate.

The present application discloses a rock classification method, apparatus, device, and storage medium based on the fusion of multi-scale and dual-attention features, relating to the technical field of rock classification. The rock classification method based on the fusion of multi-scale and dual-attention features includes: generating a dual-attention feature based on an initial rock feature map, generating a multi-scale context feature based on the initial rock feature map; obtaining a current-level fusion feature based on the dual-attention feature and the multi-scale context feature; generating a subsequent dual-attention feature based on the dual-attention feature, generating a subsequent multi-scale context feature based on the multi-scale context feature; obtaining a subsequent fusion feature based on the current-level fusion feature, the subsequent dual-attention feature, and the subsequent multi-scale context feature, and obtaining a rock classification result based on the subsequent fusion feature. The present application can improve the accuracy of rock classification.

The invention provides a naming method for salt lake mixed rock. The naming method comprises the following steps: carrying out rock division by using terrestrial clastic particles, carbonate particles and miscellaneous bases; using 50% as a boundary to distinguish siltstone and limestone; according to a sedimentary structure, the land-derived debris particle component is divided into a stratified structure, a blocky structure, a deformed structure and a wave-formed staggered bedding, siltstone is taken as a basic name when the land-derived debris particle component is larger than 50%, silty sand is taken as a basic name when the land-derived debris particle component is 25%-50%, and silty sand is taken as a basic name when the land-derived debris particle component is 15%-25%; dividing the lithofacies by taking the component characteristics and sedimentary structure characteristics of the rock as a division basis according to the conditions of the rock core and the slice; salt lake lithofacies are divided into three major classes, namely siltstone facies, granular limestone facies and marlstone facies, and are subdivided into ten lithofacies subclasses. The method provides a standardized new thought for lithofacies division in a salt lake deposition system, a standard reference is provided for lithofacies naming through outcrop observation, and a lithofacies division standard is formulated according to the scheme according to the deposition structure, the component content and the like.

The invention relates to the technical field of tunnel face surrounding rock grading in railway construction, and provides a drilling and blasting method tunnel face surrounding rock three-dimensional refined grading method based on a seismic wave reflection method, which comprises the following steps: collecting three-dimensional inversion dot matrix data of an area in front of a tunnel face; the data coordinate system is converted into a tunnel design coordinate system, the surrounding rock basic quality index BQ value of each point is calculated according to the wave velocity, and a space BQ value dot matrix database is generated; performing spatial region division on the BQ value dot matrix by adopting a three-dimensional region self-growth method to obtain a connected region with similar BQ value characteristics; after the representative value of the region boundary is determined, using a Marking Cubes algorithm to extract contour surfaces to construct a surrounding rock three-dimensional grid model; and finally, mapping the model vertex BQ value with a preset grading standard, and outputting a three-dimensional refined grading model with a surrounding rock grading label. Automatic processing and three-dimensional visualization of surrounding rock classification are achieved, and classification accuracy and construction decision reliability are improved.

The application discloses a TBM tunneling section feature extraction and cutter disc thrust prediction method based on kernel density estimation, which comprises the following steps: step 1, surrounding rock classification; step 2, construction of a cutter disc thrust prediction model; step 3, construction of a model training sample library, specifically comprising: collection of effective tunneling section data, tunneling section internal stage segmentation, extraction and loading of section operation parameters and calculation of stable section cutter disc average thrust; step 4, training of the cutter disc thrust prediction model; step 5, selection of the cutter disc thrust prediction model; step 6, tunneling; step 7, extraction of loading section operation parameters; and step 8, prediction of the stable section cutter disc average thrust. The application establishes a cutter disc thrust prediction model and engineering application by extracting rock mass quality indexes and stable excavation section operation parameters from loading section data, realizes timely prediction of the cutter disc thrust in the TBM construction process, and the prediction result can provide guidance for setting of operation parameters of on-site machine drivers, and further improves the excavation efficiency of the tunnel boring machine.