Three-dimensional calculation and analysis method for excavation with or without support

Abstract

The invention provides a three-dimensional calculation and analysis method for excavation with or without support, and relates to the field of underground engineering, and the method comprises the following steps: S1, data collection and preprocessing: obtaining geological information of field monitoring equipment and a construction area; the method comprises the following steps: acquiring multi-source data in a current construction process according to field monitoring equipment of an underground powerhouse cavern group and geological information of a construction area, wherein the multi-source data comprises construction stage data # imgabs0 #, surrounding rock monitoring data # imgabs1 # and reinforcement measure parameters # imgabs2 #; s2, data cleaning and feature extraction: executing preprocessing operation on the collected multi-source data, and extracting feature vectors according to the preprocessed multi-source data; the method has the advantages that firstly, the surrounding rock deformation rule of the cavern group of the high-crustal-stress underground powerhouse in the excavation state with or without the support can be accurately analyzed; 2, the accuracy and the reliability of stress analysis are remarkably improved; thirdly, the distribution rule of the damaged area is accurately determined; and 4, effective monitoring and analysis of the micro-seismic source parameter evolution rule are realized.

Description

Technical Field

[0001] The invention relates to the field of underground engineering, and in particular to a three-dimensional calculation and analysis method for excavation with or without support. Background Art

[0002] With the continuous growth of energy demand, the demand for underground powerhouse construction in hydropower, nuclear power and other fields is increasing. However, the high ground stress conditions make the surrounding rock present a series of unstable mechanical behaviors after the excavation of underground powerhouse caverns.

[0003] At present, although there is a certain understanding of the deformation, stress and damage zone distribution of the high-in-situ stress underground powerhouse cavern group, that is, it conforms to the specific high-in-situ stress underground powerhouse excavation deformation and damage zone distribution law, in actual engineering, when the deformation and stress of the three caverns are in a seemingly stable and controllable state, it brings great difficulties to the subsequent monitoring and analysis work. This seemingly stable state often conceals the potential unstable factors and their development trends inside the surrounding rock, making it extremely complicated to calculate and analyze the deformation, stress and damage zone distribution law of the surrounding rock under the reinforced state after monitoring, as well as the evolution law of microseismic source parameters. Traditional monitoring and analysis methods are difficult to accurately capture these key information, and thus cannot provide an accurate and reliable basis for the formulation of scientific and reasonable reinforcement measures, and it is difficult to meet the needs of long-term stable and safe operation of the high-in-situ stress underground powerhouse cavern group. Summary of the invention

[0004] In view of the shortcomings of the above-mentioned prior art, the technical problem to be solved by the present invention is to provide a three-dimensional calculation and analysis method for excavation with or without support, which can accurately capture the deformation, stress and damage zone distribution of the three major caverns, and the distribution law of the excavation deformation and damage zone of the high-ground stress underground powerhouse and analyze it, so as to provide a basis for corresponding reinforcement measures to ensure long-term safe operation.

[0005] In order to solve the above technical problems, the technical solution adopted by the present invention is: the present invention provides a three-dimensional calculation and analysis method for excavation with or without support, comprising the following steps: S1. Data collection and preprocessing: obtaining geological information of on-site monitoring equipment and construction areas; Collect multi-source data of the current construction process based on the on-site monitoring equipment of the underground powerhouse caverns and the geological information of the construction area, including construction stage data , surrounding rock monitoring data And reinforcement measures parameters ; S2, data cleaning and feature extraction: perform preprocessing operations on the collected multi-source data, and extract feature vectors based on the preprocessed multi-source data; S3. Model prediction and analysis: Integrate preprocessed multi-source data to form a complete input sample , and input into the model Conduct analysis and obtain prediction results.

[0006] In the preferred embodiment, the model It is a pre-trained integrated model, which integrates long short-term memory network LSTM, convolutional neural network CNN, support vector machine SVM and Transformer, and also includes the following steps: S4. Construction monitoring and early warning: The prediction results are integrated and feature encoded, and the prediction results are input into the Transformer. The Transformer input layer encodes the position of the data in the prediction results to capture the sequence order. Then the data enters multiple encoder layers and captures the correlation between different prediction results. The re-weighted integrated feature representation is output and then enters the feedforward neural network composed of two linear transformation layers and ReLU activation function for nonlinear transformation and feature extraction. After being processed by multiple encoder layers, the data is mapped into a comprehensive early warning indicator through a linear projection layer at the output layer. , whose weights are optimized by the back propagation algorithm during training to determine the input of each prediction result and the comprehensive warning indicator The best mapping relationship between them, and based on the comprehensive early warning indicators Compare with the threshold to determine the warning level; Among them, each encoder layer includes a multi-head self-attention mechanism and a feedforward neural network.

[0007] In a preferred solution, in step S2, the preprocessing operation includes clearing and removing outliers and erroneous data, and is used to perform integration and standardization processing on multi-source data so that each data has a unified format and dimension; From the surrounding rock monitoring data The extracted feature vectors include the surrounding rock deformation vector , the sorted surrounding rock pressure data vector , stress distribution data vector and microseismicity data vector ; Surrounding rock deformation vector , the sorted surrounding rock pressure data vector , stress distribution data vector Arranged in a certain spatial order, the microseismic activity data vector Arrange in a certain time order; Construction phase data Including the current excavation depth, face position, completed support steps, and converted into corresponding feature vectors; Reinforcement measures parameters Including the length, spacing, grouting amount of the anchor rod, and the prestressing parameters of the anchor cable, and converted into corresponding eigenvectors.

[0008] In a preferred embodiment, in step S3, the model For input samples The specific analysis steps are as follows: S31, LSTM layer for microseismic activity data vector Perform analytical processing; According to the sequence and time interval of microseismic events, the model is executed The pre-set 1-3 LSTM layers extract the evolution trend characteristics of microseismic activity and output the characteristic vector of the evolution stage of microseismic source parameters ; Among them, each LSTM layer contains 64-256 hidden units; S32, CNN performs convolution operation on the spatial distribution data of surrounding rock deformation and damage zone, extracts spatial features through convolution kernels of different scales, and outputs the spatial feature vector of surrounding rock deformation and stress distribution and ; In order to identify the local concentrated area of ​​surrounding rock deformation and the shape and position of stress concentration area, the surrounding rock deformation vector , the sorted surrounding rock pressure data vector and stress distribution data vector Spatial feature extraction is performed through 2-3 convolutional layers with kernel sizes ranging from 3×3 to 5×5 and strides of 1 or 2. Each convolutional layer is followed by a maximum pooling layer. S33. Using feature engineering to extract data from the construction phase and reinforcement measures parameters Extract key features and form vectors , and used as the input data of the SVM model, the feature vectors output by LSTM and CNN after passing through their respective fully connected layers , and And use weighted summation to calculate and fuse the feature vector The calculation formula is as follows: ; The weights are , , ; The fused feature vector Input into the SVM model and according to the fusion feature vector Execute the prediction and use the SoftMax function to output the deformation prediction value of the surrounding rock , stress prediction value , predicted probability of damage area distribution and the prediction probability of the evolution stage of microseismic source parameters .

[0009] In the preferred solution, in step S4, the standard surrounding rock data in the database is for: ; in, Represents the deformation dimension of different monitoring positions, Corresponding to four deformation levels, standard surrounding rock data Vector representation of typical deformation conditions corresponding to different deformation levels; Calculate the deformation prediction value of the current surrounding rock With various standard surrounding rock data The Euclidean distance , the Euclidean distance calculation formula is: ; By comparing the Euclidean distance middle The size of determines the deformation level: like , it is determined to be a first-level slight deformation, and the daily deformation amount is expressed as ; like , it is determined to be a secondary medium deformation, and the daily deformation is expressed as ; like , it is determined to be a third-level severe deformation, and the daily deformation is expressed as ; like , it is determined to be extremely strong deformation of level 4, and the daily deformation is expressed as .

[0010] In the preferred solution, according to the Euclidean distance Determine the deformation level of the surrounding rock and combine it with the model Output of predicted deformation value of surrounding rock , stress prediction value , predicted probability of damage area distribution and the prediction probability of the evolution stage of microseismic source parameters Conduct comprehensive early warning; Defining comprehensive early warning indicators , which is a weighted combination of the following: ; in, , , , They are the weight coefficients of deformation level, stress, probability of distribution of damage zone and evolution stage of microseismic source parameters in the calculation of comprehensive early warning indicators; Determine according to the actual situation and importance of the project , , , , and satisfies ; get: ; Among them, the surrounding rock deformation grade is obtained , according to the surrounding rock deformation grade Substitute the value into the deformation level function Get the corresponding function value and convert the stress prediction value With stress threshold , Compare, substitute the stress function Get the corresponding function value and predict the probability of damage zone distribution and the prediction probability of the evolution stage of microseismic source parameters , and then substituted into the probability function of the damage area distribution after comparing with their respective thresholds and the probability function of the evolution stage of microseismic source parameters Get the corresponding function value, and multiply the corresponding function value by the corresponding weight coefficient , , , After adding, we get the comprehensive early warning index .

[0011] In the preferred solution, the comprehensive early warning indicator The specific calculation steps are as follows: Assume that the surrounding rock deformation level determined by the Euclidean distance is ; Among them, the surrounding rock deformation level The values ​​are 1, 2, 3, and 4, corresponding to level 1 slight deformation, level 2 moderate deformation, level 3 strong deformation, and level 4 extremely strong deformation, respectively, and are used to reflect the severity of surrounding rock deformation; Deformation level function According to the surrounding rock deformation grade Assign different basic scores to the surrounding rock deformation level Factor quantification, that is, according to the input surrounding rock deformation level value, directly output the corresponding fixed score, the formula is as follows: ; set up and is the stress threshold, according to the stress prediction value Relationship with threshold value determines stress function The function value of is: ; set up and is the probability threshold of the damage zone distribution, and , , then the probability function of the damage zone distribution is The formula is as follows: ; set up and is the probability threshold of the microseismic source parameter evolution stage, and , , then the probability function of the evolution stage of microseismic source parameters is The formula is as follows: ; set up , and is the warning threshold, and the comprehensive warning index is calculated based on Compare with the set warning threshold to determine the warning level; Among them, , , , then the formula is expressed as: ; Through the visual interface display, according to The value of is represented by different colors in the animation simulation of the deformation of the surrounding rock. The color cloud map of stress distribution is rendered with different transparency and color to indicate the predicted probability of damage zone distribution. The probability of different damage zone categories in the microseismic source parameters and the predicted probability according to the evolution stage of the microseismic source parameters High-risk microseismic hotspots are highlighted in bright colors.

[0012] In the preferred solution, S5, monitoring frequency adjustment: according to the deformation prediction value of the surrounding rock , stress prediction value , predicted probability of damage area distribution and the prediction probability of the evolution stage of microseismic source parameters and comprehensive early warning indicators Determine the current status of the underground powerhouse cavern complex. The specific steps are as follows: Assume the deformation speed is , by calculating two adjacent monitoring moments, let the time interval be The deformation difference , then the formula of deformation speed is as follows: ; when mm / day, determine the monitoring frequency , and is expressed by the following formula: ; in, and To further divide the speed interval threshold, that is mm / day, mm / day; According to the determined monitoring frequency , adjust the data collection cycle of the monitoring equipment to ensure timely acquisition of sufficient surrounding rock status information.

[0013] In the preferred solution, S6, monitoring and measurement data phase analysis and construction evaluation: through weekly and monthly analysis, determine the construction phase data , surrounding rock monitoring data And reinforcement measures parameters The specific steps are as follows: S61. Data collection and collation: Assume that the surrounding rock deformation data sequence obtained in each monitoring is , the surrounding rock pressure data series is , the steel frame stress data series is , the concrete stress data series is ; in, Indicates the monitoring time. is the total number of monitoring times; S62. Weekly and monthly stage analysis Weekly Analysis: The data obtained each week are sorted and analyzed separately, that is, the average weekly deformation of the surrounding rock deformation data is calculated: ; in, For the Weekly monitoring times, Indicates The set of monitoring times corresponding to the week; Similarly, the weekly average surrounding rock pressure can be calculated , Weekly average steel frame stress , Weekly average concrete stress ; Analyze the trend of weekly data by calculating the difference between the average deformation of two consecutive weeks Observe the increase or decrease of deformation and the changes of various stress data to determine the changing trend of surrounding rock conditions; Monthly Analysis: Calculate the average monthly deformation: ; in, For the Monthly monitoring times, Indicates The monitoring time set corresponding to the month can be used to calculate the average surrounding rock pressure per month. , Monthly average steel frame stress , Monthly average concrete stress ; Through the weekly data change trend and monthly monitoring measurement data sorting and analysis, determine the change pattern of each monitoring measurement data over time .

[0014] In the preferred solution, in step S6, according to the change rule The specific steps for carrying out the construction status evaluation are as follows: set up is the incremental threshold of surrounding rock deformation, is the safety threshold interval of surrounding rock pressure, is the safety threshold range of steel frame stress, is the safety threshold interval of concrete stress; If there is a certain week k, the formula for determining the weekly risk situation is as follows: ; For two consecutive months and , then the monthly risk determination formula is as follows: ; If a week or two consecutive months are identified as being at risk, an in-depth assessment is performed and appropriate measures are taken.

[0015] The present invention provides a three-dimensional calculation and analysis method for excavation with or without support, which has the following beneficial effects through the cooperation between the above structures: First, it can accurately analyze the deformation law of the surrounding rock of the high-stress underground powerhouse cavern group under the excavation with or without support. It can not only accurately grasp the current deformation, but also deduce the development trend of deformation based on the data change curve and related calculations, providing a key basis for taking targeted deformation control measures in advance; Second, the accuracy and reliability of stress analysis are significantly improved. With the help of a three-dimensional calculation model, the system comprehensively considers various stress data such as surrounding rock pressure, steel frame stress, concrete stress, etc., accurately calculates the stress distribution, and can track stress changes in real time. In the face of a complex high-altitude stress environment, it can accurately determine whether the stress exceeds the safety threshold and promptly discover potential stress concentration risk areas; Third, accurately determine the distribution pattern of the damage zone. Based on comprehensive monitoring of the surrounding rock state and in-depth analysis of the three-dimensional model, combined with indicators such as the predicted probability of damage zone distribution, it is possible to accurately depict the possible location, scope and development trend of the damage zone; Fourth, it is possible to effectively monitor and analyze the evolution patterns of microseismic source parameters. By using data such as the prediction probability of the microseismic source parameter evolution stage, combined with professional analysis methods and models, it is possible to clearly grasp the patterns and trends of microseismic activities. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The present invention will be further described below in conjunction with the accompanying drawings and embodiments: Figure 1 It is the main structural diagram of the process of the present invention; Figure 2 is a structural diagram of a system device in Embodiment 1 of the present invention; Figure 3 This is a schematic diagram of an electronic device in Embodiment 2 of the present invention. DETAILED DESCRIPTION

[0017] In order to better understand the purpose, structure and function of the present invention, the embodiments and features in the embodiments of the present application can be combined with each other without conflict. The present invention will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0018] Example 1 like Figure 1 As shown, a three-dimensional calculation and analysis method for excavation with or without support includes the following steps: S1. Data collection and preprocessing: obtaining geological information of on-site monitoring equipment and construction areas; Collect multi-source data of the current construction process based on the on-site monitoring equipment of the underground powerhouse caverns and the geological information of the construction area, including construction stage data , surrounding rock monitoring data And reinforcement measures parameters ; S2, data cleaning and feature extraction: perform preprocessing operations on the collected multi-source data, and extract feature vectors based on the preprocessed multi-source data; Preprocessing operations include clearing, removing outliers and erroneous data, and integrating and standardizing multi-source data to make each data have a unified format and dimension. Specifically, the raw data collected from the multi-source data are cleaned to remove obviously abnormal or erroneous data points. For the surrounding rock deformation data, if the deformation value of a certain monitoring point suddenly deviates seriously from the surrounding monitoring points and historical data, the data point may be caused by sensor failure or other interference factors and should be eliminated or corrected.

[0019] At the same time, meaningful features are extracted from the original data in the multi-source data. For the surrounding rock deformation data, in addition to the direct deformation value, the deformation rate can also be calculated. For example, the deformation difference between two adjacent monitoring moments is divided by the time interval, and the deformation rate is recorded as , and the deformation acceleration is obtained by The second difference calculation of Features; for microseismic activity data, extract the magnitude of microseismic events ,frequency ,energy Features; For surrounding rock pressure data, calculate the pressure gradient feature.

[0020] From the surrounding rock monitoring data The extracted feature vectors include the surrounding rock deformation vector , the sorted surrounding rock pressure data vector , stress distribution data vector and microseismicity data vector ; Surrounding rock deformation vector , the sorted surrounding rock pressure data vector , stress distribution data vector Arranged in a certain spatial order, the microseismic activity data vector Arrange in a certain time order; Construction phase data Including the current excavation depth, face position, completed support steps, and converted into corresponding feature vectors; Reinforcement measures parameters Including the length, spacing, grouting amount of the anchor rod, and the prestressing parameters of the anchor cable, and converted into corresponding eigenvectors.

[0021] S3. Model prediction and analysis: Integrate preprocessed multi-source data to form a complete input sample , and input into the model Conduct analysis; Among them, the model It is a pre-trained integrated model that integrates long short-term memory network LSTM, convolutional neural network CNN and support vector machine SVM. The specific analysis steps are as follows: The pre-processed construction phase data , surrounding rock monitoring data and reinforcement measures parameters Integrate to form a complete input sample ; The constructed input sample Feed the trained model combining long short-term memory network (LSTM), convolutional neural network (CNN), support vector machine (SVM) and Transformer middle; In this embodiment, the model The aim is to make a comprehensive and accurate prediction of the surrounding rock state of underground powerhouse caverns by integrating the advantages of the three models of LSTM, CNN and SVM. First, the LSTM layer focuses on processing the time series characteristics of microseismic activity data and exploring the evolution trend of microseismic events over time; at the same time, CNN performs convolution operations on the spatial distribution data of surrounding rock deformation and stress to extract key spatial features; then, feature engineering is used to extract key features from construction stage data and reinforcement measures parameters, and weighted fusion is performed with the feature vectors output by LSTM and CNN; finally, the fused feature vector is input into the SVM model for the final prediction, and key information such as deformation, stress, damage zone distribution of surrounding rock and evolution stage of microseismic source parameters is output, providing a scientific basis and decision-making support for underground engineering construction.

[0022] LSTM layer for microseismic activity data vector Perform analytical processing; According to the sequence and time interval of microseismic events, the model is executed The pre-set 1-3 LSTM layers extract the evolution trend characteristics of microseismic activity and output the characteristic vector of the evolution stage of microseismic source parameters ; Among them, each LSTM layer contains 64-256 hidden units; Specifically, based on the complexity of engineering data and the training effect of the model, after many experiments and adjustments, it was found that 64-256 hidden units can capture the time series characteristics of microseismic activity while avoiding overfitting and underfitting problems, thereby better extracting the evolution trend characteristics of microseismic activity. Furthermore, for cases where the data volume is small and the microseismic activity is relatively simple, 64 hidden units are sufficient to learn key information; when the data volume is large and the microseismic activity is more complex, increasing the number of hidden units to 256 helps to improve the expressiveness and accuracy of the model.

[0023] CNN performs convolution operation on the spatial distribution data of surrounding rock deformation and damage zone, extracts spatial features through convolution kernels of different scales, and outputs the spatial feature vectors of surrounding rock deformation and stress distribution. and ; In order to identify the local concentrated area of ​​surrounding rock deformation and the shape and position of stress concentration area, the surrounding rock deformation vector And the sorted surrounding rock pressure data vector Spatial feature extraction is performed through 2-3 convolutional layers with kernel sizes ranging from 3×3 to 5×5 and strides of 1 or 2. Each convolutional layer is followed by a maximum pooling layer. Specifically, 2-3 convolutional layers are used to gradually extract the spatial characteristics of surrounding rock deformation and stress distribution, from shallow local features to deep more abstract and global features. Smaller convolution kernels (3×3 and 5×5) can focus on the characteristics of local areas, such as subtle changes in surrounding rock deformation and the starting point of stress concentration, while larger step sizes can appropriately reduce the amount of calculation while expanding the receptive field, which helps to capture a wider range of spatial relationships. The maximum pooling layer after each convolutional layer is used to reduce the resolution of the feature map and further extract the main features, while reducing the number of parameters and computational complexity of the model, so that the model can converge faster and generalize better to new data.

[0024] Using feature engineering to extract data from construction phases and reinforcement measures parameters Extract key features and form vectors , and used as the input data of the SVM model, the feature vectors output by LSTM and CNN after passing through their respective fully connected layers , and The weighted summation method is used for calculation, and the calculation steps are as follows: Assume the weights are , , ; Specifically, the weight , , The determination of the weights was carried out by using a grid search method based on cross-validation, and different weight combinations were tried on the training set to find the weight value that makes the model predict the best performance on the validation set. For example, the initial weight range was set to 0 to 1 with a step size of 0.1. Through the evaluation of different combinations, the current weight value was finally determined, so that the features extracted by LSTM and CNN can reasonably contribute information according to their importance to the prediction of the surrounding rock state in the decision-making process of the SVM model, thereby improving the prediction accuracy of the overall model.

[0025] ; Get the fused feature vector , the fusion feature vector Input into the SVM model and according to the fusion feature vector Execute the final prediction and use the SoftMax function to output the deformation prediction value of the surrounding rock , stress prediction value , predicted probability of damage area distribution and the prediction probability of the evolution stage of microseismic source parameters .

[0026] S4. Construction monitoring and early warning: The model Output of predicted deformation value of surrounding rock , stress prediction value , predicted probability of damage area distribution and the prediction probability of the evolution stage of microseismic source parameters After the prediction results are integrated and feature encoded, they are passed to the Transformer model as input; In the input layer of Transformer, the input data is first positionally encoded. This step adds position information to each input feature through a specific function, so that the model can capture the sequence order of the data. This is crucial for processing time series-related prediction results (such as time series prediction values ​​of deformation and stress) and spatial information of different monitoring locations (such as the probability of damage zone distribution in different regions). The data then enters the core architecture consisting of multiple encoder layers and decoder layers. In each encoder layer, there are two key parts: the Multi-Head Self-Attention mechanism and the Feed-Forward Network. The multi-head self-attention mechanism allows the model to simultaneously focus on various parts of the input data in different representation subspaces, thereby being able to fully capture the complex dependencies and interactions between different prediction results. For example, it can simultaneously focus on the correlation between the changing trend of deformation values ​​and the stress concentration area, as well as the potential connection between microseismic activity and the development of the damage zone, and output a set of reweighted and integrated feature representations through the calculation of the multi-head attention mechanism.

[0027] Next, this set of feature representations enters the feedforward neural network, which consists of two linear transformation layers and a ReLU activation function. Its function is to perform further nonlinear transformation and feature extraction on the features processed by the attention mechanism, enhance the expressive power of the model, and enable the model to learn more complex feature combinations and patterns.

[0028] After being processed in sequence by multiple encoder layers, the data is continuously refined and information fused. Finally, at the output layer, a linear projection layer is used to map the final feature representation into a single comprehensive warning indicator. The weight of this linear projection layer is continuously optimized through the back propagation algorithm during the model training process. Its purpose is to find the various prediction results of the input and the comprehensive warning indicators. The optimal mapping relationship between them makes the comprehensive early warning indicators It can accurately reflect the overall safety status of the surrounding rock so as to provide a comprehensive early warning indicator By comparing with the pre-set threshold, effective engineering risk warning and reasonable construction decision-making can be achieved, providing strong protection for the construction safety of underground powerhouse cavern groups.

[0029] In the preferred solution, in step S4, the surrounding rock deformation level and early warning are determined based on the Euclidean distance formula, and the specific steps are as follows: Assume that the standard surrounding rock data in the database for: ; in, Indicates the deformation dimension of different monitoring positions, such as the deformation value of different measuring points at the arch, side wall, etc. Corresponding to four deformation levels, standard surrounding rock data Vector representation of typical deformation conditions corresponding to different deformation levels; Calculate the deformation prediction value of the current surrounding rock With various standard surrounding rock data The Euclidean distance , the Euclidean distance calculation formula is: ; By comparison The size of determines the deformation level: like , it is judged as a slight deformation of the first level, and the deformation amount per day is expressed as ; Among them, the deformation of each monitoring position is taken The average value of the daily deformation is measured as ,but,

[0030] And the duration is longer and the duration is set to , , The duration threshold of slight deformation is determined based on engineering experience. At the same time, there is local block drop. The local block drop judgment index is set as ,satisfy ,but To determine the threshold for local block loss.

[0031] like , it is judged as secondary medium deformation, and the daily deformation is expressed as , and initial support cracking occurs, and the initial support cracking judgment index is set as ,satisfy , To determine the threshold of initial support cracking and block falling, the same And the steel frame distortion phenomenon, the steel frame distortion judgment index is set as ,satisfy , The threshold for determining steel frame distortion.

[0032] like , it is judged as grade 3 severe deformation, and the daily deformation is expressed as At the same time, the support crack damage is serious. The judgment index of support crack damage is ,satisfy , In order to determine the threshold of severe support crack damage and steel frame distortion and fracture, the steel frame distortion and fracture judgment index is set as ,satisfy , In order to determine the threshold of steel frame distortion and fracture, and with obvious damage to new wires, the new wire damage obvious judgment index is set as ,satisfy , The threshold for determining whether new line damage is obvious.

[0033] like , it is judged as the fourth level of extremely strong deformation, and the daily deformation is expressed as , and the supporting structure is seriously damaged, the judgment index of serious damage of the supporting structure is ,satisfy , To determine the threshold of serious damage to the supporting structure, the steel frame is twisted and broken, meeting the , the clearing line damage is obvious, and the clearing line damage is obvious. ,satisfy , In order to determine the threshold of obvious line damage, even 2-inch cracks appeared locally, the crack size judgment index was set as ,satisfy inch corresponding length threshold .

[0034] In the preferred solution, when the Euclidean distance After determining the deformation level of the surrounding rock, combined with the model Output of predicted deformation value of surrounding rock , stress prediction value , predicted probability of damage area distribution and the prediction probability of the evolution stage of microseismic source parameters Conduct comprehensive early warning.

[0035] Defining comprehensive early warning indicators , which is a weighted combination of the following: ; in, , , , The weight coefficients of the four factors, namely, deformation level, stress, probability of distribution of damage zone, and evolution stage of microseismic source parameters, in the calculation of comprehensive early warning indicators reflect the relative importance of each factor to the overall risk assessment. The weight coefficient determines the relative contribution of each factor in the calculation of comprehensive early warning indicators. Determine according to the actual situation and importance of the project , , , , and satisfies ; get: ; Among them, first obtain the surrounding rock deformation grade , according to the surrounding rock deformation grade Substitute the value into the deformation level function Get the corresponding function value, and then convert the stress prediction value With stress threshold , Compare, substitute the stress function Get the corresponding function value and predict the probability of damage zone distribution and the prediction probability of the evolution stage of microseismic source parameters , and then substituted into the probability function of the damage area distribution after comparing with their respective thresholds and the probability function of the evolution stage of microseismic source parameters Get the corresponding function value, and finally, multiply the corresponding function value by the corresponding weight coefficient , , , After adding, we get the comprehensive early warning index .

[0036] Comprehensive early warning indicators The specific calculation steps are as follows: Assume that the surrounding rock deformation level determined by the Euclidean distance is ; Among them, the surrounding rock deformation level The values ​​are 1, 2, 3, and 4, corresponding to level 1 slight deformation, level 2 moderate deformation, level 3 strong deformation, and level 4 extremely strong deformation, respectively, and are used to reflect the severity of surrounding rock deformation; Deformation level function According to the surrounding rock deformation grade Assign different basic scores to the surrounding rock deformation level Factors are quantified. The higher the level, the greater the score, to reflect the importance of deformation level in comprehensive early warning. That is, according to the input surrounding rock deformation level value, directly output the corresponding fixed score, the formula is as follows: ; set up and is the stress threshold, according to the stress prediction value Relationship with threshold value determines stress function The function value of is: ; When the stress prediction value When , the function value is 1, indicating that the stress is at a low level and its contribution to the comprehensive early warning index is relatively small; When the stress prediction value exist and When the value of the function increases linearly, it reflects the increasing influence of stress on risk in this interval; When the stress prediction value When , the function value increases with the stress, and the growth rate is The ratio of reflects the rapid increase in risk after stress exceeds a higher threshold; set up and is the probability threshold of the damage zone distribution, and , , then the probability function of the damage zone distribution is The formula is as follows: ; Predicted probability based on damage zone distribution With threshold , The relationship between the damage zone and the impact of the damage zone probability is analyzed and its contribution to the comprehensive early warning index is quantified through piecewise function, so that the function value can more reasonably reflect the impact of the damage zone probability.

[0037] set up and is the probability threshold of the microseismic source parameter evolution stage, and , , then the probability function of the evolution stage of microseismic source parameters is The formula is as follows: ; This function predicts the probability of the evolution stage of microseismic source parameters With threshold , By comparing the values ​​of the above two methods, the function value is determined in a piecewise form, so as to incorporate the microseismic factors into the comprehensive early warning system and reflect the relationship between the degree of its influence on the early warning and the change of probability.

[0038] set up , and is the warning threshold, and the comprehensive warning index is calculated based on Compare with the set warning threshold to determine the warning level; Among them, , , , then the formula is expressed as: ; Specifically, when When , it is a safe state, and normal construction and monitoring frequency can be maintained without taking special measures; when When , which is a low-risk state. Although the risk has increased, it is still within an acceptable range. Normal construction and monitoring frequency can be maintained, but some simple special measures may need to be taken, such as increasing the frequency of data monitoring; when When , which is a medium-risk state, issues an early warning signal to prompt construction personnel to strengthen on-site inspections, check the integrity and stability of the support structure, and prepare possible emergency measures, such as preparing a certain amount of support materials and emergency equipment.

[0039] when When , it is a high-risk state, and an alarm is immediately issued to suspend construction, organize personnel to evacuate the dangerous area, and take emergency rescue measures, such as rapid reinforcement of the surrounding rock. Spraying of concrete and installation of temporary supports began within hours. At the same time, a comprehensive assessment and redesign of the project were carried out to develop a safer and more reliable construction plan, including adjustments to excavation methods and support parameters. The surrounding rock conditions were continuously and closely monitored before the implementation of the new plan.

[0040] Through the visual interface display, according to The value of is represented by different colors in the animation simulation of the deformation of the surrounding rock. The color cloud map of stress distribution is rendered with different transparency and color to indicate the predicted probability of damage zone distribution. The probability of different damage zone categories in the microseismic source parameters and the predicted probability according to the evolution stage of the microseismic source parameters High-risk microseismic hotspots are highlighted in bright colors.

[0041] For the surrounding rock deformation, according to the vector The preset color mapping rules are used to map different deformations to different colors, and then they are presented in the form of animation simulation. As time goes by and construction progresses, the animation can dynamically display the spatial distribution of surrounding rock deformation and its changing trend, allowing engineers to clearly identify the areas of increase and decrease in deformation, as well as the rate and direction of deformation, so as to have an intuitive understanding of the stability of the surrounding rock.

[0042] The stress distribution is presented in the form of a color cloud map based on the stress prediction value. , using color rendering technology, low stress areas are represented by cool blue, high stress areas are represented by warm red, and intermediate stress values ​​correspond to different degrees of transition colors. In this way, engineers can know the distribution of internal stress in the surrounding rock at a glance, just like looking at a weather cloud map to understand the distribution of air pressure or temperature, and quickly locate stress concentration areas so that corresponding measures can be taken in time, such as strengthening support or adjusting construction technology, to prevent surrounding rock damage caused by stress concentration.

[0043] The probability map of the damage area distribution is obtained by predicting the probability of damage area distribution. The probability of each damage zone category is distinguished by using different transparency and colors. Low-probability damage zones are displayed in more transparent colors. As the probability increases, the transparency of the color decreases and the saturation increases. In this way, engineers can intuitively distinguish which areas have a higher probability of damage, as well as the relative high and low probability of damage in different areas, thus providing a strong basis for taking reinforcement measures in advance or adjusting the construction schedule, and ensuring the safe advancement of the project.

[0044] Microseismic activity hotspot map predicts the probability of microseismic source parameter evolution stage The areas with frequent and high probability of microseismic activity are highlighted with bright colors, such as red or yellow, to form easily identifiable hot spots, while the areas with low probability of microseismic activity are represented by darker or less conspicuous colors. This enables engineering personnel to quickly determine the distribution of dangerous areas and the trend of strength of microseismic activity, rationally plan the work areas of construction personnel, avoid dangerous operations in high-risk microseismic areas, and strengthen monitoring and early warning of these areas, effectively prevent safety accidents such as surrounding rock instability caused by microseismic activity, and ensure the safety and smoothness of the construction process of underground powerhouse caverns.

[0045] S5. Monitoring frequency adjustment Assume the deformation speed is , by calculating two adjacent monitoring moments, let the time interval be The deformation difference , then the deformation speed ; when mm / day, determine the monitoring frequency : ; in, and To further divide the speed interval threshold, that is mm / day, mm / day; According to the determined monitoring frequency , adjust the data collection cycle of the monitoring equipment to ensure timely acquisition of sufficient surrounding rock status information.

[0046] S6. Monitoring and measurement data analysis and construction evaluation S61. Data collection and compilation Assume that the surrounding rock deformation data sequence obtained in each monitoring is , the surrounding rock pressure data series is , the steel frame stress data series is , the concrete stress data series is ; in, Indicates the monitoring time. is the total number of monitoring times; S62. Weekly and monthly stage analysis Weekly Analysis: The data obtained each week are sorted and analyzed separately. For example, for the surrounding rock deformation data, the average weekly deformation is calculated: ; in, For the Weekly monitoring times, Indicates The set of monitoring times corresponding to the week; Similarly, the weekly average surrounding rock pressure can be calculated , Weekly average steel frame stress , Weekly average concrete stress ; Analyze the trend of weekly data by calculating the difference between the average deformation of two consecutive weeks Observe the increase or decrease of deformation and the changes of various stress data to determine the changing trend of surrounding rock conditions; Monthly Analysis: Calculate the average monthly deformation: ; in, For the Monthly monitoring times, Indicates The monitoring time set corresponding to the month is also used to calculate the average surrounding rock pressure per month. , Monthly average steel frame stress , Monthly average concrete stress ; By collating and analyzing the monthly monitoring and measurement data, drawing accurate data change curves, and using rigorous mathematical methods and professional data analysis methods to determine the change patterns of each monitoring and measurement data over time .

[0047] Specifically, use trend fitting techniques in statistical analysis, such as linear regression, polynomial fitting, or seasonal decomposition models, to conduct in-depth data mining. For data with obvious periodic characteristics, use methods such as Fourier transform to accurately determine its period length and fluctuation amplitude; for data with long-term growth or decline trends, use linear regression models to accurately calculate its slope and intercept, so as to describe its changing trend in detail with precise mathematical expressions. If the data changes are more complex and cannot be summarized with simple mathematical expressions, then use rigorous text to elaborate on the characteristics of its changes, including but not limited to phased change trends, the impact of special event points on data, and the correlation changes between different monitoring quantities, etc., to ensure that the grasp of the law of data changes is accurate and unambiguous. .

[0048] S63. Construction status evaluation According to the summary of the monitoring measurement data change rules Evaluate the construction situation. If the surrounding rock deformation continues to increase rapidly, or If the pressure is continuously greater than a certain growth threshold, and the surrounding rock pressure, steel frame stress, concrete stress, etc. also show abnormal changes, that is, they exceed the corresponding safety threshold or the change trend does not meet normal expectations, then it is evaluated that the current construction situation may be risky, and it is necessary to adjust the construction process and strengthen support measures in time; if the changes of various monitoring and measurement data are stable and within the safety range, then the construction situation is good and construction can continue as planned, as shown below: set up is the incremental threshold of surrounding rock deformation, is the safety threshold interval of surrounding rock pressure, is the safety threshold range of steel frame stress, is the safety threshold range of concrete stress.

[0049] If there is a certain week k, the formula for determining the weekly risk situation is as follows: ; If it is determined that there is a risk in the construction situation in a certain week, corresponding measures need to be taken, such as adjusting construction parameters, strengthening on-site inspections, etc. For two consecutive months and , then the monthly risk determination formula is as follows: ; It is determined that there is a risk in the construction situation for two consecutive months, and an in-depth assessment is carried out and measures such as suspending construction and optimizing support plans are implemented.

[0050] For continuous Week or Months are determined by the following week determination formula: ; Or, it can be determined by the following month determination formula: ; The construction is judged to be in good condition and can continue as planned, while maintaining normal monitoring frequency and data analysis process.

[0051] Example 2 Further illustrate with reference to Example 1, Figure 3 The structure shown, Figure 3 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. The electronic device may include: A memory, a processor, and a computer program stored in the memory and executable on the processor.

[0052] When the processor executes the program, the three-dimensional calculation and analysis method for excavation with or without support provided in the above embodiment is implemented.

[0053] Furthermore, the electronic device further comprises: Communication interface, used for communication between memory and processor.

[0054] Memory is used to store computer programs that can be run on the processor.

[0055] The memory may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0056] If the memory, processor and communication interface are implemented independently, the communication interface, memory and processor can be connected to each other through a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The bus can be divided into an address bus, a data bus, a control bus, etc.

[0057] The processor may include one or more processing units, for example, the processor may include an application processor (AP), an application specific integrated circuit (ASIC), a modem processor, a graphics processor (CPU), an image signal processor (ISP), a controller, a memory, a video codec, a digital signal processor (DSP), a baseband processor, and / or a neural-network processing unit (NPU). Among them, different processing units may be independent devices or integrated into one or more processors. Among them, the controller may be a neural center and a command center. The controller may generate an operation control signal according to the instruction opcode and the timing signal to complete the control of fetching and executing instructions. A memory may also be provided in the processor for storing instructions and data. In some embodiments, the memory in the processor is a high-speed cache memory. The memory may store instructions or data that have just been used or circulated by the processor. If the processor needs to use the instruction or data again, it may be directly called from the memory. Repeated access is avoided, the waiting time of the processor is reduced, and the efficiency of the system is improved.

[0058] A visualization module is used to display images, videos, etc. The visualization module may include a display panel, which may be a liquid crystal display (LCD), an organic light-emitting diode (OLED), an active-matrix organic light-emitting diode or an active-matrix organic light-emitting diode (AMOLED), a flexible light-emitting diode (FLED), Miniled, MicroLed, Micro-oLed, a quantum dot light-emitting diode (QLED), etc.

[0059] Optionally, in a specific implementation, if the memory, processor and communication interface are integrated on a chip, the memory, processor and communication interface can communicate with each other through an internal interface.

[0060] An embodiment of the present application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-mentioned three-dimensional calculation and analysis method for excavation with or without support.

[0061] An embodiment of the present application also provides a computer program product, which can run computer instructions. When the computer instructions are executed by a processor, the three-dimensional calculation and analysis method of excavation with or without support as described above is implemented.

[0062] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purpose of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or N wirings (electronic devices), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways as necessary and then storing it in a computer memory.

[0063] The storage medium mentioned above may be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limiting the present application. A person of ordinary skill in the art may change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A three-dimensional calculation and analysis method for excavation with or without support, characterized in that: The following steps are involved: S1. Data collection and preprocessing: obtaining geological information of on-site monitoring equipment and construction areas; Collect multi-source data of the current construction process based on the on-site monitoring equipment of the underground powerhouse caverns and the geological information of the construction area, including construction stage data , surrounding rock monitoring data And reinforcement measures parameters ; S2, data cleaning and feature extraction: perform preprocessing operations on the collected multi-source data, and extract feature vectors based on the preprocessed multi-source data; S3. Model prediction and analysis: Integrate preprocessed multi-source data to form a complete input sample , and input into the model Conduct analysis and obtain prediction results.

2. The three-dimensional calculation and analysis method for excavation with or without support according to claim 1 is characterized in that: Model It is a pre-trained integrated model, which integrates long short-term memory network LSTM, convolutional neural network CNN, support vector machine SVM and Transformer, and also includes the following steps: S4. Construction monitoring and early warning: The prediction results are integrated and feature encoded, and the prediction results are input into the Transformer. The Transformer input layer encodes the position of the data in the prediction results to capture the sequence order. Then the data enters multiple encoder layers and captures the correlation between different prediction results. The re-weighted integrated feature representation is output and then enters the feedforward neural network composed of two linear transformation layers and ReLU activation function for nonlinear transformation and feature extraction. After being processed by multiple encoder layers, the data is mapped into a comprehensive early warning indicator through a linear projection layer at the output layer. , whose weights are optimized by the back propagation algorithm during training to determine the input prediction results and comprehensive warning indicators The best mapping relationship between them, and based on the comprehensive early warning indicators Compare with the threshold to determine the warning level; Among them, each encoder layer includes a multi-head self-attention mechanism and a feedforward neural network.

3. The three-dimensional calculation and analysis method for excavation with or without support according to claim 1 is characterized in that: In step S2, the preprocessing operation includes clearing and removing outliers and erroneous data, and is used to integrate and standardize multi-source data so that each data has a unified format and dimension; From the surrounding rock monitoring data The extracted feature vectors include the surrounding rock deformation vector , the sorted surrounding rock pressure data vector , stress distribution data vector and microseismicity data vector ; Surrounding rock deformation vector , the sorted surrounding rock pressure data vector , stress distribution data vector Arranged in a certain spatial order, the microseismic activity data vector Arrange in a certain time order; Construction phase data Including the current excavation depth, face position, completed support steps, and converted into corresponding feature vectors; Reinforcement measures parameters Including the length, spacing, grouting amount of the anchor rod, and the prestressing parameters of the anchor cable, and converted into corresponding eigenvectors.

4. The three-dimensional calculation and analysis method for excavation with or without support according to claim 2 is characterized in that: In step S3, the model For input samples The specific analysis steps are as follows: S31, LSTM layer for microseismic activity data vector Perform analytical processing; According to the sequence and time interval of microseismic events, the model is executed The pre-set 1-3 LSTM layers extract the evolution trend characteristics of microseismic activity and output the characteristic vector of the evolution stage of microseismic source parameters ; Among them, each LSTM layer contains 64-256 hidden units; S32, CNN performs convolution operation on the spatial distribution data of surrounding rock deformation and damage zone, extracts spatial features through convolution kernels of different scales, and outputs the spatial feature vector of surrounding rock deformation and stress distribution and ; In order to identify the local concentrated area of ​​surrounding rock deformation and the shape and position of stress concentration area, the surrounding rock deformation vector , the sorted surrounding rock pressure data vector and stress distribution data vector Spatial feature extraction is performed through 2-3 convolutional layers with kernel sizes ranging from 3×3 to 5×5 and strides of 1 or 2. Each convolutional layer is followed by a maximum pooling layer. S33. Using feature engineering to extract data from the construction phase and reinforcement measures parameters Extract key features and form vectors , and used as the input data of the SVM model, the feature vectors output by LSTM and CNN after passing through their respective fully connected layers , and And use weighted summation to calculate and fuse the feature vector The calculation formula is as follows: ； The weights are , , ; The fused feature vector Input into the SVM model and according to the fusion feature vector Execute the prediction and use the SoftMax function to output the deformation prediction value of the surrounding rock , stress prediction value , predicted probability of damage area distribution and the prediction probability of the evolution stage of microseismic source parameters .

5. The three-dimensional calculation and analysis method for excavation with or without support according to claim 4 is characterized in that: In step S4, the standard surrounding rock data in the database is for: ； in, Represents the deformation dimension of different monitoring positions, Corresponding to four deformation levels, standard surrounding rock data Vector representation of typical deformation conditions corresponding to different deformation levels; Calculate the deformation prediction value of the current surrounding rock With various standard surrounding rock data The Euclidean distance , the Euclidean distance calculation formula is: ； By comparing the Euclidean distance middle The size of determines the deformation level: like , it is determined to be a first-level slight deformation, and the daily deformation amount is expressed as ; like , it is determined to be a secondary medium deformation, and the daily deformation is expressed as ; like , it is determined to be a third-level severe deformation, and the daily deformation is expressed as ; like , it is determined to be extremely strong deformation of level 4, and the daily deformation is expressed as .

6. The three-dimensional calculation and analysis method for excavation with or without support according to claim 5 is characterized in that: According to Euclidean distance Determine the deformation level of the surrounding rock and combine it with the model Output of predicted deformation value of surrounding rock , stress prediction value , predicted probability of damage area distribution and the prediction probability of the evolution stage of microseismic source parameters Conduct comprehensive early warning; Defining comprehensive early warning indicators , which is a weighted combination of the following: ； in, , , , They are the weight coefficients of deformation level, stress, probability of distribution of damage zone and evolution stage of microseismic source parameters in the calculation of comprehensive early warning indicators; Determine according to the actual situation and importance of the project , , , , and satisfies ; get: ; Among them, the surrounding rock deformation grade is obtained , according to the surrounding rock deformation grade Substitute the value into the deformation level function Get the corresponding function value and convert the stress prediction value With stress threshold , Compare, substitute the stress function Get the corresponding function value and predict the probability of damage zone distribution and the prediction probability of the evolution stage of microseismic source parameters , and then substituted into the probability function of the damage area distribution after comparing with their respective thresholds and the probability function of the evolution stage of microseismic source parameters Get the corresponding function value, and multiply the corresponding function value by the corresponding weight coefficient , , , After adding, we get the comprehensive early warning index .

7. The three-dimensional calculation and analysis method for excavation with or without support according to claim 6 is characterized in that: The comprehensive early warning indicators The specific calculation steps are as follows: Assume that the surrounding rock deformation level determined by the Euclidean distance is ; Among them, the surrounding rock deformation level The values ​​are 1, 2, 3, and 4, corresponding to level 1 slight deformation, level 2 moderate deformation, level 3 strong deformation, and level 4 extremely strong deformation, respectively, and are used to reflect the severity of surrounding rock deformation; Deformation level function According to the surrounding rock deformation grade Assign different basic scores to the surrounding rock deformation level Factor quantification, that is, according to the input surrounding rock deformation level value, directly output the corresponding fixed score, the formula is as follows: ； set up and is the stress threshold, according to the stress prediction value The relationship with the threshold determines the stress function Function value of : ； set up and is the probability threshold of the damage zone distribution, and , , then the probability function of the damage zone distribution is The formula is as follows: ； set up and is the probability threshold of the microseismic source parameter evolution stage, and , , then the probability function of the microseismic source parameter evolution stage is The formula is as follows: ； set up , and is the warning threshold, and the comprehensive warning index is calculated based on Compare with the set warning threshold to determine the warning level; Among them, , , , then the formula is expressed as: ； Through the visual interface display, according to The value of is represented by different colors in the animation simulation of the deformation of the surrounding rock. The color cloud map of stress distribution is rendered with different transparency and colors to indicate the predicted probability of damage zone distribution. The probability of different damage zone categories in the microseismic source parameters and the predicted probability according to the evolution stage of the microseismic source parameters High-risk microseismic hotspots are highlighted in bright colors.

8. The three-dimensional calculation and analysis method for excavation with or without support according to claim 6 is characterized in that: S5. Monitoring frequency adjustment: according to the deformation prediction value of surrounding rock , stress prediction value , predicted probability of damage area distribution and the prediction probability of the evolution stage of microseismic source parameters and comprehensive early warning indicators Determine the current status of the underground powerhouse cavern complex. The specific steps are as follows: Assume the deformation speed is , by calculating two adjacent monitoring moments, let the time interval be The deformation difference , then the formula of deformation speed is as follows: ； when mm / day, determine the monitoring frequency , and is expressed by the following formula: ； in, and To further divide the speed interval threshold, that is mm / day, mm / day; According to the determined monitoring frequency , adjust the data collection cycle of the monitoring equipment to ensure timely acquisition of sufficient surrounding rock status information.

9. The three-dimensional calculation and analysis method for excavation with or without support according to claim 8 is characterized in that: S6. Monitoring and measurement data phase analysis and construction evaluation: Determine the construction phase data through weekly and monthly analysis. , surrounding rock monitoring data And reinforcement measures parameters The specific steps are as follows: S61. Data collection and collation: Assume that the surrounding rock deformation data sequence obtained in each monitoring is , the surrounding rock pressure data series is , the steel frame stress data series is , the concrete stress data series is ; in, Indicates the monitoring time. is the total number of monitoring times; S62. Weekly and monthly stage analysis Weekly Analysis: The data obtained each week are sorted and analyzed separately, that is, the average weekly deformation of the surrounding rock deformation data is calculated: ； in, For the Weekly monitoring times, Indicates The set of monitoring times corresponding to the week; Similarly, the weekly average surrounding rock pressure can be calculated , Weekly average steel frame stress , Weekly average concrete stress ; Analyze the trend of weekly data by calculating the difference between the average deformation of two consecutive weeks Observe the increase or decrease of deformation and the changes of various stress data to determine the changing trend of surrounding rock conditions; Monthly Analysis: Calculate the average monthly deformation: ； in, For the Monthly monitoring times, Indicates The monitoring time set corresponding to the month can be used to calculate the average surrounding rock pressure per month. , Monthly average steel frame stress , Monthly average concrete stress ; Through the weekly data change trend and monthly monitoring measurement data collation and analysis, determine the change pattern of each monitoring measurement data over time .

10. The three-dimensional calculation and analysis method for excavation with or without support according to claim 9 is characterized in that: In step S6, according to the change rule The specific steps for carrying out the construction status evaluation are as follows: set up is the incremental threshold of surrounding rock deformation, is the safety threshold interval of surrounding rock pressure, is the safety threshold range of steel frame stress, is the safety threshold interval of concrete stress; If there is a certain week k, the formula for determining the weekly risk situation is as follows: ； For two consecutive months and , then the monthly risk determination formula is as follows: ； If a week or two consecutive months are identified as being at risk, an in-depth assessment is performed and appropriate measures are taken.

Images