Excavating and supporting method for underground powerhouse of pumped storage power station

Abstract

The invention provides a pumped storage power station underground powerhouse excavating and supporting method, an underground powerhouse comprises a first space with an arch-shaped section at the top and a second space with a rectangular section at the bottom, and the method comprises the steps that a tunnel boring machine is adopted to excavate the middle area of the section of the first space, and a middle pilot tunnel penetrating through the underground powerhouse is formed; the section of the middle pilot tunnel is circular and is tangent to the vault of the first space; areas on the two sides of the section of the first space are excavated through a blasting method, and the areas on the two sides of the section communicate with the middle pilot tunnel and comprise an upstream area and a downstream area; along with excavation, a bolting-grouting integrated trolley is adopted for conducting anchor rod supporting on the arch crown of the upstream area and the arch crown of the downstream area, so that anchor rod supporting of the whole arch crown is completed; and the second space continues to be excavated through the blasting method, and excavation of the underground powerhouse is completed. The excavation supporting method for the underground powerhouse of the pumped storage power station is simple, convenient, high in construction efficiency, short in consumed time, low in cost and high in safety.

Description

Technical Field

[0001] The present application relates to the field of pumped-storage power station control technology, and in particular to a method for excavating and supporting an underground powerhouse in a pumped-storage power station. Background Art

[0002] Pumped storage is the use of electricity during the low load period to pump water to the upper reservoir, and then release the water stored in the upper reservoir to the lower reservoir for power generation during the peak load period, also known as energy storage power generation. It can convert the excess electricity during the low load period of the power grid into high-value electricity during the high load period of the power grid, suitable for frequency and phase modulation, can be used to stabilize the frequency and voltage of the power system, and is suitable for emergency standby, and can also improve the efficiency of thermal power plants and nuclear power plants in the power system.

[0003] The span of the underground powerhouse of a pumped-storage power station is generally 22m-30m, and the height is 52m-60m. It is a large underground cavern. The excavation and support of the underground powerhouse will be affected by factors such as geological conditions, surrounding rock deformation, construction resources, and construction organization. The existing excavation and support methods are inefficient and have high construction costs. Therefore, a more efficient excavation and support method for underground powerhouses of pumped-storage power stations is urgently needed. Summary of the invention

[0004] In view of this, the purpose of the present application is to propose a method for excavating and supporting an underground powerhouse of a pumped-storage power station to solve the related problems mentioned in the background technology.

[0005] The present application provides a method for excavating and supporting an underground powerhouse in a pumped-storage power station, wherein the underground powerhouse comprises a first space with an arched cross-section at the top and a second space with a rectangular cross-section at the bottom, and the method comprises: using a tunnel boring machine to excavate the middle area of ​​the cross-section of the first space to form a middle guide tunnel that runs through the underground powerhouse, wherein the cross-section of the middle guide tunnel is circular and tangent to the arch of the first space; using a blasting method to respectively excavate the areas on both sides of the cross-section of the first space, wherein the areas on both sides of the cross-section are connected to the middle guide tunnel, including an upstream area and a downstream area; as the excavation proceeds, using an anchor-grouting integrated trolley to respectively anchor the arches of the upstream area and the downstream area, so that the entire arch is anchored; using a blasting method to continue excavating the second space to complete the excavation of the underground powerhouse.

[0006] Furthermore, the blasting method is used to respectively excavate the areas on both sides of the cross-section of the first space, including: excavating the downstream area laterally from the middle guide tunnel to the edge of the underground factory building, and then excavating the downstream area along the axial direction of the middle guide tunnel; after the excavation of the downstream area reaches a preset length, synchronously excavating the upstream area laterally from the middle guide tunnel to the edge of the underground factory building, and excavating the upstream area along the axial direction of the middle guide tunnel.

[0007] Furthermore, the step of excavating the two side regions of the cross section of the first space by blasting also includes: excavating the two side regions of the cross section synchronously from both ends of the middle guide hole along the axial direction toward the middle.

[0008] Furthermore, the anchor support includes a drilling process, a grouting process and a rod inserting process, and the time of the drilling process is longer than the time of the grouting process, which is longer than the time of the rod inserting process.

[0009] Furthermore, the time of the anchor support is obtained by pre-using the anchor-grouting integrated trolley to perform anchor support multiple times, recording the time of the drilling process, the grouting process and the rod insertion process, and using statistical software to analyze the time optimization of each process.

[0010] Furthermore, the anchor support comprises: alternately anchoring a first anchor and a second anchor at intervals along a vault cross section of the first space, wherein the length of the first anchor is greater than the length of the second anchor.

[0011] Furthermore, the anchor support comprises: real-time monitoring of the deformation displacement of multiple areas of the vault of the first space; and within a preset time, anchor support is performed on the area where the deformation displacement is greater than a first preset displacement.

[0012] Furthermore, the anchor support further comprises: performing prediction based on the deformation displacement to obtain a predicted displacement of the area after a predetermined period; and performing anchor support on an area where the predicted displacement is greater than a second preset displacement.

[0013] Furthermore, predicting based on the deformation displacement to obtain the predicted displacement of the area after a predetermined period includes: inputting the deformation displacement into a pre-trained prediction model to obtain a displacement simulation curve; and determining the predicted displacement of the area after a predetermined period based on the displacement simulation curve.

[0014] Furthermore, the prediction model is a back propagation neural network model improved by the sparrow search algorithm, wherein the number of input nodes of the neural network model is 6, the number of output nodes is 1, and the number of nodes in the hidden layer is 4; the initial population size of the sparrow search algorithm is 20, the maximum number of iterations is 50, the explorer ratio is 0.2, the scout ratio is 0.2, and the warning value is 0.8.

[0015] As can be seen from the above, the present application provides a method for excavating and supporting an underground powerhouse in a pumped-storage power station, wherein the underground powerhouse includes a first space with an arched cross-section at the top and a second space with a rectangular cross-section at the bottom, and the method includes: using a tunnel boring machine to excavate the middle area of ​​the cross-section of the first space to form a middle guide tunnel that runs through the underground powerhouse, and the cross-section of the middle guide tunnel is circular and tangent to the arch of the first space; using blasting to respectively excavate the areas on both sides of the cross-section of the first space, and the areas on both sides of the cross-section are connected to the middle guide tunnel, including an upstream area and a downstream area; as the excavation proceeds, using an integrated anchor-grouting trolley to respectively anchor the arches of the upstream area and the downstream area, so that the entire arch is anchored; using blasting to continue excavating the second space to complete the excavation of the underground powerhouse. The middle guide hole has a circular cross section, which is smaller than the existing structural cross section area, and there is no exposed vault. By setting the middle guide hole tangent to the vault, it has been tested that the deformation displacement of the middle guide hole is very low. The vault does not need to be anchored during the entire process of digging the middle guide hole. Anchor support is only performed when excavating the two sides. In this way, an anchor-injection integrated trolley can be used to reciprocate in the upstream and downstream areas for anchor support. Compared with the existing anchor support method, the efficiency is greatly improved and the safety is guaranteed. The excavation and support method of the underground powerhouse of the pumped storage power station is simple and convenient, with high construction efficiency, short time consumption, low cost, and strong safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the present application or related technologies, the drawings required for use in the embodiments or related technical descriptions are briefly introduced below. Obviously, the drawings described below are only embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0017] Figure 1 It is a schematic diagram of the cross-sectional structure of an underground workshop;

[0018] Figure 2 It is a schematic diagram of the cross-sectional structure of the first space excavation in the related art;

[0019] Figure 3 A top view of a first space excavation in the related art;

[0020] Figure 4 This is a schematic diagram of the cross-sectional structure of the first space excavation in the embodiment of the present application;

[0021] Figure 5 A top view of a first space excavation in an embodiment of the present application;

[0022] Figure 6 A top view of another first space excavation in an embodiment of the present application;

[0023] Figure 7 A schematic diagram of a process for excavating and supporting an underground powerhouse of a pumped-storage power station in an embodiment of the present application;

[0024] Figure 8 This is a schematic diagram of the anchoring time of the first anchor rod in the embodiment of the present application;

[0025] Fig. 9 This is a schematic diagram of the anchoring time of the second anchor rod in the embodiment of the present application;

[0026] Fig.10 This is a schematic diagram of the deformation and displacement of the pilot hole excavation in the first space in the embodiment of the present application;

[0027] Fig.11 This is a flow chart of the inversion of surrounding rock mechanical parameters of the SSA-BP model in the embodiment of the present application;

[0028] Fig.12 This is a comparison chart of the prediction results of the SSA-BP model and the BP model in the embodiments of the present application.

[0029] Figure numerals: 1, first space; 1-1, middle guide hole; 1-2, upstream area; 1-3, downstream area; 2, second space; 3, first anchor rod; 4, second anchor rod. DETAILED DESCRIPTION

[0030] In order to make the objectives, technical solutions and advantages of the present application more clearly understood, the present application is further described in detail below in combination with specific embodiments and with reference to the accompanying drawings.

[0031] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the embodiments of the present application should be understood by people with ordinary skills in the field to which the present application belongs. "Include" or "comprising" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect.

[0032] Pumped storage is the use of electricity during the low load period to pump water to the upper reservoir, and then release the water stored in the upper reservoir to the lower reservoir for power generation during the peak load period, also known as energy storage power generation. It can convert the excess electricity during the low load period of the power grid into high-value electricity during the high load period of the power grid, suitable for frequency and phase modulation, can be used to stabilize the frequency and voltage of the power system, and is suitable for emergency standby, and can also improve the efficiency of thermal power plants and nuclear power plants in the power system.

[0033] The span of the underground powerhouse of a pumped-storage power station is generally 22m-30m, and the height is 52m-60m. It is a large underground cavern. The excavation and support of the underground powerhouse will be affected by factors such as geological conditions, surrounding rock deformation, construction resources, and construction organization. The existing excavation and support methods are inefficient and have high construction costs. Therefore, a more efficient excavation and support method for underground powerhouses of pumped-storage power stations is urgently needed.

[0034] like Figure 1 As shown in FIG. 1 , it is a schematic cross-sectional view of an underground powerhouse, including a first space 1 with an arched cross-section at the top and a second space 2 with a rectangular cross-section at the bottom. Currently, the drilling and blasting method is often used to excavate underground powerhouses in sections, such as Figure 2 As shown, for the first space 1, a middle guide hole 1-1 in the middle area, and downstream areas 1-3 and upstream areas 1-2 on both sides are excavated respectively. The cross section of the middle guide hole 1-1 is similar to a rectangle, and part of the vaults of the middle guide hole 1-1, upstream area 1-2 and downstream area 1-3 are exposed; Figure 3 As shown, the three areas will be excavated in a staggered manner, with the middle guide tunnel 1-1 excavated first. After the middle guide tunnel 1-1 is excavated for 30m, the downstream area 1-3 will be excavated simultaneously. After the downstream area 1-3 is excavated for 30m, the upstream area 1-2 will be excavated simultaneously to avoid cavern collapse. In order to ensure the stability of the underground powerhouse, while excavating the three areas, the arches of the three areas also need to be anchored. If an integrated anchor-grouting trolley is used for anchoring, it is necessary to repeatedly move the trolley position for anchor support. The trolley is first placed in the middle guide tunnel 1-1, then moved to the downstream area 1-3, and then moved to the upstream area 1-2, and so on, which greatly reduces the construction efficiency. If three integrated anchor-grouting trolleys are used to anchor the three areas respectively, the cost is very high on the one hand, and it occupies a large space on the other hand.

[0035] The technical solution of the present application is described in detail below through specific embodiments in conjunction with the accompanying drawings.

[0036] Some embodiments of the present application provide a method for excavating and supporting an underground powerhouse of a pumped storage power station, such as Figure 7 As shown, the following steps are included:

[0037] S1. Use a tunnel boring machine to dig the middle area of ​​the cross section of the first space 1 to form a middle guide tunnel 1-1 that runs through the underground factory building. The cross section of the middle guide tunnel 1-1 is circular and tangent to the vault of the first space 1.

[0038] like Figure 4As shown, the middle guide tunnel 1-1 has a circular cross-section, which is smaller than the existing structural cross-section area and has no exposed vault. The diameter of the middle guide tunnel 1-1 can be equal to the height of the first space 1, and can also be adjusted according to the model of the tunnel boring machine (TBM). The middle guide tunnel 1-1 can be excavated quickly using a tunnel boring machine.

[0039] like Fig.10 As shown, it is a schematic diagram of the deformation displacement of the middle guide tunnel 1-1 after excavation. By setting the middle guide tunnel 1-1 to be tangent to the arch, it is tested that the deformation displacement of the middle guide tunnel 1-1 is very low. There is no need to anchor the arch during the entire process of excavating the middle guide tunnel 1-1, which improves efficiency.

[0040] S2. Use blasting method to respectively excavate the areas on both sides of the cross section of the first space 1, the areas on both sides of the cross section are connected to the middle guide tunnel 1-1, including the upstream area 1-2 and the downstream area 1-3; as the excavation proceeds, use an integrated anchoring and grouting trolley to respectively anchor the vaults of the upstream area 1-2 and the downstream area 1-3, so that the entire vault is anchored.

[0041] Anchor support is only carried out when excavating the areas on both sides. In this way, an integrated anchor-grouting trolley can be used to reciprocate between the upstream area 1-2 and the downstream area 1-3 for anchor support. Compared with the existing method, the efficiency is greatly improved and the safety is guaranteed. Alternatively, two integrated anchor-grouting trolleys can be used to carry out anchor support for the upstream area 1-2 and the downstream area 1-3 respectively. Compared with using three devices, the space occupied is smaller and the cost is lower.

[0042] S3. Continue to excavate the second space 2 by blasting to complete the excavation of the underground factory building.

[0043] After the vault of the first space 1 is supported, the overall deformation and displacement of the second space 2 is small, so the second space 2 can be directly excavated, and the side walls of the second space 2 can also be supported after excavation.

[0044] The excavation and support method for the underground powerhouse of the pumped storage power station is simple and convenient, has high construction efficiency, short time consumption, low cost, and strong safety.

[0045] In some embodiments, the step of excavating the areas on both sides of the cross section of the first space 1 by blasting includes:

[0046] S201, excavating the downstream area 1-3 laterally from the middle guide tunnel 1-1 toward the edge of the underground powerhouse, and then excavating the downstream area 1-3 along the axial direction of the middle guide tunnel 1-1.

[0047] S202. After the excavation of the downstream area 1-3 reaches a preset length, the upstream area 1-2 is excavated horizontally from the middle guide tunnel 1-1 to the edge of the underground powerhouse, and the upstream area 1-2 is excavated along the axial direction of the middle guide tunnel 1-1.

[0048] like Figure 4 and Figure 5 As shown, after the middle guide tunnel 1-1 is dug through, excavation is carried out from the middle guide tunnel 1-1 to both sides of the cross section, and anchor support is performed during the excavation process to ensure the overall stability of the underground powerhouse. In addition, the downstream area 1-3 and the upstream area 1-2 are excavated in a staggered manner, which can also improve the structural stability of the underground powerhouse.

[0049] In some embodiments, the step of excavating the areas on both sides of the cross section of the first space 1 by blasting also includes:

[0050] S203, excavating the areas on both sides of the cross section synchronously from both ends of the middle guide hole 1-1 along the axial direction toward the middle.

[0051] like Figure 6 As shown, after the middle guide tunnel 1-1 is dug through, excavation can be started synchronously from both ends of the middle guide tunnel 1-1, and the upstream area 1-2 and the downstream area 1-3 are also excavated in a staggered manner, which greatly improves the excavation efficiency. For a long underground factory building, a working surface can also be set in the middle of the middle guide tunnel 1-1. On the basis of starting excavation synchronously from both ends of the middle guide tunnel 1-1, excavation can be carried out synchronously from the working surface to both ends of the middle guide tunnel 1-1, further improving the excavation efficiency.

[0052] In some embodiments, the anchor support includes a drilling process, a grouting process and a rod insertion process, and the time of the drilling process is longer than the time of the grouting process and longer than the time of the rod insertion process.

[0053] like Fig. 9 As shown, for a 6-meter-long anchor rod, the time for the drilling process is, for example, 185s-215s, the time for the grouting process is, for example, 70s-110s, and the time for the rod insertion process is, for example, 62s-93s. The total time can be controlled within 400s; Figure 8 As shown in the figure, for a 9m long anchor, the time of the drilling process is, for example, 348s-372s, the time of the grouting process is, for example, 106s-123s, and the time of the rod insertion process is, for example, 88s-108s, and the total time can be controlled within 590s. According to the test, the time of the drilling process is set to be greater than the time of the grouting process and greater than the time of the rod insertion process. Under the condition of satisfying the support effect, the total time of the anchor support is the shortest and the construction efficiency is the highest.

[0054] In some embodiments, the time of the anchor support is obtained by pre-using the anchor-grouting integrated trolley to perform anchor support multiple times, recording the time of the drilling process, the grouting process and the rod insertion process, and using statistical software to analyze the time optimization of each process.

[0055] SPSS (Statistical Product and Service Solutions) social science statistical software is a series of software products used for statistical analysis, data mining, predictive analysis and decision support tasks. Based on the statistical analysis software SPSS, the construction process time of the anchor drilling and injection trolley under the conditions of 6-meter drilling depth and 9-meter drilling depth was statistically analyzed to identify the key optimization processes and give optimization suggestions for each process time. For example, the coefficient of variation of multiple process times can be calculated. If the coefficient of variation is low, it means that the probability of abnormal values ​​is small, and the average value of each process can be used as the time of each process.

[0056] In some embodiments, the performing bolt support comprises:

[0057] S204 , anchoring first anchor rods 3 and second anchor rods 4 alternately and at intervals along the vault cross section of the first space 1 , wherein the length of the first anchor rods 3 is greater than that of the second anchor rods 4 .

[0058] The length of the first anchor rod 3 is, for example, 9 m, and the length of the second anchor rod 4 is, for example, 6 m. Figure 4 As shown, by alternately anchoring the first anchor rod 3 and the second anchor rod 4, the structural stability of the arch is improved and the stress concentration is reduced.

[0059] In some embodiments, the performing bolt support comprises:

[0060] S205 , monitoring the deformation displacement of multiple regions of the dome of the first space 1 in real time.

[0061] S206. Perform anchor support on the area where the deformation displacement is greater than the first preset displacement within a preset time.

[0062] The deformation displacement can be monitored by anchor stress gauges, four-point multi-point displacement gauges, prestressed anchor dynamometers, anchor cable stress gauges, etc. The preset time is, for example, 30 days, and the first preset displacement is, for example, 1 mm. If the deformation displacement is greater than the first preset displacement within the preset time, it means that the stability of the area is poor and anchor support is required.

[0063] In some embodiments, the bolt support further comprises:

[0064] S207: Predict the deformation displacement according to the deformation displacement to obtain the predicted displacement of the area after a predetermined period.

[0065] S208. Anchor support is performed on the area where the predicted displacement is greater than the second preset displacement.

[0066] Prediction algorithms can also be used to predict future deformation displacements. The predetermined period is, for example, 30 days, and the second preset displacement is, for example, 1.5 mm. When the predicted displacement is greater than the second preset displacement, it means that the stability of the area in the later stage of construction is poor, and anchor support is required to further improve safety.

[0067] In some embodiments, step S207 includes:

[0068] S2071. Input the deformation displacement into a pre-trained prediction model to obtain a displacement simulation curve.

[0069] S2072. Determine the predicted displacement of the area after a predetermined period according to the displacement simulation curve.

[0070] The prediction model is a back propagation neural network model improved by the sparrow search algorithm, namely the SSA-BP model, wherein the number of input nodes of the neural network model is 6, the number of output nodes is 1, and the number of nodes in the hidden layer is 4; the initial population size of the sparrow search algorithm is 20, the maximum number of iterations is 50, the explorer ratio is 0.2, the scout ratio is 0.2, and the warning value is 0.8. Fig.12 As shown in the figure, the obtained deformation displacement and SSA-BP model can be used to obtain a simulation curve. After testing, the simulation curve is closer to the actual value of actual monitoring and has good prediction accuracy.

[0071] The underground powerhouse of a pumped storage power station in Qinhuangdao was excavated and supported. The cavern is buried at a depth of 215m-540m, and the lithology is Yanshanian potassium feldspar granite. The surrounding rock of the underground powerhouse is mainly Class III, and the faults and moderately-severely altered rock masses are developed in Class IV-V. The axis direction of the underground powerhouse is NE45°, with a burial depth of 196m-323m. Its layout avoids the influence of major structures such as the dense joint zones J1, J2, and fault fp18. The lithology is fresh potassium feldspar granite, medium-grained structure, and blocky structure. The surrounding rock is mainly Class III, and the faults and altered rock masses are exposed in Class IV-V.

[0072] The construction is carried out in the order of first drilling through the middle guide tunnel and then excavating the two sides at staggered intervals. The middle guide tunnel is excavated first from the ventilation and safety tunnel. After the excavation of the middle guide tunnel is completed, the downstream area excavation construction is given priority. After the excavation forms a working surface, the top arch support of the downstream area is carried out in time. The excavation of the upstream area can only be carried out after the downstream area has been excavated and supported for more than 30m, and the excavation working surface of the upstream area lags behind that of the downstream area by more than 30m.

[0073] During the excavation of the middle guide tunnel, monitoring equipment was arranged at different depths in multiple locations of the middle guide tunnel to monitor deformation and displacement. The monitoring results are shown in Table 1. After testing, the maximum displacement was 0.42 mm, and the displacement of each measuring point was very small, all less than 1 mm, which was in a relatively stable state. There was no need to anchor the top of the middle guide tunnel.

[0074] Table 1 Deformation displacement monitoring table

[0075]

[0076] After the excavation of the middle guide tunnel is completed, anchor support is carried out in the downstream area and the upstream area respectively, including a 9-meter-long first anchor and a 6-meter-long second anchor, which are arranged alternately with a spacing of 1.5m between adjacent anchors. The time for each process of anchor support can be obtained as follows.

[0077] A total of 25 rounds of time statistics were conducted in advance for the three processes of drilling, grouting, and rod insertion in the anchor-injection integrated trolley cycle at a drilling depth of 6 meters. Among them, the first 8 rounds were in the performance improvement stage, and the total cycle time was not fixed. The number of cycles that can be used for the key process analysis in subsequent chapters is 17 rounds. The time of each process is shown in Figures 2 and Fig. 9 shown.

[0078] Table 2 Second bolt support schedule

[0079] Serial number Drilling time Grouting time Insertion time Total time 1 480 481 180 865 2 365 200 165 730 3 306 203 160 669 4 270 198 145 613 5 245 185 150 540 6 195 170 90 405 7 210 150 80 440 8 200 155 100 455 9 205 110 62 377 10 214 100 65 379 11 211 95 84 390 12 205 110 62 377 13 194 86 75 355 14 185 90 85 360 15 195 85 88 368 16 212 80 93 385 17 208 81 85 374 18 205 75 76 356 19 215 70 81 366 20 205 78 88 371 21 214 80 72 366 22 199 82 86 367 23 210 78 91 379 24 199 82 88 369 25 205 70 84 369

[0080] The cycle time can be divided into three stages: Stage 1: Cycle 1 to Cycle 5. Since the anchor-grouting trolley is a new type of equipment introduced, there are many uncertainties. As the cycle progresses, problems are gradually exposed and solved, which greatly shortens the cycle time; Stage 2: Cycle 6 to Cycle 8. After the optimization of the first stage, the total cycle time tends to be stable, not higher than 480 seconds, but there are still some technical problems to be solved, especially in the grouting process; Stage 3: Cycle 9 to Cycle 25. After further optimization, the total cycle time is stable, not higher than 400 seconds.

[0081] The 17 rounds of time statistics from cycle 9 to cycle 25 were used as samples, and descriptive statistics were performed using SPSS software, including sample size, maximum value, minimum value and other statistics, to study the overall situation of quantitative data. The overall descriptive results are shown in Table 3. The coefficients of variation (CV) of the three variables of drilling, grouting and rod insertion were calculated to be 0.04, 0.141 and 0.124, respectively, all less than 0.15, indicating that the probability of abnormal values ​​in the data is small and the analysis is effective.

[0082] Table 3 Overall description results

[0083] Variable Name Maximum Minimum average value Standard Deviation median variance Kurtosis Skewness Drilling time 215 185 204.77 8.189 205 67.077 0.554 -0.882 Grouting time 110 70 85.41 12.068 82 145.63 0.286 0.97 Insertion time 93 62 80.29 9.93 84 98.00 -0.502 -0.83

[0084] In addition, it can be seen from Table 3 that the variance of the grouting process is greater than that of the other two processes, and the time stability is worse; at the same time, the average values ​​of the grouting process and the rod insertion process are close, but the difference between the maximum and minimum values ​​of the grouting process is more obvious, indicating that there may still be a certain space for optimization, and the time of the grouting and rod insertion processes gradually approaches the average value with the increase of the number of cycles, and the optimization possibility is small; only the grouting process has a time anomaly, indicating that a sub-process during the grouting process construction has greater uncertainty, which needs to be paid attention to in the anchor-grouting integrated construction.

[0085] In summary, for the anchor drilling and grouting trolley process at a drilling depth of 6 meters, the grouting process is the key optimization direction, which may be related to various factors such as slurry properties and grouting pressure in the grouting process, resulting in relatively poor time stability.

[0086] The time statistics of the three processes of drilling, grouting and rod insertion in the cycle of the anchor-injection integrated trolley at a drilling depth of 9 meters were conducted for a total of 25 rounds. Among them, the first 10 rounds were in the performance improvement stage, and the total cycle time was not fixed. The number of cycles that can be used for the key process analysis in subsequent chapters is 15 rounds. The time of each process is shown in Figure 4 and Figure 8 shown.

[0087] Table 4 First bolt support schedule

[0088]

[0089]

[0090] The cycle time can be divided into three stages: Stage 1: Cycle 1 to Cycle 7. The 9m drilling depth has higher requirements on the trolley performance, and the cycle time is unstable, but it tends to be shortened overall. Stage 2: Cycle 8 to Cycle 10. After the optimization of the first stage, the total cycle time tends to be stable, not higher than 620 seconds, but there is still a certain possibility of optimization, especially for the grouting process. Stage 3: Cycle 11 to Cycle 25. After further optimization, the total cycle time is stable, not higher than 590 seconds.

[0091] The 15 rounds of time statistics from cycle 11 to cycle 25 were used as samples, and descriptive statistics were performed using SPSS software, including sample size, maximum value, minimum value and other statistics, to study the overall situation of quantitative data. The overall descriptive results are shown in Table 5. The coefficients of variation (CV) of the three variables of drilling, grouting and rod insertion were 0.019, 0.037 and 0.059, respectively, all less than 0.15, indicating that the probability of abnormal values ​​in the data is small and the analysis is effective.

[0092] Table 5 Overall description results

[0093] Variable Name Maximum Minimum average value Standard Deviation median variance Kurtosis Skewness Drilling time 372 348 363.07 6.984 365 48.78 -0.067 -0.702 Grouting time 123 106 111.67 4.082 111 16.67 3.512 1.549 Insertion time 108 88 99 5.831 100 34 -0.512 -0.294

[0094] In addition, it can be seen from Table 5 that the variance of the drilling process is greater than that of the other two processes, and the absolute value of the variance is small, indicating that the stability of the three processes is relatively strong; at the same time, due to the pilot test under the condition of 6-meter drilling depth, certain optimization experience has been accumulated, and the time of the three processes gradually approaches the average value with the increase of the number of cycles, indicating that the three processes have become stable; only the grouting process has a time anomaly, indicating that compared with other processes, the uncertainty during grouting construction is greater and should be taken seriously in actual construction; at the same time, the difference between the upper and lower limits of the time distribution of the grouting process is significantly smaller than that of the other two processes, further indicating that the overall construction difficulty of the grouting process is not high, but a sub-process in the grouting is easily affected by external interference, which makes the grouting time have both abnormality and small range characteristics.

[0095] In summary, the anchor drilling and grouting trolley process at a drilling depth of 9 meters is similar to the working condition at a drilling depth of 6 meters. In order to ensure the stability of the total construction time of the anchoring and grouting, the grouting process should be optimized as the key direction, and the abnormality of the grouting process itself needs to be taken seriously.

[0096] During the excavation of the upstream and downstream areas, if the geological conditions are poor and there may be local collapse sections, or if there is inverted rock mass due to the intersecting cutting of faults, the SSA-BP neural network and numerical simulation can be combined to achieve advance prediction of excavation deformation under adverse geological conditions, and to carry out anchor support in advance to ensure structural stability.

[0097] Based on the SSA-BP neural network, the surrounding rock mechanical parameters were inverted and the deformation time-varying curve was obtained, which provided a reference for subsequent deformation prediction and excavation support organization strategy.

[0098] The core problem of the inversion of surrounding rock mechanical parameters is to find a reasonable combination of rock mechanical parameters within a reasonable range of values, so that the absolute value of the difference between the numerical simulation calculation results of the displacement of each measuring point and the field monitoring results is minimized. It can be considered that the parameters are consistent with the field rock parameters, which can be expressed as the following formula:

[0099]

[0100] γ=f(E1,c1,φ1,E2,c2,φ2)

[0101] Where: m is the number of monitoring points, is the calculated deformation displacement value of surrounding rock; is the deformation displacement value of the surrounding rock monitored on site. E1 and E2 are the elastic moduli of Class III and Class IV surrounding rocks respectively; c1 and c2 are the cohesion of the corresponding surrounding rocks; φ1 and φ2 are the friction angles of the corresponding surrounding rocks.

[0102] Taking into account the displacement values ​​monitored on site is a certain value, then the key to the above problem is to establish a mapping f with nonlinear and highly complex characteristics, and solve the surrounding rock parameter group that can make Y reach the minimum value. This is in line with the back-propagation characteristics of the BP neural network and the ability to directly establish a nonlinear mapping model based on input and output. However, due to the complexity of the surrounding rock mechanical characteristics and the nonlinear and multi-extreme characteristics of the algorithm error space, the BP neural network is prone to local optimality and it is difficult to obtain reliable inversion results.

[0103] The Sparrow Search Algorithm (SSA) is an evolutionary algorithm based on population behavior, which is inspired by the foraging and anti-foraging behavior of sparrow populations. The algorithm is based on three different roles in the foraging of sparrow populations: explorers, followers, and scouts. Fig.11 As shown in the figure, SSA can effectively solve the problem that the BP neural network model is prone to fall into the local optimal solution by finding the optimal neural network weights and thresholds.

[0104] In order to realize the inversion process, an orthogonal test scheme with elastic modulus, cohesion and friction angle as variables was designed, as shown in Table 6. The SSA-BP inversion analysis program was written using Matlab software, and the finite element software Abaqus was used for numerical simulation calculation to realize the inversion study of the mechanical parameters of the surrounding rock of the underground powerhouse excavation based on the SSA-BP neural network.

[0105] Table 6 Orthogonal test design of surrounding rock elastic-plastic mechanics inversion parameters

[0106]

[0107]

[0108] Considering that the values ​​of the parameters to be inverted are within a certain range and there are many possible combinations, in order to ensure generality and eliminate the influence of random errors as much as possible, the inversion results of the SSA-BP neural network were screened, and a group of more reasonable parameter combinations were selected as shown in Table 7. After numerical simulation calculations, it was found that the deformation calculation results under this group of parameter combinations can correctly reflect the deformation characteristics of surrounding rock excavation, and subsequent excavation deformation prediction analysis can be carried out.

[0109] Table 7 Comparison of surrounding rock inversion parameter schemes and monitoring values

[0110]

[0111] The excavation of the first space of the underground powerhouse is a typical arch excavation, and the surrounding rock deformation monitoring time-history curve mainly shows the characteristics of increasing deformation. The second space belongs to the side wall excavation, and the significant feature of the surrounding rock deformation monitoring time-history curve is the slow convergence speed, showing obvious time-effect characteristics, which is manifested as after the side wall layer is excavated, the time-history curve needs a long time to gradually converge and stabilize.

[0112] Since the multi-point displacement meter was arranged later than the underground powerhouse excavation, the monitoring data of some underground powerhouse excavation deformation was missing, and the amount of monitoring data was small, which was not enough to build a reliable neural network prediction model. The displacement calculation value of the above inversion parameter scheme can be used to supplement it. This further verifies the correctness of the surrounding rock inversion parameter selection in the previous article, and also provides reliable sample data for the subsequent surrounding rock deformation excavation prediction.

[0113] Since excavation deformation prediction belongs to the problem of time series prediction, the setting of neural network parameters will greatly affect the performance of the model. Combined with the above characteristics of the excavation deformation time history curve, the specific parameters of the SSA-BP neural network are set as follows: construct a BP neural network with 6 input nodes, 1 output node and 4 nodes in the hidden layer, that is, the topological structure of the BP neural network is 6-4-1; set the BP network training parameters, the number of training times of the model is set to 1000 times, the training target value is 10-6, and the learning rate is set to 0.001; initialize the SSA algorithm parameters, the initial sparrow population size is 20, the maximum number of iterations is 50, the explorer proportion PD is 0.2, the scout proportion SD is 0.2, and the warning value ST is set to 0.8.

[0114] The monitoring data were divided into training set and test set in a ratio of 8:2, and the BP neural network and SSA-BP neural network were trained respectively using the data of every 7 days to establish the nonlinear mapping relationship between the deformation value of the first 6 days and the deformation value of the 7th day. Fig.12 As shown in the test set results, the SSA-BP neural network is more accurate in judging the upward trend of the data, and the prediction results are closer to the true value, and the effect is better than the BP neural network.

[0115] In order to better demonstrate the superiority of the SSA-BP neural network model, the error judgment indicators MAE, MBE, and RMSE of the BP neural network and the SSA-BP neural network are compared using the test set results as an example. As shown in Table 8, the SSA-BP neural network is superior to the BP neural network in all error indicators, which proves that the SSA-BP neural network has better accuracy and performance than the BP neural network in the prediction of underground powerhouse excavation. The SSA-BP prediction model is used to predict the deformation of underground powerhouse excavation and guide the construction. Anchor support can be set for areas with large deformation.

[0116] Table 8 Comparison of evaluation indicators of different neural network methods

[0117] Neural Network Methods MAE / % MBE / % RMSE / % BP 1.41e-05 -1.4411e-05 2.926e-05 SSA-BP 4.8105e-06 -1.5798e-06 5.8706e-06

[0118] It is understandable that before using the technical solutions of each embodiment of the present disclosure, the type, scope of use, usage scenarios, etc. of the personal information involved will be informed to the user in an appropriate manner, and the user's authorization will be obtained.

[0119] For example, in response to receiving an active request from a user, a prompt message is sent to the user to clearly remind the user that the operation requested to be performed will require obtaining and using the user's personal information. Thus, the user can independently choose whether to provide personal information to software or hardware such as an electronic device, application, server, or storage medium that performs the operation of the technical solution of the present disclosure according to the prompt message.

[0120] As an optional but non-limiting implementation, in response to receiving the user's active request, the prompt information may be sent to the user in the form of a pop-up window, in which the prompt information may be presented in text form. In addition, the pop-up window may also carry a selection control for the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0121] It is understandable that the above notification and the process of obtaining user authorization are merely illustrative and do not constitute a limitation on the implementation of the present disclosure. Other methods that meet relevant laws and regulations may also be applied to the implementation of the present disclosure.

[0122] Based on the same inventive concept, corresponding to any of the above-mentioned embodiments and methods, the present application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the prediction model described in any of the above embodiments when executing the program.

[0123] The device may include: a processor, a memory, an input / output interface, a communication interface and a bus, wherein the processor, the memory, the input / output interface and the communication interface are connected to each other in communication within the device through the bus.

[0124] The processor can be implemented as a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this specification.

[0125] The memory can be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage device, dynamic storage device, etc. The memory can store operating systems and other application programs. When the technical solutions provided in the embodiments of this specification are implemented by software or firmware, the relevant program codes are stored in the memory and called and executed by the processor.

[0126] The input / output interface is used to connect the input / output module to realize information input and output. The input / output module can be configured as a component in the device (not shown in the figure), or it can be externally connected to the device to provide corresponding functions. It is characterized in that the input device can include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output device can include a display, a speaker, a vibrator, an indicator light, etc.

[0127] The communication interface is used to connect the communication module (not shown in the figure) to realize the communication interaction between the device and other devices. It is characterized in that the communication module can realize communication through wired means (such as USB, network cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.).

[0128] The bus comprises a pathway that transmits information between the various components of a device (eg, processor, memory, input / output interface, and communication interface).

[0129] It should be noted that, although the above device only shows a processor, a memory, an input / output interface, a communication interface, and a bus, in a specific implementation process, the device may also include other components necessary for normal operation. In addition, it can be understood by those skilled in the art that the above device may also only include components necessary for implementing the embodiments of the present specification, and does not necessarily include all the components shown in the figure.

[0130] The electronic device of the above embodiment is used to implement the corresponding prediction model in any of the above embodiments, and has the beneficial effects of the corresponding method embodiment, which will not be repeated here.

[0131] Those skilled in the art should understand that the discussion of any of the above embodiments is merely illustrative and is not intended to imply that the scope of the present application (including the claims) is limited to these examples. In line with the concept of the present application, the technical features in the above embodiments or different embodiments may be combined, the steps may be implemented in any order, and there are many other variations of the different aspects of the embodiments of the present application as described above, which are not provided in detail for the sake of simplicity.

[0132] In addition, to simplify the description and discussion, and in order not to make the embodiments of the present application difficult to understand, the device can be shown in the form of a block diagram, so as to avoid making the embodiments of the present application difficult to understand, and this also takes into account the following fact, that is, the details of the implementation method of these block diagram devices are highly dependent on the platform to be implemented in the embodiments of the present application (that is, these details should be fully within the scope of understanding of those skilled in the art). In the case of elaborating specific details to describe the exemplary embodiments of the present application, it is obvious to those skilled in the art that the embodiments of the present application can be implemented without these specific details or when these specific details are changed. Therefore, these descriptions should be considered to be illustrative rather than restrictive.

[0133] Although the present application has been described in conjunction with specific embodiments thereof, many alternatives, modifications and variations of these embodiments will be apparent to those skilled in the art in light of the foregoing description.

[0134] The embodiments of the present application are intended to cover all such substitutions, modifications and variations that fall within the broad scope of the appended claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the embodiments of the present application should be included in the scope of protection of the present application.

Claims

1. A method for excavating and supporting an underground powerhouse of a pumped storage power station, characterized in that: The underground plant includes a first space with an arched cross-section at the top and a second space with a rectangular cross-section at the bottom, and the method includes: Using a tunnel boring machine to dig the middle area of ​​the cross section of the first space to form a middle guide tunnel that penetrates the underground factory building, wherein the middle guide tunnel has a circular cross section and is tangent to the vault of the first space; The blasting method is used to respectively excavate the areas on both sides of the cross section of the first space, the areas on both sides of the cross section are connected to the middle guide tunnel, including the upstream area and the downstream area; as the excavation proceeds, the anchor-grouting integrated trolley is used to respectively anchor the vaults of the upstream area and the downstream area, so that the entire vault is anchored; The second space is further excavated by blasting to complete the excavation of the underground factory building.

2. The method for excavating and supporting underground powerhouses of a pumped storage power station according to claim 1, characterized in that: The step of using the blasting method to respectively excavate the areas on both sides of the cross section of the first space comprises: Excavating the downstream area laterally from the middle guide tunnel toward the edge of the underground powerhouse, and then excavating the downstream area along the axial direction of the middle guide tunnel; After the excavation of the downstream area reaches a preset length, the upstream area is excavated horizontally from the middle guide tunnel to the edge of the underground powerhouse, and the upstream area is excavated along the axial direction of the middle guide tunnel.

3. The method for excavating and supporting underground powerhouses of a pumped storage power station according to claim 2, characterized in that: The step of using blasting to respectively excavate the areas on both sides of the cross section of the first space further includes: The areas on both sides of the cross section are excavated synchronously from both ends of the middle guide hole along the axial direction toward the middle.

4. The method for excavating and supporting underground powerhouses of a pumped storage power station according to claim 1, characterized in that: The anchor support includes a drilling process, a grouting process and a rod inserting process, and the time of the drilling process is longer than the time of the grouting process and longer than the time of the rod inserting process.

5. The method for excavating and supporting underground powerhouses of a pumped storage power station according to claim 4, characterized in that: The time of the anchor support is obtained by using the anchor-grouting integrated trolley to perform anchor support multiple times in advance, recording the time of the drilling process, the grouting process and the rod insertion process, and optimizing the time of each process by using statistical software.

6. The method for excavating and supporting underground powerhouses of a pumped storage power station according to claim 1, characterized in that: The anchor support comprises: A first anchor rod and a second anchor rod are anchored alternately at intervals along a vault cross section of the first space, wherein the length of the first anchor rod is greater than that of the second anchor rod.

7. The method for excavating and supporting underground powerhouses of a pumped storage power station according to claim 1, characterized in that: The anchor support comprises: Real-time monitoring of deformation displacement of multiple regions of the vault of the first space; Within a preset time, anchor support is performed on the area where the deformation displacement is greater than the first preset displacement.

8. The method for excavating and supporting underground powerhouses of a pumped storage power station according to claim 7, characterized in that: The anchor support also includes: Predicting the deformation displacement to obtain the predicted displacement of the area after a predetermined period; Anchor support is performed on the area where the predicted displacement is greater than the second preset displacement.

9. The method for excavating and supporting underground powerhouses of a pumped storage power station according to claim 8, characterized in that: The step of predicting the deformation displacement to obtain the predicted displacement of the area after a predetermined period includes: Inputting the deformation displacement into a pre-trained prediction model to obtain a displacement simulation curve; The predicted displacement of the area after a predetermined period is determined according to the displacement simulation curve.

10. The method for excavating and supporting underground powerhouses of a pumped storage power station according to claim 9, characterized in that: The prediction model is a back propagation neural network model improved by the sparrow search algorithm, wherein the number of input nodes of the neural network model is 6, the number of output nodes is 1, and the number of nodes in the hidden layer is 4; the initial population size of the sparrow search algorithm is 20, the maximum number of iterations is 50, the explorer ratio is 0.2, the scout ratio is 0.2, and the warning value is 0.8.

Images