Automatic identification method for excavation footage of long-distance tunnel construction

Abstract

The invention relates to an automatic identification method for excavation footage of long-distance tunnel construction. The method comprises the following steps: S1, determining charge blasting personnel and tunnel entering and leaving time; s2, position track points of all charge blasting personnel in the hole are obtained; s3, a charging operation position point set is determined; s4, carrying out clustering analysis on the charging operation position point set based on a K-means algorithm; and S5, calculating the excavation footage. According to the method, the position of the current excavation tunnel face of the tunnel can be accurately determined by performing clustering analysis on the charging operation positions of the charging blasting personnel, so that the accuracy of excavation footage identification is ensured; automatic identification of the excavation footage can be realized, the human input is reduced, and the construction efficiency can be improved.

Description

Technical Field

[0001] The invention belongs to the technical field of tunnel engineering construction, and in particular relates to a method for automatically identifying excavation footage of long-distance tunnel construction. Background Art

[0002] In recent years, as my country's transportation, water conservancy and energy infrastructure has extended to the southwestern mountainous areas, long-distance tunnel construction has become a key area of ​​focus. By the end of 2022, my country had built 1,752 extra-long highway tunnels with a total length of 7,951.1 km[1]; 360 extra-long railway tunnels had been put into operation with a total length of 3,152 km[2]; the largest single-hole length of the completed and under-construction water diversion tunnels in my country exceeded 85 km. According to the Outline of the 2035 Vision Goals, my country will also build a large number of long-distance tunnels.

[0003] Long-distance tunnel construction has the characteristics of complex geological conditions, high construction intensity, multiple construction processes, complex construction organization, limited working space and long construction period. In such a complex and changeable environment, effective control of excavation footage is particularly important. Timely and accurate identification of excavation footage not only helps to discover and solve problems in construction and ensure construction safety and quality, but also can predict potential risks in advance, adjust construction plans, and ensure that long-distance tunnel projects can be completed on time and with quality.

[0004] In the traditional tunnel construction process, in order to strictly control the excavation progress, it is necessary to manually collect the current excavation progress every day. However, the manual collection of excavation progress information relies on manual measurement, has poor real-time performance, and is affected by human factors. It often cannot truly and accurately reflect the excavation progress information, but instead brings burdens to construction personnel and cannot effectively manage the construction progress.

[0005] References

[0006] Ministry of Transport. Statistical Communiqué on the Development of the Transportation Industry in 2022[R]. Beijing: Ministry of Transport of the People's Republic of China, 2023.

[0007] Editorial Department of China Journal of Highway and Transport. Review of Academic Research on China's Traffic Tunnel Engineering 2022[J]. China Journal of Highway and Transport, 2022, 35(4): 1-40. Summary of the invention

[0008] The purpose of the present invention is to overcome the shortcomings of the prior art and provide a method for automatically identifying the excavation footage of long-distance tunnel construction. On the basis of using ultrawideband (UWB) technology to locate construction workers in the tunnel in real time, cluster analysis is performed on the charging operation positions of charging blasting workers to achieve automatic identification of the current face position, and then accurately calculate the excavation footage, providing a new and effective means for long-distance tunnel construction progress control.

[0009] The present invention solves the technical problem by the following technical solutions:

[0010] An automatic identification method for excavation footage of long-distance tunnel construction. During the charging process, the blasting personnel charge close to the tunnel face. The front position of all blasting personnel in the tunnel excavation direction can be considered as the position of the tunnel face. The trajectory of the blasting personnel is located by UWB. The identity of the blasting personnel is determined by the ID number of the positioning tag, and the front position can be determined by clustering analysis of trajectory points within a certain period of time.

[0011] The steps of the method are:

[0012] S1. Determine the personnel for blasting and the time of entering and leaving the cave;

[0013] S2, obtaining the position trajectory points of all personnel who are charging and blasting in the cave;

[0014] S3, determining a charging operation position point set;

[0015] S4. Perform cluster analysis on the charging operation location point set based on K-means algorithm;

[0016] S5. Calculation of excavation depth.

[0017] Moreover, the S1 is specifically:

[0018] The ID number of the UWB positioning tag is matched with the corresponding input process team and name identity information, and the position number x of operator j in process i at time t is obtained through UWB positioning technology. i,j (t), that is, x i,j (t) = x ID (t), where i = 1, 2, 3, 4, 5, respectively representing the five main processes of drilling, charging and blasting, slag removal, erection of frames, and concrete spraying; j = 1, 2, ..., p i , p i is the number of operators in process i;

[0019] According to the ID number of the positioning tag, all the charging and blasting personnel are determined, and the real-time position x of charging and blasting personnel j, j = 1, 2, ..., p2 at time t is compared respectively.2,j (t) is relative to the starting pile number x0 of the tunnel entrance, which can determine the entry time ET of the blasting personnel. 2,j , time to leave the cave LT 2,j , the specific calculation is as follows:

[0020]

[0021] Moreover, the S2 is specifically:

[0022] Get the charging and blasting personnel j in ET respectively 2,j To LT 2,j The position trajectory point X within the time range, i.e. in the hole 2,j :

[0023] X 2,j ={x 2,j (ET 2,j ),x 2,j (ET 2,j +1),…,x 2,j (LT 2,j )}.

[0024] Moreover, the S3 is specifically:

[0025] Sort the position stake numbers of each charging and blasting personnel in the cave from large to small, and select the first n position stake numbers of each charging and blasting personnel as their position during charging operation at the tunnel face. Then the position point set of charging and blasting personnel j during charging operation at the tunnel face is in is the first n position stake numbers in the position trajectory of the charging and blasting personnel in the j-hole; where t ch is the charging operation time of the blasting personnel used for positioning, and Δt is the positioning time interval;

[0026] Thus, the position points of all p2 charging blasting personnel during the charging operation on the face together constitute the charging operation position point set j=1,2,…,p2.

[0027] Moreover, the S4 is specifically:

[0028] Will The position points in the figure are divided into two categories: position points close to the tunnel face and position points far from the tunnel face, that is, the number of categories is 2;

[0029] from Randomly select 2 points as the initial cluster centers, and the initial cluster center set is recorded as

[0030] right Any point in (j=1,2,…,p2;b=1,2,…,n), and are assigned to the corresponding classes according to the following classification principle.

[0031]

[0032] Recalculate new cluster centers:

[0033]

[0034] Among them, n k Is a class The number of location points in the cluster is used to obtain a new set of cluster centers.

[0035] Repeat the above steps δ times with the new cluster center set until the cluster center set no longer changes, then return to the cluster center set and stop calculating;

[0036] Pick The larger cluster center is the location stake number of the tunnel face. The drilling process starts and the concrete spraying process ends as a construction cycle. The tunnel face location stake number identified in the cth construction cycle is recorded as x face,c .

[0037] Moreover, S5 is specifically: the full section method is often used in the long-distance tunnel drilling and blasting construction, and is calculated as follows:

[0038] K c =x face,c+1 -x face,c

[0039] Where: K c This is the excavation progress of the cth construction cycle.

[0040] The positive effects that the present invention can produce are:

[0041] 1. The present invention can accurately determine the position of the current tunnel excavation face by clustering analysis of the charging operation positions of the charging blasting personnel, thereby ensuring the accuracy of the excavation footage identification.

[0042] 2. Compared with traditional manual measurement and collection methods, the present invention can realize automatic identification of excavation progress, reduce manpower input, and help improve construction efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 This is a diagram of the charging process of the blasting personnel of the present invention;

[0044] Figure 2 It is a specific implementation step diagram of the present invention;

[0045] Figure 3 It is a sample set diagram of pile numbers of working positions of personnel performing blasting in the present invention;

[0046] Figure 4 This is a cluster analysis result diagram of the charging operation position of the charging blasting personnel of the present invention;

[0047] Figure 5 This is a tunnel face identification error diagram of the present invention;

[0048] Figure 6 This is an analysis diagram of excavation footage for each construction cycle of the present invention. DETAILED DESCRIPTION

[0049] The present invention is further described in detail below through specific examples. The following examples are only illustrative and not restrictive, and the protection scope of the present invention cannot be limited thereto.

[0050] In the charging process of the present invention, the charging and blasting personnel charge close to the tunnel face. The front position of all charging and blasting personnel in the tunnel excavation direction can be regarded as the position of the tunnel face. Figure 1 As shown in the figure, UWB positioning technology is used to identify the tunnel excavation progress based on the real-time positioning of construction workers in the tunnel. The system arranges UWB positioning base stations at certain intervals in the tunnel, and places UWB positioning tags on the safety helmets worn by the workers. The tags have the identity information of the bound personnel, so as to realize the real-time positioning and tracking of the workers entering the tunnel.

[0051] like Figure 2 As shown, a method for automatically identifying the excavation footage of a long-distance tunnel construction is innovative in that the steps of the method are:

[0052] Step 1: Determine the personnel for blasting and the time of entering and leaving the cave

[0053] The ID number of the UWB positioning tag is matched with the corresponding input process team, name and other identity information, and the position number x of operator j in process i at time t is obtained through UWB positioning technology. i,j (t), that is, x i,j (t) = x ID (t), where i = 1, 2, 3, 4, 5, respectively representing the five main processes of drilling, charging and blasting, slag removal, erection of frames, and concrete spraying; j = 1, 2, ..., p i , p i is the number of operators in process i.

[0054] According to the ID number of the positioning tag, it is determined that there are 8 charging and blasting personnel loading the explosives, and the real-time position x of charging and blasting personnel j (j = 1, 2, ..., 8) at time t is compared respectively. 2,j (t) is relative to the starting pile number x0 of the tunnel entrance, which can determine the entry time ET of the blasting personnel. 2,j , time to leave the cave LT 2,j , the specific calculation is as follows:

[0055]

[0056] Step 2: Obtain the location trajectory points of all blasting personnel in the cave

[0057] Get the charging and blasting personnel j in ET respectively 2,j To LT 2,j Position trajectory point X within the time range (i.e. inside the cave) 2,j :

[0058] X 2,j ={x 2,j (ET 2,j ),x 2,j (ET 2,j +1),…,x 2,j (LT 2,j )}.

[0059] Step 3: Determine the charging operation location point set

[0060] Sort the position stake numbers of each charging and blasting personnel in the cave from large to small, and select the first n position stake numbers of each charging and blasting personnel as their position during charging operation at the tunnel face. Then the position point set of charging and blasting personnel j during charging operation at the tunnel face is in is the first n position stake numbers in the position trajectory of the charging and blasting personnel in the j-hole; where t ch is the charging operation time of the blasting personnel used for positioning, and Δt is the positioning time interval.

[0061] The duration of the blasting operation by the blasting personnel t ch The value is 30min. According to the positioning once every 1s, the first 1800 positioning positions with the largest pile number of each charging and blasting personnel are selected. Thus, the position points of 8 charging and blasting personnel during the charging operation on the face together constitute the charging operation position point set. j=1,2,…,8, the charging operation position point set is Figure 3 .

[0062] Step 4: Cluster analysis of charging operation location points based on K-means algorithm

[0063] Based on K-means algorithm, the charging operation location point set To perform cluster analysis, the specific steps are as follows:

[0064] Will The position points in the figure are divided into two categories: position points close to the tunnel face and position points far from the tunnel face, that is, the number of categories is 2.

[0065] from Randomly select 2 points as the initial cluster centers, and the initial cluster center set is recorded as

[0066] right Any point in (j=1,2,…,p2;b=1,2,…,n), and are assigned to the corresponding classes according to the following classification principle.

[0067]

[0068] Recalculate new cluster centers:

[0069]

[0070] Among them, n k Is a class The number of location points in the cluster is used to obtain a new set of cluster centers.

[0071] Repeat the above steps δ times with the new cluster center set until the cluster center set no longer changes, then return to the cluster center set and stop the calculation.

[0072] Pick The larger cluster center is the location stake number of the tunnel face. The drilling process starts and the concrete spraying process ends as a construction cycle. The tunnel face location stake number identified in the cth construction cycle is recorded as x face,c .

[0073] The cluster analysis results are shown in Figure 4 In this cycle, the actual face position is ZK305+146.09, the identified face position is ZK305+145.80, and the absolute error is 0.29m. The error of the identified face position in all operation cycles is shown in Figure 5 The average error is 0.20m, the maximum value is 0.42m, and the minimum value is 0.05m. The accuracy of face position recognition is relatively high.

[0074] Step 5: Excavation Length Calculation

[0075] In order to meet the needs of large-scale mechanical construction such as three-arm rock drilling trolleys and arch anchor installation trolleys, the full-section method is often used in the long-distance tunnel drilling and blasting construction. The calculation is as follows:

[0076] K c =x face,c+1 -x face,c

[0077] Where: K c This is the excavation progress of the cth construction cycle.

[0078] The calculation results of excavation footage are shown in Figure 6 The average absolute error of excavation footage detection was 0.25m, and the maximum absolute error was 0.51m. The total excavation footage of 19 operation cycles was 62.25m (the actual excavation footage was 62.00m), and the average excavation footage was 3.28m.

[0079] Although the embodiments and drawings of the present invention are disclosed for illustrative purposes, those skilled in the art will appreciate that various substitutions, changes and modifications are possible without departing from the spirit and scope of the present invention and the appended claims. Therefore, the scope of the present invention is not limited to the contents disclosed in the embodiments and drawings.

Claims

1. A method for automatically identifying the excavation footage of a long-distance tunnel construction, characterized in that: During the charging process, the blasting personnel charge close to the tunnel face. The frontier position of all blasting personnel in the tunnel excavation direction can be considered as the position of the tunnel face. The trajectory of the blasting personnel is located by UWB. The identity of the blasting personnel is determined by the ID number of the positioning tag, and the frontier position can be determined by clustering analysis of trajectory points within a certain period of time. The steps of the method are: S1. Determine the personnel for blasting and the time of entering and leaving the cave; S2, obtaining the position trajectory points of all personnel who are charging and blasting in the cave; S3, determining a charging operation position point set; S4. Perform cluster analysis on the charging operation location point set based on K-means algorithm; S5. Calculation of excavation depth.

2. The method for automatically identifying the excavation footage of a long-distance tunnel construction according to claim 1 is characterized in that: The S1 is specifically: The ID number of the UWB positioning tag is matched with the corresponding input process team and name identity information, and the position number x of operator j in process i at time t is obtained through UWB positioning technology. i,j (t), that is, x i,j (t) = x ID (t), where i = 1, 2, 3, 4, 5, respectively representing the five main processes of drilling, charging and blasting, slag removal, erection of frames, and concrete spraying; j = 1, 2, ..., p i , p i is the number of operators in process i; According to the ID number of the positioning tag, all the charging and blasting personnel are determined, and the real-time position x of charging and blasting personnel j, j = 1, 2, ..., p2 at time t is compared respectively. 2,j (t) is relative to the starting pile number x0 of the tunnel entrance, which can determine the entry time ET of the blasting personnel. 2,j , time to leave the cave LT 2,j , the specific calculation is as follows:

3. The method for automatically identifying the excavation footage of a long-distance tunnel construction according to claim 1 is characterized in that: The S2 is specifically: Get the charging and blasting personnel j in ET respectively 2,j To LT 2,j The position trajectory point X within the time range, i.e. in the hole 2,j : X 2,j ={x 2,j (AND 2,j ),x 2,j (AND 2,j +1),…,x 2,j (LT 2,j )}.

4. The method for automatically identifying the excavation footage of a long-distance tunnel construction according to claim 1 is characterized in that: The S3 is specifically: Sort the position stake numbers of each charging and blasting personnel in the cave from large to small, and select the first n position stake numbers of each charging and blasting personnel as their position during charging operation at the tunnel face. Then the position point set of charging and blasting personnel j during charging operation at the tunnel face is in is the first n position stake numbers in the position trajectory of the charging and blasting personnel in the j-hole; where t ch is the charging operation time of the blasting personnel used for positioning, and Δt is the positioning time interval; Thus, the position points of all p2 charging blasting personnel during the charging operation on the face together constitute the charging operation position point set 5. The method for automatically identifying the excavation footage of a long-distance tunnel construction according to claim 1 is characterized by: The S4 is specifically: Will The position points in the figure are divided into two categories: position points close to the tunnel face and position points far from the tunnel face, that is, the number of categories is 2; from Randomly select 2 points as the initial cluster centers, and the initial cluster center set is recorded as right Any point in According to the following classification principle, assign to the corresponding class Recalculate new cluster centers: Among them, n k Is a class The number of location points in the cluster is used to obtain a new set of cluster centers. Repeat the above steps δ times with the new cluster center set until the cluster center set no longer changes, then return to the cluster center set and stop calculating; Pick The larger cluster center is the location stake number of the tunnel face. The drilling process starts and the concrete spraying process ends as a construction cycle. The tunnel face location stake number identified in the cth construction cycle is recorded as x face,c .

6. The method for automatically identifying the excavation footage of a long-distance tunnel construction according to claim 1 is characterized by: The S5 is specifically: the full section method is often used in the long-distance tunnel drilling and blasting construction, and is calculated as follows: K c =x face,c+1 -x face,c Where: K c This is the excavation progress of the cth construction cycle.

Images