JP7544633B2 - Construction management method for shield tunneling machine - Google Patents

Description

The present invention relates to a construction management method for a shield tunneling machine, and in particular to a construction management method for a shield tunneling machine that uses the results of machine learning by artificial intelligence to manage the tunneling of the shield tunneling machine.

The shield tunneling method involves excavating the ground with a rotating cutter while pressing down and stabilizing the face at the tip of a known earth pressure or slurry type shield machine using mud soil pressure, muddy water pressure, etc., and forming a tunnel underground from the starting shaft to the arrival shaft while assembling a tunnel lining made of segments ring by ring behind the shield machine. This method is widely adopted for major tunnel construction in urban areas and plains.

Shield tunneling machines, such as earth pressure and slurry types, used in the shield tunneling method are equipped with a rotating cutter that cuts the tunnel face, a bulkhead, a cutter drive device, an earth removal mechanism, etc., at the front of a metal outer shell called a skin plate, and a shield jack and an erector device, etc., at the rear of the skin plate. The erector device is used to assemble the tunnel lining made of segments ring by ring, and while receiving a reaction force from the assembled tunnel lining, the shield jack pushes out the rotating cutter together with the skin plate, thereby excavating the shield tunnel while cutting the tunnel face.

In this type of shield tunneling method, it is necessary to precisely drive the shield machine along the planned excavation line set underground. However, because the work is carried out underground, various factors such as changes in the geological quality of the surrounding ground, changes in environmental conditions, and the characteristics of each shield machine can make it difficult to control the operation so that the machine excavates precisely along the planned excavation line. Generally, horizontal, vertical, and directional deviations from the planned excavation line occur at the tip of the shield machine. In particular, various factors resulting from the characteristics of each shield machine are called the "habits" of the shield machine at each construction site, and are difficult to grasp accurately. Conventionally, the shield machine was controlled by experienced workers using their experience and intuition to control the operation so that the deviation from the planned excavation line would not become too large.

Furthermore, in recent years, the use of large amounts of data and AI based on technological innovations in IoT (Internet of Things) and AI (Artificial Intelligence) is expected to bring about the Fourth Industrial Revolution, and in the field of shield tunneling, for example, a shield tunneling planning support system that utilizes AI has been developed (see, for example, Non-Patent Document 1). In the shield tunneling planning support system of Non-Patent Document 1, a reinforcement learning method is used in which the AI self-learns through trial and error to arrive at an optimal solution, making it possible to derive planned values for the operation of the shield machine according to the linear shape of the shield tunnel and a segment placement plan.

Developing a shield tunneling planning support system using AI / Corporate information / Shimizu Corporation, May 25, 2018, [Retrieved June 10, 2019], Internet (URL: https://www.shimz.co.jp/company/about/news-release/2018/2018005/html)

Patent Publication No. 2021-14727

However, the shield tunneling planning support system in Non-Patent Document 1 merely sets planned values by performing a preliminary simulation of the operation method of the shield machine for the planned alignment and the allocation method of multiple segments of different shapes prior to actually carrying out shield tunneling work at the construction site. Furthermore, the data items (parameters) of the training data for creating a trained model are limited and specific, making it difficult to obtain an accurate prediction model that reflects the "habits" of the shield machine due to various uncertain factors resulting from changes in the geology of the surrounding ground, changes in environmental conditions, or the characteristics of each shield machine at each construction site, and to properly manage the shield machine so that it excavates along the planned extension line set underground.

Meanwhile, shield tunneling methods often use shield tunneling management systems to get a detailed understanding of the tunneling status as the shield machine progresses. Shield tunneling management systems are well-known systems that collect various data, such as survey data from shield tunneling work and measurement data from various sensors installed on the shield machine, and centralize the management of the shield machine. They are able to estimate the condition of the excavated soil in the ground and the load on the shield machine based on the results of changes over time in the measurement data during construction and statistical processing of the data, and by inputting the survey results, they are able to calculate the position of the shield machine and segments and determine the deviation from the tunneling plan extension line.

In addition, in the shield tunnel excavation management system, when excavation is carried out corresponding to each ring of the lining body made of segments that form the shield tunnel, data on numerous parameters (data items) is collected, for example, at time intervals of about 5 seconds, or for each jack stroke of about 10 mm by the shield jack, and stored as a large amount of data. By analyzing this large amount of data using AI, it is thought that it will be possible to appropriately manage the shield tunneling machine so that it excavates along the excavation plan extension line set underground, reflecting the characteristics of the shield tunneling machine that are caused by various uncertain factors such as changes in the geology of the surrounding ground and changes in environmental conditions at each construction site, or changes in the characteristics of each shield tunneling machine.

For this reason, the applicant of the present application has proposed, for example, in Patent Document 1, a construction management method for a shield machine that uses the results of machine learning by artificial intelligence using construction measurement data sent from a shield excavation management system as teacher data to manage the excavation of the shield machine. In the construction management method for a shield machine in Patent Document 1, a learning area is set on the excavation plan extension line of the shield machine at the construction site, and in the set learning area, a learned model is created by machine learning with the construction measurement data when one or more rings on the rear side of the excavation direction are constructed as explanatory variables and the deviation of the tip of the shield machine when a specified ring on the front side of the excavation direction is constructed as the objective variable. In the main excavation area forward of the excavation direction from the learning area, the created learned model is used as a prediction model, and the construction measurement data when one or more rings on the rear side of the excavation direction are constructed is input, and the deviation of the tip of the shield machine when a specified ring on the front side of the excavation direction is output, so that the excavation of the shield machine is managed while predicting the deviation of the tip of the shield machine from the excavation plan extension line.

However, in the shield tunneling machine construction management method of Patent Document 1, in the learning area set on the extension line of the excavation plan and in the actual excavation area, it is possible to create a learned model from construction measurement data at the shield construction site that is sent from the shield tunneling management system and accumulated, which is in a quantity sufficient to create a learned model through machine learning by artificial intelligence, and to manage the excavation of the shield tunneling machine. However, in the initial excavation area, which is the area when the shield tunneling machine departs from the departure shaft, it is not possible to collect a sufficient amount of construction measurement data from the shield construction site to create a learned model through machine learning, making it difficult to manage the excavation of the shield tunneling machine using a learned model created through machine learning by artificial intelligence at the shield construction site.

In response to this, it is conceivable to repurpose and use a trained model created through machine learning using artificial intelligence at another shield construction site different from the one in question to manage the excavation of a shield machine in the initial excavation area of the one shield construction site. However, because the size, specifications, and performance of the shield machines used at the one shield construction site and other shield construction sites are different, for example, a special technology is required to generalize the trained model in order to repurpose and use a trained model created at a different shield construction site.

The present invention aims to provide a construction management method for a shield tunneling machine that enables a trained model created by machine learning using artificial intelligence to be reused and used at other shield construction sites, and that can manage the excavation of the shield tunneling machine using the trained model, particularly in the initial excavation area of the shield construction site.

The present invention is a construction management method for a shield tunneling machine at a shield construction site, using the results of machine learning by artificial intelligence using construction measurement data sent from a shield tunneling management system as teacher data, and managing the excavation of the shield tunneling machine at a shield construction site, wherein, in an initial excavation area of the shield construction site, at a shield construction site other than the shield construction site where the size, specification, and performance of the shield tunneling machine are different, data including predetermined data related to the operation of the shield tunneling machine is used as an explanatory variable, and the deviation of the tip of the shield tunneling machine when constructing a predetermined ring on the front side of the excavation direction is used as an objective variable , and a trained general-purpose model created by machine learning is used as a prediction model for initial excavation, with the predetermined data related to the structure of the shield tunneling machine and the performance of the mechanical equipment being normalized from the construction measurement data that is the explanatory variable, the deviation of the tip of the shield machine when constructing a predetermined ring on the forward side in the excavation direction is output, and the excavation of the shield machine in the initial excavation area is managed while predicting the deviation of the tip of the shield machine; and in a main excavation area further forward in the excavation direction than the initial excavation area at the shield construction site, the construction measurement data when one or more rear rings are constructed, which is created by machine learning in a learning area set rearward in the excavation direction than the main excavation area, is used as an explanatory variable, and a learned model with the deviation of the tip of the shield machine when constructing a predetermined ring on the forward side in the excavation direction as the objective variable is used as a main excavation prediction model, whereby the construction measurement data when one or more rings constructed on the rear side in the excavation direction are input, the deviation of the tip of the shield machine when constructing a predetermined ring on the forward side in the excavation direction is output, and the excavation of the shield machine in the main excavation area is managed while predicting the deviation of the tip of the shield machine from the excavation plan extension line.

And, in the construction management method for a shield tunneling machine of the present invention, it is preferable that the learning area is set in the initial tunneling area.

In addition, in the construction management method for a shield tunneling machine of the present invention, it is preferable that the machine learning is machine learning using a neural network that uses a support vector machine as an algorithm.

Furthermore, in the construction management method for a shield tunneling machine of the present invention, it is preferable that the deviation of the tip of the shield tunneling machine, which is the objective variable, is a horizontal deviation, a vertical deviation, and a directional deviation.

The construction management method for a shield tunneling machine of the present invention makes it possible to reuse a trained model created by machine learning using artificial intelligence at another shield construction site, and to use the trained model to manage the excavation of the shield tunneling machine, particularly in the initial excavation area of that shield construction site.

1 is an explanatory diagram of a system network in which a construction management method for a shield machine according to a preferred embodiment of the present invention is implemented. FIG. 1 is an explanatory diagram of the trained model creation process. FIG. 13 is an explanatory diagram of a ring report. FIG. 1 is an explanatory diagram illustrating a plurality of variables (parameters) that serve as training data for creating a trained model. FIG. 4 is an explanatory diagram of the positional relationship of construction data. FIG. 1 is an explanatory diagram of a process for creating a trained model and a process for creating a model for parameter confirmation.

A construction management method for a shield machine according to a preferred embodiment of the present invention is implemented, for example, by a system network having the configuration shown in FIG. 1. The construction management method for a shield machine according to this embodiment uses, for example, a shield tunneling management system 10 that manages the construction of a shield tunneling machine 20 (see FIG. 2) via a LAN 12, and preferably a cloud server 11 that incorporates a known machine learning tool (software) capable of implementing a neural network with a support vector machine algorithm as AI (artificial intelligence), to create a predictive model with the deviation of the tip of the shield tunneling machine as the objective variable, so that the shield tunneling machine 20 can be appropriately managed so that it excavates along the excavation plan extension line 21 (see FIG. 2) set underground. In addition, the shield tunneling machine construction management method of this embodiment uses a large amount of data related to many parameters stored in the shield tunneling management system 10, and by using AI machine learning, it is possible to appropriately manage the shield tunneling machine 20 so that it excavates along the excavation plan extension line 21 set underground by reflecting changes in the geological condition of the surrounding ground at each construction site, changes in the environmental conditions, or the "habits" of the shield tunneling machine 20, and it is also possible to reuse and use the trained model created by AI machine learning at other shield construction sites, and it is possible to use the trained model to manage the excavation of the shield tunneling machine at that shield construction site, especially in the initial excavation area, which is the area when the shield tunneling machine 20 starts from the starting shaft.

Here, in this embodiment, for example, the product name "Arigataya" (manufactured by Calculation Studio Co., Ltd.) can be preferably used as a known shield excavation management system 10. The cloud server 11 is configured to include, for example, a computer. The computer includes a CPU (Central Processing Unit), a ROM (Read Only Memory), a RAM (Random Access Memory), an I/F (Interface), a HDD (Hard Disk Drive), a storage means, an input means, a display means, an output means, etc. The CPU controls machine learning by AI while using the RAM as a work area according to various programs built into the ROM. In addition, the CPU, by having various computer programs built into the ROM, functions the storage means, input means, display means, output means, etc., and stores large amounts of data sent from the shield excavation management system 10 and analysis results by AI, for example, in a database unit, or displays them as specified information on, for example, a display 14 at the site via a LAN 12 or a personal computer 13 installed at the site, or outputs them from a printer.

The construction management method for a shield tunneling machine of this embodiment is a construction management method for managing the excavation of a shield tunneling machine 20 at a shield construction site by utilizing the results of machine learning by AI using construction measurement data sent from a shield tunneling management system as teacher data, and in the initial excavation area of the shield construction site, at a shield construction site other than the shield construction site where the size, specifications, and performance of the shield tunneling machine are different , data including predetermined data related to the operation of the shield tunneling machine among the construction measurement data (see Figure 2) when constructing one or more rings N-1' to N-5' on the rear side in the excavation direction is used as an explanatory variable, and data including predetermined data related to the operation of the shield tunneling machine ... when constructing predetermined rings N' to N+5' on the front side in the excavation direction is used as an explanatory variable. The deviation of the tip of the shield tunneling machine 20 is used as the objective variable, and certain data related to the structure of the shield tunneling machine 20 and the performance of the mechanical equipment, which are part of the construction measurement data and serve as explanatory variables, are normalized.A trained general-purpose model created by machine learning is used as a prediction model for initial excavation, and data including certain data related to the operation of the shield tunneling machine 20 from the construction measurement data when one or more rings are constructed on the rear side of the excavation direction is input, and the deviation of the tip of the shield tunneling machine 20 when a certain ring on the front side of the excavation direction is constructed is output, and the excavation of the shield tunneling machine in the initial excavation area is managed while predicting the deviation of the tip of the shield tunneling machine 20 from the excavation plan extension line 21.

In addition, in the main excavation area further forward in the excavation direction than the initial excavation area of the shield construction site, the construction measurement data, preferably when constructing one or more rings N-1 to N-5 on the rear side, which was created by machine learning in a learning area set rearward in the excavation direction from the main excavation area, is used as an explanatory variable, and a trained model, preferably with the deviation of the tip of the shield tunneling machine 20 when constructing a predetermined ring N to N+5 on the front side in the excavation direction as the objective variable, is used as a prediction model for the main excavation, and the construction measurement data when constructing one or more rings on the rear side in the excavation direction that have been constructed is input, and the deviation of the tip of the shield tunneling machine 20 when constructing a predetermined ring on the front side in the excavation direction is output, and the excavation of the shield tunneling machine 20 in the main excavation area is managed while predicting the deviation of the tip of the shield tunneling machine 20 from the excavation plan extension line 21.

In addition, in this embodiment, a learning area is preferably set in the initial excavation area.

In this embodiment, the construction measurement data during tunnel excavation, which serves as teacher data and is sent from the shield excavation management system 10 at the shield construction site or another shield construction site, is data relating to a large number of parameters, for example, the approximately 187 items shown in Figure 4, selected preferably by the knowledge of a shield engineer from a large number of data items that can be output as "ring reports" (see Figure 3) by the shield excavation management system 10. These data are collected as a set of data for each ring of the lining that constitutes the shield tunnel, and are sent to the cloud server 11 preferably every 5 seconds and stored in, for example, a memory unit. That is, in the shield tunneling method, the shield tunneling machine 20 excavates the tunnel face with the rotary cutter 20a at the tip of the shield tunneling machine 20 while extending the shield jack 20b for an excavation length corresponding to the length of one ring, and then the excavation work of the shield tunneling machine 20 is temporarily stopped and one ring's worth of tunnel lining is assembled from the segments 20e using the erector device 20d at the rear of the skin plate 20c. Since excavation work is carried out ring by ring, the construction measurement data is preferably processed as a set of data for each ring.

In this embodiment, the selected construction measurement data of preferably 187 data items (parameters) is classified into a total of 44 pieces of excavation data (front body, middle body, rear body, gyrocompass, coordinates, deviation, displacement, etc.) 50A related to grasping the position of the shield tunneling machine 20, a total of 120 pieces of excavation data (shield jack, center bending jack, copy cutter, etc.) 50B related to the directional control of the shield tunneling machine 20, and a total of 23 pieces of excavation data (recording date and time, cutter bit acceleration, tail clearance, etc.) 50C related to soil quality, etc. These classified data items are sent to the cloud server 11 via the shield tunneling management system 10, for example, every 5 seconds, as described above, and are collected as data that changes over time and are stored in, for example, a memory unit. In FIG. 4, the horizontal deviation of the tip, the vertical deviation of the tip, and the azimuth deviation (directional deviation) indicated by "*" are the objective variables.

These construction measurement data are preferably collected with the ring number of the assembly position of the segment 20e as the title. That is, as shown in FIG. 5, depending on the data item, the position where the data is collected, for example, the position of the face at the tip of the shield tunneling machine 20 where the rotary cutter 20a is placed, the position where the backfill material is injected behind the skin plate 20c, and the assembly position of each ring by the segment 20e placed in the expansion and contraction part of the shield jack 20b, are located at a position that is more than the length of one ring away, and data at positions that are more than the length of one ring are also sent to the shield tunneling management system 10 and collected as data during excavation work on the face to ensure the ring width at the assembly position of the ring number, and data during assembly work on the ring at the assembly position of the ring number, with the ring number of the segment assembly position as the title.

Furthermore, in this embodiment, prerequisite data regarding the structure of the shield tunneling machine or the performance of the mechanical equipment is input and registered in advance in the shield tunneling management system 10 or the cloud server 11. Examples of prerequisite data regarding the structure of the shield tunneling machine include the diameter of the cutter face plate, the number and arrangement of shield jacks and bending jacks, etc. These prerequisite data regarding the structure of the shield tunneling machine are not directly input as explanatory variables, but can be combined with construction measurement data during tunnel excavation sent from the shield tunneling management system 10 and normalized by performing feature engineering before being input. Examples of prerequisite data regarding the performance of the mechanical equipment of the shield tunneling machine include the maximum pressure, maximum speed of extension and contraction, and maximum stroke of each shield jack and bending jack. These prerequisite data regarding the performance of the mechanical equipment of the shield tunneling machine are input with the maximum value converted to 1.0, and can be used to normalize and evaluate the construction measurement data during tunnel excavation sent from the shield tunneling management system 10 with values between 0.0 and 1.0.

Furthermore, in this embodiment, the measurement data processed by feature engineering and normalization and input from the construction measurement data during tunnel excavation sent from the shield tunneling management system 10 includes, for example, data related to the operation of the operator, such as data related to the pressure and stroke of the shield jack and the center bending jack, and data related to the cutter rotation. Also, for example, data related to the position and direction of the shield tunneling machine includes data related to the horizontal displacement amount, vertical displacement amount, directional displacement amount, etc. Furthermore, for example, data related to the surrounding environment affecting the shield tunneling machine includes data related to the face water pressure, tail clearance, etc.

In addition, in this embodiment, the construction measurement data during tunnel excavation sent from the shield excavation management system 10 includes data that takes positive and negative values. Examples of such data that takes positive and negative values include data related to the pitching angle and rolling angle of the front body, the pitching angle and rolling angle of the rear body, cutter rotation, cutter torque, etc. For example, in the case of cutter torque, where there is a positive side (right rotation) and a negative side (left rotation), the minimum value after normalization can be -0.5 and the maximum value can be +0.5 (the difference between the minimum and maximum is 1.0). If the maximum value of the cutter torque is 300 kN·m and it rotates right at 150 kN·m, the normalized value can be +0.25.

In this embodiment, at a shield construction site other than the shield construction site, a trained general-purpose model is created using machine learning with AI that can be used as a prediction model for the initial excavation in the initial excavation area, which is the area at the time of departure from the departure shaft at the shield construction site.

That is, at another shield construction site, an initial construction section set on the excavation plan extension line 21 of the shield tunneling machine 20, for example, an extension of 70 rings (1 ring = 1.5 m), is set as the learning area for the first week (for example, 125 m), and as shown in FIG. 2, a trained model is created in which the construction measurement data when constructing preferably five rings N-1' to N-5' on the rear side of the excavation direction is used as explanatory variables, and the deviation (horizontal deviation, vertical deviation, directional deviation) of the tip of the shield tunneling machine 20 when constructing each of six rings N' to N+5' on the front side of the excavation direction is used as the objective variable. Here, the explanatory variables can be data including predetermined data regarding the operation of the shield tunneling machine when constructing five rings N-1' to N-5' on the rear side of the excavation direction, and the predetermined data regarding the structure of the shield tunneling machine and the performance of the mechanical equipment can be normalized. The deviation of the tip of the shield tunneling machine 20, which is the objective variable, can be calculated according to a predetermined formula from data related to predetermined surveying data, such as measurement data from a gyrocompass attached to the shield tunneling machine 20, based on construction measurement data obtained when constructing each of the six rings N' to N+5' on the forward side in the excavation direction, and can preferably be the value of the horizontal deviation, vertical deviation, or directional deviation of the cutter center at the tip of the shield tunneling machine 20 from the planned excavation extension line 21 of the shield tunnel.

In this embodiment, the specified data regarding the operation of the shield tunneling machine can include the jacking pattern selected by the shield jack, the jacking speed of the shield jack, the stroke of the shield jack, the pressure of the shield jack, the selection of the copy cutter, the stroke of the copy cutter, the overexcavation position of the copy cutter, and if the shield tunneling machine is equipped with a folding jack, the vertical folding angle, the horizontal folding angle, and the rotation direction of the face cutter.

In addition, examples of the specified data related to the structure of the shield tunneling machine and the performance of the machinery and equipment to be normalized include the arrangement (selection) and pressure of the shield jack and the center bending jack, the speed of the shield jack, the position and stroke of the copy cutter, the torque, the rotation of the cutter, the diameter and torque value of the cutter plate, etc. When normalizing the specified data related to the structure of the shield tunneling machine and the performance of the machinery and equipment, it is preferable to set the maximum pressure of the shield jack to 1.0, the pressure when stopped to 0.0, and to allow the pressure when tunneling to be input as a numerical value between 0.0 and 1.0. For example, if the maximum pressure of the shield jack is 100 kN, 100 kN can be set to 1.0 and normalized to a non-dimensional value between 0.0 and 1.0, and if the maximum pressure of the shield jack is 5000 kN, 5000 kN can be set to 1.0 and normalized to a non-dimensional value between 0.0 and 1.0. In this case, it is preferable to normalize the maximum capacity such as the maximum pressure as the maximum capacity (maximum performance) according to the specifications of the machinery and equipment, rather than the range of the maximum capacity of the machinery and equipment that is expected to be actually used. Note that the specified data regarding the structure of the shield machine and the performance of the machinery and equipment used to create the initial excavation prediction model are the data that are first input as initial settings, and may be different data from the data measured during excavation, as shown in FIG. 4. The specified data regarding the structure can be used when calculating feature engineering, and the specified data regarding the performance can be used as the denominator when normalizing.

Furthermore, certain data related to the structure of the shield tunneling machine and the performance of the mechanical equipment can also be normalized by feature engineering based on the knowledge of the shield engineer. Examples of such data that can be normalized by feature engineering include the inclination of the cutter face plate in the horizontal and vertical directions (calculated from the difference between the horizontal and vertical jack strokes), the horizontal and vertical moments (a resultant moment is generated by detecting whether the jack is on or off, and the resultant vector is decomposed into the horizontal and vertical directions for calculation), the horizontal and vertical overexcavation amount (after calculating the total overexcavation amount, the overexcavation amount vector is calculated and then decomposed into the horizontal and vertical directions for calculation), and directional torque (the direction in which the torque is applied is calculated based on the direction of rotation of the cutter face plate).

In this embodiment, at another shield construction site, these explanatory variables and objective variables are used as training data, and machine learning is performed, preferably using a neural network with a support vector machine as an algorithm, to create a trained model in which construction measurement data, including predetermined data on the structure of the shield machine and the performance of the mechanical equipment, for the five rings N-1' to N-5' on the rear side of the excavation direction is used as input data, and the deviation of the tip of the shield machine 20 when constructing each of the six rings N' to N+5' on the front side of the excavation direction is used as output data. In the learning area for the first week, six of these trained models can be created as trained general-purpose models in which the deviation of the tip of the shield machine 20 when constructing each of the six rings N to N+5 on the front side of the excavation direction is used as output data (see Figure 2).

In addition, in this embodiment, following the learning area for the first week, a section similar to the learning area for the first week, for example an extension of 70 rings (for example 125 m), is set as the learning area for the second to fourth weeks on the excavation plan extension line 21 of the shield tunneling machine 20, and, similar to the learning area for the first week, six trained general-purpose models are created for each of the learning areas for the second to fourth weeks, as shown in Figure 6, in a manner similar to the learning area for the first week. That is, in each of the learning areas from the second to fourth weeks, as shown in FIG. 2, construction measurement data including predetermined data regarding the operation of the shield machine 20 when constructing preferably five rings N-1' to N-5' on the rear side in the excavation direction is used as an explanatory variable, and the deviation of the tip of the shield machine 20 when constructing each of the six rings N' to N+5' on the front side in the excavation direction is used as the objective variable. By performing machine learning using a neural network preferably using a support vector machine as an algorithm, six trained general-purpose models are created in which construction measurement data including predetermined data regarding the operation of the shield machine for the five rings N-1' to N-5' on the rear side in the excavation direction is used as input data, and the deviation of the tip of the shield machine 20 when constructing each of the six rings N' to N+5' on the front side in the excavation direction is used as output data.

As a result, in this embodiment, as shown in FIG. 6, the prediction period is the first week to the fourth week, the prediction interval is the future six rings (N' to N+5') in each prediction period, and a total of 24 trained general-purpose models are created to output deviations, with the tip of each shield machine 20 being the predicted destination point when constructing six rings N' to N+5'.

In addition, in this embodiment, it is preferable to select the trained general-purpose model with the most accurate prediction period and prediction interval from a total of 24 trained general-purpose models obtained by machine learning at another shield construction site, and use it as an initial excavation prediction model that can be used in the initial excavation area, which is the area at the time of departure from the starting shaft at the shield construction site. Here, the selection of the trained general-purpose model with the most accurate prediction period and prediction interval to be used as the initial excavation prediction model can be easily performed, for example, by comparing the output data when construction measurement data including predetermined data on the operation of the shield tunneling machine obtained in a learning area in a week other than the week in which one trained general-purpose model was obtained, inputted into the one trained general-purpose model with a known value related to the deviation of the tip of the shield tunneling machine in the construction measurement data obtained in the learning area in the other week.

In this embodiment, by using the initial excavation prediction model created at another shield construction site as described above, in the initial excavation area, which is the area when the shield tunneling machine 20 starts from the starting shaft at the shield construction site, data including predetermined data related to the operation of the shield tunneling machine is input from construction measurement data, preferably from construction of one or more rings N-1 to N-5 on the rear side of the excavation direction, and the deviation of the tip of the shield tunneling machine when constructing a predetermined ring N to N+5 on the front side of the excavation direction is output, making it possible to manage the excavation of the shield tunneling machine in the initial excavation area while predicting the deviation of the tip of the shield tunneling machine.

In this embodiment, the initial excavation area is preferably set as a learning area at the shield construction site, and the construction measurement data when constructing one or more rings N-1 to N-5 (see Figure 2) on the rear side is preferably used as explanatory variables, and the predetermined data related to the operation, preferably excluding data related to the surrounding environment of the shield machine (recording date and time, cutter bit acceleration, tail clearance, etc.), is used as explanatory variables, and the trained model, which preferably uses the deviation of the tip of the shield machine when constructing the predetermined rings N to N+5 on the front side of the excavation direction as the objective variable, is used as the prediction model for the main excavation, and the construction measurement data when constructing one or more rings on the rear side of the excavation direction that have been constructed is input, and the deviation of the tip of the shield machine when constructing the predetermined ring on the front side of the excavation direction is output, and the excavation of the shield machine in the main excavation area is managed while predicting the deviation of the tip of the shield machine from the excavation plan extension line. Note that in this learning area, data related to the surrounding environment is measured, but it is possible not to use it as an explanatory variable.

In other words, to create this excavation prediction model at the shield construction site using AI machine learning, preferably an initial construction section extending for example 70 rings (1 ring = 1.5 m) set in the initial excavation area is set as the first week's learning area (e.g. 125 m), and as shown in Figure 2, in the same way as when creating an initial excavation prediction model at another shield construction site, a learned model is created in which the construction measurement data when constructing preferably five rings N-1 to N-5 on the rear side in the excavation direction is used as an explanatory variable, and the deviation (horizontal deviation, vertical deviation, directional deviation) of the tip of the shield tunneling machine 20 when constructing each of the six rings N to N+5 on the front side in the excavation direction is used as an objective variable. Here, the explanatory variables can include data including specific data regarding the operation of the shield machine when constructing the five rings N-1 to N-5 on the rear side of the excavation direction, specific data regarding normalized performance of the structure and mechanical equipment of the shield machine 20, as well as excavation data regarding understanding the position of the shield machine that can reflect the "habits" of the shield machine 20 at the shield construction site, and other excavation data such as soil type. Data regarding the surrounding environment that was not used in the initial excavation area can also be included.

In this embodiment, in the learning area of the shield construction site, these explanatory variables and objective variables are used as teacher data, and machine learning is performed using a neural network, preferably with a support vector machine as an algorithm, to create a trained model in which the input data is the specified construction measurement data of the five rings N-1 to N-5 on the rear side of the excavation direction, and the output data is the deviation of the tip of the shield tunneling machine 20 when constructing each of the six rings N to N+5 on the front side of the excavation direction. As with the trained general-purpose model at the shield construction site described above, in the learning area of the first week, six trained models can be created as trained models in which the output data is the deviation of the tip of the shield tunneling machine 20 when constructing each of the six rings N to N+5 on the front side of the excavation direction (see Figure 6).

In addition, in this embodiment, preferably following the first week's learning area, a section with an extension of, for example, 70 rings (for example, 125 m) similar to the first week's learning area is set as the second to fourth week's learning area on the excavation plan extension line 21 of the shield tunneling machine 20, which is further forward in the excavation direction than the initial excavation area, and six learned models can be created for each of the second to fourth week's learning areas, as shown in Figure 6, similar to the first week's learning area. That is, in each of the learning areas from the second to fourth weeks, as shown in FIG. 2, the predetermined construction measurement data when constructing preferably five rings N-1 to N-5 on the rear side in the excavation direction is used as the explanatory variable, and the deviation of the tip of the shield machine 20 when constructing each of the six rings N to N+5 on the front side in the excavation direction is used as the objective variable, and machine learning is preferably performed using a neural network with a support vector machine algorithm to create six trained general-purpose models in which the predetermined construction measurement data of the five rings N-1 to N-5 on the rear side in the excavation direction is used as input data, and the deviation of the tip of the shield machine 20 when constructing each of the six rings N to N+5 on the front side in the excavation direction is used as output data.

As a result, in this embodiment, as shown in FIG. 6, the prediction period is the first week to the fourth week, the prediction interval is the future six rings (N to N+5) in each prediction period, and a total of 24 trained models are created to output deviations, with the tip of each shield machine 20 being the predicted destination point when constructing six rings N to N+5.

In addition, in this embodiment, it is preferable to select the trained model with the most accurate prediction period and prediction interval from these total of 24 trained models, and use it as the main excavation prediction model that can be used in the main excavation area of the shield construction site. Here, the selection of the trained model with the most accurate prediction period and prediction interval to be the main excavation prediction model can be easily performed, as in the case of the initial excavation prediction model described above, by, for example, comparing the output data when specific construction measurement data obtained in a learning area in a week other than the week in which a trained model was obtained is input into the trained model with a known value related to the deviation of the tip of the shield tunneling machine in the construction measurement data obtained in the learning area in the other week.

In this embodiment, by using the main excavation prediction model created at the shield construction site as described above, it is possible to input specified construction measurement data when constructing one or more rings N-1 to N-5, preferably on the rear side of the excavation direction, in the main excavation area at the shield construction site, and output the deviation of the tip of the shield machine when constructing specified rings N to N+5, preferably on the front side of the excavation direction, and manage the excavation of the shield machine in the main excavation area while predicting the deviation of the tip of the shield machine 20 from the excavation plan extension line 21.

As a result, the shield tunneling machine construction management method of this embodiment makes it possible to reuse and use a trained general-purpose model created by AI machine learning at another shield construction site, and in the initial excavation area, particularly at the shield construction site, it becomes possible to use the trained general-purpose model created as an initial excavation prediction model to manage the excavation of the shield tunneling machine, and by using this excavation prediction model created at the shield construction site, particularly at the initial excavation area, it becomes possible to reflect the characteristics of the shield tunneling machine known as its "habits" and appropriately manage the shield tunneling machine 20 so that it excavates along the excavation plan extension line 21 set underground.

The present invention is not limited to the above embodiment and can be modified in various ways. For example, the construction measurement data that serves as the explanatory variables for creating the trained general-purpose model or trained model does not necessarily have to be obtained from the five rings immediately preceding the rear side of the excavation direction, and one or more rings on the rear side of the excavation direction can be appropriately selected and the construction measurement data obtained from these rings can be used. The ring in which the deviation of the tip of the shield tunneling machine, which serves as the objective variable, is measured does not necessarily have to be one of the six rings immediately following the front side of the excavation direction, and may be the deviation of the tip of the shield tunneling machine in a ring seven or more rings forward. Machine learning for creating the trained model, parameter confirmation model, or prediction model does not necessarily have to be based on a neural network that uses a support vector machine as an algorithm, and may be based on various other algorithms that are capable of analyzing large amounts of construction measurement data.

10 Shield tunneling management system 11 Cloud server 12 LAN
13 Personal computer 14 Display 20 Shield tunneling machine 20a Rotary cutter 20b Shield jack 20c Skin plate 20d Erector device 20e Segment 21 Excavation plan extension line 22 Learning area N to N+5, N-1 to N-5, N' to N+5', N-1' to N-5' Ring

Claims (4)

A construction management method for a shield machine that manages the excavation of a shield machine at a shield construction site by using the results of machine learning by artificial intelligence using construction measurement data sent from a shield excavation management system as training data,
In the initial excavation area of the shield construction site, at a shield construction site other than the shield construction site where the size, specifications, and performance of the shield machine are different, data including predetermined data related to the operation of the shield machine from the construction measurement data when one or more rings on the rear side of the excavation direction are constructed is used as an explanatory variable, the deviation of the tip of the shield machine when constructing a predetermined ring on the front side of the excavation direction is used as the objective variable, and predetermined data related to the structure of the shield machine and the performance of the mechanical equipment from the construction measurement data that is the explanatory variable is normalized, and a learned general-purpose model created by machine learning is used as a prediction model for initial excavation, inputting data including predetermined data related to the operation of the shield machine from the construction measurement data when one or more rings on the rear side of the excavation direction that have been constructed are used, and outputting the deviation of the tip of the shield machine when constructing a predetermined ring on the front side of the excavation direction, thereby managing the excavation of the shield machine in the initial excavation area while predicting the deviation of the tip of the shield machine;
A shield construction management method for managing the excavation of the shield machine in the main excavation area, in which, in a main excavation area further forward in the excavation direction than the initial excavation area at the shield construction site, the construction measurement data when one or more rings on the rear side were constructed, which was created by machine learning in a learning area set rearward in the excavation direction than the main excavation area, is used as an explanatory variable, and a learned model with the deviation of the tip of the shield machine when constructing a specified ring on the forward side in the excavation direction as the objective variable is used as a prediction model for the main excavation, inputting the construction measurement data when one or more rings on the rear side in the excavation direction that have been constructed are constructed, and outputting the deviation of the tip of the shield machine when constructing a specified ring on the forward side in the excavation direction, thereby predicting the deviation of the tip of the shield machine from the excavation plan extension line. The construction management method for a shield tunneling machine according to claim 1, in which the learning area is set in the initial tunneling area. The construction management method for a shield tunneling machine according to claim 1 or 2, wherein the machine learning is machine learning using a neural network that uses a support vector machine as an algorithm. A construction management method for a shield tunneling machine according to any one of claims 1 to 3, in which the deviation of the tip of the shield tunneling machine, which is the objective variable, is a horizontal deviation, a vertical deviation, and a directional deviation.

Images