JP7311244B2 - Ground evaluation system and ground evaluation method - Google Patents

Description

TECHNICAL FIELD The present invention relates to a ground evaluation system and a ground evaluation method for evaluating the support layer of the ground on which piles are installed.

When constructing a structure, there is a construction method in which a plurality of piles are driven into a hard stratum in the ground and the load of the structure is supported in this hard stratum via the piles. A hard layer suitable for supporting a structure is called a support layer. Therefore, the pile holes into which the piles are inserted must reach the supporting layer. However, due to the limitations of the excavation method, confirmation of reaching the bearing layer often depends on subjective judgment based on experience, and objective judgment is difficult.

Usually, before constructing a structure, a ground investigation is performed to specify the depth (position) of the bearing layer and the like. Then, the N value, which is an index indicating the hardness of the ground, is obtained by a standard penetration test in ground investigation.

However, the geological structure is not necessarily the same throughout the construction site. In addition, it is difficult to conduct a ground survey at all pile hole positions because the ground survey is costly and time-consuming.

Therefore, conventionally, as an index that indicates the hardness of the ground during excavation, a value (integrated current value) obtained by integrating the current value for outputting the drilling torque for each drilling depth is used. A technique for determining is being studied (see, for example, Patent Document 1). In this patent document 1, a current value during excavation of an auger drive motor for driving an auger of an excavator that drills the ground is detected, and a vertical movement distance of the auger is detected. At the same time when the excavator starts excavating, the current data of the auger and the excavation depth are measured, and these measured values are displayed on the same screen.

JP-A-5-287721

As shown in Patent Document 1 mentioned above, the change in the integrated current value may be used to determine the support layer. However, there are cases where the change in the integral current value is not linked to the change in the N value. Therefore, when the N value is specified based on the integral current value, the N value may not be appropriate.

In addition, the applicant has invented a method for determining using a speed index value for the excavation speed during excavation of pile holes and a frequency analysis of vibration during excavation. Japanese Patent Application No. 2017-153621 has been filed.

A ground evaluation system for solving the above problems includes a measured value storage unit that stores an index value indicating an excavation load during excavation and ground evaluation information in association with each other for each depth, and a measured value storage unit that stores Using the index value as an input layer as an input element, performing machine learning using teacher data using the ground evaluation information at the depth of the index value as an output layer, and executing a learning process for generating a ground evaluation model. and a calculation unit that executes estimation processing for estimating the ground evaluation information to be evaluated using the ground evaluation model and input elements to be evaluated.

ADVANTAGE OF THE INVENTION According to this invention, the ground can be evaluated exactly.

BRIEF DESCRIPTION OF THE DRAWINGS It is explanatory drawing of the excavation apparatus which excavates the pile hole in embodiment, Comprising: (a) is a schematic sectional drawing of an excavation apparatus, (b) is a block diagram which shows the structure of a drilling management system. FIG. 4 is an explanatory diagram of a data configuration stored in a measured value storage unit according to the embodiment; FIG. 4 is a schematic explanatory diagram for explaining processing of a learning unit in the embodiment; 4 is a flow chart for explaining a processing procedure of overall processing in the embodiment; FIG. 4 is an explanatory diagram for explaining the process of associating with depth in the embodiment, in which (a) is a graph of measured values, (b) is a graph obtained by extracting the drilling time zone, and (c) is the measured value of the drilling time zone. The graph which connected, (d) is a flow chart of a processing procedure. It is an explanatory diagram of data corresponding to the depth in the embodiment, (a) is the excavation time, (b) is the current value, (c) is the water flow rate, (d) is the drilling speed, and (e) is the integrated current. indicate a value. It is an explanatory diagram of the estimated N value corresponding to the depth and the graph of the N value in the embodiment. ) shows the case where the estimated N value is calculated using the speed, current value, amount of water and integrated current value. It is an explanatory diagram when considering the vibration in the modification, (a) is the vibration characteristic value corresponding to the depth, (b) is estimated using the depth, speed, current value, water volume, integrated current value and vibration characteristic value When the N value is calculated, (c) shows the case where the estimated N value is calculated using the speed, current value, water volume, integrated current value and vibration characteristic value.

An embodiment embodying a ground evaluation system and a ground evaluation method will be described below with reference to FIGS. 1 to 7. FIG. In the present embodiment, whether or not the ground is hard enough to form a support layer is evaluated. For this evaluation, ground evaluation information for evaluating the ground on which the building is built is used. Here, the N value is used as the ground evaluation information. This ground evaluation information is estimated using an index value indicating the excavation load during excavation. In this embodiment, the index value indicating the excavation load includes the elapsed time corresponding to the excavation depth, the (instantaneous) current value supplied to the excavator, the flow rate of excavation water supplied to the excavator head, and Calculated values (drilling speed and integrated current value) calculated from these measured values (depth, current value, water volume) are used.

FIG. 1(a) shows an excavator 10 as an excavator for excavating a pile hole h0 for installing a building pile. The excavator 10 includes a base machine 11 , a mast 14 and an auger machine 16 . The base machine 11 includes a lower running body including crawlers 12 and an upper revolving body including an operation room 13 .

A mast 14 is erected on the base machine 11 . Inside the mast 14, wires for depth/velocity measurement are provided. An auger machine 16 is attached to the mast 14 so as to be able to move up and down. The auger machine 16 includes a drive motor housed in a box and an excavating rod 17 rotationally driven by the drive motor. A drilling head 18 is attached to the tip (lower end) of the drilling rod 17 . The excavation head 18 has excavation blades formed at the tips of a pair of (two) rocking excavation arms. The elevation of the drilling head 18 is controlled by an operator in the operation room 13. FIG.

A drilling water supply device (not shown) for supplying drilling water to the drilling head 18 is also connected to the drilling machine 10 . The amount of the drilling water is adjusted by the operator of the drilling water supply device (not shown) according to the instruction of the operator in the operation room 13 according to the drilling situation.

As shown in FIG. 1(b), the excavator 10 includes a drilling management system 20. As shown in FIG. This drilling management system 20 includes a computer terminal 30 , a drilling depth measuring device 21 , a flow rate measuring device 22 , a current measuring device 23 , an input section 25 and a display section 26 . Each measuring device (21 to 23) always performs measurement and transmits the measured values to the computer terminal 30. FIG.

The drilling depth measuring instrument 21 measures the amount of feeding of the wire in the mast 14 and measures the drilling depth (depth) corresponding to the position of the drilling head 18 .
The flow rate measuring device 22 measures the injection flow rate (water volume) of the drilling water supplied from the drilling water supply device (not shown).
The current measuring device 23 measures the load current (instantaneous current value) of the driving motor of the auger machine 16 .

The input unit 25 includes a keyboard, pointing device, etc. arranged in the operation room 13 and is used to input various data to the computer terminal 30 .
The display unit 26 has a display or the like arranged in the operation room 13 and displays various data.

The computer terminal 30 acquires each measured value data from each measuring instrument (21-23). The computer terminal 30 includes a control unit (CPU, RAM, ROM, etc.), a measured value storage unit 35, and a learning result storage unit 36, and processes described later (management stage, N value learning stage, N value calculation stage, etc.) ). Therefore, the control section of the computer terminal 30 functions as a management section 31, an N value learning section 32 and an N value calculation section 33 by executing a drilling management program stored in the memory.

The management unit 31 stores the start instruction from the input unit 25 and each measured value (depth, water volume, current value) from each measuring instrument (21 to 23) in the memory 31a. Furthermore, the management unit 31 calculates a calculated value based on the measured value for each predetermined time. Specifically, the management unit 31 calculates the drilling speed and the integral current value in the time zone (drilling time zone) during which the drilling actually progressed. The excavating head 18 may be temporarily pulled up immediately before digging into a hard stratum or the like. For this reason, the actual drilling depth of the drilling head 18 does not necessarily increase monotonically with elapsed time, as shown in FIG. 5(a). Therefore, the management unit 31 eliminates the periods during which the drilling head 18 is pulled up and stopped (the shaded time periods in FIG. Identify the measurements of the hole time window. The management unit 31 connects the measured values in the specified drilling time period to generate the graph shown in FIG. 5(c).

Furthermore, the management unit 31 controls the N value learning unit 32 and the N value calculation unit 33 .
The N-value learning unit 32 uses teacher data to generate an N-value calculation model as a ground evaluation model. The N-value learning unit 32 estimates an N-value calculation model by deep learning (machine learning) using the index value indicating the excavation load and the depth as input elements as an input layer and the N-value as an output layer. Here, the flow rate of water used for excavation, the (instantaneous) current value at the time of excavation, the drilling speed, and the integral current value are used as index values indicating the excavation load.

The N-value calculation unit 33 uses the N-value calculation model and the input elements (the index value indicating the excavation load and the depth) associated with the depth (depth) to execute the process of calculating the N-value.

As shown in FIG. 2 , the measured value storage unit 35 stores measured value information 350 . This measured value information 350 includes a log 351, N value data 352 corresponding to depth, a pile hole identifier 353, measured value data 355, and calculated value data 356 in association with the site identifier.

A site identifier is an identifier for specifying each site.
The log 351 is created based on a soil sample obtained in a boring survey at a construction site where a pile hole is excavated. N value data 352 according to depth is created based on the standard penetration test data acquired in this boring survey.

The pile hole identifier 353 is an identifier for specifying the drilled pile hole.
The measured value data 355 and the calculated value data 356 are index values indicating excavation loads. The measured value data 355 are index values actually measured during excavation. This measured value data 355 is generated and recorded when the measured value is acquired. The measured value data 355 includes depth-dependent elapsed time data R1, depth-dependent current value data R2, and depth-dependent water volume (flow rate) data R3 per unit time.

6A to 6C show examples of elapsed time data R1 corresponding to depth, (instantaneous) current value data R2 corresponding to depth, and water volume (flow rate) data R3 per unit time corresponding to depth. showing.

The calculated value data 356 is an index value calculated using the measured value data 355 . In this embodiment, the calculated value data 356 includes the drilling speed data R11 corresponding to the depth and the integrated current value data R21 corresponding to the depth.

FIGS. 6(d) and 6(e) show an example of the drilling speed data R11 corresponding to the depth and the integrated current value data R21 corresponding to the depth.
The drilling speed data R11 is calculated using the elapsed time data R1 by dividing each fixed excavation range (for example, 0.5 m deep) by the time required to drill the fixed excavation range.
The integral current value data R21 is calculated by summing the current values for the time required to excavate each fixed excavation range (for example, 0.5 m depth) using the current value data R2.

As shown in FIG. 3, the learning result storage unit 36 stores the learning result (N value calculation model) generated by the N value learning unit 32 through learning. This learning result is generated by machine learning (deep learning) using an input layer with an index value indicating the excavation load and depth as input elements, and an N value as an output layer.

(excavation)
Next, excavation processing of pile holes using the excavator 10 configured as described above will be described with reference to FIGS. 4 to 7. FIG.

<Boring survey process>
First, as shown in FIG. 4, a boring investigation process is performed before excavation. In this boring survey process, as is well known, a geological survey is conducted on the site of the construction site. A histogram is generated according to the type of soil sample obtained during this geological survey. Also, an N value is obtained for each predetermined depth, and N value data is generated.

Then, using the management unit 31 of the computer terminal 30, the columnar diagram and the N value are registered (step S1-1). Specifically, the management unit 31 outputs a ground information registration screen to the display unit 26 . The ground information registration screen includes input fields for registering data relating to the columnar map and N-value data corresponding to depth. The building site manager inputs a site identifier, a columnar diagram, and a graph of N values corresponding to the depth on the ground information registration screen. The management unit 31 of the computer terminal 30 generates the measured value information 350 including the field identifier, the histogram 351 and the N value data 352 corresponding to the depth, and records it in the measured value storage unit 35 .

<Exploratory drilling process>
After that, the trial drilling process is performed. In this trial drilling step, for example, a pile hole is drilled near the point where the boring survey was performed, and an index value indicating the drilling load at this time is acquired.

Here, first, the control unit of the computer terminal 30 of the drilling management system 20 acquires the start of excavation input using the input unit 25 . The management section 31 of the control section starts the rotation of the drive motor of the auger machine 16, inserts the excavation head 18 into the ground, and starts drilling. In this case, the management unit 31 displays an output screen including a histogram 351 and N value data 352 corresponding to the depth on the display of the display unit 26 . This output screen includes a display area for displaying elapsed time, current value, amount of water, drilling speed and integrated current value according to depth.

Then, during drilling, the management unit 31 of the computer terminal 30 executes a process of acquiring actual measured values (step S2-1). Specifically, the management unit 31 acquires actual values measured by the respective measuring devices (21 to 23) at predetermined time intervals.

Next, the control section of the computer terminal 30 executes depth association processing (step S2-2). Specifically, the management unit 31 of the control unit, among the actual measurement values obtained from the respective measuring instruments (21 to 23), calculates the actual measurement values during the drilling time zone excluding the time during which no drilling is actually performed, Identifies the measured value to be evaluated. Details of this process will be described later.

Next, the control section of the computer terminal 30 executes processing for calculating the drilling speed and the integral current value (step S2-3). Specifically, the management unit 31 of the control unit uses the excavation distance (depth) corresponding to the time (excavation time) in the drilling time period specified in step S2-2 to set each constant excavation range to this constant excavation range. The drilling speed is calculated by dividing by the time required to drill the drilled area. Furthermore, the management unit 31 uses the depth and the current value according to the time in the drilling time period, totaling the current values for the time required to excavate each fixed excavation range in the drilling time period, Calculate the integrated current value. Then, the management unit 31 records the calculated drilling speed and integrated current value in the memory 31a.

During drilling, every time an actual measured value is acquired (every time the process of step S2-1 is executed), the control unit of the computer terminal 30 executes the processes of steps S2-2 and S2-3. do.

After that, when it is determined that the hole has been drilled to a predetermined depth using the histogram 351 and the N value data 352, the controller of the computer terminal 30 raises the drilling head 18 to pull it out of the pile hole. Here, when the management unit 31 of the control unit acquires an instruction to raise the excavation head 18 via the input unit 25, it determines that drilling has ended. When it is determined that drilling has ended, the elapsed time, current value, water flow rate, drilling speed and integrated current value corresponding to the depth stored in the memory 31a are stored in each data (R1, R2, R3, R11, R21) is recorded in the measured value storage unit 35. It should be noted that the determination of the end of drilling may be made at another timing. For example, it may be immediately before stopping the auger machine 16 after the excavation head 18 is completely lifted.

[Association processing with depth]
Next, using FIG. 5, the details of the above-described depth association processing (step S2-2) will be described.

First, as shown in FIG. 5(d), the management unit 31 executes processing for acquiring the drilling depth of the drilling head (step S5-1). Specifically, as shown in FIG. 5A, the management unit 31 acquires the measured drilling depth from the drilling depth measuring device 21, and temporarily stores it in the memory 31a together with the acquired measurement time.

Then, the management unit 31 of the control unit executes extraction processing of the drilling time zone (step S5-2). Specifically, as shown in FIG. 5B, in this drilling, the management unit 31 determines that the drilling depth temporarily stored in the memory 31a is greater than or equal to the maximum value among past drilling depths. specifies the drilling time zone (region other than the shaded portion in FIG. 5(b)) in which the depth monotonously increases. When the drilling head 18 is pulled up, the time when the drilling head 18 reaches the bottom of the hole is added to the drilling time period again.

Next, the management section 31 of the control section executes processing for specifying the measured value of the drilling time period (step S5-3). Specifically, as shown in FIG. 5(c), the management unit 31 connects the drilling depths in the drilling time period and calculates the elapsed time corresponding to the drilling depths. Then, the management unit 31 stores the depth, the current value, and the amount of water in the memory 31a in association with the time (excavation time) in the drilling time zone.

<Learning process>
Next, as shown in FIG. 4, the learning process of learning the N-value calculation model is executed using the measured values and calculated values obtained in the trial drilling process as teaching data.

Here, first, the control section of the computer terminal 30 executes a teacher data acquisition process (step S3-1). Specifically, a model generation execution screen is output to the display unit 26 . This model generation execution screen includes an input field for entering a site identifier for specifying the site for which the N value is to be calculated, and an execution button. The construction site manager enters the site identifier in the input field of the model generation execution screen and selects the execution button. The management unit 31 of the computer terminal 30 acquires the execution instruction of the learning process together with the input site identifier.

In this case, the N-value learning unit 32 extracts the N-value data 352, the measured value data 355, and the calculated value data 356 associated with the site identifier in the measured value storage unit 35. Then, the N value learning unit 32 uses the elapsed time data R1, the current value data R2 and the water volume data R3 of the measured value data 355, the drilling speed data R11 and the integrated current value data R21 of the calculated value data 356 (with depth). is identified as the input element of the input layer. Each of these data (R1, R2, R3, R11, R21) is associated with depth. Furthermore, the N-value learning unit 32 specifies, as an output layer, the N-value data 352 associated with the depth of each data (R1, R2, R3, R11, R21) specified as the input layer.

Next, the control section of the computer terminal 30 executes learning processing for calculating the N value (step S3-2). Specifically, the N-value learning unit 32 of the control unit performs machine learning (deep learning) using an input layer and an output layer to generate an N-value calculation model.

Next, the control section of the computer terminal 30 executes the learning result storage process (step S3-3). Specifically, the N-value learning unit 32 of the control unit stores the generated N-value calculation model in the learning result storage unit 36 .

<Excavation process>
Next, the excavation process will be described with reference to FIG. In this excavation process, the calculated N value calculation model is used to estimate the N value of the ground located at the tip of the excavation head 18 during excavation. The computer terminal 30 of the drilling management system 20 starts rotating the drive motor of the auger machine 16 to insert the drilling head 18 into the ground to start drilling, as in the trial drilling process. In this case, the output screen including the estimation result display area is displayed on the display unit 26 . This estimation result display area is an area in which the N value calculated in the estimation process described later is displayed.

Then, similarly to steps S2-1 to S2-3, the control unit of the computer terminal 30 performs the actually measured value output processing (step S4-1), the depth association processing (step S4-2), the drilling speed and Calculation processing of the integral current value (step S4-3) is executed.

Next, the control unit of the computer terminal 30 executes N value estimation processing (step S4-4). Specifically, the N value calculation unit 33 of the control unit calculates the N value using the N value calculation model stored in the learning result storage unit 36, the acquired measured value, and the calculated calculated value. Here, the input elements including the current value, the amount of water, the drilling speed and the integrated current value corresponding to the depth (evaluation object) stored in the memory 31a are used as the input layer, and the output layer at that depth (evaluation object) Estimate the N value.

Then, the control unit of the computer terminal 30 executes N value output processing (step S4-5). Specifically, the management unit 31 of the control unit outputs the estimated N value to the estimation result display area of the output screen.

Then, the operator determines whether or not the supporting layer has been reached using the histogram 351 displayed on the output screen, the depth, and the calculated N value. It should be noted that the processing of steps S4-2 to S4-5 is executed each time the actually measured value acquisition processing (step S4-1) is executed.

Next, the control section of the computer terminal 30 executes a reach determination process to the support layer (step S4-6). Specifically, the management unit 31 of the control unit receives an instruction to stop drilling from the operator who has determined that the support layer has been reached. Furthermore, the management unit 31 receives an instruction to raise the excavation head 18 in order to withdraw the excavation head 18 from the pile hole, as in the trial drilling process. Then, the management unit 31 records each data corresponding to the depth stored in the memory in the measurement value storage unit 35 .

[N value calculation model and estimated N value]
FIG. 7(a) shows N values estimated using an N value calculation model generated from each value of depth, speed, current value, water volume, and integrated current value as an input layer. In addition, FIG. 7(b) shows the N value estimated using the N value calculation model generated from each value of the speed, current value, water volume and integral current value without using the depth value in FIG. 7(a). ing. In FIGS. 7(a) and 7(b), the dashed line is the actually measured N value, and the solid line is the estimated N value. curve. In this embodiment, a B-spline curve is used as the evaluation curve. The evaluation curve is not limited to the B-spline curve, and other curves (Bezier curve, moving average curve, etc.) that can complement the N value may be used.
Comparing the evaluation curve and the distribution of N values, as shown in FIG. A support layer can be determined. As an input layer, the N-value calculation model using multiple measured values and measured values is closer to the actual N-value than the N-value calculation model using either one of the measured values and calculated values. could be calculated. In addition, in FIGS. 7(a) and 7(b), the N value calculated for the depth shallower than 24 m is not shown.

According to this embodiment, the following effects can be obtained.
(1) In the present embodiment, the N-value calculator 33 of the computer terminal 30 is an input layer that uses the index values indicating the excavation load as input elements, such as the measured values of the measuring instruments (21 to 23) during drilling. , the N value is calculated using the N value calculation model stored in the learning result storage unit 36 . This makes it possible to estimate the N value and evaluate the hardness of the ground.

(2) In the present embodiment, the N-value learning unit 32 of the computer terminal 30 uses the measured value data 355 and the calculated value data 356 acquired in the trial drilling process and the corresponding N-value data as teacher data, Machine learning is performed to generate an N-value calculation model. As a result, an N-value calculation model can be generated using numerical values obtained by processing the measured values.

(3) In this embodiment, the N-value learning unit 32 of the computer terminal 30 acquires the depth specified from the elapsed time data R1, the current value data R2, the water volume data R3, the drilling speed data R11, and the integrated current value data R21. Using it as an input element, an N-value calculation model is generated. As a result, it is possible to accurately estimate the N value by using values obtained by measuring the excavation load from various aspects.

(4) In this embodiment, the N-value learning unit 32 of the computer terminal 30 generates an N-value calculation model using the measured value information 350 having the same field identifier. As a result, it is possible to generate an accurate N-value calculation model using the actual measurement values of the same site as the ground to be evaluated.

(5) In the present embodiment, in the excavation process, the N-value calculator 33 of the computer terminal 30 executes an actual measurement value acquisition process (step S4-1) and an N-value estimation process (step S4-4). This makes it possible to determine whether the support layer has been reached during drilling.

This embodiment can be implemented with the following modifications. This embodiment and the following modified examples can be implemented in combination with each other within a technically consistent range.
In the above embodiment, the N-value learning unit 32 of the computer terminal 30 uses depth, speed, (instantaneous) current value, water volume, and integrated current value as input layers to generate the N-value calculation model. . The index value indicating the excavation load used as the input layer is not limited to these. For example, an N-value calculation model is generated using multiple (at least two or more) input factors such as the depth of the measured values, the current value, the water volume, the drilling speed calculated from these, the integral current value, the drilling resistance value, etc. good too.

Furthermore, vibration information at the time of hole formation may be used as an index value indicating the excavation load used as an input factor. In this case, a vibration measuring instrument attached to the inside of the operation room 13, the roof of the operation room 13, or the operation lever inside the operation room 13 is used. This vibration measuring instrument measures vibration (for example, horizontal vibration) at the mounting location.

Then, the management unit 31 of the computer terminal 30 executes vibration characteristic analysis processing by performing frequency analysis of the vibration acquired from the vibration measuring instrument. Specifically, the management unit 31 calculates the magnitude of vibration (for example, maximum amplitude, etc.) for each frequency band of the measured horizontal vibration.

Then, the management unit 31 generates vibration characteristic value data in which the calculated magnitude of vibration, the N value at this time, and the depth are associated with each other. In this case, a vibration characteristic value of a frequency that is strongly correlated with the magnitude of vibration calculated by vibration analysis and the N value is used.
Specifically, as shown in FIG. 8A, the management unit 31 generates vibration characteristic value data that associates the depth with the maximum amplitude (vibration frequency: 5 Hz), and measures the vibration characteristic value data. It is stored in the measured value storage unit 35 as value data 355 .
In FIG. 8A, the solid line is the vibration characteristic value (maximum amplitude at a frequency of 5 Hz), and the two-dot chain line is the N value.

The N-value learning unit 32 learns using the vibration characteristic value corresponding to each depth as one of the teacher data, and stores the learning result (N-value calculation model) in the learning result storage unit 36 .
Then, the N value calculator 33 executes N value estimation processing (step S4-4). In this case, the N value calculator 33 also uses the vibration characteristic value calculated by the manager 31 as an index value indicating the excavation load to estimate the N value.

For example, FIG. 8(b) shows N values estimated using an N value calculation model generated from each value of depth, speed, current value, water volume, integrated current value, and vibration characteristic value in the input layer. In addition, FIG. 8(c) is estimated using an N value calculation model generated from each value of speed, current value, water volume, integral current value and vibration characteristic value without using depth value in FIG. 8(b) N values are shown. In these figures, the dashed line is the actually measured N value, and the solid line is an evaluation curve created using a statistical method to evaluate the estimated N value. In addition, the N value is not displayed at a depth shallower than 24 m.
The N value calculated by the N value calculation model used in FIGS. 8 (b) and 8 (c) is higher than the N value calculated by the N value calculation model used in FIGS. The variation is smaller, and the support layer can be determined stably.

Further, the vibration characteristic value used in the input layer for calculating the N value is not limited to the maximum amplitude at the vibration frequency of 5 Hz in the horizontal direction. For example, vertical vibration may be used, or a statistical value (eg, average value) of the magnitude of vibration at all frequencies may be used. In this case, any value (vibration characteristic value) related to vibration determined to have a strong correlation with the N value may be used.

- In the above embodiment, the N-value learning unit 32 of the computer terminal 30 uses the N-value as the ground evaluation information to be the output layer. The ground evaluation information to be output is not limited to the N value for evaluating soil hardness, and may be geological information (information specifying geological features) estimated from the estimated N value and histogram 351 . Also, instead of estimating the N value, information indicating that the ground is hard enough to serve as a pile support layer may be used. In this case, for example, a judgment condition for judging that it is the supporting layer of the pile is stored. Then, it is determined whether or not the stored determination condition is satisfied based on the index value indicating the excavation load, and the determination result is displayed on the display unit 26 .

- In the above embodiment, the N value learning unit 32 of the computer terminal 30 generated the N value calculation model by machine learning using the measured value data 355 and the calculated value data 356 corresponding to the depth. In this case, the N value calculation model may be generated by machine learning using only the index values of regions deeper than a predetermined depth. Index values may not be stable in shallow areas. For example, the drilling speed shown in FIG. 6(d) fluctuates greatly in a portion shallower than 23 m. Therefore, a more accurate N-value calculation model can be generated by performing machine learning using only numerical values of portions deeper than the reference depth (for example, 24 m) where variations are small.

- In the above embodiment, during drilling in the excavation process, actual measurement values were obtained from the measuring instruments (21 to 23) and the N value was calculated. The timing of calculating the N value is not limited to the time of drilling. For example, the N value may be calculated for ground evaluation after drilling. Specifically, the N value corresponding to the depth is estimated using the N value calculation model with the measured value data 355 and the calculated value data 356 obtained during drilling as input layers.

- In the above-described embodiment, the N value calculation model is generated by using the measurement value data acquired in the trial drilling as teaching data. The measured value data used for generating the N-value calculation model is not limited to the values acquired during test drilling. It may be index value data indicating the excavation load when a hole is formed in the ground including the support layer where the pile is provided, for example, data acquired when forming a hole in a boring survey. May be used.
- In the above-described embodiment, the computer terminal 30 includes the N-value learning unit 32 and the N-value calculating unit 33 . The learning unit that generates the hardness calculation model and the calculation unit that executes the process of estimating the ground evaluation information may be provided in different computer terminals.

h0... pile hole, R1... elapsed time data, R2... current value data, R3... water volume data, R11... drilling speed data, R21... integral current value data, 10... excavator, 11... base machine, 12... crawler, 13... Operation room, 14... Mast, 16... Auger machine, 17... Drilling rod, 18... Drilling head, 20... Drilling management system, 21... Drilling depth measuring instrument, 22... Flow measuring instrument, 23... Current measuring instrument , 25... input section, 26... display section, 30... computer terminal, 31... management section as control section, 31a... memory, 32... N value learning section as control section, 33... N value calculation section as control section , 35... Measured value storage unit, 36... Learning result storage unit, 350... Measured value information, 352... N value data, 353... Pile hole identifier, 355... Measured value data, 356... Calculated value data.

Claims (3)

Depth created based on the index value indicating the drilling load when drilling a hole in the ground of the site to be evaluated with a drilling device for each depth and the standard penetration test data acquired in the boring survey in the ground A measured value storage unit that stores the N value of each in association with each other;
Machine learning using teacher data using the depth of the site and the index value stored in the measured value storage unit as an input layer as input elements, and using the N value at the depth as an output layer. a learning unit that performs a learning process for generating a ground evaluation model;
An estimation process for estimating the N value of the evaluation object is executed using the ground evaluation model and the input element of the evaluation object acquired when a hole is formed in the ground of the site using the excavator. A ground evaluation system, comprising: a calculator. In the learning process and the estimation process, as the index values, the flow rate of water used for excavation, the current value supplied to the excavator, the excavation speed calculated from the excavation time and the excavation distance, and the integrated current value of the current value 2. The ground evaluation system according to claim 1, wherein a plurality of input elements of vibration characteristic values for vibration generated during excavation are used. Depth created based on the index value indicating the drilling load when drilling a hole in the ground of the site to be evaluated with a drilling device for each depth and the standard penetration test data acquired in the boring survey in the ground A measured value storage unit that stores the N value of each in association with each other;
a learning unit that generates a ground evaluation model using the index value of the site ;
A method for evaluating the ground using a ground evaluation system comprising a calculation unit that estimates the N value using the ground evaluation model,
The learning unit uses as an input layer the depth and the index value of the site stored in the measured value storage unit as input elements, and uses the N value at the depth as an output layer to create teacher data. Performing machine learning using the machine learning to generate the ground evaluation model,
The calculation unit estimates the evaluation target N value using the ground evaluation model and the evaluation target input elements acquired when a hole is formed in the ground at the site using the excavator. A ground evaluation method characterized by executing an estimation process.

Images