Support layer access support device and support layer access support method

Abstract

To provide a support layer reaching determination device and a support layer reaching determination method capable of highly accurately determining whether a support layer has been reached.SOLUTION: A support layer reaching determination device 30 comprises: a data acquisition unit 32 that acquires drilling recording data composed of a maximum depth of drilling and a value related to drilling resistance of a drilling machine for each preset measurement depth; a memory 31a that stores design soil quality data indicating a relation between the depth and soil quality based on a result of ground survey; an N value estimation unit 35 that calculates an estimated N value by using an N value estimation model including the drilling recording data and the design soil quality data in input elements; and a soil quality estimation unit 36 that estimates the soil quality by using a soil quality estimation model including the drilling recording data and the estimated N value in input elements.SELECTED DRAWING: Figure 3

Description

Technical Field

[0001] The present invention relates to a support layer reach determination device and method for determining whether excavation by an excavator has reached a support layer. of Determination Support Support layer reach support Device and support layer reach support Method.

Background Art

[0002] As a construction method for supporting the load of a structure, there is a method of excavating a pile hole to a support layer, which is a hard stratum in the ground, and supporting the load of the structure through a plurality of piles driven using the pile hole. As such a method, for example, as described in Patent Document 1, the all-casing method is known. In the all-casing method, a casing tube is pressed into the ground while being oscillated or rotated, and the earth and sand inside the casing tube are discharged to the ground with a hammer grab to form a pile hole. Then, when the casing tube reaches the support layer, after building a reinforcing cage or the like inside the casing tube, concrete is placed while pulling out the casing tube.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Incidentally, before the construction of a structure, a ground survey is conducted to determine the depth of the bearing layer. During this ground survey, a standard penetration test is performed to obtain indicators such as the N-value, which shows the hardness of the ground. However, the geological structure at the location where the ground survey was conducted is not necessarily the same as the location where the pile holes are excavated. Furthermore, conducting a ground survey at each excavation location is impractical considering the cost and effort involved. Therefore, there is a need for technology that can determine with high accuracy whether or not the bearing layer has been reached at each excavation location. It should be noted that this requirement applies not only to the all-casing method but to all methods of excavating down to the bearing layer using an excavator. [Means for solving the problem]

[0005] A bearing layer arrival determination device that solves the above problems is a bearing layer arrival determination device that determines whether excavation by an excavator has reached a bearing layer, and comprises: a data acquisition unit that acquires excavation record data consisting of the maximum depth of the excavation and a value relating to the excavation resistance of the excavator at each preset measurement timing; a design soil type storage unit that stores design soil type data showing the relationship between depth and soil type based on the results of a ground investigation; an N-value estimation unit that calculates an estimated N-value using an N-value estimation model that includes the excavation record data and the design soil type data as input elements; and a soil type estimation unit that estimates the soil type using a soil type estimation model that includes the excavation record data and the estimated N-value as input elements. [Effects of the Invention]

[0006] According to the present invention, it is possible to determine with high accuracy whether or not the excavation by the excavator has reached the supporting layer. [Brief explanation of the drawing]

[0007] [Figure 1] This diagram schematically shows the general configuration of an excavation system using one embodiment of a device for determining whether a bearing layer has been reached. [Figure 2] This figure shows an example of the hardware configuration of an information processing device that functions as a support layer arrival determination device. [Figure 3] This is a functional block diagram showing the device for determining whether the support layer has been reached. [Figure 4] This graph illustrates the filtering process for elapsed time when the maximum depth is below the set value in the condition setting interval. [Figure 5] This graph illustrates the filtering process for elapsed time where the maximum depth is greater than the set value in the condition setting interval. [Figure 6] (a) A graph showing an example of the relationship between maximum depth and elapsed time before filtering, and (b) A graph showing an example of the relationship between maximum depth and elapsed time after filtering. [Figure 7] This flowchart shows the flow of one embodiment of the method for determining whether the support layer has been reached. [Figure 8] This diagram illustrates a part of the display on a display device. [Modes for carrying out the invention]

[0008] An embodiment of the bearing layer arrival determination device and bearing layer arrival determination method will be described with reference to Figures 1 to 8. In this embodiment, the bearing layer arrival determination device and bearing layer arrival determination method will be described using the case in which the pile hole is excavated by the all-casing method as an example. Furthermore, the device for determining whether the bearing layer has been reached is a device for assisting in reaching the bearing layer, and the method for determining whether the bearing layer has been reached is a method for assisting in reaching the bearing layer.

[0009] As shown in Figure 1, in the all-casing method, pile holes are formed in the ground 10 by a full-circumference rotary drilling machine 15. The full-circumference rotary drilling machine 15 is equipped with a base device 16, a holding device 17, a rotating mechanism 18, and a pushing mechanism 19.

[0010] The base device 16 is a device for installing the circumferential rotary drilling machine 15 on the ground 10. The holding device 17 is a device that supports the casing tube 20, which is pressed into the ground 10, from the outside. The holding device 17 supports the casing tube 20 so that it can rotate around its central axis as the center of rotation, and also so that it can move vertically.

[0011] The rotating mechanism 18 rotates the casing tube 20 around its central axis when power is supplied from the power unit 21. The pushing mechanism 19 pushes the casing tube 20 into the ground when power is supplied from the power unit 21. The depth at which the lower end of the casing tube 20 is located after being pushed into the ground is called the maximum depth D.

[0012] The power unit 21 supplies power, for example, hydraulic pressure, to the circumferential rotary excavator 15. The power unit 21 is equipped with a control panel (not shown). The operator operates the circumferential rotary excavator 15 by operating the control panel. In response to the operator's operation, the circumferential rotary excavator 15 oscillates or rotates the casing tube 20 with the rotation mechanism 18, while the pushing mechanism 19 pushes the casing tube 20 into the ground 10. The soil inside the casing tube 20 is removed by a hammer grab (not shown) or the like.

[0013] In addition, in the case of the all-around rotating drilling machine 15, if the length of the casing tube 20 is insufficient, an extension operation is performed in which a new casing tube is connected to the upper end of the casing tube 20.

[0014] The power unit 21 is equipped with a rotation torque measuring instrument 22 for measuring the rotation torque of the rotation mechanism 18, and a pressing force measuring instrument 23 for measuring the pressing force of the pressing mechanism 19. The full-circumference rotating drilling machine 15 is also equipped with a displacement measuring instrument 25. When the full-circumference rotating drilling machine 15 is driven, the displacement measuring instrument 25 measures the displacement of the casing tube 20. Each measuring instrument 22, 23, and 25 takes measurements at a predetermined sampling period (e.g., 1 sec) and outputs the measured values ​​to the support layer arrival determination device 30.

[0015] (Support layer reach determination device) As shown in FIG. 2, the support layer arrival determination device 30 is configured using the information processing device H10. The information processing device H10 includes a communication device H11, an input device H12, a display device H13, a storage device H14, and a processor H15. Note that this hardware configuration is an example, and it may have other hardware.

[0016] The communication device H11 is an interface that establishes a communication path with other devices and executes data transmission and reception. The input device H12 is a device that receives input from a user or the like, such as a mouse or a keyboard. The display device H13 is a display or a touch panel that displays various information. The storage device H14 is a storage unit that stores data and various programs for executing various functions of the support layer arrival determination device 30. Examples of the storage device H14 include a ROM, a RAM, and a hard disk.

[0017] The processor H15 controls each process in the support layer arrival determination device 30 using the programs and data stored in the storage device H14. Examples of the processor H15 include a CPU and an MPU. This processor H15 expands the program stored in the ROM or the like into the RAM and executes various processes corresponding to various processes. For example, when the application program of the support layer arrival determination device 30 is started, the processor H15 operates a process that executes each process described later.

[0018] The processor H15 is not limited to performing software processing for all processes it executes. For example, the processor H15 may include a dedicated hardware circuit (e.g., an application-specific integrated circuit: ASIC) that performs hardware processing for at least a part of the processes it executes. That is, the processor H15 can be configured as follows.

[0019] (1) One or more processors that operate according to a computer program (software) (2) One or more dedicated hardware circuits that execute at least a part of various processes, or (3) Circuits that include combinations of those. A processor includes a CPU and memory such as RAM and ROM, where memory stores program code or instructions configured to cause the CPU to perform processing. Memory, or computer-readable media, includes any available media that can be accessed by a general-purpose or dedicated computer.

[0020] As shown in Figure 3, the bearing layer arrival determination device 30 includes a management unit 31, a data acquisition unit 32, an N-value learning unit 33, a soil type learning unit 34, an N-value estimation unit 35, and a soil type estimation unit 36 ​​as functional units that operate through the execution of various programs. The bearing layer arrival determination device 30 also includes a data storage unit 41, an N-value estimation model storage unit 42, and a soil type estimation model storage unit 43 as storage units for storing various data.

[0021] The management unit 31 manages the handling of various data input to the support layer arrival determination device 30 and the execution of processes using these various data. The data acquisition unit 32 acquires various types of data. The data acquisition unit 32 includes a measurement value acquisition unit 51, an elapsed time acquisition unit 52, a filtering unit 53, an integrated torque calculation unit 54, an average value calculation unit 55, and a standard deviation calculation unit 56.

[0022] The measurement value acquisition unit 51 acquires the maximum depth D based on the displacement measured by the displacement measuring instrument 25. The measurement value acquisition unit 51 also acquires the rotational torque T and the indentation force F at each measurement timing. In this embodiment, the measurement value acquisition unit 51 acquires the rotational torque T and the indentation force F at predetermined measurement depths based on the maximum depth D. The measurement depth is set to, for example, 0.1m. For example, the measurement value acquisition unit 51 acquires the rotational torque T as the average value of the measurement values ​​of the rotational torque measuring instrument 22 during the period in which the maximum depth D changes by the measurement depth. The measurement value acquisition unit 51 also acquires the indentation force F as the average value of the measurement values ​​of the indentation force measuring instrument 23 during the period in which the maximum depth D changes by the measurement depth.

[0023] The elapsed time acquisition unit 52 acquires the time required to excavate to a unit depth as the elapsed time t (= time required / measured depth), based on the displacement measured by the displacement measuring instrument 25 and the time required to excavate to the measured depth.

[0024] The filtering unit 53 removes abnormal values ​​from the elapsed time t acquired by the elapsed time acquisition unit 52 by performing a filtering process on the elapsed time t. The filtering unit 53 removes abnormally large elapsed time t as an abnormal value, for example, when the casing tube 20 is extended while only the measurement depth is being excavated.

[0025] The integrated torque calculation unit 54 calculates the integrated torque Ta when drilling only to the measured depth. For example, the integrated torque calculation unit 54 calculates the integrated torque Ta by multiplying the rotational torque T by the elapsed time t.

[0026] The average value calculation unit 55 calculates the average rotational torque T1, average indentation force F1, and average integrated torque Ta1 for each of the rotational torque T, indentation force F, and integrated torque Ta, using the values ​​in the calculation target section up to the maximum depth D as the population. The calculation target section is set to, for example, 1.0 m. The average value calculation unit 55 calculates various average values ​​T1, F1, and Ta1 for each measurement depth.

[0027] The standard deviation calculation unit 56 calculates the rotational torque standard deviation T2, the indentation force standard deviation F2, and the integrated torque standard deviation Ta2 for each of the rotational torque T, indentation force F, and integrated torque Ta, using the values ​​in the calculation interval as the population. The standard deviation calculation unit 56 calculates various standard deviations T2, F2, and Ta2 for each measurement depth.

[0028] The N-value learning unit 33 generates an N-value estimation model that calculates the estimated N-value at the maximum depth D by performing machine learning using the N-value training data stored in the data storage unit 41. The N-value learning unit 33 stores the generated N-value estimation model in the N-value estimation model storage unit 42.

[0029] The soil learning unit 34 generates a soil estimation model that estimates the soil type at the maximum depth D by performing machine learning using soil training data stored in the data storage unit 41. The soil estimation unit 36 ​​stores the generated soil estimation model in the soil estimation model storage unit 43.

[0030] The N-value estimation unit 35 calculates the estimated N-value at the maximum depth D based on the design soil type of the construction site, the excavation record at the excavation location, and the N-value estimation model stored in the N-value estimation model storage unit 42.

[0031] The soil type estimation unit 36 ​​estimates the soil type at the maximum depth D based on the excavation record at the excavation location, the estimated N-value calculated by the N-value estimation unit 35, and the soil type estimation model stored in the soil type estimation model storage unit 43.

[0032] (Filtering section) An example of the filtering process performed by the filtering unit 53 will be described below. As mentioned above, the filtering process is the process of removing abnormal values ​​from the elapsed time t.

[0033] In the filtering process, the filtering unit 53 sets the time to be removed and the condition setting interval. The time to be removed is the elapsed time t that is to be removed in the filtering process. The condition setting interval is an interval for setting a determination value for determining whether the time to be removed satisfies an abnormal condition, based on the elapsed time t in that interval. The condition setting interval is set to, for example, 2.0m.

[0034] The filtering unit 53 sets all elapsed time t to be removed for periods where the corresponding maximum depth D is less than or equal to the set value of the condition setting interval, and sets the interval up to the maximum depth D corresponding to the set value as the condition setting interval.

[0035] For example, as shown in Figure 4, if the setting value for the condition setting interval is 2.0m, the filtering unit 53 sets all elapsed times t as time to be removed, using the elapsed time t corresponding to the maximum depth D as 2.0m or less as the reference elapsed time ts, and sets a judgment value based on those elapsed times t.

[0036] The filtering unit 53 sets the time to be removed and the condition setting interval, using the elapsed time t as the reference elapsed time ts for any elapsed time t where the corresponding maximum depth D is greater than the set value of the condition setting interval.

[0037] Specifically, the filtering unit 53 sets the reference elapsed time ts and the two elapsed times t before and after the reference elapsed time ts as the time to be removed. The filtering unit 53 sets a predetermined depth interval, which is an interval based on the set value and extends up to the maximum depth D corresponding to the reference elapsed time ts, as the condition setting interval.

[0038] For example, as shown in Figure 5, if the setting value for the condition setting interval is 2.0m and the elapsed time t corresponding to the maximum depth of 5.0m is set as the reference elapsed time ts, the filtering unit 53 sets the maximum depth from 3.0m to 5.0m as the condition setting interval and sets the judgment value based on the elapsed time t measured in that interval.

[0039] As illustrated in Figures 4 and 5, the filtering unit 53, which has set the time to be removed and the condition setting interval, calculates the median value tc of the elapsed time t in the condition setting interval. The filtering unit 53 then sets abnormal conditions based on the median value tc. Abnormal conditions are conditions that indicate that the elapsed time t is abnormally large, regardless of changes in soil properties, such as when casing tube extension work is performed. Based on the results of verification performed in advance, the abnormal conditions are set to be, for example, an elapsed time tb or more, which is three times the median value tc. The filtering unit 53 removes elapsed time t that satisfies the abnormal conditions as abnormal values. In Figures 4 and 5, the elapsed time t that has been removed as an abnormal value is shown as a black circle. The filtering unit 53 may also set a corrected elapsed time by linearly interpolating using the elapsed time t before and after the abnormal value as the elapsed time t that has been removed as an abnormal value.

[0040] The graph in Figure 6(a) shows the relationship between the maximum depth D and the elapsed time t before filtering, for examples where casing tube extension work was performed at maximum depths D around 0m, 5m, 10m, and 15m. The graph in Figure 6(b) shows the relationship between the maximum depth D and the elapsed time t after filtering, for the elapsed time t shown in Figure 6(a). As shown in Figures 6(a) and 6(b), it can be seen that the filtering process described above removes the elapsed time t when casing tube extension work or other such work is performed as an outlier.

[0041] (Method for determining support layer reach) As shown in Figure 7, the method for determining the arrival of the bearing layer using the bearing layer arrival determination device 30 comprises a pre-construction process, an investigation process, a pre-excavation process, and an excavation process. The pre-construction process is a process in which an N-value estimation model and a soil type estimation model are generated based on actual data. The investigation process is a process in which a ground investigation (e.g., boring investigation) is conducted at the investigation location of the construction site where excavation will be carried out. The pre-excavation process is a process performed at the construction site before excavating at each excavation location. The excavation process is a process performed during excavation at each excavation location.

[0042] (Pre-construction process) In the pre-construction process, when an input device H12 performs a training data acquisition operation while an external storage medium or external terminal for storing actual data is connected to the communication device H11, the management unit 31 executes a training data acquisition process to acquire training data based on actual data (step S1-1). Furthermore, when a training operation is performed on the input device H12 after the training data acquisition process is completed, the management unit 31 executes a training process (step S1-2).

[0043] The performance data consists of various measurement values ​​obtained at past construction sites. Specifically, the performance data is data associated with identification information that identifies the construction site and the excavation location within that site, including design soil data, measured N values ​​and actual soil properties for each measurement depth, as well as rotational torque T, compression force F, maximum depth D, and elapsed time t before filtering for each measurement depth. Actual soil properties are classified into four types, for example: cohesive soil, sandy soil, gravel, and bedrock. The design soil data is data based on the results of ground investigations conducted at predetermined investigation locations at the construction site. The design soil data shows the actual soil properties for each depth at the investigation location.

[0044] (Training data acquisition process) In the training data acquisition process (step S1-1), the data acquisition unit 32 acquires actual excavation data based on actual data for each excavation location.

[0045] In acquiring actual drilling data, the data acquisition unit 32 performs filtering by elapsed time t and calculates the cumulative torque Ta, various average values ​​T1, F1, Ta1, and standard deviations T2, F2, Ta2 for each measurement depth. The data acquisition unit 32 then acquires actual drilling data by associating the elapsed time t after filtering, the rotational torque T, pushing force F, maximum depth D, cumulative torque Ta, and various average values ​​T1, F1, Ta1 and standard deviations T2, F2, Ta2 corresponding to the elapsed time t with the identification information.

[0046] The data acquisition unit 32 creates N-value training data by associating the measured N-values ​​corresponding to each maximum depth D with the actual excavation data and the design soil data as ground truth data. The data acquisition unit 32 also creates soil training data by associating the actual soil properties corresponding to each maximum depth D with the actual excavation data and the measured N-values ​​as ground truth data. The data acquisition unit 32 outputs the created N-value training data and soil training data to the management unit 31. Once the management unit 31 stores the N-value training data and soil training data output by the data acquisition unit 32 in the data storage unit 41, it terminates the training data acquisition process.

[0047] (Learning process) The learning process (step S1-2) is the process of generating an N-value estimation model and a soil type estimation model.

[0048] In the learning process, the N-value learning unit 33 generates an N-value estimation model by performing machine learning using the N-value training data stored in the data storage unit 41. Specifically, the N-value learning unit 33 generates an N-value estimation model by performing machine learning with actual excavation data and design soil data as input layers and the measured N-values ​​corresponding to the actual excavation data as output layers. The N-value learning unit 33 stores the generated N-value estimation model in the N-value estimation model storage unit 42.

[0049] Furthermore, during the learning process, the soil learning unit 34 generates a soil estimation model by performing machine learning using soil training data stored in the data storage unit 41. Specifically, the soil learning unit 34 generates a soil estimation model by performing machine learning with actual excavation data and measured N values ​​as the input layer and the actual soil properties corresponding to the actual excavation data as the output layer. The soil learning unit 34 stores the generated soil estimation model in the soil estimation model storage unit 43.

[0050] Various machine learning methods can be applied to each learning unit. Among these, suitable methods for generating N-value estimation models and soil type estimation models include bagging, an ensemble learning method; LSTM (Long Short-Term Memory), a deep learning method; and XAI (Explainable AI) methods such as GAM (Generalized Additive Model) and LIME (Local Interpretable Modelagnostic Explanations), which allow for explanation of the process leading to the prediction and estimation results. For generating soil type estimation models, CNN (Convolutional Neural Network), a deep learning method, is suitable. Once the N-value estimation model and soil type estimation model are stored, the management unit 31 terminates the learning process. This completes the pre-construction process.

[0051] (Investigation process) In the investigation process, a ground investigation is conducted at the investigation site (Step S2-1), and then design data based on the investigation results is created using an external terminal or the like (Step S2-2). The design data consists of design soil data, which is the soil type at each depth at the investigation site, and design N-value data, which is the N-value at each depth. The design data is saved on an external terminal or external storage medium.

[0052] (Pre-excavation process) In the pre-excavation process, installation work is carried out to set up the all-around rotating excavator 15 and the power unit 21 at the excavation site (Step S3-1). Subsequently, wiring work is carried out to connect the wiring of various measuring instruments such as the rotation torque measuring instrument 22, the indentation force measuring instrument 23, and the displacement measuring instrument 25 to the support layer arrival determination device 30 (Step S3-2).

[0053] Furthermore, various information such as design data for the construction site, identification information for the construction site, and identification information for the excavation location are input to the bearing layer arrival determination device 30 (step S3-3). The design data is input to the bearing layer arrival determination device 30 when an external storage medium or external terminal that stores the design data is connected to the communication device H11 and a design data input operation is performed on the input device H12. The identification information for the construction site and the excavation location is input to the bearing layer arrival determination device 30 when an identification information input operation is performed on the input device H12. Once the design data and identification information are input, the management unit 31 performs a registration process to register them in the memory 31a (step S3-4). The memory 31a that stores the design data functions as a design soil storage unit.

[0054] (Excavation process) In the excavation process, the operator controls the control panel to start excavation using the full-rotation drilling machine 15. Once excavation has started, the input device H12 performs an excavation start operation. After the excavation start operation is performed, the control unit 31 performs excavation record acquisition processing (step S4-1), estimation processing (step S4-2), and output processing (step S4-3), and then determines whether the supporting layer has been reached (step S4-4).

[0055] In the drilling record acquisition process (step S4-1), the data acquisition unit 32 acquires the rotational torque T, indentation force F, maximum depth D, and elapsed time t for each measurement depth. In addition, the data acquisition unit 32 performs a filtering process on the elapsed time t and calculates the integrated torque Ta, as well as various average values ​​T1, F1, Ta1 and standard deviations T2, F2, Ta2 for each measurement depth. The data acquisition unit 32 then acquires drilling record data for each measurement depth, associating the rotational torque T, indentation force F, maximum depth D, elapsed time t after filtering, integrated torque Ta, and various average values ​​T1, F1, Ta1 and standard deviations T2, F2, Ta2. The data acquisition unit 32 outputs the acquired drilling record data to the management unit 31. The management unit 31 associates the drilling record data output by the data acquisition unit 32 with the design data stored in memory 31a and saves it in memory 31a.

[0056] In the estimation process (step S4-2), the management unit 31 outputs the latest excavation record data and design soil data to the N-value estimation unit 35. The N-value estimation unit 35 inputs the excavation record data and design soil data as input elements into the N-value estimation model stored in the N-value estimation model storage unit 42. The N-value estimation unit 35 then calculates the value output to the output layer of the N-value estimation model as the estimated N-value at the maximum depth D. The management unit 31 also outputs the latest excavation record data to the soil estimation unit 36. The soil estimation unit 36 ​​inputs the excavation record data and the estimated N-value calculated by the N-value estimation unit 35 as input elements into the soil estimation model stored in the soil estimation model storage unit 43. The soil estimation unit 36 ​​then estimates the soil type corresponding to the value output to the output layer of the soil estimation model as the actual soil type at the maximum depth D.

[0057] In the output processing (step S4-3), the control unit 31 outputs the information obtained through the excavation record acquisition process and estimation process, etc., along with the design data, to the display device H13 or the like. Figure 8 illustrates a portion of the display on the display device H13. The display device H13 displays the design N value, estimated N value, rotational torque T, integrated torque Ta, required time (time required to excavate to each maximum depth), elapsed time t after filtering, indentation force F, design soil type, and estimated soil type. Here, it is preferable that the design N value and estimated N value are displayed in the same graph. This makes it easier to understand the trends of the design N value and estimated N value, and to compare the design N value and estimated N value. It is also preferable that the design soil type and estimated soil type are displayed side by side. This makes it easier to compare the design soil type and estimated soil type.

[0058] In the determination of reaching the bearing layer (step S4-4), it is determined whether the maximum depth D has reached the bearing layer based on the estimated N value and estimated soil type. If it is determined that the maximum depth D has not reached the bearing layer, drilling by the full-rotation drilling machine 15 continues, and steps (S4-1) to (S4-4) are repeated. On the other hand, if it is determined that the maximum depth D has reached the bearing layer, the control panel is operated to terminate drilling by the full-rotation drilling machine 15, and the drilling termination operation is performed on the input device H12. Once the drilling termination operation is performed, the management unit 31 erases the various identification information, design data, and drilling record data stored in the memory 31a.

[0059] Once the drilling by the 360-degree rotary drilling machine 15 is complete, the reinforcement cage is installed inside the casing tube 20, and then concrete is poured using a tremie pipe while the casing tube 20 is withdrawn. This constructs a pile at the drilled location. Once the pile is constructed, the wiring of various measuring instruments is disconnected from the bearing layer arrival determination device 30, and then the pre-drilling process and drilling process are carried out for the next drilled location. The bearing layer arrival determination device 30 may be configured so that the registration of design data is omitted in the pre-drilling process from the second time onward.

[0060] The effects of this embodiment will now be explained. (1) In the bearing layer arrival determination device 30, the estimated N value is calculated using an N value estimation model generated with actual excavation data and design soil data as input layers and the measured N value as the output layer. In addition, the soil type is estimated using a soil type estimation model generated with actual excavation data and measured N value as input layers and the actual soil type as the output layer. As a result, the accuracy of the estimated N value and estimated soil type is improved, making it possible to determine with high accuracy whether or not the maximum depth D has reached the bearing layer.

[0061] (2) By filtering the elapsed time t acquired for each measurement depth, abnormal values ​​of elapsed time t can be removed, such as when the casing tube 20 is extended. As a result, the accuracy of the estimated N value and estimated soil properties can be further improved.

[0062] (3) In the filtering process, the judgment value is set based on the median value tc of the elapsed time t in the condition setting interval. This makes it possible to set a judgment value that is robust to outliers in elapsed time t. As a result, even if outliers in elapsed time t are included in the condition setting interval, those outliers can be removed more reliably.

[0063] (4) By setting a corrected elapsed time obtained by linearly interpolating the elapsed time t before and after the outlier as a substitute for the outlier, the N value at the maximum depth D corresponding to the outlier can be estimated with high accuracy in terms of soil quality.

[0064] (5) The drilling record data includes the average values ​​T1, F1, Ta1 and standard deviations T2, F2, Ta2 of the rotational torque T, the indentation force F, and the cumulative torque Ta, respectively. With this configuration, the N value and soil type can be estimated by taking into account the change in drilling resistance as the drilling progresses.

[0065] This embodiment can be implemented with the following modifications. This embodiment and the following modifications can be combined with each other to the extent that they do not contradict each other technically. In the above embodiment, the bearing layer arrival determination device 30 and the bearing layer arrival determination method were applied to an all-casing method using a full-rotation drilling machine 15. However, the bearing layer arrival determination device 30 and the bearing layer arrival determination method can also be applied to other methods in which it is possible to obtain the drilling resistance of the drilling machine, such as the earth auger method.

[0066] The filtering unit 53 may perform filtering over elapsed time t based on a predetermined judgment value (a constant value) rather than a judgment value set based on the condition setting interval. In this case, it is preferable that the judgment value is set for each depth based on design data, for example.

[0067] The bearing layer arrival determination device 30 only needs to have a management unit 31, a data acquisition unit 32, an N-value estimation model storage unit 42, a soil type estimation model storage unit 43, an N-value estimation unit 35, and a soil type estimation unit 36. Therefore, the bearing layer arrival determination device 30 may be configured to acquire the learned N-value estimation model and soil type estimation model from an external storage medium or external terminal and store these models in the respective storage units 42 and 43.

[0068] In the above embodiment, various models were generated by supervised learning using measured N-values ​​and actual soil properties as ground truth data. However, the N-value estimation model may be generated by unsupervised learning using actual excavation data and designed soil property data as input layers. Similarly, the soil property estimation model may be generated by unsupervised learning using actual excavation data and the output results of the N-value estimation model as input layers. Furthermore, in this configuration, it is preferable that the management unit 31 stores the various identification information, design data, and excavation record data stored in memory 31a in the data storage unit 41 at the end of the estimation process. This allows each learning unit 33, 34 to perform further machine learning using the excavation record data, thereby improving the accuracy of the various models.

[0069] • When using XAI, which can be explained as a machine learning method, input elements with high contributions may be displayed on the display device H13. With this configuration, it is possible to understand which input elements have a high contribution depending on the situation at the time.

[0070] The support layer arrival determination device 30 may have a selection unit for selecting a machine learning method. The selection unit selects a machine learning method according to the circumstances and various settings at the time, for example, according to the contribution of the design data and input elements at that time.

[0071] The bearing layer arrival determination device 30 may have a determination unit that determines whether or not the maximum depth has reached the bearing layer based on the estimated N value and estimated soil properties. The determination unit can be configured, for example, by a determination model generated by machine learning, in which the estimated N value and estimated soil properties are the input layers and whether or not the bearing layer has been reached is the output layer. The input layers of the determination model may include resistance data and design soil property data.

[0072] In the above embodiment, the filtering unit 53 sets the reference elapsed time ts and the two elapsed times t before and after the reference elapsed time ts as the time to be removed. However, the filtering unit 53 may also set the latest value of the elapsed time t as the reference elapsed time and the time to be removed.

[0073] In the above embodiment, the data acquisition unit 32 acquires drilling record data for each measurement depth, that is, using the timing based on the change in the maximum depth D as the measurement timing. However, the data acquisition unit 32 may also acquire drilling record data at regular intervals, using a fixed time interval as the measurement timing. The fixed time interval may be set to, for example, 10 seconds.

[0074] When acquiring drilling record data at regular intervals, the data acquisition unit 32 acquires the average value of the rotational torque measuring instrument 22 over the regular time period as the rotational torque T, and the average value of the indentation force measuring instrument 23 as the indentation force F. The data acquisition unit 32 also acquires a value based on the regular time period and the maximum depth D (= regular time period / change in maximum depth D over the regular time period) as the elapsed time t.

[0075] Furthermore, when excavation record data is acquired at regular intervals, if work such as extending the casing tube is performed, a large amount of excavation record data will be acquired around the depth at the time of that work. For this reason, it is preferable that the filtering unit 53, for example, if multiple excavation record data are acquired in a predetermined depth section (e.g., 0.1 m), set a threshold for the number of data points with elapsed time t in that depth section and perform filtering processing. [Explanation of symbols]

[0076] H10... Information processing device, H11... Communication device, H12... Input device, H13... Display device, H14... Memory device, H15... Processor, 10... Ground, 15... Full rotation drilling machine, 16... Base device, 17... Holding device, 18... Rotation mechanism, 19... Pushing mechanism, 20... Casing tube, 21... Power device, 22... Rotation torque measuring instrument, 23... Pushing force measuring instrument, 25... Displacement measuring instrument, 30... Support layer arrival judgment Fixed device, 31... Management unit, 31a... Memory, 32... Data acquisition unit, 33... N-value learning unit, 34... Soil type learning unit, 35... N-value estimation unit, 36... Soil type estimation unit, 41... Data storage unit, 42... N-value estimation model storage unit, 43... Soil type estimation model storage unit, 51... Measured value acquisition unit, 52... Elapsed time acquisition unit, 53... Filtering unit, 54... Cumulative torque calculation unit, 55... Average value calculation unit, 56... Standard deviation calculation unit.

Claims

1. A support device for reaching a support layer, which assists in determining whether excavation by an excavator has reached a support layer, A data acquisition unit acquires drilling record data consisting of the maximum drilling depth and a value related to the drilling resistance of the drilling machine at pre-set measurement timings. A storage unit that stores design soil data showing the relationship between depth and soil type based on the results of a ground investigation, and design N-value data showing the relationship between depth and N-value based on the results of the ground investigation, An N-value estimation unit calculates an estimated N-value using an N-value estimation model that includes the aforementioned excavation record data and the aforementioned design soil data as input elements. A soil type estimation unit that estimates soil type using a soil type estimation model that includes the excavation record data and the estimated N value as input elements, The system includes a display device that displays the design N-value based on the design N-value data, the estimated N-value, the design soil properties based on the design soil properties data, and the estimated soil properties estimated by the soil properties estimation unit, corresponding to the depth of excavation by the excavator. Support layer reaching support device.

2. The display device displays the design N value and the estimated N value superimposed on each other, and displays the design soil type and the estimated soil type side by side. The support layer reaching support device according to claim 1.

3. The data acquisition unit, A time acquisition unit that acquires the elapsed time required to excavate to a unit depth, The system includes a filtering unit that performs filtering processing based on the elapsed time, The elapsed time after the filtering process is obtained as a component of the excavation record data. The filtering unit is A reference elapsed time is set, and a predetermined section leading up to the maximum depth corresponding to the reference elapsed time is set as the condition setting section. An abnormal condition is set based on the median elapsed time in the aforementioned condition setting interval. If the aforementioned standard elapsed time satisfies the aforementioned abnormal conditions, the said standard elapsed time shall be removed as an abnormal value. The support layer reaching support device according to claim 1.

4. The filtering unit is The aforementioned reference elapsed time and the elapsed time before and after the aforementioned reference elapsed time are set as the time to be removed. The time period to be removed that satisfies the aforementioned abnormal conditions is removed as an abnormal value. The support layer reaching support device according to claim 3.

5. The aforementioned drilling machine is a full-circumference rotating drilling machine having a rotation mechanism for rotating the casing tube and a pushing mechanism for pushing the casing tube into the ground. The data acquisition unit, As values ​​relating to the excavation resistance of the excavator, the rotational torque of the rotating mechanism, the pushing force of the pushing mechanism, and the integrated torque based on the rotational torque are acquired at each measurement timing. For each of the rotational torque, the pushing force, and the integrated torque, the average value and standard deviation are obtained using the values ​​in a predetermined interval up to the maximum depth as the calculation target interval. A support layer reaching support device according to any one of claims 1 to 4.

6. A method for supporting the arrival of a supporting layer, which uses a supporting layer arrival support device to support the determination of whether the excavation by the excavator has reached the supporting layer, The aforementioned support layer reaching assistance device, A step of acquiring drilling record data consisting of the maximum drilling depth and a value related to the drilling resistance of the drilling machine at each predetermined measurement timing, A process for storing design soil data showing the relationship between depth and soil type based on the results of a ground investigation, and design N-value data showing the relationship between depth and N-value based on the results of the ground investigation, A step of calculating an estimated N-value using an N-value estimation model that includes the aforementioned excavation record data and the aforementioned design soil data as input elements, A step of estimating soil properties using a soil property estimation model that includes the aforementioned excavation record data and the estimated N-value as input elements, The process involves displaying the design N-value based on the design N-value data, the estimated N-value, the design soil properties based on the design soil properties data, and the estimated soil properties estimated using the soil property estimation model on a display device, corresponding to the depth of excavation by the excavator. How to support reaching your support base.

Images