Information processing method and drilling system

Abstract

To provide an information processing method or the like that supports an operator manipulating an excavator.SOLUTION: An information processing method includes obtaining observation data observed in excavation work with a jacking method, inputting obtained observation data to a model that outputs a prediction about the excavation work when inputting the observation data, and executing a processing to indicate information based on the prediction output from the model by a computer. The information processing method includes indicating an observation data obtained via a network and observed in excavation work with a jacking method, receiving directions for an excavator 50, and sending the directions to the excavator 50 via the network.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to an information processing method. Law and drilling systems. [Background technology]

[0002] Many of the lifelines, such as electricity, gas, water and sewerage, and communications, are supplied to consumers through underground pipes.

[0003] The pipe jacking method is used, in which an excavator is installed in the starting tunnel and a pipe is laid from the starting tunnel to form a pipeline (Patent Document 1). Because it is a trenchless construction method in which no excavation is required along the way, the construction area and noise are small, and the impact on the lives of nearby residents can be reduced. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Laid-Open No. 2015-166531 Summary of the Invention [Problem to be solved by the invention]

[0005] However, during excavation, obstacles such as hard rock or other buried pipelines may be encountered. With the jacking method, the operator cannot visually confirm the obstacles and must deal with them based on limited information such as sound and vibration. Therefore, to properly lay the jacking pipe according to the conditions at the construction site, the operator who operates the excavator needs sufficient knowledge and experience. However, there is a shortage of skilled operators.

[0006] In one aspect, an object of the present invention is to provide an information processing method and the like that supports an operator who operates an excavator. [Means for solving the problem]

[0007] The information processing method was based on the data observed during the excavation work using the jacking method. Includes data on drilling noise Observation data is acquired and input. Performed by the operator excavation Machine operation Output predictions for As shown above, the data was generated by machine learning using observation data on drilling operations that were successfully completed by skilled operators as training data. The acquired observation data is input into the model, and the output from the model is Excavator operation forecasts The computer executes a process for displaying the [Effects of the Invention]

[0008] In one aspect, an information processing method or the like can be provided that supports an operator who operates an excavator. [Brief explanation of the drawings]

[0009] [Figure 1] FIG. 2 is an explanatory diagram illustrating the configuration of the excavation system. [Figure 2] FIG. 2 is an explanatory diagram illustrating the configuration of the excavation system. [Figure 3] FIG. 2 is an explanatory diagram illustrating the configuration of an excavator. [Figure 4] FIG. 2 is an explanatory diagram illustrating the record layout of an excavation data DB. [Figure 5] 10 is a flowchart illustrating the flow of processing of a program. [Figure 6] 10 is a flowchart illustrating a process flow of a subroutine for determining abnormality. [Figure 7] 10 is an example of a screen displayed on a display unit. [Figure 8] 10 is an example of a screen displayed on a display unit. [Figure 9] FIG. 2 is an explanatory diagram illustrating the configuration of a learning model. [Figure 10] 10 is a flowchart illustrating the flow of program processing in the machine learning stage. [Figure 11] 10 is a flowchart illustrating the processing flow of the program at the stage of using the learning model. [Figure 12] 10 is an example of a screen displayed on a display unit according to the second embodiment. [Figure 13]11 is a flowchart illustrating the flow of processing of a program according to the third embodiment. [Figure 14] FIG. 10 is an explanatory diagram illustrating the configuration of an excavation system according to a fourth embodiment. [Figure 15] FIG. 10 is a functional block diagram of an excavation system according to a fifth embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0010] [Embodiment 1] 1 is an explanatory diagram illustrating the configuration of an excavation system 10. The excavation system 10 of this embodiment is a system for a jacking method that buries a jacking pipe 52 to form a pipeline while excavating horizontally or obliquely from a starting tunnel 19 that has been excavated in advance.

[0011] The excavation system 10 includes an excavation control device 40, an excavator 50, an external sensor 471, a surveying device 472, an information processing device 30, and a control panel 37. The excavator 50, the external sensor 471, and the surveying device 472 are connected to the excavation control device 40 via wires or wirelessly. The excavation control device 40 and the information processing device 30 are connected via a network.

[0012] The excavator 50 is equipped with an excavation head 51 and is installed inside the starting tunnel 19. The surveying device 472 is used to survey the direction of travel of the excavation head 51. Details of the information processing device 30, excavation control device 40, excavator 50 and surveying device 472 will be described later.

[0013] The control panel 37 is connected to the information processing device 30 via a wire or wirelessly. The control panel 37 has a display unit 371, a joystick 372, a control switch 373, etc. The control panel 37 is used when an operator operates the excavator 50. The control panel 37 has an appearance similar to that used when an operator operates the excavator 50 at a conventional excavation site. By using the control panel 37, the operator can operate the excavator 50 using the same operating procedures as those used at a conventional excavation site.

[0014] The external sensor 471 is a sensor that collects data related to the excavation situation, such as a microphone, a vibration sensor, a temperature sensor, and a ground displacement sensor. The external sensors 471 that collect various data are appropriately placed inside the starting tunnel 19, around the starting tunnel 19, on the ground near the excavation route, etc. The external sensor 471 may be a so-called IoT (Internet of Things) device that is directly connected to a network without going through the excavation control device 40.

[0015] Fig. 2 is an explanatory diagram illustrating the configuration of the excavation system 10. Fig. 2 shows the details of the configurations of the information processing device 30 and the excavation control device 40.

[0016] The information processing device 30 includes a control unit 31, a main memory device 32, an auxiliary memory device 33, a communication unit 34, an output unit 35, an input unit 36, a control panel I / F (Interface) 379, and a bus. The control unit 31 is an arithmetic and control device that executes the program of this embodiment. The control unit 31 uses one or more central processing units (CPUs), graphics processing units (GPUs), multi-core CPUs, or the like. The control unit 31 is connected to each hardware unit that constitutes the information processing device 30 via the bus.

[0017] The main memory device 32 is a storage device such as an SRAM (Static Random Access Memory), a DRAM (Dynamic Random Access Memory), a flash memory, etc. The main memory device 32 temporarily stores information required during processing performed by the control unit 31 and programs currently being executed by the control unit 31.

[0018] The auxiliary storage device 33 is a storage device such as an SRAM, a flash memory, a hard disk, or a magnetic tape. The auxiliary storage device 33 stores an excavation data DB (Database) 61, programs to be executed by the control unit 31, and various data required for executing the programs. The communication unit 34 is an interface for communication between the information processing device 30 and a network or other devices.

[0019] The output unit 35 includes a display unit 351 and a speaker 352. The display unit 351 is, for example, a liquid crystal display panel or an organic EL (electro-luminescence) panel. The display unit 351 may be a display device separate from the information processing device 30. The display unit 351 may be a wearable device such as an HMD (Head Mount Display). The speaker 352 may be headphones, earphones, or the like separate from the information processing device 30.

[0020] The input unit 36 ​​is an input device such as a keyboard and a mouse. The input unit 36 ​​and the display unit 351 may be stacked to form a touch panel. The control panel I / F 379 is an interface that connects the information processing device 30 and the control panel 37. The control panel I / F 379 is a general-purpose interface such as a USB (Universal Serial Bus).

[0021] The information processing device 30 is a general-purpose personal computer, tablet, smartphone, etc. used by an operator. The information processing device 30 may be configured by a combination of a mainframe computer, a virtual machine running on a mainframe computer, multiple personal computers performing distributed processing, or a cloud computing system and a terminal device.

[0022] The excavation control device 40 includes a control unit 41, a main memory device 42, an auxiliary memory device 43, a communication unit 44, an excavator I / F 46, a measurement I / F 47, and a bus. The control unit 41 uses one or more CPUs, GPUs, multi-core CPUs, etc. The control unit 41 is connected to each hardware unit that constitutes the excavation control device 40 via the bus.

[0023] The main memory device 42 is a memory device such as an SRAM, a DRAM, a flash memory, etc. The main memory device 42 temporarily stores information required during the processing performed by the control unit 41 and programs being executed by the control unit 41.

[0024] The auxiliary storage device 43 is a storage device such as an SRAM, a flash memory, a hard disk, or a magnetic tape. The auxiliary storage device 43 stores programs to be executed by the control unit 41 and various data required for executing the programs. The communication unit 44 is an interface that performs communication between the excavation control device 40 and a network.

[0025] The excavator I / F 46 is an interface that connects the excavation control device 40 and the excavator 50. The measurement I / F 47 is an interface that connects the surveying device 472 and the external sensor 471 with the excavation control device 40. The excavator I / F 46 and the measurement I / F 47 are general-purpose interfaces such as USB.

[0026] The excavation control device 40 is a general-purpose personal computer, a tablet, a smartphone, etc. The excavation control device 40 may be a control computer built into the excavator 50.

[0027] 3 is an explanatory diagram illustrating the configuration of excavator 50. In addition to the above-mentioned excavation head 51, excavator 50 has a rotating unit 55, an advancing / retreating unit 56, and an internal sensor 57. Rotating unit 55 and advancing / retreating unit 56 are, for example, hydraulically driven mechanisms.

[0028] The drilling head 51 is connected to the leading jacking pipe 52. Every time the drilling head 51 advances a distance corresponding to one jacking pipe 52, a new jacking pipe 52 is connected behind the rearmost jacking pipe 52. The process of connecting the jacking pipes 52 has been conventionally carried out in the jacking method, so a description thereof will be omitted. After the drilling head 51 reaches the destination hole, the drilling head 51 and the leading jacking pipe 52 are separated. In this way, a pipeline is formed.

[0029] Figures 1 and 3 show a schematic diagram of a drilling head 51 for the press-in method, which is suitable for excavating soft ground and relatively soft, normal ground. The tip of the drilling head 51 for the press-in method is a flat surface inclined with respect to the excavation direction, and receives pressure from the ground in the direction shown by the thick arrow in Figure 3. The operator can adjust the excavation direction by operating the rotating part 55 to rotate the drilling head 51 via the thrust pipe 52.

[0030] The internal sensor 57 is a sensor that detects the state of the excavator 50 and the buried thrust pipe 52, for example, the thrust force when the advance / retraction part 56 advances and retracts the excavation head 51, the rotational torque when the rotation part 55 rotates the excavation head 51, the distance advanced and retracted by the excavation head 51, the angle by which the excavation head 51 rotates, the power consumption of the excavator 50, and the vibration state of the excavation head 51.

[0031] A target object 473 is disposed at the rear end of the excavation head 51. The target object 473 is, for example, an LED (Light Emitting Diode) disposed at the center and periphery of the excavation head 51. The surveying device 472 is, for example, an electronic theodolite. The electronic theodolite is used for surveying with its optical axis facing the direction of the excavation target.

[0032] The electronic theodolite measures the traveling direction of the drilling head 51 based on the positional relationship between the optical axis and the target object 473. The traveling direction can be quantified, for example, by the distance that the target object 473, which is placed at the center of the drilling head 51, is shifted from the optical axis in the observation optical field of the electronic theodolite. The traveling direction may also be quantified by the angle of the traveling direction of the drilling head 51 with respect to the optical axis.

[0033] Instead of using the target body 473, the surveying device 472 may be an electronic theodolite of a type that irradiates a laser onto the rear end of the drilling head 51 and measures the direction of travel of the drilling head 51 based on the reflected light.

[0034] The surveying device 472 transmits the surveying results to the excavation control device 40. The surveying results may include an image of the target body 473.

[0035] 2, the explanation will be continued. The surveying results, the detection data by the internal sensor 57, and the detection data by the surveying device 472 are transmitted in real time via the network to the information processing device 30. The control unit 31 records the received data in the excavation data DB 61.

[0036] The control unit 31 displays the position of the target 473 photographed by the surveying device 472 and its relationship to the optical axis on the display unit 371. For example, the control unit 31 displays an image of the target 473 photographed by the surveying device 472 and characters indicating the orientation of the drilling head 51 on the display unit 371. The control unit 31 may reproduce the image of the target 473 based on the orientation of the drilling head 51 that was surveyed. The operator can intuitively grasp the orientation of the drilling head 51, i.e., changes in the orientation of the hole being drilled.

[0037] The control unit 31 displays various other data on the display unit 351 etc. Examples of screens displayed on the display unit 351 will be described later.

[0038] The control panel 37 outputs the audio data from the speaker 352. When multiple microphones are installed, it is desirable that the operator be able to select which microphone's audio is to be output from the speaker 352. The control unit 31 may also combine the audio from the multiple microphones and output it from the speaker 352.

[0039] The operator checks the survey data displayed on display unit 371, the audio output from speaker 352, the display on display unit 351, etc., and operates control switch 373. The operations performed by the operator are transmitted to excavation control device 40 via information processing device 30 and the network. Excavation control device 40 controls excavator 50 based on the operations performed by the operator.

[0040] If an abnormality occurs in the data, the control unit 31 notifies the operator of the abnormality or automatically stops excavation. For example, if the excavation head 51 hits another buried pipeline, hard rock, or a concrete structure, the direction of the excavation head 51 will change suddenly, and loud noises and vibrations will occur.

[0041] The operator checks the data and, if necessary, contacts the site supervisor or the like to ask for instructions. For example, if the site supervisor instructs the operator to continue moving the excavation head 51 forward and destroy the obstacle, the operator continues the excavation work. Similarly, if the site supervisor instructs the operator to go around the obstacle, the operator pulls back the excavation head 51, adjusts the excavation direction, and then resumes excavation.

[0042] Since the data on the excavation status is digitized, the operator can send the data to the site supervisor's smartphone or other information device as needed. This allows the operator and the site supervisor to share sufficient information, allowing the site supervisor to make accurate decisions based on accurate information.

[0043] As described above, the operator can operate the excavator 50 from his / her home, office, or the like, which is far from the excavation site. By using the excavation system 10 of this embodiment, the time required to travel to a distant excavation site can be saved, thereby ensuring that the operator has more time to work.

[0044] The operator may operate multiple excavators 50 in parallel. For example, when excavating multiple holes in parallel, there is a low possibility of encountering obstacles or other problems when excavating the second or subsequent holes. Therefore, the operator can operate excavators 50 at different excavation sites in parallel. This makes it possible to provide an excavation system 10 that allows one operator to be in charge of multiple sites simultaneously.

[0045] 4 is an explanatory diagram illustrating the record layout of the excavation data DB 61. The excavation data DB 61 is a DB that records various data measured by the external sensor 471, the surveying device 472, and the internal sensor 57 during excavation work, as well as the operation of the excavator 50 by the operator.

[0046] The excavation data DB 61 has an excavation ID (Identifier) ​​field, an operator ID field, a start date and time field, an excavation time field, a result field, an excavation head field, and an in-construction data field. The excavation data DB 61 has one record for each excavation. Figure 4 shows a schematic diagram of one record.

[0047] The drilling ID field records a drilling ID that is uniquely assigned to a hole drilled using the drilling system 10. The operator ID field records an operator ID that is uniquely assigned to an operator in charge of operating the drilling system 10. The start date and time field records the date and time that drilling started. The drilling time field records the time required for drilling.

[0048] The result field displays the excavation results. "Completed normally" indicates that excavation was completed normally as planned. For example, if excavation was stopped during excavation because it intersected with another buried pipeline, the result field will record the excavated distance and the reason why the operator or site supervisor decided to stop excavation, such as "Aborted due to intersection with other pipeline at ** meters."

[0049] The drilling head field records the type of drilling head 51. As mentioned above, when a drilling head 51 for the injection method is used, "for injection method" is recorded in the drilling head field. For example, when a drilling head 51 for the hydraulic balance method, which is suitable for water-retaining sand layers and hard ground, is used, "for hydraulic balance method" is recorded in the drilling head field.

[0050] Similarly, when a drilling head 51 for the percussion crushing method, which is suitable for gravel, boulders, and bedrock layers, is used, "for percussion crushing method" is recorded in the drilling head field. When a drilling head 51 for the single-pipe drilling method or the double-pipe drilling method, which is suitable for clayey soil, sandy soil, and gravel soil, is used, "for single-pipe drilling method" or "for double-pipe drilling method" is recorded in the drilling head field.

[0051] The data during construction field records various time-series data recorded during excavation work, such as thrust data, rotational torque data, measurement data, acoustic data, vibration data, operation data, video data, etc. The data recorded in the data during construction field is an example of observation data in this embodiment observed during excavation work.

[0052] 4 shows examples of thrust data and operation data. The thrust data is data that correlates the thrust distance of the excavation head 51 with the thrust applied by the advance / retract unit 56 when advancing the excavation head 51, and is recorded in, for example, a CSV (Comma Separated Value) format. The thrust distance is measured, for example, by the internal sensor 57.

[0053] Similarly, the operation data is data recorded in association with the advancement distance of the drilling head 51 and the operations performed by the operator using the control panel 37. "Start" indicates that the operator has performed an operation to start drilling. The advance / retract unit 56 applies a predetermined thrust to the drilling head 51 to move it forward. "Right" means that the operator has performed an operation to tilt the joystick 372 in the "right" direction. "Thrust down 10%" means that the operator has performed an operation to reduce the output of the advance / retract unit 56 by 10 percent. "Forward" means that the operator has performed an operation to tilt the joystick 372 in the "forward" direction.

[0054] Although examples of data will be omitted, the rotational torque data is data that associates the advancing distance of the drilling head 51 with the rotational torque applied to the drilling head 51 by the rotating unit 55. The surveying data is data that associates the advancing distance of the drilling head 51 with the drilling direction surveyed by the surveying device 472. These data may be recorded in association with time instead of advancing distance. Data that associates time with advancing distance may be recorded in the construction data field. Data that associates time with external pressure applied to each part of the construction pipe 52 may be recorded in the construction data field.

[0055] The acoustic data is audio data recorded via microphones appropriately placed in the starting tunnel 19, around the starting tunnel 19, and on the ground near the excavation route. Similarly, the vibration data is vibration data of the ground, the excavator 50, etc., recorded via appropriately placed vibration sensors.

[0056] Although not shown in the figure, the excavation data DB 61 also records ground displacement data that records ground displacement around the starting tunnel 19 and on the advancing route measured by a ground displacement sensor.

[0057] The excavation data DB 61 may have any field for recording information related to excavation work, such as a field for recording the model number and serial number of the excavation head 51, for example.

[0058] The items shown in Figure 4 are examples. For example, when excavation is performed using the hydraulic balance method, the pressure, amount, and temperature of the face water supplied to the excavation head 51, and the density of the excavated soil discharged from the excavator 50, etc. may be recorded in the data during construction field. When excavation is performed using the impact crushing method, the air pressure supplied to the excavator 50, the density of the excavated soil discharged from the excavator 50, or the particle size of the excavated soil, etc. may be recorded in the data during construction field. In addition, data according to the excavation method, the model of the excavation head 51, the model of the excavator 50, the purpose of excavation, the type of external sensor 471 that can be placed, etc. may be recorded in the data during construction field.

[0059] Fig. 5 is a flowchart explaining the flow of program processing. The program shown in Fig. 5 is executed after the completion of preparatory work such as excavating the starting tunnel 19, installing the excavator 50, and aligning the optical axis of the surveying device 472.

[0060] The control unit 31 transmits an instruction to prepare for startup to the excavation control device 40 (step S501). The control unit 41 receives the instruction (step S601). The control unit 41 transmits the construction data acquired from the internal sensor 57, the external sensor 471, and the surveying device 472, and data relating to the operating status of the excavator 50, to the information processing device 30 (step S602). By step S602, the control unit 41 realizes the function of the first transmission unit of this embodiment, which transmits data to the information processing device 30 via the network.

[0061] The control unit 31 receives the data (step S502). The control unit 31 starts an abnormality determination subroutine (step S503). The abnormality determination subroutine is a subroutine that determines whether or not there is an abnormality in the excavation state based on the data received from the excavation control device 40. The processing flow of the abnormality determination subroutine will be described later.

[0062] The control unit 31 outputs the data received in step S502 in a format that can be recognized by the operator (step S504). Specifically, the control unit 31 generates an image of the target 473 photographed by the surveying device 472 based on the surveying results, and displays it on the display unit 371. The control unit 31 outputs sound from the speaker 352 based on the sound data. The control unit 31 outputs a graph showing time-series changes in thrust, etc. to the display unit 351, as will be described later.

[0063] The control unit 31 receives instructions from the operator via the control panel 37 (step S505). The operator can use the joystick 372, control switches 373, etc. to give instructions using the same operating procedures as at an excavation site. If the operator does not perform any operation for a predetermined period of time, the control unit 31 determines that it has received an instruction to "not change the state of the excavator 50." In other words, for example, if the excavation work is to be continued under the current conditions, the operator does not need to operate the control panel 37.

[0064] The control unit 31 determines whether or not to end excavation (step S506). For example, if the operator operates a switch to instruct the end of excavation, the control unit 31 determines to end excavation. If it determines not to end excavation (NO in step S506), the control unit 31 transmits the operation content accepted from the user to the excavation control device 40 (step S507). In step S507, the control unit 31 realizes the function of the second transmission unit of this embodiment, which transmits data to the excavation control device 40 via the network. Thereafter, the control unit 31 returns to step S502.

[0065] The control unit 41 receives the operation content (step S611). The control unit 41 controls the excavator 50 to reflect the received operation content (step S612). The control unit 41 returns to step S602.

[0066] If it is determined that excavation should be ended (YES in step S506), the control unit 31 transmits an instruction to end excavation to the excavation control device 40 (step S508). The control unit 41 receives the instruction to end excavation (step S613). The control unit 41 stops the operation of the excavator 50 by a predetermined termination process (step S614). The control unit 41 transmits a message to the information processing device 30 that the operation of the excavator 50 has stopped (step S615).

[0067] The control unit 31 receives the notification that the operation of the excavator 50 has stopped (step S509). The control unit 31 displays on the display unit 351 that the operation of the excavator 50 has stopped (step S510). Thereafter, the control unit 31 ends the process.

[0068] 6 is a flowchart illustrating the flow of processing in the abnormality determination subroutine. The abnormality determination subroutine is a subroutine that determines whether or not there is an abnormality in the excavation state based on data received from excavation control device 40.

[0069] The control unit 31 determines whether the thrust of the excavator 50 is within a predetermined normal range based on the data received from the excavation control device 40 (step S531). If it is determined that the thrust is outside the range (NO in step S531), the control unit 31 determines that there is an abnormality in the thrust of the excavator 50, and temporarily stores this in the main memory device 32 or the auxiliary memory device 33 (step S541).

[0070] If it is determined that the rotational torque is within the normal range (YES in step S531), or after step S541 is completed, the control unit 31 determines whether the rotational torque of the excavator 50 is within a predetermined normal range based on the data received from the excavation control device 40 (step S532). If it is determined that the rotational torque is outside the range (NO in step S532), the control unit 31 determines that there is an abnormality in the rotational torque of the excavator 50, and temporarily stores this in the main memory device 32 or the auxiliary memory device 33 (step S542).

[0071] If it is determined that the direction of travel of the drilling head 51 is within the normal range (YES in step S532), or after step S542 is completed, the control unit 31 determines whether the direction of travel of the drilling head 51 is within a predetermined normal range based on the data received from the drilling control device 40 (step S533). If it is determined that the direction of travel of the drilling head 51 is outside the range (NO in step S533), the control unit 31 determines that there is an abnormality in the direction of travel of the drilling head 51, and temporarily stores this in the main memory device 32 or the auxiliary memory device 33 (step S543).

[0072] If it is determined to be within the normal range (YES in step S533), or after step S543 is completed, the control unit 31 performs frequency analysis of the vibration data based on the data received from the excavation control device 40, and calculates the frequency characteristics (step S534). Since frequency analysis algorithms such as FFT (Fast Fourier Transform) are commonly used, detailed explanations will be omitted.

[0073] The control unit 31 performs pattern matching between the frequency characteristics calculated in step S534 and frequency characteristics of vibration data measured in advance for various grounds, and extracts grounds showing similar frequency characteristics (step S535). Examples of grounds include "clayey soil," "soft ground," "rock," "concrete," and "buried pipelines."

[0074] The control unit 31 performs frequency analysis of the acoustic data based on the data received from the excavation control device 40, and calculates the frequency characteristics (step S536). The control unit 31 performs pattern matching between the frequency characteristics calculated in step S536 and frequency characteristics of acoustic data measured in advance for various grounds, and extracts grounds showing similar frequency characteristics (step S537). Thereafter, the control unit 31 ends the process.

[0075] 7 and 8 are examples of screens displayed on display unit 351. Control unit 31 outputs the screen of Fig. 7 or 8 to display unit 351 in step S504 of the program described using Fig. 5.

[0076] Figure 7 shows an example where there are no abnormalities in the excavation status. On the left side of the screen, a construction conditions column 71, a management conditions column 72, an operating status column 73, and an observation data column 74 are displayed. On the right side of the screen, a thrust force graph column 751, a rotational torque graph column 752, and a direction graph column 753 are displayed.

[0077] The construction conditions determined when the construction plan was created are displayed in the construction conditions column 71. The management conditions determined when the construction plan was created are displayed in the management conditions column 72. The construction conditions and management conditions are acquired from a database or the like in which the construction plan is recorded.

[0078] The operating status field 73 displays the operating status of the excavator 50 in real time. The observation data field 74 displays a vibration data field 741, an acoustic data field 742, and a notification field 748. The vibration data field 741 briefly displays points that the operator should pay attention to, which have been determined based on the vibration data from the observation data acquired from the excavation control device 40 in step S502 described using Fig. 5. Similarly, the acoustic data field 742 briefly displays points that the operator should pay attention to, which have been determined based on the acoustic data.

[0079] The presence or absence of an abnormality in the observation data is simply displayed in the notification field 748. Fig. 7 shows an example in which it is determined that there is no abnormality in any of steps S531 to S533, S535, and S537 described using Fig. 6.

[0080] The horizontal axis of the thrust graph field 751 is the thrust distance of the excavation head 51. The unit of the horizontal axis is meters. The minimum value on the horizontal axis is 0 meters, and the maximum value on the horizontal axis is the planned excavation distance.

[0081] The vertical axis of the thrust graph field 751 is the thrust applied to the drilling head 51. The unit of the vertical axis is kilonewtons. The dashed line indicates the reference value of the thrust. If the thrust exceeds the reference value, it is determined that there is an abnormality. The solid line indicates the actual measured value of the thrust.

[0082] The horizontal axis of the rotational torque graph field 752 is the same as the horizontal axis of the thrust graph field 751. The vertical axis of the rotational torque graph field 752 is the rotational torque applied to the drilling head 51. The unit of the vertical axis is kilonewton meters. The dashed line indicates the reference value of the rotational torque. If the rotational torque exceeds the reference value, it is determined that there is an abnormality. The solid line indicates the actual measured value of the rotational torque.

[0083] The horizontal axis of the direction graph field 753 is the same as the horizontal axis of the thrust graph field 751. The vertical axis of the direction graph field 753 is the distance that the target 473 placed at the center of the drilling head 51 is shifted from the optical axis. The vertical axis is in centimeters. The dashed line indicates the reference distance value. If the distance exceeds the reference value on either the positive or negative side, it is determined that there is an abnormality. The thin solid line indicates the actual measured value in the left-right direction. The thick solid line indicates the actual measured value in the up-down direction.

[0084] The operator can grasp the chronological changes in the excavation situation from the start of excavation to the present time from the thrust graph field 751, the rotational torque graph field 752, and the direction graph field 753. The operator controls the excavator 50 while checking this information displayed on the screen.

[0085] FIG. 8 is an example of a screen that the control unit 31 displays on the display unit 351 when an abnormality occurs in the vibration data and the acoustic data. FIG. 8 shows a case where the drilling head 51 comes into contact with concrete. A concrete pattern is detected in both the vibration data and the acoustic data. A notice that an abnormality has occurred is displayed in the notification field 748. The control unit 31 may also alert the operator by sounding an alarm, flashing the screen, or the like.

[0086] The operator takes action such as bringing the excavator 50 to an emergency stop, and considers what measures to take afterwards. Note that the screens shown in Figures 7 and 8 are examples. The displayed items and layout are not limited to those shown in Figures 7 and 8.

[0087] In excavation work using the jacking method, even if the operator is at the excavation site, he or she cannot directly check the condition of the excavation head 51 or the condition of the ground being excavated. On the other hand, if a sufficient number of external sensors 471 and internal sensors 57 are appropriately arranged and a communication line of sufficient quality is secured, the operator can obtain detailed information about the excavation condition by using the excavation system 10 of this embodiment.

[0088] Therefore, by using the excavation system 10 of this embodiment, the operator can make appropriate decisions based on detailed information and carry out excavation work, whether he is at the excavation site or at a location away from the excavation site.

[0089] The output unit 35 may include a BodySonic chair. The control unit 31 vibrates the BodySonic chair based on the vibration data, allowing the seated operator to physically grasp the vibration data using their entire body.

[0090] The output unit 35 and the input unit 36 ​​may be used instead of the control panel 37. The operator can operate the excavator 50 using general hardware such as a general-purpose personal computer and software for controlling the excavator 50, without preparing any special hardware.

[0091] According to this embodiment, it is possible to provide an excavation system 10 that allows an operator to operate an excavator 50 from home, an office, or the like. Since the time spent traveling to a distant excavation site is saved, the operator's actual working hours can be extended. Since the operator can work from an air-conditioned home or office, etc., the working conditions of the operator can be improved. As described above, the excavation system 10 of this embodiment can contribute to resolving the shortage of operators.

[0092] Once they have mastered the excavation techniques, even operators who have difficulty working at excavation sites due to a disability, childcare or nursing care, etc., can operate the excavator 50. Therefore, the excavation system 10 of this embodiment can contribute to creating employment opportunities for people with disabilities, improving work-life balance, and eliminating the gender gap, thereby contributing to solving various social problems.

[0093] According to this embodiment, for example, when multiple microphones are arranged, the operator can switch between the microphones that listen to the acoustic data as needed. For example, when an abnormal sound is occurring, the operator can switch between the microphones arranged along the excavation path in order and check the sound at each position, thereby properly grasping the condition of the excavator 50.

[0094] According to this embodiment, when a plurality of data such as thrust data collected during excavation exceed predetermined thresholds, the control unit 31 displays the data on the display unit 351 to attract the operator's attention. Furthermore, the control unit 31 displays time-series changes in the state of the excavator 50 using graphs such as the thrust graph field 751. In this way, an excavation system 10 can be provided that supports the operator's judgment.

[0095] A plurality of information processing devices 30 may be connected to a network. For example, when an inexperienced operator is in charge of excavation work using one information processing device 30, a skilled operator can use another information processing device 30 to observe the state of the work and provide guidance as necessary. Conversely, a plurality of operators in training can each use an information processing device 30 to observe the state of the work performed by a skilled operator during excavation work. Therefore, it is possible to provide an excavation system 10 that is useful for on-the-job training (OJT) of operators and contributes to resolving labor shortages.

[0096] According to this embodiment, the information that the operator uses to grasp the status of the excavator 50 during excavation work and the operations performed by the operator are all electronically transmitted via a network, making it possible to provide an excavation system 10 that can electronically record all information related to the progress of excavation work.

[0097] For example, if a sudden problem occurs, the control unit 31 may extract information from the electronically recorded information immediately before the problem occurred and present it to the operator. By reconfirming the conditions before and at the time of the problem, the operator can properly estimate the cause of the problem and plan countermeasures. Other examples of how to utilize electronically recorded information will be described later.

[0098] The external sensor 471 may include a camera disposed as appropriate, and the data during construction may include video data recorded via the camera. An excavation system 10 can be provided that appropriately records the construction status of excavation work. If the capacity of the communication line is insufficient, the control unit 41 may temporarily record the video data in the auxiliary storage device 43 and transmit it to the information processing device 30 after excavation is completed.

[0099] [Embodiment 2] This embodiment relates to an excavation system 10 that supports an operator using a learning model 65. Explanation of parts common to the first embodiment will be omitted.

[0100] 9 is an explanatory diagram illustrating the configuration of the learning model 65. The learning model 65 is a model that receives input of in-construction data and the like received from the excavation control device 40 up to now, and outputs a prediction regarding the next operation that the operator will perform.

[0101] The input data input to the learning model 65 is, for example, the thrust data, rotational torque data, survey data, acoustic data, vibration data, and operation data described using FIG. 4. The input data may be a portion of the data listed above. The input data may also include the results of a ground survey at the excavation site. The learning model 65 is stored in the auxiliary storage device 33 or an external mass storage device connected to the information processing device 30.

[0102] In the example shown in Figure 9, there is an 80 percent probability that the operator will not operate the excavator 50 and will continue excavating as is, a 2% probability that the operator will operate to turn the excavation head 51 to the right, a 1% probability that the operator will operate to move the excavation head 51 backward, and a 1% probability that the operator will press the emergency stop button.

[0103] The training data used to generate the learning model 65 is data relating to excavations that were "successfully completed" by, for example, an experienced operator, among data previously recorded in the excavation data DB 61. The learning model 65 is created using any machine learning method suitable for predicting time-series data, such as a recurrent neural network (RNN) or a long short-term memory (LSTM).

[0104] The learning model 65 may be created using any machine learning method, such as a convolutional neural network (CNN) or a random forest, etc. The learning model 65 may also be created by reinforcement learning, which determines a reward based on the excavation time.

[0105] The learning model 65 is generated for each type of excavation head 51, such as for the press-in method or the hydraulic balance method. The learning model 65 may be generated for each type of excavation head 51. The learning model 65 may be generated for each type of soil to be excavated. The learning model 65 may further be generated for each depth to which the propulsion pipe 52 is buried. The control unit 41 selects and uses the learning model 65 that corresponds to the conditions of the excavation work.

[0106] Figure 10 is a flowchart illustrating the flow of program processing in the machine learning stage. In the following explanation, an example will be described in which the information processing device 30 is used to generate a learning model 65. The program in Figure 10 may be executed on hardware separate from the information processing device 30, and the learning model 65 after machine learning has been completed may be copied to the auxiliary storage device 33 via a network. A learning model 65 trained on one piece of hardware can be used by multiple information processing devices 30.

[0107] Before executing the program in Fig. 10, an untrained learning model 65 such as an RNN or LSTM is prepared. The program in Fig. 10 adjusts each parameter of the prepared learning model 65, and machine learning is performed.

[0108] A training data DB is constructed by extracting records that meet certain conditions from the excavation data DB 61. The configuration of the training data DB is the same as that of the excavation data DB 61. In the following description, the records recorded in the training data DB will be referred to as training records. Note that a training data DB having a large number of training records can be created by creating a training data DB using the excavation data DB 61 in which data is recorded in each of multiple information processing devices 30.

[0109] The control unit 31 acquires training records to be used for training one epoch from the training data DB (step S551). The number of training records to be used for training one epoch is a so-called hyperparameter, and is determined appropriately.

[0110] The control unit 31 adjusts the parameters of the model so that when construction data up until the drilling head 51 advances to a certain position is input into the input layer of the learning model 65, the next operation performed by the operator is output from the output layer (step S552).

[0111] The control unit 31 determines whether to end the process (step S553). For example, the control unit 31 determines to end the process when learning for a predetermined number of epochs has been completed. The control unit 31 may acquire test data from the training data DB, input it to the model under machine learning, and determine to end the process when an output with a predetermined accuracy is obtained.

[0112] If it is determined not to end the process (NO in step S553), the control unit 31 returns to step S551. If it is determined to end the process (YES in step S553), the control unit 31 records the parameters of the trained model in the auxiliary storage device 33 (step S554). Thereafter, the control unit 31 ends the process. Through the above process, machine learning of the learning model 65 is completed.

[0113] 11 is a flowchart illustrating the flow of program processing in the use stage of the learning model 65. The program in FIG. 11 is used during excavation work in place of the program of the first embodiment described using FIG. 5.

[0114] The processing up to step S502 is the same as the processing flow of the program in embodiment 1 explained using Fig. 5, and therefore will not be explained further. The control unit 31 selects a learning model 65 corresponding to the excavation head 51 in use. The control unit 31 inputs the in-use data received in step S502 from the start of excavation to that point into the selected learning model 65, and obtains a prediction of the next operation to be performed by the operator (step S561).

[0115] The control unit 31 outputs the data received in step S502 and the prediction obtained in step S561 in a format that can be recognized by the operator (step S562). The control unit 31 accepts an operation by the operator via the control panel 37 (step S505). The subsequent processing is the same as the processing flow of the program in the first embodiment described using FIG. 5, and therefore description thereof will be omitted.

[0116] Fig. 12 is an example of a screen displayed on the display unit 351 in the second embodiment. The control unit 31 outputs the screen shown in Fig. 11 in step S562 of the program described using Fig. 11. The basic configuration of the screen shown in Fig. 12 is the same as that of Figs. 7 and 8, with a recommended operation column 76 added to the operating status column 73. The recommended operation column 76 displays the "right" operation acquired from the learning model 65, indicating that a skilled operator would likely perform an operation to turn the drilling head 51 to the right.

[0117] The control unit 31 may determine the display mode of the recommended operation field 76 based on the probability described with reference to Fig. 9. For example, the control unit 31 displays the recommended operation field 76 in large characters when the probability is high, and displays the recommended operation field 76 in small characters when the probability is low. When the learning model 65 outputs probabilities of the same degree for multiple operations, the control unit 31 may display multiple operations in the recommended operation field 76.

[0118] According to this embodiment, it is possible to provide an excavation system 10 that supports an operator by constantly presenting predictions regarding operations that a skilled operator will perform.

[0119] The information processing device 30 may be placed at the excavation site, and an operator may operate the excavator 50 at the excavation site. When the information processing device 30 is placed at the excavation site, the information processing device 30 and the excavation control device 40 may be connected by wire.

[0120] [Embodiment 3] This embodiment relates to an excavation system 10 that performs automatic excavation using a learning model 65 that has been trained to output predictions with sufficiently high reliability. Explanation of parts common to embodiment 2 will be omitted.

[0121] 13 is a flowchart illustrating the processing flow of the program according to embodiment 3. The processing up to step S502 is the same as the processing flow of the program according to embodiment 1 described using FIG. 5, and therefore the description thereof will be omitted.

[0122] The control unit 31 determines whether the scheduled excavation has been completed (step S571). Specifically, when the propulsion distance included in the data received in step S502 reaches the planned distance, the control unit 31 determines that the excavation has been completed.

[0123] If it is determined that the excavation has ended (YES in step S571), the control unit 31 transmits an instruction to end the excavation to the excavation control device 40 (step S508). The subsequent processing is the same as the processing of the program in the first embodiment described using Fig. 5, and therefore description thereof will be omitted.

[0124] If it is determined that the excavation has not ended (NO in step S571), the control unit 31 inputs the construction data received in step S502 from the start of excavation to that point into the learning model 65, and obtains a prediction of the next operation that the operator will perform (step S572).

[0125] The control unit 31 determines whether the prediction acquired in step S572 is to stop the excavator 50 (step S573). If it is determined that the excavator 50 will stop (YES in step S573), the control unit 31 notifies the operator that the excavator 50 will stop even though excavation has not been completed (step S574). The notification can be made by any means, such as an alarm sound, a flashing screen, or sending a message to a smartphone carried by the operator.

[0126] If it is determined that the excavation control device 40 is not stopped (NO in step S573), or after step S574 ends, the information processing device 30 transmits the operation acquired in step S572 to the excavation control device 40 (step S575). After that, the control unit 31 returns to step S502.

[0127] The control unit 41 receives the operation content (step S611). The subsequent processing is the same as the processing of the program in the first embodiment described with reference to FIG. 5, and therefore a description thereof will be omitted.

[0128] According to this embodiment, it is possible to provide an excavation system 10 that automatically performs excavation using the learning model 65. For example, it is possible to provide an excavation system 10 that automatically stops the excavator 50 and notifies the operator in an irregular situation, such as when the excavation head 51 hits another buried pipeline, hard rock, or a concrete structure.

[0129] [Embodiment 4] This embodiment relates to a form in which the excavation system 10 of this embodiment is realized by operating a general-purpose computer 90 in combination with a program 97. Fig. 14 is an explanatory diagram showing the configuration of the excavation system 10 of embodiment 4. Explanation of parts common to embodiment 1 will be omitted.

[0130] The excavation system 10 of this embodiment includes a computer 90 instead of the information processing device 30. The computer 90 includes a control unit 31, a main memory device 32, an auxiliary memory device 33, a communication unit 34, an output unit 35, an input unit 36, a control panel I / F 379, a reading unit 39, and a bus. The computer 90 is an information device such as a general-purpose personal computer, a tablet, or a server computer.

[0131] The program 97 is recorded on a portable recording medium 96. The control unit 31 reads the program 97 via the reading unit 39 and stores it in the auxiliary storage device 33. The control unit 31 may also read the program 97 stored in a semiconductor memory 98, such as a flash memory, implemented in the computer 90. Furthermore, the control unit 31 may download the program 97 from another server computer (not shown) connected via the communication unit 34 and a network (not shown) and store it in the auxiliary storage device 33.

[0132] Of the program 97, the portion executed by the control unit 31 is installed as a control program of the computer 90, and is loaded into the main memory device 32 and executed. Of the program 97, the portion executed by the control unit 41 is transmitted to the excavation control device 40 via the network and stored in the auxiliary memory device 43 of the excavation control device 40. The stored program is installed as a control program of the excavation control device 40, and is loaded into the main memory device 42 and executed.

[0133] As described above, the computer 90 and the excavation control device 40 cooperate to function as the excavation system 10 described above.

[0134] [Embodiment 5] 15 is a functional block diagram of an excavation system 10 according to a fifth embodiment. The excavation system 10 includes an excavator 50 for jacking, an excavation control device 40, and an information processing device 30. The excavation control device 40 includes an acquisition unit 83 and a first transmission unit 81. The information processing device 30 includes a display unit 84, a reception unit 85, and a second transmission unit 82.

[0135] The acquisition unit 83 acquires observation data observed during excavation work by the excavator 50. The first transmission unit 81 transmits the observation data to the information processing device 30 via the network. The display unit 84 displays the observation data. The reception unit 85 receives instructions for the excavator 50. The second transmission unit 82 transmits the instructions to the excavation control device 40 via the network. The excavation control device 40 controls the excavator 50 based on the instructions.

[0136] The technical features (constituent elements) described in each embodiment can be combined with each other, and by combining them, new technical features can be formed. The embodiments disclosed herein are illustrative in all respects and should not be considered as limiting. The scope of the present invention is defined by the claims, not by the above meaning, and is intended to include all modifications within the meaning and scope of the claims. [Explanation of symbols]

[0137] 10. Drilling System 19 Departure shaft 30 Information processing equipment 31 Control Unit 32 Main storage 33 Auxiliary storage device 34 Communications Department 35 Output section 351 Display section 352 Speaker 36 Input section 37 Control Panel 371 Display section 372 Joystick 373 Control Switch 379 Control Panel I / F 39 Reading unit 40 Excavation control device 41 Control Unit 42 Main storage 43 Auxiliary storage device 44 Communications Department 46 Excavator I / F 47 Measurement I / F 471 External Sensor 472 Surveying equipment 473 Target body 50 Excavator 51 Drilling Head 52 Propulsion tube 55 Rotating part 56 Advancement and retreat section 57 Internal Sensor 61 Drilling Data DB 65 Learning Model 71 Construction conditions column 72 Management conditions column 73 Operation status column 74 Observation data column 741 Vibration Data Column 742 Acoustic Data Column 748 Notification column 751 Thrust graph column 752 Rotational torque graph column 753 Directional Graph Column 76 Recommended operations column 81 First Transmission Unit 82 Second Transmission Unit 83 Acquisition Department 84 Display section 85 Reception 90 Computer 96 Portable recording media 97 Programs 98 Semiconductor Memory

Claims

1. Obtaining observation data including data on sounds of excavation operations observed during excavation operations using a jacking method; The acquired observation data is input into a model generated by machine learning using observation data relating to excavation operations that have been successfully completed by skilled operators as training data, so that a prediction regarding the operation of the excavator performed by the operator is output when the observation data is input, and a prediction regarding the operation of the excavator is output from the model. An information processing method in which processing is performed by a computer.

2. The observation data includes data regarding the orientation of the hole during drilling. The information processing method according to claim 1 .

3. Get information about the drilling head in use, Selecting one model based on the acquired information from among multiple models generated by machine learning using observation data relating to excavation operations that have been successfully completed by skilled operators as training data, so that a prediction regarding the operation of the excavator performed by the operator when the observation data is input, Input the acquired observation data into the selected model and display the predictions regarding the operation of the excavator output from the model.

3. The information processing method according to claim 1.

4. Based on the acquired observation data, the relationship between the thrust distance of the excavation work and the thrust force during excavation is displayed.

4. The information processing method according to claim 1.

5. displaying observation data obtained via the network, including data on sounds of excavation work observed during excavation work using the jacking method; inputting the acquired observation data into a model generated by machine learning using, as training data, observation data relating to excavation operations that have been successfully completed by an experienced operator, so that a prediction relating to the operation of the excavator performed by the operator when the observation data is input is output; and displaying the prediction relating to the operation of the excavator output from the model; Accepts instructions for the excavator, Transmitting the instructions to the excavator via a network. An information processing method in which processing is performed by a computer.

6. Based on the observation data, it is determined whether or not there is an abnormality in the excavation work. The information processing method according to claim 5 .

7. If it is determined that there is an abnormality in the excavation work, information about the abnormality is displayed. The information processing method according to claim 6.

8. The observation data includes data regarding the orientation of the hole during drilling.

8. The information processing method according to claim 5.

9. An excavation system including an excavator for a jacking method, an excavation control device, and an information processing device, The excavation control device includes: an acquisition unit that acquires observation data including data related to excavation operation sounds observed during excavation operation by the excavator; a first transmission unit that transmits the observation data to an information processing device via a network; The information processing device includes: a display unit that displays the observation data; a prediction display unit that inputs the acquired observation data into a model generated by machine learning using, as training data, observation data relating to excavation that has been carried out by an experienced operator and completed successfully, so as to output a prediction relating to the operation of the excavator performed by the operator when the observation data is input, and displays a prediction relating to the operation of the excavator output from the model; a reception unit that receives instructions for the excavator; a second transmitting unit that transmits the instruction to the excavation control device via a network; The excavation control device controls the excavator based on the instruction. Drilling system.

Images