JP2023151277A - Construction method of rubble mound - Google Patents

Abstract

To calculate an appropriate height for dropping a weight during leveling construction of a rubble mound.SOLUTION: Measured value acquisition means 111 acquires a measured value of a height of a top surface 30 of a rubble mound 3 before tamping, and a measured value of the displacement amount of the height of the rubble mound 3 after tamping. Teacher data generating means 112 generates first teacher data 121 by specifying or calculating an explanatory variable and a target variable from the conditions of the executed tamping and the acquired measurement values. Learning model construction means 113 uses the generated first teacher data 121 to calculate a group of parameters for deriving the objective variable from the explanatory variables, and constructs a first learning model 122 using these. Fall height estimating means 114 estimates, based on the constructed first learning model 122, the height at which the weight 212 should be lifted and dropped in the next instructed tamping. Display control means 115 instructs a display unit 15 to display an estimated value of a fall height.SELECTED DRAWING: Figure 11

Description

The present invention relates to a method for constructing a rubble mound.

In order to install a bank protection caisson (concrete block) horizontally, it is necessary to level the rubble mound that serves as the foundation approximately evenly to a specified height (design height) before installation. Leveling methods include the roller compaction method, the weight method, the hydraulic hammer method, and the vibrohammer method, but currently, compaction using the weight method, hydraulic hammer method, and vibrohammer method is the main method.

Compaction using a weight is a method in which a weight is dropped freely from a predetermined height and the impact energy is used to compact the rubble in the rubble mound.

Patent Document 1 discloses that in order to bring the top surface of the rubble mound close to the design height, the height of the top surface of the rubble mound is obtained by measuring the height direction position of a weight after falling onto the rubble mound. It is stated that

Japanese Patent Application Publication No. 10-152839

For example, in order to further displace (sink) the height of the top surface of the rubble mound, a weight may be dropped from a higher position. However, if it is dropped from an unnecessarily high position, the height of the top surface will be displaced to a position lower than the design height. Once it is displaced to a position lower than the design height, the height of the top surface cannot be easily returned to its original height, and the construction work will have to be reworked considerably. Additionally, if the weight is dropped from a relatively low position, the rubble mound will not be displaced, and in order to adjust the height of the top surface to the design height, many drops will be required, reducing construction efficiency. . For efficient construction, it is necessary to compact the rubble mound firmly to a leveled surface that is the design height with as few falls as possible, but it is necessary to measure the current height of the top surface of the rubble mound. Even if the difference from the design height can be recognized, it is up to the operator to decide from what height the weight should be dropped in order to obtain the amount of displacement that will bring the current height closer to the design height. We have no choice but to rely on empirical rules such as Furthermore, when a certain section of the top surface of a rubble mound is struck, the amount of height displacement due to the strike may differ depending on whether or not the surrounding sections have already been struck.

In view of the above-mentioned background, the present invention provides a means for calculating an appropriate height to drop a weight in leveling work of a rubble mound without relying on an operator's empirical rules.

The construction method according to claim 1 of the present invention includes the step of measuring the height of the top surface of the rubble mound before striking with a weight, for each of a plurality of sections obtained by dividing the top surface of the rubble mound. and a step of dropping the weight from a set height and hitting each of the plurality of sections multiple times, and measuring the amount of displacement in the height of the rubble mound due to the hitting; calculating, for each of the plurality of sections and the entire area of the top surface, a ratio of the displacement amount to the square root of the product of the height at which the object is dropped and the number of times the object is dropped; In the entire area, the height at which the weight was dropped, the number of times, the previous displacement indicating the amount of displacement in the height of the rubble mound due to the previous strike, and the height of the rubble mound due to the previous strike. a step of constructing a first learning model using the cumulative amount of displacement up to the previous time indicating the cumulative amount of displacement and training data using the ratio as an explanatory variable and the amount of displacement as an objective variable; and using the first learning model. a step of estimating the height at which the weight is to be dropped with respect to the rubble mound; and a step of dropping the weight from the height estimated in the estimating step, and touching the top surface of the rubble mound with the weight. A method for constructing a rubble mound, which includes a step for pounding.

In the construction method according to claim 2 of the present invention, in the step of calculating the ratio, the ratio of the entire area is an arithmetic mean value, a mode value, a median value of all the ratios of the plurality of sections, The method for constructing a rubble mound according to claim 1, wherein the value is either a geometric mean value or a maximum value.

In the construction method according to claim 3 of the present invention, in addition to each of the plurality of sections and the entire area, the step of calculating the ratio includes moving and dropping a weight among the plurality of sections. This is a step of calculating the ratio for each group consisting of the above sections, and the step of constructing includes the height at which the weight was dropped, the number of times, and the previous time for the section, the group, and the entire area. 3. The step of constructing the first learning model using training data in which the amount of displacement, the cumulative amount of displacement up to the previous time, and the ratio are used as explanatory variables, and the amount of displacement is used as a target variable. This is a method of constructing a rubble mound.

In the construction method according to claim 4 of the present invention, in the step of calculating the ratio, the ratio of the group is an arithmetic mean value, a mode value, a median value of the ratios of all sections belonging to the group, 4. The method for constructing a rubble mound according to claim 3, wherein the value is either a geometric mean value or a maximum value.

In the construction method according to claim 5 of the present invention, the height at which the weight is dropped, the number of times, the previous displacement amount, the cumulative displacement amount up to the previous time, and the a step of constructing a second learning model using training data in which the ratio is an explanatory variable and the displacement amount of a section different from the section in which the weight is dropped is an objective variable; A claim comprising the steps of calculating the amount of displacement of another section caused by dropping the weight into a certain section of a plurality of sections, and notifying the calculated amount of displacement of the other section. A method for constructing a rubble mound according to any one of Items 1 to 4.

The construction method according to claim 6 of the present invention uses the first learning model to determine whether a state in which the displacement amount due to dropping the weight is less than a threshold value occurs in any of the plurality of sections. a step of predicting whether the amount of displacement is less than the threshold; and a step of notifying that the amount of displacement is predicted to be less than the threshold; The method for constructing a rubble mound according to any one of claims 1 to 5, further comprising the step of comparing the height with the height of the ripple mound.

In the construction method according to claim 7 of the present invention, the second learning model is used to drop the weight into any of the plurality of divisions so that the displacement amount of the other division is less than a threshold value. a step of predicting whether a state in which the amount of displacement of the other section is less than the threshold value is predicted; and a step of notifying that the amount of displacement of the other section is predicted to be less than the threshold value. 6. The method for constructing a rubble mound according to claim 5, further comprising the step of comparing the top surface of the rubble mound predicted to be in a state where the height is less than a predetermined height with a predetermined height.

In the construction method according to claim 8 of the present invention, the step of measuring the displacement amount of the height of the rubble mound due to the striking uses depths of at least three points on the upper surface of the weight measured by a measuring device. A method for constructing a rubble mound according to any one of Items 1 to 7.

According to the present invention, it is possible to calculate an appropriate height for dropping a weight during leveling construction of a rubble mound.

The figure which showed the state in which the top end surface 30 of the rubble mound 3 is leveled by the construction method M. A top view of leveling machine 2. FIG. 2 is a diagram showing an example of the configuration of a leveling machine 2. FIG. The figure which shows the example of the structure of the striking machine 21. The figure which shows the example of the leveling height sensor 23 lined up in the width direction. A diagram showing an example of a leveling frame R. 1 is a diagram showing an example of the configuration of a learning device 1. FIG. FIG. 3 is a diagram showing an example of first teacher data 121. FIG. 4 is a diagram showing an example of the configuration of a control device 4. FIG. FIG. 5 is a diagram showing an example of a configuration of a management device 5. FIG. 1 is a diagram showing an example of a functional configuration of a learning device 1. FIG. FIG. 3 is a flow diagram showing an example of the processing flow of construction method M. FIG. 3 is a diagram showing the state before the leveling machine 2 levels the top surface 30. FIG. 3 is a diagram showing how the leveling machine 2 performs rake leveling. FIG. 3 is a flow diagram showing an example of the process flow of weight leveling. FIG. 7 is a diagram showing the state before the top surface 30 is struck by the weight 212; FIG. 7 is a diagram showing the state after the top surface 30 is struck by the weight 212; The figure which shows the example of a structure of the learning device 1 in a modification. The figure which shows the example of the 2nd teacher data 123 in a modification. The figure which shows the example of the functional structure of the learning device 1 in a modification. The figure which shows the example of the functional structure of the learning device 1 in a modification.

<Embodiment>
<Overall configuration>
Below, a method M for constructing the top surface of a rubble mound according to an embodiment of the present invention will be described. FIG. 1 is a diagram showing a state in which the top end surface 30 of the rubble mound 3 is leveled by the construction method M. In the following description, directions in the rubble mound 3 will be described using the X-axis, Y-axis, and Z-axis indicated by three arrows in the figure. Here, -Z is the direction of gravity, that is, the downward direction. Further, +X is, for example, the north direction, and +Y is, for example, the west direction.

Construction method M uses a learning device 1, a control device 4, and a management device 5 mounted on a ship stopped on the sea surface W, and a leveling machine 2 placed on a rubble mound 3. Implemented.

The rubble mound 3 is constructed by throwing rubble into the seabed B. The rubble mound 3 built on the seabed B becomes the foundation of a port structure such as a caisson built thereon.

The learning device 1, the control device 4, and the management device 5 are communicably connected to each other via a wired or wireless communication line.

The control device 4 is a device that controls the leveling machine 2, and is, for example, a programmable logic controller. The control device 4 may include, for example, an FPGA (Field Programmable Gate Array) or an ASIC (Application Specific Integrated Circuit). Further, in this embodiment, the control device 4 receives operations from an operator.

The management device 5 is a device that acquires and stores data for managing the leveling machine 2 from the leveling machine 2 and the control device 4. The management device 5 is, for example, a computer.

The learning device 1 is a device that acquires at least part of the above-mentioned data from the management device 5 and performs machine learning. The learning device 1 is, for example, a computer.

The leveling machine 2 is lowered from the sea toward the seabed by a hoist ship or the like, and is placed at a planned location on the top surface 30 of the rubble mound 3. FIG. 2 is a top view of the leveling machine 2. FIG. 3 is a diagram showing an example of the configuration of the leveling machine 2. As shown in FIG.

<Smoothing machine configuration>
As shown in FIG. 3, the leveling machine 2 includes a pedestal 20, a striking machine 21, a rake device 22, a leveling height sensor 23, a communication line 24, a positioning device 25, a control line 26, and an azimuth inclinometer 27. .

The pedestal 20 is a structure that supports each component of the leveling machine 2. The pedestal 20 has three or more legs that contact the top surface 30 and a connecting section that connects these legs to each other. Note that the leveling machine 2 shown in FIG. 3 has eight legs (not shown). Of these eight legs, four are legs that support the leveling machine 2, and the remaining four are legs for movement that come into contact with the top surface 30 when the leveling machine 2 is moved. The legs and the connecting portion are made of steel, for example. A punching machine 21, a rake device 22, and a leveling height sensor 23 are supported on a horizontally extending frame so as to be movable along the X and Y axes.

FIG. 4 is a diagram showing an example of the configuration of the striking machine 21. As shown in FIG. The striking machine 21 shown in FIG. 4 includes a hanging wire 210, a weight height sensor 211, a weight 212, a weight fitting platform 213, a platform height sensor 214, a weight lifting winch 215, and a weight moving It has a traversing truck 216.

The weight-running transverse truck 216 is a truck that runs horizontally or the like along the frame of the pedestal 20 . The weight traveling transverse truck 216 is equipped with a weight lifting winch 215, and moves the weight lifting winch 215 above the area where the weight 212 is expected to fall.

The weight lifting winch 215 is a winch mounted on the weight traveling transverse truck 216, and winds up and lets out the hanging wire 210.

The suspension wire 210 is a wire that suspends and holds (also referred to as "suspension") the weight fitting platform 213.

The weight fitting base plate 213 is a base plate whose upper surface is suspended by the hanging wire 210. The weight fitting base plate 213 has a fitting member such as a latch for fitting the weight 212 (also referred to as “fitting”) on the lower surface, for example.

The weight 212 is a rectangular parallelepiped-shaped object made of metal such as steel. The upper surface of this weight 212 can be attached to and detached from the weight fitting base plate 213 using the above-mentioned fitting member. When the weight 212 is detached from the weight fitting platform 213 and dropped onto the top surface 30 of the rubble mound 3, the weight 212 hits the top surface 30 of the rubble mound 3 and compacts it. Equalize the height of 30.

The weight 212 travels on the frame via a weight traveling transverse truck 216 and is suspended by a hanging wire 210 together with a weight fitting base plate 213 starting from a weight lifting winch 215 arranged at a predetermined location. There is. The falling height of the weight 212 is adjusted by the amount of winding of the hanging wire 210 by the weight lifting winch 215. When the weight lifting winch 215 adjusts the winding amount of the hanging wire 210, the weight fitting base plate 213 is suspended at the specified height. This weight lifting winch 215 holds the hanging wire 210 wound with a force that resists the gravity applied to the weight 212 and the weight fitting base plate 213 in order to maintain the length of the hanging wire 210. .

When the weight fitting base plate 213 removes the fitting member at this adjusted height and releases the force holding the weight 212, the weight 212 is detached from the weight fitting base plate 213 and the rubble is removed. It falls freely onto the top surface 30 which is the upper surface of the mound 3.

That is, the weight lifting winch 215 winds up or lets out the hanging wire 210 by a predetermined length, so that the weight 212 is suspended at a designated height. Thereafter, when the weight fitting platform 213 releases the weight 212, the weight 212 falls toward the top surface 30 and hits the fallen position.

After striking, the weight lifting winch 215 lets out the hanging wire 210 and lowers the weight fitting base plate 213 to the height of the weight 212. The lowered weight fitting base plate 213 is fitted with the weight 212 again by the fitting member. Then, when the weight lifting winch 215 winds up the hanging wire 210, the weight fitting base plate 213 and the weight 212 rise from the top surface 30 and are lifted up to a height corresponding to the amount of winding. That is, the weight 212 that struck the top surface 30 is again fitted into the weight fitting base plate 213 connected to the end of the hanging wire 210 suspended from the weight lifting winch 215. suspended by.

The platform height sensor 214 is installed on the lower surface of the weight-traversing truck 216 and measures the distance to the weight-fitting platform 213. This platform height sensor 214 is attached to the lower surface of the weight-traversing truck 216. The platform height sensor 214 measures the distance from the lower surface of the weight traveling transverse truck 216 to the upper surface of the weight fitting platform 213, which corresponds to the amount of payout of the hanging wire 210.

Therefore, the distance measurement result by the platform height sensor 214 may be used to verify the amount of payout of the hanging wire 210 measured by a rotary encoder or the like provided in the weight lifting winch 215. The payout amount of the hanging wire 210 or the measurement result of the distance by the platform height sensor 214 is used to calculate the depth of the top surface of the weight fitting platform 213 based on the position of the bottom surface of the weight traveling transverse truck 216. It will be done.

The weight height sensor 211 is a measuring device that measures the depth at the top surface of the weight 212, and is an ultrasonic distance meter. The weight height sensor 211 is attached to the lower surface of the weight fitting base plate 213. The weight height sensor 211 has a wave transmitting section that transmits ultrasonic waves toward the upper surface of the weight 212 located below. Further, the weight height sensor 211 includes a wave receiving section that receives the ultrasonic waves reflected from the upper surface of the weight 212. The weight height sensor 211 measures the height of the weight from the bottom surface of the weight fitting base plate 213 to the top surface of the weight 212 based on the time it takes for the ultrasonic waves transmitted from the wave transmitting section to be reflected and return to the wave receiving section. Measure the distance to.

For example, by offsetting the thickness of the weight fitting base plate 213 to the depth of the top surface of the weight fitting base plate 213 calculated based on the amount of payout of the hanging wire 210, the depth of the bottom surface of the weight fitting base plate 213 can be determined. . The upper surface of the weight 212 is located at a position further down a distance measured by the weight height sensor 211 from this depth. By offsetting the thickness of the weight 212 from the position of the top surface of the weight 212, the depth of the bottom surface of the weight 212, that is, the top surface 30 is measured.

The weight height sensors 211 are preferably attached to at least three locations on the lower surface of the weight fitting base plate 213 at equal intervals in the horizontal direction, and it is more desirable that the intervals be as wide as possible. This is because the upper surface of the weight 212 is recognized as a plane, and its inclination is specified.

Note that the leveling machine 2 may have a guide that contacts the weight 212 on the side surface when it falls and guides the falling position. The guide is, for example, a rail-shaped steel member erected perpendicularly to the top surface 30.

The rake device 22 shown in FIG. 3 can move in the Y-axis and Z-axis directions, and its tip contacts the top surface 30 and is moved in the Y-axis direction, thereby scraping off rubble, etc. on the top surface of the top surface 30. It is a member that smooths the surface. Note that it is preferable that the rake device 22 level the surface by moving in a direction away from the center line C shown in FIG.

For example, as shown in FIG. 2, when the leveling frame R is on the +Y side with respect to the center line C, the rake device 22 scrapes off the rubble on the top surface of the top surface 30 while moving in the +Y direction. As a result, the scraped stones are dropped onto the slope on the +Y side of the top surface 30. In this way, the rake device 22 scrapes the rubble in the direction away from the center line C and drops it from the slope, so the scraped rubble does not collect at the center of the top surface 30.

The rake device 22 includes a leveling height sensor 23 on the rear side in the direction in which the rake device 22 moves. These leveling height sensors 23 measure the shape of the top surface 30 of the rubble mound 3 by moving the rake device 22 back and forth. In this embodiment, the leveling height sensor 23 moves as the rake device 22 moves.

Measurement using the leveling height sensor 23 is performed three times: a pre-measurement, a middle measurement, and a post-measurement. In the preliminary measurement, the shape of the top surface 30 of the rubble mound 3 into which rubble has been thrown is measured before it is leveled by the rake device 22.
In the intermediate measurement, the shape of the mound after being leveled by the rake device 22 is measured.
Post-measurement measures the shape of the top surface 30 leveled by the rake device 22 and after the weight 212 falls and compacts it. Note that this leveling height sensor 23 is, for example, an ultrasonic sensor.

A plurality of leveling height sensors 23 may be arranged in the width direction of the rake device 22. FIG. 5 is a diagram showing an example of leveling height sensors 23 arranged in the width direction. FIG. 5 shows a schematic diagram of the rake device 22 and the leveling height sensor 23 viewed from above. On the -Y side of the rake device 22 shown in FIG. , if these are not distinguished, they are simply referred to as "leveling height sensors 23") are lined up.

The leveling height sensors 23-1, 23-2, 23-3, 23-4, and 23-5 measure the height of the top surface 30 of the portion through which the rake device 22 has passed, as well as the unevenness in the width direction. In addition, in this explanation, the number of leveling height sensors installed is 5, but as long as the entire width of the leveling machine can be measured in the horizontal direction, there is no need for 5, and it is possible to use 6 or more. I don't mind.

The positioning device 25 measures the position of the leveling device 2. The positioning device 25 includes, for example, a GNSS (Global Navigation Satellite System) receiver. Further, the azimuth inclinometer 27 has a gyro sensor.

The GNSS receiver of the positioning device 25 measures the three-dimensional position of the leveling device 2 on the earth by receiving radio waves from a plurality of satellites. However, since the radio waves from the satellite may not reach underwater, the positioning device 25 is installed above the sea level W. Further, in this construction method M, a GNSS receiver and a transceiver may be installed in a ship stopped on the sea surface W, and a transponder may be installed at a known position on the mount 20.

The coordinates of the positioning point P shown in FIG. 2 are measured by the GNSS receiver, and the position of the leveling machine 2 is specified based on this positioning point P.

The gyro sensor of the azimuth inclinometer 27 measures the attitude of the leveling machine 2, that is, the inclination of the leveling machine 2 with respect to the X-axis direction, Y-axis direction, and Z-axis direction. As a result, the global coordinates indicating the north, south, east, and west directions on the earth are associated with the local coordinates indicating the relative positional relationship between the constituent members of the leveling machine 2.

Then, by determining the installation position of the leveling machine 2 and associating the global coordinates with the local coordinates, the range of the top surface 30 where the weight 212 can fall and strike is determined as shown in FIG. It is determined as the leveling frame R.

The communication line 24 communicably connects the positioning device 25 disposed above the sea surface W and each component disposed below the sea surface W.

The control line 26 is a communication wire, and is a composite cable that sends and receives control instructions for the leveling machine 2, measurement data, and transmits power to the leveling machine 2, and connects the leveling machine 2, the control device 4, and the management device 5. Connect to enable communication. Note that the control line 26 may be wireless for transmitting and receiving control instructions and measurement data. When communicating wirelessly, the radio waves may not reach underwater, so if the leveling machine 2 has a communication device that wirelessly communicates with the control device 4 and the management device 5 installed above the sea level W. good. The control line 26 allows the leveling machine 2 to communicate with the control device 4 and the management device 5, and is placed under the control of the control device 4.

The control line 26 transmits control signals and the like from the control device 4 to a drive device (not shown) of the leveling machine 2. As a result, the striking machine 21, the rake device 22, the weight-running traverse truck 216, and the weight-fitting platform 213 driven by this drive device are controlled by the control device 4, such as the leveling height sensor 23 and the platform height sensor. 214 and the weight height sensor 211 are controlled by the management device 5.
Note that the various sensors may be controlled by the control device 4 instead of the management device 5 depending on the communication format used.

FIG. 6 is a diagram showing an example of the leveling frame R. The leveling frame R shown in FIG. 6 is composed of eight sections R1 to R8 arranged in two rows and four columns. The surface of the top surface 30 that is struck by the bottom surface of the weight 212 at one time (strike surface) is, for example, a 2 meter square. In this case, since the striking surfaces are arranged in two rows and four columns, the area set as the leveling frame R is a rectangle measuring 4 meters in the X-axis direction and 8 meters in the Y-axis direction.

Using the control device 4, the operator first divides the entire area into a plurality of leveling frames R in order to level the entire area of the top surface 30 of the rubble mound 3. Then, the operator assigns an order to the divided leveling frames R and specifies them in order to the control device 4. Then, the control device 4 instructs the leveling machine 2 to be moved to a position for leveling the designated leveling frame R. Further, the control device 4 causes the leveling machine 2 to measure the height of the top surface 30 until the measured height satisfies the set height condition suitable for striking by the striking machine 21. Instruct them to level with a rake.

When the rake device 22 moves in the leveling machine 2 that has been moved to the above position and the top surface 30 is leveled, the leveling height sensor 23 that moves with the rake device 22 detects the height of the top surface 30 after leveling. The height is measured and sent to the control device 4 via the management device 5. When the measured height of the top surface 30 satisfies the condition of the setting height for striking start, the operator further divides the specified leveling frame R into a plurality of sections (R1 to R8) and assigns an order to the sections (R1 to R8). These partitions are designated in order to the control device 4.

Then, the operator instructs the control device 4 to measure the height of the top surface 30 of the rubble mound 3 before hitting a specified section, and drops the weight 212 onto that section to measure the top surface 30. An instruction to strike and an instruction to measure the amount of displacement in height of the section after striking is given.

If the fall height is not estimated before the first learning model 122 is constructed, the operator of the control device 4 can strike the leveling machine 2 at a preset fall height via the operation unit. Instruct to do so. Further, when the fall height is estimated after the first learning model 122 is constructed, the operator of the control device 4 confirms the fall height displayed on the display unit 15 or uses it as a reference. The falling height is inputted into the operating section, thereby instructing the leveling machine 2 to perform the hammering at the inputted falling height.

The leveling machine 2, which receives this instruction via the control line 26, first operates the weight lifting winch 215 to wind up the hanging wire 210, and lifts the weight fitting base plate 213 and the weight to the specified falling height. Lift up the weight 212. Next, the leveling machine 2 releases the fitting member of the weight fitting base plate 213 and causes the weight 212 to fall. Thereafter, the leveling machine 2 uses the weight height sensor 211 to measure the amount of displacement in the height of the rubble mound 3 due to striking.

The management device 5 acquires the measured displacement amount via the control line 26. The management device 5 acquires and stores the measured displacement amount and each condition at the time of impact. The learning device 1 acquires data such as the amount of displacement described above from the control device 4 when performing machine learning.

<Configuration of learning device>
FIG. 7 is a diagram showing an example of the configuration of the learning device 1. The learning device 1 includes a processor 11, a memory 12, and an interface 13. Furthermore, the learning device 1 may include an operation section 14 and a display section 15 as shown in FIG. These structures are communicatively connected to each other, for example by a bus.

The processor 11 controls each part of the learning device 1 by reading and executing a computer program (hereinafter simply referred to as a program) stored in the memory 12 . The processor 11 is, for example, a CPU (Central Processing Unit).

The memory 12 is a storage means for storing an operating system read into the processor 11, various programs, data, and the like. The memory 12 includes RAM (Random Access Memory) and ROM (Read Only Memory). Note that the memory 12 may include a solid state drive, a hard disk drive, or the like.

The memory 12 also stores first teacher data 121 and a first learning model 122. FIG. 8 is a diagram showing an example of the first teacher data 121. The first teacher data 121 stores various measurement values measured each time the weight 212 hits the top surface 30 and various conditions in association with each other. The first teacher data 121 shown in FIG. 8 is assigned a data ID, which is identification information for identifying data for each impact, and uses explanatory variables as the number of falls, the height of the fall, the height at which the weight is dropped, and the number of times the weight is dropped. The previous section constant, which is the ratio of the amount of displacement to the square root of the product of The cumulative amount of displacement up to the previous time indicating the cumulative amount of displacement in the height of the rubble mound is stored.

Here, the number of falls is the number of times, including the current impact, that the weight 212 has been dropped to a certain section of the top surface 30 that is the target of impact. The falling height is the height at which the weight was dropped during this strike.

Further, the previous section constant, the previous frame constant, and the previous overall constant are all a striking constant α. Here, the impact constant α will be explained. It is known that weight compaction has a relationship expressed by the following equation (1).

Here, P is the weight penetration amount, and the unit is, for example, [m]. The amount of weight penetration is the amount of displacement of the top surface 30 when the weight 212 is dropped and penetrated. c is a ground constant, and the unit is, for example, [m ² s/t]. m is the weight mass, and the unit is, for example, [t]. A is the area of the bottom of the weight, and the unit is, for example, [m ² ]. v ₀ is the collision speed, and the unit is, for example, [m/s]. N is the number of hits (number of falls). H is the falling height, and the unit is, for example, [m].

Therefore, according to this equation (1), the amount of weight penetration is proportional to the weight mass, the collision speed, and the square root of the number of falls. Moreover, according to this formula (1), the amount of weight penetration is inversely proportional to the bottom area of the weight.

Incidentally, the collision velocity v ₀ of the weight 212 when it falls a distance indicated by H and collides with the top surface 30 is expressed by the following equation (2) using the gravitational acceleration g.

In other words, the amount of weight penetration, which is proportional to the collision speed, is proportional to the square root of the falling height H. The following equation (3) collectively represents the above-mentioned equations (1) and (2).

Here, the striking constant α is a constant that includes various conditions related to striking, such as the mass of the weight m and the bottom area A of the weight, in addition to the ground constant c that depends on the characteristics of the rubble and the like. In this equation, P _N is the amount of weight penetration when the weight 212 falls (strike) for the Nth time. By transforming equation (3), it can be seen that the striking constant α is the value obtained by dividing the weight penetration amount P _N by the square root of the product of the number of falls N and the fall height H (NH). The weight penetration amount P _N is the amount of displacement in the height of the top surface 30 of the rubble mound 3 due to the Nth impact. Therefore, the striking constant α is an example of the ratio of the amount of displacement in the height of the rubble mound due to striking to the square root of the product of the height at which the weight is dropped and the number of times the weight is dropped.

Then, the difference between the amount of weight penetration in the Nth impact and the amount of weight penetration in the previous (that is, (N-1)th) impact is expressed by the following equation (4).

The striking constant α is updated every time the weight strikes, and is calculated based on a different measurement value for each section. Further, as the striking constant α calculated in association with the leveling frame composed of a plurality of sections, a representative value of the striking constant α calculated for each section is adopted. Furthermore, for the striking constant α calculated in association with the entire area of the top surface 30 of the rubble mound 3, the representative value of the striking constant α calculated for each of all the sections included in this entire area is adopted. .

That is, the previous section constant is the strike constant α calculated when the previous strike against a certain section was completed.

Further, the previous frame constant is a representative value of the striking constant α calculated for each of all the sections constituting the leveling frame R when the previous striking was completed. This representative value is, for example, the arithmetic average value of the striking constants α calculated for each of the eight sections R1 to R8 constituting the leveling frame R. The leveling frame R is a group consisting of two or more sections. In other words, this previous frame constant is an example of the arithmetic average value of the ratios of all sections belonging to the group.

The previous overall constant is a representative value of the impact constant α calculated for each of all the sections constituting the entire area of the top surface 30 when the previous impact was completed. This representative value is, for example, the arithmetic average value of the impact constant α calculated for each of all the sections that constitute the entire area of the top surface 30. In this case, the previous overall constant is an example of the arithmetic average value of all the ratios of a plurality of sections obtained by sectioning the top surface of the rubble mound. Note that this representative value is not limited to the arithmetic mean value of the impact constant α of each section, but may be various statistical values such as the mode, the median, the geometric mean, and the maximum value.

The first teacher data 121 stores the amount of displacement of the top surface 30 due to the impact, that is, the amount of displacement due to the current impact, as a target variable in association with the data ID indicating the impact described above. The first teacher data 121 also stores the previous displacement amount, which is the previous displacement amount specified based on the displacement amount specified for each impact. The first teacher data 121 also stores the cumulative amount of displacement up to the previous time, which is the cumulative amount of displacement up to the previous time.

The first learning model 122 shown in FIG. 7 is generated by machine learning based on the first teacher data 121. This first learning model includes a group of parameters used in formulas, matrices, etc. for predicting the objective variable from the explanatory variables stored in the first teacher data 121. For example, linear regression, decision tree, xgboost, etc. can be applied to machine learning for generating the first learning model.

The interface 13 is a communication circuit that communicably connects the learning device 1 to the management device 5 and the control device 4 via a wired or wireless communication line.

The operation unit 14 includes operators such as operation buttons, a keyboard, a touch panel, and a mouse for issuing various instructions, and receives operations and sends signals to the processor 11 according to the contents of the operations. This operation is, for example, a press on a keyboard, a gesture on a touch panel, or the like.

The display unit 15 has a display screen such as a liquid crystal display, and displays images under the control of the processor 11. A transparent touch panel of the operation unit 14 may be placed on top of the display screen. Note that the learning device 1 does not need to have the operation section 14 and the display section 15. The learning device 1 may be operated by an external device via the interface 13 or may present information to an external device.

<Configuration of control device>
FIG. 9 is a diagram showing an example of the configuration of the control device 4. As shown in FIG. The control device 4 shown in FIG. 9 includes a processor 41, a memory 42, an interface 43, an operation section 44, and a display section 45. These structures are communicatively connected to each other, for example by a bus.

The processor 41 controls each part of the control device 4 by reading and executing a program stored in the memory 42 . The processor 41 is, for example, a CPU.

The interface 43 is a communication circuit that communicably connects the control device 4 to other devices by wire or wirelessly.

The operation unit 44 includes operators such as operation buttons, lever boxes, and touch panels for issuing various instructions, and receives operations and sends signals to the processor 41 according to the contents of the operations.

The display unit 45 has a display screen such as a liquid crystal display, and displays images under the control of the processor 41. A transparent touch panel of the operation unit 44 may be placed on top of the display screen. Note that the control device 4 does not need to have the operation section 44 and the display section 45. The control device 4 may be operated by an external device via the interface 43 or may present information to an external device.

The memory 42 is a storage means for storing an operating system, various programs, data, etc. read into the processor 41. The memory 42 includes RAM and ROM. Note that the memory 42 may include a solid state drive, a hard disk drive, or the like.

<Configuration of management device>
FIG. 10 is a diagram showing an example of the configuration of the management device 5. As shown in FIG. The management device 5 shown in FIG. 10 includes a processor 51, a memory 52, an interface 53, an operation section 54, and a display section 55. These structures are communicatively connected to each other, for example by a bus.

The processor 51 controls each part of the management device 5 by reading and executing a program stored in the memory 52. The processor 51 is, for example, a CPU.

The interface 53 is a communication circuit that communicably connects the management device 5 to other devices by wire or wirelessly.

The operation unit 54 includes operators such as operation buttons, a keyboard, a touch panel, and a mouse for issuing various instructions, and receives operations and sends signals to the processor 51 according to the contents of the operations. It has an operation section.

The display unit 55 has a display screen such as a liquid crystal display, and displays images under the control of the processor 51. A transparent touch panel of the operation unit 54 may be placed on top of the display screen. Note that the management device 5 does not need to have the operation section 54 and the display section 55. The management device 5 may be operated by an external device via the interface 53, or may present information to an external device.

The memory 52 is a storage means for storing an operating system, various programs, data, etc. read into the processor 51. The memory 52 includes RAM and ROM. Note that the memory 52 may include a solid state drive, a hard disk drive, or the like.

<Functional configuration of learning device>
FIG. 11 is a diagram showing an example of the functional configuration of the learning device 1. The learning device 1 functions as a measurement value acquisition means 111, a teacher data generation means 112, a learning model construction means 113, a fall height estimation means 114, and a display control means 115 when the processor 11 executes a program.

The measured value acquisition means 111 receives from the management device 5 the measured value of the height of the top end surface 30 of the rubble mound 3 before pounding and the measured value of the displacement amount of the height of the rubble mound 3 after pounding from the interface 13. Get it via.

The teacher data generating means 112 generates the first teacher data 121 by specifying or calculating an explanatory variable and a target variable from the conditions of the executed strike and the acquired measurement values.

The learning model construction means 113 uses the generated first teacher data 121 to calculate a group of parameters for deriving the objective variable from the explanatory variables, and constructs the first learning model 122 using these.

The fall height estimating means 114 estimates, based on the constructed first learning model 122, the height at which the weight 212 should be lifted and dropped in the next instructed strike (fall height). First, the fall height estimating means 114 specifies a fall height, for example, 1 m, at which even if the weight 212 falls and compacts the top surface 30, it will not sink more than the designed leveling height, The amount of displacement of a certain section when the weight 212 is dropped at that falling height is estimated. Then, the fall height estimating means 114 varies the fall height so that the estimated displacement approaches a preset desired displacement. Thereby, the fall height estimating means 114 estimates a "fall height" which is an appropriate height at which the weight 212 should be dropped. The estimated fall height is transmitted to the display control means 115. The display control means 115 instructs the display unit 15 to display the estimated value of the fall height.

<Processing of construction method>
FIG. 12 is a flow diagram showing an example of the processing flow of construction method M. The operator instructs the leveling machine 2 via the operation section of the control device 4 to adjust the work start position (step S001). As a result, the position of the leveling machine 2 is determined, and the leveling frame R is determined. Next, the operator instructs the leveling machine 2 from the management device 5 to perform preliminary measurement with the leveling height sensor 23, and then levels the rake until the set height is reached via the operation section of the control device 4. (Step S002). As a result, the leveling frame R is roughly leveled.

The leveling machine 2 uses a leveling height sensor 23 to measure (intermediate measurement) the height of the top surface 30 after leveling with a rake according to instructions from the management device 5. Based on the measured results, the management device 5 determines whether the top surface 30 satisfies the condition of the height set at the start of impact (step S003). If the management device 5 determines that the top surface 30 does not satisfy the condition of the set height for striking start (step S003; NO), the control device 4 instructs the leveling machine 2 to level the surface with a rake again.

FIG. 13 is a diagram showing the state before the leveling machine 2 levels the top surface 30. Under the control of the control device 4 and the management device 5, the leveling machine 2 scans the leveling height sensor 23 together with the rake device 22 to measure (preliminarily measure) the height of the top surface 30. At this time, the rake device 22 pulls up the tip of the rake and separates it from the top surface 30 for measurement. The control device 4 determines in advance the upper limit of the height of the top surface 30 and the range of the difference in height between the highest point and the lowest point as conditions for the set height for striking start. The height measured by the leveling height sensor 23 is transmitted from the leveling machine 2 to the management device 5, and it is determined whether the set height condition is satisfied.

FIG. 14 is a diagram showing how the leveling machine 2 performs rake leveling. Under the control of the control device 4, the leveling machine 2 performs "rake leveling" in which the rake device 22 is driven in the direction of the arrow shown in FIG. 14 to scrape and level rubble from the top surface 30. The scraped stones and the like on the top surface 30 are moved to the outside of the top surface 30. The leveling height sensor 23 measures the height of the top surface 30 as an intermediate measurement after the rake device 22 has leveled the water and the turbidity in the water has settled down, and transmits this to the control device 4 via the management device 5.

On the other hand, if it is determined that the top surface 30 satisfies the set striking start height condition (step S003; YES), the control device 4 instructs the leveling machine 2 to execute the weight leveling process. (Step S100).

When the weight leveling process is completed, the control device 4 determines whether leveling of the entire area of the top surface 30 has been completed (step S004). If it is determined that the rake leveling and weight leveling of the entire area of the top surface 30 has not been completed (step S004; NO), the operator returns the process to step S001. That is, the operator specifies the leveling frame R on the top surface 30 that has not yet been leveled, and instructs the leveling machine 2 to perform a series of position adjustment → rake leveling → weight leveling. This process is performed on the new leveling frame R. On the other hand, if the operator determines that the entire area of the top surface 30 has been leveled, the operator ends the process.

FIG. 15 is a flowchart showing an example of the flow of the weight leveling process (step S100). The control device 4 further divides the specified leveling frame R to determine sections R1 to R8. Then, the operator assigns an order to these sections R1 to R8, and decides which section should start weight drop compaction in accordance with the order. The operator instructs the leveling machine 2 to measure (intermediate measurement) the height of the determined section before hitting it (step S101). The results of this measurement are transmitted from the leveling machine 2 to the control device 4 via the management device 5, and the data are stored in the management device 5. The learning device 1 acquires recorded data from the management device 5, and generates first teacher data and constructs a first learning model.

This step S101 is performed sequentially for each leveling frame R for each of a plurality of sections obtained by dividing the top end surface 30 of the rubble mound 3. Therefore, this step S101 is an example of a step of measuring the height of the top surface of the rubble mound before striking with a weight, for each of a plurality of sections obtained by dividing the top surface of the rubble mound.

The learning device 1 determines whether the first learning model exists (has been constructed) in the memory 12 (step S102). Note that in new construction, re-learning may be performed using a generated learning model used in other construction. When determining that the first learning model does not exist in the memory 12 (step S102; NO), the operator specifies a predetermined fall height for the leveling machine 2 to the control device 4 (step S103).

On the other hand, if it is determined that the first learning model exists in the memory 12 (step S102; YES), the learning device 1 estimates the fall height of the weight 212 using this first learning model, and The fall height is displayed on the display unit 15 for the operator to confirm (step S104). This step S104 is an example of a step of estimating the height at which the weight is dropped to the rubble mound using the first learning model. After confirming the display of the falling height, the operator adjusts the falling height of the control device 4 via the operation unit if the numerical value indicating the falling height by the first learning model requires adjustment, or if no adjustment is necessary. For example, the leveling machine 2 is instructed to strike from the estimated falling height.

Under the control of the control device 4, the hammering machine 21 of the leveling machine 2 lifts the weight 212 to a specified fall height, and then releases the weight 212 to allow it to fall freely to hit the above-mentioned section. (Step S105). This step S105 is an example of a step in which a weight is dropped from the height estimated in the estimation step and the weight is struck against the top surface of the rubble mound.

FIG. 16 is a diagram showing the state before the top surface 30 is struck by the weight 212. The weight-traversing cart 216 moves above the designated section of the leveling frame R. When the movement is completed, the weight lifting winch 215 lets out the hanging wire 210 and lowers the weight fitting platform 213 to a height corresponding to the specified drop height.

FIG. 17 is a diagram showing the state after the weight 212 hits the top surface 30. The weight fitting base plate 213 that has been lowered to a predetermined position releases the weight 212 by removing the fitting member. As a result, the weight 212 falls freely and hits the top surface 30 of the rubble mound 3. As a result, the weight 212 penetrates the top surface 30, and its height is displaced.

This step S105 is performed for each of a plurality of sections obtained by dividing the top end surface 30 of the rubble mound 3 until the respective sections fall within a predetermined range from the design compaction height. Therefore, this step S105 is an example of a step in which a weight is dropped from a set height a predetermined number of times and struck into each of a plurality of sections obtained by dividing the top surface of the rubble mound.

When the weight 212 penetrates the top surface 30 after one impact, the leveling machine 2 measures the amount of displacement in the height of the rubble mound 3 due to the impact under the control of the management device 5. Step S106). At this time, the leveling machine 2 measures the amount of displacement using the weight height sensor 211 that the weight 212 that has penetrated into the top surface 30 has. This measurement is performed every time a strike is made. Therefore, this step S106 is an example of a step of measuring the amount of displacement in the height of the rubble mound due to striking.

Note that when the leveling machine 2 measures the amount of height displacement using the weight height sensor 211, which is a transponder attached to at least three locations on the top surface of the weight 212, this step S106 is performed using a measuring device. This is an example of the step of measuring the amount of displacement in the height of the rubble mound due to impact using the depths of at least three points on the upper surface of the weight measured by the method.

Next, the learning device 1 calculates the square root of the product of the height at which the weight 212 is dropped (fall height) and the number of times it is dropped (number of falls), and calculates the ratio of the above-mentioned displacement amount to the square root. Calculate (step S107). This step S107 is performed for each of the plurality of leveling frames R forming the top surface 30, the plurality of sections forming the leveling frames R, and the entire area of the top surface 30. In other words, this step S107 calculates the product of the height at which the weight is dropped and the number of times the weight is dropped for each of a plurality of sections obtained by dividing the top surface of the rubble mound and the entire area of the top surface of the rubble mound. This is an example of the step of calculating the ratio of the amount of displacement to the square root of .

Further, the leveling frame R is a group consisting of two or more sections in which the weight 212 is moved and dropped. In other words, in step S107, in addition to each of the plurality of sections on the top surface and the entire area of the top surface, the ratio is calculated for each group consisting of two or more sections in which the weight is moved and dropped among the plurality of sections. This is an example of steps to calculate.

After calculating the ratio, the learning device 1 generates the first teacher data 121 using this ratio together with the various conditions of striking. Further, if the first teacher data 121 has already been generated, the learning device 1 updates the first teacher data 121 using the calculated new ratio (step S108). As a result, first teacher data 121 shown in FIG. 8 is generated in the memory 12 of the learning device 1. In other words, in step S108, the previous displacement, which indicates the height and number of times the weight was dropped, and the amount of displacement in the height of the rubble mound due to the previous impact, in the multiple sections of the top surface and the entire area of the top surface. The explanatory variables are the cumulative displacement of the height of the rubble mound due to previous strikes, and the ratio of the displacement to the square root of the product of the fall height and the number of falls, and the displacement due to the current strike is used as the objective. This is an example of steps for generating training data to be used as variables.

Further, the leveling frame R is a group consisting of two or more sections in which the weight 212 is moved and dropped. In other words, this step S108 includes a plurality of sections on the top surface, a group consisting of two or more sections in which the weight is to be moved and dropped among the plurality of sections, and a whole region of the top surface where the weight is dropped. Training data in which the explanatory variables are the height, the number of strikes, the previous displacement amount, the cumulative displacement amount up to the previous time, and the ratio of the displacement amount to the square root of the product of the fall height and the number of falls, and the displacement amount due to the current impact is the objective variable. This is an example of steps to generate .

After generating or updating the first teacher data 121, the learning device 1 constructs or updates a first learning model using the first teacher data 121 (step S109). This step S109 is an example of a step of constructing a first learning model using the generated or updated teacher data.

The control device 4 determines whether the weight leveling process for all sections of the top surface 30 has been completed (step S110). If it is determined that the weight leveling process for all sections has not been completed (step S110; NO), the control device 4 selects unprocessed sections among the plurality of sections of the leveling frame R according to the above-mentioned order. The leveling machine 2 is designated and the process returns to step S101. On the other hand, if it is determined that the weight leveling process for all sections of the leveling frame R has been completed (step S110; YES), the control device 4 ends the process.

The operator instructs the leveling machine 2 when step S110 becomes YES (when the control device 4 determines that weight compaction of all sections in the leveling frame R has been completed), As the post-measurement described above, the height of the top surface 30 is measured by scanning the leveling height sensor 23. The results of this measurement are transmitted from the leveling machine 2 to the control device 4 via the management device 5, and the data are stored in the management device 5.

After confirming through post-measurement that the entire area within the leveling frame R is compacted to the design height, the operator moves the leveling machine 2 to the next leveling frame R. As a result, the process of construction method M returns to the calling source of step S100 and moves to step S004 (see FIG. 12).

As described above, according to the construction method M described above, the height and number of times the weight was dropped, and the height of the rubble mound caused by the previous impact, in multiple sections of the top surface and in the entire area of the top surface. The explanatory variables are the previous displacement amount, the cumulative displacement amount of the height of the rubble mound due to previous hammering, and the ratio of the displacement amount to the square root of the product of the fall height and the number of falls, and the displacement amount is the objective variable. First teacher data is generated. According to this construction method M, the height at which the weight 212 is dropped is estimated by the first learning model constructed using the first teacher data, so the height at which the weight 212 is dropped is estimated, so the height at which the weight 212 is dropped can be estimated without relying on the empirical rules of the operator. The falling height of the weight 212 during weight compaction can be set.

<Modified example>
The above is the description of the embodiment, but the content of this embodiment can be modified as follows. Further, the following modifications may be combined.

<1>
In the embodiment described above, the first teacher data 121 includes information on the height and number of times the weight was dropped, and the height of the rubble mound caused by the previous impact in a plurality of sections of the top surface and the entire area of the top surface. The explanatory variables are the previous displacement amount, the cumulative displacement amount of the height of the rubble mound due to previous hammering, and the ratio of the displacement amount to the square root of the product of the fall height and the number of falls, and the displacement amount is the objective variable. Although this is teaching data, teaching data using other indicators as objective variables may be generated. For example, the target variable of the teacher data may be the amount of displacement of "another section" different from the section that was struck.

FIG. 18 is a diagram showing an example of the configuration of the learning device 1 in a modified example. The learning device 1 shown in FIG. 18 stores second teacher data 123 and a second learning model 124 in the memory 12 instead of or in addition to the first teacher data 121 and the first learning model 122.

FIG. 19 is a diagram showing an example of second teacher data 123 in a modified example. Like the first teacher data 121, the second teacher data 123 is assigned a data ID, which is identification information for identifying data for each impact, and has explanatory variables such as the number of falls, fall height, previous division constant, previous frame constant, The previous overall constant, the previous displacement amount, and the cumulative displacement amount up to the previous time are stored.

On the other hand, the second teacher data 123 differs from the first teacher data 121 in that the objective variable is a block around a certain block that has been struck, and is different from the certain block in the leveling frame R. The amount of displacement (peripheral displacement amount) of the section (also referred to as the surrounding section) is stored. This second teacher data 123 is used to construct a second learning model 124 for estimating the amount of peripheral displacement.

Here, the peripheral displacement amount is not limited to the amount of subsidence. This is because when a certain section is rammed and the section sinks, rubble or the like may be pushed out into the surrounding sections, causing them to rise.

FIG. 20 is a diagram showing an example of the functional configuration of the learning device 1 in a modified example. The teacher data generation means 112 shown in FIG. 20 generates second teacher data 123 in addition to or in place of the first teacher data 121 described above.

Furthermore, in addition to or in place of constructing the first learning model 122 using the first teacher data 121 described above, the learning model construction means 113 shown in FIG. Build model 124.

Since the second teacher data 123 uses the amount of peripheral displacement as an objective variable, the second learning model 124 includes a parameter group for deriving the amount of peripheral displacement, which is the objective variable, from the above-mentioned explanatory variables.

That is, in this modification, the construction method M includes a plurality of sections on the top surface, the section where the weight was dropped in the entire area of the top surface, the height, the number of times, the previous displacement amount, the cumulative displacement amount until the previous time, and a step of generating second training data 123 in which the ratio of the displacement amount to the square root of the product of the falling height and the number of falls is used as an explanatory variable, and the displacement amount of another section different from the section where the weight was dropped is used as the objective variable. will be held.

Furthermore, in this modification, the construction method M includes a step of constructing a second learning model 124 using the generated second teacher data 123.

Further, the processor 11 shown in FIG. 20 also functions as a peripheral displacement amount calculation means 116 and a notification means 117.

The peripheral displacement amount calculating means 116 uses the constructed second learning model 124 to calculate the amount of displacement caused in the peripheral section by the current impact. In other words, the peripheral displacement amount calculation means 116 is an example of a means for executing a step of calculating the displacement amount of another section caused by dropping a weight on a certain section using the second learning model.

The notification means 117 displays the estimated displacement amount of the surrounding section calculated by the peripheral displacement amount calculation means 116 on the display section 15 or displays it on the display section 55 of the management device 5 via the interface 13 to notify it. In other words, this notification means 117 is an example of means for executing the step of notifying the calculated estimated displacement amount of another section.

According to the construction method M in this modification, it is possible to know the estimated amount of displacement that will occur in other sections due to the current impact.

<2>
In the embodiment described above, the learning device 1 uses the first learning model 122 to estimate the "fall height" which is the appropriate height at which the weight 212 should be dropped. It is also possible to predict a state in which the amount of displacement is less than a threshold value.

FIG. 21 is a diagram showing an example of the functional configuration of the learning device 1 in a new modification. By executing a program, the processor 11 shown in FIG. 21 functions as a measurement value acquisition means 111, a teacher data generation means 112, and a learning model construction means 113, as well as a displacement amount prediction means 118 and a comparison means 119. , and functions as a notification means 117.

The displacement prediction means 118 uses the first learning model 122 to assume a plurality of fall heights for each of the plurality of sections, and predicts whether the section will be hit by any impact regardless of the fall heights. It is determined whether or not the amount of displacement is less than the threshold value even due to a collision. When determining that this state exists, the displacement prediction means 118 notifies the comparison means 119 and the notification means 117 that this state has been predicted. This displacement amount prediction means 118 executes a step of predicting whether or not a state will occur in which the amount of displacement caused by dropping the weight becomes less than a threshold value in any of the plurality of sections using the first learning model. This is an example of a means to do so.

The comparing means 119 compares the current height of the top surface 30 of the rubble mound 3 with a predetermined height that is a design height when the displacement amount predicting means 118 predicts the above-mentioned state. In other words, the comparison means 119 is an example of a means for performing a step of comparing the top end face of the rubble mound predicted to have a displacement amount less than the threshold value with the design compaction height.

When the displacement prediction means 118 predicts the above-mentioned state, the notification means 117 displays on the display section 15 or on the display section 55 of the management device 5 via the interface 13 that this state has been predicted. Notify users. Further, the notification means 117 displays the comparison result by the comparison means 119 on the display section 15 or the display section 55 of the management device 5 to notify the user. In other words, this notification means 117 is an example of means for performing a step of notifying that a state in which the amount of displacement is less than a threshold value is predicted.

According to this modification, it can be determined whether the height of the top surface 30 of the rubble mound 3 will not be displaced by a threshold value or more due to the impact caused by the free fall of the weight 212. Also, according to this modification, when the height of the top surface 30 of the rubble mound 3 is no longer displaced by more than the threshold value, how close is the height to the predetermined height that is the design height? I understand.

Note that in this modification, the displacement amount prediction means 118 uses the first learning model 122 to predict whether or not the above-mentioned state will occur in any of the plurality of sections. This can be predicted using In this case, the displacement amount prediction means 118 uses the second learning model to determine whether or not a state will occur in which the displacement amount of the other section due to dropping the weight in any of the plurality of sections becomes less than the threshold value. This is an example of means for performing the step of predicting.

<3>
In the embodiment described above, the construction method M is performed by the learning device 1, the leveling machine 2, the control device 4, and the management device 5, but it may be performed by other configurations. For example, construction method M is carried out using a hoist mounted on a hoist ship that is stopped on the sea surface W, a weight suspended from the hoist, and an information processing device installed inside the hoist ship. Good too.

Furthermore, construction method M constructs a first learning model 122 and a second learning model 124 by simultaneously using the first teaching data 121 and the second teaching data 123 generated by the teaching data generating means 112, and constructs both learning models. They may be used in combination.

DESCRIPTION OF SYMBOLS 1...Learning device, 11...Processor, 111...Measurement value acquisition means, 112...Teacher data generation means, 113...Learning model construction means, 114...Fall height estimation means, 115...Display control means, 116...Periphery displacement amount calculation Means, 117... Notification means, 118... Displacement amount prediction means, 119... Comparison means, 12... Memory, 121... First teacher data, 122... First learning model, 123... Second teacher data, 124... Second learning model , 13... Interface, 14... Operating unit, 15... Display unit, 2... Leveling machine, 20... Frame, 21... Hammering machine, 210... Hanging wire, 211... Weight height sensor, 212... Weight, 213 ... Weight fitting platform, 214... Platform height sensor, 215... Weight elevating winch, 216... Weight traveling transverse trolley, 22... Rake device, 23 (23-1, 23-2, 23-3, 23-4, 23-5)... leveling height sensor, 24... communication line, 25... positioning device, 26... control line, 27... direction inclinometer, 3... rubble mound, 30... top surface, 4... control device ,
41...Processor, 42...Memory, 43...Interface, 44...Operation unit, 45...Display unit, 5...Management device, 51...Processor, 52...Memory, 53...Interface, 54...Operation unit, 55...Display unit, C ...Central line, D1-D5...Arrow (movement path of the leveling machine sensor), P...Positioning point, R...Leveling frame, R1-R8...Division

Claims (8)

measuring the height of the top surface of the rubble mound before striking with a weight for each of a plurality of sections obtained by dividing the top surface of the rubble mound;
Dropping the weight from a set height and hitting each of the plurality of sections multiple times, and measuring the amount of displacement in the height of the rubble mound due to the hitting;
calculating a ratio of the displacement amount to the square root of the product of the height at which the weight is dropped and the number of times the weight is dropped for each of the plurality of sections and the entire area of the top surface;
The height at which the weight was dropped in the plurality of sections and the entire area, the number of times, the previous displacement amount indicating the amount of displacement in the height of the rubble mound due to the previous strike, and the previous displacement due to the previous strike. constructing a first learning model using the cumulative displacement amount up to the previous time indicating the cumulative amount of displacement in the height of the rubble mound, and training data in which the ratio is used as an explanatory variable and the displacement amount is used as an objective variable;
estimating the height at which the weight is dropped to the rubble mound using the first learning model;
Dropping the weight from the height estimated in the estimating step, and hitting the top surface of the rubble mound with the weight;
A construction method for a rubble mound with In the step of calculating the ratio, the ratio of the entire area is any one of an arithmetic mean value, a mode, a median value, a geometric mean value, or a maximum value of all the ratios of the plurality of sections. The construction method for the rubble mound described in Item 1. In the step of calculating the ratio, in addition to each of the plurality of sections and the entire area, the ratio is calculated for each group consisting of two or more sections in which the weight is moved and dropped among the plurality of sections. This step is to
In the step of constructing, the height at which the weight is dropped, the number of times, the previous displacement amount, the cumulative displacement amount up to the previous time, and the ratio of the division, the group, and the entire area are used as explanatory variables. The rubble mound construction method according to claim 1 or 2, further comprising the step of constructing the first learning model using training data in which the amount of displacement is an objective variable. In the step of calculating the ratio, the ratio of the group is either an arithmetic mean value, a mode, a median value, a geometric mean value, or a maximum value of the ratios of all sections belonging to the group. The construction method for the rubble mound described in Section 3. The height at which the weight was dropped, the number of times, the previous displacement amount, the cumulative displacement amount up to the previous time, and the ratio in the plurality of sections and the entire area are used as explanatory variables, and the weight is dropped. a step of constructing a second learning model using training data in which the objective variable is the displacement amount of a division different from the divided division;
Using the second learning model, calculating the amount of displacement of another section caused by dropping the weight into a certain section of the plurality of sections;
a step of notifying the calculated displacement amount of the other section;
The method for constructing a rubble mound according to any one of claims 1 to 4. Using the first learning model,
predicting whether a state will occur in any of the plurality of sections in which the amount of displacement due to dropping the weight will be less than a threshold;
Notifying that a state in which the amount of displacement is less than the threshold is predicted;
The method for constructing a rubble mound according to any one of claims 1 to 5, further comprising the step of comparing a state in which the displacement amount is less than the threshold value with a predicted top surface of the rubble mound and a predetermined height. . Using the second learning model,
predicting whether or not a state will occur in any of the plurality of sections in which the amount of displacement of the other section due to dropping the weight will be less than a threshold;
Notifying that a state in which the displacement amount of the other section is predicted to be less than the threshold value;
Comparing the top surface of the rubble mound predicted to be in a state in which the displacement amount of the other section is less than the threshold value with a predetermined height;
The method for constructing a rubble mound according to claim 5. The step of measuring the displacement amount of the height of the rubble mound due to the striking uses depths of at least three points on the upper surface of the weight measured by a measuring device. Construction method of rubble mound.

Images