JP2019039264A - Operation setting presentation device and program - Google Patents

Abstract

To provide an operation setting presentation device and a program capable of indicating a setting value of an accurate operation in a shield excavator.SOLUTION: A model creation unit is provided that creates a setting prediction model that predicts a setting value of an operation in a shield excavator by performing machine learning using learning data in which setting data on a setting value of an operation in the shield excavator in a drilling status is added to the drilling status data on the drilling status of the shield excavator.SELECTED DRAWING: Figure 2

Description

  The present invention relates to an operation setting presentation device and a program.

  Conventionally, when constructing a tunnel, etc. by earth pressure shield method (mud pressure shield method), the construction environment of the site where the shield excavator excavates (the state of the ground such as soil and water pressure) changes every moment depending on the location of the site. . Therefore, the operator manually operates the shield excavator while comparing the planned excavation instruction with the measurement data from various measuring devices measured in accordance with the construction environment and monitoring the measurement data. I do. For example, in the earth pressure type shield method, the operator performs an operation of discharging the earth generated by excavation so that the earth pressure in the chamber is within a predetermined range while monitoring the earth pressure in the chamber at the time of excavation. For example, the operator manually changes the set value of the rotational speed of the screw conveyor to control the amount of soil discharged in a predetermined time, and performs an operation so that the earth pressure in the chamber is within a predetermined range ( For example, Patent Document 1).

JP 2013-199772 A

However, in order to adjust the rotation speed of the screw conveyor so that the earth pressure in the chamber is within a predetermined range, it is necessary to balance the excavation speed and the earth discharging speed by the screw conveyor. Drilling speed is closely related to many data such as cutter torque and total thrust. Therefore, the rotational speed of the screw conveyor must be operated while monitoring a large amount of data, and the operation is difficult unless the operator is highly skilled.
Skilled operators tend to decrease, it is difficult to secure, and it takes a lot of time to request highly skilled operators. In addition, even a skilled operator may mistake the operation timing and setting values, and if the shield excavator is not properly operated, the accuracy and safety of the excavated tunnel design will be reduced. There are concerns.
For this reason, a method for appropriately presenting the set value of the operation in the shield excavator is required.

  This invention is made | formed in view of such a situation, The objective is to provide the operation setting presentation apparatus which can show the setting value of the accurate operation in a shield excavator, and a program. .

  In order to solve the above-described problem, in the operation setting presentation device according to an embodiment of the present invention, setting data related to a set value of an operation in the shield excavator in the excavation situation is attached to the excavation situation data related to the excavation situation of the shield excavator. And a model creation unit for creating a setting prediction model for predicting a setting value of an operation in the shield excavator by executing machine learning using the learned data.

  In the operation setting presentation device according to an embodiment of the present invention, the excavation status data includes environmental data related to a construction environment of the shield excavator and operation data related to excavation operation of the shield excavator corresponding to the environmental data. It is characterized by that.

  In the operation setting presentation device according to an embodiment of the present invention, the environmental data includes an instruction earth pressure at the time of excavation and a control earth pressure, and the operation data includes a measurement related to a screw conveyor of a shield excavator. A value is included, and the setting data includes a setting value of an operation related to the screw conveyor.

  In the operation setting presentation device according to an embodiment of the present invention, the model creating unit uses machine learning by using data selected from data in which the setting data is added to the excavation status data as learning data. It is characterized by performing.

  In the operation setting presentation device according to the embodiment of the present invention, the model creation unit selects and selects the excavation status data in which a difference between the control earth pressure and the indicated earth pressure is a predetermined threshold value or less. Machine learning is performed using learning data in which the setting data is added to the excavation status data.

  Further, the operation setting presentation device of one embodiment of the present invention uses the excavation status data acquisition unit that acquires the excavation status data every predetermined time, and the setting prediction model created by the model creation unit, The apparatus further includes a prediction unit that predicts a set value of an operation in the shield excavator in a situation indicated by the excavation state data, and an output unit that outputs a prediction result predicted by the prediction unit.

  The operation setting presentation device according to an embodiment of the present invention includes a setting data acquisition unit that acquires the setting data every predetermined time, and the setting in the excavation status data acquired by the excavation status data acquisition unit A storage unit that stores data associated with the setting data acquired by the data acquisition unit; and the prediction unit causes the model creation unit to perform machine learning using the data stored in the storage unit Thus, the setting prediction model is updated.

  A program according to an embodiment of the present invention is a program for causing a computer to function as the operation setting presentation device described above.

  As described above, according to the present invention, it is possible to indicate a set value for an accurate operation in a shield excavator.

It is a figure explaining shield excavator 20 for which operation setting presentation device 100 of an embodiment creates a setting prediction model. It is a block diagram which shows the structural example of the operation setting presentation apparatus 100 of embodiment. It is a figure which shows the structural example of the learning data table in the learning data storage part 107 of embodiment. It is a flowchart which shows the operation example of the operation setting presentation apparatus 100 of embodiment.

  Hereinafter, an operation setting presentation device and a program according to an embodiment will be described with reference to the drawings.

FIG. 1 is a diagram illustrating a shield excavator 20 that is a target for which the operation setting presentation device 100 (see FIG. 2) of the present embodiment creates a setting prediction model.
Fig.1 (a) has shown the conceptual diagram of the shield excavator 20 of the object which the operation setting presentation apparatus 100 of this embodiment produces a setting prediction model. FIG. 1B is a conceptual diagram of a propulsion jack that propels the shield excavator 20.

As shown in FIG. 1 (a), the shield excavator 20 constructs a primary lining S by assembling segments with an erector (not shown) at the rear of the cylindrical skin plate 2 in the direction of arrow D1. On the other hand, it is a mechanism for excavating the natural ground 30. In the shield excavator 20, the mud clay chamber 7 is provided at the rear of the annular and face plate type cutter 10 having the cutter bit 23 in the direction of the arrow D 1. A plurality of earth pressure gauges 70 are installed in the mud clay chamber 7. The earth pressure gauge 70 measures the mud pressure in the mud mud chamber 7. Mud material 9 is injected into the mud chamber 7 from the mud material injection pipe 8 and mixed by a mixing blade (not shown), so that the excavated earth and sand is converted into mud. The shield excavator 20 performs excavation by stabilizing the natural ground by balancing the mud pressure in the mud mud chamber 7 with the earth pressure and the water pressure on the excavation surface (face face) of the natural ground 30. The excavated residual soil accumulated in the mud clay chamber 7 is introduced into the screw conveyor 60 and discharged through the conveyors 62 and 63 to the outside of the excavating tunnel. The gantry M supports the screw conveyor 60 and the conveyors 62 and 63.
Further, the shield excavator 20 adds a bubble made of a special foaming material to the excavated soil instead of injecting the mud material 9, and improves the fluidity of the excavated soil 7 (chamber). There are also cases where excavation is performed by adjusting the earth pressure inside.

  Here, as for the screw conveyor 60, the rotational speed of a screw is controlled by hydraulic control. When the screw rotation speed of the screw conveyor 60 (hereinafter simply referred to as the screw rotation speed) increases, the mud mud pressure in the mud mud chamber 7 decreases, and the mud pressure decreases, and when the screw rotation speed decreases, the mud mud chamber 7 The mud pressure increases due to the stagnation of mud. That is, the mud pressure is controlled by performing an operation for setting the rotational speed of the screw.

  As shown in FIG. 1B, the propulsion jack is disposed between the skin plate 2 and the segment so as to surround the inner periphery of the skin plate 2. When the propulsion jack is propelled (extended) by hydraulic operation, the surface of the skin plate 2 is pushed and the shield excavator 20 propels.

  Here, a force point for propelling the surface of the skin plate 2 is set according to which position of the propulsion jack is propelled, and the propulsion direction of the shield excavator 20 is determined. The propulsion speed of the shield excavator 20 is determined by the speed at which the propulsion jack is propelled. That is, the propulsion direction of the shield excavator 20 is controlled by performing an operation for setting which propulsion jack is selected. Further, the propulsion speed of the shield excavator 20 is controlled by performing an operation for setting the propulsion speed of the propulsion jack. In other words, in the shield excavator 20, the earth pressure is controlled by balancing the excavation speed of the shield excavator 20 and the earth discharging speed accompanying the rotation of the screw, and the ground is stabilized by controlling the earth pressure. And drilling.

In the present embodiment, excavation status data regarding the excavation status at the time of excavation of the shield excavator 20 is acquired. The excavation status data includes environmental data related to the construction environment of the shield excavator and operation data related to the excavation operation of the shield excavator corresponding to the environmental data.
The environmental data is, for example, an instruction earth pressure and a control earth pressure. Here, the indicated earth pressure is the earth pressure of the natural ground 30 that works in the direction of the arrow A, and is determined in consideration of the influence of the earth subsidence on the earth pressure derived based on the depth and geology. The control earth pressure is a representative value of the mud pressure in the mud mud chamber 7. For example, the control earth pressure is an average value of the mud pressure measured at predetermined time intervals (for example, every second) of the earth pressure gauge 70 installed near the center of the mud mud chamber 7.
The operation data includes, for example, a measured value of the rotational speed of the screw, the hydraulic pressure of the screw conveyor 60, the opening of the gate (exit) of the screw conveyor 60, the stroke of the propulsion jack, the torque of the cutter 10, the propulsion speed of the shield excavator 20, The total propulsive force of the propulsion jack, the bubble injection rate, etc. These environmental data and operation data are measured every predetermined time (for example, every second).

  In the present embodiment, setting data related to the operation of the shield excavator 20 is acquired. The setting data is, for example, a setting value for the screw rotation speed, a setting value for selecting the propulsion jack, and a setting value for the propulsion speed of the propulsion jack. These setting data are acquired every time equivalent to every predetermined time when the operation data is measured.

FIG. 2 is a block diagram illustrating a configuration example of the operation setting presentation device 100 according to the embodiment.
The operation setting presentation device 100 includes, for example, an excavation status data input unit 101, a setting data input unit 102, a prediction result output unit 103, a processing unit 104, a model creation unit 105, a setting prediction unit 106, and learning data. And a storage unit 107.

  The excavation status data input unit 101, for example, at the timing when a timing signal indicating the passage of a predetermined time (for example, 1 second) from a timer (not shown) of the operation setting presentation device 100 is supplied, is described above. To get. The excavation status data input unit 101 receives, for example, a measurement result measured by a soil pressure gauge 70 installed near the center of the mud clay chamber 7. In addition, detection values detected by various sensors (not shown) installed in the screw conveyor 60 or the propulsion jack are input to the excavation status data input unit 101, for example. The excavation status data input unit 101 stores the acquired excavation status data in the learning data table in the learning data storage unit 107 in association with the acquired time (time stamp).

  The setting data input unit 102 acquires the setting data described above, for example, at the timing when the excavation status data input unit 101 acquires the excavation status data. The setting data input unit 102 receives setting values for various operations that are input to a touch panel or the like on an operation panel (not shown) of the shield excavator 20. The setting data input unit 102 causes the learning data table in the learning data storage unit 107 to store the acquired setting data in association with the acquired time.

  The prediction result output unit 103 outputs the content of the operation predicted by the setting prediction unit 106. The prediction result output unit 103 is a display device, for example, and displays the content of the operation predicted by the setting prediction unit 106. Further, the prediction result output unit 103 is, for example, a speaker, and outputs the content of the operation predicted by the setting prediction unit 106 by voice or alarm sound.

  The processing unit 104 generates learning data based on the excavation status data acquired by the excavation status data input unit 101 and the setting data acquired by the setting data input unit 102. For example, the processing unit 104 extracts feature quantities in a plurality of time-series excavation status data. The feature amount is a characteristic component included in the excavation status data. For example, the difference between the command earth pressure and the control earth pressure, and a value obtained by moving average the excavation status data for a short time (for example, 10 seconds) or a long time ( For example, it can be obtained by calculating a moving average value or the like. The processing unit 104 stores the extracted feature amount in the learning data table in the learning data storage unit 107 in association with the corresponding time.

Further, the processing unit 104 determines whether or not to use the excavation status data and the setting data acquired at each timing as learning data. The determination as to whether or not to use as learning data is performed based on, for example, the degree of deviation between the command earth pressure and the control earth pressure.
When the difference between the designated earth pressure and the control earth pressure at a certain time (hereinafter referred to as earth pressure difference) is equal to or greater than a predetermined threshold, the processing unit 104 does not use the excavation status data and the setting data at that time as learning data. Is determined. Further, when the earth pressure difference at a certain time is less than a predetermined threshold, the processing unit 104 determines to use the excavation status data and the setting data at that time as learning data. The processing unit 104 stores the result of the determination made on the learning data table in the learning data storage unit 107 in association with the corresponding time.
Note that the processing unit 104 may perform determination based on not only the earth pressure difference but also the frequency and variation of the operation. Further, the processing unit 104 may make a determination based on the result of cluster analysis of the excavation status data and the setting data.

The model creation unit 105 performs machine learning using the data stored in the learning data table in the learning data storage unit 107 as learning data, thereby setting prediction for predicting the set value of the operation in the shield excavator 20 Create a model. Here, as a machine learning technique for creating the setting prediction model, any of commonly used techniques such as decision tree learning, neural network, genetic programming, and support vector machine may be used.
Further, the model creation unit 105 executes machine learning using the excavation status data determined to be used as learning data by the processing unit 104 and the setting data corresponding to the excavation status data as learning data. Thereby, the model preparation part 105 can learn the excavation condition data and setting data in case earth pressure is controlled more appropriately and accurately, for example.

  The setting prediction unit 106 uses the setting prediction model created by the model creation unit 105 to predict a setting value in the operation of the shield excavator 20 in the situation indicated by the excavation situation data. The setting prediction unit 106 sets data output from the setting prediction model when the excavation state data acquired at a certain time is input to the setting prediction model as data indicating a predicted operation.

The learning data storage unit 107 stores a learning data table for causing the model creation unit 105 to create a setting prediction model.
FIG. 3 is a diagram illustrating a configuration example of a learning data table in the learning data storage unit 107 of the embodiment. In the example of FIG. 3, the learning data table includes items of time stamp, excavation status data, excavation status data short-term moving average, excavation status data long-term moving average, earth pressure difference, setting data, and classification. The time stamp stores the time when the excavation status data and the setting data are acquired. The excavation status data stores excavation status data acquired at the time indicated by the time stamp. The excavation status data stores each of a plurality of excavation status data (excavation status data # 1, # 2,..., #N). Here, N is an arbitrary natural number.

  In the excavation status data short-term moving average, a moving average value of each excavation status data for a short time (for example, 10 seconds) is stored. In the excavation status data long-term moving average, a moving average value of each excavation status data for a long time (for example, 60 seconds) is stored. The difference between the command earth pressure and the control earth pressure is stored in the earth pressure difference. The setting data stores excavation status data acquired at the time indicated by the time stamp. Each of the plurality of setting data (excavation status data # 1,..., #M) is stored in the setting data. Here, M is an arbitrary natural number. In the classification, a number indicating the classification performed by the processing unit 104 is stored. For example, the number 0 indicates that the degree used as learning data is lower than the number 3.

FIG. 4 is a flowchart illustrating an operation example of the operation setting presentation device 100 according to the embodiment.
First, the operation setting presentation device 100 acquires learning data (step S1). Here, the learning data acquired by the operation setting presentation device 100 may be excavation status data and setting data in the shield excavator 20 for which the operation setting presentation device 100 predicts a setting value in the operation. It may be standard excavation status data and setting data during excavation in a shield excavator.

Next, the operation setting presentation device 100 creates a setting prediction model by executing machine learning using the acquired learning data (step S2).
Next, the operation setting presentation device 100 acquires excavation status data and setting data in the shield excavator 20 that is a target for predicting a setting value in the operation (step S3). The acquired excavation status data and setting data are stored in the learning data storage unit 107. In addition, the operation setting presentation device 100 stores the feature data extracted based on the acquired excavation status data and information indicating the classification as learning data in the learning data storage unit 107, so that the learning data storage unit 107. The learning data is stored in the learning data table (step S4).

Next, the operation setting presentation device 100 determines whether or not to update the setting prediction model (step S5). The operation setting presentation device 100 determines to update the setting prediction model when the learning data table in the learning data storage unit 107 stores the amount of learning data necessary for creating the model.
If it is determined that the setting prediction model is to be updated, the operation setting presentation device 100 updates the setting prediction model (step S6). The operation setting presentation device 100 causes the model creation unit 105 to perform machine learning using the learning data stored in the learning data table in the learning data storage unit 107, thereby creating a new setting prediction model. Then, the operation setting presentation device 100 updates the setting prediction model by replacing the setting prediction model with a new setting prediction model. Here, the newly created setting prediction model is a model created using the excavation status data and the setting data acquired with the excavation of the shield excavator 20. For this reason, the operation setting presentation device 100 can present a set value of a more accurate operation by performing a highly accurate prediction according to the excavation environment and the characteristics of the shield excavator 20 to be predicted. Become.

  And the operation setting presentation apparatus 100 predicts the setting value in operation of the shield excavator 20 by inputting the acquired excavation condition data into the setting prediction model (step S7). The operation setting presentation device 100 outputs data indicating the set value of the predicted operation (step S8).

As described above, the operation setting presentation device 100 according to the embodiment performs machine learning on the operation on the shield excavator 20 by using the learning data in which the setting data in the excavation status is added to the excavation status data. And a model creation unit 105 that creates a setting prediction model for predicting a setting value in the operation of the shield excavator 20.
Thereby, the operation setting presentation device 100 according to the embodiment can indicate the set value of the operation with high accuracy in the shield excavator 20. This is because the model creation unit 105 can create a model indicating the relationship between the excavation status and the operation set value. By presenting the set value output by inputting the excavation status to the model created by the model creating unit 105, it is possible to indicate the set value of the operation with high accuracy in the shield excavator 20.

  Further, in the operation setting presentation device 100 of the embodiment, the excavation status data includes environmental data related to the construction environment of the shield excavator 20 and operation data related to the excavation operation of the shield excavator 20 corresponding to the environmental data. Thereby, the operation setting presentation device 100 according to the embodiment can create a setting prediction model based on the environment of the excavation site and the characteristics of the shield excavator 20, and shield based on the setting data output from the model. It is possible to indicate a set value of an accurate operation in the excavator 20.

  Further, in the operation setting presentation device 100 of the embodiment, the environmental data includes the instruction earth pressure and the instruction earth pressure at the time of excavation, and the operation data includes the measurement values related to the screw conveyor 60 of the shield excavator 20. The setting data includes setting values for operations related to the screw conveyor 60. Thereby, the operation setting presentation device 100 of the embodiment can create a setting prediction model based on the relationship between the highly relevant instruction earth pressure and instruction earth pressure, and the setting value of the screw conveyor 60, Based on the setting data output from the model, it is possible to indicate a set value for a precise operation in the shield excavator 20.

In the operation setting presentation device 100 according to the embodiment, the model creation unit 105 executes machine learning using data determined to be used as learning data based on the difference between the designated earth pressure and the control earth pressure. Thereby, the operation setting presentation device 100 according to the embodiment can create a setting prediction model using more appropriate data, and the operation of the accurate operation in the shield excavator 20 based on the setting data output from the model. A set value can be indicated.
Further, in the operation setting presentation device 100 of the embodiment, the model creation unit 105 selects excavation status data in which the earth pressure difference is equal to or less than a predetermined threshold, and learns data in which the setting data is added to the selected excavation status data. To perform machine learning. Thereby, the operation setting presentation device 100 according to the embodiment creates a setting prediction model using more appropriate data by using data when the earth pressure is appropriately controlled to be closer to the target value as learning data. Therefore, it is possible to indicate the set value of the operation with high accuracy in the shield excavator 20 based on the setting data output from the model.

  In addition, the operation setting presentation device 100 according to the embodiment uses the excavation status data input unit 101 that acquires excavation status data every predetermined time and the setting prediction model created by the model creation unit to indicate the excavation status data. A setting prediction unit 106 that predicts a setting value in the operation of the shield excavator 20 in a situation in which the prediction is performed, and a prediction result output unit 103 that outputs a prediction result predicted by the setting prediction unit 106. Thereby, the operation setting presentation device 100 according to the embodiment can predict the setting value in the operation by the setting prediction unit 106 based on the excavation status of the shield excavator 20 acquired by the excavation status data input unit 101. An operation predicted by the prediction result output unit 103 can be output. For this reason, the operation setting presentation device 100 according to the embodiment can present a recommended value for an operation set by the operator, and can function as an operation support device that implements operation guidance, for example. Further, automatic operation can be performed by converting the recommended value of the operation into a setting signal in the operation panel of the shield excavator 20 and outputting it to the operation panel.

  In addition, the operation setting presentation device 100 according to the embodiment acquires a setting data input unit 102 that acquires setting data every predetermined time, and the setting data input unit 102 acquires the excavation status data acquired by the excavation status data input unit 101. The learning data storage unit 107 that stores data in which the set data is associated is further included, and the setting prediction unit 106 causes the model creation unit 105 to execute machine learning using the data stored in the learning data storage unit 107. To update the setting prediction model. Thereby, the operation setting presentation device 100 according to the embodiment of the shield excavator 20 to be used for predicting the setting value in the operation, the excavation status data accumulated as the excavation progresses, and the settings corresponding to the excavation status data The set prediction model can be updated based on the data, and accurate prediction can be performed. For this reason, the set value of the operation with high accuracy in the shield excavator 20 can be shown.

  You may make it implement | achieve all or one part of the process which the operation setting presentation apparatus 100 in embodiment mentioned above performs. In that case, a program for realizing this function may be recorded on a computer-readable recording medium, and the program recorded on this recording medium may be read into a computer system and executed. Here, the “computer system” includes an OS and hardware such as peripheral devices. The “computer-readable recording medium” refers to a storage device such as a flexible medium, a magneto-optical disk, a portable medium such as a ROM and a CD-ROM, and a hard disk incorporated in a computer system. Furthermore, the “computer-readable recording medium” dynamically holds a program for a short time like a communication line when transmitting a program via a network such as the Internet or a communication line such as a telephone line. In this case, a volatile memory inside a computer system serving as a server or a client in that case may be included and a program held for a certain period of time. Further, the program may be a program for realizing a part of the above-described functions, and may be a program capable of realizing the functions described above in combination with a program already recorded in a computer system. It may be realized using a programmable logic device such as an FPGA.

  The embodiment of the present invention has been described in detail with reference to the drawings. However, the specific configuration is not limited to this embodiment, and includes designs and the like that do not depart from the gist of the present invention.

DESCRIPTION OF SYMBOLS 100 ... Operation setting presentation apparatus, 101 ... Excavation condition data input part, 102 ... Setting data input part, 103 ... Prediction result output part, 104 ... Processing part, 105 ... Model preparation part, 106 ... Setting prediction part, 107 ... Learning data Memory part.

Claims (8)

Setting the operation in the shield excavator by executing machine learning using the learning data to which the setting data relating to the operation setting value in the shield excavator in the excavation situation is attached to the excavation status data relating to the excavation status of the shield excavator An operation setting presentation device comprising a model creating unit that creates a setting prediction model for predicting a value. 2. The operation setting presentation according to claim 1, wherein the excavation status data includes environmental data related to a construction environment of a shield excavator and operation data related to excavation operation of the shield excavator corresponding to the environmental data. apparatus. The environmental data includes a command earth pressure and a control earth pressure,
The operation data includes measurement values related to the screw conveyor of the shield excavator,
The operation setting presenting device according to claim 2, wherein the setting data includes a setting value of an operation related to the screw conveyor. The operation according to claim 3, wherein the model creation unit executes machine learning by using, as learning data, data selected from data in which the setting data is added to the excavation status data. Setting presentation device. The model creation unit selects the excavation status data in which a difference between the control earth pressure and the command earth pressure is a predetermined threshold value or less, and learning data in which the setting data is added to the selected excavation situation data 5. The operation setting presentation device according to claim 3 or 4, wherein machine learning is executed using. An excavation status data acquisition unit for acquiring the excavation status data every predetermined time;
Using the setting prediction model created by the model creation unit, a prediction unit that predicts a setting value of the operation in the shield excavator in the situation shown in the excavation situation data;
The operation setting presentation device according to claim 1, further comprising: an output unit that outputs a prediction result predicted by the prediction unit. A setting data acquisition unit that acquires the setting data every predetermined time;
A storage unit for storing data in which the setting data acquired by the setting data acquisition unit is associated with the excavation status data acquired by the excavation status data acquisition unit;
The operation setting presentation device according to claim 6, wherein the prediction unit updates the setting prediction model by causing the model creation unit to perform machine learning using data stored in the storage unit. .   The program for functioning a computer as the operation setting presentation apparatus as described in any one of Claims 1-7.

Images