JP2022072640A - Rolling machine and asphalt mixture density estimation system - Google Patents

Abstract

To provide an asphalt mixture density estimation method, a rolling machine, and an asphalt mixture density estimation system that can estimate the density of an asphalt mixture forming a road surface with a small workload.SOLUTION: A rolling machine 10 includes a density estimation device 11 that is attached to a rolling machine body 1 and estimates the density of an asphalt mixture A of a road surface 30. The density estimation device 11 includes: a transmitting unit 3a that transmits an electromagnetic wave W1 toward the road surface 30; a receiving unit 3b that receives a reflection wave W2 of the electromagnetic wave W1 reflected from the road surface 30; and a calculation unit 4 that estimates the density of the asphalt mixture of the road surface 30 based on reflection wave information indicating characteristics of the reflection wave W2.SELECTED DRAWING: Figure 1

Description

The present invention relates to a method for estimating the density of an asphalt mixture, a compaction machine, and a system for estimating the density of an asphalt mixture.

The road surface formed of the asphalt mixture is compacted by a compaction machine at the time of construction so as to have a density equal to or higher than a predetermined density. Conventionally, in order to confirm the density of the asphalt mixture after construction, a sample is cut out from the asphalt mixture after construction, and the density of the asphalt mixture is measured based on the mass of the sample measured at the test site (Patent Document). 1).

Japanese Unexamined Patent Publication No. 10-010032

However, when a sample is cut out from an already constructed asphalt mixture, there is a problem that the work load for measuring the density of the asphalt mixture becomes excessive.

The problem to be solved by the present invention is to provide a method for estimating the density of an asphalt mixture, a compaction machine, and a system for estimating the density of the asphalt mixture, which can estimate the density of the asphalt mixture forming the road surface with a small work load. That is.

[1] In order to solve the above problems, the asphalt mixture density estimation method according to the present invention estimates the density of the asphalt mixture forming the road surface, emits an electromagnetic wave toward the road surface, and causes the above. This is a method for estimating the density of an asphalt mixture, which receives the reflected wave of the electromagnetic wave reflected from the road surface and estimates the density of the asphalt mixture on the road surface based on the reflected wave information indicating the characteristics of the reflected wave.

[2] In the above invention, the reflected wave information may be information indicating a change over time in the intensity of the reflected wave.

[3] In the above invention, the feature amount is extracted from the reflected wave information indicating the change in the intensity of the reflected wave with time, and the feature amount is input to the trained model to estimate the density of the asphalt mixture and trained model. May be machine-learned using teacher data relating the density of the asphalt mixture to the features.

[4] In the above invention, the intensity of the reflected wave at at least one preset feature time point may be extracted as the feature amount.

[5] In the above invention, the feature is that the difference in the intensity of the reflected wave corresponding to each of the densities of the asphalt mixture becomes equal to or more than a predetermined threshold based on at least two reflected wave information acquired in advance. It may be set as a time point.

[6] In the above invention, the maximum value of the intensity of the reflected wave in at least one feature period set in advance may be extracted as the feature amount.

[7] In the above invention, the difference in the maximum value of the intensity of the reflected wave corresponding to each of the densities of the asphalt mixture is predetermined in the characteristic period based on the at least two reflected wave information acquired in advance. The feature period may be set so as to be equal to or greater than the threshold value.

[8] In the above invention, the wavelength of the electromagnetic wave transmitted toward the road surface may be 10 to 100 cm.

[9] Further, the compaction machine according to the present invention compacts the road surface formed by the asphalt mixture, and is attached to the compaction machine main body and the compaction machine main body, and the asphalt mixture on the road surface. The density estimation device includes a transmission unit that emits an electromagnetic wave toward the road surface, a reception unit that receives the reflected wave of the electromagnetic wave reflected from the road surface, and a reception unit. Is a compaction machine having a calculation unit for estimating the density of the asphalt mixture on the road surface based on the reflected wave information indicating the characteristics of the reflected wave received by the machine.

[10] In the above invention, an output device that outputs density estimation information indicating the density of the asphalt mixture estimated by the calculation unit of the density estimation device may be further provided.

[11] In the above invention, the density estimation information output by the output device may include a road surface map showing the density distribution of the asphalt mixture on the road surface.

[12] In the above invention, the calculation unit of the density estimation device may set the movement path of the compaction machine on the road surface based on the density of the asphalt mixture.

[13] Further, the asphalt mixture density estimation system according to the present invention estimates the density of the asphalt mixture forming the road surface, and is attached to a compaction machine for compacting the road surface toward the road surface. An electromagnetic wave receiving / transmitting device having a transmitting unit for transmitting an electromagnetic wave and a receiving unit for receiving the reflected wave of the electromagnetic wave reflected from the road surface, and reflected wave information indicating the characteristics of the reflected wave are acquired from the electromagnetic wave receiving / transmitting device. It is an asphalt mixture density estimation system including an arithmetic device for estimating the density of the asphalt mixture on the road surface based on the reflected wave information.

According to the present invention, since the density of the asphalt mixture is estimated based on the characteristics of the reflected wave of the electromagnetic wave reflected from the road surface, there is an effect that the density of the asphalt mixture forming the road surface can be estimated with a small work load. ..

It is a figure which shows the structure of the compaction machine which concerns on 1st Embodiment. It is a figure which shows the structure of the transmitting part and the receiving part of the electromagnetic wave receiving and transmitting apparatus shown in FIG. It is a figure which shows the graph which shows the time-dependent change of the intensity of the electromagnetic wave received by the receiving part of the electromagnetic wave receiving and transmitting apparatus shown in FIG. 2, and the characteristic time point on the graph. It is a figure which shows the electromagnetic wave received and transmitted by the electromagnetic wave receiving and transmitting apparatus shown in FIG. 2, and the unevenness of the surface of a road surface. It is a figure which shows the trained model which the density estimator provided in the compaction machine shown in FIG. 1 uses for estimating the density of an asphalt mixture. It is a figure which shows the graph which shows the time-dependent change of the intensity of the electromagnetic wave received by the receiving part of the electromagnetic wave receiving and transmitting apparatus shown in FIG. 2, and the characteristic period on the graph. 7 (a) is a diagram showing an example of a road surface map output by an output device 5 provided in the compaction machine shown in FIG. 1, and FIG. 7 (b) is a road surface map shown in FIG. 7 (a). It is a figure which shows the example of the movement route displayed in. It is a figure which shows the structure of the density estimation system of the asphalt mixture which concerns on 2nd Embodiment.

<< First Embodiment >>
The compaction machine 10 according to the present embodiment and the method for estimating the density of the asphalt mixture using the compaction machine 10 will be described with reference to FIGS. 1 to 7. In FIG. 1, the left side on the paper surface is the front of the compaction machine 10, and the right side on the paper surface is the rear side of the compaction machine 10.
As shown in FIG. 1, the compaction machine 10 has a compaction machine main body 1 and a substantially cylindrical roller 2 rotatably provided in front of and behind the compaction machine main body 1. Further, the compaction machine main body 1 is provided with an operator seat 1a for the operator to sit on. When the asphalt mixture A is applied to the road surface 30, the asphalt mixture A is spread and leveled to form the road surface 30, and then the compaction machine 10 moves on the road surface 30, so that the asphalt mixture A is compacted by the rollers 2. As the asphalt mixture A is compacted by the roller 2, the density of the asphalt mixture A increases.

The compaction machine 10 is, for example, a tire roller or a road roller (macadam roller, tandem roller). Further, the type of the compaction machine 10 to be used may be changed according to the stage of the compaction process (initial compaction, secondary compaction, finish compaction). For example, a road roller may be used for the initial rolling compaction, and a tire roller may be used for the secondary rolling compaction and the finishing rolling compaction.

Further, the compaction machine main body 1 includes an electromagnetic wave receiving / transmitting device 3, an arithmetic unit 4 wirelessly or wiredly connected to the electromagnetic wave receiving / transmitting device 3, and an output device 5 wirelessly or wiredly connected to the arithmetic unit 4. Is installed. The electromagnetic wave receiving / transmitting device 3 is provided in front of the compaction machine main body 1 so as to face the road surface 30. The electromagnetic wave receiving / transmitting device 3 has a transmitting unit 3a for transmitting electromagnetic waves and a receiving unit 3b for receiving electromagnetic waves. The arithmetic unit 4 is, for example, a computer. The output device 5 is a terminal having a display, and is detachably attached to the front of the operator's seat 1a of the compaction machine main body 1. The output device 5 may be a display fixed in front of the operator's seat 1a of the compaction machine main body 1. The output device 5 outputs density estimation information indicating the density of the asphalt mixture A estimated by the calculation unit 4. That is, on the display of the output device 5, density estimation information indicating the density of the asphalt mixture A is displayed as image information or text information. Further, the output device 5 has a speaker, and may output density estimation information by voice.
The transmission unit 3a, the reception unit 3b, and the calculation unit 4 of the electromagnetic wave transmission / reception device 3 constitute a density estimation device 11.

As shown in FIG. 2, the transmission unit 3a of the electromagnetic wave receiving / transmitting device 3 transmits the electromagnetic wave W1 toward the road surface 30. The receiving unit 3b of the electromagnetic wave receiving / transmitting device 3 receives the reflected wave W2 of the electromagnetic wave W1 reflected on the road surface 30. The transmitting unit 3a and the receiving unit 3b are plate-shaped bowtie antennas having an antenna circuit, but the present invention is not limited to this, and any shape and size can be used as long as the reflected wave W2 can be accurately acquired. Further, the radially outer side of the electromagnetic wave receiving / transmitting device 3 may be covered with a tubular electromagnetic wave shield (not shown). The electromagnetic wave W1 transmitted by the transmitting unit 3a of the electromagnetic wave receiving / transmitting device 3 is a UHF (Ultra High Frequency) having a frequency of 300 MHz to 3 GHz and a wavelength of 10 cm to 100 cm.

Next, a method of estimating the density of the asphalt mixture A by the density estimation device 11 provided in the compaction machine 10 will be described with reference to FIGS. 3 to 6.

FIG. 3 is a waveform graph showing changes over time in voltage values created using an oscilloscope based on information on electromagnetic waves (electromagnetic waves W1, reflected waves W2) received by the receiving unit 3b. The waveform on the positive side of the voltage value shown in FIG. 3 is influenced by the electromagnetic wave W1 (electromagnetic wave other than the reflected wave W2) directly received by the receiving unit 3b from the transmitting unit 3a. On the other hand, the waveform on the negative side of the voltage value shown in FIG. 3 shows the characteristics of the reflected wave W2 received by the receiving unit 3b. That is, the absolute value on the negative side of the voltage value shown in FIG. 3 indicates the intensity of the reflected wave W2, and the waveform on the negative side of the voltage value shown in FIG. 3 indicates the change over time in the intensity of the reflected wave W2. ing. Therefore, the information of the electromagnetic wave (electromagnetic wave W1, reflected wave W2) received by the receiving unit 3b includes the reflected wave information indicating the time-dependent change in the intensity of the reflected wave W2.

The graph of the broken line shown in FIG. 3 shows the electromagnetic wave (electromagnetic wave W1, reflection) received by the receiving unit 3b when the electromagnetic wave W1 is projected from the transmitting unit 3a toward the asphalt mixture A having a density corresponding to the compaction degree of 100%. It is a figure which shows the time-dependent change of the voltage value of a wave W2). On the other hand, the solid line graph shows the electromagnetic waves (electromagnetic waves W1 and reflected waves W2) received by the receiving unit 3b when the electromagnetic wave W1 is projected from the transmitting unit 3a toward the asphalt mixture A having a density corresponding to the compaction degree of 85%. It is a figure which shows the time-dependent change of the voltage value of). The degree of compaction is the ratio of the density when the reference density (target density) at the time of construction of the asphalt mixture A is 100%. The density corresponding to the compaction degree of 100% varies depending on the type of the asphalt mixture A and the situation at the time of production, but is, for example, 2.255 g / cm ³ .

From the graph of FIG. 3, it can be seen that the difference in the density of the asphalt mixture A affects the waveform of the negative voltage value, that is, the change over time in the intensity of the reflected wave W2. Here, as shown in FIG. 4, since the asphalt mixture A contains the aggregate Ag, unevenness is formed on the surface of the road surface 30. As the density of the asphalt mixture A increases, the distance between the aggregates Ag becomes smaller, so that the unevenness of the surface of the road surface 30 increases. Therefore, the unevenness of the surface of the road surface 30 according to the density of the asphalt mixture A affects the change over time in the intensity of the reflected wave W2, as shown in FIG.
Further, the waveform of the voltage value graph shown in FIG. 3 is also affected by the temperature, humidity, atmospheric pressure, air flow, and the like.

The calculation unit 4 estimates the density of the asphalt mixture A by utilizing the change over time in the intensity of the reflected wave W2 according to the density of the asphalt mixture A. Specifically, as shown in FIG. 3, the arithmetic unit 4 is based on the intensity of the reflected wave W2 (absolute value of the voltage value on the negative side) at the three feature time points P1, P2, and P3 set in advance. Estimate the density of the asphalt mixture A. The feature time points P1, P2 and P3 are the differences in the intensity (absolute value of the voltage value on the negative side) of the reflected wave W2 corresponding to each of the densities of the asphalt mixture A at the feature time points P1, P2 and P3. Is set to be equal to or greater than a predetermined threshold value. In FIG. 3, as a result of comparing the broken line graph corresponding to the density of 100% compaction and the solid line graph corresponding to the density of 85% compaction, the intensity of the reflected wave W2 (absolute value of the voltage value on the negative side) is shown. ) When the difference dP1, dP2, dP3 is 1.0 [V] or more is set as the feature time point P1, P2, P3. The "predetermined threshold value" in the present embodiment is not limited to 1.0 [V], and is appropriately set according to the performance of the antenna and the measuring instrument of the electromagnetic wave transmitting / receiving device 3.

It should be noted that, as a result of the operator visually observing the waveform of the graph of the voltage value based on at least two reflected wave information acquired in advance by the test, the time point at which the difference in the density of the asphalt mixture A appears most prominently is the characteristic time point. It may be set in advance as P1, P2, P3. Further, the arithmetic unit 4 may set the feature time points P1, P2, and P3 based on at least two reflected wave information acquired in advance by the test. The feature time points to be set are not limited to three, and may be one, two, or four or more.

As shown in FIG. 5, the arithmetic unit 4 uses machine learning to estimate the density D [mg / cm ³ ] of the asphalt mixture A. Specifically, the calculation unit 4 obtains the intensity of the reflected wave W2 (absolute value of the voltage value on the negative side) E1 at the feature time points P1, P2, and P3 from the reflected wave information indicating the change in the intensity of the reflected wave W2 with time. [V], E2 [V], and E3 [V] are extracted as feature quantities. Then, the arithmetic unit 4 inputs the voltage values E1 [V], E2 [V], and E3 [V] indicating the features into the trained model 1001, and thereby uses a neural network to input the density D of the asphalt mixture A. Calculate [mg / cm ³ ].

The intensity of the reflected wave W2 (absolute value of the voltage value on the negative side) E1 [V], E2 [V], E3 [V] input as the feature amount, and the density D output by the trained model 1001 of the calculation unit 4. An example of [g / cm ³ ] is shown below.

The arithmetic unit 4 applies to a plurality of combinations of reflected wave W2 intensity data (E1 [V], E2 [V], E3 [V]) based on a plurality of reflected wave information acquired at the same location. Then, data that has been subjected to processing such as averaging and a low-pass filter may be created, and these data may be input to the trained model 1001 as feature quantities. As a result, the influence of temperature, humidity, atmospheric pressure, air flow, etc. can be further reduced, and the accuracy of estimating the density of the asphalt mixture A can be improved.

The trained model 1001 is machine-learned using the teacher data 1003 that correlates the density of the asphalt mixture A with respect to the intensity of the reflected wave W2 at feature time points P1, P2, P3. In order to acquire the teacher data 1003, first, an electromagnetic wave (electromagnetic wave W1, reflected wave) received by the receiving unit 3b at the same position or at a plurality of different positions using a specimen of asphalt mixture A having a known density. Measurement data showing the change over time of the voltage value of W2) is acquired, for example, for 10,000 times. Then, from the measurement data for 10,000 times, the density of the asphalt mixture A and the intensity of the reflected wave W2 at the feature time points P1, P2, P3 (absolute value of the voltage value on the negative side) E1 [V], E2 [V], E3. Machine learning data showing the relationship with [V] is extracted. Further, the machine learning data for 10,000 times is divided into the teacher data for 8,000 times and the test data for 2000 times, and the trained model 1001 is created by learning several tens to hundreds times using these data.

An example of teacher data 1003 is shown below.

The intensity E1 [V] of the reflected wave W2 at the feature time point P1 tends to be higher as the density D [g / cm ³ ] is higher. The intensity E2 [V] of the reflected wave W2 at the time point P2 tends to be lower as the density D [g / cm ³ ] is higher. The intensity E3 [V] of the reflected wave W3 at the time point P3 tends to be lower as the density D [g / cm ³ ] is higher.

The graph shown in FIG. 6 is the same as the graph shown in FIG. That is, the arithmetic unit 4 estimates the density of the asphalt mixture A based on the maximum value of the intensity (absolute value of the voltage value on the negative side) of the reflected wave W2 in the three preset feature periods G1, G2, and G3. You may. Based on at least two reflected wave information acquired in advance, the calculation unit 4 has a difference dG1 of the maximum value of the intensity of the reflected wave W2 corresponding to each of the densities of the asphalt mixture A in the feature periods G1, G2 and G3. The feature periods G1, G2, and G3 are set so that dG2 and dG3 are equal to or higher than a predetermined threshold value. Specifically, in FIG. 6, as a result of comparing the broken line graph corresponding to the density of 100% compaction and the solid line graph corresponding to the density of 85% compaction, each of the feature periods G1, G2, and G3. In the feature period G1, G2, so that the difference dG1, dG2, dG3 of the maximum value of the intensity (voltage value) of the reflected wave W2 corresponding to each of the densities of the asphalt mixture A is 0.5 [V] or more. G3 is set. In FIG. 6, the maximum value of the intensity (voltage value) of the reflected wave W2 is the voltage value of the apex of the waveform on the negative side of the graph. That is, the maximum value of the intensity of the reflected wave W2 in each of the characteristic periods G1, G2, and G3 is the boundary where the rate of change of the voltage value of the reflected wave W2 with time changes from negative to positive, and the rate of change with time is 0. It is the voltage value at the time of becoming. Further, the "predetermined threshold value" in the present embodiment is not limited to 0.5 [V], and is appropriately set according to the performance of the antenna and the measuring instrument of the electromagnetic wave transmitting / receiving device 3.

As shown in FIG. 6, when the calculation unit 4 extracts the maximum value of the intensity of the reflected wave W2 in each of the feature periods G1, G2, and G3 as feature quantities, these feature quantities are transferred to the trained model 1001. By inputting, the density of the asphalt mixture A may be estimated. The trained model 1001 in this case is machine-learned using the teacher data in which the density of the asphalt mixture A is associated with the maximum value of the intensity of the reflected wave W2 in each of the feature periods G1, G2, and G3.

The trained model 1001 obtains the overall shape or graph pattern of the waveform graph showing the change over time of the voltage value based on the information of the electromagnetic wave (electromagnetic wave W1, reflected wave W2) received by the receiving unit 3b. , May be trained using teacher data associated with the density of the asphalt mixture A. In this case, the calculation unit 4 can estimate the density of the asphalt mixture A based on the overall shape of the waveform graph shown in FIGS. 3 and 6.

Further, as shown in FIG. 7A, the calculation unit 4 creates a road surface map M showing the density distribution of the asphalt mixture A on the road surface 30. The output device 5 of the compaction machine 10 outputs the road surface map M. That is, on the display of the output device 5 of the compaction machine 10, a road surface map M showing the density distribution of the asphalt mixture A on the road surface 30 is displayed as the density estimation information. For example, the region X1 shown in FIG. 7A is a region where the density of the asphalt mixture A has reached the reference density, and the region X2 is a region where the density of the asphalt mixture A has not reached the reference density. That is, in the region X1, the asphalt mixture A is sufficiently compacted, and in the region X2, the degree of compaction of the asphalt mixture A is insufficient.

Further, as shown in FIG. 7B, the calculation unit 4 sets the movement path R of the compaction machine 10 on the road surface 30 based on the density of the asphalt mixture A. The movement route R is superimposed on the road surface map M and displayed on the display of the output device 5. Specifically, the arithmetic unit 4 creates a movement path R so that the compaction machine 10 compacts the region X2 again. Further, the calculation unit 4 may create a movement path R so that the rolling machine 10 compacts the region more as the density of the asphalt mixture A becomes lower. Further, the display of the output device 5 may display the current position of the compaction machine 10 on the road surface map M by using the GPS function.

From the above, the density estimation device 11 according to the present embodiment has a transmitting unit 3a that emits an electromagnetic wave W1 toward the road surface 30, a receiving unit 3b that receives the reflected wave W2 of the electromagnetic wave W1 reflected from the road surface 30, and a reflected wave. It has a calculation unit 4 for estimating the density of the asphalt mixture A based on the reflected wave information showing the characteristics of W2. As a result, the density estimation device 11 can easily estimate the density of the asphalt mixture A in a short time. Further, since the density of the asphalt mixture A can be estimated without cutting out a sample from the asphalt mixture A after construction, the quality of the road surface 30 can be maintained. Further, the density estimation device 11 can estimate the density of the asphalt mixture A in a state of non-contact with the road surface 30 even if the asphalt mixture A immediately after laying is in a high temperature state. Further, since the compaction machine 10 according to the present embodiment includes the density estimation device 11, the density of the asphalt mixture A can be estimated while compacting the asphalt mixture A.

Further, the calculation unit 4 of the density estimation device 11 estimates the density of the asphalt mixture A based on the information indicating the time-dependent change in the intensity of the reflected wave W2. Since the change in the intensity of the reflected wave W2 with time is affected by the difference in the density of the asphalt mixture A, the calculation unit 4 of the density estimation device 11 can accurately estimate the density of the asphalt mixture A.

The calculation unit 4 of the density estimation device 11 extracts a feature amount from the reflected wave information indicating a change in the intensity of the reflected wave W2 with time, and inputs the feature amount to the trained model 1001 to obtain the density of the asphalt mixture A. presume. The trained model 1001 is machine-learned using the teacher data in which the density of the asphalt mixture A is associated with the feature amount. By estimating the density of the asphalt mixture A using the trained model 1001 in this way, the influence (noise) of environmental conditions such as temperature, humidity, atmospheric pressure, and air flow on the density estimation can be minimized. The density of the asphalt mixture A can be estimated more accurately.

When estimating the density of the asphalt mixture A using the trained model 1001, the intensity of the reflected wave W2 at the preset feature time points P1, P2, and P3 is extracted as the feature quantity. Further, the time points at which the difference in intensity of the reflected waves W2 corresponding to each of the densities of the asphalt mixture A becomes equal to or more than a predetermined threshold value are set as the feature time points P1, P2, and P3. Thereby, characteristic data that is easily affected by the difference in the density of the asphalt mixture A can be extracted as a feature amount from the reflected wave information indicating the change in the intensity of the reflected wave W2 with time.

When estimating the density of the asphalt mixture A using the trained model 1001, the maximum value of the intensity of the reflected wave W2 in the preset feature periods G1, G2, and G3 may be extracted as the feature quantity. .. The characteristic periods G1, G2, and G3 are set so that the difference between the maximum values of the intensities of the reflected waves W2 corresponding to each of the densities of the asphalt mixture A is equal to or more than a predetermined threshold value. As a result, even if the timing of the waveform (change over time) of the reflected wave W2 is deviated due to the difference in the density of the asphalt mixture A, the asphalt mixture A is based on the voltage values that change in the feature periods G1, G2, and G3. It is possible to extract features suitable for estimating the density of.

The wavelength of the electromagnetic wave W1 transmitted toward the road surface 30 is 10 to 100 cm (frequency: 300 MHz to 3 GHz). When the wavelength of the electromagnetic wave W1 is a millimeter wave (frequency: 30 GHz to 300 GHz / wavelength: 1 mm to 10 mm) or a microwave (frequency: 3 GHz to 30 GHz / wavelength: 1 cm to 10 cm) shorter than 10 to 100 cm, the electromagnetic wave W1 is Diffuse reflection may occur due to the unevenness of the road surface 30, and the receiving unit 3b may not be able to receive an appropriate reflected wave W2. Further, when the wavelength of the electromagnetic wave W1 is longer than 10 to 100 cm and the frequency is low, the electromagnetic wave W1 may pass through the asphalt mixture A. Therefore, by setting the wavelength of the electromagnetic wave W1 to 10 to 100 cm and the frequency to 300 MHz to 3 GHz, the receiving unit 3b can receive the reflected wave W2 suitable for estimating the density of the asphalt mixture A.

Further, the display of the output device 5 of the compaction machine 10 displays density estimation information indicating the density of the asphalt mixture A estimated by the calculation unit 4 of the density estimation device 11. As a result, the operator who operates the compaction machine 10 can perform the compaction work of the asphalt mixture A while confirming whether or not the density of the asphalt mixture A on the road surface 30 has reached the reference density.

Further, as shown in FIG. 7A, the density estimation information output by the output device 5 includes a road surface map M showing the density distribution of the asphalt mixture A on the road surface 30. As a result, the operator who operates the compaction machine 10 can perform the compaction work of the asphalt mixture A while visually confirming the progress of the compaction work of the asphalt mixture A on the road surface 30.

Further, as shown in FIG. 7B, the calculation unit 4 of the density estimation device 11 sets the movement path R of the compaction machine 10 on the road surface 30 based on the density of the asphalt mixture A. As a result, the operator can move the compaction machine 10 along the movement path R, so that the compaction work of the region X2 whose density does not reach the reference density can be efficiently performed. Further, the compaction machine 10 may perform compaction work of the asphalt mixture A by autonomously moving along the movement path R by automatic operation.

<< Second Embodiment >>
Hereinafter, the density estimation system 100 according to the second embodiment of the present invention will be described with reference to FIG. Since the same reference numerals indicate the same or similar structures, detailed description thereof will be omitted below.

The density estimation system 100 acquires reflected wave information from the electromagnetic wave receiving / transmitting device 3 attached to the compaction machine 20 for compacting the road surface 30 and the electromagnetic wave receiving / transmitting device 3, and determines the density of the asphalt mixture A based on the reflected wave information. It is provided with a calculation device 24 for estimation. Similar to the first embodiment, the electromagnetic wave receiving / transmitting device 3 has a transmitting unit 3a that transmits the electromagnetic wave W1 toward the road surface 30 and a receiving unit 3b that receives the reflected wave W2 of the electromagnetic wave W1 reflected from the road surface 30. .. The arithmetic unit 24 is not mounted on the compaction machine 20, and can exchange information with the compaction machine 20 via a known communication means. The arithmetic unit 24 may be a cloud server. The arithmetic unit 24 estimates the density of the asphalt mixture A by the same method as the arithmetic unit 4 of the density estimation device 11 according to the first embodiment.

In addition to the electromagnetic wave receiving / transmitting device 3 and the arithmetic unit 24, the density estimation system 100 includes an output device 5 mounted on the compaction machine 20 and a second output device 25 not mounted on the compaction machine 20. And have. The second output device 25 may be a terminal used at the construction site of the road surface 30, or may be a monitor provided in an operator room away from the construction site. The output device 5 outputs the density estimation information received from the arithmetic unit 24. Also. The second output device 25 also receives the density estimation information from the arithmetic unit 24 by a known communication means. The second output device 25 outputs density estimation information as image information or character information to the display. Further, the second output device 25 may have a speaker and output density estimation information as voice. Further, as shown in FIGS. 7A and 7B, the density estimation information is displayed on the road surface map M showing the density distribution of the asphalt mixture A on the road surface 30 and the movement route superimposed on the road surface map M. R may be displayed.
The second output device 25 constitutes the output device of the density estimation system 100. The density estimation system 100 has an output device 5 and a second output device 25 as output devices, but is not limited to this, and may have only the second output device 25.

The operator may remotely control the compaction machine 20 while checking the density estimation information displayed on the display of the second output device 25. Further, the compaction machine 20 may be automatically controlled based on the control command received from the arithmetic unit 24.

From the above, the density estimation system 100 according to the present embodiment acquires reflected wave information from the electromagnetic wave receiving / transmitting device 3 attached to the compaction machine 20 and the electromagnetic wave receiving / transmitting device 3, and based on the reflected wave information, the road surface 30 It is provided with a calculation device for estimating the density of the asphalt mixture A of the above. As a result, the density estimation system 100 can easily estimate the density of the asphalt mixture A in a short time as in the density estimation device 11 according to the first embodiment. Further, since the density of the asphalt mixture A can be estimated without cutting out a sample from the asphalt mixture A after construction, the quality of the road surface 30 can be maintained. Further, the density estimation system 100 can estimate the density of the asphalt mixture A in a state of non-contact with the road surface 30 even when the asphalt mixture A immediately after laying is in a high temperature state. Further, since the electromagnetic wave receiving / transmitting device 3 is attached to the compaction machine 20, the density of the asphalt mixture A can be estimated while performing the compaction work of the asphalt mixture A.

100 ... Density estimation system 10 ... Rolling machine 1 ... Rolling machine body 3 ... Electromagnetic wave receiving / transmitting device 3a ... Transmitting unit 3b ... Receiver unit 4 ... Computing unit 5 ... Output device 11 ... Density estimation device 24 ... Computing device 25 ... No. 2 Output device 30 ... Road surface 1001 ... Trained model 1003 ... Teacher data A ... Asphalt mixture P1, P2, P3 ... Feature time point G1, G2, G3 ... Feature period W1 ... Electromagnetic wave W2 ... Reflected wave

The present invention relates to a compaction machine and a density estimation system for an asphalt mixture.

An object to be solved by the present invention is to provide a compaction machine capable of estimating the density of an asphalt mixture forming a road surface with a small work load, and a density estimation system of the asphalt mixture.

[1] In order to solve the above problems, the compaction machine according to the present invention is a compaction machine for compacting a road surface formed of an asphalt mixture, and is attached to a compaction machine main body and the compaction machine main body. A density estimation device for estimating the density of the asphalt mixture on the road surface is provided, and the density estimation device receives a transmitting unit that emits an electromagnetic wave toward the road surface and a reflected wave of the electromagnetic wave reflected from the road surface. It has a receiving unit for estimating the density of the asphalt mixture on the road surface based on the reflected wave information indicating a change in the intensity of the reflected wave received by the receiving unit over time . Estimates the density of the asphalt mixture by extracting the feature amount from the reflected wave information and inputting the feature amount into the trained model, and the trained model uses the density of the asphalt mixture as the feature amount. It is a compaction machine that is machine-learned using the teacher data associated with .

[ 2 ] In the above invention, the calculation unit may extract the intensity of the reflected wave at at least one preset feature time point as the feature amount.

[ 3 ] In the above invention, the feature is that the difference in the intensity of the reflected wave corresponding to each of the densities of the asphalt mixture becomes equal to or more than a predetermined threshold based on at least two reflected wave information acquired in advance. It may be set as a time point.

[ 4 ] In the above invention, the maximum value of the intensity of the reflected wave in at least one feature period set in advance may be extracted as the feature amount.

[ 5 ] In the above invention, the difference in the maximum value of the intensity of the reflected wave corresponding to each of the densities of the asphalt mixture is predetermined in the feature period based on the at least two reflected wave information acquired in advance. The feature period may be set so as to be equal to or greater than the threshold value.

[ 6 ] In the above invention, the wavelength of the electromagnetic wave transmitted toward the road surface may be 10 to 100 cm.

[ 7 ] In the above invention, an output device that outputs density estimation information indicating the density of the asphalt mixture estimated by the calculation unit of the density estimation device may be further provided.

[ 8 ] In the above invention, the density estimation information output by the output device may include a road surface map showing the density distribution of the asphalt mixture on the road surface.

[ 9 ] In the above invention, the calculation unit of the density estimation device may set the movement path of the compaction machine on the road surface based on the density of the asphalt mixture.

[ 10 ] Further, the asphalt mixture density estimation system according to the present invention estimates the density of the asphalt mixture forming the road surface, is attached to a compaction machine for compacting the road surface, and faces the road surface. An electromagnetic wave receiving / transmitting device having a transmitting unit for transmitting an electromagnetic wave and a receiving unit for receiving the reflected wave of the electromagnetic wave reflected from the road surface, and a time-dependent change in the intensity of the reflected wave from the electromagnetic wave receiving / transmitting device are shown. A computing device that acquires reflected wave information and estimates the density of the asphalt mixture on the road surface based on the reflected wave information is provided , and the computing device extracts a feature amount from the reflected wave information and describes the feature. By inputting the amount into the trained model, the density of the asphalt mixture is estimated, and the trained model is machine-learned using the teacher data in which the density of the asphalt mixture is associated with the feature amount. , Asphalt mixture density estimation system.

Claims (13)

A method for estimating the density of an asphalt mixture that estimates the density of the asphalt mixture that forms the road surface.
It emits electromagnetic waves toward the road surface and emits electromagnetic waves.
The reflected wave of the electromagnetic wave reflected from the road surface is received, and the reflected wave is received.
A method for estimating the density of an asphalt mixture, which estimates the density of the asphalt mixture on the road surface based on the reflected wave information indicating the characteristics of the reflected wave. The method for estimating the density of an asphalt mixture according to claim 1.
The reflected wave information is information indicating a change over time in the intensity of the reflected wave, which is a method for estimating the density of an asphalt mixture. The method for estimating the density of an asphalt mixture according to claim 2.
A feature amount is extracted from the reflected wave information indicating a change in the intensity of the reflected wave with time.
By inputting the features into the trained model, the density of the asphalt mixture is estimated.
The trained model is a method for estimating the density of an asphalt mixture, which is machine-learned using teacher data in which the density of the asphalt mixture is associated with the features. The method for estimating the density of an asphalt mixture according to claim 3.
A method for estimating the density of an asphalt mixture, which extracts the intensity of the reflected wave at at least one feature time set as the feature amount. The method for estimating the density of an asphalt mixture according to claim 4.
Based on at least two reflected wave information acquired in advance, a time point at which the difference in intensity of the reflected wave corresponding to each of the densities of the asphalt mixture becomes a predetermined threshold value or more is set as the feature time point. Mixture density estimation method. The method for estimating the density of an asphalt mixture according to claim 3.
A method for estimating the density of an asphalt mixture, which extracts the maximum value of the intensity of the reflected wave in at least one feature period set in advance as the feature amount. The method for estimating the density of an asphalt mixture according to claim 6.
Based on at least two previously acquired reflected wave information, the difference in the maximum value of the reflected wave intensity corresponding to each of the densities of the asphalt mixture in the feature period is equal to or more than a predetermined threshold. A method for estimating the density of an asphalt mixture in which the characteristic period is set. The method for estimating the density of an asphalt mixture according to any one of claims 1 to 7.
A method for estimating the density of an asphalt mixture, wherein the wavelength of the electromagnetic wave transmitted toward the road surface is 10 to 100 cm. A compaction machine that compacts the road surface formed by an asphalt mixture.
Rolling machine body and
A density estimation device attached to the compaction machine main body and estimating the density of the asphalt mixture on the road surface is provided.
The density estimation device is
A transmitter that emits electromagnetic waves toward the road surface,
A receiving unit that receives the reflected wave of the electromagnetic wave reflected from the road surface, and
A compaction machine having a calculation unit for estimating the density of the asphalt mixture on the road surface based on the reflected wave information indicating the characteristics of the reflected wave received by the receiving unit. The compaction machine according to claim 9, wherein the compaction machine is used.
A compaction machine further comprising an output device that outputs density estimation information indicating the density of the asphalt mixture estimated by the calculation unit of the density estimation device. The rolling compaction machine according to claim 10.
The density estimation information output by the output device is a compaction machine including a road surface map showing the density distribution of the asphalt mixture on the road surface. The rolling compaction machine according to claim 10.
The calculation unit of the density estimation device is a compaction machine that sets a movement path of the compaction machine on the road surface based on the density of the asphalt mixture. An asphalt mixture density estimation system that estimates the density of the asphalt mixture that forms the road surface.
An electromagnetic wave transmitting / receiving device attached to a compaction machine for compacting the road surface and having a transmitting unit that emits an electromagnetic wave toward the road surface and a receiving unit that receives a reflected wave of the electromagnetic wave reflected from the road surface.
Density estimation of an asphalt mixture including an arithmetic device that acquires reflected wave information indicating the characteristics of the reflected wave from the electromagnetic wave receiving / transmitting device and estimates the density of the asphalt mixture on the road surface based on the reflected wave information. system.

Images