Monitoring system for filled steel pipe concrete columns

Abstract

To improve quality of filled steel pipe concrete columns.SOLUTION: A monitoring system 100 for filled steel pipe concrete columns comprises: an image capturing unit 20 capable of capturing images inside steel pipes; an identification unit 31 that identifies objects in an image P captured by the image capturing unit 20 based on learning results of machine learning; and a condition determination unit 32 that determines a state inside a steel pipe based on objects in the image P identified by the identification unit 31. The learning results stored in the identification unit 31 include learning results of machine learning conducted in advance using image data of the inside of the steel pipe taken when the concrete is normally filled into the steel pipe as teacher data.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present invention relates to a monitoring system for filled steel tubular concrete columns.

Background Art

[0002] Patent Document 1 discloses a management device for a filled steel tubular concrete column, which includes an imaging unit capable of imaging the top end of the concrete filled in the steel pipe of the filled steel tubular concrete column.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] When filling concrete into a steel pipe using the management device for a filled steel tubular concrete column described in Patent Document 1, in order to confirm the quality of the filled steel tubular concrete column, for example, whether the concrete is filled in the steel pipe without gaps and whether foreign substances are mixed in, an operator needs to constantly monitor the image captured by the imaging unit.

[0005] However, monitoring relatively monotonous images over a long period of time requires excessive labor even if multiple operators take turns, and since the confirmation work is based on personal visual inspection, there may be differences in the judgment of the presence or absence of abnormalities due to differences in the experience of the operators. Therefore, it is difficult to sufficiently ensure the quality of filled steel tubular concrete columns.

[0006] An object of the present invention is to improve the quality of filled steel tubular concrete columns.

Means for Solving the Problems

[0007] The present invention is a monitoring system for a filled-type steel pipe concrete column, comprising an imaging unit capable of imaging the inside of the steel pipe, The imaging unit is suspended inside the steel pipe, along with a lighting device that illuminates the inside of the steel pipe, The system includes an identification unit that stores the results of a machine learning study performed in advance and identifies objects in an image captured by an imaging unit based on the learning results, and a state determination unit that determines the state inside the steel pipe based on the objects in the image identified by the identification unit. The imaging unit is a digital camera that does not have a depth measurement function. The learning results stored in the identification unit include the results of machine learning that was previously performed using image data of the inside of a steel pipe, captured when concrete was being properly filled into the steel pipe, as training data. [Effects of the Invention]

[0008] According to the present invention, the quality of filled steel pipe concrete columns can be improved. [Brief explanation of the drawing]

[0009] [Figure 1] This is a schematic diagram showing an example of a filled steel pipe concrete column monitored by a monitoring system according to an embodiment of the present invention. [Figure 2] This is a block diagram showing the overall configuration of a monitoring system according to an embodiment of the present invention. [Figure 3] This figure shows an example of an image of the inside of a steel pipe captured by the imaging unit. [Figure 4] This figure shows an example of an image used as training data in machine learning, and is a diagram of the concrete filling state, following Figure 3. [Figure 5] This figure shows an example of an image used as training data in machine learning, and is a diagram of the concrete filling state, following Figure 4. [Figure 6] This figure shows an example of an image used as training data in machine learning, and is a diagram of the concrete filling state, following Figure 5. [Figure 7] This figure shows an example of an image used as training data in machine learning, and is a diagram of the concrete filling state, following Figure 6. [Figure 8]This figure shows an example of images (with different shapes) used as training data in machine learning. [Figure 9] This figure shows an example of an image (foreign object) used as training data in machine learning. [Figure 10] This is a flowchart illustrating the monitoring procedure using the monitoring system according to an embodiment of the present invention. [Modes for carrying out the invention]

[0010] Hereinafter, with reference to the drawings, a monitoring system for a filled-type steel pipe concrete column according to an embodiment of the present invention will be described.

[0011] The monitoring system 100 for a filled-type steel pipe concrete column according to an embodiment of the present invention is a system that monitors the filling state of fresh concrete (unhardened fresh concrete; hereinafter referred to as "fresh concrete") into a filled-type steel pipe concrete column 10 as shown in Figure 1, and automatically determines whether or not the filling of the fresh concrete has been carried out correctly.

[0012] The filled-steel-tube concrete column 10 is a column member of a CFT (Concrete Filled Steel Tube) structure, which is formed by pouring ready-mix concrete into a square or circular steel pipe. For example, as shown in Figure 1, it is composed of a steel pipe section 11 formed from a square steel pipe and a diaphragm 12 provided between the steel pipe sections 11 in the vertical direction and integrated with the steel pipe sections 11 by butt welding.

[0013] The diaphragm 12 is a so-called through diaphragm, formed from a roughly square steel plate with a side length greater than that of the steel pipe section 11, and is installed in the filled-type steel pipe concrete column 10 as a reinforcing member for stress transmission from the beam 15 to the column 10. A pouring hole 12a is formed through the approximate center of each diaphragm 12, through which the ready-mix concrete filled inside the steel pipe can pass, and multiple air vents 12b, described later, are formed through the pouring hole 12a.

[0014] Since the flange portions of the beam 15 formed of H-shaped steel materials are welded to the diaphragm 12, the diaphragm 12 is arranged with a predetermined interval in the vertical direction in accordance with the interval between the pair of flange portions of the beam 15. That is, the installation interval of the diaphragm 12 provided in the filled steel tube concrete column 10 is preset according to the installation interval of the beam 15 in the vertical direction and the interval between the flange portions of the beam 15.

[0015] Note that the diaphragm 12 is not limited to a through diaphragm, and may be an inner diaphragm welded and fixed inside the steel pipe portion 11.

[0016] The upper end of the filled steel tube concrete column 10 is closed by a closing plate 14. In the closing plate 14, similar to the diaphragm 12 shown in FIG. 3, a placing hole 14a is formed penetrating substantially at the center for checking the filling condition of the fresh concrete, and a plurality of air vent holes (not shown) are formed around the placing hole 14a. The placing hole 14a is used as a through hole for suspending the imaging unit 20 described later into the steel pipe. Note that the through hole for suspending the imaging unit 20 into the steel pipe may be provided by penetrating the steel pipe portion 11 in a substantially horizontal direction.

[0017] Also, below the steel pipe portion 11 located at the lowermost end side of the filled steel tube concrete column 10, a filling port 13 for filling fresh concrete into the steel pipe is provided. To the filling port 13, a pressure pumping pump device 18 capable of pressure pumping fresh concrete or a fresh concrete supply pipe extending from a pressure pumping pump truck (not shown) is connected. When the filled steel tube concrete column 10 is high, since the fresh concrete cannot be filled up to the top of the column at once, the filling port 13 may be appropriately provided at an intermediate floor. Note that the filling port 13 provided at an intermediate floor in this way can also be used as a through hole for suspending the imaging unit 20 into the steel pipe.

[0018] Note that the filled steel tube concrete column 10 is not limited to being erected along the vertical direction as shown in FIG. 1, and may be erected while being inclined at a predetermined angle, or may be inclined from the middle.

[0019] The monitoring system 100 for monitoring the filling state of ready-mix concrete into the filled-type steel pipe concrete column 10, as shown in Figure 2, mainly comprises: an imaging unit 20 capable of imaging the inside of the steel pipe of the filled-type steel pipe concrete column 10; an identification unit 31 that identifies objects in the image P captured by the imaging unit 20; a state determination unit 32 that determines the state inside the steel pipe based on the objects in the image P identified by the identification unit 31; a display unit 40 that displays the results determined by the state determination unit 32, etc.; and a communication unit 42 that transmits the results determined by the state determination unit 32, etc. to the outside.

[0020] The imaging unit 20 is a so-called digital camera, and as shown in Figure 1, it is suspended via a cable 21 into the steel pipe of the filled-type steel pipe concrete column 10 through a through hole formed in the closing plate 14.

[0021] As shown in Figure 1, the imaging unit 20 is suspended via the cable 21 in a position that allows it to image the area including the top surface 16a of the ready-mix concrete 16 when the ready-mix concrete 16 is filled into the steel pipe of the filled-type steel pipe concrete column 10, i.e., with the imaging direction facing downwards, and captures an image P as shown in Figure 3, for example.

[0022] In image P shown in Figure 3, the top surface 16a of the ready-mix concrete 16, as captured through the pouring hole 12a of the diaphragm 12, is shown approximately in the center. Furthermore, image P shows the entire diaphragm 12 and the inner wall surfaces 11a of the four inner surfaces of the steel pipe section 11 that extends upward from all four sides of the diaphragm 12. In addition, multiple air vents 12b are shown around the pouring hole 12a of the diaphragm 12.

[0023] The image P captured by the imaging unit 20 is transmitted to the control unit 30 (described later) via wireless or wired communication. Alternatively, the cable 21 may be used as a transmission cable to transmit the image P through the cable 21.

[0024] The cable 21 is wound up and unwound by a reel device (not shown), and the raising and lowering speeds of the imaging unit 20 are controlled by the reel device. The control of the reel device may be performed by a control unit 30 (described later) or by an operator. In addition, a laser distance meter (not shown) capable of measuring the distance between the imaging unit 20 and the top surface 16a of the ready-mix concrete 16 may be suspended together with the imaging unit 20 via the cable 21, and the reel device may be controlled so that the distance measured by this laser distance meter is of a constant magnitude.

[0025] Furthermore, in order to illuminate the inside of the steel pipe where light does not penetrate, a lighting device such as an LED light (not shown) is suspended via a cable 21 together with the imaging unit 20, in a position that allows it to irradiate light toward the top surface 16a of the ready-mix concrete 16.

[0026] The identification unit 31 and the state determination unit 32 represent some of the functions of a typical personal computer used as the control unit 30, as virtual units, and do not exist physically.

[0027] The control unit 30, which includes an identification unit 31 and a state determination unit 32 as part of its functions, is composed of a microcomputer equipped with a CPU (Central Processing Unit), ROM (Read-Only Memory), RAM (Random Access Memory), and an I / O interface (Input / Output Interface). The RAM stores data from CPU processing, the ROM stores CPU control programs and the like in advance, and the I / O interface is used for inputting and outputting information with devices connected to the control unit 30. The control unit 30 may be composed of multiple microcomputers. Furthermore, it is preferable that the control unit 30 is equipped with a GPU (Graphics Processing Unit) specialized for image processing.

[0028] The identification unit 31 stores the results of machine learning that have been performed in advance. Based on the stored learning results, the identification unit 31 identifies what the object in the image P captured by the imaging unit 20 and transmitted to the control unit 30 is.

[0029] The learning results stored in the identification unit 31 include the results of machine learning that was previously performed using a large number of image data of the inside of the steel pipe, which were captured when the ready-mix concrete 16 was being properly filled into the steel pipe, as training data; the results of machine learning that was previously performed using image data of the top surface 16a of the ready-mix concrete 16 abnormally beginning to solidify or having solidified when the ready-mix concrete 16 was being filled into the pipe; the results of machine learning that was previously performed using image data of the inner wall surface 11a of various shaped steel pipe sections 11 into which the ready-mix concrete 16 is being filled as training data; the results of machine learning that was previously performed using image data of various shaped diaphragms 12 installed in the filled-type steel pipe concrete column 10 as training data; and the results of machine learning that was previously performed using image data of various foreign objects F1 to F3 mixed into the steel pipe as training data.

[0030] As a machine learning technique, for example, a type of segmentation using deep learning called semantic segmentation is used, which identifies the type of object displayed in each pixel and detects the pixel region where the object to be identified exists. In order to identify from image data, as types of objects, mainly ready-mix concrete 16, diaphragm 12, inner wall surface 11a of the steel pipe section 11, and unknown objects that do not fall into these categories, learning is performed to detect the pixel region where ready-mix concrete 16 exists, the pixel region where diaphragm 12 exists, the pixel region where the inner wall surface 11a of the steel pipe section 11 exists, and the pixel region where unknown objects or foreign objects F1 to F3 exist.

[0031] The machine learning method is not limited to semantic segmentation; any method that enables the identification of object types and region classification in image data may be used. For example, other known deep learning methods such as instance segmentation or panoptic segmentation may also be used.

[0032] In machine learning, various image data are used as training data, such as images P of the inside of a steel pipe taken when ready-mix concrete 16 is properly filled into the steel pipe, as shown in Figures 3 to 7; images P when the shape of the inner wall surface 11a of the steel pipe section 11 and the shape of the diaphragm 12 differ from those shown in Figure 3, as shown in Figure 8; and images P when foreign objects F1 to F3 are present inside the steel pipe, as shown in Figure 9. These are just examples, and a large number of equivalent image data are used as training data.

[0033] Specifically, Figure 3 shows the state before the top surface 16a of the ready-mix concrete 16 passes through the pouring hole 12a of the diaphragm 12, and Figure 4 shows the state after the top surface 16a of the ready-mix concrete 16 has passed through the pouring hole 12a of the diaphragm 12, and a first boundary line B1 has been formed, which is the boundary between the ready-mix concrete 16 that has passed through the pouring hole 12a and the diaphragm 12.

[0034] Furthermore, Figure 5 shows a state in which the ready-mix concrete 16 passes through multiple air vents 12b in addition to the pouring hole 12a, and a second boundary line B2 is formed, which is the boundary between the ready-mix concrete 16 that has passed through the air vents 12b and the diaphragm 12. Figure 6 shows a state in which the ready-mix concrete 16 that has passed through the pouring hole 12a and the ready-mix concrete 16 that has passed through multiple air vents 12b merge, causing the first boundary line B1 and the second boundary line B2 to overlap, and some of the ready-mix concrete 16 reaches the inner wall surface 11a of the steel pipe section 11, creating a third boundary line B3, which is the boundary between the ready-mix concrete 16 and the inner wall surface 11a.

[0035] Furthermore, Figure 7 shows a state where the first boundary line B1 and the second boundary line B2 completely overlap, the ready-mix concrete 16 reaches the inner wall surface 11a around the entire circumference of the steel pipe section 11, and only the third boundary line B3 exists.

[0036] As shown in Figures 3 to 7, a series of images P taken when the ready-mix concrete 16 is properly filled into the steel pipe allow for the learning of the positional relationship between the ready-mix concrete 16, the diaphragm 12, and the inner wall surface 11a of the steel pipe section 11. It also allows for the learning of the order in which the ready-mix concrete 16 emerges from the pouring hole 12a and the air vent hole 12b as it passes through the diaphragm 12. Furthermore, the positions of the boundaries between the ready-mix concrete 16 and the diaphragm 12 (first boundary line B1 and second boundary line B2) and the boundary between the ready-mix concrete 16 and the inner wall surface 11a (third boundary line B3) during normal operation are also learned.

[0037] Furthermore, Figure 8 shows an example of a filled-type steel pipe concrete column 10 in which the steel pipe section 11 is a circular steel pipe instead of a square steel pipe, the casting hole 12a of the diaphragm 12 is octagonal (polygonal) instead of circular, and there are 8 air vents 12b instead of 4.

[0038] As shown in Figure 8, even though the shape of the inner wall surface 11a of the steel pipe section 11 and the shape of the diaphragm 12 differ, the general positional relationship between the casting hole 12a and the air vent hole 12b of the diaphragm 12, and the general positional relationship between the diaphragm 12 and the inner wall surface 11a are learned from the image P. By learning the general positional relationship of the internal structure of the filled steel pipe concrete column 10 in advance, it becomes possible to perform the determination by the state determination unit 32, described later, for filled steel pipe concrete columns 10 with various cross-sectional shapes.

[0039] Furthermore, Figure 9 shows an example in which foreign matter F1 is accumulated water such as rainwater or condensation, foreign matter F2 is a plastic bottle, and foreign matter F3 is a tool inside the steel pipe.

[0040] As shown in Figure 9, the image P, which contains foreign objects F1 to F3 inside the steel pipe, allows for learning about various types of foreign objects. Although the image P in Figure 9 shows multiple foreign objects F1 to F3 together, it is also acceptable for only one of the foreign objects F1 to F3 to be visible. Furthermore, the foreign objects are not limited to the aforementioned foreign objects F1 to F3; they could also be construction materials such as binding wire or reinforcing bars, or even living organisms such as work gloves or insects or small animals that have entered the steel pipe.

[0041] In order to have the identification unit 31, which stores the above-mentioned learning results, identify what an object is in the image P captured by the imaging unit 20, known image processing such as binarization or processing to process the image data three-dimensionally using SfM (Structure from Motion) may be applied to the image P in advance to improve the accuracy of object identification.

[0042] The state determination unit 32 determines the state of the ready-mix concrete 16 being filled into the steel pipe and the filling speed of the ready-mix concrete 16 being filled into the steel pipe, based on the objects in the image P identified by the identification unit 31, mainly the ready-mix concrete 16, the diaphragm 12, and the inner wall surface 11a of the steel pipe section 11, and determines whether or not the ready-mix concrete 16 is being filled into the steel pipe normally. In addition, the state determination unit 32 determines whether or not there is an abnormality inside the steel pipe, based on whether or not the objects in the image P identified by the identification unit 31 are, for example, foreign objects F1 to F3 or unknown objects.

[0043] Specifically, the condition determination unit 32, when the identification unit 31 identifies the ready-mix concrete 16 and the inner wall surface 11a of the steel pipe section 11 as objects, and when the boundary (third boundary line B3) between the inner wall surface 11a and the ready-mix concrete 16 is identified, determines that there is an abnormality in the ready-mix concrete 16, for example, if there is a difference of more than a predetermined amount in the position of the third boundary line B3 formed on each inner wall surface 11a and they are not uniform, that is, if the top surface 16a of the ready-mix concrete 16 is not spreading evenly toward each inner wall surface 11a, but is spreading unevenly toward one of the inner wall surfaces 11a, then it determines that there is an abnormality in the ready-mix concrete 16, as there is a possibility that the properties of the ready-mix concrete 16 are inconsistent and that localized hardening is progressing.

[0044] Furthermore, if the shape of the third boundary line B3 formed on each inner wall surface 11a is a convex arc in the central part, and its curvature is greater than a predetermined standard value, that is, if it is assumed that the bulge of the top surface 16a of the ready-mixed concrete 16 is relatively large near the center of the filled steel pipe concrete column 10 (near the center of the pouring hole 12a), then it is determined that there is an abnormality in the ready-mixed concrete 16, as there is a possibility that the properties of the ready-mixed concrete 16 are inconsistent and that localized hardening is progressing.

[0045] Furthermore, the condition determination unit 32, when the identification unit 31 identifies the ready-mix concrete 16 and the diaphragm 12 as objects, and when it identifies the boundary between the ready-mix concrete 16 that has passed through the pouring hole 12a and the diaphragm 12 (first boundary line B1) and the boundary between the ready-mix concrete 16 that has passed through the air vent hole 12b and the diaphragm 12 (second boundary line B2), determines that there is an abnormality in the ready-mix concrete 16 if there is a deviation in the flow of the ready-mix concrete 16 from the normal order of appearance of the ready-mix concrete 16, as this indicates variations in the properties of the ready-mix concrete 16 and the possibility of localized voids where the ready-mix concrete 16 is not filled.

[0046] Specifically, when the ready-mix concrete 16 passes through the diaphragm 12 normally, it first emerges from the central pouring hole 12a and spreads out in a roughly circular shape on the diaphragm 12 (see Figure 4). Then, before the ready-mix concrete 16 emerging from the pouring hole 12a (first boundary line B1) reaches each air vent hole 12b, ready-mix concrete 16 emerges from each air vent hole 12b (see Figure 5). Subsequently, the ready-mix concrete 16 emerging from the pouring hole 12a (first boundary line B1) merges with the ready-mix concrete 16 emerging from each air vent hole 12b (second boundary line B2), and finally reaches the inner wall surface 11a of the steel pipe section 11 (see Figures 6 and 7).

[0047] In contrast, for example, if the first boundary line B1 reaches the air vent hole 12b before the second boundary line B2 is identified at any of the air vent holes 12b, or if there is variation in the degree of spread of the second boundary line B2 of the ready-mix concrete 16 emerging from each air vent hole 12b that exceeds a predetermined allowable range, it is determined that there is an abnormality in the ready-mix concrete 16, as there has been a deviation in the flow of the ready-mix concrete 16 from the normal order of emergence.

[0048] Furthermore, if the first boundary line B1 does not spread evenly toward each air vent hole 12b, and there is variation exceeding a predetermined allowable range at the time when the first boundary line B1 overlaps with each second boundary line B2, it is determined that there is an abnormality in the ready-mix concrete 16, as there is a possibility that localized voids will occur where the ready-mix concrete 16 is not filled.

[0049] In making such a determination, the state determination unit 32 stores threshold values, such as standard values ​​and tolerance ranges, for determining whether or not there is an abnormality in the ready-mix concrete 16 based on the position and shape of each boundary line B1, B2, and B3. The magnitude of these threshold values ​​may be updated as needed based on the learning results stored in the identification unit 31.

[0050] Furthermore, as training data in the above-mentioned machine learning, an image P of the inside of a steel pipe taken when the ready-mix concrete 16 was not properly filled into the steel pipe may be used, and the learning results for when the ready-mix concrete 16 is not properly filled may be stored in advance in the identification unit 31. The identification unit 31 may then determine whether or not there is an abnormality in the ready-mix concrete 16 based on which learning result—the learning results for when the ready-mix concrete 16 is properly filled or the learning results for when the ready-mix concrete 16 is not properly filled—is closer to the positional relationship of the objects in the image P identified by the identification unit 31.

[0051] Furthermore, the state determination unit 32, when the identification unit 31 identifies the ready-mix concrete 16 and the diaphragm 12 as objects, and when the boundary (first boundary line B1) between the ready-mix concrete 16 that has passed through the pouring hole 12a and the diaphragm 12 is identified, determines the filling speed of the ready-mix concrete 16 into the steel pipe based on the time elapsed from when the first boundary line B1 is identified by the identification unit 31 until the ready-mix concrete 16 passes through the pouring hole 12a of another diaphragm 12 located above the diaphragm 12, that is, until the first boundary line B1 is identified by the identification unit 31 on the other diaphragm 12. Note that since the installation interval of the diaphragms 12 in the vertical direction is predetermined as described above, the filling speed of the ready-mix concrete 16 can be easily determined by measuring the time it takes for the ready-mix concrete 16 to pass through the pouring holes 12a of the two diaphragms 12 arranged vertically.

[0052] If the filling speed of the ready-mix concrete 16 determined in this way exceeds a preset standard speed (for example, 1 m / min), it is determined that there is an abnormality in the filling speed of the ready-mix concrete 16, as it is possible that voids will be created on the underside of the diaphragm 12 due to the high filling speed. Also, if the filling speed of the ready-mix concrete 16 is less than the standard speed, it is determined that there is an abnormality in the filling speed of the ready-mix concrete 16, as it is possible that localized hardening is progressing.

[0053] The state determination unit 32 stores threshold values, such as standard values ​​and tolerance ranges, for determining whether or not there is an abnormality in the filling speed of the ready-mix concrete 16. The magnitude of these threshold values ​​may be updated as needed based on the learning results stored in the identification unit 31.

[0054] Furthermore, if the identification unit 31 identifies foreign objects F1 to F3 as objects, the condition determination unit 32 determines that, for example, if foreign object F1 is a liquid such as standing water, there is a risk that the water-cement ratio of the ready-mix concrete 16 will change and the strength of the concrete after hardening will decrease, and that there is an abnormality inside the steel pipe and the condition inside the steel pipe is unsuitable for filling with ready-mix concrete 16. Also, if foreign objects F2 and F3 are solids such as plastic bottles or tools, the condition determination unit 32 determines that there is an abnormality inside the steel pipe and the condition inside the steel pipe is unsuitable for filling with ready-mix concrete 16, and that there is a risk that the strength of the filled-type steel pipe concrete column 10 after hardening will decrease due to cross-sectional defects.

[0055] Furthermore, if an unknown object that cannot be identified using the learning results stored in the identification unit 31 is identified as an object by the identification unit 31, the state determination unit 32 determines that there is a possibility of some kind of malfunction occurring, that there is an abnormality inside the steel pipe, and that the condition inside the steel pipe is unsuitable for filling with ready-mix concrete 16.

[0056] The determination results determined by the state determination unit 32, the identification results from the identification unit 31, and the image P of the inside of the steel pipe captured by the imaging unit 20 are displayed on the display unit 40 and transmitted to the outside via the communication unit 42.

[0057] The display unit 40 is a monitoring device installed at the work site, and the worker checks the judgment result displayed on the display unit 40 and considers how to take action. Multiple display units 40 may be provided; for example, they may be installed near the control panel for operating the reel device that unwinds the cable 21 or near the control panel for operating the pressure pump device 18. In addition, the display unit 40 may be equipped with a speaker that can notify the worker of an abnormality with sound or a rotating light that can notify the worker of an abnormality with light in order to quickly notify the worker of an abnormality.

[0058] The communication unit 42 is a general wired or wireless communication device capable of transmitting data via an internet connection. It transmits the determination results determined by the status determination unit 32 to a tablet terminal or computer held by a supervisor who monitors the work status at a remote location away from the work site.

[0059] This allows for the rapid consideration of countermeasures based on the determination results made by the condition determination unit 32, not only at the work site where the ready-mix concrete 16 is being filled, but also at remote locations far from the work site.

[0060] Furthermore, the identification unit 31 and the state determination unit 32 do not necessarily have to be located within a single control unit 30, i.e., within a single personal computer. For example, they may be located on different servers and configured to transmit and receive data via wired or wireless connections.

[0061] Next, the monitoring method performed using the monitoring system 100 with the above configuration will be explained with reference to the flowchart in Figure 10.

[0062] First, before filling with ready-mix concrete 16, in step S11, a determination is made of the internal state of the filled steel pipe concrete column 10 that has not yet been filled with ready-mix concrete 16.

[0063] The pre-filling determination is initiated in the following step S12 by gradually lowering the imaging unit 20 into the steel pipe of the filled-type steel pipe concrete column 10, and continues while the imaging unit 20 is lowered.

[0064] Specifically, the imaging unit 20 is inserted into the steel pipe through a through-hole provided in the closing plate 14, and the cable 21 is unwound from the reel device at a relatively slow predetermined speed (for example, 1 m / min), thereby lowering the imaging unit 20 to a predetermined position, for example, a predetermined height higher than the filling opening 13 into which the ready-mix concrete 16 is filled.

[0065] While the imaging unit 20 descends inside the steel pipe, the identification unit 31 identifies objects in the image P captured by the imaging unit 20 based on the learning results, and the state determination unit 32 determines the state inside the steel pipe based on the objects in the image P identified by the identification unit 31 (step S13).

[0066] Since the ready-mix concrete 16 has not yet been filled, the objects identified by the identification unit 31 are the diaphragm 12, the inner wall surface 11a of the steel pipe section 11, foreign objects F1 to F3, and unknown objects that cannot be identified using the learning results.

[0067] Therefore, in step S13, if foreign objects F1 to F3 or an unknown object are identified by the identification unit 31, it is determined that there is an abnormality inside the steel pipe and that the condition inside the steel pipe is such that ready-mix concrete 16 cannot be filled in. Also, if the pouring holes 12a or air vent holes 12b provided in the diaphragm 12 are not identified, it is determined that there is an abnormality in the arrangement relationship between the steel pipe section 11 and the diaphragm 12, i.e., in the steel frame arrangement, and that the condition inside the steel pipe is such that ready-mix concrete 16 cannot be filled in, and the process proceeds to step S21.

[0068] If no abnormality is detected inside the steel pipe, the imaging unit 20 continues to descend until it reaches a predetermined position, and the identification by the identification unit 31 and the determination by the state determination unit 32 continue (steps S13 and S14).

[0069] In step S14, if it is determined that the imaging unit 20 has reached a predetermined position, the process proceeds to step S15, and the determination of the internal state of the filled steel pipe concrete column 10 into which the ready-mix concrete 16 is filled begins.

[0070] Furthermore, if there is time before the filling of the ready-mix concrete 16 begins, the identification by the identification unit 31 and the determination by the state determination unit 32 may be temporarily suspended. In addition, before the filling of the ready-mix concrete 16 begins, the imaging unit 20 may be moved back and forth multiple times between a predetermined position and the closing plate 14 to further determine whether there are any abnormalities inside the filled steel pipe concrete column 10 that has not yet been filled with ready-mix concrete 16.

[0071] The determination that the ready-mix concrete 16 is being filled begins in the following step S16 when the filling of the ready-mix concrete 16 into the filled-type steel pipe concrete column 10 starts and the imaging unit 20 is gradually raised from a predetermined position, and continues while the imaging unit 20 is raised.

[0072] Specifically, in step S16, the imaging unit 20 is raised toward the closing plate 14 by rewinding the cable 21 onto the reel device at a predetermined speed according to the delivery speed of the ready-mix concrete 16 delivered from the pressure pump device 18 into the filled steel pipe concrete column 10.

[0073] While the imaging unit 20 moves upward inside the steel pipe, the identification unit 31 identifies objects in the image P captured by the imaging unit 20 based on the learning results, and the state determination unit 32 determines the state inside the steel pipe based on the objects in the image P identified by the identification unit 31 (steps S17 to S19).

[0074] Specifically, in step S17, as described above, the condition determination unit 32 determines whether there is an abnormality in the filling state, that is, whether there is a problem with the properties of the ready-mix concrete 16 filled inside the steel pipe, based on the boundary lines B1, B2, and B3 between the objects identified by the identification unit 31.

[0075] Then, as described above, if there is a possibility of variation in the properties of the ready-mixed concrete 16, the condition determination unit 32 determines that there is an abnormality in the ready-mixed concrete 16, and the process proceeds to step S21.

[0076] Furthermore, in step S18, the presence or absence of foreign matter inside the steel pipe is determined. As described above, if the object identified by the identification unit 31 is a foreign matter F1 to F3 or an unknown object, the state determination unit 32 determines that there is an abnormality inside the steel pipe, and the process proceeds to step S21.

[0077] In step S19, it is determined whether there is an abnormality in the filling speed of the ready-mix concrete 16. For example, if there is a difference of a predetermined amount or more between the calculated filling speed and the reference speed, the state determination unit 32 determines that there is an abnormality in the filling speed of the ready-mix concrete 16, as described above, and the process proceeds to step S21.

[0078] Furthermore, the determinations made by the state determination unit 32 in steps S17 to S19 do not need to be made in the predetermined order described above. These determinations may be made in parallel and simultaneously, or in any order. The control flow should be such that if an abnormality is determined in any of the determinations in steps S17 to S19, the process proceeds to step S21.

[0079] If no abnormality is detected inside the steel pipe, the imaging unit 20 continues to rise until it reaches a predetermined position near the upper end of the filled steel pipe concrete column 10, and the identification by the identification unit 31 and the determination by the state determination unit 32 continue (steps S17 to S20).

[0080] In step S20, when it is determined that the imaging unit 20 has reached a predetermined position, the monitoring of the inside of the steel pipe by the monitoring system 100 is terminated.

[0081] In step S21, various abnormalities determined by the status determination unit 32 are reported through the display unit 40 and the communication unit 42. For example, if foreign objects F1-F3 or unknown objects are identified as objects in step S13 or step S18, the display unit 40 highlights the areas where foreign objects F1-F3 or unknown objects are visible by flashing or the like. In step S17, if it is determined that the ready-mix concrete 16 is not filled properly, the display unit 40 highlights the areas where the flow of ready-mix concrete 16 deviates from the normal order of appearance of the ready-mix concrete 16, or where the ready-mix concrete 16 is unevenly spread on the inner wall surface 11a, by flashing or the like. Also, in step S19, if it is determined that there is an abnormality in the filling speed of the ready-mix concrete 16, the display unit 40 highlights the calculated filling speed by flashing or the like, and visually displays the extent to which it deviates from the allowable range of the filling speed using a graph or the like. Furthermore, specific methods for notifying of an abnormality include displaying a pop-up notification on the screen of the display unit 40, or notifying the worker or supervisor via a short message through the communication unit 42.

[0082] Subsequently, the workers and monitors consider appropriate countermeasures for the reported abnormality. For example, if the abnormality is minor and occurs before the ready-mix concrete 16 is filled, the system is operated to return to step S14 in order to continue monitoring by the monitoring system 100. If the abnormality is minor and occurs while the ready-mix concrete 16 is being filled, the system is operated to return to step S20 in order to continue monitoring by the monitoring system 100.

[0083] On the other hand, if there is a serious abnormality that would prevent the start of concrete filling 16, or a serious abnormality that would require interrupting the filling of concrete 16, the monitoring system 100 will be operated to temporarily terminate the monitoring.

[0084] In this way, the monitoring system 100 automatically determines and reports whether there are any abnormalities inside the steel pipe before the ready-mix concrete 16 is filled in, and whether there are any abnormalities inside the steel pipe while the ready-mix concrete 16 is being filled in.

[0085] According to the above embodiments, the following effects are achieved.

[0086] According to the monitoring system 100 with the above configuration, objects in the image P of the inside of the steel pipe captured by the imaging unit 20 are identified by the identification unit 31 which stores the learning results of machine learning, and based on the identified objects in the image P, the state determination unit 32 determines the state of the inside of the steel pipe into which the ready-mix concrete 16 is filled, that is, whether or not there is an abnormality inside the steel pipe.

[0087] In this way, the presence or absence of abnormalities when the ready-mix concrete 16 is filled into the steel pipe, and the presence or absence of abnormalities inside the steel pipe before the ready-mix concrete 16 is filled, are automatically determined based on the image P captured by the imaging unit 20. This eliminates the need for workers or supervisors to continuously monitor the image P displayed on the display unit 40, such as a monitor. As a result, the labor involved in monitoring is greatly reduced, lowering the workload of workers and supervisors. Furthermore, since the determination of the presence or absence of abnormalities is made using the learning results of machine learning, there is no need to rely on the experience of workers or supervisors, thus enabling a stable improvement in the quality of the filled steel pipe concrete column 10.

[0088] Furthermore, the determination results determined by the status determination unit 32 are automatically reported to the supervisor who monitors the work status at a remote location away from the work site, making it possible to quickly consider how to deal with any abnormalities.

[0089] Furthermore, the following modifications are also within the scope of the present invention, and it is possible to combine the configurations shown in the modifications with the configurations described in each of the embodiments described above, or to combine the configurations described in the following different modifications.

[0090] In the above embodiment, the inside of the filled-type steel pipe concrete column 10 is hollow before the ready-mix concrete 16 is filled in, but the filled-type steel pipe concrete column 10 may also be a reinforced type with multiple main reinforcements arranged inside.

[0091] Furthermore, although a digital camera is used as the imaging unit 20 in the above embodiment, in order to improve the accuracy of detecting objects inside the steel pipe, the imaging unit 20 may also be equipped with, or in place of, a distance measuring sensor that can measure the distance and depth to objects inside the steel pipe over a wide range, such as a 3D-ToF sensor or an infrared sensor.

[0092] Furthermore, in order to clarify the reference position of the image P captured by the imaging unit 20, letters, symbols, or colors indicating the reference position may be applied to the inner wall surface 11a of the diaphragm 12 or the steel pipe section 11.

[0093] Furthermore, in the above embodiment, the filling speed of the ready-mixed concrete 16 is calculated based on the time from when the ready-mixed concrete 16 passes through the pouring hole 12a until it passes through the pouring hole 12a of another diaphragm 12. However, the method for determining the filling speed of the ready-mixed concrete 16 is not limited to this. For example, the filling speed of the ready-mixed concrete 16 may be determined by measuring the upward speed of the top surface 16a of the ready-mixed concrete 16 using a distance measuring sensor that utilizes laser light, or it may be determined from the lifting speed of the imaging unit 20 using a self-position estimation method based on VisualSLAM (Simultaneous Localization and Mapping).

[0094] Furthermore, although the above embodiment described a case in which only a diaphragm 12 is provided inside the filled-type concrete steel pipe column 10, if the filled-type concrete steel pipe column 10 is, for example, a welded assembled square steel pipe column assembled by welding together four flat plates, then a shape-retaining plate provided to ensure that the angle between adjacent flat plates is a right angle may be appropriately arranged inside the filled-type concrete steel pipe column 10 in addition to the diaphragm 12. The shape-retaining plate may also be appropriately provided inside the filled-type concrete steel pipe column 10 to prevent deformation during transportation or erection of the filled-type concrete steel pipe column 10. Thus, the shape-retaining plate provided inside the filled-type concrete steel pipe column 10 together with the diaphragm 12 is provided with a pouring hole formed through approximately the center and a plurality of through holes or notches formed around the pouring hole for air venting, similar to the diaphragm 12. Therefore, it is possible to determine whether or not the ready-mix concrete 16 has passed through the shape-retaining plate normally in the same way as when the ready-mix concrete 16 passes through the diaphragm 12. Furthermore, the learning results stored in the identification unit 31 may include the results of machine learning that was previously performed using image data of various shapes of shape-retaining plates installed on the filled-type steel pipe concrete column 10 as training data.

[0095] Although embodiments of the present invention have been described above, these embodiments only represent a part of the application examples of the present invention, and are not intended to limit the technical scope of the present invention to the specific configurations of the above embodiments. [Explanation of Symbols]

[0096] 100... Surveillance System 10. Filled steel pipe concrete column 11...Steel pipe section 11a...Interior wall surface 12. Diaphragm 12a...Pouring hole 12b...Air vent hole 16. Ready-mix concrete 16a...Top surface 20. Imaging Unit 31...Identification section 32. State determination unit

Claims

1. A monitoring system for filled-type steel pipe concrete columns, An imaging unit capable of imaging the inside of a steel pipe, A lighting device is suspended inside the steel pipe together with the imaging unit and illuminates the inside of the steel pipe, The identification unit stores the results of machine learning that has been performed in advance, and identifies objects in the image captured by the imaging unit based on the learning results, The system comprises a state determination unit that determines the state inside the steel pipe based on the object in the image identified by the identification unit, The imaging unit is a digital camera that does not have a depth measurement function. The learning results stored in the identification unit include the results of machine learning that was previously performed using image data of the inside of the steel pipe, captured when concrete was properly filled into the steel pipe, as training data. Monitoring system.

2. The learning results stored in the identification unit include the learning results of machine learning that was previously performed using image data of the inner wall surface of the steel pipe filled with concrete as training data. The identification unit identifies the inner wall surface of the steel pipe and the concrete filled inside the steel pipe as objects from the image captured in the region including the top surface of the concrete. The state determination unit determines the state of the concrete filled inside the steel pipe based on the boundary line between the inner wall surface and the concrete identified by the identification unit. The monitoring system according to claim 1.

3. The learning results stored in the identification unit include the results of machine learning that was previously performed using image data of the diaphragm installed on the filled-type steel pipe concrete column as a reinforcing member as training data. The identification unit identifies the diaphragm and the concrete passing through the pouring holes and air vents formed in the diaphragm as objects from the image captured of the region including the top surface of the concrete. The state determination unit determines the state of the concrete filled into the steel pipe based on the boundary line between the concrete that has passed through the pouring hole identified by the identification unit and the diaphragm, and the boundary line between the concrete that has passed through the air vent hole identified by the identification unit and the diaphragm. The monitoring system according to claim 1.

4. The learning results stored in the identification unit include the results of machine learning that was previously performed using image data of the diaphragm installed on the filled-type steel pipe concrete column as a reinforcing member as training data. The identification unit identifies the diaphragm and the concrete passing through the pouring hole formed in the diaphragm as objects from the image captured in the region including the top surface of the concrete. The state determination unit determines the filling speed of the concrete being filled into the steel pipe based on the elapsed time from when the identification unit identifies that the concrete has passed through the pouring hole of the diaphragm until when the identification unit identifies that the concrete has passed through the pouring hole of another diaphragm located above the diaphragm. The monitoring system according to claim 1.

5. The learning results stored in the identification unit include the learning results of machine learning that was previously performed using image data of foreign matter mixed into the steel pipe as training data. The state determination unit determines that there is an abnormality in the steel pipe filled with concrete when the foreign object is identified as such by the identification unit from the image captured of the region including the top surface of the concrete. The monitoring system according to claim 1.

6. The state determination unit determines that there is an abnormality in the steel pipe filled with concrete if an unknown object that cannot be identified using the learning results stored in the identification unit from the image taken of the region including the top surface of the concrete is identified as the object by the identification unit. A monitoring system according to any one of claims 1 to 5.

7. The learning results stored in the identification unit include the learning results of machine learning that was previously performed using image data of foreign matter mixed into the steel pipe as training data. The state determination unit determines that the state inside the steel pipe is in a state where concrete cannot be filled if the identification unit identifies the foreign object as the object from the image of the inside of the steel pipe taken before the concrete is filled, or if an unknown object that cannot be identified using the learning results stored in the identification unit is identified as the object. The monitoring system according to claim 1.

Images