System for self-diagnosis of concrete utility pole vertical cracks

Abstract

The present invention relates to a system for self-diagnosis of concrete utility pole vertical cracks and, more specifically, to a system for self-diagnosis of concrete utility pole vertical cracks, the system determining whether concrete utility pole vertical cracks occur so that a user can be notified thereof.

Description

Concrete utility pole vertical crack self-diagnosis system

[0001] The present invention relates to a self-diagnosis system for vertical cracks in concrete utility poles, and more particularly, to a self-diagnosis system for vertical cracks in concrete utility poles that can determine whether a vertical crack has occurred and inform a user of the presence of the crack.

[0002]

[0003] Typically, concrete utility poles are partially buried underground and are composed of cantilever-shaped structural members, and the weight of wires and various transmission and distribution-related accessories is installed on the top of the utility pole to act as a load.

[0004]

[0005] The load acts mostly as an axial compressive load on the utility pole, but when the horizontal arrangement angle of the power cable changes or the transmission and distribution equipment is installed to one side, it acts as an eccentric load and acts as a moment load on the cantilever member.

[0006]

[0007] Due to the action of this eccentric load, the largest moment load is applied from the ground surface location where the utility pole is embedded in the ground to a certain depth, which causes bending of the utility pole, and there is a problem that cracks may occur in the longitudinal direction of the utility pole when excessive moment load occurs, when a continuous moment load occurs for a long period of time, or when temperature load due to climate change occurs.

[0008]

[0009] The present invention was created to solve such problems, and the purpose of the present invention is to provide a self-diagnosis system for vertical cracks in concrete utility poles that can determine whether vertical cracks have occurred in concrete utility poles and inform the user of the occurrence.

[0010]

[0011] In order to achieve the above object, the present invention provides a self-diagnosis system for vertical cracks in a concrete utility pole, comprising: a crack detection device installed on the concrete utility pole and generating detection information; a crack detection server receiving detection information from the crack detection device, analyzing the detection information using a pre-learned artificial intelligence algorithm, and determining whether or not there is a vertical crack in the concrete utility pole; and a user terminal receiving a crack occurrence alarm from the crack detection server.

[0012]

[0013] In addition, the crack detection device is characterized by including a crack detection sensor unit including a first sensor unit and a second sensor unit installed on the outer surface of the concrete utility pole to generate detection information; a crack detection control unit that receives detection information from the crack detection sensor unit, stores the detection information, and transmits the detection information to the crack detection server; and a sensor cable that is wired inside the concrete utility pole to connect the crack detection sensor unit and the crack detection control unit to each other.

[0014]

[0015] In addition, the first sensor unit is characterized by including a plurality of first sensor body units installed in close contact to surround a crack or a portion expected to have a crack on the outer surface of the concrete utility pole; and a plurality of first sensor detection units installed on the side of the first sensor body unit to generate detection information.

[0016]

[0017] In addition, the first sensor unit is a strain gauge, typically two of which are installed on the side of the first sensor body unit, and when a vertical crack occurs in a concrete utility pole due to an external force and is transmitted to the first sensor body unit, the strain transmitted to the first sensor body unit is measured to generate detection information.

[0018]

[0019] In addition, the second sensor unit is characterized by including a second sensor body unit that is installed in a plurality of pieces so as to be tightly fitted to surround a crack or a portion expected to have a crack on the outer surface of the concrete utility pole; and a second sensor detection unit that is installed in a plurality of pieces on the side of the second sensor body unit to generate detection information.

[0020]

[0021] In addition, the second sensor unit is characterized by having four strain gauges installed on the side of the second sensor body, and generating detection information by directly measuring the increase in diameter of the concrete utility pole.

[0022]

[0023] In addition, the crack detection server is characterized by including an algorithm learning unit that learns a plurality of artificial intelligence algorithms through a learning dataset, and selects and stores the artificial intelligence algorithm with the highest performance among the plurality of artificial intelligence algorithms through a verification and test dataset; an algorithm adoption unit that adopts one of the artificial intelligence algorithms stored in the algorithm learning unit when detection information is transmitted from the crack detection device; an algorithm prediction unit that analyzes the detection information through the algorithm adopted by the algorithm adoption unit and transmits crack alarm information to the user terminal when it is determined to be a crack; and an algorithm re-learning unit in which the algorithm prediction unit re-learns the artificial intelligence algorithm through the detection information analysis result.

[0024]

[0025] In addition, the algorithm learning unit is characterized in that it uses a Bayesian Optimizer technique that optimizes hyperparameters of artificial intelligence algorithms to measure at least one of sensitivity, specificity, accuracy, PPV (positive predictive value), NPV (negative predictive value), and AUC (area under the ROC (receiver operating characteristic)) scores of multiple artificial intelligence algorithms, and selects and stores the artificial intelligence algorithm with the highest performance.

[0026]

[0027] The self-diagnosis system for vertical cracks in a concrete utility pole according to the present invention can improve the efficiency of managing concrete utility poles by determining whether vertical cracks have occurred in a concrete utility pole and informing the user of the same.

[0028]

[0029] The problems solved by the present invention are not limited to those mentioned above, and other problems not mentioned can be clearly understood by those skilled in the art from the description below.

[0030]

[0031] Figure 1 is a block diagram of a self-diagnosis system for vertical cracks in a concrete utility pole according to an embodiment of the present invention.

[0032] Figure 2 is an example of a vertical crack in a concrete utility pole according to one embodiment of the present invention.

[0033] Figure 3 is an example of a crack detection device according to an embodiment of the present invention.

[0034] Figure 4 is an exemplary diagram of a first sensor unit according to an embodiment of the present invention.

[0035] Figure 5 is an exemplary diagram of a second sensor unit according to an embodiment of the present invention.

[0036] Figure 6 is a block diagram of a crack detection server according to an embodiment of the present invention.

[0037] Figure 7 is a flow chart of a method for self-diagnosing vertical cracks in a concrete utility pole using a self-diagnosing system for vertical cracks in a concrete utility pole according to an embodiment of the present invention.

[0038]

[0039] <Explanation of symbols>

[0040] 1: Concrete telephone pole

[0041] 100: Crack detection device

[0042] 110: Crack detection sensor unit

[0043] 111: First sensor section

[0044] 111a: First sensor body

[0045] 111b: First sensor detection unit

[0046] 112: Second sensor section

[0047] 112a: Second sensor body

[0048] 112b: Second sensor detection unit

[0049] 120: Crack detection control unit

[0050] 130: Sensor cable

[0051] 200: Crack detection server

[0052] 210: Algorithm Learning Department

[0053] 220: Algorithm Adoption Department

[0054] 230: Algorithm Prediction Section

[0055] 240: Algorithm Relearning Department

[0056] 300: User terminal

[0057]

[0058] The above-described purposes, other purposes, features, and advantages of the present invention will be readily understood through the following preferred embodiments, illustrated in the accompanying drawings. However, the present invention is not limited to the embodiments described herein and may be embodied in other forms. Rather, the embodiments introduced herein are provided to ensure that the disclosure is thorough and complete, and to ensure that the spirit of the present invention is fully conveyed to those skilled in the art.

[0059]

[0060] When any element, component, device, or system is referred to in this specification as including a component consisting of a program or software, even if not explicitly stated, it should be understood that the element, component, device, or system includes hardware (e.g., memory, CPU, etc.) or other programs or software (e.g., an operating system or drivers necessary to operate hardware) necessary for the program or software to be executed or operated.

[0061]

[0062] Additionally, unless specifically stated otherwise in the implementation of any element (or component), it should be understood that the element (or component) may be implemented in software, hardware, or both software and hardware.

[0063]

[0064] Additionally, the terminology used herein is for the purpose of describing embodiments and is not intended to limit the present invention. In this specification, the singular also includes the plural unless specifically stated otherwise. As used herein, the terms "comprises" and / or "comprising" do not exclude the presence or addition of one or more other components.

[0065]

[0066] Additionally, terms such as "part" and "device" in this specification may be intended to refer to the functional and structural combination of hardware and software driven by or for driving the hardware. For example, the hardware herein may be a data processing device including a CPU or other processor. Furthermore, software driven by the hardware may refer to a running process, object, executable, thread of execution, program, etc.

[0067]

[0068] Hereinafter, the specific technical contents to be implemented in the present invention will be described in detail with reference to the attached drawings.

[0069]

[0070] It will be readily apparent to an average expert in the art that each component depicted in the drawings is functionally and logically separable, and does not necessarily mean that each component is separated into a separate physical device or written in separate code.

[0071]

[0072] Fig. 1 is a block diagram of a self-diagnosis system for vertical cracks in concrete utility poles according to an embodiment of the present invention. As illustrated in Fig. 1, the self-diagnosis system for vertical cracks in concrete utility poles according to the present invention may include a crack detection device (100), a crack detection server (200), and a user terminal (300).

[0073]

[0074] As previously explained, the concrete utility pole (1) may be subject to bending depending on changes in the horizontal arrangement angle of the wire cables installed at the top, or if transmission and distribution accessories are installed to one side, and if such bending occurs for a long period of time or due to various loads such as temperature loads due to climate change, vertical cracks may occur as shown in Fig. 2. Fig. 2 is an example of vertical cracks in a concrete utility pole according to an embodiment of the present invention. (Source: https: / www.aitimes.kr / news / articleView.html?idxno=17551)

[0075]

[0076] The above crack detection device (100) is installed on the concrete utility pole (1) and, when bending occurs in the concrete utility pole (1), is configured to detect this and generate detection information. As shown in FIG. 3, the device may include a crack detection sensor unit (110), a crack detection control unit (120), and a sensor cable (130).

[0077]

[0078] The above crack detection sensor unit (110) is configured to be installed on the outer surface of the concrete utility pole (1) to generate detection information, and may include a first sensor unit (111) and a second sensor unit (112). The first sensor unit (111) and the second sensor unit (112) may include a first sensor body unit (111a) and a first sensor detection unit (111b) and a second sensor body unit (112a) and a second sensor detection unit (112b), as shown in FIGS. 4 and 5, respectively. FIG. 4 is an exemplary diagram of a first sensor unit according to an embodiment of the present invention, and FIG. 5 is an exemplary diagram of a second sensor unit according to an embodiment of the present invention.

[0079]

[0080] The first sensor body part (111a) and the second sensor body part (112a) are installed in a belt shape to be tightly attached to the outer surface of the concrete utility pole (1) so as to surround a crack or a part expected to have a crack, and can preferably be manufactured from a steel plate.

[0081]

[0082] The first sensor detection unit (111b) is installed in multiple numbers on the side of the first sensor body (111a) in the direction of the circumference of the concrete utility pole to generate detection information, and may preferably be a strain gauge sensor installed, typically two or as many as necessary, around the circumference of the first sensor body (111a).

[0083]

[0084] The first sensor detection unit (111b) can generate detection information by measuring the strain transmitted to the first sensor body (111a) when the longitudinal bending moment of the concrete utility pole (1) is transmitted to the first sensor body (111a).

[0085]

[0086] The second sensor detection unit (112b) is installed in multiple numbers on the side of the second sensor body (112a) in the direction of the circumference of the concrete utility pole to generate detection information, and may preferably be a strain gauge sensor installed in a representative number of four or a required quantity around the circumference of the second sensor body (112a).

[0087]

[0088] The above second sensor detection unit (112b) can directly measure the increase in diameter when the diameter of the concrete utility pole (1) changes due to bending and generate detection information.

[0089]

[0090] Although the first sensor unit (111) and the second sensor unit (112) are shown as being installed only in the drawing, multiple units may be installed to generate detection information as needed.

[0091]

[0092] The above sensor detection control unit (120) is configured to receive and store detection information generated by the crack detection sensor unit (110) and transmit the detection information to the crack detection server (200), and may be installed on one side of the exterior of the concrete utility pole (1). For this purpose, the sensor detection control unit (120) may further include configurations for communication, storage, and control.

[0093]

[0094] The above sensor cable (130) is configured to be wired inside the concrete utility pole (1) to connect the crack detection sensor unit (110) and the crack detection control unit (120) to each other, and can utilize the existing electric line without drilling the concrete utility pole (1) for wiring.

[0095]

[0096] In the embodiment, the sensor cable (130) is shown for data transmission and reception of the crack detection sensor unit (110) and the crack detection control unit (120), but it can be replaced wirelessly as needed.

[0097]

[0098] The above crack detection server (200) receives detection information from the crack detection device (100), analyzes the detection information using a pre-learned artificial intelligence algorithm, and determines whether the concrete utility pole has a horizontal crack. To this end, as shown in FIG. 6, it may include an algorithm learning unit (210), an algorithm adoption unit (220), an algorithm prediction unit (230), and an algorithm re-learning unit (240). FIG. 6 is a block diagram of a crack detection server according to an embodiment of the present invention.

[0099]

[0100] The above algorithm learning unit (210) is configured to perform learning of multiple artificial intelligence algorithms through a learning data set, and select and store the artificial intelligence algorithm with the highest performance among multiple artificial intelligence algorithms through a verification and test data set.

[0101]

[0102] Here, the above learning dataset, verification dataset, and test dataset may be datasets in which labeling and preprocessing have been performed on detection information generated by detecting a concrete utility pole (1).

[0103]

[0104] In addition, the algorithm learning unit (210) can use a Bayesian Optimizer technique that optimizes hyperparameters of artificial intelligence algorithms to measure at least one of sensitivity, specificity, accuracy, PPV (positive predictive value), NPV (negative predictive value), and AUC (area under the ROC (receiver operating characteristic)) scores of multiple artificial intelligence algorithms to select and store the artificial intelligence algorithm with the highest performance.

[0105]

[0106] The above algorithm adoption unit (220) is configured to adopt one of the artificial intelligence algorithms stored in the algorithm learning unit (110) when detection information is transmitted from the crack detection device (100).

[0107]

[0108] The above algorithm prediction unit (130) is configured to analyze the detection information through the algorithm adopted by the algorithm adoption unit (120) and, if it is determined to be a crack, transmit crack alarm information to the user terminal (300).

[0109]

[0110] The above algorithm relearning unit (140) is configured to continuously improve the performance of the artificial intelligence algorithm by relearning the artificial intelligence algorithm through the detection information analysis results performed by the above algorithm prediction unit (130).

[0111]

[0112] The above user terminal (300) is a terminal used by an administrator who manages the concrete utility pole (1), and is configured to receive crack alarm information transmitted from the crack detection server (200) and perform management, control, etc. of the crack detection device (100) and the crack detection server (200).

[0113]

[0114] Each of the above components (100, 200 or 300) may include at least one processor. The at least one processor may be implemented as an Application Specific Integrated Circuit (ASIC), a Digital Signal Processor (DSP), a Programmable Logic Device (PLD), a Field Programmable Gate Array (FPGA), a Central Processing Unit (CPU), a Graphic Processing Unit (GPU), a microcontroller and / or a microprocessor. Each of the components (100, 200 or 300) may further include a memory. The memory may include storage media such as flash memory, hard disk, solid state disk (SSD), random access memory (RAM), static random access memory (SRAM), read only memory (ROM), programmable read only memory (PROM), electrically erasable and programmable ROM (EEPROM), erasable and programmable ROM (EPROM), and / or embedded multimedia card (eMMC).

[0115]

[0116] In addition, each component (100, 200 or 300) can be connected via a network, where the network means a connection structure that enables information exchange between each node, such as a plurality of terminals and servers, and examples of such networks include a local area network (LAN), a wide area network (WAN), the Internet (WWW: World Wide Web), a wired / wireless data communication network, a telephone network, a wired / wireless television communication network, etc. Examples of wireless data communication networks include, but are not limited to, 3G, 4G, 5G, 3GPP (3rd Generation Partnership Project), 5GPP (5th Generation Partnership Project), LTE (Long Term Evolution), WIMAX (World Interoperability for Microwave Access), Wi-Fi, the Internet, LAN (Local Area Network), Wireless LAN (Wireless Local Area Network), WAN (Wide Area Network), PAN (Personal Area Network), RF (Radio Frequency), Bluetooth network, NFC (Near-Field Communication) network, satellite broadcasting network, analog broadcasting network, and DMB (Digital Multimedia Broadcasting) network.

[0117]

[0118] Hereinafter, a method for self-diagnosing a vertical crack in a concrete utility pole using a self-diagnosing system for vertical cracks in a concrete utility pole configured as described above will be described with reference to Fig. 7.

[0119]

[0120] FIG. 7 is a flowchart of a method for self-diagnosing vertical cracks in a concrete utility pole using a self-diagnostic system for vertical cracks in a concrete utility pole according to an embodiment of the present invention. As illustrated in FIG. 7, the method for self-diagnosing vertical cracks in a concrete utility pole using a self-diagnostic system for vertical cracks in a concrete utility pole according to the present invention comprises a step (S100) in which a crack detection device (100) is installed on a concrete utility pole (1) to generate detection information, a step (S200) in which a crack detection server (200) receives detection information from the crack detection device (100) and analyzes the detection information using a pre-learned artificial intelligence algorithm to determine whether a vertical crack exists in the concrete utility pole (1), and a step (S300) in which a user terminal (300) receives a crack occurrence alarm from the crack detection server (200).

[0121]

[0122] Therefore, as described above, through the concrete utility pole vertical crack self-diagnosis system according to the present invention, a user can receive crack alarm information when a vertical crack occurs in a concrete utility pole, thereby improving the management efficiency of the concrete utility pole.

[0123]

[0124] Although all components constituting the embodiments of the present invention have been described above as being combined or operating in combination, the present invention is not necessarily limited to these embodiments. That is, within the scope of the purpose of the present invention, all of the components may be selectively combined and operated one or more times. In addition, although all of the components may be implemented as individual independent hardware, some or all of the components may be selectively combined and implemented as a computer program having program modules that perform some or all of the functions of the combined hardware in one or more pieces. The codes and code segments constituting the computer program can be easily inferred by those skilled in the art of the present invention. Such a computer program may be stored in a computer-readable storage medium and read and executed by a computer, thereby implementing the embodiments of the present invention.

[0125]

[0126] Meanwhile, while the preferred embodiments have been described and illustrated to illustrate the technical concept of the present invention, the present invention is not limited to the configuration and operation as illustrated and described above, and those skilled in the art will readily understand that numerous changes and modifications to the present invention are possible without departing from the scope of the technical concept. Accordingly, all such appropriate changes and modifications and equivalents should be considered to fall within the scope of the present invention. Accordingly, the true technical protection scope of the present invention should be determined by the technical concept of the appended claims.

Claims

1. In a system for detecting cracks in concrete utility poles, A crack detection device installed on the above concrete utility pole and generating detection information; A crack detection server that receives detection information from the crack detection device, analyzes the detection information using a pre-learned artificial intelligence algorithm, and determines whether there is a vertical crack in the concrete utility pole; and A user terminal that receives a crack occurrence alarm from the crack detection server; A self-diagnosis system for vertical cracks in concrete utility poles, characterized by including:

2. In paragraph 1, The above crack detection device, A crack detection sensor unit including a first sensor unit and a second sensor unit installed on the outer surface of the concrete utility pole and generating detection information; A crack detection control unit that receives detection information from the crack detection sensor unit, stores the detection information, and transmits the detection information to the crack detection server; and A sensor cable that is wired inside the concrete telephone pole and connects the crack detection sensor unit and the crack detection control unit to each other; A self-diagnosis system for vertical cracks in concrete utility poles, characterized by including:

3. In paragraph 2, The above first sensor part, A first sensor body part installed in multiple pieces so as to be tightly wrapped around a crack or a part expected to have a crack on the outer surface of the concrete electric pole; and A first sensor detection unit which is installed in multiple numbers on the side of the first sensor body to generate detection information; A self-diagnosis system for vertical cracks in concrete utility poles, characterized by including:

4. In paragraph 3, The above first sensor part, Two strain gauges are typically installed on the side of the first sensor body. A self-diagnosis system for a concrete utility pole vertical crack, characterized in that when a vertical crack occurs in a concrete utility pole due to an external force and is transmitted to the first sensor body, the system generates detection information by measuring the strain transmitted to the first sensor body.

5. In paragraph 2, The above second sensor part, A second sensor body part installed in multiple pieces so as to be tightly wrapped around a crack or a part expected to have a crack on the outer surface of the concrete electric pole; and A second sensor detection unit installed in multiple numbers on the side of the second sensor body to generate detection information; A self-diagnosis system for vertical cracks in concrete utility poles, characterized by including:

6. In paragraph 5, The above second sensor part, Four strain gauges are installed on the side of the second sensor body. A self-diagnosis system for vertical cracks in concrete utility poles characterized by generating detection information by directly measuring the increase in diameter of the concrete utility pole.

7. In paragraph 1, The above crack detection server, An algorithm learning unit that performs learning of multiple artificial intelligence algorithms through a learning dataset, and selects and stores the artificial intelligence algorithm with the highest performance among multiple artificial intelligence algorithms through a verification and test dataset; An algorithm adoption unit that adopts one of the artificial intelligence algorithms stored in the algorithm learning unit when detection information is transmitted from the crack detection device; An algorithm prediction unit that analyzes the detection information through the algorithm adopted by the algorithm adoption unit and, if it is determined to be a crack, transmits crack alarm information to the user terminal; and An algorithm re-learning unit in which the above algorithm prediction unit re-learns the artificial intelligence algorithm through the analysis results of the detection information; A self-diagnosis system for vertical cracks in concrete utility poles, characterized by including:

8. In paragraph 7, The above algorithm learning unit is, A concrete utility pole vertical crack self-diagnosis system characterized by using a Bayesian Optimizer technique that optimizes the hyperparameters of artificial intelligence algorithms, and selecting and storing the artificial intelligence algorithm with the highest performance by measuring at least one of the sensitivity, specificity, accuracy, PPV (positive predictive value), NPV (negative predictive value), and AUC (area under the ROC (receiver operating characteristic)) scores of multiple artificial intelligence algorithms.

Images