Foreign matter detection method and device for gas insulated switchgear

Abstract

The invention provides a foreign matter detection method and device for a gas insulated switchgear, and relates to the technical field of intelligent nondestructive testing of high-voltage electrical equipment.The foreign matter detection method for the gas insulated switchgear comprises the steps that three-dimensional reconstruction is conducted on the surface of a to-be-detected object in the gas insulated switchgear; a three-dimensional temperature cloud picture of the surface of the object to be detected is obtained, and the temperature in the three-dimensional temperature cloud picture is distinguished according to the RGB value of the image; the three-dimensional temperature cloud picture is input into a trained neural network model, foreign matter on the surface of the to-be-detected object is detected, and the neural network model executes the following operations that S21, abnormal points in the three-dimensional temperature cloud picture are recognized according to the RGB value of the three-dimensional temperature cloud picture; and S22, taking the abnormal points as foreign matters on the surface of the to-be-detected object, and determining the types, the number, the sizes and the positions of the foreign matters, thereby improving the sensitivity of detecting the foreign matters in the gas insulated switchgear, and being relatively high in accuracy.

Description

TECHNICAL FIELD

[0001] The present application generally relates to the technical field of intelligent non-destructive testing of high-voltage electrical equipment. More particularly, the present application relates to a foreign matter detection method, device, medium and electronic device for a gas insulated switchgear. BACKGROUND

[0002] During production, installation and long-term operation of a gas insulated switchgear, assembly leftovers, dust or metal micro debris generated during operation may be left inside. These small foreign matters, especially sub-millimeter particles, may cause partial discharge and even lead to equipment failure. Traditional detection methods such as X-ray detection and ultrasonic detection have the following problems: X-ray detection: large radiation hazard and low sensitivity to metal and non-metal micro particles; Ultrasonic detection: weak signal interference from structure reflection and micro particles, making it difficult to distinguish and identify micro particles.

[0003] The conventional solution is to use non-woven fabric to wipe and then observe the metallic luster to detect micro particles. However, the detection sensitivity is low, and micro particles may be missed, resulting in low accuracy. SUMMARY

[0004] To solve at least one or more of the above-mentioned technical problems, the present application provides a foreign matter detection method and device for a gas insulated switchgear in multiple aspects.

[0005] In a first aspect, the present application provides a foreign matter detection method for a gas insulated switchgear, comprising the following steps: S1, performing three-dimensional reconstruction on a surface of an object to be detected inside the gas insulated switchgear to obtain a three-dimensional temperature cloud image of the surface of the object to be detected, wherein the temperature level in the three-dimensional temperature cloud image is distinguished by the RGB value of the image; S2, inputting the three-dimensional temperature cloud image into a trained neural network model to detect foreign matters on the surface of the object to be detected, wherein the trained neural network model performs the following operations: S21, identifying an abnormal point in the three-dimensional temperature cloud image according to the RGB value of the three-dimensional temperature cloud image; S22, regarding the abnormal point as a foreign matter on the surface of the object to be detected and determining the type, quantity, size and position of the foreign matter.

[0006] In some examples, identifying an abnormal point in the three-dimensional temperature cloud image according to the RGB value of the three-dimensional temperature cloud image comprises: When a point with red color is detected in the three-dimensional temperature cloud image, the point is regarded as an abnormal point in the three-dimensional temperature cloud image.

[0007] In some examples, before the surface of the object to be detected inside the gas insulated switchgear is three-dimensionally reconstructed to obtain a three-dimensional temperature cloud map of the surface of the object to be detected, the method further comprises: heating the surface of the object to be detected inside the gas insulated switchgear.

[0008] In a second aspect, the application provides a foreign matter detection device for a gas insulated switchgear, comprising: a thermal excitation module configured to heat the surface of the object to be detected inside the gas insulated switchgear; an infrared imaging module configured to three-dimensionally reconstruct the surface of the object to be detected inside the gas insulated switchgear after being heated, to generate a three-dimensional temperature cloud map and input the three-dimensional temperature cloud map into an analysis module; the analysis module is configured to perform the steps S21-S22 as described in claim 1, wherein, the thermal excitation module and the infrared imaging module are both fixedly arranged on a mechanical arm.

[0009] In some examples, the training process of the trained neural network model comprises: pre-placing foreign matters of a set type, size, spacing and number at corresponding positions on the surface of the object to be detected; generating an image training set by changing the type, size, spacing, number and position of the foreign matters multiple times; inputting the image training set into a neural network model to train the neural network model, to obtain a trained neural network model.

[0010] In some examples, the thermal excitation module is a laser, a pulse resistance heater or a microwave heater.

[0011] In some examples, the infrared imaging module is a camera array comprising multiple infrared cameras, each of which has infrared thermal imaging and visible light imaging functions.

[0012] In some examples, the mechanical arm is a multi-degree-of-freedom mechanical arm.

[0013] In a third aspect, the application provides a computer-readable storage medium containing program instructions, which, when executed by a processor, cause the implementation of the method disclosed in the first aspect.

[0014] In a fourth aspect, the application provides an electronic device, comprising: a processor; and a memory storing computer instructions, which, when executed by the processor, cause the electronic device to perform the method disclosed in the first aspect.

[0015] The foreign matter detection method, device, medium and electronic device for the gas insulated switchgear provided by the present application identify an abnormal point in the three-dimensional temperature cloud map according to the RGB value of the three-dimensional temperature cloud map, determine the type, quantity, size and position of the foreign matter as the object surface to be detected, and improve the sensitivity of the foreign matter detection inside the gas insulated switchgear, with high accuracy. BRIEF DESCRIPTION OF DRAWINGS

[0016] The above and other objects, features and advantages of the present application will become more apparent from the following detailed description read in conjunction with the accompanying drawings. In the drawings, several embodiments of the present application are shown by way of example, and the same or corresponding reference numbers indicate the same or corresponding parts, in which: Figure 1 An exemplary flowchart of the foreign matter detection method for the gas insulated switchgear provided by the embodiment of the present application is shown; Figure 2 An exemplary three-dimensional temperature cloud map effect diagram generated by the foreign matter detection method for the gas insulated switchgear provided by the embodiment of the present application is shown; Figure 3 An exemplary structural block diagram of the foreign matter detection device for the gas insulated switchgear provided by the embodiment of the present application is shown; Figure 4 An exemplary structural block diagram of the electronic device of some embodiments of the present application is shown.

[0017] In Figure 2 , the following is shown: 1, fixing device; 2, rotating shaft; 3, buckle sleeve; 4, mechanical arm; 5, thermal excitation module; 6, infrared imaging module; 7, analysis module; 8, connecting rod. DETAILED DESCRIPTION

[0018] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are some, but not all, of the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work fall within the scope of protection of the present application.

[0019] It should be understood that the terms "include" and "contain" used in the specification and claims of the present application indicate the presence of the described features, whole, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, whole, steps, operations, elements, components and / or sets thereof.

[0020] It is also to be understood that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting. As used in this specification and in the claims, the singular forms "a," "an," and "the" include plural referents unless the context clearly dictates otherwise. It will be further understood that the terms "comprises" and / or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof. It will be further understood that the terms "comprises" and / or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0021] As used in this specification and claims, the terms "if' and "when" can each be interpreted to mean "upon a determination" or "in response to a determination" or "in response to detecting," as appropriate, depending on the context. Similarly, the phrase "if it is determined" or "if [a described condition or event] is detected" can each be interpreted to mean "upon determining" or "in response to determining" or "upon detecting [the described condition or event]" or "in response to detecting [the described condition or event]," as appropriate, depending on the context.

[0022] The detailed description of the application will be made with reference to the accompanying drawings.

[0023] Embodiment 1 As Figure 1 shown, the foreign matter detection method for a gas insulated switchgear provided by the present application comprises the following steps: S101, a three-dimensional reconstruction is performed on the surface of an object to be detected inside the gas insulated switchgear to obtain a three-dimensional temperature cloud image of the surface of the object to be detected, wherein the temperature level in the three-dimensional temperature cloud image is distinguished by the RGB value of the image.

[0024] Specifically, the obtained three-dimensional temperature cloud image is as shown in Figure 2 The points with brightness greater than the background color are foreign matters, and the higher the temperature of the foreign matter, the greater the brightness.

[0025] S102, the three-dimensional temperature cloud image is input into a trained neural network model to detect the foreign matter on the surface of the object to be detected, wherein the trained neural network model performs the following operations: S201, according to the RGB value of the three-dimensional temperature cloud image, an abnormal point in the three-dimensional temperature cloud image is identified; S202, the abnormal point is determined as a foreign matter on the surface of the object to be detected and the type, quantity, size and position of the foreign matter are determined.

[0026] Specifically, the brightness Brightness = 0.3R + 0.6G + 0.1B‌.‌ In some examples, according to the RGB value of the three-dimensional temperature cloud image, identifying the abnormal point in the three-dimensional temperature cloud image comprises: When it is detected that there is a point with a brightness value greater than a preset threshold in the three-dimensional temperature cloud map, the point is taken as an abnormal point in the three-dimensional temperature cloud map.

[0027] In some examples, before the surface of the object to be detected in the gas insulated switchgear is three-dimensionally reconstructed to obtain a three-dimensional temperature cloud map of the surface of the object to be detected, the method further comprises: The surface of the object to be detected in the gas insulated switchgear is heated.

[0028] Specifically, the foreign matter on the surface of the object to be detected in the gas insulated switchgear is heated at the same time when the surface of the object to be detected in the gas insulated switchgear is heated. Since the foreign matter on the surface of the object to be detected in the gas insulated switchgear is mostly dust or metal debris, the thermal conductivity is high, and the temperature is sensitive. After being heated, it is convenient to detect by using the infrared imaging device.

[0029] According to the RGB value of the three-dimensional temperature cloud map, the application identifies the abnormal point in the three-dimensional temperature cloud map, takes the abnormal point as the foreign matter on the surface of the object to be detected, and determines the type, quantity, size and position of the foreign matter, thereby improving the sensitivity of the foreign matter detection in the gas insulated switchgear and having high accuracy.

[0030] Embodiment 2 As shown in Figure 3 The foreign matter detection device for the gas insulated switchgear provided by the application embodiment includes a mechanical arm 4, a thermal excitation module 5, an infrared imaging module 6, and an analysis module 7. Wherein: The thermal excitation module 5 is used for heating the foreign matter on the surface of the object to be detected in the gas insulated switchgear.

[0031] In some examples, the thermal excitation module 5 is a laser or a pulse resistance heater or a microwave heater, and can also be other devices with the same function.

[0032] Specifically, the thermal excitation module 5 is a 1.2-4 μm wide tuning laser with a power of 0-100 W and a spot diameter of 0.5-20 mm. The wide tuning laser is provided with a cooling device inside, which is used for heat dissipation of the excitation device inside the wide tuning laser.

[0033] The infrared imaging module 6 is used for three-dimensionally reconstructing the surface of the object to be detected in the gas insulated switchgear after heating, generating a three-dimensional temperature cloud map, and inputting the three-dimensional temperature cloud map into the analysis module.

[0034] In some examples, the infrared imaging module 6 is an infrared camera.

[0035] Specifically, the infrared imaging module 6 is a camera array including a plurality of infrared cameras, each of which has infrared thermal imaging and visible light imaging functions, wherein each infrared camera is a medium wave infrared camera (resolution of 640x512, noise equivalent temperature difference NETD<20mK) matched with a long wave infrared lens. The infrared imaging module embeds a thermal feature extraction algorithm and identifies targets based on the thermal conductivity difference between foreign objects and the detected objects. That is, through the short-time high-energy heating of the foreign object by the thermal excitation module 5, the foreign object is located by observing the temperature difference of the surface cooling process, so that the infrared imaging module 6 can perform all-around imaging on the surface of the gas insulated switchgear.

[0036] Specifically, the infrared imaging module 6 inputs the generated three-dimensional temperature cloud image into the analysis module 7.

[0037] After the analysis module 7 receives the three-dimensional temperature cloud image input by the infrared imaging module 6, the following operations are performed: S21, identifying an abnormal point in the three-dimensional temperature cloud image according to the RGB value of the three-dimensional temperature cloud image; S22, regarding the abnormal point as a foreign object on the surface of the detected object and determining the type, number, size and position of the foreign object.

[0038] In some examples, the analysis module 7 is a host computer.

[0039] Specifically, the analysis module 7 can be a local server or a cloud server, and can also be a home desktop computer, a notebook computer, etc.

[0040] In some examples, the training process of the trained neural network model includes: Pre-placing foreign objects of a set type, size, spacing and number at corresponding positions on the surface of the detected object; Generating an image training set by changing the type, size, spacing, number and position of the foreign object multiple times; Inputting the image training set into the neural network model to train the neural network model, to obtain the trained neural network model.

[0041] Specifically, by changing the type, size, spacing, number and position of the foreign object multiple times, the trained neural network model can identify foreign objects of different types (metal / non-metal), sizes, spacings, numbers and positions, thereby improving the detection accuracy.

[0042] In some examples, the neural network model is a deep convolutional neural network.

[0043] Specifically, the neural network model adopts a ResNet-18 neural network structure. ResNet-18 (Residual Network with 18 layers) is a classic deep convolutional neural network, which solves the problem of gradient vanishing / explosion in deep network by introducing a residual connection module, and is very suitable for image classification tasks (such as foreign matter detection).

[0044] The thermal excitation module 5 and the infrared imaging module 6 are both fixedly arranged on the mechanical arm 4.

[0045] Specifically, as shown in Figure 1 , the mechanical arm 4 is arranged on the fixed device 1 through a connecting rod 8, wherein the connecting rod 8 is arranged on the fixed device 1 through a rotating shaft 2, and the mechanical arm 4 is fixedly connected to one end of the connecting rod 8 through a buckle type sleeve 3.

[0046] In some examples, the mechanical arm 4 is a multi-degree-of-freedom mechanical arm.

[0047] Specifically, under the control of a controller, the telescopic stroke of the mechanical arm 4 is not less than 1.5 m, the head end thereof can rotate 360°, and the repeatability positioning accuracy is ±0.05 mm. The mechanical arm 4 adopts a carbon fiber composite material shell, and the electromagnetic shielding effectiveness is not less than 60 dB. The thermal excitation module and the infrared imaging module are both fixedly arranged on the head end of the mechanical arm 4, so that the thermal excitation module and the infrared imaging module can scan any position on the surface of the object to be detected.

[0048] The present application can realize non-contact detection of 0.1 mm level foreign matter through the cooperative work of the thermal excitation module and the infrared imaging module. The system adopts an anti-electromagnetic interference mechanical arm carrying a composite sensor, combines a thermal feature inversion algorithm and a deep learning classification technology, and solves the problem of insufficient high sensitivity detection of micron level small foreign matter particles in the limited space inside the GIS device and the insufficient light environment.

[0049] In another aspect, the embodiments of the present application also provide an electronic device, as shown in Figure 4 , Figure 4 is an exemplary structural block diagram of an electronic device according to an embodiment of the present application, as shown in Figure 4 , the electronic device comprises a processor and a memory, the memory stores computer instructions, and the processor executes the computer instructions to perform the method provided by the present application.

[0050] In particular, the processor 601 can include a central processing unit (CPU) or a graphics processing unit (GPU), or an application specific integrated circuit (ASIC), or can be configured to implement one or more integrated circuits to implement embodiments of the present application. The memory 602 can include a memory for storing data or instructions. For example, the memory 602 can be at least one of a hard disk drive (HDD), a read-only memory (ROM), a random access memory (RAM), a floppy disk drive, a flash drive, an optical disk, a magneto-optical disk, a magnetic tape, a universal serial bus (USB) drive, or other physical / tangible memory storage device. Also, for example, the memory 602 includes a removable or non-removable (or fixed) medium. Further, for example, the memory 602 can be internal or external to the integrated gateway disaster recovery device. The memory 602 can be a non-volatile solid-state memory. In other words, generally, the memory 602 includes a tangible (non-transitory) computer-readable storage medium (such as a memory device) encoded with executable instructions, where the stored executable instructions, when executed by the processor 601 (such as by one or more processors), implement the methods in embodiments of the present application.

[0051] In one example, Figure 4 The electronic device shown can also include a communication interface 603 and a bus 610. The processor 601, the memory 602, the communication interface 603 are connected through the bus 610 and complete the communication between each other. The communication interface 603 is mainly used to realize the communication between the modules, devices, units and / or devices in the electronic device. The bus 610 includes hardware, software or both, which can couple the components of the online data flow billing device to each other. For example, the bus can include at least one of an accelerated graphics port (AGP) or other graphics bus, an enhanced industry standard architecture (EISA) bus, a front side bus (FSB), a hyper transport (HT) interconnect, an industry standard architecture (ISA) bus, an infiniband interconnect, a low pin count (LPC) bus, a memory bus, a microchannel architecture (MCA) bus, a peripheral component interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a serial advanced technology attachment (SATA) bus, a video electronics standards association local (VLB) bus, or other suitable bus. The bus 610 can include one or more buses. Although specific buses are described or shown in embodiments of the present application, any suitable bus or interconnect can be considered in embodiments of the present application.

[0052] In another aspect, the embodiments of the present application further provide a computer readable storage medium, having stored thereon computer program instructions, which, when executed by a processor, implement the method described above. The computer readable storage medium is, for example, a classical computer readable storage medium, such as a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk storage medium, an optical storage medium, a flash memory device, an electrical, optical, or other physical / tangible storage device.

[0053] In another aspect, the embodiments of the present application further provide a computer program product, which includes computer program instructions, which, when executed by a processor, implement the method provided by the embodiments of the present application. The computer program product is, for example, a software installation package, a plug-in compatible with a related software system, etc.

[0054] The flowcharts and / or block diagrams above exemplarily describe the flowcharts and / or block diagrams of the method and system of the embodiments of the present application, and describe the related aspects. It should be understood that each block in the flowcharts and / or block diagrams, or a combination thereof, can be implemented by computer program instructions, or by special hardware performing specified functions or actions, or by a combination of special hardware and computer instructions. When implemented in hardware, it can be, for example, an electronic circuit, an application specific integrated circuit (ASIC), appropriate firmware, a plug-in, a functional card, etc.; when implemented in software, it is a program or a code segment used to perform the required tasks. The program or code segment can be stored in a memory, or transmitted in a data signal carried in a carrier wave over a transmission medium or a communication link. The code segment can be downloaded via a computer network, such as the Internet, an intranet, etc.

[0055] Although the present application has shown and described several embodiments, it is obvious that such embodiments are provided by way of example only. Numerous changes and modifications can be made by those skilled in the art without departing from the spirit and scope of the present application. It should be understood that in the process of practicing the present application, various alternatives to the embodiments of the present application described herein can be employed. The appended claims are intended to cover and encompass such alternatives and equivalents.

Claims

1. A foreign matter detection method for a gas-insulated switchgear, characterized by, The method comprises: S1, three-dimensionally reconstructing the surface of an object to be detected inside a gas insulated switchgear to obtain a three-dimensional temperature cloud image of the surface of the object to be detected, wherein the temperature level in the three-dimensional temperature cloud image is distinguished by the RGB value of an image; S2, inputting the three-dimensional temperature cloud image into a trained neural network model to detect foreign matter on the surface of the object to be detected, wherein the trained neural network model performs the following operations: S21, identifying an abnormal point in the three-dimensional temperature cloud image according to the RGB value of the three-dimensional temperature cloud image; S22, regarding the abnormal point as foreign matter on the surface of the object to be detected and determining the type, quantity, size and position of the foreign matter.

2. The foreign matter detection method according to claim 1, characterized by, Identifying an abnormal point in the three-dimensional temperature cloud image according to the RGB value of the three-dimensional temperature cloud image comprises: When a point with a brightness value greater than a preset threshold is detected in the three-dimensional temperature cloud image, the point is regarded as an abnormal point in the three-dimensional temperature cloud image.

3. The foreign body detection method for a gas-insulated switchgear according to claim 1, characterized by, Before three-dimensionally reconstructing the surface of an object to be detected inside a gas insulated switchgear to obtain a three-dimensional temperature cloud image of the surface of the object to be detected, the method further comprises: heating the surface of the object to be detected inside the gas insulated switchgear.

4. A foreign object detection device for a gas-insulated switchgear, characterized in that The method comprises: a thermal excitation module for heating the surface of an object to be detected inside a gas insulated switchgear; an infrared imaging module for three-dimensionally reconstructing the surface of the heated object to be detected inside the gas insulated switchgear, generating a three-dimensional temperature cloud image and inputting the three-dimensional temperature cloud image into an analysis module; the analysis module is configured to perform steps S21-S22 described in claim 1, wherein the thermal excitation module and the infrared imaging module are both fixedly arranged on a mechanical arm.

5. The foreign object detection apparatus of claim 4, wherein The training process of the trained neural network model comprises: pre-placing foreign matter of a set type, size, spacing and quantity at corresponding positions on the surface of the object to be detected; generating an image training set by changing the type, size, spacing, quantity and position of the foreign matter multiple times; inputting the image training set into a neural network model to train the neural network model to obtain the trained neural network model.

6. The foreign object detection apparatus of claim 4, wherein The thermal excitation module is a laser, a pulse resistance heater or a microwave heater.

7. The foreign object detection apparatus of claim 4, wherein The infrared imaging module is a camera array comprising a plurality of infrared cameras, each of which has infrared thermal imaging and visible light imaging functions.

8. The foreign object detection apparatus of claim 4, wherein The mechanical arm is a multi-degree-of-freedom mechanical arm.

9. A computer-readable storage medium, characterized in that, The program instructions, when executed by a processor, cause the implementation of the method according to claim 1 or 2.

10. An electronic device, comprising: The method comprises: a processor; and a memory storing computer instructions, which, when executed by the processor, cause the electronic device to perform the method according to claim 1 or 2.

Images