Intelligent inspection method and device for power plant

Abstract

The invention belongs to the technical field of intelligent inspection, and discloses an intelligent inspection method and device for a power plant. The method comprises the following steps: generating an inspection path based on an inspection target of a power plant, wherein the inspection target is cooling equipment in the power plant; controlling an inspection robot to move according to the inspection path so as to inspect the cooling equipment of the power plant; acquiring an original image of the cooling equipment acquired by the inspection robot, and processing the original image; carrying out image region-of-interest extraction on the processed image; and the cooling equipment is detected based on the extracted region of interest of the image, and the water leakage condition of the cooling equipment is inspected by using the inspection robot in the manner, so that the inspection efficiency can be ensured, the leakage detection condition can be effectively avoided, and the inspection accuracy is also improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent inspection technology, and in particular to an intelligent inspection method and device for a power plant. Background Art

[0002] As the demand for electricity continues to grow, power equipment continues to increase. In order to ensure the stable operation of these equipment, regular inspections are required. During the inspection process, condensation water in cooling equipment and water leakage problems often occur. These problems not only damage the on-site environment, but also may bring safety hazards to power equipment, thereby affecting the stable operation of the entire power system.

[0003] Currently, power inspections are mainly carried out manually. However, manual inspections are not only inefficient, but also result in untimely inspections and missed inspections due to the inspectors' own faults.

[0004] The above contents are only used to assist in understanding the technical solution of the present invention and do not constitute an admission that the above contents are prior art. Summary of the invention

[0005] The main purpose of the present invention is to provide an intelligent inspection method and device for a power plant, aiming to solve the technical problem that the manual inspection method not only has low inspection efficiency, but also has the problem of untimely inspection and missed inspection due to the inspection personnel themselves.

[0006] To achieve the above object, the present invention provides a power plant intelligent inspection method, the power plant intelligent inspection method comprising the following steps:

[0007] Generate an inspection path based on an inspection target of the power plant, where the inspection target is cooling equipment in the power plant;

[0008] Controlling the inspection robot to move along the inspection path to inspect the cooling equipment of the power plant;

[0009] Acquire an original image of the cooling device collected by the inspection robot, and process the original image;

[0010] Extracting the region of interest from the processed image;

[0011] The cooling device is detected based on the extracted image region of interest.

[0012] In some embodiments, the generating of the inspection path based on the inspection target of the power plant includes:

[0013] Determining an initial position of the inspection robot and a target position of the inspection object;

[0014] Starting the search from the initial position and the target position simultaneously, storing the initial path points corresponding to the initial position into a first list, and storing the target path points corresponding to the target position into a second list;

[0015] During the bidirectional search, path points less than a preset evaluation value are stored in the first list or the second list, and when the initial path point exists in the second list and the target path point exists in the first list, the bidirectional search is stopped;

[0016] A patrol path is generated based on the initial path point, the target path point, and other path points stored in the first list and the second list.

[0017] In some embodiments, the calculation formula of the evaluation value f(n) corresponding to the path point in the bidirectional search process is f(n)=g(n)+ah(n), where n is the current path point searched, g(n) is the actual cost required to reach the current path point from the initial path point, h(n) is the estimated cost from the current path point to the target path point, a is a dynamic parameter, and the calculation formula of the estimated cost h(n) is

[0018]

[0019] Wherein, M is the number of path points in the search area, L(n) is the path corresponding to the current path point and the initial path point or the target path point, and θ is the angle corresponding to the search direction.

[0020] In some embodiments, the processing of the original image includes:

[0021] Obtain component values ​​corresponding to the red component, the blue component, and the green component of the pixel point in the original image;

[0022] A weighted calculation is performed based on the weight coefficients corresponding to the red component, the blue component, and the green component and the component values ​​to obtain a processed image. The weighted calculation formula is:

[0023] I(i,j)=ω R R(i,j)+ω G G(i,j)+ω B B(i,j)

[0024] Among them, I(i,j) is the processed image, ω R ,ω G And ω Bare the weight coefficients corresponding to the red component, the blue component and the green component respectively, and R(i,j), G(i,j) and B(i,j) are the component values ​​corresponding to the red component, the blue component and the green component respectively.

[0025] In some embodiments, extracting the image region of interest from the processed image includes:

[0026] Get the gray value of each pixel in the processed image;

[0027] Determine the grayscale value mean and grayscale value variance according to the grayscale value of each pixel;

[0028] The image segmentation threshold is calculated according to the gray value mean and the gray value variance. The calculation formula of the image segmentation threshold is:

[0029]

[0030] Among them, I T is the image segmentation threshold, is the mean gray value, a is the gray value variance;

[0031] The area formed by the pixel points whose pixel values ​​are greater than the image segmentation threshold is taken as the image region of interest.

[0032] In some embodiments, the detecting the cooling device based on the extracted image region of interest includes:

[0033] identifying a contour of the cooling device based on the extracted image region of interest;

[0034] Obtain polar coordinates corresponding to the contour of the cooling device;

[0035] The water mark area of ​​the cooling device is calculated according to the preset coordinates corresponding to the polar coordinates and the contour points of the cooling device without water marks. The water mark area calculation formula is:

[0036]

[0037] Where s is the water mark area, V ROI Represents the polar coordinates corresponding to the contour of the cooling device, x, y, z are respectively the abscissa, ordinate and oblique coordinates corresponding to the polar coordinates corresponding to the contour of the cooling device, x0, y0, z0 are respectively the preset abscissa, preset ordinate and preset oblique coordinates corresponding to the contour point of the cooling device without water marks;

[0038] The cooling device is detected based on the water trace area.

[0039] In some embodiments, the detecting the cooling device based on the water trace area includes:

[0040] If the water mark area is 0, it is determined that the cooling device has no water marks and no water leakage;

[0041] If the water mark area is a non-zero positive number, it is determined that the cooling device has water marks and water leakage exists.

[0042] In addition, to achieve the above-mentioned purpose, the present invention also proposes an intelligent inspection device for a power plant, the intelligent inspection device for a power plant comprising:

[0043] A generation module, used to generate an inspection path based on an inspection target of the power plant, wherein the inspection target is a cooling device in the power plant;

[0044] A control module, used to control the inspection robot to move along the inspection path to inspect the cooling equipment of the power plant;

[0045] A processing module, used to obtain the original image of the cooling device collected by the inspection robot and process the original image;

[0046] An extraction module, used for extracting the region of interest of the processed image;

[0047] A detection module is used to detect the cooling device based on the extracted image region of interest.

[0048] In some embodiments, the generating module is used to determine the initial position of the inspection robot and the target position of the inspection target;

[0049] Starting the search from the initial position and the target position simultaneously, and storing the initial path points corresponding to the initial position into a first list, and storing the target path points corresponding to the target position into a second list;

[0050] During the bidirectional search, path points less than a preset evaluation value are stored in the first list or the second list, and when the initial path point exists in the second list and the target path point exists in the first list, the bidirectional search is stopped;

[0051] A patrol path is generated based on the initial path point, the target path point, and other path points stored in the first list and the second list.

[0052] In some embodiments, the calculation formula of the evaluation value f(n) corresponding to the path point in the bidirectional search process is f(n)=g(n)+ah(n), where n is the current path point searched, g(n) is the actual cost required to reach the current path point from the initial path point, h(n) is the estimated cost from the current path point to the target path point, a is a dynamic parameter, and the calculation formula of the estimated cost h(n) is

[0053]

[0054] Wherein, M is the number of path points in the search area, L(n) is the path corresponding to the current path point and the initial path point or the target path point, and θ is the angle corresponding to the search direction.

[0055] In the present invention, an inspection path is generated based on the inspection target of the power plant, and the inspection target is the cooling equipment in the power plant; the inspection robot is controlled to move along the inspection path to inspect the cooling equipment of the power plant; the original image of the cooling equipment collected by the inspection robot is obtained, and the original image is processed; the image region of interest is extracted from the processed image; and the cooling equipment is detected based on the extracted image region of interest. Through the above method, the inspection robot is used to inspect the water leakage of the cooling equipment, which can not only ensure the efficiency of the inspection, but also effectively avoid the existing missed inspections and improve the accuracy of the inspection. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 It is a flow chart of the first embodiment of the intelligent inspection method for power plants of the present invention;

[0057] Figure 2 This is a structural block diagram of the first embodiment of the power plant intelligent inspection device of the present invention.

[0058] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0059] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0060] The embodiment of the present invention provides a power plant intelligent inspection method, referring to Figure 1 , Figure 1 The figure is a flow chart of a first embodiment of a power plant intelligent inspection method according to the present invention.

[0061] In this embodiment, the power plant intelligent inspection method includes the following steps:

[0062] Step S10: Generate an inspection path based on an inspection target of the power plant, where the inspection target is cooling equipment in the power plant.

[0063] In this embodiment, the executor of this embodiment is the intelligent inspection equipment of the power plant, wherein the intelligent inspection equipment of the power plant has functions such as data processing, data communication and program running. The intelligent inspection equipment of the power plant can be a computer terminal device or other network device, and of course it can also be other devices with similar functions, and this embodiment does not limit this.

[0064] It should be noted that currently, power inspections are mainly carried out manually. However, the manual inspection method not only has low inspection efficiency, but also may result in untimely inspections and missed inspections due to the inspectors' own reasons.

[0065] In order to solve the above technical problems, in this embodiment, an inspection path is generated based on the inspection target of the power plant, and the inspection target is the cooling equipment in the power plant; the inspection robot is controlled to move along the inspection path to inspect the cooling equipment of the power plant; the original image of the cooling equipment collected by the inspection robot is obtained, and the original image is processed; the image region of interest is extracted from the processed image; the cooling equipment is detected based on the extracted image region of interest. Through the above method, the inspection robot is used to inspect the water leakage of the cooling equipment, which can not only ensure the efficiency of the inspection, but also effectively avoid the existing missed inspections and improve the accuracy of the inspection. Specifically, it can be achieved as follows.

[0066] In the specific implementation, in this embodiment, the intelligent inspection of the distribution room is realized by a patrol robot. Before controlling the patrol robot to perform the inspection work, it is necessary to generate a patrol path. The specific process of generating the patrol path is to determine the initial position of the patrol robot and the target position of the inspection target; start searching from the initial position and the target position at the same time, and store the initial path point corresponding to the initial position in the first list, and store the target path point corresponding to the target position in the second list; in the process of two-way search, store the path points less than the preset evaluation value in the first list or the second list, and stop the two-way search when the initial path point exists in the second list and the target path point exists in the first list; generate a patrol path based on the initial path point, the target path point and other path points stored in the first list and the second list.

[0067] It should be noted that, during the two-way search, if a path point with a value less than the preset evaluation value appears, it is directly stored in the first list or the second list. For example, when the search starts from the initial path point, assuming that a path point A with a value less than the preset evaluation value is found, path point A is stored in the first list. And assuming that the search starts from the target path point, assuming that a path point B with a value less than the preset evaluation value is found, path point B is stored in the first list. Through continuous two-way search, they will eventually meet, that is, the initial path point is in the second list, and the target path point is in the first list.

[0068] Furthermore, in this embodiment, an evaluation value is calculated for any searched path point, and the evaluation value f(n)=g(n)+ah(n), wherein n is the current path point searched, g(n) is the actual cost required to reach the current path point from the initial path point, h(n) is the estimated cost from the current path point to the target path point, and a is a dynamic parameter, which can be determined by g(n) and the initial position and the target position, as shown in the following formula:

[0069]

[0070] Among them, (x1, y1) is the initial position and (x2, y2) is the target position.

[0071] The calculation formula for the estimated cost h(n) is:

[0072]

[0073] Among them, M is the number of path points in the search area, L(n) is the path corresponding to the current path point and the initial path point or the target path point, θ is the angle corresponding to the search direction, which can be the angle between the search direction and the horizontal direction, and M is all path points including the current path point. Taking the first list as an example, M is the number of all path points stored in the first list including the current path point.

[0074] Step S20: Control the inspection robot to move along the inspection path to inspect the cooling equipment of the power plant.

[0075] After the inspection path is generated, the inspection robot is controlled to move along the inspection path, and after the inspection robot moves to the cooling device along the inspection path, the cooling device is photographed by a camera arranged on the inspection robot to obtain an image of the cooling device.

[0076] Step S30: acquiring the original image of the cooling device collected by the inspection robot, and processing the original image.

[0077] In order to improve the accuracy of subsequent detection, the collected original image needs to be processed in this embodiment. The processing process is specifically to obtain the component values ​​corresponding to the red component, blue component and green component of the pixel point in the original image; perform weighted calculation based on the weight coefficients corresponding to the red component, the blue component and the green component and the component values ​​to obtain the processed image, wherein the weighted calculation formula is:

[0078] I(i,j)=ω R R(i,j)+ω G G(i,j)+ω B B(i,j)

[0079] I(i,j) is the processed image, ω R ,ω G And ω B are weight coefficients corresponding to the red component, the blue component and the green component, respectively, and R(i,j), G(i,j) and B(i,j) are component values ​​corresponding to the red component, the blue component and the green component, respectively. After the original image is processed as above, the processed image obtained is also a grayscale image.

[0080] Step S40: extracting the image region of interest from the processed image.

[0081] In a specific implementation, in this embodiment, the grayscale value of each pixel in the processed image is obtained; the grayscale value mean and the grayscale value variance are determined according to the grayscale value of each pixel, and the image segmentation threshold is calculated according to the grayscale value mean and the grayscale value variance. The calculation formula of the image segmentation threshold is:

[0082]

[0083] Among them, I T is the image segmentation threshold, is the mean gray value, a is the gray value variance;

[0084] Finally, based on the image segmentation threshold calculated above, the area formed by the pixel points whose pixel values ​​are greater than the image segmentation threshold is taken as the image region of interest.

[0085] It should be noted that the image segmentation threshold can divide the processed image into two parts, one of which is the pixels with grayscale values ​​higher than the threshold, which are judged to belong to the cooling equipment; the other part is the pixels with grayscale values ​​lower than the threshold, which are judged to belong to the background or other non-equipment parts, which can be expressed as:

[0086]

[0087] Among them, G represents the cooling equipment image segmentation result; 1 represents the image background area; 0 represents the image area of ​​interest.

[0088] Step S50: detecting the cooling device based on the extracted image region of interest.

[0089] It should be noted that in the image region of interest, there is a significant difference between the contour of the image region of interest of a normal cooling device and the contour of the device image containing water marks. The contour of the image region of interest is extracted and compared with the contour of the normal image to obtain the water mark area of ​​the cooling device. Specifically, the contour of the cooling device is identified based on the extracted image region of interest; the polar coordinates corresponding to the contour of the cooling device are obtained; the water mark area of ​​the cooling device is calculated based on the preset coordinates corresponding to the polar coordinates and the contour points of the cooling device without water marks. The water mark area calculation formula is:

[0090]

[0091] Where s is the water mark area, V ROI Represents the polar coordinates corresponding to the contour of the cooling device, x, y, z are the horizontal coordinate, vertical coordinate and oblique coordinate corresponding to the polar coordinates of the contour of the cooling device, x0, y0, z0 are the preset horizontal coordinate, preset vertical coordinate and preset oblique coordinate corresponding to the contour point of the water-free cooling device.

[0092] In this embodiment, the above V ROI The expression is

[0093] Among them, x, y, z represent the horizontal coordinate, vertical coordinate and oblique coordinate of the contour polar coordinate respectively; a and b represent the fitting coefficients; α represents the angle between the line connecting any point to the origin of the coordinate system and the horizontal axis.

[0094] After calculating the water mark area, if the value of the water mark area s is 0, it means that the outline of the cooling equipment in the inspection robot detection sample completely overlaps with the outline of the cooling equipment under normal conditions, the current equipment has no water marks, and there is no water leakage; if the value of the water mark area s is a non-zero positive number, it means that there is a difference between the outline of the cooling equipment in the inspection robot detection sample and the outline of the cooling equipment under normal conditions, and they cannot overlap, and there are water marks on the current equipment.

[0095] In this embodiment, an inspection path is generated based on the inspection target of the power plant, and the inspection target is the cooling equipment in the power plant; the inspection robot is controlled to move along the inspection path to inspect the cooling equipment of the power plant; the original image of the cooling equipment collected by the inspection robot is obtained, and the original image is processed; the image region of interest is extracted from the processed image; and the cooling equipment is detected based on the extracted image region of interest. In the above manner, the inspection robot is used to inspect the water leakage of the cooling equipment, which can not only ensure the efficiency of the inspection, but also effectively avoid the existing missed inspections and improve the accuracy of the inspection.

[0096] Reference Figure 2 , Figure 2 This is a structural block diagram of the first embodiment of the power plant intelligent inspection device of the present invention.

[0097] like Figure 2 As shown, the power plant intelligent inspection device proposed in the embodiment of the present invention includes:

[0098] A generation module 10, for generating an inspection path based on an inspection target of the power plant, wherein the inspection target is a cooling device in the power plant;

[0099] A control module 20, used to control the inspection robot to move along the inspection path to inspect the cooling equipment of the power plant;

[0100] The processing module 30 is used to obtain the original image of the cooling device collected by the inspection robot and process the original image;

[0101] An extraction module 40 is used to extract an image region of interest from the processed image;

[0102] The detection module 50 is used to detect the cooling device based on the extracted image region of interest.

[0103] In this embodiment, an inspection path is generated based on the inspection target of the power plant, where the inspection target is the cooling equipment in the power plant; the inspection robot is controlled to move along the inspection path to inspect the cooling equipment of the power plant; the original image of the cooling equipment collected by the inspection robot is obtained, and the original image is processed; the image region of interest is extracted from the processed image; and the cooling equipment is detected based on the extracted image region of interest. In the above manner, the inspection robot is used to inspect the water leakage of the cooling equipment, which can not only ensure the efficiency of the inspection, but also effectively avoid the existing missed inspections and improve the accuracy of the inspection.

[0104] In some embodiments, the generating module 10 is used to determine the initial position of the inspection robot and the target position of the inspection target;

[0105] Starting the search from the initial position and the target position simultaneously, and storing the initial path points corresponding to the initial position into a first list, and storing the target path points corresponding to the target position into a second list;

[0106] During the bidirectional search, path points less than a preset evaluation value are stored in the first list or the second list, and when the initial path point exists in the second list and the target path point exists in the first list, the bidirectional search is stopped;

[0107] A patrol path is generated based on the initial path point, the target path point, and other path points stored in the first list and the second list.

[0108] In some embodiments, the calculation formula of the evaluation value f(n) corresponding to the path point in the bidirectional search process is f(n)=g(n)+ah(n), where n is the current path point searched, g(n) is the actual cost required to reach the current path point from the initial path point, h(n) is the estimated cost from the current path point to the target path point, a is a dynamic parameter, and the calculation formula of the estimated cost h(n) is

[0109]

[0110] Wherein, M is the number of path points in the search area, L(n) is the path corresponding to the current path point and the initial path point or the target path point, and θ is the angle corresponding to the search direction.

[0111] In some embodiments, the processing module 30 is used to obtain component values ​​corresponding to the red component, the blue component and the green component of the pixel point in the original image;

[0112] A weighted calculation is performed based on the weight coefficients corresponding to the red component, the blue component, and the green component and the component values ​​to obtain a processed image. The weighted calculation formula is:

[0113] I(i,j)=ω R R(i,j)+ω G G(i,j)+ω B B(i,j)

[0114] Among them, I(i,j) is the processed image, ω R ,ω G And ω Bare the weight coefficients corresponding to the red component, the blue component and the green component respectively, and R(i,j), G(i,j) and B(i,j) are the component values ​​corresponding to the red component, the blue component and the green component respectively.

[0115] In some embodiments, the extraction module 40 is used to obtain the gray value of each pixel in the processed image;

[0116] Determine the grayscale value mean and grayscale value variance according to the grayscale value of each pixel;

[0117] The image segmentation threshold is calculated according to the gray value mean and the gray value variance. The calculation formula of the image segmentation threshold is:

[0118]

[0119] Among them, I T is the image segmentation threshold, is the mean gray value, a is the gray value variance;

[0120] The area formed by the pixel points whose pixel values ​​are greater than the image segmentation threshold is taken as the image region of interest.

[0121] In some embodiments, the detection module 50 is used to identify the contour of the cooling device based on the extracted image region of interest;

[0122] Obtain polar coordinates corresponding to the contour of the cooling device;

[0123] The water mark area of ​​the cooling device is calculated according to the preset coordinates corresponding to the polar coordinates and the contour points of the cooling device without water marks. The water mark area calculation formula is:

[0124]

[0125] Where s is the water mark area, V ROI Represents the polar coordinates corresponding to the contour of the cooling device, x, y, z are respectively the abscissa, ordinate and oblique coordinates corresponding to the polar coordinates corresponding to the contour of the cooling device, x0, y0, z0 are respectively the preset abscissa, preset ordinate and preset oblique coordinates corresponding to the contour point of the cooling device without water marks;

[0126] The cooling device is detected based on the water trace area.

[0127] In some embodiments, the detection module 50 is used to determine that the cooling device has no water marks and no water leakage if the water mark area is 0;

[0128] If the water mark area is a non-zero positive number, it is determined that the cooling device has water marks and water leakage exists.

[0129] An embodiment of the present application also provides an intelligent inspection device for a power plant, including a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus, and the memory is used to store the intelligent inspection program for the power plant; the processor is used to implement the above-mentioned intelligent inspection method for the power plant when executing the program stored in the memory.

[0130] The communication bus mentioned in the above-mentioned power plant intelligent inspection equipment can be a peripheral component interconnect standard (English: Peripheral Component Interconnect, referred to as: PCI) bus or an extended industry standard architecture (English: Extended Industry Standard Architecture, referred to as: EISA) bus, etc. The communication bus can be divided into an address bus, a data bus, a control bus, etc.

[0131] The communication interface is used for communication between the above-mentioned power plant intelligent inspection equipment and other equipment.

[0132] The memory may include a random access memory (RAM) or a non-volatile memory (NVM), such as at least one disk memory. Optionally, the memory may also be at least one storage device located away from the aforementioned processor.

[0133] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, and discrete hardware components.

[0134] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from a website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrated. The available medium may be a magnetic medium, (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive Solid State Disk (SSD)), etc.

[0135] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0136] Each embodiment in this specification is described in a related manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0137] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

[0138] It should be understood that the above is only an example and does not constitute any limitation on the technical solution of the present invention. In specific applications, technicians in this field can make settings as needed, and the present invention does not limit this.

[0139] It should be noted that the workflow described above is merely illustrative and does not limit the scope of protection of the present invention. In practical applications, technicians in this field can select part or all of them according to actual needs to achieve the purpose of the present embodiment, and no limitation is made here.

[0140] In addition, for technical details not fully described in this embodiment, reference can be made to the intelligent inspection method for a power plant provided in any embodiment of the present invention, and will not be repeated here.

[0141] In addition, it should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.

[0142] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0143] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as a read-only memory (ROM) / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0144] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

[0145] It is understandable that the system provided by the embodiment of the present invention corresponds to the method provided by the embodiment of the present invention, and the explanation, examples and beneficial effects of the relevant contents can refer to the corresponding parts in the above method.

Claims

1. A power plant intelligent inspection method, characterized in that: The power plant intelligent inspection method comprises: Generate an inspection path based on an inspection target of the power plant, where the inspection target is cooling equipment in the power plant; Controlling the inspection robot to move along the inspection path to inspect the cooling equipment of the power plant; Acquire an original image of the cooling device collected by the inspection robot, and process the original image; Extracting the region of interest from the processed image; The cooling device is detected based on the extracted image region of interest.

2. The power plant intelligent inspection method according to claim 1, characterized in that: The generating of the inspection path based on the inspection target of the power plant includes: Determining an initial position of the inspection robot and a target position of the inspection object; Starting the search from the initial position and the target position simultaneously, storing the initial path points corresponding to the initial position into a first list, and storing the target path points corresponding to the target position into a second list; During the bidirectional search, path points less than a preset evaluation value are stored in the first list or the second list, and when the initial path point exists in the second list and the target path point exists in the first list, the bidirectional search is stopped; A patrol path is generated based on the initial path point, the target path point, and other path points stored in the first list and the second list.

3. The power plant intelligent inspection method according to claim 2, characterized in that: The calculation formula of the evaluation value f(n) corresponding to the path point in the bidirectional search process is f(n)=g(n)+ah(n), where n is the current path point searched, g(n) is the actual cost required to reach the current path point from the initial path point, h(n) is the estimated cost from the current path point to the target path point, a is a dynamic parameter, and the calculation formula of the estimated cost h(n) is Wherein, M is the number of path points in the search area, L(n) is the path corresponding to the current path point and the initial path point or the target path point, and θ is the angle corresponding to the search direction.

4. The power plant intelligent inspection method according to claim 1, characterized in that: The processing of the original image comprises: Obtain component values ​​corresponding to the red component, the blue component, and the green component of the pixel point in the original image; A weighted calculation is performed based on the weight coefficients corresponding to the red component, the blue component, and the green component and the component values ​​to obtain a processed image. The weighted calculation formula is: I(i,j)=ω R R(i,j)+ω G G(i,j)+ω B B(i,j) Among them, I(i,j) is the processed image, ω R ,ω G And ω B are the weight coefficients corresponding to the red component, the blue component and the green component respectively, and R(i,j), G(i,j) and B(i,j) are the component values ​​corresponding to the red component, the blue component and the green component respectively.

5. The power plant intelligent inspection method according to claim 1, characterized in that: The step of extracting the image region of interest from the processed image comprises: Get the gray value of each pixel in the processed image; Determine the grayscale value mean and grayscale value variance according to the grayscale value of each pixel; The image segmentation threshold is calculated according to the gray value mean and the gray value variance. The calculation formula of the image segmentation threshold is: Among them, I T is the image segmentation threshold, is the mean gray value, a is the gray value variance; The area formed by the pixel points whose pixel values ​​are greater than the image segmentation threshold is taken as the image region of interest.

6. The power plant intelligent inspection method according to any one of claims 1 to 5, characterized in that: The detecting of the cooling device based on the extracted image region of interest comprises: identifying a contour of the cooling device based on the extracted image region of interest; Obtain polar coordinates corresponding to the contour of the cooling device; The water mark area of ​​the cooling device is calculated according to the preset coordinates corresponding to the polar coordinates and the contour points of the cooling device without water marks. The water mark area calculation formula is: Where s is the water mark area, V ROI Represents the polar coordinates corresponding to the contour of the cooling device, x, y, z are respectively the abscissa, ordinate and oblique coordinates corresponding to the polar coordinates corresponding to the contour of the cooling device, x0, y0, z0 are respectively the preset abscissa, preset ordinate and preset oblique coordinates corresponding to the contour point of the cooling device without water marks; The cooling device is detected based on the water trace area.

7. The power plant intelligent inspection method according to claim 6, characterized in that: The detecting the cooling device based on the water mark area includes: If the water mark area is 0, it is determined that the cooling device has no water marks and no water leakage; If the water mark area is a non-zero positive number, it is determined that the cooling device has water marks and water leakage exists.

8. An intelligent inspection device for a power plant, characterized in that: The power plant intelligent inspection device comprises: A generation module, used to generate an inspection path based on an inspection target of the power plant, wherein the inspection target is a cooling device in the power plant; A control module, used to control the inspection robot to move along the inspection path to inspect the cooling equipment of the power plant; A processing module, used to obtain the original image of the cooling device collected by the inspection robot and process the original image; An extraction module, used for extracting the region of interest of the processed image; A detection module is used to detect the cooling device based on the extracted image region of interest.

9. The intelligent inspection device for a power plant according to claim 8, characterized in that: The generating module is used to determine the initial position of the inspection robot and the target position of the inspection object; Starting the search from the initial position and the target position simultaneously, storing the initial path points corresponding to the initial position into a first list, and storing the target path points corresponding to the target position into a second list; During the bidirectional search, path points less than a preset evaluation value are stored in the first list or the second list, and when the initial path point exists in the second list and the target path point exists in the first list, the bidirectional search is stopped; A patrol path is generated based on the initial path point, the target path point, and other path points stored in the first list and the second list.

10. The intelligent inspection device for a power plant according to claim 9, characterized in that: The calculation formula of the evaluation value f(n) corresponding to the path point in the bidirectional search process is f(n)=g(n)+ah(n), where n is the current path point searched, g(n) is the actual cost required to reach the current path point from the initial path point, h(n) is the estimated cost from the current path point to the target path point, a is a dynamic parameter, and the calculation formula of the estimated cost h(n) is Wherein, M is the number of path points in the search area, L(n) is the path corresponding to the current path point and the initial path point or the target path point, and θ is the angle corresponding to the search direction.

Images