Steam turbine blade water erosion damage inspection method and system based on visual information

Abstract

The invention belongs to the technical field of nuclear power, and particularly relates to a steam turbine blade water erosion damage inspection method and system based on visual information. According to the steam turbine blade water erosion damage inspection method based on the visual information, detection and analysis of blade water erosion damage are achieved through image collection, modeling restoration, modeling comparative analysis and mechanical simulation, and compared with manual detection, higher efficiency and precision can be achieved. The macro camera is used for carrying out visual sampling on the blade surface damage, compared with a laser scanner, the scanning precision is higher, and mesoscopic damage analysis is more friendly. The mechanical arm is used for clamping the macro camera for shooting and sampling, high-precision stepping shooting is achieved through the preset route, the shooting precision is high, the picture quality is good, and reverse analysis modeling of software is facilitated.

Description

Technical Field

[0001] This invention belongs to the field of nuclear power technology, specifically relating to a method and system for inspecting water erosion damage of steam turbine blades based on visual information. Background Technology

[0002] Steam turbine blades operate in high-temperature, high-pressure, high-humidity, and high-speed environments, facing severe water erosion problems. To reduce safety hazards and prevent abnormal unit operation, the detection of water erosion damage to steam turbine blades is crucial. Traditional manual visual inspection is insufficient in accuracy and efficiency; contact measurement is complex, time-consuming, and prone to secondary deformation or damage. Currently, 3D modeling technology shows promise, effectively avoiding the above disadvantages and offering numerous methods. Traditionally used laser scanning or structured light scanning techniques are limited by factors such as scanner size and optimal working distance. On the one hand, laser scanners struggle to acquire surface information of complex blade shapes with mutual occlusion and are expensive; on the other hand, due to applicability limitations, the working distance of current laser scanners is generally above 200mm. Although the nominal accuracy can reach the 0.01mm level, it cannot actually achieve this nominal accuracy for identifying small water erosion pits and cracks, which is detrimental to the safety research of mesoscale surface water erosion damage. Summary of the Invention

[0003] To overcome the problems existing in related technologies, a method and system for inspecting water erosion damage of steam turbine blades based on visual information is provided.

[0004] According to one aspect of the present disclosure, a method for inspecting water erosion damage on turbine blades based on visual information is provided, the method comprising:

[0005] Obtain binocular visual data of the turbine blades, and reconstruct coarse point cloud information and spatial position information of the turbine blades based on the binocular visual data;

[0006] Based on the coarse point cloud information and spatial location information, the leaf shape is offset by an equidistant offset, with the offset amount being the preset optimal object distance of the macro camera, in order to generate the optimal shooting path feature line.

[0007] Based on the damaged area of ​​the turbine blade, the effective aperture parameters of the macro camera, and the blade shape parameters, the damaged area is divided into multiple shooting sub-areas;

[0008] Control the robotic arm equipped with the macro camera to move along the optimal shooting path feature line and a preset path, and stop to shoot at a designated location in the shooting sub-region during the movement, so as to collect a sequence of mesoscale blade surface images.

[0009] Based on the image sequence of the blade surface, mesoscale 3D modeling is performed to generate a high-precision 3D model of the turbine blade.

[0010] The high-precision three-dimensional model is compared with the original geometric information of the turbine blade to identify damage and calculate the amount of deformation and surface material loss.

[0011] Based on the damage, deformation, and material loss, mechanical analysis and fatigue life analysis are performed to generate a quantitative evaluation report and safety analysis conclusions for the turbine blades.

[0012] In one possible implementation, the width and height of the shooting sub-region are respectively half the effective width and height of the macro camera.

[0013] In one possible implementation, the size of the imaging sub-region can be adjusted according to the surface curvature radius of the blade and the size of the water erosion damage. When the surface curvature radius of the blade is small or the damage size is small, the imaging sub-region can be subdivided multiple times. The transition between sub-regions of different scales can be smoothly transitioned according to the curvature change.

[0014] In one possible implementation, the preset path is an S-shaped or zigzag-shaped path that travels back and forth along the edge of the shooting sub-region.

[0015] In one possible implementation, the robotic arm moves a distance equal to half the width or height of one of the shooting sub-regions each time.

[0016] In one possible implementation, the step of stopping and taking pictures at a designated location includes:

[0017] If the specified location point is located on the common boundary of two shooting sub-regions, then take a picture once from the left, center and right angles respectively at that location point;

[0018] If the specified location point is located on the outermost boundary of the damaged area, then take a photo at the center angle and a photo at the inner angle at that location point.

[0019] In one possible implementation, the mesoscale 3D modeling algorithm uses parameters measured by a binocular camera and a macro camera to perform 3D reconstruction of the part using inverse 3D reconstruction technology based on multi-view stereo vision.

[0020] According to another aspect of the present disclosure, a turbine blade water erosion damage inspection system based on visual information is provided, the system comprising: a binocular camera, a macro camera, a multi-axis robotic arm, and a control device;

[0021] The binocular camera is used to obtain coarse point cloud information and spatial position information of the turbine blades;

[0022] The robotic arm is used to hold and move the macro camera;

[0023] The control device is used to perform the above-described method.

[0024] According to another aspect of the present disclosure, a non-volatile computer-readable storage medium is provided, on which computer program instructions are stored, which, when executed by a processor, implement the above-described method.

[0025] The beneficial effects of this disclosure are as follows: The visual information-based turbine blade water erosion damage inspection method provided by this disclosure achieves the detection and analysis of blade water erosion damage through image acquisition, model restoration, model comparison analysis, and mechanical simulation, achieving higher efficiency and accuracy compared to manual inspection. Using a macro camera for visual sampling of blade surface damage offers higher scanning accuracy than laser scanners and is more suitable for mesoscopic damage analysis. A robotic arm holds the macro camera for sampling, achieving high-precision step-by-step imaging via a preset route, resulting in high-precision images and good image quality, which is beneficial for software reverse engineering and modeling. Utilizing a robotic arm to hold the macro camera enables low-cost, low-redundancy, high-efficiency, and rapid sampling and detection with mesoscopic accuracy. Attached Figure Description

[0026] Figure 1 This is a flowchart illustrating a method for inspecting water erosion damage of steam turbine blades based on visual information, according to an exemplary embodiment.

[0027] Figure 2 This is a schematic diagram illustrating the extraction of leaf shape features according to an exemplary embodiment.

[0028] Figure 3 This is a schematic diagram illustrating the conversion of shape features into a shooting trajectory according to an exemplary embodiment.

[0029] Figure 4 This is a schematic diagram illustrating a sub-region division and shooting method according to an exemplary embodiment.

[0030] Figure 5 This is a schematic diagram of a steam turbine blade water erosion damage inspection system based on visual information, according to an exemplary embodiment.

[0031] Figure 6 This is a reverse modeling effect diagram illustrated according to an exemplary embodiment.

[0032] Figure 7 This is an illustration of the extraction effect of surface water erosion damage pits according to an exemplary embodiment. Detailed Implementation

[0033] The present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0034] Figure 1 This is a flowchart illustrating a method for inspecting water erosion damage on turbine blades based on visual information, according to an exemplary embodiment. See also... Figure 1 The method includes: using a binocular camera to obtain coarse point cloud information and spatial location information of turbine blades at the millimeter level. For example... Figure 2 As shown, based on the obtained parameters such as blade shape, blade size, damage condition, and blade spatial position, the blade shape is extracted by equidistant offset, with the offset amount being the optimal object distance, resulting in the optimal shooting path feature line. Figure 3 The optimal object distance for the camera can be expressed as the specific distance between the front of the camera lens (the surface of the front lens element) and the object being photographed, at which the clearest image is obtained. Next, the damaged area of ​​the blade is divided into appropriate sub-regions based on parameters such as the effective image size of the macro camera and the shape of the blade. Figure 4 The size of a sub-region is generally 1 / 4 of the effective area, meaning its width and height are both 1 / 2 of the effective area's width and height. The robotic arm is positioned to move along the edge of the sub-region, following the shape of the aforementioned feature line, and its direction is an S-shape or a crisscross pattern between the air-facing and air-exit edges. Simultaneously, lateral spacing is considered to prevent collisions between the robotic arm / camera and objects during movement, while also taking into account the position and repeatability requirements of the macro camera. It is configured to move along the boundary by 1 / 2 the width and height of one sub-region at a time, then stop at the midpoint or apex of the corresponding sub-region to take a picture; for example... Figure 4 If the movement path is located at the common boundary of two sub-regions, then take a picture once at the midpoint or vertex from the left, center, and right angles; if the movement path is located at the boundary of the damaged area, that is, the outer edge of the outermost sub-region, then take a picture at the midpoint or vertex from the center angle and an inner angle, until the entire path and sub-region are photographed.

[0035] like Figure 5 A robotic arm is used to grip a macro camera and perform high-precision, low-redundancy sampling of mesoscopic surface structures according to the described work path. The sampled data is then imported into a computer, and a mesoscopic-scale 3D modeling algorithm is used to digitally reconstruct the turbine blades, generating a model as shown below. Figure 6 A three-dimensional model is then created. Finally, this model is imported into an evaluation system based on the comparison of visual and three-dimensional structural information, as well as a safety analysis system based on mechanical analysis, for analysis and calculation. The evaluation system based on the comparison of visual and three-dimensional structural information automatically compares the geometric information of the turbine blades after service with that of the turbine blades in their original, unserviced state. Figure 7Damage is identified, and its deformation and surface material loss are further obtained. Based on this, mechanical analysis and fatigue life analysis are performed, and finally a quantitative evaluation report of the turbine blade is generated, yielding safety analysis conclusions including operating parameters such as maximum allowable stress and safe operating range.

[0036] The visual information-based method for inspecting water erosion damage in turbine blades disclosed herein achieves detection and analysis of water erosion damage through image acquisition, model restoration, model comparison analysis, and mechanical simulation. Compared with manual inspection, it achieves higher efficiency and accuracy. A macro camera is used to visually sample damage on the blade surface, which offers higher scanning accuracy than a laser scanner and is more suitable for mesoscopic damage analysis. A robotic arm holds the macro camera for sampling, achieving high-precision step-by-step imaging via a preset route. This results in high-precision imaging, good image quality, and facilitates reverse engineering and modeling in software.

[0037] This disclosure can be a system, method, and / or computer program product. A computer program product may include a computer-readable storage medium having computer-readable program instructions loaded thereon for causing a processor to implement various aspects of this disclosure.

[0038] Computer-readable storage media can be tangible devices capable of holding and storing instructions for use by an instruction execution device. Computer-readable storage media can be, for example—but not limited to—electrical storage devices, magnetic storage devices, optical storage devices, electromagnetic storage devices, semiconductor storage devices, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of computer-readable storage media include: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static random access memory (SRAM), portable compact disc read-only memory (CD-ROM), digital multifunction disc (DVD), memory sticks, floppy disks, mechanical encoding devices, such as punch cards or recessed protrusions storing instructions thereon, and any suitable combination of the foregoing. The computer-readable storage media used herein are not to be construed as transient signals themselves, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (e.g., light pulses through fiber optic cables), or electrical signals transmitted through wires.

[0039] The computer-readable program instructions described herein can be downloaded from computer-readable storage media to various computing / processing devices, or downloaded via a network, such as the Internet, local area network, wide area network, and / or wireless network, to an external computer or external storage device. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards them to the computer-readable storage media in the respective computing / processing device.

[0040] Computer program instructions used to perform the operations of this disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, status setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk, C++, etc., and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The computer-readable program instructions may execute entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or may be connected to an external computer (e.g., via the Internet using an Internet service provider). In some embodiments, electronic circuitry, such as programmable logic circuitry, field-programmable gate arrays (FPGAs), or programmable logic arrays (PLAs), is personalized by utilizing the status information of the computer-readable program instructions to implement various aspects of this disclosure.

[0041] Various aspects of this disclosure are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this disclosure. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions.

[0042] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that, when executed by the processor of the computer or other programmable data processing apparatus, they create means for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and / or other device to operate in a particular manner; thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0043] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to perform the functions / actions specified in one or more boxes of a flowchart and / or block diagram.

[0044] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of an instruction containing one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions marked in the blocks may occur in a different order than those shown in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0045] The various embodiments of this disclosure have been described above. These descriptions are exemplary and not exhaustive, nor are they limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen to best explain the principles, practical application, or improvement of the technology in the market, or to enable others skilled in the art to understand the embodiments disclosed herein.

Claims

1. A method for inspecting water erosion damage on steam turbine blades based on visual information, characterized in that, The method includes: Obtain binocular visual data of the turbine blades, and reconstruct coarse point cloud information and spatial position information of the turbine blades based on the binocular visual data; Based on the coarse point cloud information and spatial location information, the leaf shape is offset by an equidistant offset, with the offset amount being the preset optimal object distance of the macro camera, in order to generate the optimal shooting path feature line. Based on the damaged area of ​​the turbine blade, the effective aperture parameters of the macro camera, and the blade shape parameters, the damaged area is divided into multiple shooting sub-areas; Control the robotic arm equipped with the macro camera to move along the optimal shooting path feature line and a preset path, and stop to shoot at a designated location in the shooting sub-region during the movement, so as to collect a sequence of mesoscale blade surface images. Based on the image sequence of the blade surface, mesoscale 3D modeling is performed to generate a high-precision 3D model of the turbine blade. The high-precision three-dimensional model is compared with the original geometric information of the turbine blade to identify damage and calculate the amount of deformation and surface material loss. Based on the damage, deformation, and material loss, mechanical analysis and fatigue life analysis are performed to generate a quantitative evaluation report and safety analysis conclusions for the turbine blades.

2. The method according to claim 1, characterized in that, The width and height of the shooting sub-region are respectively 1 / 2 of the effective width and height of the macro camera.

3. The method according to claim 1, characterized in that, The size of the imaging sub-region can be adjusted according to the surface curvature radius of the blade and the size of the water erosion damage. When the surface curvature radius of the blade is small or the damage size is small, the imaging sub-region can be subdivided multiple times. The transition between sub-regions of different scales can be smoothly transitioned according to the curvature change.

4. The method according to claim 1, characterized in that, The preset path is an S-shaped or zigzag-shaped path that travels back and forth along the edge of the shooting sub-area.

5. The method according to claim 1, characterized in that, The distance the robotic arm moves each time is half the width or height of one of the shooting sub-areas.

6. The method as described in claim 1, characterized in that, The step of stopping and taking photos at a designated location includes: If the specified location point is located on the common boundary of two shooting sub-regions, then take a picture once from the left, center and right angles respectively at that location point; If the specified location point is located on the outermost boundary of the damaged area, then take a photo at the center angle and a photo at the inner angle at that location point.

7. The method according to any one of claims 1 to 6, characterized in that, The mesoscale 3D modeling algorithm uses parameters measured by a binocular camera and a macro camera to perform 3D reconstruction of the parts using inverse 3D reconstruction technology based on multi-view stereo vision.

8. A visual information-based system for inspecting water erosion damage in steam turbine blades, characterized in that, The system includes: a binocular camera, a macro camera, a multi-axis robotic arm, and a control device; The binocular camera is used to obtain coarse point cloud information and spatial position information of the turbine blades; The robotic arm is used to hold and move the macro camera; The control device is used to perform the method as described in any one of claims 1 to 7.

9. A non-volatile computer-readable storage medium storing computer program instructions thereon, characterized in that, When the computer program instructions are executed by the processor, they implement the method described in any one of claims 1 to 7.

Images