A method and system for detecting defects on the inner surface of a heat exchanger tube bore
By controlling the movement of the endoscope with a pusher and using a convolutional neural network algorithm to identify defects on the inner surface of the heat exchanger tube holes, the problem of resource waste and identification errors caused by manual operation is solved, and efficient and accurate automated detection is achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- HARBIN TURBINE
- Filing Date
- 2026-03-12
- Publication Date
- 2026-05-29
AI Technical Summary
In existing technologies, the detection of defects on the inner surface of heat exchanger tube holes requires manual operation and relies on human experience, resulting in a waste of human resources and identification errors.
The endoscope is controlled by a pusher to extend and retract within the pipe. Combined with a defect recognition algorithm based on a convolutional neural network model, the endoscope automatically acquires and identifies images of the inner surface of the pipe hole and generates a defect report.
It enables intelligent detection without human intervention, improving the accuracy and efficiency of detection and avoiding waste of human resources and subjective bias.
Smart Images
Figure CN122109138A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of defect identification technology, and in particular to a method and system for detecting defects on the inner surface of heat exchanger tube holes. Background Technology
[0002] A heat exchanger is an energy-saving device that facilitates heat transfer between two or more fluids at different temperatures. It transfers heat from a higher-temperature fluid to a lower-temperature fluid, bringing the fluid temperature to the specified parameters to meet process requirements. It is also one of the key devices for improving energy efficiency. Heat exchangers play an important role in chemical, petroleum, power, food, and many other industrial production processes, serving as heaters, coolers, condensers, evaporators, and reboilers, and are widely used.
[0003] Inspecting the inner surface of heat exchanger tubes is crucial for ensuring safe operation and extending equipment lifespan. However, due to the narrowness of the tube openings, current technology often requires three operators working together: one to insert an endoscope into the tube to photograph the inner surface, and the other two to interpret the images and identify defects. This method not only wastes manpower but also suffers from subjective interpretation, leading to potential defects inaccuracies.
[0004] Therefore, how to avoid wasting human resources and achieve more accurate detection of defects on the inner surface of heat exchanger tube holes is a problem that urgently needs to be solved by those skilled in the art. Summary of the Invention
[0005] The purpose of this invention is to solve the problems of the current technology, which requires manual operation to control the extension and retraction of the endoscope and the waste of human resources due to the reliance on human experience for defect identification. Therefore, this invention provides a method and system for detecting defects on the inner surface of heat exchanger tube holes, so as to free up manpower and realize intelligent detection of defects on the inner surface of heat exchanger tube holes.
[0006] To address the aforementioned technical problems, this invention provides a method for detecting defects on the inner surface of heat exchanger tube holes, comprising:
[0007] Acquire images of the inner surface of the tube holes of the heat exchanger under test;
[0008] The defect identification algorithm is invoked to identify defects in the inner surface image of the pipe hole; the defect identification algorithm is an algorithm built based on historical detection data through a convolutional neural network model.
[0009] Preferably, the method for acquiring the image of the inner surface of the tube hole includes:
[0010] Send the cable output command to the pusher and obtain the cable output length;
[0011] When the cable length reaches the preset length, a shooting command is sent to the endoscope, and a cable retraction command is sent to the pusher, so as to acquire an image of the inner surface of the tube hole along the cable retraction path.
[0012] Preferably, after sending the take-up command to the pusher, the method further includes:
[0013] Obtain the take-up length and determine whether the take-up length is the same as the output length;
[0014] If so, a stop command is sent to the endoscope and the pusher.
[0015] Preferably, before the step of defect identification of the inner surface image of the pipe hole, the method further includes: denoising, correcting and enhancing the inner surface image of the pipe hole.
[0016] Preferably, after the step of defect identification of the inner surface image of the tube hole, the method further includes:
[0017] A defect report is generated based on the defect identification results; the defect report includes the defect location, defect type, and severity.
[0018] To address the aforementioned technical problems, the present invention also provides a heat exchanger tube bore inner surface inspection system, comprising:
[0019] Memory, used to store computer programs;
[0020] A processor is used to execute the computer program to implement the steps of the heat exchanger tube bore inner surface detection method as described above.
[0021] Preferably, the detection system further includes: a pusher, an endoscope, and a position detector;
[0022] The endoscope is fixed to the protruding end of the rigid cable of the pusher and is used to photograph the inner surface of the tube hole of the heat exchanger under test.
[0023] The position detector is located at the outlet of the pusher and is used to detect the length of the cable.
[0024] The signal transmission terminals of the position detector, the pusher, and the endoscope are all connected to the processor.
[0025] Preferably, the pusher further includes:
[0026] PLC controller, stepper motor, lead screw drive mechanism, guide rail system and winding reel;
[0027] The signal terminals of the PLC controller and the stepper motor are both connected to the processor. The output terminal of the PLC controller is connected to the input terminal of the stepper motor. The stepper motor controls the extension and retraction of the rigid cable on the reel through a lead screw transmission mechanism to drive the endoscope to move.
[0028] Preferably, the endoscope includes: a video camera, a lighting device, and a heat-resistant protective cover;
[0029] The lighting equipment is positioned around the video camera, and the heat-resistant protective cover surrounds the video camera and the lighting equipment.
[0030] Preferably, the detection system further includes a touch screen; the touch screen is connected to the processor and is used to display captured images and defect identification results.
[0031] This invention provides a method and system for inspecting the inner surface of heat exchanger tubes. Compared to current technologies that require manual operation to control the extension and retraction of the endoscope and rely on human experience for defect identification, resulting in wasted human resources, this invention controls the movement of the endoscope within the pipe using a pusher. The endoscope is initiated to capture images and then retracted when it has penetrated a certain depth into the pipe, ensuring the completeness and comprehensiveness of the image capture. After acquiring the images, a preset algorithm is used to identify defects. This eliminates the need for manual intervention, enabling the capturing and identification of the inner surface of the heat exchanger tubes, avoiding wasted human resources. Furthermore, algorithmic defect identification avoids the subjective bias present in manual review, improving accuracy. Attached Figure Description
[0032] To more clearly illustrate the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0033] Figure 1 This is a flowchart of a method for detecting defects on the inner surface of heat exchanger tube holes, provided as an embodiment of the present invention. Detailed Implementation
[0034] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the protection scope of the present invention.
[0035] The core of this invention is to provide a method and system for detecting defects on the inner surface of heat exchanger tube holes, so as to free up manpower and realize intelligent detection of defects on the inner surface of heat exchanger tube holes.
[0036] To enable those skilled in the art to better understand the present invention, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.
[0037] Figure 1 A flowchart of a method for detecting defects on the inner surface of heat exchanger tube holes provided in an embodiment of the present invention is shown below. Figure 1 As shown, the method includes:
[0038] S10: Acquire an image of the inner surface of the tube holes of the heat exchanger under test;
[0039] S11: Call the defect identification algorithm to identify defects in the inner surface image of the pipe hole; the defect identification algorithm is an algorithm built based on historical detection data through a convolutional neural network model.
[0040] The method for detecting defects on the inner surface of heat exchanger tube holes provided in this application is mainly used to automate the detection of defects on the inner wall surface of narrow tubes in tubular heat exchangers during the inspection and acceptance stages of heat exchanger production and the maintenance stages of later use. The purpose of this application is to achieve an intelligent detection method, reduce the waste of human resources, and improve detection efficiency. In specific implementations, the executing entity of this method can be a heat exchanger tube hole inner surface defect detection device. This device may specifically include a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the steps of the heat exchanger tube hole inner surface defect detection method provided in the embodiments of this application. In some embodiments, the heat exchanger tube hole inner surface defect detection device may also include a display, touch screen, or other human-computer interaction device. In specific implementations, the heat exchanger tube hole inner surface defect detection device provided in this embodiment may include, but is not limited to, smartphones, tablets, laptops, or desktop computers.
[0041] Of course, it is understood that if the methods in the embodiments of this application are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, all or part of the technical solutions of this application can be embodied in the form of a software product, which is stored in a storage medium and executes all or part of the steps of the methods described in the various embodiments of this application.
[0042] This application relies on an endoscope for inspecting the inner surface of pipe orifices. The endoscope is inserted into the pipe orifice to take pictures, and defects are identified by recognizing the captured images. To reduce manpower, this application uses a pusher to control the extension and retraction of the endoscope within the pipe orifice. Specifically, the processor sends a cable extension command to the pusher, which extends the cable. The endoscope at the extended end of the cable extends into the pipe orifice along with the cable. Simultaneously, the processor obtains the cable extension length to avoid excessive cable bending inside the pipe and wasted resources. Then, imaging is initiated. When the cable extension length reaches a preset length, the processor sends an imaging command to the endoscope to initiate imaging, and sends a retraction command to the pusher to retract the cable, allowing the endoscope to capture a complete picture of the inside of the pipe. The preset length is the length of the area to be inspected, typically the length of the pipe. In this application, the endoscope is first inserted into the pipe, and then imaging is performed during the cable retraction process. This avoids the possibility of the endoscope or cable scratching the pipe during the retraction phase, preventing the capture of images if imaging is performed during the insertion phase. Similarly, when performing the reel-in action, it is also necessary to obtain the reel-in length and determine whether the reel-in length is the same as the output length; if so, a stop command is sent to the endoscope and the pusher. By promptly closing the endoscope and the pusher, damage to the motor in the pusher is avoided, and the waste of computing resources caused by capturing additional images is prevented.
[0043] Finally, the processor can perform defect identification on the captured images using a preset algorithm. This algorithm can be trained based on historical detection data, and the defect identification results can include information such as the location and length of the defect.
[0044] As can be seen, the inspection of the inner surface of the pipe hole in this application does not require manual intervention. The insertion of the endoscope, the taking of pictures, and the analysis of the pictures do not require the participation of technical personnel. In actual production, for the inspection of multiple heat exchangers or multiple pipes, the endoscope can be moved to the corresponding pipe opening by means of a robotic arm, robot, or manual labor, thereby achieving overall inspection through this application.
[0045] The heat exchanger tube bore inner surface inspection method provided in this application addresses the shortcomings of current technologies, which require manual operation to control the extension and retraction of the endoscope and rely on human experience for defect identification, leading to wasted human resources. This method controls the movement of the endoscope within the pipe using a pusher / puller. The endoscope is initiated to capture images and then retracted when it has penetrated a certain depth into the pipe, ensuring the completeness and comprehensiveness of the image capture. After acquiring the images, a preset algorithm is used to identify defects. This eliminates the need for manual intervention, enabling the capturing and identification of the heat exchanger tube inner surface, avoiding wasted human resources. Furthermore, algorithmic defect identification avoids the subjective bias inherent in manual review, improving accuracy.
[0046] The above embodiments disclose defect identification of images using a preset algorithm. In specific implementations, to achieve more accurate defect identification, the images captured by the endoscope need to be preprocessed after acquisition to improve image quality, eliminate interference, and highlight effective information. This embodiment provides a specific method for defect identification of images using a preset algorithm, including: denoising, correcting, and enhancing the image; and calling a defect identification algorithm to identify defects in the processed image. The defect identification algorithm is an algorithm built based on historical detection data using a convolutional neural network model. In this embodiment, the historical detection data refers to relevant data for identifying internal surface defects, which may include parameters such as defect type, features, depth, and shape. Defect identification is achieved by training a convolutional neural network model.
[0047] After the defect identification step of the processed image, a defect report can be generated based on the defect identification results. The defect report includes the defect location, defect type, and severity. It is understood that the defect location can be determined by the cable length and the position of the captured image, and the defect type and severity can be determined by a preset algorithm. This embodiment generates a detailed report to facilitate technicians in inferring and handling the causes of defects.
[0048] The above embodiments provide a detailed description of the heat exchanger tube hole inner surface detection method provided in this application. This embodiment also provides an application component for implementing this method. The heat exchanger tube hole inner surface detection system provided in this application includes a memory for storing a computer program and a processor for executing the computer program to implement the steps of the heat exchanger tube hole inner surface detection method as described above.
[0049] The heat exchanger tube bore inner surface inspection system provided in this embodiment can include, but is not limited to, smartphones, tablets, laptops, or desktop computers.
[0050] The processor may include one or more processing cores, such as a quad-core processor or an octa-core processor. The processor may be implemented using at least one hardware form of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), or Programmable Logic Array (PLA). The processor may also include a main processor and coprocessors. The main processor, also known as the Central Processing Unit (CPU), is used to process data in the wake-up state; the coprocessors are low-power processors used to process data in the standby state. In some embodiments, the processor may integrate a Graphics Processing Unit (GPU), which is responsible for rendering and drawing the content to be displayed on the screen. In some embodiments, the processor may also include an Artificial Intelligence (AI) processor, which handles computational operations related to machine learning.
[0051] The memory may include one or more computer-readable storage media, which may be non-transitory. The memory may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices or flash memory devices. In this embodiment, the memory is used to store at least the following computer program, which, after being loaded and executed by a processor, is capable of implementing the relevant steps of the heat exchanger tube bore inner surface detection method disclosed in any of the foregoing embodiments. Furthermore, the resources stored in the memory may also include an operating system and data, and the storage method may be temporary or permanent storage.
[0052] In some embodiments, the heat exchanger tube bore inner surface inspection system may further include a display screen, input / output interface, communication interface, power supply, and communication bus.
[0053] Based on the above embodiments, in this embodiment, the heat exchanger tube hole inner surface inspection system further includes: a pusher, an endoscope, and a position detector;
[0054] The endoscope is fixed to the protruding end of the rigid cable of the pusher; the position detector is set at the outlet of the pusher to detect the length of the cable; the signal transmission ends of the position detector, the pusher, and the endoscope are all connected to the processor.
[0055] In this embodiment, the pusher acts as an actuator, controlling the extension and retraction of the rigid cable under the control of the processor, thereby moving the endoscope at the cable's protruding end within the tube. It is understood that, in order to achieve the cable-driven endoscope movement, the cable in this application should be a rigid cable; in other embodiments, a telescopic rod or other components may also be used.
[0056] In practical implementation, the pusher pulls out or retracts the wire evenly at a preset speed according to the processor signal. The position detector is set at the wire outlet, which can be a position sensor. By detecting the wire length, the position of the endoscope inside the pipe can be determined. The heat exchanger tube bore inner surface inspection system can also include a touch screen; the touch screen is connected to the processor and is used to display captured images and defect identification results.
[0057] Based on the above embodiments, this embodiment provides a specific pusher structure, including: a PLC controller, a stepper motor, a lead screw transmission mechanism, a guide rail system, and a cable reel. The signal terminals of both the PLC controller and the stepper motor are connected to the processor. The output terminal of the PLC controller is connected to the input terminal of the stepper motor. The stepper motor controls the extension and retraction of the rigid cable on the cable reel through the lead screw transmission mechanism to drive the endoscope movement. In specific implementations, to ensure stable cable feeding, the pusher may also include a guide rail system. In practical applications, to adapt to more production environments, in addition to automatic cable extension and retraction via the processor and PLC controller, manual operation via the control panel is also possible. In this embodiment, the endoscope and cable are connected via a quick-release interface using Lemo00 series waterproof connectors. The processor and pusher are connected via a Modbus bus, and the processor and endoscope are connected via a USB cable. The cable reel in this embodiment is equipped with a slip ring device for smooth cable winding and unwinding. In this embodiment, the stepper motor can be a JD-Motor-2048 series stepper motor with a microstepping accuracy of 51,200 steps / revolution. It achieves dual closed-loop control through a photoelectric encoder and a pressure sensor.
[0058] This embodiment also provides a specific endoscope, including: a video camera, an illumination device, and a heat-resistant protective cover; the illumination device is disposed around the video camera, and the heat-resistant protective cover surrounds the video camera and the illumination device. The video camera can use a back-illuminated CMOS sensor with a resolution of 1920×1080 and a frame rate of 30fps, equipped with a nano-oleophobic coating to prevent stain adhesion. The illumination device is an 8-group adjustable brightness LED array (color temperature 5000K±200K), supporting a pulse strobe mode. The heat-resistant protective cover is made of a soft material to avoid scratching the pipes. In addition, the endoscope can also be used with a centering device, through which the endoscope is fixed.
[0059] The heat exchanger tube bore inner surface inspection system provided in this application addresses the shortcomings of current technologies, which require manual operation to control the extension and retraction of the endoscope and rely on human experience for defect identification, resulting in wasted human resources. This system controls the movement of the endoscope within the pipe using a pusher / puller. The system initiates imaging and retracts the endoscope once it has penetrated a certain depth into the pipe, ensuring the completeness and comprehensiveness of the image capture. After acquiring the images, a preset algorithm is used to identify defects. This eliminates the need for manual intervention, enabling the imaging and identification of the heat exchanger tube inner surface, avoiding wasted human resources. Furthermore, algorithmic defect identification avoids the subjective bias inherent in manual review, improving accuracy.
[0060] The method and system for detecting defects on the inner surface of heat exchanger tube holes provided by this invention have been described in detail above. The various embodiments in the specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. It should be noted that those skilled in the art can make various improvements and modifications to this invention without departing from its principles, and these improvements and modifications also fall within the protection scope of the claims of this invention.
Claims
1. A method for detecting defects on the inner surface of heat exchanger tube holes, characterized in that, include: Acquire images of the inner surface of the tube holes of the heat exchanger under test; The defect identification algorithm is invoked to identify defects in the inner surface image of the pipe hole; The defect identification algorithm is an algorithm built based on historical detection data using a convolutional neural network model.
2. The method for detecting the inner surface of heat exchanger tube holes according to claim 1, characterized in that, The method for acquiring the image of the inner surface of the pipe hole includes: Send the cable output command to the pusher and obtain the cable output length; When the cable length reaches the preset length, a shooting command is sent to the endoscope, and a cable retraction command is sent to the pusher, so as to acquire an image of the inner surface of the tube hole along the cable retraction path.
3. The method for detecting the inner surface of heat exchanger tube holes according to claim 2, characterized in that, After the step of sending a take-up command to the pusher, the method further includes: Obtain the take-up length and determine whether the take-up length is the same as the output length; If so, a stop command is sent to the endoscope and the pusher.
4. The method for detecting the inner surface of heat exchanger tube holes according to claim 1, characterized in that, Before the step of defect identification of the inner surface image of the pipe hole, the method further includes: denoising, correcting and enhancing the inner surface image of the pipe hole.
5. The method for detecting the inner surface of heat exchanger tube holes according to claim 3, characterized in that, After the step of identifying defects in the image of the inner surface of the pipe hole, the method further includes: A defect report is generated based on the defect identification results; the defect report includes the defect location, defect type, and severity.
6. A system for inspecting the inner surface of heat exchanger tube holes, characterized in that, include: Memory, used to store computer programs; A processor, configured to execute the computer program to implement the steps of the heat exchanger tube bore inner surface inspection method as described in any one of claims 1 to 5.
7. The heat exchanger tube bore inner surface inspection system according to claim 6, characterized in that, The detection system also includes: a pusher, an endoscope, and a position detector; The endoscope is fixed to the protruding end of the rigid cable of the pusher and is used to photograph the inner surface of the tube hole of the heat exchanger under test. The position detector is located at the outlet of the pusher and is used to detect the length of the cable. The signal transmission terminals of the position detector, the pusher, and the endoscope are all connected to the processor.
8. The heat exchanger tube bore inner surface inspection system according to claim 7, characterized in that, The pusher also includes: PLC controller, stepper motor, lead screw drive mechanism, guide rail system and winding reel; The signal terminals of the PLC controller and the stepper motor are both connected to the processor. The output terminal of the PLC controller is connected to the input terminal of the stepper motor. The stepper motor controls the extension and retraction of the rigid cable on the reel through a lead screw transmission mechanism to drive the endoscope to move.
9. The heat exchanger tube bore inner surface inspection system according to claim 7, characterized in that, The endoscope includes: a video camera, a lighting device, and a heat-resistant protective cover; The lighting equipment is positioned around the video camera, and the heat-resistant protective cover surrounds the video camera and the lighting equipment.
10. The heat exchanger tube bore inner surface inspection system according to claim 7, characterized in that, The detection system also includes a touch screen; the touch screen is connected to the processor and is used to display captured images and defect identification results.