Engine heat insulation layer defect detection system and method

Abstract

The invention relates to the technical field of power transmission line fault positioning, in particular to an engine heat insulation layer defect detection system and method, and the method specifically comprises the following steps: S1, light source selection: selecting a proper light source to assist detection; a laser triangulation measurement technology and a visual detection technology are combined to obtain point cloud data of each surface, a scanning space measurement point cloud image is established, three-dimensional reconstruction of a detection target is realized through a point cloud image processing technology, and a high-resolution three-dimensional point cloud is utilized to realize three-dimensional reconstruction of the detection target. The height condition of a measured object and the calculation problem of the geometrical relationship of different surfaces can be analyzed, and the application problems of product quality detection, online measurement, part assembly and the like are solved in cooperation with a deep learning computer vision algorithm technology. A three-dimensional point cloud splicing technology and a point cloud piece defect mapping technology are utilized, key data such as defects, length and thickness are obtained through a data processing software structure algorithm, and a result is output in a data set display center in an image mode.

Description

Technical Field

[0001] The invention relates to the technical field of transmission line fault location, and relates to a system and method for detecting defects in an engine thermal insulation layer. Background Art

[0002] Surface defect detection mainly involves areas with uneven physical or chemical properties on the surface of an object. Common examples include scratches, spots and holes on the surface of metal or plastic products, color difference, dirt and damage on the surface of paper, indentations and protrusions on the surface of paper products, impurities, damage, stains and flatness on the surface of non-metallic products such as glass. The basic components of a visual inspection system mainly include image acquisition, image processing and analysis, data management and human-computer interaction. Some systems are divided into five parts: camera, light source, lens, image acquisition card and visual processing system.

[0003] In the prior art, the hardware part of the image acquisition module mainly includes lighting sources, cameras, lenses, image acquisition cards, etc., and the image processing and analysis, the software algorithm part mainly includes image preprocessing and detection processing. The preprocessing processes the image data to make the image features we need more obvious; the detection processing is to detect damage and size based on image features, data management and human-computer interaction, and the qualified and destination of the detected objects are processed accordingly according to actual needs. Summary of the invention

[0004] In view of the above-mentioned shortcomings of the prior art, the first object of the present invention is to provide an engine insulation layer defect detection system and method to solve the problems in the above-mentioned background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] An engine insulation layer defect detection system and method, comprising the following steps:

[0007] S1: Light source selection: Select a suitable light source to assist detection;

[0008] S2: Data collection: used to collect cracks, bulges, and folding defects of the insulation layer;

[0009] S3: Ultrasonic review: Use ultrasonic imaging detection technology to review and compare the scanned defect data.

[0010] Preferably, the illumination mode selected by the light source can be divided into dome light source, annular light source, parallel light source, coaxial light source, point light source, low-angle light source, line light source, grating, etc. Dome light source is mainly used for defect detection of spherical or curved objects, detection of uneven smooth surface characters, and surface detection of metal or mirror.

[0011] Preferably, after selecting a suitable light source in the light source selection, it is also necessary to select a corresponding illumination mode according to the actual situation. Different illumination modes can be divided into backlighting, frontlighting, structured light and stroboscopic illumination, etc. Backlighting is when the object to be measured is placed between the light source and the camera. Its advantage is that a high-contrast image can be obtained, and the image effect is a clear black and white outline of the object to be measured, which is often used for size measurement; front lighting is when the light source and the camera are located on the same side of the object to be measured.

[0012] Preferably, the data acquisition system is mainly used to detect cracks, bulges, and folding defects in the insulation layer. This method uses a combination of laser triangulation technology and visual inspection technology to obtain point cloud data for each surface, establish a point cloud image of the scanning space measurement point, and realize three-dimensional reconstruction of the detection target through point cloud image processing technology. Using high-resolution three-dimensional point clouds, the height of the object being measured and the calculation problem of the geometric relationship of different surfaces can be analyzed, and the deep learning computer vision algorithm technology independently developed can be used to solve application problems such as product quality inspection, online measurement, and parts assembly. Using three-dimensional point cloud splicing technology and point cloud defect mapping technology, through the data processing software structure algorithm, key data such as defects, length, thickness, etc. are obtained, and the central output results are displayed in the data set in the form of images.

[0013] Preferably, the ultrasonic review uses ultrasonic imaging detection technology to review and compare various defect data collected by the intelligent three-dimensional laser scanning visual data acquisition system. The review and comparison mainly includes data such as debonding area and debonding position, and the results are output by the data centralized display system.

[0014] The above technical scheme is adopted: in the ultrasonic review, a composite chip is used through a high-sensitivity air-coupled ultrasonic special probe with a frequency range of 30kHz to 5MHz. The composite chip with a connection structure can reduce the impedance of the sensor material, has higher efficiency and better coupling performance, and has a larger sound power output. Starting from the traditional piezoelectric ceramic ultrasonic transducer, a composite chip is selected, and a coupling layer is added and a porous composite material is selected to design the coupling layer. On the basis of considering the close-range sound field boundary distance x0 and the pointing angle γ when emitting ultrasonic waves into the air, an ultrasonic probe of various shapes suitable for using air as a coupling medium is produced. This sensor can be driven by a traditional ultrasonic transmitter and receiver. Compared with the traditional ultrasonic probe, the air-coupled ultrasonic probe has many advantages, such as the sound speed in the air is very slow compared with steel, the wavelength is short, and it is easy to produce a sharp focused sound beam.

[0015] A system for detecting defects in an engine thermal insulation layer, wherein the system is used to obtain point cloud data of each surface using three-dimensional visual detection technology, establish a point cloud image of a scanning space measurement point, and realize three-dimensional reconstruction of a detection target through point cloud image processing technology. By using high-resolution three-dimensional point clouds, the height of the object being measured and the calculation problem of the geometric relationship of different surfaces can be analyzed. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 This is a schematic diagram of the ultrasonic air coupling detection principle of the present invention;

[0017] Figure 2 This is a schematic diagram of the principle of the acoustic-photoelectric sensing air coupling detection imaging of the present invention.

[0018] Beneficial Effects

[0019] Compared with the known public technology, the technical solution provided by the present invention has the following beneficial effects:

[0020] The data acquisition system in the present invention is mainly used to detect cracks, bulges, and folding defects in the insulation layer. The system uses a combination of laser triangulation technology and visual detection technology to obtain point cloud data for each surface, establish a point cloud image of the scanning space measurement point, and realize three-dimensional reconstruction of the detection target through point cloud image processing technology. The high-resolution three-dimensional point cloud can be used to analyze the height of the object being measured and the calculation problem of the geometric relationship of different surfaces, and cooperate with deep learning computer vision algorithm technology to solve application problems such as product quality inspection, online measurement, and parts assembly. Using three-dimensional point cloud splicing technology and point cloud defect mapping technology, through the data processing software structure algorithm, key data such as defects, length, thickness, etc. are obtained, and the central output results are displayed in the data set in the form of images. DETAILED DESCRIPTION

[0021] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0022] Combine the following Figure 1-2 The present invention is further described with reference to the accompanying drawings and examples.

[0023] Example 1

[0024] An engine insulation layer defect detection system and method, comprising the following steps:

[0025] S1: Light source selection: Select a suitable light source to assist detection;

[0026] S2: Data collection: used to collect cracks, bulges and folding defects of the insulation layer.

[0027] S3: Ultrasonic review: Use ultrasonic imaging detection technology to review and compare the scanned defect data.

[0028] Among them, it is necessary to select the corresponding light source and reasonable lighting method in order to achieve the best application effect.

[0029] Light sources can be divided into visible light and invisible light. Commonly used visible light sources include LED lights, fluorescent lights, halogen lights (fiber optic light sources), and special light sources.

[0030] According to the different illumination methods, it can be divided into backlighting, forward lighting, structured light and stroboscopic lighting. Backlighting is to place the object to be measured between the light source and the camera. Its advantage is that it can obtain a high-contrast image with a black and white outline of the object to be measured. It is often used for size measurement. Forward lighting is that the light source and the camera are located on the same side of the object to be measured. This method is easy to install and is mainly used to detect important details, defects and scratches on the surface of the object. Structured light illumination is to project a grating or line light source onto the object to be measured, and demodulate the three-dimensional information of the object to be measured based on the distortion they produce. Stroboscopic lighting is to irradiate high-frequency light pulses onto the object, and the camera shooting is required to be synchronized with the light source.

[0031] According to the lighting method, it can be divided into dome light source, ring light source, parallel light source, coaxial light source, point light source, low-angle light source, line light source, grating, etc. Dome light source is mainly used for defect detection of spherical or curved objects, detection of uneven smooth surface characters, and surface detection of metal or mirror surfaces. Such as glass bottles, ball bearings, small workpiece surfaces, plastic or aluminum containers, etc. Ring light irradiation is mostly used for integrated circuit strips and pin characters, metal workpiece engraved characters, smooth surface scratches, bottle mouth size or cracks, and flat workpiece surface quality detection. Strip light source (controllable lighting, red, blue, green monochromatic light source) is also called strip light. It is a lighting source that illuminates from the side. The commonly used angle is 45 degrees, and there are also smaller angles. Side light can avoid the strong reflection caused by frontal illumination, and can also achieve high-brightness lighting on the edge. It is a very widely used lighting method in size measurement and appearance inspection. Commonly used for: LCD defect detection, packaging text detection, packaging film damage detection, paper quality detection, conventional printing quality detection, manufacturing crack detection, electronic component shape recognition and size measurement, various linear array detection, etc. Coaxial light irradiation, the image effect is a black feature on a bright background, used for the detection of flat objects with severe reflections, can enhance the surface features at different angles, enhance the surface texture (scratches, dents, embossing), and reduce shadows. Such as scratch and defect detection on smooth surfaces such as metal and glass, chip and silicon wafer damage detection, stamping character detection on metal parts, circuit board solder joints and symbols, integrated circuit pin character detection, etc.

[0032] Select the angle of the light source: select light sources with different incident angles according to the desired image effect. High-angle illumination makes the image brighter overall, which is suitable for objects with non-reflective surfaces; low-angle illumination makes the image background black and the features white, which can highlight the object being measured;

[0033] The hardware part of the acquisition module mainly includes lighting source, camera, lens, image acquisition card, etc. The software algorithm part of image processing and analysis mainly includes image preprocessing and detection processing. The preprocessing processes the image data to make the image features we need more obvious; the detection processing is to detect damage and size based on the image features. Data management and human-computer interaction are used to process the qualified and destination of the detected objects according to actual needs.

[0034] Light source selection

[0035] Light sources can be divided into visible light and invisible light. Commonly used visible light sources include LED lights, fluorescent lights, halogen lights, and special light sources.

[0036] According to the different illumination methods, it can be divided into backlighting, forward lighting, structured light and stroboscopic lighting. Backlighting is to place the object to be measured between the light source and the camera. Its advantage is that it can obtain a high-contrast image with a black and white outline of the object to be measured. It is often used for size measurement. Forward lighting is that the light source and the camera are located on the same side of the object to be measured. This method is easy to install and is mainly used to detect important details, defects and scratches on the surface of the object. Structured light illumination is to project a grating or line light source onto the object to be measured, and demodulate the three-dimensional information of the object to be measured based on the distortion they produce. Stroboscopic lighting is to irradiate high-frequency light pulses onto the object, and the camera shooting is required to be synchronized with the light source.

[0037] According to the lighting method, it can be divided into dome light source, ring light source, parallel light source, coaxial light source, point light source, low-angle light source, line light source, grating, etc. Dome light source is mainly used for defect detection of spherical or curved objects, detection of uneven smooth surface characters, and surface detection of metal or mirror surfaces. Such as glass bottles, ball bearings, small workpiece surfaces, plastic or aluminum containers, etc. Ring light irradiation is mostly used for integrated circuit strips and pin characters, metal workpiece engraved characters, smooth surface scratches, bottle mouth size or cracks, and flat workpiece surface quality detection. Strip light source (controllable lighting, red, blue, green monochromatic light source) is also called strip light. It is a lighting source that illuminates from the side. The commonly used angle is 45 degrees, and there are also smaller angles. Side light can avoid the strong reflection caused by frontal illumination, and at the same time, it can also achieve high-brightness lighting on the edge. It is a kind of lighting method that is widely used in dimension measurement and appearance inspection. It is often used for: LCD defect detection, packaging text detection, packaging film damage detection, paper quality detection, conventional printing quality detection, manufacturing crack detection, electronic component shape recognition and size measurement, various linear array detection, etc. Coaxial light irradiation, the image effect is black features on a bright background, which is used for the detection of flat objects with severe reflections. It can enhance the surface features with different angles, enhance the surface texture, and reduce shadows. Such as scratch and defect detection on smooth surfaces such as metal and glass, chip and silicon wafer damage detection, stamping character detection on metal parts, circuit board solder joints and symbols, integrated circuit pin character detection, etc. Select the angle of the light source: select light sources with different incident angles according to the desired image effect. High-angle irradiation, the overall image is brighter, suitable for objects with non-reflective surfaces; low-angle irradiation, the image background is black and the features are white, which can highlight the object being measured.

[0038] Among them, the data acquisition system is mainly used to detect cracks, bulges, and folding defects in the insulation layer. The system uses a combination of laser triangulation technology and visual inspection technology to obtain point cloud data for each surface, establish a point cloud image of the scanning space measurement point, and realize three-dimensional reconstruction of the detection target through point cloud image processing technology. Using high-resolution three-dimensional point clouds, the height of the object being measured and the calculation of the geometric relationship of different surfaces can be analyzed, and deep learning computer vision algorithm technology can be used to solve application problems such as product quality inspection, online measurement, and parts assembly. Using three-dimensional point cloud splicing technology and point cloud defect mapping technology, through the data processing software structure algorithm, key data such as defects, length, thickness, etc. are obtained, and the center output results are displayed in the data set in the form of images.

[0039] Among them, ultrasonic imaging detection technology is used to review and compare various defect data collected by the intelligent three-dimensional laser scanning visual data acquisition system, mainly reviewing and comparing data such as debonding area and debonding position. The results are displayed in the data set. The high-sensitivity air-coupled ultrasonic special probe uses a constructed composite chip with a frequency range of 30kHz to 5MHz. The composite chip with a connection structure can reduce the impedance of the sensor material, has higher efficiency and better coupling performance, and has a greater sound power output. Starting from the traditional piezoelectric ceramic ultrasonic transducer, a composite chip with a connection structure is selected. By adding a coupling layer and selecting a porous composite material to design the coupling layer, considering the close-range sound field limit distance q0 and the pointing angle γ when emitting ultrasonic waves into the air, ultrasonic probes of various shapes (frequency: 30kHz~5MHz) that are suitable for using air as a coupling medium are made, such as Figure 1-2 This sensor can be driven by a conventional ultrasonic transmitter and receiver. Compared with conventional ultrasonic probes, air-coupled ultrasonic probes have many advantages, such as the sound velocity in air is much slower than that in steel, the wavelength is short, and it is easy to make a sharp focused sound beam.

[0040] The invention discloses an engine insulation layer defect detection system, which is used to obtain point cloud data of each surface by using three-dimensional visual detection technology, establish point cloud images of scanning space measurement points, realize three-dimensional reconstruction of the detection target by point cloud image processing technology, and analyze the height of the object being measured and the calculation problem of the geometric relationship of different surfaces by using high-resolution three-dimensional point clouds. The system uses 3D visual inspection technology to obtain point cloud data of each surface, establishes point cloud images of scanning space measurement points, and realizes 3D reconstruction of the detection target through point cloud image processing technology. Using high-resolution 3D point clouds, the height of the object being measured and the calculation problems of the geometric relationship of different surfaces can be analyzed. With the self-developed deep learning computer algorithm technology, the engine shape data is fully inspected, including the thickness, length and shape defect data of the engine casing. This project uses a six-axis industrial robot to maximize the safety of workers. The robot continues to bring efficient production to customers with its excellent speed and accuracy. The motion trajectory of the robot joints is well-predicted in advance. The speed and position must be set in the software or teaching device. The selected coordinate system is used as the reference. The movement of each joint is automatically executed according to the motion trajectory, realizing fast movement and precise movement. The robot control is integrated with the equipment control. The mechanical arm is controlled by the equipment controller to execute, and it can stop immediately in case of emergency. The robot is installed next to the equipment, surrounded by guardrails and gratings to protect personnel safety.

[0041] 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. Such modifications or replacements will not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for detecting defects in an engine insulation layer, characterized in that: The following steps are involved: S1: Light source selection: Select a suitable light source to assist detection; S2: Data collection: used to collect cracks, bulges and folding defects of the insulation layer. S3: Ultrasonic review: Use ultrasonic imaging detection technology to review and compare the scanned defect data.

2. The method for detecting defects in an engine insulation layer according to claim 1, characterized in that: The lighting methods selected by the light source can be divided into one or more of dome light source, ring light source, parallel light source, coaxial light source, point light source, low-angle light source, line light source, and grating. The dome light source is used for defect detection of spherical or curved objects, detection of characters on uneven smooth surfaces, and surface detection of metals or mirrors.

3. The method for detecting defects in an engine insulation layer according to claim 1, characterized in that: After selecting a suitable light source, it is also necessary to select a corresponding illumination method according to actual conditions. Different illumination methods can be divided into backlighting, forward lighting, structured light and stroboscopic lighting. Backlighting is when the object to be measured is placed between the light source and the camera. Its advantage is that a high-contrast image can be obtained. The image effect is a clear black and white outline of the object to be measured, which is often used for size measurement. Forward lighting is when the light source and the camera are located on the same side of the object to be measured.

4. The method for detecting defects in an engine insulation layer according to claim 1, characterized in that: The data acquisition system is mainly used to detect cracks, bulges, and folding defects in the insulation layer. This method uses a combination of laser triangulation technology and visual inspection technology to obtain point cloud data for each surface, establish a point cloud image of the scanning space measurement points, and realize three-dimensional reconstruction of the detection target through point cloud image processing technology. Using high-resolution three-dimensional point clouds, the height of the object being measured and the calculation problems of different-surface geometric relationships can be analyzed. Using three-dimensional point cloud splicing technology and point cloud defect mapping technology, through the data processing software structure algorithm, key data of defects, length, and thickness are obtained, and the central output results are displayed in the data set in the form of images.

5. The method for detecting defects in an engine thermal insulation layer according to claim 1, characterized in that: The ultrasonic review utilizes ultrasonic imaging detection technology to review and compare various defect data collected by the intelligent three-dimensional laser scanning visual data acquisition system, mainly reviewing and comparing the debonding area and debonding position data, and the formed results are output by the data centralized display system.

6. The method for detecting defects in an engine thermal insulation layer according to claim 1, characterized in that: In the ultrasonic verification, a composite chip is used through a high-sensitivity air-coupled ultrasonic special probe with a frequency range of 30kHz to 5MHz. The composite chip with a connection structure can reduce the impedance of the sensor material. The composite chip is selected, and a coupling layer is added and a porous composite material is selected to design the coupling layer. On the basis of considering the close-range sound field limit distance x0 and the pointing angle γ when emitting ultrasonic waves into the air, ultrasonic probes of various shapes that are suitable for using air as a coupling medium are manufactured. This sensor can be driven by a traditional ultrasonic transmitter and receiver.

7. An engine insulation layer defect detection system, characterized in that: The engine insulation layer defect detection system is used to use three-dimensional visual detection technology to obtain point cloud data of each surface, establish a point cloud image of the scanning space measurement point, and realize three-dimensional reconstruction of the detection target through point cloud image processing technology. Using high-resolution three-dimensional point clouds, the height of the object being measured and the calculation problems of the geometric relationship of different surfaces can be analyzed.

Images