Intelligent coating defect detection and repair system

Abstract

The present invention discloses an intelligent coating defect detection and repair system, and relates to the field of intelligent manufacturing technology. The present invention includes: an image acquisition and processing system, wherein the image acquisition system includes a plurality of laser scanners for acquiring surface images of products in real time, and a preprocessing module is equipped with a graphics processor for analyzing and processing image information acquired by the laser scanner; a defect recognition system, which is provided with a data processor and a decision module, and the data processor has a built-in coating defect recognition model, and the data processor is connected to the decision module; a repair system, wherein the repair system is connected to the decision module, and the repair system is composed of a group of programmable robotic arms, and each robotic arm is equipped with different repair tools. The present invention realizes the automation of the entire process from image acquisition, defect recognition to automatic repair, reduces the time and frequency of manual intervention, and can quickly discover and repair coating defects by real-time monitoring of product defects and immediate processing, avoiding product accumulation and production line stagnation.

Description

Technical Field

[0001] The present invention belongs to the field of intelligent manufacturing technology, and in particular relates to an intelligent coating defect detection and repair system. Background Art

[0002] Coating is a key surface treatment process in industrial manufacturing and is widely used in many industries such as automobiles, home appliances, furniture, and construction. Its main purpose is to protect products from environmental factors (such as corrosion, UV rays, etc.) and provide an aesthetic appearance. However, during the coating process, various defects such as bubbles, cracks, peeling, uneven color, etc. often occur due to multiple factors such as material properties, construction conditions, or equipment accuracy. These defects not only affect the appearance quality of the product, but may also reduce its service life and performance. Traditional coating defect detection methods usually rely on manual visual inspection, which has several obvious limitations:

[0003] Manual inspection is slow and cannot keep up with the demands of modern high-speed production lines. Different operators have different experiences and judgment criteria, which leads to unstable inspection results. It requires a lot of manpower and is very costly for complex or large-scale production. Long working hours can easily lead to fatigue, which increases the risk of missed or false inspections.

[0004] To this end, we provide an intelligent coating defect detection and repair system to solve the above problems. Summary of the invention

[0005] In order to solve the above technical problems, the present invention is achieved through the following technical solutions:

[0006] The present invention is an intelligent coating defect detection and repair system, comprising:

[0007] An image acquisition and processing system, wherein the image acquisition system comprises a plurality of laser scanners for acquiring surface images of products in real time, the laser scanners being installed at key positions of the production line, the laser scanners being connected to a preprocessing module via an industrial Ethernet interface, and the preprocessing module being equipped with a graphics processor for analyzing and processing image information acquired by the laser scanners;

[0008] The defect recognition system is provided with a data processor and a decision module, wherein the data processor is connected to the graphics processor via a network communication interface, and the data processor has a built-in coating defect recognition model, and the data processor is connected to the decision module;

[0009] The repair system is connected to the decision module and is composed of a group of programmable robotic arms, each of which is equipped with different repair tools.

[0010] The present invention is further configured such that the repair system is equipped with a material supply system, wherein the material supply system is composed of a plurality of independent storage tanks, wherein different types of coating materials are stored in the storage tanks, and the storage tanks are equipped with metering pumps and supply pipelines.

[0011] The present invention is further configured such that the material supply system is connected to a spray gun in a repair tool via a feed pipeline, and the flow of the material supply system is controlled by a decision module via a digital signal.

[0012] The present invention is further configured such that the robotic arm is equipped with a force feedback sensor, and the force feedback sensor is connected to the control system via a network communication interface.

[0013] The present invention is further configured such that the control system is equipped with a touch screen display and physical buttons, and the control system is connected to the image acquisition and processing system, the defect recognition system and the repair system via a network communication interface.

[0014] The present invention is further configured such that the operation logic of the coating defect recognition model is:

[0015] The pre-processed image is passed to the data processor, where the coating defect recognition model starts working. It first extracts features from the image and uses deep learning algorithms to automatically identify patterns and anomalies in the image.

[0016] After extracting features, the model will classify the defects and identify different types of coating defects, such as bubbles, cracks, peeling, uneven color, etc.

[0017] After the defects are identified and classified, the defect type and severity are sent to the decision module.

[0018] The present invention is further configured that the training method of the coating defect recognition model is:

[0019] Build a dataset that contains a large number of representative coating defect samples, covering all possible defect types, such as bubbles, cracks, peeling, uneven color, etc., and including images under different lighting conditions, angles, and backgrounds;

[0020] The dataset is augmented by applying various transformations to the original images (such as rotation, flipping, scaling, cropping, adjusting brightness contrast, etc.) to increase the robustness of the model to different situations, converting all input images to the same size, and normalizing them;

[0021] Select an appropriate neural network architecture based on the complexity of the problem and available resources, and start the training process using the selected dataset and model architecture;

[0022] After training, the model's performance is evaluated on an independent test set.

[0023] The present invention is further configured such that the training method of the coating defect recognition model also includes regularly collecting newly emerging defect cases to supplement the existing data set and retrain the model.

[0024] The present invention is further configured such that the image acquisition and processing system, the defect recognition system and the repair system form a closed-loop product inspection and repair process.

[0025] The intelligent coating defect detection and repair system is applied to product coating process detection and automatic repair.

[0026] The present invention has the following beneficial effects:

[0027] 1. The present invention realizes the automation of the whole process from image acquisition, defect recognition to automatic repair, reduces the time and frequency of manual intervention, and can quickly discover and repair coating defects by real-time monitoring of product defects and immediate processing, thus avoiding product accumulation and production line stagnation.

[0028] 2. The present invention utilizes laser scanners and deep learning algorithms, enabling the system to capture and analyze subtle defects on the product surface with high precision, ensuring that no problems are missed. The automated repair process ensures that the repair quality of each product is the same, eliminating the uncertainty caused by human factors.

[0029] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0031] Figure 1 It is a system block diagram of the present invention.

[0032] Figure 2 This is a logical diagram of the coating defect recognition model operation in the present invention.

[0033] Figure 3 This is a flow chart of the coating defect recognition model training in the present invention. DETAILED DESCRIPTION

[0034] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only 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.

[0035] Example

[0036] See also Figure 1-3 The present invention is an intelligent coating defect detection and repair system, comprising:

[0037] An image acquisition and processing system, wherein the image acquisition system comprises a plurality of laser scanners for acquiring surface images of products in real time, the laser scanners being installed at key positions of the production line, the laser scanners being connected to a preprocessing module via an industrial Ethernet interface, and the preprocessing module being equipped with a graphics processor for analyzing and processing image information acquired by the laser scanners;

[0038] The defect recognition system is provided with a data processor and a decision module, wherein the data processor is connected to the graphics processor via a network communication interface, and the data processor has a built-in coating defect recognition model, and the data processor is connected to the decision module;

[0039] The repair system is connected to the decision module and is composed of a group of programmable robotic arms, each of which is equipped with different repair tools.

[0040] Specifically, the repair system is equipped with a material supply system, which is composed of several independent storage tanks. Different types of coating materials are stored in the storage tanks, and the storage tanks are equipped with metering pumps and supply pipelines. The material supply system is connected to the spray gun in the repair tool through the supply pipeline, and the material supply system is controlled by a decision module through digital signals.

[0041] Furthermore, the robotic arm is equipped with a force feedback sensor, which is connected to a control system via a network communication interface. The control system is equipped with a touch screen display and physical buttons, and the control system is connected to an image acquisition and processing system, a defect recognition system, and a repair system via a network communication interface.

[0042] The operating logic of the coating defect recognition model is:

[0043] The pre-processed image is passed to the data processor, where the coating defect recognition model starts working. It first extracts features from the image and uses deep learning algorithms to automatically identify patterns and anomalies in the image.

[0044] After extracting features, the model will classify the defects and identify different types of coating defects, such as bubbles, cracks, peeling, uneven color, etc.

[0045] After the defects are identified and classified, the defect type and severity are sent to the decision module.

[0046] Among them, the training method of the coating defect recognition model is:

[0047] Build a dataset that contains a large number of representative coating defect samples, covering all possible defect types, such as bubbles, cracks, peeling, uneven color, etc., and including images under different lighting conditions, angles, and backgrounds;

[0048] The dataset is augmented by applying various transformations to the original images (such as rotation, flipping, scaling, cropping, adjusting brightness contrast, etc.) to increase the robustness of the model to different situations, converting all input images to the same size, and normalizing them;

[0049] Select an appropriate neural network architecture based on the complexity of the problem and available resources, and start the training process using the selected dataset and model architecture;

[0050] After training, evaluate the model’s performance on an independent test set.

[0051] New defect cases are regularly collected to supplement existing datasets and retrain models.

[0052] The image acquisition and processing system, defect recognition system and repair system constitute a closed-loop product inspection and repair process. The intelligent coating defect detection and repair system is applied to product coating process inspection and automatic repair.

[0053] The specific steps of using the intelligent coating defect detection and repair system are as follows:

[0054] Turn on the power of the image acquisition and processing system, defect recognition system, and repair system, ensure that all components are properly connected and network communication is normal (for example, industrial Ethernet interface), and initialize the control system, including the settings of the touch screen display and physical buttons.

[0055] Before starting production, the laser scanner is calibrated to ensure that it can accurately capture the surface details of the product, and the scanning parameters such as scanning speed and resolution are adjusted according to the size and shape of the product.

[0056] Check if there is enough coating material in the storage tank, add or replace material if necessary, and test the function of metering pumps and supply lines to ensure that they can respond to control signals and provide a stable material flow.

[0057] Load the latest coating defect recognition model into the data processor. If there are new defect types or improved algorithms, update the model to improve recognition accuracy.

[0058] The product moves along the production line and reaches the preset inspection position. The laser scanner acquires the surface image of the product in real time and sends the image to the preprocessing module via industrial Ethernet. The preprocessing module uses the graphics processor to perform preliminary analysis of the image, including denoising, contrast enhancement, etc., to optimize the image quality. The preprocessed image is passed to the data processor, where the coating defect recognition model starts working. The model automatically identifies and classifies defects (such as bubbles, cracks, peeling, uneven color, etc.) and sends the results to the decision module. The decision module determines the repair measures to be taken based on the received defect information and issues specific commands to the repair system, including the tools to be used, the materials to be applied, and the location of the repair.

[0059] The programmable robotic arm selects the appropriate tool according to the instructions and moves to the designated position for repair. The material supply system provides the required coating material to the spray gun or other repair tools through the feed pipeline. The decision module controls the flow. The force feedback sensor on the robotic arm monitors the pressure applied during the repair process to ensure that the product surface is not damaged. If abnormal force is detected, the control system will immediately adjust the movement of the robotic arm to prevent excessive repair.

[0060] After the repair is completed, the product needs to pass through the laser scanner again to confirm the repair effect. If the defect still exists or a new problem arises, the above repair steps are repeated and the repaired product continues to move along the production line, eventually completing the entire manufacturing process.

[0061] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0062] The preferred embodiments of the present invention disclosed above are only used to help illustrate the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to the specific implementation methods described. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. Intelligent coating defect detection and repair system, characterized by: include: An image acquisition and processing system, wherein the image acquisition system comprises a plurality of laser scanners for acquiring surface images of products in real time, the laser scanners being installed at key positions of the production line, the laser scanners being connected to a preprocessing module via an industrial Ethernet interface, and the preprocessing module being equipped with a graphics processor for analyzing and processing image information acquired by the laser scanners; The defect recognition system is provided with a data processor and a decision module, wherein the data processor is connected to the graphics processor via a network communication interface, and the data processor has a built-in coating defect recognition model, and the data processor is connected to the decision module; The repair system is connected to the decision module and is composed of a group of programmable robotic arms, each of which is equipped with different repair tools.

2. The intelligent coating defect detection and repair system according to claim 1 is characterized in that: The repair system is equipped with a material supply system, which is composed of a plurality of independent storage tanks. Different types of coating materials are stored in the storage tanks, and the storage tanks are equipped with metering pumps and supply pipelines.

3. The intelligent coating defect detection and repair system according to claim 2 is characterized in that: The material supply system is connected to the spray gun in the repair tool through a supply pipeline, and the flow of the material supply system is controlled by a decision module through a digital signal.

4. The intelligent coating defect detection and repair system according to claim 1 is characterized in that: The robotic arm is equipped with a force feedback sensor, and the force feedback sensor is connected to the control system via a network communication interface.

5. The intelligent coating defect detection and repair system according to claim 4 is characterized in that: The control system is equipped with a touch screen display and physical buttons, and the control system is connected to the image acquisition and processing system, the defect recognition system and the repair system via a network communication interface.

6. The intelligent coating defect detection and repair system according to claim 1 is characterized in that: The operating logic of the coating defect recognition model is: The pre-processed image is passed to the data processor, where the coating defect recognition model starts working. It first extracts features from the image and uses deep learning algorithms to automatically identify patterns and anomalies in the image. After extracting features, the model will classify the defects and identify different types of coating defects, such as bubbles, cracks, peeling, uneven color, etc. After the defects are identified and classified, the defect type and severity are sent to the decision module.

7. The intelligent coating defect detection and repair system according to claim 1 is characterized in that: The training method of the coating defect recognition model is: Build a dataset that contains a large number of representative coating defect samples, covering all possible defect types, such as bubbles, cracks, peeling, uneven color, etc., and including images under different lighting conditions, angles, and backgrounds; The dataset is augmented by applying various transformations to the original images (such as rotation, flipping, scaling, cropping, adjusting brightness contrast, etc.) to increase the robustness of the model to different situations, converting all input images to the same size, and normalizing them; Select an appropriate neural network architecture based on the complexity of the problem and available resources, and start the training process using the selected dataset and model architecture; After training, the model's performance is evaluated on an independent test set.

8. The intelligent coating defect detection and repair system according to claim 1 is characterized in that: The training method of the coating defect recognition model also includes regularly collecting newly emerging defect cases to supplement the existing data set and retrain the model.

9. The intelligent coating defect detection and repair system according to claim 1, characterized in that: The image acquisition and processing system, defect recognition system and repair system constitute a closed-loop product inspection and repair process.

10. The intelligent coating defect detection and repair system according to any one of claims 1 to 9 is applied to product coating process detection and automatic repair.

Images