Circuit breaker appearance quality CCD detection system

Abstract

The invention discloses a circuit breaker appearance quality CCD detection system, and belongs to the field of circuit breaker appearance detection, the circuit breaker appearance quality CCD detection system comprises a feeding conveying module, an image acquisition module, an image processing module, a defect analysis module, a classification discharging module and a central control module, the feeding conveying module is used for conveying a to-be-detected circuit breaker to a detection station; the device comprises a conveyor belt and a positioning device, appearance images of the circuit breaker can be comprehensively and clearly acquired through a plurality of CCD cameras with different angles and functions and a multispectral imaging technology, and the detection precision of fine defects can be effectively improved by combining an advanced image processing algorithm and a deep learning defect recognition model; the requirement of high-precision production is met, the central control module can automatically adjust detection parameters according to the model and specification of the circuit breaker, tedious manual setting is not needed, the detection system can adapt to detection of different types of circuit breakers, and the universality and flexibility of the system are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of circuit breaker appearance detection, and particularly to a CCD detection system for the appearance quality of circuit breakers. Background Art

[0002] In the power system, the circuit breaker is a key device to ensure the safe and stable operation of the power system. Its appearance quality not only affects the overall performance of the device, but also relates to the reliability and safety of the power system. At present, the appearance detection system based on CCD has been widely used in the production process of circuit breakers, but there are still many defects in the existing detection systems. For example, the traditional CCD detection system has insufficient detection accuracy for the fine scratches, stains on the surface of the circuit breaker and the complex structure parts, and it is difficult to meet the requirements of high-precision production; at the same time, when the existing system faces circuit breakers of different models and specifications, the adjustment of detection parameters is complex and the versatility is poor; moreover, the image acquisition speed is slow during the detection process, which affects the production efficiency and cannot achieve real-time and efficient online detection. In addition, some detection systems lack intelligent analysis and diagnosis functions, and cannot quickly and accurately judge and feedback the detection results, resulting in low efficiency of product quality control.

[0003] Therefore, a CCD detection system for the appearance quality of circuit breakers is needed to solve the problems of low detection accuracy, poor versatility, low detection efficiency and lack of intelligent analysis function in the existing technology. Summary of the Invention

[0004] Aiming at the deficiencies of the existing technology, the present invention provides a CCD detection system for the appearance quality of circuit breakers to solve the problems of low detection accuracy, poor versatility, low detection efficiency and lack of intelligent analysis function in the existing technology, and realize high-precision, high-efficiency and intelligent detection of the appearance quality of circuit breakers.

[0005] Technical Solution: To solve the above technical problems, according to one aspect of the present invention, more specifically, a CCD detection system for the appearance quality of circuit breakers includes a feeding and conveying module, an image acquisition module, an image processing module, a defect analysis module, a classification and discharging module and a central control module;

[0006] The feeding and conveying module: is used to convey the circuit breaker to be detected to the detection station, and it includes a conveyor belt and a positioning device. The conveyor belt is driven by a variable-frequency speed-regulating motor and can adjust the conveying speed according to the detection requirements; the positioning device is installed on both sides of the conveyor belt and can accurately position the circuit breaker through the cooperation of photoelectric sensors and mechanical clamps, ensuring that the circuit breaker is fixed in position during the detection process and facilitating image acquisition.

[0007] Image acquisition module: It is set above and on the side of the inspection station and contains multiple CCD cameras with different angles and functions. Among them, a high-resolution color CCD camera is set on the top to collect the overall image of the upper surface of the circuit breaker; two CCD cameras with inclined angles are arranged on the side to capture detailed images of the side of the circuit breaker. At the same time, it is also equipped with a multi-spectral CCD camera, which can collect images under different spectra to improve the recognition ability of surface defects (such as scratches, stains, oxide layers, etc.). In addition, the image acquisition module also includes an annular shadowless light source and a strip light source. The annular shadowless light source is installed around the top CCD camera to eliminate shadows during shooting. The strip light source is set on the side to enhance the contrast of the side image and make the defect features more obvious.

[0008] Image processing module: connected to the image acquisition module, receiving the collected image data. This module first pre-processes the image, including noise reduction, enhancement, grayscale and other operations to improve the image quality; then uses the image segmentation algorithm to separate the circuit breaker image from the background; then uses the edge detection algorithm to extract the outline and defect edge information of the circuit breaker; finally, through the feature extraction algorithm, various characteristic parameters of the circuit breaker appearance, such as size, shape, color, texture, etc.

[0009] Defect analysis module: It has a built-in defect recognition model based on deep learning. The model is trained through a large number of circuit breaker appearance defect images and can accurately identify various types of defects on the circuit breaker surface, such as scratches, pits, cracks, stains, blurred markings, etc. The defect analysis module inputs the feature parameters extracted by the image processing module into the defect recognition model. The model judges whether there are defects on the circuit breaker appearance based on the preset defect standards and thresholds, and determines the location, size and severity of the defects.

[0010] Classification and unloading module: According to the detection results of the defect analysis module, the circuit breakers are unloaded by classification. This module includes multiple unloading channels and sorting devices. The sorting device uses a combination of pneumatic push rods and mechanical arms. When qualified products are detected, the sorting device pushes them to the qualified product unloading channel; when unqualified products are detected, they are sorted to the corresponding unqualified product unloading channel according to the defect type for subsequent processing.

[0011] Central control module: As the core of the entire detection system, it is used to coordinate and control the operation of each module. The central control module receives the detection data from the image processing module and the defect analysis module, stores and statistically analyzes the detection results; at the same time, according to circuit breakers of different models and specifications, it automatically adjusts the shooting parameters of the image acquisition module (such as camera angle, focal length, exposure time, etc.), the algorithm parameters of the image processing module, and the defect judgment threshold of the defect analysis module, realizing the versatility and intelligence of the detection system. In addition, the central control module can also perform data interaction with the production management system through the network interface, and upload the detection results in real time, facilitating production managers to monitor and manage product quality.

[0012] The beneficial effects of a CCD detection system for the appearance quality of a circuit breaker according to the present invention are as follows:

[0013] (1) Through multiple CCD cameras with different angles and functions and multi-spectral imaging technology, the present invention can comprehensively and clearly collect the appearance images of the circuit breaker. Combining advanced image processing algorithms and deep learning defect recognition models, it can effectively improve the detection accuracy of subtle defects and meet the requirements of high-precision production.

[0014] (2) The central control module of the present invention can automatically adjust the detection parameters according to the model and specifications of the circuit breaker, without the need for cumbersome manual settings, enabling the detection system to adapt to the detection of different types of circuit breakers and improving the versatility and flexibility of the system;

[0015] The image acquisition module uses a high-speed CCD camera and an optimized light source design, combined with a fast image processing algorithm, to achieve fast image acquisition and processing, greatly improving the detection efficiency and meeting the requirements of on-line real-time detection of the production line.

[0016] (3) Through the defect recognition model based on deep learning, the present invention can automatically identify the type, location and severity of defects, and classify the circuit breakers according to the detection results, reducing the errors and labor intensity of manual detection and improving the intelligent level of product quality control. Description of the Drawings

[0017] The following further elaborates on the present invention in detail in conjunction with the drawings and specific implementation methods.

[0018] Figure 1 is the structural schematic diagram of the present invention;

[0019] Figure 2 is the structural schematic diagram of the feeding conveyor module and the image acquisition module of the present invention. Detailed Description of the Invention

[0020] The present invention will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments. It should be noted that, without conflict, the embodiments in the present application and the features in the embodiments can be combined with each other.

[0021] To make the technical solution of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0022] Refer to Figure 1 - Figure 2 , a CCD detection system for the appearance quality of a circuit breaker, including a feeding and conveying module, an image acquisition module, an image processing module, a defect analysis module, a sorting and discharging module, and a central control module. The feeding and conveying module is used to convey the circuit breaker to be detected to the detection station, and it includes a conveyor belt driven by a variable-frequency speed-regulating motor and positioning devices installed on both sides of the conveyor belt. The positioning devices cooperate with photoelectric sensors and mechanical clamps to position the circuit breaker.

[0023] The image acquisition module includes multiple CCD cameras with different angles and functions, which are arranged above and on the side of the detection station. Among them, a high-resolution color CCD camera is installed on the top, two CCD cameras with inclined angles are arranged on the side, and a multi-spectral CCD camera is also equipped. At the same time, it includes an annular shadowless light source installed around the top CCD camera and a strip light source arranged on the side.

[0024] The image processing module is connected to the image acquisition module and is used to perform preprocessing, segmentation, edge detection, and feature extraction operations on the collected image data.

[0025] The defect analysis module is built with a defect recognition model based on deep learning. This model is trained with a large number of appearance defect images of circuit breakers. The feature parameters extracted by the image processing module are input into this model to determine whether there are defects in the appearance of the circuit breaker, and to determine the position, size, and severity of the defects.

[0026] The sorting and discharging module sorts and discharges the circuit breakers according to the detection results of the defect analysis module, and includes multiple discharging channels and a sorting device that combines pneumatic push rods and robotic arms.

[0027] The central control module, as the core of the entire detection system, is used to coordinate and control the operation of each module, receive the detection data of the image processing module and the defect analysis module, store and statistically analyze the detection results, automatically adjust the shooting parameters of the image acquisition module, the algorithm parameters of the image processing module, and the defect judgment threshold of the defect analysis module according to different models and specifications of circuit breakers, and can also perform data interaction with the production management system through a network interface.

[0028] Workflow: S1. Place the circuit breaker to be detected on the conveyor belt. The variable-frequency speed-regulating motor drives the conveyor belt to run according to the preset detection speed. When the circuit breaker reaches the position of the positioning device, the photoelectric sensor detects the presence of the circuit breaker and triggers the mechanical fixture to act, accurately fixing the circuit breaker at the detection station to ensure its stable position during the subsequent image acquisition process.

[0029] S2. The high-resolution color CCD camera at the top takes pictures of the upper surface of the circuit breaker to collect the overall image; the two inclined-angle CCD cameras on the side take pictures of the side of the circuit breaker from different angles respectively to obtain the side detail information; the multi-spectral CCD camera simultaneously collects images under different spectra. The annular shadowless light source and the strip light source continuously emit light during the shooting process. The annular shadowless light source eliminates the shadow on the upper surface, and the strip light source enhances the contrast of the side image, enabling the captured images to clearly present the appearance features and defect information of the circuit breaker. The collected image data is transmitted to the image processing module in real time through the data line.

[0030] S3. After receiving the image data, the image processing module first uses the median filtering algorithm to perform noise reduction processing on the image to remove the noise interference in the image; then uses the histogram equalization algorithm to enhance the contrast of the image to make the image details clearer; then converts the color image into a grayscale image for subsequent processing. The threshold segmentation algorithm is used to separate the circuit breaker image from the background, and the Canny edge detection algorithm is used to extract the contour and defect edge information of the circuit breaker. Finally, through feature extraction algorithms such as the gray-level co-occurrence matrix, the characteristic parameters such as the size, shape, color, and texture of the appearance of the circuit breaker are obtained, and these characteristic parameters are sent to the defect analysis module.

[0031] S4. The defect analysis module receives the characteristic parameters transmitted by the image processing module and inputs them into the pre-trained defect recognition model based on deep learning. This model analyzes and processes the characteristic parameters through a convolutional neural network (CNN), compares them with the preset defect standards and thresholds, and judges whether there are defects in the appearance of the circuit breaker. If there are defects, the model can accurately determine the type, position, size, and severity of the defects and send the detection results to the central control module and the classification and blanking module.

[0032] S5. The classification and blanking module controls the action of the sorting device according to the detection results of the defect analysis module. For qualified products, the pneumatic push rod pushes them to the qualified product blanking channel; for unqualified products, the robotic arm sorts them to the corresponding unqualified product blanking channels according to the defect type, realizing the automatic classification and blanking of the circuit breaker.

[0033] S6. When the system starts up, the central control module automatically adjusts the shooting parameters of the image acquisition module (such as camera angle, focal length, exposure time, etc.), the algorithm parameters of the image processing module, and the defect judgment threshold of the defect analysis module according to the input circuit breaker model and specification information. During the detection process, it receives the detection data of the image processing module and the defect analysis module in real time, stores the data in the database, and conducts statistical analysis to generate a detection report. At the same time, it uploads the detection results to the production management system through the network interface so that production management personnel can timely understand the product quality status. When abnormal situations occur during the detection process (such as equipment failures, abnormal detection data, etc.), the central control module issues an alarm signal and takes corresponding fault handling measures to ensure the normal operation of the detection system.

[0034] The above-described embodiments merely represent several implementation manners of the present invention. The description is relatively specific and detailed, but it should not be construed as a limitation on the scope of the patent of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present invention, several modifications and improvements can still be made, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the appended claims.

Claims

1. A CCD detection system for the appearance quality of a circuit breaker, characterized in that: It includes a feeding and conveying module, an image acquisition module, an image processing module, a defect analysis module, a sorting and discharging module, and a central control module; The feeding and conveying module is used to convey the circuit breaker to be detected to the detection station. It includes a conveyor belt driven by a variable-frequency speed-regulating motor and positioning devices installed on both sides of the conveyor belt. The positioning devices cooperate with photoelectric sensors and mechanical clamps to position the circuit breaker; The image acquisition module includes multiple CCD cameras with different angles and functions, which are arranged above and on the side of the detection station. Among them, a high-resolution color CCD camera is set on the top, two CCD cameras with inclined angles are arranged on the side, and a multi-spectral CCD camera is also equipped. At the same time, it includes an annular shadowless light source installed around the top CCD camera and a strip light source set on the side; The image processing module is connected to the image acquisition module and is used to perform preprocessing, segmentation, edge detection, and feature extraction operations on the collected image data; The defect analysis module is built-in with a defect recognition model based on deep learning. This model is trained with a large number of appearance defect images of circuit breakers. The feature parameters extracted by the image processing module are input into this model to judge whether there are defects on the appearance of the circuit breaker and determine the position, size, and severity of the defects; The sorting and discharging module sorts and discharges the circuit breakers according to the detection results of the defect analysis module, including multiple discharging channels and a sorting device that combines pneumatic push rods and robotic arms; The central control module, as the core of the entire detection system, is used to coordinate and control the operation of each module, receive the detection data of the image processing module and the defect analysis module, store and statistically analyze the detection results, automatically adjust the shooting parameters of the image acquisition module, the algorithm parameters of the image processing module, and the defect judgment threshold of the defect analysis module according to different models and specifications of circuit breakers, and can also perform data interaction with the production management system through a network interface.

2. The CCD detection system for the appearance quality of a circuit breaker according to claim 1, characterized in that: The conveyor belt of the feeding and conveying module is driven by a variable-frequency speed-regulating motor and can adjust the conveying speed according to the detection requirements.

3. The CCD detection system for the appearance quality of a circuit breaker according to claim 1, wherein: The high-resolution color CCD camera on the top of the image acquisition module is used to collect the overall image of the upper surface of the circuit breaker, the two CCD cameras with inclined angles on the side are used to take detailed images of the side of the circuit breaker, and the multi-spectral CCD camera is used to collect images under different spectra.

4. The CCD detection system for the appearance quality of a circuit breaker according to claim 1, wherein: The preprocessing operations of the image processing module include noise reduction, enhancement, and grayscale conversion. The image segmentation algorithm is used to separate the circuit breaker image from the background, the edge detection algorithm is used to extract the contour and defect edge information of the circuit breaker, and the feature extraction algorithm is used to obtain the size, shape, color, and texture feature parameters of the appearance of the circuit breaker.

5. A CCD inspection system for the appearance quality of a circuit breaker according to claim 1, characterized in that: The defect recognition model based on deep learning of the defect analysis module can accurately identify defect types such as scratches, pits, cracks, stains, and blurred markings on the surface of the circuit breaker.

6. The CCD detection system for the appearance quality of a circuit breaker according to claim 1, characterized in that: When the sorting device of the sorting and discharging module detects a qualified product, it pushes it to the qualified product discharging channel; when it detects an unqualified product, it sorts it to the corresponding unqualified product discharging channel according to the defect type.

7. The CCD detection system for the appearance quality of a circuit breaker according to claim 1, characterized in that: When the system starts up, the central control module automatically adjusts the parameters of each module according to the input circuit breaker model and specification information. During the detection process, it receives the detection data in real time, stores and statistically analyzes the data, generates a detection report, uploads the detection results to the production management system, and issues an alarm signal and takes fault handling measures when abnormal situations occur.

Images