Programmable control defect detection lighting system

Abstract

The invention provides a programmable control defect detection lighting system, and relates to the technical field of industrial automation, and the programmable control defect detection lighting system comprises a light emitting device which emits linear light with a preset radian; the image acquisition equipment acquires a workpiece surface reflective picture and sends the workpiece surface reflective picture to the processor when the light-emitting equipment works; and the processor analyzes the reflective picture to determine workpiece surface defects. The operation panel provides illumination mode selection for an operator; and the controller calculates a light emitting sequence and a collection period according to selection and collection parameters of the operation panel, controls the light emitting equipment and the image collection equipment to work, and can also send reflective pictures to the processor in groups for defect analysis. Through the system, the surface defects of the workpiece can be accurately and efficiently detected.

Description

Technical Field

[0001] The present application relates to the field of industrial automation technology, and in particular to a programmable defect detection lighting system. Background Art

[0002] During the production process of industrial parts, surface defects or small cracks often occur due to bumps, storage, transportation, etc. For some workpieces with high surface accuracy requirements, how to detect surface cracks is an important process to ensure subsequent use.

[0003] In the prior art, some obvious crack damage can be directly detected manually. For some small cracks on the surface, the operator can place the workpiece under a microscope or other instruments for observation. For some metal parts, visual inspection can also be adopted to judge the surface defects of the metal parts by shining light on the surface of the metal parts and detecting the reflection of the surface of the metal parts.

[0004] However, the detection light source in the prior art can often only illuminate a certain area, and the damage forms on the workpiece surface are different. When irradiating from a fixed angle, the damage on the workpiece surface cannot be fully observed. In order to fully detect defects on the surface of parts, workers are often required to irradiate from different angles with different light sources, which is cumbersome and ineffective. Summary of the invention

[0005] The present application provides a programmable defect detection lighting system for efficiently and accurately detecting surface defects of workpieces and improving the level of product quality control.

[0006] In a first aspect, the present application provides a programmable defect detection lighting system, which includes: a light-emitting device for emitting a light source, wherein the light source is a linear light with a preset curvature and m rows and n columns, wherein m and n are positive integers; an image acquisition device, which is arranged on one side of the light-emitting device and is respectively connected to the light-emitting device and a processor for acquiring a reflection picture of the surface of a workpiece irradiated by the light-emitting device when the light-emitting device is working, and after determining the acquired reflection picture, sending the reflection picture to the processor for processing; a processor, which receives the reflection picture sent by the image acquisition device and analyzes the reflection picture to determine the defect on the surface of the workpiece; an operation panel, which is connected to the processor; The controller is communicatively connected, and the operation panel is used to provide the operator with a lighting mode selection for the light-emitting device; the controller is communicatively connected with the light-emitting device, the image acquisition device and the operation panel respectively, and the controller is used to calculate the light-emitting sequence of the light-emitting device and the acquisition cycle of the image acquisition device according to the lighting mode and acquisition parameters selected by the operator on the operation panel, and control the light sources of each row and column in the light-emitting device to light up in sequence according to the light-emitting sequence, and control the image acquisition device to collect reflective images according to the acquisition cycle, and after receiving multiple groups of image analysis request instructions sent by the operation panel, divide the reflective images into multiple groups according to preset rules and send them to the processor for defect analysis.

[0007] By adopting the above technical solution, the light-emitting device in the programmable defect detection lighting system emits linear light with a preset arc to provide specific lighting conditions for the workpiece. The image acquisition device collects the reflected light picture when the light-emitting device is working and sends it to the processor for analysis, so as to determine the surface defects of the workpiece. The operation panel and the controller enable the operator to select the lighting mode, and the controller controls the working order of the light-emitting device and the image acquisition device according to the selection. This method can achieve precise lighting control and image acquisition, and improve the accuracy and efficiency of defect detection.

[0008] In combination with some embodiments of the first aspect, in some embodiments, a conveying device is further included for conveying the workpiece to a detection area between the light-emitting device and the image acquisition device; the controller is also used to calculate the acquisition interval of the image acquisition device according to the workpiece conveying speed of the conveying device, so that the image acquisition device captures the reflective picture according to the position of the workpiece.

[0009] By adopting the above technical solution, it can be effectively ensured that the image acquisition device can accurately capture the reflective image according to the position of the workpiece.

[0010] In combination with some embodiments of the first aspect, in some embodiments, an ambient light detection device is further included, which is used to detect ambient light in the system working environment and send the ambient light data to the controller. The controller is also used to receive the ambient light data sent by the ambient light detection device, and calculate the compensation parameters of the image acquisition device based on the ambient light data, and send the compensation parameters to the image acquisition device so that the image acquisition device compensates the captured reflective picture according to the compensation parameters.

[0011] By adopting the above technical solution, the image acquisition device compensates the collected reflective image according to the compensation parameters, which can reduce the impact of ambient light on the detection results and improve the accuracy and stability of the detection.

[0012] In combination with some embodiments of the first aspect, in some embodiments, a machine learning module is further included, which is used to obtain a machine learning model by training based on multiple different types of images of workpieces with known defects and defect-free workpieces. During the detection process, the controller sends the reflective image to the machine learning module for analysis to determine the defects of the new workpiece.

[0013] By adopting the above technical solution, during the inspection process, the controller sends the reflected image to the machine learning module for analysis, which can quickly and accurately determine the defects of new workpieces and improve inspection efficiency and accuracy.

[0014] In combination with some embodiments of the first aspect, in some embodiments, a three-dimensional reconstruction module is also included for performing three-dimensional reconstruction of multiple reflective images acquired by the image acquisition device from different angles to obtain a three-dimensional model of the workpiece, and determining defects in multiple parts of the workpiece in combination with the three-dimensional model.

[0015] By adopting the above technical solution and combining it with the three-dimensional model to determine the defects of multiple parts of the workpiece, the defects of the workpiece can be detected more comprehensively, and the accuracy and reliability of detection can be improved.

[0016] In combination with some embodiments of the first aspect, in some embodiments, an energy management module is also included, which is used to control the light-emitting sequence, light-emitting intensity and light-emitting time of the light sources in each row and column of the light-emitting device according to the detection requirements and characteristics of different workpieces, so as to reduce energy in the process of defect detection.

[0017] By adopting the above technical solution, energy consumption can be reduced and production costs can be lowered during defect detection, while also meeting the requirements of energy conservation and environmental protection.

[0018] In combination with some embodiments of the first aspect, in some embodiments, a temperature monitoring module is also included for monitoring the temperature of the light-emitting device and the image acquisition device, and when the temperature exceeds a set threshold, a cooling prompt message is sent to the operation panel.

[0019] By adopting the above technical solution, when the temperature exceeds the set threshold, a cooling prompt message is sent to the operation panel, which can promptly detect overheating of the equipment, avoid equipment damage, and improve the stability and reliability of the detection system.

[0020] In combination with some embodiments of the first aspect, in some embodiments, a workpiece positioning auxiliary module is also included, which is communicated with the controller and is used to accurately position the workpiece entering the detection area based on laser positioning or visual recognition technology. When the workpiece position does not conform to the optimal detection position, an adjustment instruction is sent to the controller to enable the handling equipment to readjust the workpiece position to the optimal detection position.

[0021] By adopting the above technical solution, it is possible to ensure that the workpiece is in the best detection position, thereby improving the accuracy and reliability of detection.

[0022] In combination with some embodiments of the first aspect, in some embodiments, it also includes a spray module for performing gas spray treatment on the surface of the workpiece to remove dust; a steam module for spraying water vapor on the surface of the workpiece to dissolve oil stains; a cleaning module for rinsing the workpiece after steam treatment with clean water; the controller pre-stores a mapping relationship between the surface conditions of different workpiece materials and corresponding treatment schemes. When inspecting different workpieces, the image acquisition device captures the workpiece surface image, the controller determines the main contamination condition of the current workpiece surface based on the workpiece surface image, and determines the treatment scheme of the spray module, the steam module and the cleaning module based on the pre-stored mapping relationship, and controls the corresponding module to perform surface pretreatment on the current workpiece to be inspected according to the treatment scheme to remove surface dust or oil stains.

[0023] By adopting the above technical solution, the spray module, steam module and cleaning module pre-treat the surface of the workpiece under the control of the controller to remove dust or oil stains on the surface. The controller determines the contamination situation and determines the treatment plan based on the workpiece surface image, which can improve the cleanliness of the workpiece surface and thus improve the accuracy of defect detection.

[0024] In combination with some embodiments of the first aspect, in some embodiments, an image preprocessing module is provided in the image acquisition device for performing image quality improvement processing on the reflective image.

[0025] By adopting the above technical solution, the clarity, contrast and other qualities of the image can be enhanced, making it easier for the processor to analyze the defects on the surface of the workpiece, thereby improving the accuracy and reliability of detection.

[0026] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: 1. Due to the use of linear light emitting devices with preset arcs, an operating panel with selectable lighting modes, and a controller to accurately control light emission and image acquisition, the technical problems of single lighting conditions and difficulty in accurately controlling the detection process in the prior art are effectively solved, thereby achieving the technical effect of improving the accuracy and efficiency of defect detection.

[0027] 2. Due to the use of a machine learning module to train a model based on images of known defects and defect-free workpieces and analyze the reflective images of new workpieces, the technical problems of low efficiency and insufficient accuracy in the existing technology for new workpiece defect detection are effectively solved, thereby achieving the technical effect of quickly and accurately determining new workpiece defects and improving detection efficiency and accuracy.

[0028] 3. Since a three-dimensional reconstruction module is used to reconstruct three-dimensional reflection images at different angles to determine defects in multiple parts of the workpiece, the technical problem that it is difficult to comprehensively detect workpiece defects in the existing technology is effectively solved, thereby achieving a more comprehensive detection of workpiece defects and improving detection accuracy and reliability. Technical effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 is a module connection diagram of an embodiment of the present application; Figure 2 is a schematic diagram of an exemplary scenario using an embodiment of the present application; Figure 3 This is another module connection diagram of an embodiment of the present application.

[0030] Description of reference numerals: 1. Light-emitting device; 2. Image acquisition device; 3. Processor; 4. Operation panel; 5. Controller; 6. Conveying device; 7. Ambient light detection device; 8. Machine learning module; 9. Three-dimensional reconstruction module; 10. Energy management module; 11. Temperature monitoring module; 12. Workpiece positioning auxiliary module; 13. Injection module; 14. Steam module; 15. Cleaning module; 16. Image preprocessing module. DETAILED DESCRIPTION

[0031] The terms used in the following embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to be used as limitations to the present application. As used in the specification and appended claims of the present application, the singular expressions "one", "a kind of", "said", "above", "the" and "this" are intended to also include plural expressions, unless there is a clear indication to the contrary in the context. It should also be understood that the term "and / or" used in the present application refers to and includes any or all possible combinations of one or more listed items.

[0032] In the following, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as suggesting or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features, and in the description of the embodiments of the present application, unless otherwise specified, "plurality" means two or more.

[0033] The present application embodiment provides a programmable controllable defect detection lighting system, such as Figure 1 As shown, Figure 1 It is a module connection diagram of an embodiment of the present application, including: A light emitting device 1, for emitting a light source, wherein the light source is a linear light with a preset arc and m rows and n columns, where m and n are positive integers; The image acquisition device 2 is arranged on one side of the light emitting device 1, and is respectively connected to the light emitting device 1 and the processor 3 for collecting a reflection picture of the light emitting device 1 irradiating the workpiece surface when the light emitting device 1 is working, and after determining the collected reflection picture, the reflection picture is sent to the processor 3 for processing; The processor 3 receives the reflective image sent by the image acquisition device 2 and analyzes the reflective image to determine the defects on the surface of the workpiece; An operation panel 4, which is in communication with the controller 5 and is used to provide an operator with a lighting mode selection for the light emitting device 1; The controller 5 is respectively connected to the light-emitting device 1, the image acquisition device 2 and the operation panel 4 for communication. The controller 5 is used to calculate the light-emitting sequence of the light-emitting device 1 and the acquisition cycle of the image acquisition device 2 according to the lighting mode and acquisition parameters selected by the operator on the operation panel 4, and control the light sources of each row and column in the light-emitting device 1 to light up in sequence according to the light-emitting sequence, and control the image acquisition device 2 to acquire the reflective image according to the acquisition cycle. After receiving multiple groups of image analysis request instructions sent by the operation panel 4, the reflective image is divided into multiple groups according to preset rules and sent to the processor 3 for defect analysis.

[0034] Specifically, a special linear light emitting diode (LED) array can be used to realize this multi-row and multi-column light source. Through precise circuit design and layout, it is ensured that each row and column of LEDs can be independently controlled. The preset curvature can be achieved by mounting the LED on a substrate with a specific curved shape, or by using optical elements such as lenses to refract and bend the light, thereby forming a linear light with a preset curvature. In practical applications, the light source can be divided into 35 rows and 41 rows of linear light. When the light emitting device 1 is working, the image acquisition device 2 synchronously acquires the reflective image of the light emitting device 1 irradiating the surface of the workpiece, and after determining the acquired reflective image, sends it to the processor 3 for processing. In this application, a high-resolution industrial camera can be used as the image acquisition device 2. The processor 3 can use a high-performance computer or an embedded processor 3 as the processing core, first pre-processing the acquired image to remove noise and interference, and then identifying possible defective areas by comparing the images under different lighting conditions. By processing and analyzing the image, various defects on the surface of the workpiece, such as scratches, cracks, pits, etc., can be quickly and accurately detected, providing strong support for quality control. The operation panel 4 can be a touch screen or a key panel, which is connected to the controller 5 via a data cable or wireless communication. At the software level, an intuitive user interface is designed so that the operator can easily select different lighting modes. The lighting mode can include multiple modes such as full lighting, lighting row by row, lighting column by column, lighting in a specific area, etc., or it can be a mode including parameters such as luminous frequency and luminous intensity. The operator can select a suitable lighting mode according to actual needs. Different lighting modes can adapt to different workpieces and detection scenes, thereby improving the flexibility and efficiency of detection. The controller 5 can be a microcontroller 5 or a programmable logic controller 5, which implements the control logic of the light-emitting device 1 and the image acquisition device 2 through programming. According to the input parameters on the operation panel 4, the appropriate light-emitting sequence and acquisition cycle are calculated. For the control of the light-emitting device 1, the lighting and extinguishing control of the LEDs in different rows and columns can be realized by sending a specific control signal to the LED driving circuit. For the control of the image acquisition device 2, the acquisition time and frequency of the camera can be controlled by sending a trigger signal to the camera. According to the operator's choice, the lighting mode of the light-emitting device 1 and the acquisition cycle of the image acquisition device 2 are controlled, and high-quality reflective images can be acquired, thereby improving the accuracy of the workpiece surface defect analysis.

[0035] The following is an example of the image acquisition device 2 being a camera, and the camera's shooting frequency being 4. The operator sets the lighting mode of the light source through the operation panel 4, and the processor 3 will set the camera's shooting frequency accordingly. Here, four shots are used as an example for description: the shooting cycle of the light source is set to 4, and the shooting direction (horizontal or vertical, vertical is used as an example here), and the camera will also be set to the shooting cycle accordingly. When the workpiece is transported to the light source through a conveyor belt, etc., the linear light on the light source will be divided into 4 corresponding groups. When the first group of light sources is on, the camera takes a shot, which is recorded as reflective picture one, and then the second group of light sources is on, and the camera takes another shot, which is recorded as reflective picture two, and so on, until reflective picture four is taken. After recording four pictures, the first group of light sources lights up again, the camera takes pictures, and it is recorded as reflective picture five. The second group of light sources lights up, the camera takes pictures, and it is recorded as reflective picture six. And so on, until reflective picture eight is taken. After selecting to take multiple groups of pictures as needed, the reflective pictures taken by the camera will be imported into the processor 3. The processor 3 will record the reflective picture one and reflective picture four taken by the camera when the first group of light sources are illuminated as a group for analysis, and record the reflective picture two and reflective picture five taken by the second group of light sources as two groups, and then analyze them.

[0036] In this way, the automated detection of workpiece surface defects is realized, various defects can be detected quickly and accurately, and production efficiency and product quality can be improved.

[0037] For ease of understanding, the following describes an application scenario diagram of an embodiment of the present application. Figure 2 , Figure 2 It is a schematic diagram of an exemplary scenario using an embodiment of the present application.

[0038] Figure 2 The light-emitting device 1 emits m rows and n columns of light sources, and each row and column can be controlled individually through programming. The operator can set the desired lighting mode through the control panel. After setting, the defect detection work can be started. During the working process after startup, the working frequency of the image acquisition device 2 is consistent with that of the light-emitting device 1. The image acquisition device 2 is set at a preset position between the workpiece and the light-emitting device 1. When the light source is irradiated on the surface of the workpiece, the image acquisition device 2 captures the reflected image of the workpiece surface and sends the captured reflected image to the processor 3 for processing and analysis to determine the defects on the workpiece surface.

[0039] For ease of understanding, the following is a further module description of the system provided by this implementation in combination with the above scenarios. Figure 3 , Figure 3 This is another module connection diagram of an embodiment of the present application.

[0040] exist Figure 3In the embodiment, the programmable defect detection lighting system includes a conveyor 6 for conveying the workpiece to the detection area between the light emitting device 1 and the image acquisition device 2; the controller 5 is also used to calculate the acquisition interval of the image acquisition device 2 according to the workpiece conveying speed of the conveyor 6, so that the image acquisition device 2 can capture the reflective image according to the position of the workpiece. Specifically, the conveyor 6 can be a conveyor belt driven by a motor, and the speed of the motor can be adjusted by a frequency converter to adapt to different workpiece conveying speed requirements. The workpiece is accurately transported to the detection area to ensure the automation and continuity of the detection process. By adjusting the transmission speed, different production rhythms and detection requirements can be adapted. For example, for workpieces on a high-speed production line, the transmission speed can be increased, and the parameters of the image acquisition device 2 can be adjusted accordingly to ensure that the detection of the workpiece is completed in a short time. The controller 5 can monitor the running speed of the conveyor 6 in real time through a sensor or other device, and then calculate the acquisition interval of the image acquisition device 2 according to the preset detection requirements and parameters such as the size of the workpiece. When the acquisition time calculated by the controller 5 arrives, the controller 5 sends a trigger signal to the image acquisition device 2, and the image acquisition device 2 takes a shot after receiving the signal. At the same time, the controller 5 can also adjust the parameters of the image acquisition device 2, such as exposure time, focal length, etc., as needed to adapt to different lighting conditions and workpiece surface features. This can effectively enable the image acquisition device 2 to capture the reflective image of the workpiece at the appropriate time and position. By adjusting the acquisition interval according to the speed of the conveyor 6, it can be ensured that no matter how fast the workpiece is conveyed, the image acquisition device 2 can accurately obtain the required image data.

[0041] In some embodiments, the programmable defect detection lighting system also includes an ambient light detection device 7, which is used to detect the ambient light in the system working environment and send the ambient light data to the controller 5. The controller 5 is also used to receive the ambient light data sent by the ambient light detection device 7, and calculate the compensation parameters of the image acquisition device 2 according to the ambient light data, and send the compensation parameters to the image acquisition device 2, so that the image acquisition device 2 compensates the collected reflective pictures according to the compensation parameters. Specifically, in the actual defect detection process, changes in ambient light may affect the quality of the reflective pictures collected by the image acquisition device 2. If the ambient light is too strong or too weak, it may cause the image to be too bright or too dark, affecting the subsequent defect analysis. Therefore, by monitoring the changes in ambient light in real time through the ambient light detection device 7, accurate ambient light data can be provided to the system for corresponding adjustments and compensations. The ambient light detection device 7 can use photosensitive sensors, which can generate corresponding electrical signal changes according to changes in the intensity of ambient light. The ambient light detection device 7 is installed near the light emitting device 1 and the image acquisition device 2 so as to accurately detect the light conditions in the actual working environment. The controller 5 can receive the ambient light data through a serial communication interface or a wireless communication method. The controller 5 calculates the compensation parameters of the image acquisition device 2 according to the ambient light data and a preset algorithm. These parameters may include exposure time adjustment, gain adjustment, contrast adjustment, etc. For example, if the ambient light is too strong, the controller 5 may calculate compensation parameters such as shortening the exposure time and reducing the gain to avoid the image being too bright; if the ambient light is too weak, the controller 5 may calculate compensation parameters such as extending the exposure time and increasing the gain to increase the brightness of the image. The controller 5 sends the calculated compensation parameters to the image acquisition device 2. After receiving the compensation parameters sent by the controller 5, the image acquisition device 2 will compensate the collected reflective image according to these parameters. In this way, the influence of the change of ambient light on the quality of the reflective image can be effectively compensated, and the accuracy and reliability of defect detection can be improved.

[0042] In some embodiments, the programmable defect detection lighting system further includes a machine learning module 8, which is used to train a machine learning model based on multiple different types of known defects and defect-free workpiece images. During the detection process, the controller 5 sends the reflective image to the machine learning module 8 for analysis to determine the defects of the new workpiece. Specifically, it is necessary to collect a large number of different types of known defects and defect-free workpiece images. These images can come from historical data in the actual production process, a special defect sample library, or images generated by simulating defects. The collected images are preprocessed, including image enhancement, denoising, normalization and other operations to improve the quality and consistency of the image. At the same time, the image is annotated to clearly indicate the defect type and location in the image (if there is a defect). Select a suitable machine learning algorithm and use the prepared annotated image data to train the selected machine learning model. In order to improve the generalization ability of the model, cross-validation, data enhancement and other technologies can be used. Cross-validation can divide the data into multiple subsets, and train and verify on different subsets to evaluate the performance of the model. In the actual detection process, the controller 5 transmits the reflective image to the machine learning module 8. These images can be single images or a set of continuous image sequences. The machine learning module 8 inputs the input image into the trained machine learning model. The model extracts and classifies the image features to determine whether there are defects in the image and the type and location of the defects. The machine learning module 8 outputs the analysis results to the controller 5, which sends them to the control panel for display. The results can be a simple judgment of whether the defect exists or not, or detailed information such as the defect type, location and severity. Through reasonable data collection, model training and optimization, the advantages of machine learning can be fully utilized to improve the accuracy and efficiency of defect detection, providing strong support for quality control of industrial production.

[0043] In some embodiments, the programmable defect detection lighting system further includes a three-dimensional reconstruction module 9, which is used to perform three-dimensional reconstruction on multiple reflective images collected by the image acquisition device 2 from different angles to obtain a three-dimensional model of the workpiece, and determine defects in multiple parts of the workpiece in combination with the three-dimensional model. Specifically, the image acquisition device 2 needs to shoot the workpiece from multiple different angles. This can be achieved by using multiple cameras arranged at different positions, or by moving a single camera around the workpiece for shooting. The three-dimensional reconstruction module 9 extracts features from each collected reflective image, and the purpose of feature extraction is to find corresponding points in different images for three-dimensional reconstruction. By comparing the features in the image, the pixel position representing the same physical point in different images is found, and three-dimensional reconstruction can be performed based on the corresponding point information obtained by stereo matching and the parameters of the camera. Using the three-dimensional model, the surface and internal structure of the workpiece can be observed from multiple angles, and defects that are difficult to detect in traditional two-dimensional image detection can be more easily found. By comparing the difference between the three-dimensional model and the standard model, or by analyzing the surface shape, texture and other features of the three-dimensional model, it can be determined whether the workpiece has defects. In this way, defects in multiple parts of the workpiece can be determined more comprehensively and accurately, providing strong support for quality control of industrial production.

[0044] In some embodiments, the programmable defect detection lighting system also includes an energy management module 10, which is used to control the lighting sequence, lighting intensity and lighting time of the light sources in each row and column of the light emitting device 1 according to the detection requirements and characteristics of different workpieces, so as to reduce energy in the process of detecting defects. Specifically, the system needs to analyze the detection requirements of different workpieces. This includes the shape, size, material, surface characteristics and possible defect types of the workpiece. At the same time, the accuracy requirements of the detection also need to be considered. If the detection accuracy requirements are high, more sophisticated lighting control may be required to ensure that the tiny defects on the surface of the workpiece can be clearly captured. The energy management module 10 can optimize the lighting sequence of the light sources in each row and column of the light emitting device 1 according to the characteristics of the workpiece and the detection requirements. For example, for a workpiece with a specific shape, the light source in the area that is most critical for defect detection can be lit first, and then the light sources in other areas can be gradually lit to reduce unnecessary energy waste. The control of the lighting sequence can be achieved by programming. The controller 5 sends a corresponding control signal to the light emitting device 1 according to the preset algorithm and detection requirements to determine the lighting sequence of the light sources in each row and column. The energy management module 10 can also dynamically adjust the luminous intensity of the light-emitting device 1 according to the material and surface characteristics of the workpiece. For workpieces with strong reflectivity, the luminous intensity can be reduced to avoid overexposure; for workpieces with weak reflectivity, the luminous intensity can be increased to ensure that the image acquisition device 2 can capture enough light. The energy management module 10 can reasonably control the luminous time of the light-emitting device 1 according to the detection speed and accuracy requirements of the workpiece. For workpieces that are detected at high speed, the luminous time can be shortened to improve the detection efficiency; for workpieces that require high-precision detection, the luminous time can be appropriately extended to ensure that the image acquisition device 2 can fully collect information on the surface of the workpiece. In this way, the luminous order, luminous intensity and luminous time of the light sources in each row and column of the light-emitting device 1 can be accurately controlled, thereby minimizing energy consumption in the process of defect detection and improving the energy utilization efficiency of the system.

[0045] In some embodiments, the programmable defect detection lighting system further includes a temperature monitoring module 11, which is used to monitor the temperature of the light-emitting device 1 and the image acquisition device 2, and when the temperature exceeds a set threshold, a cooling prompt message is sent to the operation panel 4. Specifically, the temperature monitoring module 11 usually uses a temperature sensor to measure the temperature of the light-emitting device 1 and the image acquisition device 2. The temperature sensor converts the measured temperature signal into an electrical signal and transmits it to the temperature monitoring module 11. The temperature monitoring module 11 converts the analog electrical signal into a digital signal through an analog-to-digital converter, and determines whether the temperature exceeds the set threshold according to a preset algorithm. When the temperature monitoring module 11 detects that the temperature of the device exceeds the set threshold, a cooling prompt message is sent to the operation panel 4. After receiving the cooling prompt message, the operation panel 4 can send an alarm to the operator through a display screen, an indicator light or a sound, etc., to remind the operator to take corresponding cooling measures. For example, the operation of the device can be suspended, the power of the heat dissipation device can be increased, and the ventilation conditions can be improved. In this way, the temperature of the device can be grasped in time, and the cooling prompt message is sent to the operation panel 4 when the temperature exceeds the set threshold, which can effectively avoid damage to the device due to overheating and ensure the stable operation of the system.

[0046] In some embodiments, the programmable defect detection lighting system also includes a workpiece positioning auxiliary module 12, which is connected to the controller 5 for accurately positioning the workpiece entering the detection area according to laser positioning or visual recognition technology. When the workpiece position does not meet the optimal detection position, an adjustment instruction is sent to the controller 5 so that the handling equipment readjusts the workpiece position to the optimal detection position. Specifically, the laser positioning system is usually composed of a laser transmitter, a laser receiver, and a signal processing unit. The laser transmitter emits a laser beam of a specific wavelength and irradiates the surface of the workpiece. The laser receiver receives the reflected laser signal and transmits it to the signal processing unit. The signal processing unit analyzes and processes the received laser signal to determine the position and posture information of the workpiece. By setting multiple laser receivers at different positions, the position information of multiple points on the workpiece surface can be measured simultaneously. According to the position information of these points, the three-dimensional position and posture of the workpiece can be determined. When the workpiece enters the detection area, the laser transmitter emits a laser beam to the surface of the workpiece. The laser receiver receives the reflected laser signal and transmits it to the signal processing unit. The signal processing unit analyzes and processes the received laser signal to calculate the current position and posture of the workpiece. If the position of the workpiece does not conform to the optimal detection position, the signal processing unit will send an adjustment instruction to the controller 5. After receiving the adjustment instruction, the controller 5 will control the handling equipment to adjust the workpiece until the position of the workpiece reaches the optimal detection position. The principle of visual recognition is based on image processing and pattern recognition technology. After the camera takes an image of the workpiece, the controller 5 extracts the feature information of the workpiece from the image. Based on this feature information, the controller 5 can identify the type, shape and position of the workpiece. Finally, based on the identified workpiece position and posture information, it is determined whether the workpiece is in the optimal detection position. If the workpiece position does not conform to the optimal detection position, the controller 5 controls the adjustment device to make adjustments. This ensures that the image acquisition device 2 can capture a clear image of the workpiece at the optimal angle and distance, and the light-emitting device 1 can also illuminate the surface of the workpiece in the most effective way, thereby improving the accuracy of defect detection.

[0047] In some embodiments, the programmable defect detection lighting system also includes a spray module 13 for performing gas spray treatment on the surface of the workpiece to remove dust; a steam module 14 for spraying water vapor on the surface of the workpiece to dissolve oil stains; a cleaning module 15 for washing the workpiece after steam treatment with clean water; the controller 5 pre-stores a mapping relationship between the surface conditions of different workpiece materials and the corresponding treatment schemes. When inspecting different workpieces, the image acquisition device 2 captures the workpiece surface image, and the controller 5 determines the main pollution conditions of the current workpiece surface according to the workpiece surface image, and determines the treatment schemes of the spray module 13, the steam module 14 and the cleaning module 15 according to the pre-stored mapping relationship, and controls the corresponding modules to perform surface pretreatment on the current workpiece to be inspected according to the treatment scheme to remove surface dust or oil stains. Specifically, the spray module 13 sprays gas to the workpiece surface at a certain pressure and speed through a specific gas spray device. This gas can be purified compressed air, or other inert gases selected according to the material and surface conditions of the workpiece. When the gas is sprayed onto the surface of the workpiece, the dust particles will be lifted and carried away due to the impact force of the gas, thereby achieving the purpose of removing dust. The steam module 14 generates water vapor by heating water, and sprays the water vapor onto the surface of the workpiece through a specific pipe and nozzle. Water vapor has a high temperature and energy. When it contacts the oil stains on the surface of the workpiece, it can intensify the movement of the oil stain molecules, thereby reducing the viscosity of the oil stains, making it easier to dissolve and remove. At the same time, water vapor can also penetrate into the tiny gaps between the oil stains and the surface of the workpiece, further promoting the dissolution of the oil stains. For example, in some mechanical processing industries, some oil stains formed by lubricating oil often remain on the surface of the workpiece. By spraying water vapor through the steam module 14, these oil stains can be effectively dissolved, preparing for subsequent cleaning and defect detection. After the steam module 14 dissolves the oil stains on the surface of the workpiece, the cleaning module 15 will use clean water to rinse the workpiece. The purpose of clean water rinsing is to completely remove the oil stains and other impurities dissolved in the water. The cleaning module 15 can spray clean water evenly on the surface of the workpiece through a nozzle, or soak the workpiece in clean water for a period of time to ensure that oil stains and impurities are completely removed. The controller 5 pre-stores the mapping relationship between the surface conditions of different workpiece materials and the corresponding treatment schemes. When inspecting different workpieces, the image of the workpiece surface is first captured by the image acquisition device 2, and then the controller 5 determines the main pollution condition of the current workpiece surface based on the workpiece surface image. For example, if the image shows that there are more dust particles on the workpiece surface and less oil stains, the controller 5 will determine that the main pollution condition of the current workpiece is dust pollution. Then, according to the pre-stored mapping relationship, the controller 5 will determine the treatment schemes of the injection module 13, the steam module 14 and the cleaning module 15.In this way, the surface of the workpiece to be inspected can be pretreated to remove surface dust or oil stains, thereby improving the cleanliness of the workpiece surface and providing better conditions for subsequent defect detection.

[0048] In some embodiments, the image acquisition device 2 in the programmable defect detection lighting system is provided with an image preprocessing module 16 for improving the image quality of the reflective image. Specifically, during the image acquisition process, due to factors such as ambient light and noise from electronic equipment, the acquired image may contain certain noise, which will affect the subsequent analysis of defects on the workpiece surface. The image preprocessing module 16 uses a filtering algorithm to remove the noise. Due to the reflective conditions on the workpiece surface, the contrast of the image may not be ideal, which is not conducive to the observation and analysis of defects. The image preprocessing module 16 enhances the contrast by adjusting the grayscale value distribution of the image. In order to make the defective area in the image clearer, the image preprocessing module 16 can also appropriately sharpen the reflective image. This can enhance the quality of the image such as clarity and contrast, making it easier for the processor 3 to analyze the defects on the workpiece surface and improve the accuracy and reliability of detection.

[0049] The programmable defect detection lighting system of this embodiment includes: a light-emitting device 1, an image acquisition device 2, a processor 3, an operation panel 4, a controller 5, a conveying device 6, an ambient light detection device 7, a machine learning module 8, a three-dimensional reconstruction module 9, an energy management module 10, a temperature monitoring module 11, a workpiece positioning auxiliary module 12, a spray module 13, a steam module 14, a cleaning module 15, and an image preprocessing module 16.

[0050] A light emitting device 1, for emitting a light source, wherein the light source is a linear light with a preset arc and m rows and n columns, where m and n are positive integers; The image acquisition device 2 is arranged on one side of the light emitting device 1, and is respectively connected to the light emitting device 1 and the processor 3 for collecting a reflection picture of the light emitting device 1 irradiating the workpiece surface when the light emitting device 1 is working, and after determining the collected reflection picture, the reflection picture is sent to the processor 3 for processing; The processor 3 receives the reflective image sent by the image acquisition device 2 and analyzes the reflective image to determine the defects on the surface of the workpiece; An operation panel 4, which is in communication with the controller 5 and is used to provide an operator with a lighting mode selection for the light emitting device 1; The controller 5 is respectively connected to the light-emitting device 1, the image acquisition device 2 and the operation panel 4 for communication. The controller 5 is used to calculate the light-emitting sequence of the light-emitting device 1 and the acquisition cycle of the image acquisition device 2 according to the lighting mode and acquisition parameters selected by the operator on the operation panel 4, and control the light sources of each row and column in the light-emitting device 1 to light up in sequence according to the light-emitting sequence, and control the image acquisition device 2 to collect the reflection picture according to the acquisition cycle. After receiving the multiple groups of picture analysis request instructions sent by the operation panel 4, the reflection picture is divided into multiple groups according to the preset rules and sent to the processor 3 for defect analysis; The conveying device 6 is used to convey the workpiece to the detection area between the light emitting device 1 and the image acquisition device 2; the controller 5 is also used to calculate the acquisition interval of the image acquisition device 2 according to the workpiece conveying speed of the conveying device 6, so that the image acquisition device 2 captures the reflection picture according to the position of the workpiece; The ambient light detection device 7 is used to detect the ambient light in the working environment of the system and send the ambient light data to the controller 5. The controller 5 is also used to receive the ambient light data sent by the ambient light detection device 7, calculate the compensation parameters of the image acquisition device 2 according to the ambient light data, and send the compensation parameters to the image acquisition device 2, so that the image acquisition device 2 compensates the collected reflective image according to the compensation parameters; A machine learning module 8, which is used to obtain a machine learning model by training according to a plurality of different types of workpiece images with known defects and without defects. During the detection process, the controller 5 sends the reflected image to the machine learning module 8 for analysis to determine the defects of the new workpiece; A three-dimensional reconstruction module 9 is used to perform three-dimensional reconstruction on a plurality of reflective images acquired by the image acquisition device 2 from different angles to obtain a three-dimensional model of the workpiece, and determine defects at multiple locations of the workpiece in combination with the three-dimensional model; The energy management module 10 is used to control the light-emitting sequence, light-emitting intensity and light-emitting time of the light sources in each row and column of the light-emitting device 1 according to the detection requirements and characteristics of different workpieces, so as to reduce energy in the process of defect detection; The temperature monitoring module 11 is used to monitor the temperature of the light emitting device 1 and the image acquisition device 2, and when the temperature exceeds a set threshold, a temperature reduction prompt message is sent to the operation panel 4; The workpiece positioning auxiliary module 12 is connected to the controller 5 for accurately positioning the workpiece entering the detection area according to laser positioning or visual recognition technology, and when the workpiece position does not meet the optimal detection position, an adjustment instruction is sent to the controller 5 so that the handling device readjusts the workpiece position to the optimal detection position; The spray module 13 is used to perform gas spraying treatment on the surface of the workpiece to remove dust; The steam module 14 is used to spray water vapor onto the surface of the workpiece to dissolve the oil stains; The cleaning module 15 is used to rinse the workpiece after the steam treatment with clean water; the controller 5 pre-stores the mapping relationship between the surface conditions of different workpiece materials and the corresponding treatment schemes. When inspecting different workpieces, the image acquisition device 2 captures the workpiece surface image, and the controller 5 determines the main pollution situation of the current workpiece surface according to the workpiece surface image, and determines the treatment scheme of the injection module 13, the steam module 14 and the cleaning module 15 according to the pre-stored mapping relationship, and controls the corresponding module to perform surface pre-treatment on the current workpiece to be inspected according to the treatment scheme to remove surface dust or oil stains; The image pre-processing module 16 is used to perform image quality improvement processing on the reflective image.

[0051] Through the above embodiment, the light-emitting device 1 emits specific linear light, the image acquisition device 2 collects the reflection picture and the processor 3 analyzes and determines the surface defects of the workpiece, the operation panel 4 and the controller 5 realize the lighting mode selection and precise control of light emission and image acquisition, thereby improving the accuracy and efficiency of defect detection.

Claims

1. A programmable defect detection lighting system, characterized in that: include: A light emitting device, used to emit a light source, wherein the light source is a linear light with a preset arc and m rows and n columns, wherein m and n are positive integers; An image acquisition device is arranged on one side of the light-emitting device, and is respectively connected to the light-emitting device and the processor for acquiring a reflection picture of the light-emitting device irradiating the surface of the workpiece when the light-emitting device is working, and after determining the acquired reflection picture, the reflection picture is sent to the processor for processing; A processor receives the reflective image sent by the image acquisition device and analyzes the reflective image to determine the defects on the surface of the workpiece; An operation panel, connected to the controller for communication, and configured to provide an operator with a lighting mode selection for the light emitting device; A controller is respectively connected to the light-emitting device, the image acquisition device and the operation panel for communication. The controller is used to calculate the light-emitting sequence of the light-emitting device and the acquisition cycle of the image acquisition device according to the lighting mode and acquisition parameters selected by the operator on the operation panel, and control the light sources of each row and column in the light-emitting device to light up in sequence according to the light-emitting sequence, and control the image acquisition device to collect reflective images according to the acquisition cycle. After receiving multiple groups of image analysis request instructions sent by the operation panel, the controller divides the reflective images into multiple groups according to preset rules and sends them to the processor for defect analysis.

2. The programmable defect detection lighting system according to claim 1, characterized in that: It also includes a conveying device for conveying the workpiece to the detection area between the light-emitting device and the image acquisition device; the controller is also used to calculate the acquisition interval of the image acquisition device according to the workpiece conveying speed of the conveying device, so that the image acquisition device captures the reflective image according to the position of the workpiece.

3. The programmable defect detection lighting system according to claim 1, characterized in that: It also includes an ambient light detection device, which is used to detect the ambient light in the system working environment and send the ambient light data to the controller. The controller is also used to receive the ambient light data sent by the ambient light detection device, and calculate the compensation parameters of the image acquisition device according to the ambient light data, and send the compensation parameters to the image acquisition device, so that the image acquisition device compensates the collected reflective picture according to the compensation parameters.

4. The programmable defect detection lighting system according to claim 1, characterized in that: It also includes a machine learning module, which is used to obtain a machine learning model by training based on multiple different types of known defects and defect-free workpiece images. During the detection process, the controller sends the reflective image to the machine learning module for analysis to determine the defects of the new workpiece.

5. The programmable defect detection lighting system according to claim 1, characterized in that: It also includes a three-dimensional reconstruction module for performing three-dimensional reconstruction on multiple reflective images collected by the image acquisition device from different angles to obtain a three-dimensional model of the workpiece, and determining defects in multiple parts of the workpiece in combination with the three-dimensional model.

6. The programmable defect detection lighting system according to claim 1, characterized in that: It also includes an energy management module for controlling the lighting sequence, lighting intensity and lighting time of the light sources in each row and column of the light-emitting device according to the detection requirements and characteristics of different workpieces, so as to reduce energy in the process of defect detection.

7. The programmable defect detection lighting system according to claim 1, characterized in that: It also includes a temperature monitoring module for monitoring the temperature of the light-emitting device and the image acquisition device, and sending a cooling prompt message to the operation panel when the temperature exceeds a set threshold.

8. The programmable defect detection lighting system according to claim 1, characterized in that: It also includes a workpiece positioning auxiliary module, which is communicated with the controller and is used to accurately position the workpiece entering the detection area based on laser positioning or visual recognition technology. When the workpiece position does not conform to the optimal detection position, an adjustment instruction is sent to the controller to enable the handling equipment to readjust the workpiece position to the optimal detection position.

9. The programmable defect detection lighting system according to claim 1, characterized in that: Also included is a spray module for performing a gas spray treatment on the surface of the workpiece to remove dust; The steam module is used to spray water vapor on the surface of the workpiece to dissolve the oil stains; A cleaning module is used to rinse the workpiece after steam treatment with clean water; The controller pre-stores a mapping relationship between the surface conditions of different workpiece materials and the corresponding processing solutions. When inspecting different workpieces, the image acquisition device captures the workpiece surface image. The controller determines the main contamination condition of the current workpiece surface based on the workpiece surface image, and determines the processing solutions of the injection module, the steam module and the cleaning module based on the pre-stored mapping relationship, and controls the corresponding modules to perform surface pre-treatment on the current workpiece to be inspected according to the processing solution to remove surface dust or oil stains.

10. The programmable defect detection lighting system according to claim 1, characterized in that: The image acquisition device is provided with an image preprocessing module for performing image quality improvement processing on the reflective image.

Images