Industrial robot data processing system based on machine vision

Abstract

The invention discloses an industrial robot data processing system based on machine vision, and relates to the technical field of industrial robot data processing based on machine vision. The system comprises an industrial robot data acquisition module, an industrial robot data processing module, an industrial robot data analysis module and an industrial robot early warning module. The industrial robot data acquisition module is used for acquiring real-time images of visual equipment, illumination intensity, dust concentration and digital signals carrying noise data; the industrial robot data processing module is used for respectively processing the acquired data and acquiring illumination intensity, an image two-dimensional coordinate graph at a corresponding moment, an influence report of dust concentration on the quality of the acquired image and a noise data time sequence graph; the industrial robot data analysis module is used for respectively analyzing the processed data; and the industrial robot early warning module receives the abnormal signal and feeds back the abnormal signal to the client.

Description

Technical Field

[0001] The present invention relates to the technical field of industrial robot data processing based on machine vision, and in particular to an industrial robot data processing system based on machine vision. Background Art

[0002] The industrial robot data processing system based on machine vision is an advanced technology born in the context of the rapid development of the field of industrial automation. The system integrates high-precision image acquisition, intelligent image processing algorithms and powerful data analysis capabilities, aiming to improve the level and efficiency of industrial production automation. With the continuous advancement of machine vision technology, industrial robots can more accurately identify, locate and track various objects on the production line, and achieve fine control of the production process. By integrating advanced industrial robot data processing modules, the system can analyze production data in real time, optimize operation paths, and improve production quality. The introduction of this technology not only promotes the intelligent transformation of the manufacturing industry, but also enhances the flexibility and response speed of industrial production, providing strong support for the efficient and precise production of modern industry. Although the industrial robot data processing system based on machine vision has made certain progress in improving the level of industrial automation, it still faces many challenges: insufficient lighting conditions or overexposure will lead to a decrease in the quality of images collected by machine vision equipment; dust may adhere to the machine vision equipment in the working environment of the industrial robot, blocking the vision equipment's line of sight and affecting the collection results; in addition, the noise interference in the operating environment of the machine vision equipment may affect the data transmission between the vision equipment and the industrial robot, causing the coordinate system of the machine vision equipment and the industrial robot to drift, resulting in deviations in their calibration, affecting the precise positioning of the industrial robot by the machine vision equipment. Summary of the invention

[0003] In order to solve the above problems, the present invention provides an industrial robot data processing system based on machine vision, including an industrial robot data acquisition module, an industrial robot data processing module, an industrial robot data analysis module and an industrial robot early warning module; The industrial robot data acquisition module obtains the image information and light intensity data collected by the visual device in real time according to the light intensity detector carried by the camera; obtains the dust concentration data attached to the machine vision device through the dust particle sensor; and uses the noise sensor to obtain the digital signal carrying the noise data; The industrial robot data processing module uses the collected light intensity data, the corresponding moment image information and the algorithm to obtain a dynamic light intensity range suitable for visual acquisition and a two-dimensional coordinate diagram of the light intensity; obtains a report on the impact of dust concentration on the quality of the collected image based on the dust concentration data attached to the machine vision device and the deep learning algorithm; obtains a noise data time series diagram based on the digital signal carrying the noise data; The industrial robot data analysis module analyzes the effect of light intensity on image information through a two-dimensional coordinate graph; uses a dust concentration report to analyze its effect on image clarity; and uses a noise time series graph to analyze the effect of noise on machine vision and industrial robot data transmission; The industrial robot early warning module receives abnormal signals and feeds them back to the client.

[0004] Furthermore, the process of the industrial robot data acquisition module acquiring the image information and light intensity data collected in real time by the visual device includes: Using the camera, photoelectric conversion technology and image processing technology of the visual device, a digital signal carrying image data is obtained, and the digital signal is output to a computer display to obtain image information collected by the visual device in real time; The light intensity detector on the visual device has a built-in photoresistor and ADC analog-to-digital converter. According to the photoelectric effect, when the light in the machine vision device environment shines on the photoresistor, the photoresistor obtains an electrical signal carrying light intensity data, and converts the electrical signal into a digital signal carrying light intensity data through the ADC analog-to-digital converter. The light intensity detector converts the digital signal into light intensity based on the characteristics of the photoresistor and calibration data, and obtains real-time light intensity data.

[0005] Furthermore, the process of the industrial robot data acquisition module acquiring dust concentration data attached to the machine vision device includes: According to the principle of light scattering, when light shines on dust particles, a light pulse signal is generated. The photodetector built into the dust particle sensor receives the light pulse signal and converts it into an electrical pulse signal. The greater the intensity of the electrical pulse signal, the greater the corresponding dust concentration. The dust particle sensor obtains the dust concentration data attached to the machine vision device based on the intensity of the electrical pulse signal, and then obtains the image information corresponding to the dust concentration collection moment through the visual acquisition device.

[0006] Furthermore, the process of the industrial robot data acquisition module acquiring a digital signal carrying noise data includes: The noise sensor has a built-in capacitive electret microphone. When sound waves act on the electret film inside the microphone, the film vibrates and changes the capacitance value of the capacitor inside the microphone. Since the capacitance on the electret remains constant, the change in capacitance value will cause the voltage value across the capacitor to change, and the voltage value carrying noise data is obtained. The voltage signal is amplified and filtered, and then converted into a digital signal to obtain a digital signal carrying noise data.

[0007] Furthermore, the process of obtaining the two-dimensional coordinate diagram of light intensity by the industrial robot data processing module includes: The exposure condition of the operating environment of the visual device is obtained according to the real-time image information, the light intensity and its exposure condition corresponding to the real-time image information are selected, and a decision tree is independently constructed in the training data set through the random forest algorithm, and a training data set containing insufficient light and overexposure is independently constructed, and then samples are randomly selected from the training data set through sampling, and the randomly selected sample data are summarized, and the critical value of the light intensity of insufficient light and the critical value of the light intensity of overexposure in the sample are extracted by using the anomaly detection algorithm, and the critical value of the light intensity of insufficient light and the critical value of the light intensity of overexposure in the sample are respectively set as the lower threshold and the upper threshold of the light intensity, and the threshold range is adjusted according to the dynamic change of the data, and a two-dimensional coordinate system is constructed, in which the horizontal axis represents time and the vertical axis represents light intensity, the dynamic critical value range is mapped to the coordinate system in real time, and then the light intensity data is mapped to the coordinate system to obtain a two-dimensional coordinate graph of the light intensity data.

[0008] Furthermore, the process of obtaining the report on the impact of dust concentration on the quality of collected images by the industrial robot data processing module includes: Using deep learning algorithm, the MLP network structure is selected, and the dust concentration data attached to the machine vision equipment is converted into a format suitable for MLP network input. Image enhancement, filtering and edge detection are performed on the image information collected at the same time as the dust concentration. A neural network model of input layer, hidden layer and output layer is constructed. The preprocessed dust concentration data and its image information are used as input, the nonlinear characteristics of the dust data are extracted from the hidden layer and the nonlinear factors are introduced through the activation function. The MLP network is trained to obtain an MLP network that can judge the impact of dust concentration on image quality. The output layer outputs the impact of dust concentration on the quality of images collected by the visual device. The trained MLP model is evaluated using the test set data, and it is adjusted and optimized according to the evaluation results to obtain a report on the impact of dust concentration on the quality of collected images.

[0009] Furthermore, the process of obtaining the noise data time series diagram by the industrial robot data processing module includes: The digital signal carrying noise data is input into the computer, and the computer decodes and converts the format of the received digital signal. According to the characteristics of the noise data and its application scenarios, the noise threshold is set by computer using the average and standard deviation of the historical noise data, and a two-dimensional coordinate system is established with time on the horizontal axis and noise data on the vertical axis. The noise data obtained by computer processing is mapped to the coordinate system, and the distribution of the noise threshold in the time series is plotted with a red line parallel to the horizontal axis to obtain a time series graph of the noise data.

[0010] Furthermore, the industrial robot data analysis module analyzes the influence of light intensity on image information through a two-dimensional coordinate graph; uses a dust concentration report to analyze its influence on image clarity; and uses a noise time series graph to analyze the influence of noise on machine vision and industrial robot data transmission. The process includes: Through the two-dimensional coordinate diagram of light intensity, when the light intensity distribution is within the appropriate range of light intensity, the visual device collects normal images; when the light intensity is lower than the critical value of insufficient light and higher than the critical value of overexposure, the visual device collects abnormal images; Using the report on the impact of dust concentration on the quality of collected images, when the dust concentration reaches the index that affects the collection work of the visual device, the image generated by the visual device has high definition and the collected information is displayed normally; on the contrary, the visual device is blocked by dust, the image of the visual device has low definition and the collected information cannot be displayed normally; A noise data time series diagram is used to compare the actual noise data with the noise threshold in real time. When the noise data is lower than the threshold, normal data transmission between the machine vision device and the industrial robot is carried out; when the noise data is higher than the threshold, data transmission between the machine vision device and the industrial robot is interfered.

[0011] Furthermore, the process of the industrial robot early warning module receiving the abnormal signal and feeding it back to the client includes: By receiving abnormal light intensity data, abnormal dust concentration data and abnormal noise data, the abnormal feedback data is transmitted to the client for intervention and processing.

[0012] Beneficial effects of the present invention: Compared with the traditional industrial robot data processing system, the machine vision industrial robot data processing system of the present invention integrates sensors, light intensity detectors and big data processing technology to achieve the monitoring of the light intensity and dust concentration of the machine vision equipment environment and the data transmission between the machine vision equipment and the industrial robot. The system can accurately capture light intensity data, dust concentration data and noise data, wherein the light intensity data monitors the brightness of the machine vision equipment collection environment, solving the problem of image quality caused by changes in brightness due to the ambient light intensity; monitors the dust concentration data attached to the machine vision equipment, and timely uploads the anomaly to the client for intervention processing, solving the problem of attached dust blocking the normal collection work of the machine vision equipment; real-time monitoring of noise data solves the problem of data transmission between the visual equipment and the industrial robot being destroyed by noise interference, and has the ability to automatically identify the system operation status and potential defects, and sends out early warning signals in the shortest time to notify maintenance personnel to take corresponding measures to ensure that it operates in a safe, stable and efficient state. The development and application of this system significantly enhances the emergency response efficiency and fault handling capabilities of the machine vision industrial robot data processing system during operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 This is a block diagram of an industrial robot data processing system based on machine vision. DETAILED DESCRIPTION

[0014] 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.

[0015] like Figure 1 As shown, the present invention provides a technical solution: an industrial robot data processing system based on machine vision, including an industrial robot data acquisition module, an industrial robot data processing module, an industrial robot data analysis module and an industrial robot early warning module; The industrial robot data acquisition module obtains the image information and light intensity data collected by the visual device in real time through the light intensity detector installed in the camera; obtains the dust concentration data attached to the machine vision device through the dust particle sensor; and uses the noise sensor to obtain the digital signal carrying the noise data; The industrial robot data processing module uses the collected light intensity data, the corresponding image information and the algorithm to obtain the dynamic light intensity range suitable for visual acquisition and the two-dimensional coordinate diagram of the light intensity; through the dust concentration data attached to the machine vision equipment, according to the deep learning algorithm, obtain the report on the impact of dust concentration on the quality of the collected image; according to the digital signal carrying noise data, obtain the time series diagram of noise data; The industrial robot data analysis module analyzes the impact of light intensity on image information through a two-dimensional coordinate graph; uses dust concentration reports to analyze its impact on image clarity; and uses noise time series graphs to analyze the impact of noise on machine vision and industrial robot data transmission; The industrial robot early warning module receives abnormal signals and feeds them back to the client.

[0016] The industrial robot data acquisition module obtains the image information and light intensity data collected by the visual device in real time, including the following process: Using the camera, photoelectric conversion technology and image processing technology of the visual device, a digital signal carrying image data is obtained, and the digital signal is output to a computer display to obtain image information collected by the visual device in real time; The light intensity detector on the visual device has a built-in photoresistor and ADC analog-to-digital converter. According to the photoelectric effect, when the light in the machine vision device environment shines on the photoresistor, the photoresistor obtains an electrical signal carrying light intensity data, and converts the electrical signal into a digital signal carrying light intensity data through the ADC analog-to-digital converter. The light intensity detector converts the digital signal into light intensity based on the characteristics of the photoresistor and calibration data, and obtains real-time light intensity data.

[0017] The process of industrial robot data acquisition module to obtain dust concentration data attached to machine vision equipment includes: According to the principle of light scattering, when light shines on dust particles, a light pulse signal is generated. The photodetector built into the dust particle sensor receives the light pulse signal and converts it into an electrical pulse signal. The greater the intensity of the electrical pulse signal, the greater the corresponding dust concentration. The dust particle sensor obtains the dust concentration data attached to the machine vision device based on the intensity of the electrical pulse signal, and then obtains the image information corresponding to the dust concentration collection moment through the visual acquisition device.

[0018] The process of obtaining digital signals carrying noise data in the industrial robot data acquisition module includes: The noise sensor has a built-in capacitive electret microphone. When sound waves act on the electret film inside the microphone, the film vibrates and changes the capacitance value of the capacitor inside the microphone. Since the capacitance on the electret remains constant, the change in capacitance value will cause the voltage value across the capacitor to change, and the voltage value carrying noise data is obtained. The voltage signal is amplified and filtered, and then converted into a digital signal to obtain a digital signal carrying noise data.

[0019] The process of obtaining the two-dimensional coordinate diagram of light intensity in the industrial robot data processing module includes: The exposure condition of the operating environment of the visual device is obtained according to the real-time image information, the light intensity and its exposure condition corresponding to the real-time image information are selected, and a decision tree is independently constructed in the training data set through the random forest algorithm, and a training data set containing insufficient light and overexposure is independently constructed, and then samples are randomly selected from the training data set through sampling, and the randomly selected sample data are summarized, and the critical value of the light intensity of insufficient light and the critical value of the light intensity of overexposure in the sample are extracted by using the anomaly detection algorithm, and the critical value of the light intensity of insufficient light and the critical value of the light intensity of overexposure in the sample are respectively set as the lower threshold and the upper threshold of the light intensity, and the threshold range is adjusted according to the dynamic change of the data, and a two-dimensional coordinate system is constructed, in which the horizontal axis represents time and the vertical axis represents light intensity, the dynamic critical value range is mapped to the coordinate system in real time, and then the light intensity data is mapped to the coordinate system to obtain a two-dimensional coordinate graph of the light intensity data.

[0020] The process of obtaining a report on the impact of dust concentration on the quality of collected images in the industrial robot data processing module includes: Using deep learning algorithm, the MLP network structure is selected, and the dust concentration data attached to the machine vision equipment is converted into a format suitable for MLP network input. Image enhancement, filtering and edge detection are performed on the image information collected at the same time as the dust concentration. A neural network model of input layer, hidden layer and output layer is constructed. The preprocessed dust concentration data and its image information are used as input, the nonlinear characteristics of the dust data are extracted from the hidden layer and the nonlinear factors are introduced through the activation function. The MLP network is trained to obtain an MLP network that can judge the impact of dust concentration on image quality. The output layer outputs the impact of dust concentration on the quality of images collected by the visual device. The trained MLP model is evaluated using the test set data, and it is adjusted and optimized according to the evaluation results to obtain a report on the impact of dust concentration on the quality of images collected by the visual device.

[0021] Industrial robot data processing module, the process of obtaining the noise data time series graph includes: The digital signal carrying noise data is input into the computer, and the computer decodes and converts the format of the received digital signal. According to the characteristics of the noise data and its application scenarios, the noise threshold is set by computer using the average and standard deviation of the historical noise data, and a two-dimensional coordinate system is established with time on the horizontal axis and noise data on the vertical axis. The noise data obtained by computer processing is mapped to the coordinate system, and the distribution of the noise threshold in the time series is plotted with a red line parallel to the horizontal axis to obtain a time series graph of the noise data.

[0022] The industrial robot data analysis module analyzes the impact of light intensity on image information through a two-dimensional coordinate graph; uses dust concentration reports to analyze its impact on image clarity; and uses noise time series graphs to analyze the impact of noise on machine vision and industrial robot data transmission. The process includes: Through the two-dimensional coordinate diagram of light intensity, when the light intensity distribution is within the appropriate range of light intensity, the visual device collects normal images; when the light intensity is lower than the critical value of insufficient light and higher than the critical value of overexposure, the visual device collects abnormal images; Using the report on the impact of dust concentration on the quality of collected images, when the dust concentration reaches the index that affects the collection work of the visual device, the image generated by the visual device has high definition and the collected information is displayed normally; on the contrary, the visual device is blocked by dust, the image of the visual device has low definition and the collected information cannot be displayed normally; A noise data time series diagram is used to compare the actual noise data with the noise threshold in real time. When the noise data is lower than the threshold, normal data transmission between the machine vision device and the industrial robot is carried out; when the noise data is higher than the threshold, data transmission between the machine vision device and the industrial robot is interfered.

[0023] The process of the industrial robot early warning module receiving abnormal signals and feeding them back to the client includes: By receiving abnormal light intensity data, abnormal dust concentration data and abnormal noise data, the abnormal feedback data is transmitted to the client for intervention and processing.

[0024] Before starting the industrial robot data processing system, ensure that the machine vision equipment is correctly connected to the industrial robot and its data processing system to ensure that the collected data is correct. According to the actual application scenario, the system collects light intensity data, dust concentration data and noise data of the industrial robot's working environment. Combined with the image information corresponding to the time of data collection, the threshold of the above data is obtained through algorithm training, and the collected data is feature extracted and analyzed. The collection work of the visual equipment is monitored in real time, and the abnormalities are promptly fed back to the client through the system for intervention and processing.

[0025] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. An industrial robot data processing system based on machine vision, comprising an industrial robot data acquisition module, an industrial robot data processing module, an industrial robot data analysis module and an industrial robot early warning module, characterized in that: The industrial robot data acquisition module obtains the image information and light intensity data collected by the visual device in real time according to the light intensity detector carried by the camera; obtains the dust concentration data attached to the machine vision device through the dust particle sensor; and uses the noise sensor to obtain the digital signal carrying the noise data; The industrial robot data processing module uses the collected light intensity data, the corresponding moment image information and the algorithm to obtain a dynamic light intensity range suitable for visual acquisition and a two-dimensional coordinate diagram of the light intensity; obtains a report on the impact of dust concentration on the quality of the collected image based on the dust concentration data attached to the machine vision device and the deep learning algorithm; obtains a noise data time series diagram based on the digital signal carrying the noise data; The industrial robot data analysis module analyzes the effect of light intensity on image information through a two-dimensional coordinate graph; and uses a dust concentration report to analyze its effect on image clarity; The noise time series diagram is used to analyze the impact of noise on machine vision and industrial robot data transmission; The industrial robot early warning module receives abnormal signals and feeds them back to the client.

2. The industrial robot data processing system based on machine vision according to claim 1, characterized in that: The process of the industrial robot data acquisition module acquiring the image information and light intensity data collected by the visual device in real time includes: Using the camera, photoelectric conversion technology and image processing technology of the visual device, a digital signal carrying image data is obtained, and the digital signal is output to a computer display to obtain image information collected by the visual device in real time; The light intensity detector on the visual device has a built-in photoresistor and ADC analog-to-digital converter. According to the photoelectric effect, when the light in the machine vision device environment shines on the photoresistor, the photoresistor obtains an electrical signal carrying light intensity data, and converts the electrical signal into a digital signal carrying light intensity data through the ADC analog-to-digital converter. The light intensity detector converts the digital signal into light intensity based on the characteristics of the photoresistor and calibration data, and obtains real-time light intensity data.

3. The machine vision-based industrial robot data processing system according to claim 2, characterized in that: The process of the industrial robot data acquisition module acquiring dust concentration data attached to the machine vision device includes: According to the principle of light scattering, when light shines on dust particles, a light pulse signal is generated. The photodetector built into the dust particle sensor receives the light pulse signal and converts it into an electrical pulse signal. The greater the intensity of the electrical pulse signal, the greater the corresponding dust concentration. The dust particle sensor obtains the dust concentration data attached to the machine vision device based on the intensity of the electrical pulse signal, and then obtains the image information corresponding to the dust concentration collection moment through the visual acquisition device.

4. The machine vision-based industrial robot data processing system according to claim 3, characterized in that: The process of the industrial robot data acquisition module acquiring a digital signal carrying noise data includes: The noise sensor has a built-in capacitive electret microphone. When sound waves act on the electret film inside the microphone, the film vibrates and changes the capacitance value of the capacitor inside the microphone. Since the capacitance on the electret remains constant, the change in capacitance value will cause the voltage value across the capacitor to change, and the voltage value carrying noise data is obtained. The voltage signal is amplified and filtered, and then converted into a digital signal to obtain a digital signal carrying noise data.

5. The machine vision-based industrial robot data processing system according to claim 4, characterized in that: The process of obtaining the two-dimensional coordinate diagram of light intensity by the industrial robot data processing module includes: The exposure condition of the operating environment of the visual device is obtained according to the real-time image information, the light intensity and its exposure condition corresponding to the real-time image information are selected, and a decision tree is independently constructed in the training data set through the random forest algorithm, and a training data set containing insufficient light and overexposure is independently constructed, and then samples are randomly selected from the training data set through sampling, and the randomly selected sample data are summarized, and the critical value of the light intensity of insufficient light and the critical value of the light intensity of overexposure in the sample are extracted by using the anomaly detection algorithm, and the critical value of the light intensity of insufficient light and the critical value of the light intensity of overexposure in the sample are respectively set as the lower threshold and the upper threshold of the light intensity, and the threshold range is adjusted according to the dynamic change of the data, and a two-dimensional coordinate system is constructed, in which the horizontal axis represents time and the vertical axis represents light intensity, the dynamic critical value range is mapped to the coordinate system in real time, and then the light intensity data is mapped to the coordinate system to obtain a two-dimensional coordinate graph of the light intensity data.

6. The machine vision-based industrial robot data processing system according to claim 5, characterized in that: The process of obtaining the report on the influence of dust concentration on the quality of collected images by the industrial robot data processing module includes: Using deep learning algorithm, the MLP network structure is selected, and the dust concentration data attached to the machine vision equipment is converted into a format suitable for MLP network input. Image enhancement, filtering and edge detection are performed on the image information collected at the same time as the dust concentration. A neural network model of input layer, hidden layer and output layer is constructed. The preprocessed dust concentration data and its image information are used as input, the nonlinear characteristics of the dust data are extracted from the hidden layer and the nonlinear factors are introduced through the activation function. The MLP network is trained to obtain an MLP network that can judge the impact of dust concentration on image quality. The output layer outputs the impact of dust concentration on the quality of images collected by the visual device. The trained MLP model is evaluated using the test set data, and it is adjusted and optimized according to the evaluation results to obtain a report on the impact of dust concentration on the quality of collected images.

7. The machine vision-based industrial robot data processing system according to claim 6, characterized in that: The process of obtaining the noise data time series diagram by the industrial robot data processing module includes: The digital signal carrying noise data is input into the computer, and the computer decodes and converts the format of the received digital signal. According to the characteristics of the noise data and its application scenarios, the noise threshold is set by computer using the average and standard deviation of the historical noise data, and a two-dimensional coordinate system is established with time on the horizontal axis and noise data on the vertical axis. The noise data obtained by computer processing is mapped to the coordinate system, and the distribution of the noise threshold in the time series is plotted with a red line parallel to the horizontal axis to obtain a time series graph of the noise data.

8. The machine vision-based industrial robot data processing system according to claim 7, characterized in that: The industrial robot data analysis module analyzes the effect of light intensity on image information through a two-dimensional coordinate graph; and uses a dust concentration report to analyze its effect on image clarity; The process of using noise time series graphs to analyze the impact of noise on machine vision and industrial robot data transmission includes: Through the two-dimensional coordinate diagram of light intensity, when the light intensity distribution is within the appropriate range of light intensity, the visual device collects a normal image; When the light intensity is lower than the critical value of insufficient light and higher than the critical value of overexposure, the visual device captures an abnormal image; Using the report on the impact of dust concentration on the quality of collected images, when the dust concentration reaches the index that affects the collection work of the visual device, the image generated by the visual device has high definition and the collected information is displayed normally; on the contrary, the visual device is blocked by dust, the image of the visual device has low definition and the collected information cannot be displayed normally; A noise data time series diagram is used to compare the actual noise data with the noise threshold in real time. When the noise data is lower than the threshold, normal data transmission between the machine vision device and the industrial robot is carried out; when the noise data is higher than the threshold, data transmission between the machine vision device and the industrial robot is interfered.

9. The machine vision-based industrial robot data processing system according to claim 8, characterized in that: The process of the industrial robot early warning module receiving abnormal signals and feeding them back to the client includes: By receiving abnormal light intensity data, abnormal dust concentration data and abnormal noise data, the abnormal feedback data is transmitted to the client for intervention and processing.

Images