An industrial intelligent robot

Abstract

The present invention discloses an industrial intelligent robot, which relates to the technical field of image recognition in bearing processing. Through an image acquisition module, on the basis of no occlusion and covering the entire bearing processing area, image data of the bearing processing area is collected and preliminarily extracted, and key features in the image data are collected and preliminarily extracted. Based on the image data collection and preliminary extraction of the image acquisition module, and through an image adjustment and processing module, the adjusted processing parameters are transmitted to the industrial intelligent robot to perform the adjustment operation in the bearing processing direction. The image data is uploaded to the control system terminal of the industrial intelligent robot. Through the mutual cooperation of three algorithm units, in terms of improving processing accuracy, enhancing processing efficiency, strengthening the intelligent level, and promoting independent development, through measures such as introducing advanced technologies, optimizing the processing process, strengthening technology research and development and innovation, the continuous progress and development of the bearing processing technology of industrial intelligent robots are promoted.

Description

Technical Field

[0001] The present invention relates to the technical field of image recognition in bearing processing, and particularly to an industrial intelligent robot. Background Art

[0002] With the transformation and upgrading and intelligent development of the manufacturing industry, industrial intelligent robots play an increasingly important role on the production line. As one of the key components of industrial robots, the processing quality and accuracy of bearings directly affect the overall performance and lifespan of the robots. Therefore, the bearing processing technology of industrial intelligent robots has become a research hotspot in the manufacturing field. In the field of bearing processing of industrial intelligent robots, image recognition technology is gradually becoming the key means to improve processing accuracy and efficiency. Through high-precision image acquisition and intelligent analysis, the robot can more accurately identify various features in the bearing processing process, thereby optimizing processing parameters and improving processing quality.

[0003] When traditional image recognition methods process complex and variable bearing processing images, it is often difficult to accurately extract key features, resulting in limited recognition accuracy, which in turn affects the setting and adjustment of processing parameters. Moreover, due to the lack of an effective mapping relationship between image features and processing parameters, the prior art often has difficulty accurately adjusting processing parameters according to the image recognition results, resulting in unstable processing effects and difficulty in meeting the processing requirements of high-precision bearings. During the processing process, the prior art often lacks a real-time and effective feedback adjustment mechanism and cannot adjust processing parameters in real time according to the processing effects, resulting in the accumulation of processing errors and affecting the quality of the final product. In addition, most traditional processing equipment relies on manual operation and judgment, lacks intelligent control, and cannot make full use of the advantages of image recognition technology to achieve the automation and intelligence of the processing process. Summary of the Invention

[0004] The purpose of the present invention is to provide an industrial intelligent robot to solve the problems raised in the above background art.

[0005] To achieve the above purpose, the present invention provides the following technical solution, which is applied to image processing in bearing processing;

[0006] It includes an image acquisition module and an image adjustment and processing module;

[0007] The specific implementation steps are as follows:

[0008] Data acquisition: Through the image acquisition module, on the basis of no occlusion and covering the entire bearing processing area, image data of the bearing processing area is collected and preliminarily extracted, and key features in the image data are collected and preliminarily extracted. The key features include area ratio and edge complexity;

[0009] Data adjustment processing, based on the image data acquisition and preliminary extraction of the image acquisition module, and through the image adjustment processing module, the adjusted processing parameters are transmitted to the industrial intelligent robot to perform the adjustment operation of the bearing processing direction. The image adjustment processing module includes an image feature preliminary extraction processing unit, a fine processing parameter adjustment unit, and an image intelligent adjustment and optimization unit;

[0010] Data upload, uploading the image data to the terminal of the industrial intelligent robot control system;

[0011] The equipment used by the image acquisition module includes an industrial camera for acquiring image data of the bearing processing area;

[0012] The equipment used by the image adjustment processing module includes an image processing workstation and a sensor. The image processing workstation uses image processing algorithms and machine learning models to perform image adjustment processing. The sensor monitors the real-time data during the bearing processing, including cutting force and temperature.

[0013] Optionally, the calculation formula of the image feature preliminary extraction processing unit is as follows:

[0014] ;

[0015] MB = MM / ZM;

[0016] Y = TY / MY;

[0017] Where:

[0018] TC is the image feature value;

[0019] MB is the image area ratio, MM is the number of extracted image areas, and ZM is the total number of image areas;

[0020] BF is the edge complexity value, and BF reflects the complexity of the image edge within the number of extracted image areas MM;

[0021] Y is the color contrast value;

[0022] TY is the extracted image color value, and TY reflects the color presentation degree of the image within the number of extracted image areas MM;

[0023] MY is the image color value, and MY reflects the overall image background presentation degree within the total number of image areas ZM;

[0024] L is the image brightness value;

[0025] The extraction process of the image feature preliminary extraction processing unit is as follows:

[0026] Through the image acquisition module, key features including the image area ratio MB, the edge complexity value BF, the color contrast value Y, and the image brightness value L are collected and preliminarily extracted. After being input into the image feature preliminary extraction processing unit for processing, an image feature value TC for evaluating the significance and comprehensive quality of the bearing processing area in the image data is output.

[0027] Optionally, the calculation formula of the fine machining parameter adjustment unit is as follows:

[0028] ;

[0029] Where:

[0030] TZ is the adjusted fine parameter value, including cutting speed and feed rate;

[0031] BJ is the standard machining parameter value;

[0032] a is a natural number, 1 + a -TC*Y reflects the change in the sensitivity of the adjusted fine parameter value TZ as the image feature value TC changes;

[0033] The adjustment process of the fine machining parameter adjustment unit is as follows:

[0034] Based on the image feature value TC output by the image feature preliminary extraction processing unit, combined with the standard machining parameter value BJ, and the change in the sensitivity of the adjusted fine parameter value TZ as the image feature value TC changes, the adjusted fine parameter value TZ suitable for the current image feature is output.

[0035] Optionally, the calculation formula of the image intelligent adjustment and optimization unit is as follows:

[0036] ;

[0037] Where:

[0038] MB new is the adjusted image area ratio;

[0039] b is the adjustment factor;

[0040] BTZ is the target fine parameter value;

[0041] acts on the feedback adjustment of the image area ratio MB;

[0042] The adjustment and optimization process of the image intelligent adjustment and optimization unit is as follows:

[0043] Based on the image feature value TC output by the image feature preliminary extraction processing unit and the adjusted fine parameter value TZ output by the fine processing parameter adjustment unit, and combined with the target fine parameter value BTZ, the adjustment factor b is adjusted to output the adjusted image area ratio MB that affects the next intelligent robot processing direction recognition. new .

[0044] Optionally, based on the adjusted image area ratio MB output by the image intelligent adjustment optimization unit new The recognition adjustment is as follows:

[0045] The adjusted image area ratio MB output by the image intelligent adjustment optimization unit at any time new , are used as the input value in the next image feature preliminary extraction processing unit, that is, the image area ratio MB. In other words, the adjusted image area ratio MB outputted this time new , replacing the image area ratio MB input next time, and performing iterative processing, so as to continuously identify the adjusted image area ratio MB, so as to enable the industrial robot to identify and process the bearing processing area direction.

[0046] Optionally, the adjusted image area ratio MB new The control and response of the adjustment range are as follows:

[0047] S1. Set MB max is the maximum ratio of image area, and sets MB min is the minimum ratio of image area;

[0048] S2, if the image area maximum ratio MB max Greater than the adjusted image area ratio MB new Greater than the minimum image area ratio MB min , then it is considered that the adjusted image area ratio MB new If the system is in a safe adjustment range, it should be maintained and adjusted iteratively;

[0049] S3, if the adjusted image area ratio MB new Greater than the maximum image area ratio MB max , if the adjusted image area ratio MB new Smaller than the minimum image area ratio MB min Regardless of the above situation, the adjusted image area ratio MB new When in a dangerous adjustment range, the sensor monitors and issues a warning, stops adjustment, and takes action.

[0050] Optionally, the edge complexity value BF specifically uses an edge detection algorithm, including Canny and SOBEL, to identify edges in the image data, and detects edges by calculating the gradient intensity and direction of pixel points in the image data and their neighboring pixel points. Features are extracted from the detected edges, including the number, length, curvature, and direction of the edges. These features are used to quantify the complexity of the edges, and an algorithm including weighted summation and principal component analysis is used to output the edge complexity value BF.

[0051] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0052] First, by introducing advanced image recognition algorithms and deep learning technologies, and combining with the preliminary image feature extraction and processing unit, the present invention can more accurately extract key features in the bearing processing image, such as area ratio, edge complexity, color contrast, and brightness level, providing a reliable basis for setting and adjusting processing parameters, thereby improving the image recognition accuracy.

[0053] Second, based on the calculation of the fine processing parameter adjustment unit, the present invention combines the image recognition result with the preset processing parameter standard, and obtains the optimal processing parameters through fine calculation, realizing the precise adjustment of processing parameters, and improving the processing accuracy and stability.

[0054] Third, the present invention introduces a feedback adjustment mechanism through the image intelligent adjustment and optimization unit. According to the deviation between the real-time processing effect and the expected target, the area ratio and other key parameters are dynamically adjusted to form a closed-loop control, ensuring that the processing process always remains in the optimal state.

[0055] Fourth, by combining the image recognition technology with the industrial intelligent robot, the present invention realizes the automatic and intelligent control of the processing process. The robot can independently complete the processing task according to the image recognition result and the processing parameter adjustment algorithm, reducing manual intervention, improving production efficiency and product quality, and enhancing the intelligent level. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 is the method flow chart of this industrial intelligent robot;

[0057] Figure 2 is the structural schematic diagram of the image processing module of this;

[0058] Figure 3 is the equipment schematic diagram of the image acquisition module of the present invention;

[0059] Figure 4 is the equipment schematic diagram of the image processing module of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0060] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0061] Regarding the identification of the processing direction of this industrial intelligent robot, it is different from the existing identification of the processing direction of industrial intelligent robots. In the existing processing direction identification, it is often difficult to accurately extract key features, resulting in limited identification accuracy, which in turn affects the setting and adjustment of processing parameters. Moreover, due to the lack of an effective mapping relationship between image features and processing parameters, it is often difficult for the existing technology to accurately adjust processing parameters according to the image recognition results, resulting in unstable processing effects and difficulty in meeting the processing requirements of high-precision bearings. During the processing process, the existing technology often lacks a real-time and effective feedback adjustment mechanism and cannot adjust processing parameters in real time according to the processing effects, resulting in the accumulation of processing errors and affecting the quality of the final product. In addition, most traditional processing equipment relies on manual operation and judgment, lacks intelligent control, and cannot make full use of the advantages of image recognition technology to achieve the automation and intelligence of the processing process. And this algorithm unit reflects in improving processing accuracy, enhancing processing efficiency, strengthening the intelligent level, and promoting independent development. By introducing advanced technologies, optimizing processing processes, strengthening technology research and development and innovation measures, it can effectively solve the deficiencies of the existing technology and promote the continuous progress and development of the bearing processing technology of industrial intelligent robots.

[0062] For the embodiment, please refer to Figures 1 to 4 , this embodiment provides an industrial intelligent robot applied to image processing in bearing processing;

[0063] It includes an image acquisition module and an image adjustment and processing module;

[0064] The specific implementation steps are as follows:

[0065] Data acquisition: Through the image acquisition module, and on the basis of no occlusion and covering the entire bearing processing area, image data of the bearing processing area is collected and preliminarily extracted, and the key features in the image data are collected and preliminarily extracted. The key features include area ratio and edge complexity;

[0066] Data adjustment and processing: Based on the image data acquisition and preliminary extraction of the image acquisition module, and through the image adjustment and processing module, the adjusted processing parameters are transmitted to the industrial intelligent robot to perform the adjustment operation of the bearing processing direction. The image adjustment and processing module includes an image feature preliminary extraction and processing unit, a fine processing parameter adjustment unit, and an image intelligent adjustment and optimization unit;

[0067] Data upload: Upload the image data to the terminal of the industrial intelligent robot control system;

[0068] The equipment used in the image acquisition module includes an industrial camera for collecting image data of the bearing processing area;

[0069] The equipment used in the image adjustment and processing module includes an image processing workstation and sensors. The image processing workstation uses image processing algorithms and machine learning models to perform image adjustment and processing. The sensors monitor real-time data during the bearing processing, including cutting force and temperature.

[0070] In this embodiment, through the mutual cooperation of three algorithm units, when the industrial intelligent robot is applied to the recognition of the bearing processing direction, combining the TC, TZ, and MB new The three operation results together constitute the core part of the intelligent processing control system, realizing the intelligence, adaptability, and continuous optimization of the processing process. TC is the image feature value. By combining the area ratio, edge complexity, color contrast, and brightness level, a comprehensive image feature value is calculated to evaluate the significance and quality of the bearing processing area in the image, providing a basis for subsequent adjustment of processing parameters. TZ is the fine parameter value after adjustment. By non-linearly combining the image feature value TC, the standard processing parameter value BJ, and the image area ratio MB, and considering the non-linear influence of color contrast on the adjustment amplitude, the fine processing parameters suitable for the current image features are calculated to meet different processing requirements. MB new is the adjusted image area ratio value. By comparing the difference between the current fine processing parameters and the target parameters, and combining the square root of the image feature value TC as the adjustment weight, the area ratio is feedback-adjusted. This adjustment can affect the results of the next image recognition and processing, forming a closed-loop optimization system. And the calculation result of MB new can also affect the calculations feedback to TC and TZ, and iteratively calculate the image area ratio MB, making the three algorithms of this system have high relevance and entanglement, enabling the overall algorithm system to perform automated feedback and optimization according to the actual situation to be closer to reality.

[0071] Please refer to Figures 1 to 4 , the calculation formula of the image feature preliminary extraction and processing unit is as follows:

[0072] ;

[0073] MB = MM / ZM;

[0074] Y = TY / MY;

[0075] Where:

[0076] TC is the image feature value;

[0077] MB is the image area ratio, MM is the number of extracted image areas, and ZM is the total number of image areas;

[0078] BF is the edge complexity value, and BF reflects the complexity of the image edges within the number of extracted image areas MM;

[0079] Y is the color contrast value;

[0080] TY is the color value of the extracted image, and TY reflects the color presentation degree of the image within the number of extracted image areas MM;

[0081] MY is the image color value, and MY reflects the overall image background presentation degree within the total number of image areas ZM;

[0082] L is the image brightness value;

[0083] The extraction and processing process of the image feature preliminary extraction processing unit is as follows:

[0084] Through the image acquisition module, key features including the image area ratio MB, edge complexity value BF, color contrast value Y, and image brightness value L are collected and preliminarily extracted. After being input into the image feature preliminary extraction processing unit for processing, an image feature value TC for evaluating the significance and comprehensive quality of the bearing processing area in the image data is output.

[0085] In this embodiment: First, in this algorithm unit, MB is the image area ratio. Through the image processing algorithm, the number of extracted image areas MM and the total number of image areas ZM are identified, and using MB = MM / ZM, the image area ratio MB is output, which is the initial image feature area. The image area ratio MB reflects the significance of the bearing processing area in the image and is an important indicator for evaluating the position and size of the processing area. Then, the edge detection algorithm is used to identify the edges of the bearing processing area, and based on the number, length, and curvature features of the edges, the edge complexity value BF is calculated and output. The edge complexity value BF measures the complexity of the processing area edges and helps to identify edge details, which is of great significance for accurately controlling the processing path and depth. Y is the color contrast value, which is obtained from the contrast difference between the color value TY of the extracted image and the image color value MY. L is the image brightness value, which is obtained by calculating the average brightness value of the image, that is, the statistical information of the brightness histogram. The color contrast value Y and the image brightness value L consider the color and brightness information of the image, which helps to distinguish the target from the background and improve the accuracy of image recognition. With the input of multiple feature image data, the image feature value TC that provides a comprehensive basis for the subsequent adjustment of processing parameters can be output;

[0086] This algorithm unit enables industrial intelligent robots to more accurately identify the bearing processing area by precisely calculating the area ratio and edge complexity, reducing the possibilities of misidentification and missed identification, improving the identification accuracy. Moreover, the consideration of color contrast and brightness level enables industrial intelligent robots to adapt to the processing environment under different lighting conditions, enhancing the robustness of the system and its adaptability. The calculation of the preliminary image feature value TC provides an important basis for the fine-tuning of subsequent processing parameters, contributing to the intelligent control of the processing process.

[0087] Please refer to Figures 1 to 4 , and the calculation formula of the fine processing parameter adjustment unit is as follows:

[0088] ;

[0089] Where:

[0090] TZ is the adjusted fine parameter value, including cutting speed and feed rate;

[0091] BJ is the standard processing parameter value;

[0092] a is a natural number, 1 + a -TC*Y reflects the change in the sensitivity of the adjusted fine parameter value TZ to adjustment as the image feature value TC changes;

[0093] The adjustment process of the fine processing parameter adjustment unit is as follows:

[0094] Based on the image feature value TC output by the preliminary image feature extraction and processing unit, combined with the standard processing parameter value BJ, and the change in the sensitivity of the adjusted fine parameter value TZ to adjustment as the image feature value TC changes, the adjusted fine parameter value TZ suitable for the current image feature is output.

[0095] In this embodiment, first, TZ is the adjusted fine parameter value, which directly affects the processing quality and efficiency of the bearing. By comprehensively considering the image feature value TC, the standard processing parameter value BJ, and the image area ratio MB, the adjusted fine parameter value TZ can more accurately adapt to the current processing conditions, improving the processing accuracy and efficiency. Among them, the natural number a is used to introduce a non-linear relationship, such that when the image feature value TC increases, the adjustment of the adjusted fine parameter value TZ becomes more sensitive. This non-linear relationship helps to better adapt to different image features. Specifically, the exponential function of the natural number a makes the adjustment amplitude of the adjusted fine parameter value TZ larger when the image feature value TC increases, contributing to more precise processing control when the image features are significant;

[0096] By comprehensively considering multiple image features and standard parameters, the adjustment of the refined parameter value TZ after adjustment can more accurately match the actual processing requirements, thereby improving processing accuracy and consistency. While ensuring processing accuracy, by adjusting processing parameters such as cutting speed and feed rate, the processing process can be optimized and processing efficiency can be improved. The non-linear relationship introduced by the exponential function of the natural number a makes the adjustment of the refined parameter value TZ after adjustment more flexible and sensitive, which helps to cope with complex processing scenarios and changes and enhances system flexibility.

[0097] Please refer to Figures 1 to 4 , the calculation formula of the image intelligent adjustment and optimization unit is as follows:

[0098] ;

[0099] Where:

[0100] MB new is the ratio of the adjusted image area;

[0101] b is the adjustment factor;

[0102] BTZ is the target refined parameter value;

[0103] acts on the feedback adjustment of the image area ratio MB;

[0104] The adjustment and optimization process of the image intelligent adjustment and optimization unit is as follows:

[0105] Based on the image feature value TC output by the image feature preliminary extraction and processing unit and the adjusted refined parameter value TZ output by the fine processing parameter adjustment unit, combined with the target refined parameter value BTZ, and adjusted by the adjustment factor b, the adjusted image area ratio MB that affects the next intelligent robot processing direction recognition is output new .

[0106] In this embodiment, the algorithm unit first outputs the adjusted image area ratio MB based on the image feature value TC output by the image feature preliminary extraction and processing unit and the adjusted refined parameter value TZ output by the fine processing parameter adjustment unit new , the adjusted image area ratio MB new is used for the next iteration and processing cycle. It is adjusted based on the differences between the image area ratio MB, the adjustment factor b, the adjusted refined parameter value TZ and the target refined parameter value BTZ, as well as the square root of the image feature value TC. This adjustment method takes into account the deviation of processing parameters and the importance of image features, aiming to improve the subsequent image recognition and processing process by iteratively optimizing the area ratio;

[0107] In the processing of bearings for industrial intelligent robots, the adjusted image area ratio MB new represents the area ratio of the target region optimized based on the current image features and processing parameters. Its significance in entering the next iteration of the image feature preliminary extraction processing unit is that by continuously adjusting the area ratio, the industrial intelligent robot can more accurately identify and process the bearing processing region, thereby improving the processing accuracy and efficiency. This cyclic feedback mechanism helps to achieve the adaptive optimization of the processing process.

[0108] Please refer to Figures 1 to 4 , for the recognition and adjustment of the adjusted image area ratio MB new output by the image intelligent adjustment and optimization unit as follows:

[0109] Any adjusted image area ratio MB new output by the image intelligent adjustment and optimization unit is used as the input value in the next image feature preliminary extraction processing unit, that is, the image area ratio MB. In other words, the adjusted image area ratio MB new output this time replaces the image area ratio MB input next time for iterative processing, so as to continuously identify and adjust the image area ratio MB to enable the industrial robot to identify and process the bearing processing region direction;

[0110] The control and response of the adjustment range of the adjusted image area ratio MB new are as follows:

[0111] S1. Set MB max as the maximum image area ratio, and set MB min as the minimum image area ratio;

[0112] S2. If the maximum image area ratio MB max is greater than the adjusted image area ratio MB new which is greater than the minimum image area ratio MB min , it is considered that the adjusted image area ratio MB new is within the safe adjustment range, and keep and continuously iteratively adjust;

[0113] S3. If the adjusted image area ratio MB new is greater than the maximum image area ratio MB max , or if the adjusted image area ratio MB new is less than the minimum image area ratio MB min , in either of the above cases, it is considered that the adjusted image area ratio MB new is within the dangerous adjustment range, and the sensor monitors and issues a warning, stops the adjustment and processes it.

[0114] In this embodiment, based on the above, the algorithm unit adjusts the area ratio MB of the adjusted image new which represents the area ratio of the target region optimized based on the current image features and processing parameters, and enters the preliminary image feature extraction processing unit for the next iteration. During the iteration, the adjusted image area ratio MB new the output adjustment range needs to vary within a safe range, which is the maximum image area ratio MB max is greater than the adjusted image area ratio MB new is greater than the minimum image area ratio MB min , if it exceeds or is lower than, for example, the change situation described in S3, the system will take corresponding measures, including sensor monitoring and issuing warnings, stopping adjustment and performing processing, to avoid adverse effects on the processing process. During the actual processing, the processing effect will be evaluated regularly and in real time. If the adjusted image area ratio MB new results in poor processing effects, including decreased processing accuracy and deteriorated surface quality, it is necessary to readjust the threshold range and change the adjustment strategy, and adjust the adjusted image area ratio MB new , it is also necessary to consider the stability and safety of the system. Excessive and large-scale adjustments will cause the system to be unstable and even trigger safety accidents. Therefore, during the adjustment process, certain adjustment step sizes and frequency limits need to be followed to ensure the stability and safety of the system. Specifically, sensors and control systems can be used to monitor key parameters during the processing in real time, including cutting force, temperature, and feedback these parameters to the control system. The control system dynamically adjusts the adjusted image area ratio MB new to achieve precise control of the processing process. This method can improve the adaptive ability and anti-interference ability of the system.

[0115] To sum up, in the specific implementation process, by continuously iteratively adjusting the area ratio, the robot can more accurately identify and process the bearing processing area, reduce processing errors, improve processing accuracy, and the adjusted processing parameters, including cutting speed and feed rate, are more suitable for the current image features, which helps to speed up the processing speed, improve processing efficiency, optimize processing efficiency, and the feedback mechanism enables the system to meet the processing requirements under different image features, enhancing the robustness and adaptability of the system. In addition, by integrating the steps of image recognition, feature extraction, parameter adjustment, and feedback optimization, the industrial intelligent robot can achieve the intelligence of bearing processing, improve the level of production automation and production efficiency, and achieve the effect of intelligent processing.

[0116] Although embodiments of the present invention have been shown and described, it will be understood by those of ordinary skill in the art that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principles and spirit of the present invention, and the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An industrial intelligent robot, characterized in that, Image processing applied to bearing processing; It includes an image acquisition module and an image adjustment and processing module; The specific implementation steps are as follows: Data acquisition: Through the image acquisition module, on the basis of no occlusion and covering the entire bearing processing area, image data of the bearing processing area is acquired and preliminarily extracted, and key features in the image data are acquired and preliminarily extracted. The key features include area ratio and edge complexity; Data adjustment and processing: Based on the image data acquisition and preliminary extraction of the image acquisition module, and through the image adjustment and processing module, the adjusted processing parameters are transmitted to the industrial intelligent robot to perform the adjustment operation in the bearing processing direction. The image adjustment and processing module includes an image feature preliminary extraction and processing unit, a fine processing parameter adjustment unit, and an image intelligent adjustment and optimization unit; Data upload: The image data is uploaded to the terminal of the industrial intelligent robot control system; The calculation formula of the image feature preliminary extraction and processing unit is as follows: ； MB = MM / ZM; Y = TY / MY; Where: TC is the image feature value; MB is the image area ratio value, MM is the extracted image area number, and ZM is the total image area number; BF is the edge complexity value, and BF reflects the complexity of the image edge within the extracted image area number MM; Y is the color contrast value; TY is the extracted image color value, and TY reflects the color presentation degree of the image within the extracted image area number MM; MY is the image color value, and MY reflects the overall image background presentation degree within the total image area number ZM; L is the image brightness value.

2. An industrial intelligent robot according to claim 1, wherein The equipment used in the image acquisition module includes an industrial camera for acquiring image data of the bearing processing area; The equipment used in the image adjustment and processing module includes an image processing workstation and a sensor. The image processing workstation uses image processing algorithms and machine learning models to perform image adjustment and processing. The sensor monitors real-time data during the bearing processing, including cutting force and temperature.

3. An industrial intelligent robot according to claim 2, characterized in that: The calculation formula of the fine processing parameter adjustment unit is as follows: TZ = (TC * (BJ + MB)) / (1 + a -TC*Y ) Where: TZ is the adjusted fine parameter value, including cutting speed and feed rate; BJ is the standard processing parameter value; a is a natural number value, 1 + a -TC*Y It reflects the change in the sensitivity of the adjusted fine parameter value TZ as the image eigenvalue TC changes; The adjustment process of the fine processing parameter adjustment unit is as follows: Based on the image feature value TC output by the image feature preliminary extraction and processing unit, combined with the standard processing parameter value BJ, and the sensitivity change of the adjusted fine parameter value TZ when the image feature value TC changes, the adjusted fine parameter value TZ suitable for the current image feature is output.

4. An industrial intelligent robot according to claim 3, characterized in that: The calculation formula of the image intelligent adjustment and optimization unit is as follows: ； Where: MB new is the adjusted image area ratio; b is the adjustment factor; BTZ is the target fine parameter value; Act on the feedback adjustment of the image area ratio MB; The adjustment and optimization process of the image intelligent adjustment and optimization unit is as follows: Based on the image feature value TC output by the preliminary extraction and processing unit of the image features and the adjusted fine parameter value TZ output by the fine processing parameter adjustment unit, and combined with the target fine parameter value BTZ, after being adjusted by the adjustment factor b, the adjusted image area ratio MB that affects the recognition of the processing direction of the intelligent robot next time is output new 。 5. An industrial intelligent robot according to claim 4, characterized in that: Based on the adjusted image area ratio MB output by the image intelligent adjustment and optimization unit new The recognition and adjustment are as follows: The adjusted image area ratio MB output by any one of the image intelligent adjustment and optimization units new , is used as the input value in the next image feature preliminary extraction and processing unit, that is, the image area ratio MB. In other words, the adjusted image area ratio MB output this time new , replaces the image area ratio MB input next time for iterative processing, so as to continuously identify and adjust the image area ratio MB, enabling the industrial robot to identify and process the bearing processing area direction.

6. An industrial intelligent robot according to claim 5, characterized in that: The adjusted image area ratio MB new The control and response of the adjustment range are as follows: S1. Set MB max as the maximum ratio of the image area, and set MB min as the minimum ratio of the image area; S2. If the maximum ratio MB of the image area max is greater than the ratio MB of the adjusted image area new and greater than the minimum ratio MB of the image area min , then the ratio MB of the adjusted image area new is considered to be within the safe adjustment range, and keep and continuously iteratively adjust; S3. If the adjusted image area ratio MB new is greater than the maximum image area ratio MB max , or if the adjusted image area ratio MB new is less than the minimum image area ratio MB min , in either of the above cases, it is considered that the adjusted image area ratio MB new is within the dangerous adjustment range, and the sensor monitors and issues a warning, stops the adjustment, and then proceeds with the processing.

7. An industrial intelligent robot according to claim 3, characterized in that: The specific method for the edge complexity value BF is to adopt an edge detection algorithm, including Canny and SOBEL, to identify the edges in the image data. The edges are detected by calculating the gradient intensity and direction of the pixel points in the image data and their neighboring pixel points. Features are extracted from the detected edges, and the features include the number, length, curvature, and direction of the edges. The features are used to quantify the complexity of the edges, and an algorithm including weighted summation and principal component analysis is used to output the edge complexity value BF.

Images