Electrical cabinet robot intelligent wiring control system based on deep learning

Abstract

The invention discloses an electrical cabinet robot intelligent wiring control system based on deep learning, and relates to the field of electrical engineering, which comprises a data acquisition module, an image processing module, a data processing module, a data storage module and a data control module. The data acquisition module carries out light supplement and shooting on the interior of the electrical cabinet through a camera installed on the mechanical arm, and the advantages are that when the mechanical arm moves, the mechanical arm drives the camera to move, and then the camera shoots the internal data of the electrical cabinet at different visual angles in the moving process; and then the DeepMask model is utilized to process the photo data at different angles, so that the DeepMask model can obtain better electronic component data, and a subsequent system can conveniently carry out wiring processing according to the identified data.

Description

Technical Field

[0001] The present invention relates to the field of electrical engineering, and in particular to an intelligent wiring control system for an electrical cabinet robot based on deep learning. Background Art

[0002] With the continuous advancement of science and technology and the development of industrial automation, electrical cabinets play a vital role in the fields of power systems and industrial production. Electrical cabinets contain various electrical components, such as circuit breakers, contactors, relays, etc. The wiring between them directly affects the normal operation of the electrical system. In the process of applying robots to electrical cabinet wiring, deep learning technology plays a key role. Deep learning can enable robots to have stronger intelligent perception and decision-making capabilities. By learning a large amount of electrical cabinet image data, robots can quickly and accurately identify the type, position and posture of electrical components, thereby achieving precise wiring operations. In addition, robots also need to be equipped with advanced sensors and control systems to ensure that they can work safely and stably in electrical cabinets.

[0003] However, when processing the inside of the electrical cabinet on the processing production line, the internal information of the electrical cabinet is traditionally obtained by fixing the visual sensor on the top of the processing frame, which results in extremely limited image data processed by the system, affecting the recognition of electronic components such as circuit breakers, contactors, terminals, etc. in the electrical cabinet. For this reason, we propose an intelligent wiring control system for electrical cabinet robots based on deep learning. Summary of the invention

[0004] The purpose of the present invention is to provide an intelligent wiring control system for an electrical cabinet robot based on deep learning.

[0005] To solve the problems raised in the above background technology, the present invention provides the following technical solutions: an intelligent wiring control system for an electrical cabinet robot based on deep learning, the data acquisition module, the image processing module, the data processing module, the data storage module and the data control module;

[0006] The data acquisition module uses a camera installed on the robotic arm to fill in light and take photos of the interior of the electrical cabinet;

[0007] The image processing module is used to process the image data captured by the data acquisition module. When the robotic arm moves, the data acquisition module captures the interior of the electrical cabinet through a camera, and then transmits the captured image data to the image processing module. The image processing module performs denoising, enhancement, and background segmentation on the image. At the same time, the image processing module performs position recognition on the identified electronic components, and uses the image processing module to identify the boundary position of the electrical cabinet to obtain the two-dimensional plane coordinate system of the electrical cabinet. A DeepMask model is set in the image processing module, and the DeepMask model is used to extract the grayscale, color, brightness, and texture of the electronic components in the electrical cabinet, and the extracted features are used to perform image segmentation on the electronic components. A temporary storage unit is set in the DeepMask model, and the temporary storage unit is used to store electronic component model data. After the DeepMask model extracts the grayscale, color, brightness, and texture data, the DeepMask model retrieves the data in the temporary storage unit for matching, and models the successfully matched model data according to the coordinate position of the electronic component identified by the image processing module, and transmits the modeled result data to the data processing module for processing;

[0008] The data processing module is used to plan the installation data of the robot arm through the acquired electronic components and generate corresponding instruction data;

[0009] The data storage module is used to store the feature data of the image processing module and the instruction data generated by the data processing module;

[0010] The data control module is used to control the robot arm to process the circuits in the electrical cabinet.

[0011] As a further solution of the present invention: the DeepMask model obtains the loss function of electronic components through a formula, and the specific formula is as follows:

[0012]

[0013] Among them, L 1 (θ) represents the electronic component L 1 The loss function, R represents the weight coefficient of the loss function, and the weight coefficient is affected by the clarity of the image. represents the segmentation data in the DeepMask model, ij represents the pixel data of electronic components, represents the segmentation data of electronic components in pixel ij, e represents a constant, and the approximate value of the constant is about 2.71828. represents the predicted data of electronic components in the actual state, X represents the segmentation result data, and Y represents the predicted result data.

[0014] As a further solution of the present invention: the image data of electronic components at different angles in the image are acquired by moving the robot arm, and the image data of electronic components are continuously optimized by using an image processing module and a loss function.

[0015] As a further solution of the present invention: a model matching unit is set in the image processing module, and the model matching unit is used to retrieve the modeling data in the temporary storage unit, and simultaneously obtain the electrical cabinet model data constructed in the DeepMask model, and match the data in the DeepMask model with the data in the temporary storage unit.

[0016] As a further solution of the present invention: when the electrical cabinet model data constructed in the DeepMask model is consistent with the data in the temporary storage unit, the model matching unit generates a call instruction and transmits the instruction to the data processing module, the data processing module calls the instruction data in the data storage module, and optimizes the movement path of the robot arm according to the line in the image data;

[0017] When the electrical cabinet model data constructed in the DeepMask model is inconsistent with the data in the temporary storage unit, the data processing module re-plans the movement path of the robotic arm, and at the same time obtains the line route in the electrical cabinet through the data processing module, and then adjusts the height and angle of the robotic arm during movement, so that the robotic arm bypasses the blocked part of the line. At the same time, the model data in the temporary storage unit is updated and the original model data is discarded.

[0018] As a further solution of the present invention: a camera for photographing the electrical cabinet is fixedly mounted on the base of the mechanical arm, and the camera cooperates with the camera head to obtain the coordinate data of the electronic components at different angles, and the coordinate data of the electronic components is obtained by a formula, and the specific formula is as follows:

[0019]

[0020] Among them, x represents the horizontal coordinate of the electronic component coordinate data, x 1 ,y 1 Indicates the camera coordinates, x 2 ,y 2 Represents the camera coordinates, a represents the angle between the line from the camera shooting point to the target point and the horizontal direction, and b represents the angle between the line from the camera shooting point to the target point and the horizontal direction.

[0021] As a further solution of the present invention: the data processing module matches the calculated abscissa data with the abscissa data calculated by the DeepMask model. When the abscissa data are consistent, the data processing module proceeds to the next step. When the abscissa data deviates, x is substituted into y=y 1 +(xx1 )tan(a), re-verify the electronic component coordinate data.

[0022] As a further solution of the present invention: after receiving the instruction data, the data control module controls the robotic arm to perform wiring processing on the circuit in the electrical cabinet, and at the same time uses a camera to shoot the working process of the robotic arm, and transmits the working process image to the DeepMask model in real time, and uses the DeepMask model to evaluate the wiring quality of the robotic arm.

[0023] By adopting the above technical solution, compared with the prior art, the beneficial effects of the present invention are:

[0024] 1. In the present invention, when the robot arm moves, the robot arm drives the camera to move, and the camera captures the internal data of the electrical cabinet at different viewing angles during the movement, and then uses the DeepMask model to process the photo data at different angles, so that the DeepMask model can obtain better electronic component data, which is convenient for the subsequent system to perform wiring processing according to the recognized data;

[0025] 2. The present invention obtains the segmentation data of electronic components through the loss function of the formula, and continuously optimizes the electronic components through the data captured at different angles, so that the DeepMask model obtains more accurate electronic components and improves the processing effect of the data processing module on the electronic components;

[0026] 3. The present invention uses a model matching unit to quickly obtain whether the modeling data of the DeepMask model is consistent with the model data in the temporary storage unit, so that the subsequent data processing module can obtain historical instruction data, so that the data processing module can optimize the historical instruction data of the robot arm, thereby improving the optimization computing power of the data processing module, and achieving the effect of continuously optimizing the movement path of the robot arm;

[0027] 4. The present invention forms an angle between the camera and the camera head, thereby identifying the electronic components inside the electrical cabinet, and then analyzing the positions of the electronic components to prevent coordinate errors that lead to poor subsequent wiring effects. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 This is a flow chart of a wiring control system in an embodiment of the present invention;

[0029] Figure 2 4 is a flow chart of the model matching unit in an embodiment of the present invention. DETAILED DESCRIPTION

[0030] 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.

[0031] Embodiment 1:

[0032] An intelligent wiring control system for an electrical cabinet robot based on deep learning. With the continuous advancement of science and technology and the development of industrial automation, electrical cabinets play a vital role in the fields of power systems and industrial production. Electrical cabinets contain various electrical components such as circuit breakers, contactors, relays, etc. The wiring between them directly affects the normal operation of the electrical system. In the process of applying robots to electrical cabinet wiring, deep learning technology plays a key role. Deep learning can enable robots to have stronger intelligent perception and decision-making capabilities. By learning a large amount of electrical cabinet image data, robots can quickly and accurately identify the type, position and posture of electrical components, thereby achieving precise wiring operations. In addition, robots also need to be equipped with advanced sensors and control systems to ensure that they can work safely and stably in electrical cabinets.

[0033] However, when processing the inside of the electrical cabinet on the processing production line, the internal information of the electrical cabinet is traditionally obtained by fixing the visual sensor on the top of the processing frame, which results in extremely limited image data processed by the system, affecting the recognition effect of electronic components such as circuit breakers, contactors, terminals, etc. in the electrical cabinet.

[0034] Please see attached Figure 1 -Attached Figure 2 , the present invention provides an intelligent wiring control system for an electrical cabinet robot based on deep learning, a data acquisition module, an image processing module, a data processing module, a data storage module and a data control module;

[0035] The data acquisition module uses the camera installed on the robotic arm to fill in the light and take photos of the interior of the electrical cabinet;

[0036] The image processing module is used to process the image data captured by the data acquisition module. When the robotic arm moves, the data acquisition module captures the inside of the electrical cabinet through a camera, and then transmits the captured image data to the image processing module. The image processing module performs denoising, enhancement, and background segmentation on the image. At the same time, the image processing module identifies the position of the identified electronic components, and uses the image processing module to identify the boundary position of the electrical cabinet to obtain the two-dimensional plane coordinate system of the electrical cabinet. A DeepMask model is set in the image processing module, and the DeepMask model is used to extract the grayscale, color, brightness, and texture of the electronic components in the electrical cabinet, and the extracted features are used to perform image segmentation on the electronic components. A temporary storage unit is set in the DeepMask model, and the temporary storage unit is used to store electronic component model data. After the DeepMask model extracts the grayscale, color, brightness, and texture data, the DeepMask model retrieves the data in the temporary storage unit for matching, and models the successfully matched model data according to the coordinate position of the electronic component identified by the image processing module, and transmits the modeled result data to the data processing module for processing;

[0037] The data processing module is used to plan the installation data of the robot arm through the acquired electronic components and generate corresponding instruction data;

[0038] The data storage module is used to store the feature data of the image processing module and the instruction data generated by the data processing module;

[0039] The data control module is used to control the robot arm to process the circuits in the electrical cabinet.

[0040] Specific workflow: The robotic arm is installed on the robot, and then the robotic arm acquires image data during movement, and the data acquisition module transmits the captured image data to the image processing module;

[0041] The image processing module performs denoising, enhancement and background segmentation on the image;

[0042] The DeepMask model is used to extract the grayscale, color, brightness, and texture of the electronic components in the electrical cabinet; the DeepMask model retrieves the data in the temporary storage unit and matches it with the extracted features; the successfully matched model data is modeled according to the coordinate position of the electronic components identified by the image processing module; the image processing module transmits the modeled data to the data processing module;

[0043] The data processing module plans the installation data of the robotic arm according to the acquired electronic components and generates corresponding instruction data; data storage: the data storage module stores the feature data of the image processing module and the instruction data generated by the data processing module; robotic arm control: the data control module controls the robotic arm to process the circuits in the electrical cabinet according to the instruction data.

[0044] Furthermore, when the robotic arm moves, the camera is driven to move, and the camera captures the internal data of the electrical cabinet from different perspectives during the movement. The DeepMask model is then used to process the photo data from different angles, so that the DeepMask model can obtain better electronic component data, making it easier for the subsequent system to perform wiring processing based on the recognized data.

[0045] Embodiment 2:

[0046] Based on the first embodiment, as shown in the accompanying drawings, the DeepMask model obtains the loss function of electronic components through a formula, and the specific formula is as follows:

[0047]

[0048] Among them, L 1 (θ) represents the electronic component L 1 The loss function, R represents the weight coefficient of the loss function, and the weight coefficient is affected by the clarity of the image. represents the segmentation data in the DeepMask model, ij represents the pixel data of electronic components, represents the segmentation data of electronic components in pixel ij, e represents a constant, and the approximate value of the constant is about 2.71828. represents the predicted data of electronic components in the actual state, X represents the segmentation result data, and Y represents the predicted result data. The image data of electronic components at different angles in the image are obtained by moving the robotic arm, and the image processing module and the loss function are used to continuously optimize the image data of electronic components.

[0049] Specific workflow: According to the coordinate positions of the electronic components identified by the image processing module, the successfully matched model data is modeled, and the loss function of the electronic components is calculated using the formula. The loss function includes parts related to the segmentation data and the prediction data, as well as parts related to the intersection of the segmentation result data and the prediction result data. According to the results of the loss function, the DeepMask model is continuously optimized to improve the accuracy of electronic component image segmentation.

[0050] Furthermore, the segmentation data of electronic components is obtained through the loss function of the formula, and the electronic components are continuously optimized through data taken at different angles, so that the DeepMask model can obtain more accurate electronic components and improve the processing effect of the data processing module on electronic components.

[0051] Embodiment three:

[0052] Based on the second embodiment, please refer to the attached Figure 1 -As shown in the accompanying figure*, a model matching unit is set in the image processing module, and the model matching unit is used to retrieve the modeling data in the temporary storage unit, and at the same time obtain the electrical cabinet model data constructed in the DeepMask model, and match the data in the DeepMask model with the data in the temporary storage unit. When the electrical cabinet model data constructed in the DeepMask model is consistent with the data in the temporary storage unit, the model matching unit generates a retrieval instruction and transmits the instruction to the data processing module. The data processing module retrieves the instruction data in the data storage module and optimizes the movement path of the robot arm according to the line in the image data;

[0053] When the electrical cabinet model data constructed in the DeepMask model is inconsistent with the data in the temporary storage unit, the data processing module re-plans the movement path of the robotic arm, and at the same time obtains the line route in the electrical cabinet through the data processing module, and then adjusts the height and angle of the robotic arm during movement, so that the robotic arm bypasses the blocked part of the line. At the same time, the model data in the temporary storage unit is updated and the original model data is discarded.

[0054] Specific workflow: The image processing module uses the DeepMask model to extract features and model the electronic components in the electrical cabinet, and stores the modeling data in a temporary storage unit;

[0055] The model matching unit retrieves the modeling data from the temporary storage unit and obtains the latest electrical cabinet model data in the DeepMask model. The model matching unit matches and compares the two data. If the data are consistent, the model matching unit generates a retrieval instruction and transmits the instruction to the data processing module. If the data are inconsistent, it proceeds to the next step.

[0056] After receiving the call instruction, the data processing module calls the instruction data from the data storage module, the data processing module optimizes the moving path of the robot arm according to the line information in the image data, and the data control module controls the robot arm to move according to the optimized moving path;

[0057] The data processing module replans the movement path of the robotic arm. The data processing module obtains the line route in the electrical cabinet, and adjusts the height and angle of the robotic arm during movement according to the line route so that it can bypass the line blocking part, updates the model data in the temporary storage unit, and deletes the original model data. The data control module controls the movement of the robotic arm according to the new movement path and the adjusted height and angle.

[0058] Furthermore, through the model matching unit, it is possible to quickly obtain whether the modeling data of the DeepMask model is consistent with the model data in the temporary storage unit, so that the subsequent data processing module can obtain the historical instruction data, so that the data processing module can optimize the historical instruction data of the robotic arm, thereby improving the optimization computing power of the data processing module, and achieving the effect of continuously optimizing the movement path of the robotic arm.

[0059] Embodiment 4:

[0060] Based on the third embodiment, please refer to the attached drawings, a camera for photographing the electrical cabinet is fixedly installed on the base of the robot arm, and the camera and the camera head cooperate with each other to obtain the coordinate data of the electronic components at different angles, and the coordinate data of the electronic components is obtained by the formula, and the specific formula is as follows:

[0061]

[0062] Among them, x represents the horizontal coordinate of the electronic component coordinate data, x 1 ,y 1 Indicates the camera coordinates, x 2 ,y 2 represents the camera coordinates, a represents the angle between the line connecting the camera shooting point to the target point and the horizontal direction, and b represents the angle between the line connecting the camera shooting point to the target point and the horizontal direction. The data processing module matches the calculated horizontal coordinate data with the horizontal coordinate data calculated by the DeepMask model. When the horizontal coordinate data are consistent, the data processing module enters the next step. When the horizontal coordinate data deviates, x is substituted into y=y 1 +(xx 1 )tan(a), the coordinate data of the electronic components is re-verified. After receiving the instruction data, the data control module controls the robot arm to wire the circuit in the electrical cabinet. At the same time, the working process of the robot arm is photographed by the camera, and the working process image is transmitted to the DeepMask model in real time. The DeepMask model is used to evaluate the wiring quality of the robot arm.

[0063] Specific workflow: The camera cooperates with the camera in the data acquisition module on the robotic arm, and then the data processing module calculates whether there is any error in the coordinate data of the electronic components, confirms the horizontal coordinate data of the target through the formula, and then determines whether the data of the DeepMask model is consistent.

[0064] Furthermore, by forming an angle between the camera and the camera head, the electronic components inside the electrical cabinet are identified, and the positions of the electronic components are analyzed again to prevent coordinate errors that would lead to poor subsequent wiring results.

[0065] The above shows and describes the basic principles, main features and advantages of the present invention. It should be understood by those skilled in the art that the present invention is not limited to the above embodiments. The above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. An intelligent wiring control system for an electrical cabinet robot based on deep learning, characterized in that: The data acquisition module, image processing module, data processing module, data storage module and data control module; The data acquisition module uses a camera installed on the robotic arm to fill in light and take photos of the interior of the electrical cabinet; The image processing module is used to process the image data captured by the data acquisition module. When the robotic arm moves, the data acquisition module captures the interior of the electrical cabinet through a camera, and then transmits the captured image data to the image processing module. The image processing module performs denoising, enhancement, and background segmentation on the image. At the same time, the image processing module performs position recognition on the identified electronic components, and uses the image processing module to identify the boundary position of the electrical cabinet to obtain the two-dimensional plane coordinate system of the electrical cabinet. A DeepMask model is set in the image processing module, and the DeepMask model is used to extract the grayscale, color, brightness, and texture of the electronic components in the electrical cabinet, and the extracted features are used to perform image segmentation on the electronic components. A temporary storage unit is set in the DeepMask model, and the temporary storage unit is used to store electronic component model data. After the DeepMask model extracts the grayscale, color, brightness, and texture data, the DeepMask model retrieves the data in the temporary storage unit for matching, and models the successfully matched model data according to the coordinate position of the electronic component identified by the image processing module, and transmits the modeled result data to the data processing module for processing; The data processing module is used to plan the installation data of the robot arm through the acquired electronic components and generate corresponding instruction data; The data storage module is used to store the feature data of the image processing module and the instruction data generated by the data processing module; The data control module is used to control the robot arm to process the circuits in the electrical cabinet.

2. According to claim 1, an intelligent wiring control system for an electrical cabinet robot based on deep learning is characterized in that: The DeepMask model obtains the loss function of electronic components through a formula, and the specific formula is as follows: Among them, L1(θ) represents the loss function of the electronic component L1, R represents the weight coefficient of the loss function, and the weight coefficient is affected by the clarity of the image shooting. represents the segmentation data in the DeepMask model, ij represents the pixel data of electronic components, represents the segmentation data of electronic components in pixel ij, e represents a constant, and the approximate value of the constant is about 2.71828. represents the predicted data of electronic components in the actual state, X represents the segmentation result data, and Y represents the predicted result data.

3. According to claim 2, an intelligent wiring control system for an electrical cabinet robot based on deep learning is characterized in that: The image data of electronic components at different angles in the image are acquired by moving the robotic arm, and the image data of electronic components are continuously optimized using the image processing module and the loss function.

4. According to claim 3, an intelligent wiring control system for an electrical cabinet robot based on deep learning is characterized in that: A model matching unit is set in the image processing module, and the model matching unit is used to retrieve the modeling data in the temporary storage unit, simultaneously obtain the electrical cabinet model data constructed in the DeepMask model, and match the data in the DeepMask model with the data in the temporary storage unit.

5. According to claim 4, an intelligent wiring control system for an electrical cabinet robot based on deep learning is characterized in that: When the electrical cabinet model data constructed in the DeepMask model is consistent with the data in the temporary storage unit, the model matching unit generates a call instruction and transmits the instruction to the data processing module, which calls the instruction data in the data storage module and optimizes the movement path of the robot arm according to the line in the image data; When the electrical cabinet model data constructed in the DeepMask model is inconsistent with the data in the temporary storage unit, the data processing module re-plans the movement path of the robotic arm, and at the same time obtains the line route in the electrical cabinet through the data processing module, and then adjusts the height and angle of the robotic arm during movement, so that the robotic arm bypasses the blocked part of the line. At the same time, the model data in the temporary storage unit is updated and the original model data is discarded.

6. The deep learning-based intelligent wiring control system for electrical cabinet robots according to claim 5 is characterized in that: A camera for photographing the electrical cabinet is fixedly mounted on the base of the mechanical arm. The camera cooperates with the camera head to obtain the coordinate data of the electronic components at different angles. The coordinate data of the electronic components is obtained by the formula. The specific formula is as follows: Among them, x represents the horizontal coordinate of the electronic component coordinate data, x1, y1 represent the camera coordinates, x2, y2 represent the camera coordinates, a represents the angle between the line connecting the camera shooting point to the target point and the horizontal direction, and b represents the angle between the line connecting the camera shooting point to the target point and the horizontal direction.

7. The deep learning-based intelligent wiring control system for electrical cabinet robots according to claim 6 is characterized in that: The data processing module matches the calculated horizontal coordinate data with the horizontal coordinate data calculated by the DeepMask model. When the horizontal coordinate data are consistent, the data processing module enters the next step. When the horizontal coordinate data deviates, x is substituted into y=y1+(x-x1)tan(a) to re-verify the coordinate data of the electronic components.

8. The deep learning-based intelligent wiring control system for electrical cabinet robots according to claim 1 is characterized in that: After receiving the instruction data, the data control module controls the robotic arm to perform wiring processing on the circuit in the electrical cabinet. At the same time, the working process of the robotic arm is photographed by a camera, and the working process image is transmitted to the DeepMask model in real time. The DeepMask model is used to evaluate the wiring quality of the robotic arm.

Images