Leather material cutting robot and cutting method thereof

Abstract

The invention relates to a leather material cutting robot and a cutting method thereof, and belongs to the technical field of material cutting, the leather material cutting robot comprises a human-computer interaction interface, a CAD / CAM system, a multi-mode visual perception unit, a central processing system, a dynamic compensation cutting unit and a quality closed-loop system, and the multi-mode visual perception unit comprises a high-resolution multispectral imaging module and a 3D scanning module. According to the method, the problems that a traditional leather material cutting robot visual recognition system cannot recognize leather thickness changes, material waste is easily caused by subcutaneous defects, natural curling deformation of leather is difficult to adapt, and the edge precision error is large are solved, the rejection rate can be further reduced through multispectral and 3D defect recognition, and the production efficiency is improved. Three-dimensional dynamic compensation enables edge errors to be further reduced, and real-time force control further reduces the occurrence rate of crush damage.

Description

Technical Field

[0001] The present invention relates to the technical field of material cutting, in particular to a leather material cutting robot and a cutting method thereof. Background Art

[0002] Leather cutting is the core process of leather goods production. The method needs to be comprehensively selected based on material properties, product precision requirements, and production efficiency. The leather cutting robot can accurately cut leather materials.

[0003] The visual system of the leather cutting robot is the core and "eyes" of the entire automated cutting process. It undertakes multiple key tasks that directly affect the quality, efficiency and material utilization of cutting. It needs to identify shapes, locate positions, and detect defects. It needs to intelligently match the designed cutting plan (layout diagram) with the actual leather condition, accurately guide the robot to perform cutting actions, avoid defects, maximize material utilization, monitor the cutting process and results, and ensure that the product meets the standards.

[0004] Existing leather cutting robots usually only use two-dimensional vision systems to identify leather materials, which cannot identify changes in leather thickness and subcutaneous defects, easily leading to material waste. In addition, static path planning is difficult to adapt to the natural curling and deformation of leather, resulting in suspended cutting where the tool does not touch the material or crushing injuries caused by overpressure of the tool. The cutting process lacks real-time deformation compensation, and the edge accuracy error is large. Therefore, a leather material cutting robot and a cutting method are proposed. Multi-spectral and 3D defect recognition are used to further reduce the scrap rate, three-dimensional dynamic compensation is used to further reduce the edge error, and real-time force control is used to further reduce the incidence of crushing injuries. Summary of the Invention

[0005] The present invention provides a leather material cutting robot and a cutting method thereof, which solve the problems that the traditional leather material cutting robot's visual recognition system cannot identify leather thickness changes and subcutaneous defects, which easily lead to material waste, is difficult to adapt to the natural curling and deformation of leather, and has large edge precision errors.

[0006] The present invention solves the above-mentioned technical problems with the following solution: A leather material cutting robot includes a human-machine interface, a CAD / CAM system, a multimodal visual perception unit, a central processing system, a dynamic compensation cutting unit, and a quality closed-loop system. The multimodal visual perception unit includes a high-resolution multispectral imaging module and a 3D scanning module; the central processing system includes an intelligent optimization module, a defect recognition engine, a material database, a path planner, and a motion controller; the dynamic compensation cutting unit includes a six-axis cutting robot arm, a tool posture adjustment mechanism, a distributed force sensor, and a vacuum adsorption table; and the quality closed-loop system includes a cloud platform database and a laser profiler.

[0007] The cutting method includes the following steps:

[0008] S1, multimodal data fusion and feature extraction: Leather material is laid on a vacuum adsorption table, and the leather material is scanned from multiple sources using a multimodal visual perception unit. The multi-source data is fused to form a data stream that is transmitted to the central processing system. The central processing system outputs a risk heat map marked with avoidance coordinates;

[0009] S2, intelligent path planning: the human-machine interface inputs processing parameters to the central processing system, the CAD / CAM system inputs plate data to the central processing system, the intelligent optimization module uses an improved genetic algorithm to perform nested layout based on the risk heat map, and the path planner generates an initial 3D cutting path including tool pitch angle parameters and transmits it to the motion controller;

[0010] S3, dynamic compensation cutting, the dynamic compensation cutting unit performs real-time execution and feedback to the central processing system, thus realizing the dynamic compensation control loop;

[0011] S4, quality feedback closed loop, after cutting is completed, the laser profiler of the quality closed loop system scans the three-dimensional morphology of the cut and outputs a three-dimensional quality report.

[0012] On the basis of the above technical solution, the present invention can also be improved as follows.

[0013] Furthermore, the high-resolution multispectral imaging module is equipped with a visible light, near-infrared, and thermal imaging three-spectrum camera array to simultaneously collect surface texture, color difference, and subcutaneous blood vessels / scar data. The visible light camera uses 50 million pixels and the near-infrared camera is 900-1700nm.

[0014] Furthermore, the 3D structured light scanning module uses a blue light stripe projector and a high-speed industrial camera to reconstruct the three-dimensional point cloud model of leather in real time. The accuracy of the blue light stripe projector is ±0.05mm, and the high-speed industrial camera is 300fps.

[0015] Furthermore, the tool posture adjustment mechanism adopts a Z-axis piezoelectric micro-motion stage driven by piezoelectric ceramics, and the distributed force sensor is a 3D force sensing array installed on the tool head of the six-axis cutting robot arm.

[0016] Furthermore, in step S1, the high-resolution multispectral imaging module identifies surface defects such as scars and wrinkles on the leather material and subcutaneous defect areas with abnormal density. The 3D scanning module calculates the local curvature based on the 3D point cloud and marks the concave area as a pressure injury risk area.

[0017] Furthermore, in step S1, the defect recognition engine of the central processing system processes the data stream through the CNN-Transformer model and outputs a risk heat map marked with avoidance coordinates.

[0018] Furthermore, in step S4, the material database of the central processing system transmits the quality data of the material to the cloud platform database. The cloud platform database compares the historical data with the three-dimensional quality report. If there are defective missed samples, they are transmitted to the central processing system for updating the material database.

[0019] The beneficial effects of the present invention are as follows: the present invention provides a leather material cutting robot and a cutting method thereof, which have the following advantages:

[0020] 1. Compared to traditional leather cutting robots that typically only use two-dimensional vision systems to identify leather materials and are unable to identify thickness variations and subcutaneous defects, this multi-spectral vision capability, which combines near-infrared detection of subcutaneous blood vessels and scars, thermal imaging to identify density abnormalities, and visible light to identify surface defects, can effectively improve defect detection rates.

[0021] 2. It can realize 3D shape adaptive avoidance. Through curvature calculation, such as automatic avoidance of concave areas, it can avoid waste caused by cutting in bulges and concave areas, thereby effectively reducing material waste rate;

[0022] 3. The dual closed-loop dynamic compensation mechanism can correct leather deformation in real time through visual servoing. The piezoelectric ceramic micro-motion stage with force-controlled adaptive compensation mechanism can dynamically adjust the knife according to the formula, thereby further improving the cutting accuracy of the leather material cutting robot.

[0023] 4. The Z-axis can be actively lifted to compensate for bulge deformation and eliminate suspended cutting. The 3D force sensor can automatically trigger ultrasonic energy compensation when the pressure exceeds the threshold, thereby effectively reducing the incidence of pressure injuries.

[0024] 5. It solves the problems of traditional leather material cutting robot visual recognition system's inability to identify leather thickness changes and subcutaneous defects, which easily lead to material waste, difficulty in adapting to the natural curling and deformation of leather, and large edge precision errors. Multi-spectral and 3D defect recognition can further reduce the scrap rate, three-dimensional dynamic compensation can further reduce edge errors, and real-time force control can further reduce the incidence of crushing injuries.

[0025] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention and to implement it according to the contents of the description, the following preferred embodiments of the present invention are described in detail with reference to the accompanying drawings. The specific implementation methods of the present invention are given in detail by the following embodiments and the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0027] Figure 1 This is a cutting robot system architecture diagram of a leather material cutting robot and a cutting method thereof provided in one embodiment of the present invention. DETAILED DESCRIPTION

[0028] The following is combined with Figure 1 The principles and features of the present invention are described, and the examples given are only for the purpose of explaining the present invention and are not intended to limit the scope of the present invention. The following paragraphs describe the present invention in more detail by way of example with reference to the accompanying drawings. The advantages and features of the present invention will become more apparent from the following description and claims. It should be noted that the drawings are in a very simplified form and are not in exact proportions, and are only used for the purpose of conveniently and clearly assisting in illustrating the embodiments of the present invention.

[0029] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this invention pertains. The terms used in this specification of the present invention are for the purpose of describing specific embodiments only and are not intended to limit the present invention. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0030] like Figure 1 As shown, the present invention provides a leather material cutting robot, including a human-computer interaction interface, a CAD / CAM system, a multimodal visual perception unit, a central processing system, a dynamic compensation cutting unit, and a quality closed-loop system. The multimodal visual perception unit includes a high-resolution multispectral imaging module and a 3D scanning module; the central processing system includes an intelligent optimization module, a defect recognition engine, a material database, a path planner, and a motion controller; the dynamic compensation cutting unit includes a six-axis cutting robot arm, a tool posture adjustment mechanism, a distributed force sensor, and a vacuum adsorption table; the quality closed-loop system includes a cloud platform database and a laser profiler;

[0031] Preferably, the high-resolution multispectral imaging module is equipped with a visible light, near-infrared, and thermal imaging three-spectrum camera array to simultaneously collect surface texture, color difference, and subcutaneous blood vessels / scar data. The visible light camera uses 50 million pixels and the near-infrared camera is 900-1700nm.

[0032] Preferably, the 3D structured light scanning module uses a blue light stripe projector and a high-speed industrial camera to reconstruct the three-dimensional point cloud model of leather in real time. The accuracy of the blue light stripe projector is ±0.05mm, and the high-speed industrial camera is 300fps.

[0033] Preferably, the tool posture adjustment mechanism adopts a Z-axis piezoelectric micro-motion stage driven by piezoelectric ceramics, and the distributed force sensor is a 3D force sensing array installed on the tool head of the six-axis cutting robot arm.

[0034] The specific working principle and method of use of the present invention are as follows:

[0035] S1: Multimodal data fusion and feature extraction: Leather materials are laid on a vacuum adsorption table. Multispectral imaging is used to identify surface defects such as scars and wrinkles, as well as subcutaneous defects with abnormal density. Based on the local curvature of 3D point clouds, recessed areas are marked as pressure injury risk areas. Multi-source data is fused to form a data stream that is transmitted to the central processing system. The central processing system's defect recognition engine processes the data stream using a CNN-Transformer model and outputs a risk heat map marked with avoidance coordinates.

[0036] S2: Intelligent path planning: The human-machine interface inputs processing parameters to the central processing system, the CAD / CAM system inputs plate data to the central processing system, the intelligent optimization module uses an improved genetic algorithm for nested layout, and the path planner generates an initial 3D cutting path including tool pitch angle parameters and transmits it to the motion controller;

[0037] Improved genetic algorithm parameters: population size: 200, number of iterations: 1000, fitness function: 0.7×material utilization rate + 0.2×defect avoidance rate + 0.1×texture matching degree, hard constraint texture direction deviation ≤ 5°;

[0038] S3: Dynamic compensation cutting: The dynamic compensation cutting unit performs execution in real time and feeds back to the central processing system, thus realizing the dynamic compensation control loop;

[0039] 1. Read the three-axis pressure value of the force sensor;

[0040] 2. Request a local point cloud;

[0041] 3. Calculate the current curvature K value;

[0042] 4. Conditional judgment and execution

[0043] Bulging scenario (K>0 and pressure>5N)

[0044] Δh=0.15×(F z -5)×e -t / 0.2

[0045] The piezoelectric micro-motion stage lifts the Z axis;

[0046] In the concave scenario, K<0 and pressure>5N, the ultrasonic power is increased to 120%;

[0047] 5. Execute the cycle until the cutting is completed;

[0048] S4: Quality feedback closed loop. After cutting is completed, the laser profiler of the quality closed loop system scans the three-dimensional shape of the cut and outputs a three-dimensional quality report. The material database of the central processing system transmits the quality data of the material to the cloud platform database. The cloud platform database compares the historical data with the three-dimensional quality report. If there are defective samples that are missed, they will be transmitted to the central processing system to update the material database.

[0049] It should be noted that, in this document, relational terms such as first and second are used solely to distinguish one entity or operation from another, and do not necessarily require or imply any actual relationship or order between these entities or operations. Matters not described in detail in this specification are well known to those skilled in the art.

[0050] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any form. Any ordinary technician in this industry can smoothly implement the present invention as shown in the drawings and described above. However, any equivalent changes, modifications and evolutions made by technicians familiar with this profession without departing from the scope of the technical solution of the present invention using the technical content disclosed above are all equivalent embodiments of the present invention. At the same time, any equivalent changes, modifications and evolutions made to the above embodiments based on the essential technology of the present invention are still within the scope of protection of the technical solution of the present invention.

Claims

1. A leather cutting robot, comprising a human-machine interface, a CAD / CAM system, a multimodal visual perception unit, a central processing system, a dynamic compensation cutting unit, and a quality closed-loop system, characterized in that: The multimodal visual perception unit includes a high-resolution multispectral imaging module and a 3D scanning module; the central processing system includes an intelligent optimization module, a defect recognition engine, a material database, a path planner, and a motion controller; the dynamic compensation cutting unit includes a six-axis cutting robot arm, a tool posture adjustment mechanism, a distributed force sensor, and a vacuum adsorption table; the quality closed-loop system includes a cloud platform database and a laser profiler; The cutting method includes the following steps: S1, multimodal data fusion and feature extraction: Leather material is laid on a vacuum adsorption table, and the leather material is scanned from multiple sources using a multimodal visual perception unit. The multi-source data is fused to form a data stream that is transmitted to the central processing system. The central processing system outputs a risk heat map marked with avoidance coordinates; S2, intelligent path planning: the human-machine interface inputs processing parameters to the central processing system, the CAD / CAM system inputs plate data to the central processing system, the intelligent optimization module uses an improved genetic algorithm to perform nested layout based on the risk heat map, and the path planner generates an initial 3D cutting path including tool pitch angle parameters and transmits it to the motion controller; S3, dynamic compensation cutting, the dynamic compensation cutting unit performs real-time execution and feedback to the central processing system, thus realizing the dynamic compensation control loop; S4, quality feedback closed loop, after cutting is completed, the laser profiler of the quality closed loop system scans the three-dimensional morphology of the cut and outputs a three-dimensional quality report.

2. A leather material cutting robot according to claim 1, characterized in that: The high-resolution multispectral imaging module is equipped with a visible light, near-infrared, and thermal imaging three-spectrum camera array to synchronously collect surface texture, color difference, and subcutaneous blood vessel / scar data.

3. The leather cutting robot according to claim 1, characterized in that: The 3D structured light scanning module uses a blue light stripe projector and a high-speed industrial camera to reconstruct the leather 3D point cloud model in real time.

4. The leather cutting robot according to claim 1, characterized in that: The six-axis cutting robot arm is integrated with an ultrasonic cutting head.

5. The leather cutting robot according to claim 1, characterized in that: The tool posture adjustment mechanism adopts a Z-axis piezoelectric micro-motion stage driven by piezoelectric ceramics, and the distributed force sensor is a 3D force sensing array installed on the tool head of the six-axis cutting robot arm.

6. The leather cutting robot according to claim 1, characterized in that: In step S1, the high-resolution multispectral imaging module identifies surface defects such as scars and wrinkles on the leather material and subcutaneous defect areas with abnormal density. The 3D scanning module calculates the local curvature based on the 3D point cloud and marks the concave areas as pressure injury risk areas.

7. The leather cutting robot according to claim 6, characterized in that: In step S1, the defect recognition engine of the central processing system processes the data stream through the CNN-Transformer model and outputs a risk heat map marked with avoidance coordinates.

8. The leather cutting robot according to claim 1, characterized in that: In step S4, the material database of the central processing system transmits the quality data of the material to the cloud platform database. The cloud platform database compares the historical data with the three-dimensional quality report. If there are defective missed samples, they are transmitted to the central processing system for updating the material database.

Images