Search

CN-122008548-A - Foreign matter detection method and device of 3D printer, computer equipment and readable storage medium

CN122008548ACN 122008548 ACN122008548 ACN 122008548ACN-122008548-A

Abstract

The application discloses a foreign matter detection method, a device, a computer device and a readable storage medium of a 3D printer, which relate to the technical field of 3D printing, and are used for shooting a hot bed to obtain an image to be detected when a target component in the 3D printer is positioned at a target height, inputting an image to be detected into a pre-trained image recognition model to obtain hot bed recognition information, and generating a foreign matter detection result according to the hot bed recognition information, wherein the foreign matter detection result is used for indicating whether foreign matters exist on a hot bed or not in the foreign matter detection process. The method has the advantages that whether the foreign matters exist on the hot bed is automatically detected through a computer vision algorithm, missed detection caused by manual negligence is effectively avoided, the hot bed is identified based on an image identification model, whether the foreign matters exist is inferred by analyzing the identification information of the hot bed, the specific characteristics of the foreign matters do not need to be defined or learned in advance, the foreign matters of various types, sizes and appearances can be widely detected, and the universality and the robustness of the foreign matter detection are enhanced.

Inventors

  • TANG XIAOYU
  • ZHAN KAIHONG
  • LIU ZHAOGUAN

Assignees

  • 深圳市纵维立方科技有限公司

Dates

Publication Date
20260512
Application Date
20251208

Claims (13)

  1. 1. A foreign matter detection method of a 3D printer, the method comprising: The method comprises the steps of obtaining an image to be detected, wherein the image to be detected is obtained by shooting a hot bed in a 3D printer when a target component in the 3D printer is at a target height; Inputting the image to be detected into a pre-trained image recognition model to obtain hot bed recognition information; And generating a foreign matter detection result according to the hot bed identification information, wherein the foreign matter detection result is used for indicating whether the foreign matter exists on the hot bed or not in the current foreign matter detection process.
  2. 2. The method according to claim 1, characterized by comprising, after the generating of the foreign matter detection result from the hot bed identification information: Judging whether a foreign matter detection end condition is satisfied; If yes, controlling a printing head of the 3D printer to be in contact with the hot bed; if the foreign object detection condition is not met, controlling the target part to move to a new target detection height, and returning to the step of acquiring the image to be detected until the foreign object detection end condition is met.
  3. 3. The method of claim 2, comprising at least one of: A first item: The foreign matter detection ending condition comprises a foreign matter detection result indicating that the foreign matter on the hot bed is not detected at this time and the foreign matter detection times reach the preset detection times, and/or a foreign matter detection result indicating that the foreign matter on the hot bed is detected at this time and target indicating information is obtained, wherein the target indicating information is used for indicating that the foreign matter on the hot bed is removed; The second item: A target height difference value is arranged between two adjacent target height values, and the target height difference value is determined based on the height of the target assembly when the 3D printer finishes the last printing; Third item: And detecting the foreign matter for the first time, wherein the height of a target corresponding to the foreign matter detection is a reference height or the height of the target assembly when the 3D printer finishes the last printing, and the reference height is the height of the target assembly when the 3D printer finishes the Z-axis reverse zeroing operation.
  4. 4. The method of claim 1, further comprising, prior to acquiring the image to be detected, at least one of: A first item: The method comprises the steps of controlling a printing head of the 3D printer to move to a target avoiding position in the horizontal direction, wherein the target avoiding position is used for enabling an imaging device on the 3D printer to be not blocked by the printing head when shooting the hot bed; The second item: And controlling the thermal bed to move to a target shooting position in the horizontal direction, wherein the range of the thermal bed shot by the camera shooting device meets the target range condition when the thermal bed is positioned at the target shooting position.
  5. 5. The method of claim 1, wherein the hotbed identification information includes hotbed profile information and hotbed confidence; The generating a foreign matter detection result according to the hot bed identification information includes: Determining a hot bed detection area of a hot bed in the image to be detected based on the hot bed profile information; And if the hot bed confidence coefficient is greater than a confidence coefficient threshold value and the hot bed detection area is smaller than or equal to an area threshold value, generating a first foreign matter detection result for indicating that the foreign matter exists on the hot bed in the current foreign matter detection process, wherein the area threshold value is determined based on the current target detection height.
  6. 6. The method of claim 5, wherein the method further comprises: And if the thermal bed confidence is greater than a confidence threshold and the thermal bed detection area is greater than an area threshold, determining thermal bed geometric analysis information based on the thermal bed contour information, and generating a foreign matter detection result based on the thermal bed geometric analysis information.
  7. 7. The method of claim 6, wherein the thermal bed geometry analysis information comprises thermal bed blocking information; based on the hot bed contour information, determining hot bed block information corresponding to the hot bed in the image to be detected, wherein the hot bed block information is used for indicating whether the hot bed in the image to be detected is divided into a plurality of independent areas or not; and under the condition that the hot bed blocking information indicates that the hot bed in the image to be detected is divided into a plurality of independent areas, generating a first foreign matter detection result for indicating that the hot bed is detected to have foreign matters in the current foreign matter detection process.
  8. 8. The method of claim 6, wherein the thermal bed geometry analysis information comprises hollow region information; Based on the hot bed contour information, determining hollow area information corresponding to a hot bed in the image to be detected, wherein the hollow area information is used for indicating whether a hollow area exists in the hot bed in the image to be detected; And when the hollow area information indicates that a hollow area exists in the hot bed in the image to be detected, generating a first foreign matter detection result for indicating that the foreign matter exists on the hot bed in the current foreign matter detection process.
  9. 9. The method of claim 6, wherein the hotbed geometry analysis information comprises convex hull ratios; The determining thermal bed geometric analysis information based on the thermal bed contour information and generating a foreign matter detection result based on the thermal bed geometric analysis information includes: Based on the hot bed contour information, determining a convex hull corresponding to a hot bed in the image to be detected, and obtaining the area of the convex hull; obtaining a convex hull ratio based on the hot bed detection area and the convex hull area; and if the convex hull ratio is smaller than or equal to a convex hull ratio threshold, generating a first foreign matter detection result for indicating that the foreign matter exists on the hot bed in the current foreign matter detection process.
  10. 10. The method according to any one of claims 1-9, comprising at least one of: A first item: The camera device on the 3D printer is arranged at the top end of the X axis of the 3D printer, and faces to the hot bed on the 3D printer; The second item: And after a first foreign matter detection result for indicating that the foreign matter exists on the hot bed in the current foreign matter detection process is generated, the target device is indicated to carry out foreign matter reminding.
  11. 11. A foreign matter detection device of a 3D printer, comprising: The device comprises an acquisition module, a detection module and a detection module, wherein the acquisition module is used for acquiring an image to be detected, and the image to be detected is obtained by shooting a hot bed in a 3D printer when a target component in the 3D printer is at a target height; The identification module is used for inputting the image to be detected into a pre-trained image identification model to obtain hot bed identification information; The detection result generation module is also used for generating a foreign matter detection result according to the hot bed identification information, and the foreign matter detection result is used for indicating whether the foreign matter exists on the hot bed or not in the current foreign matter detection process.
  12. 12. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any one of claims 1 to 10 when the computer program is executed.
  13. 13. A readable storage medium having stored thereon a computer program, which when executed by a processor, implements the steps of the method of any of claims 1 to 10.

Description

Foreign matter detection method and device of 3D printer, computer equipment and readable storage medium Technical Field The application relates to the technical field of 3D printing, in particular to a foreign matter detection method and device of a 3D printer, computer equipment and a readable storage medium. Background In the technical field of 3D (Three-dimensional) printing, FDM (Fused Deposition Modeling) is used as a mainstream printing process, and is widely applied in various industries and fields by virtue of the advantages of low cost, simple operation, wide material applicability and the like. After heating and melting the thermoplastic material, the FDM 3D printing is piled layer by layer according to a preset model path, and finally a three-dimensional solid model is constructed. However, the printing quality is affected by various factors, wherein the presence of foreign matters in the printing scene is one of the key factors affecting the printing quality, and if the foreign matters cannot be detected and cleaned in time before printing, a series of problems such as damage caused by collision of the printing head with the foreign matters, dislocation of a model, poor interlayer adhesion, printing failure and the like can be caused in the printing process, and the quality of a printing finished product is seriously affected. In the related art, foreign matter detection is performed through manual naked eye observation, a user needs to intervene and check the printing process frequently, the use difficulty and the burden of the user are increased, the foreign matter can not be detected easily due to omission of manual detection, and the detection reliability is low. Disclosure of Invention In view of the above, the present application provides a method, apparatus, computer device and readable storage medium for detecting foreign matters in a printer, which mainly aims to solve the problems of high difficulty and low detection reliability of the conventional foreign matters detection by users. According to a first aspect of the present application, there is provided a foreign matter detection method of a 3D printer, the method comprising: The method comprises the steps of obtaining an image to be detected, wherein the image to be detected is obtained by shooting a hot bed in a 3D printer when a target component in the 3D printer is at a target height; Inputting the image to be detected into a pre-trained image recognition model to obtain hot bed recognition information; And generating a foreign matter detection result according to the hot bed identification information, wherein the foreign matter detection result is used for indicating whether the foreign matter exists on the hot bed or not in the current foreign matter detection process. According to a second aspect of the present application, there is provided a foreign matter detection device of a 3D printer, the device comprising: The device comprises an acquisition module, a detection module and a detection module, wherein the acquisition module is used for acquiring an image to be detected, and the image to be detected is obtained by shooting a hot bed in a 3D printer when a target component in the 3D printer is at a target height; The identification module is used for inputting the image to be detected into a pre-trained image identification model to obtain hot bed identification information; The detection result generation module is also used for generating a foreign matter detection result according to the hot bed identification information, and the foreign matter detection result is used for indicating whether the foreign matter exists on the hot bed or not in the current foreign matter detection process. According to a third aspect of the present application there is provided a computer device comprising a memory storing a computer program and a processor implementing the steps of the method of any of the first aspects described above when the computer program is executed by the processor. According to a fourth aspect of the present application there is provided a readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of the method of any of the first aspects described above. By means of the technical scheme, the foreign matter detection method, the device, the computer equipment and the readable storage medium of the 3D printer provided by the application are used for acquiring the image to be detected obtained by shooting the hot bed when the target part in the 3D printer is at the target height, inputting the image to be detected into a pre-trained image recognition model to obtain hot bed recognition information, and generating a foreign matter detection result according to the hot bed recognition information, wherein the foreign matter detection result is used for indicating whether foreign matters exist on the hot bed or not in the foreign matter detection process.