CN117058155B - 3DP metal printing powder spreading defect detection method, device, equipment and medium - Google Patents

3DP metal printing powder spreading defect detection method, device, equipment and medium Download PDF

Info

Publication number
CN117058155B
CN117058155B CN202311325852.3A CN202311325852A CN117058155B CN 117058155 B CN117058155 B CN 117058155B CN 202311325852 A CN202311325852 A CN 202311325852A CN 117058155 B CN117058155 B CN 117058155B
Authority
CN
China
Prior art keywords
defect
powder
image
target
powder spreading
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202311325852.3A
Other languages
Chinese (zh)
Other versions
CN117058155A (en
Inventor
杨艳艳
陈武涛
贺一轩
刘朝
成星
李庆
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Xi'an Aerospace Electromechanical Intelligent Manufacturing Co ltd
Original Assignee
Xi'an Aerospace Electromechanical Intelligent Manufacturing Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Xi'an Aerospace Electromechanical Intelligent Manufacturing Co ltd filed Critical Xi'an Aerospace Electromechanical Intelligent Manufacturing Co ltd
Priority to CN202311325852.3A priority Critical patent/CN117058155B/en
Publication of CN117058155A publication Critical patent/CN117058155A/en
Application granted granted Critical
Publication of CN117058155B publication Critical patent/CN117058155B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0004—Industrial image inspection
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B22—CASTING; POWDER METALLURGY
    • B22F—WORKING METALLIC POWDER; MANUFACTURE OF ARTICLES FROM METALLIC POWDER; MAKING METALLIC POWDER; APPARATUS OR DEVICES SPECIALLY ADAPTED FOR METALLIC POWDER
    • B22F10/00—Additive manufacturing of workpieces or articles from metallic powder
    • B22F10/10—Formation of a green body
    • B22F10/14—Formation of a green body by jetting of binder onto a bed of metal powder
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B22—CASTING; POWDER METALLURGY
    • B22F—WORKING METALLIC POWDER; MANUFACTURE OF ARTICLES FROM METALLIC POWDER; MAKING METALLIC POWDER; APPARATUS OR DEVICES SPECIALLY ADAPTED FOR METALLIC POWDER
    • B22F10/00—Additive manufacturing of workpieces or articles from metallic powder
    • B22F10/80—Data acquisition or data processing
    • B22F10/85—Data acquisition or data processing for controlling or regulating additive manufacturing processes
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B22—CASTING; POWDER METALLURGY
    • B22F—WORKING METALLIC POWDER; MANUFACTURE OF ARTICLES FROM METALLIC POWDER; MAKING METALLIC POWDER; APPARATUS OR DEVICES SPECIALLY ADAPTED FOR METALLIC POWDER
    • B22F12/00—Apparatus or devices specially adapted for additive manufacturing; Auxiliary means for additive manufacturing; Combinations of additive manufacturing apparatus or devices with other processing apparatus or devices
    • B22F12/90—Means for process control, e.g. cameras or sensors
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B33—ADDITIVE MANUFACTURING TECHNOLOGY
    • B33Y—ADDITIVE MANUFACTURING, i.e. MANUFACTURING OF THREE-DIMENSIONAL [3-D] OBJECTS BY ADDITIVE DEPOSITION, ADDITIVE AGGLOMERATION OR ADDITIVE LAYERING, e.g. BY 3-D PRINTING, STEREOLITHOGRAPHY OR SELECTIVE LASER SINTERING
    • B33Y50/00—Data acquisition or data processing for additive manufacturing
    • B33Y50/02—Data acquisition or data processing for additive manufacturing for controlling or regulating additive manufacturing processes
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84—Systems specially adapted for particular applications
    • G01N21/88—Investigating the presence of flaws or contamination
    • G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G06N3/0455—Auto-encoder networks; Encoder-decoder networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/0464—Convolutional networks [CNN, ConvNet]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/048—Activation functions
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84—Systems specially adapted for particular applications
    • G01N21/88—Investigating the presence of flaws or contamination
    • G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
    • G01N2021/8883—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges involving the calculation of gauges, generating models
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84—Systems specially adapted for particular applications
    • G01N21/88—Investigating the presence of flaws or contamination
    • G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
    • G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20081—Training; Learning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20084—Artificial neural networks [ANN]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30108—Industrial image inspection
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P10/00—Technologies related to metal processing
    • Y02P10/25—Process efficiency

Abstract

The embodiment of the invention discloses a 3DP metal printing powder paving defect detection method, a device, equipment and a medium, wherein the method comprises the following steps: collecting a powder spreading image on a powder bed, and determining a powder spreading image to be detected; preprocessing the powder spreading image to be detected through a preprocessing module to obtain a target tensor; inputting the target tensor into a preset detection algorithm model to detect whether the target-powder paving image has defects; if the target tensor has defects, determining a defect area according to the preset detection algorithm model; and generating defect detection information according to the defect area. By implementing the method provided by the embodiment of the invention, the defect of powder spreading can be monitored in real time by replacing human eyes with machine vision, so that the quality of powder spreading in the printing process is ensured.

Description

3DP metal printing powder spreading defect detection method, device, equipment and medium
Technical Field
The invention relates to the field of additive manufacturing, in particular to a 3DP metal printing powder spreading defect detection method, a device, equipment and a medium.
Background
3D printing (also called additive manufacturing) is used as one of the rapid prototyping technologies, and complex structural parts which are difficult to process and produce by the traditional process can be realized without a traditional model, so that the production process is effectively simplified, and the production period is shortened. Among them, 3DP (binder jetting) printing is a technique for constructing an object by layer-by-layer printing by bonding and molding material powder using a binder based on a digital model file. The 3DP technology has the advantages of high forming speed, low running cost and the like, and is considered to be one of the most potential new technologies in the field of additive manufacturing. However, in the specific printing powder spreading process, abnormal powder spreading can occur, if abnormal powder spreading is not found in time, abnormal conditions can be accumulated layer by layer, and part damage is very easy to cause. However, in the prior art, the defect of powder spreading is mainly detected by naked eyes of workers, so that the workload of the workers is increased, and the defect of powder spreading is easily omitted.
Disclosure of Invention
The embodiment of the invention provides a 3DP metal printing powder spreading defect detection method, device, equipment and medium, which are used for realizing that the machine vision is used for replacing manual real-time monitoring of the powder spreading defect in the 3D printing process and detecting a powder spreading image rapidly and accurately.
In a first aspect, an embodiment of the present invention provides a method for detecting a 3DP metal printing powder spreading defect, including: collecting a powder spreading image on a powder bed, and determining a powder spreading image to be detected; preprocessing the powder spreading image to be detected through a preprocessing module to obtain a target tensor; inputting the target tensor into a preset detection algorithm model to detect whether the target tensor has defects; if the target tensor has defects, determining a defect area according to the preset detection algorithm model; and generating defect detection information according to the defect area.
In a second aspect, an embodiment of the present invention further provides a 3DP metal printing powder spreading defect detection device, including: the collecting unit is used for collecting the powder paving image on the powder bed and determining the powder paving image to be detected; the preprocessing unit is used for preprocessing the powder spreading image to be detected through the preprocessing module to obtain a target tensor; the judging unit is used for inputting the target tensor into a preset detection algorithm model to detect whether the target tensor has defects; the determining unit is used for determining a defect area according to the preset detection algorithm model if the target tensor has a defect; and the generating unit is used for generating defect detection information according to the defect area.
In a third aspect, an embodiment of the present invention further provides a computer device, which includes a memory and a processor, where the memory stores a computer program, and the processor implements the method when executing the computer program.
In a fourth aspect, embodiments of the present invention also provide a computer readable storage medium storing a computer program comprising program instructions which, when executed by a processor, implement the above-described method.
The embodiment of the invention provides a 3DP metal printing powder spreading defect detection method, a device, equipment and a medium. Wherein the method comprises the following steps: collecting a powder spreading image on a powder bed, and determining a powder spreading image to be detected; preprocessing the powder spreading image to be detected through a preprocessing module to obtain a target tensor; inputting the target tensor into a preset detection algorithm model to detect whether the target tensor has defects; if the target tensor has defects, determining a defect area according to the preset detection algorithm model; and generating defect detection information according to the defect area. According to the embodiment of the invention, the powder laying image on the powder bed is acquired in real time, the powder laying image is preprocessed to obtain the target tensor, the target tensor is input into the preset detection algorithm model for defect detection, and if the target tensor has defects, corresponding defect detection information is generated, so that the problem that the human eyes are replaced by machine vision to monitor the powder laying defects in real time is solved, and the quality of the powder laying in the printing process is ensured.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of a 3DP metal printing powder spreading defect detection method provided by an embodiment of the invention;
FIG. 2 is a schematic diagram of a sub-flow of a 3DP metal printing powder spreading defect detection method provided in an embodiment of the present invention;
FIG. 3 is a schematic diagram of a sub-flow of a 3DP metal printing powder spreading defect detection method provided in an embodiment of the present invention;
FIG. 4 is a schematic diagram of a sub-flow of a 3DP metal printing powder spreading defect detection method provided by an embodiment of the present invention;
FIG. 5 is a defect type diagram of a 3DP metal printing powder spreading defect detection method provided by an embodiment of the invention;
FIG. 6 is a schematic diagram of a sub-flow of a 3DP metal printing powder spreading defect detection method provided by an embodiment of the present invention;
FIG. 7 is a schematic diagram of a sub-flow of a 3DP metal printing powder spreading defect detection method provided by an embodiment of the invention;
FIG. 8 is a schematic diagram of a sub-flow of a 3DP metal printing powder spreading defect detection method provided by an embodiment of the present invention;
FIG. 9 is a schematic block diagram of a 3DP metal printing powder spreading defect detection device provided by an embodiment of the invention;
fig. 10 is a schematic block diagram of a computer device according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
It should be understood that the terms "comprises" and "comprising," when used in this specification and the appended claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
It is also to be understood that the terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in this specification and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
It should be further understood that the term "and/or" as used in the present specification and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes such combinations.
Referring to fig. 1, fig. 1 is a flow chart of a 3DP metal printing powder spreading defect detection method according to an embodiment of the present invention. The 3DP metal printing powder spreading defect detection method in the embodiment can be applied to the powder spreading process of 3DP metal printing, the powder spreading image is collected through an industrial camera, and then the collected image is analyzed through an algorithm model to determine whether the powder spreading image has defects. The method can replace the defect of powder spreading in the 3DP metal printing process of naked eyes of workers to reduce the workload of the workers, so as to effectively ensure the quality of powder spreading in the printing process.
Fig. 1 is a schematic flow chart of a 3DP metal printing powder spreading defect detection method according to an embodiment of the present invention. As shown, the method includes the following steps S110-S150.
S110, collecting a powder spreading image on the powder bed, and determining the powder spreading image to be detected.
In this embodiment, the powder-spreading image to be detected is a powder-spreading image collected by an industrial camera from a powder bed. Specifically, an industrial camera is arranged above the powder bed, after each powder laying is completed, a powder laying image on the powder bed is acquired through the industrial camera, wherein the industrial camera is a special image acquisition device used for acquiring high-resolution image data and transmitting the image data to a computer system for processing.
S120, preprocessing the powder spreading image to be detected through a preprocessing module to obtain a target tensor. In this embodiment, the preprocessing module is a preset module for processing the powder spreading image to be detected. The preprocessing is to process the powder spreading image to be detected, and the preprocessing includes but is not limited to gray level conversion, image homogenization, image scale normalization, format conversion and the like of the powder spreading image to be detected. The target tensor of the preset format is obtained by preprocessing the powder spreading image to be detected, the preset size, the preset gray range and the target tensor of the preset format, and the target tensor of the preset format which is convenient for subsequent defect detection can be obtained by preprocessing the powder spreading image to be detected through the preprocessing module, so that the defect detection in the powder spreading process is more accurate and rapid.
In one embodiment, as shown in FIG. 2, the step S120 includes steps S121-S122.
S121, carrying out gray level conversion, image homogenization and image scale normalization on the powder spreading image to be detected;
s122, converting the processed powder paving image to be detected into the target tensor in a preset format.
In this embodiment, the gradation conversion refers to a method of changing the gradation value of each pixel in the source image point by point in a certain conversion relationship according to a certain target condition. Specifically, the pixel gray values of the powder spreading image to be detected are converted, so that the image quality is improved, and the display effect is clearer. The gray level conversion includes linear conversion, nonlinear conversion and other conversion modes, and is not limited to this, and the image homogenization is to make the image occupy as many gray levels as possible and be uniformly distributed; the image scale normalization means that the scale of the powder spreading image to be processed is unified with the scale in a preset algorithm model. Specifically, the color image of the powder spreading image to be detected, which is acquired by an industrial camera, is converted into a single-channel gray image, and the single-channel gray image is uniformly adjusted to the gray range according to a preset gray mean value and standard deviation so as to eliminate the influence of uneven illumination, and the input size of the algorithm model used subsequently is fixed, so that the powder spreading image to be detected needs to be scaled to be the same as the input size of the algorithm model; and finally, converting the processed powder paving image to be detected into a 4D Tensor format and loading the 4D Tensor format onto a GPU. Finally, the target Tensor in the 4D Tensor format after pretreatment is obtained. And performing gray conversion, image homogenization, image scale normalization and format conversion on the powder spreading image to be detected, so that defect detection is facilitated according to the obtained target tensor.
S130, inputting the target tensor into a preset detection algorithm model to detect whether the target tensor has defects.
In this embodiment, the preset detection algorithm model is a basic algorithm model based on a uiet++ algorithm model, where the uiet++ algorithm model is formed by adopting a classical encoder and decoder structure, and the preset detection algorithm model based on the uiet++ algorithm model can enable the preset detection algorithm model to have better feature extraction capability, so that a detection result is also more accurate. Specifically, the preset detection algorithm model may detect whether the target tensor has a defect, and may identify a defect type of the defect in the target tensor. Whether the target tensor has defects or not can be detected by the preset detection algorithm model to replace manual naked eye detection, so that a great amount of labor and time cost is saved, and the accuracy of a detection result is far higher than that of manual naked eye detection.
And S140, if the target tensor has defects, determining a defect area according to the preset detection algorithm model.
In this embodiment, if the preset detection algorithm model detects that the target tensor has a defect, the preset detection algorithm model classifies feature image pixels of the target tensor through a Softmax function in the model, generates a mask map of a defect area having a mapping relationship with the image to be detected, and can generate a JSON file according to the mask map, so as to facilitate detection processing of subsequent software. If the target tensor has no defect, the preset detection algorithm model returns a signal of the defect to a preset defect processing program. For example, if the target tensor has no defect, the Json file output by the preset detection algorithm model returns to "0" to a preset defect processing program, and the preset defect processing program notifies the printer device to perform the next layer of powder laying, and if the target tensor has a defect, the Json file output by the preset detection algorithm model returns to "1" and the determined defect information to the preset defect processing program. And determining a defect area by the target tensor with defects, so that the next step is conveniently executed according to the defect area judgment, the whole process does not need manual judgment, and the detection efficiency of the powder paving image is improved.
In one embodiment, as shown in FIG. 3, the step S140 includes steps S141-S142.
S141, if the target tensor has a defect, generating a defect mask diagram according to the defect and the preset detection algorithm model;
s142, determining the defect area according to the defect mask map.
In this embodiment, the defect Mask map is a Mask map, which is a binary image having the same size as the target image. Each pixel in the defect mask map is either 0, or 1, 2 or 3, wherein 0 indicates that the pixel point is a background, that is, the powder spreading image to be detected at the position has no defect, and other pixel values indicate the corresponding defect. The preset detection algorithm model judges that the defect is a scratch defect, and the defect mask map consists of pixels 0 and 1. If the target tensor has defects, generating a defect mask map according to the defects and the preset detection algorithm model, and determining the defect area according to the defect mask map. And determining the defect area through the defect mask map, so that different operations can be conveniently executed according to the defect area, and the obtained defect area has high accuracy.
And S150, generating defect detection information according to the defect area.
In this embodiment, the defect detection information is detection information generated by a preset defect processing program according to a defect area, where the defect detection information includes information such as a type, a defect size, and a defect coordinate of the defect area, specifically, after the preset defect processing program receives the defect area, mapping the defect area to obtain a mapping position of the powder spreading image to be detected, that is, obtain the defect area on the powder spreading image to be detected, and then generate the defect detection information having the type, the defect size, and the defect coordinate of the defect area. The defect type can be clearly known according to the specific defect detection information and is transmitted to the printing equipment, so that the powder spreading of each layer is monitored, the printing quality of the part is known in real time, if the abnormal condition of powder spreading occurs, the part can be processed in time, and the printing quality can be effectively guaranteed.
In one embodiment, as shown in FIG. 4, the step S150 includes steps S151-S152.
S151, determining the defect type of the defect area according to the defect mask map;
s152, generating the defect detection information according to the defect type.
In this embodiment, the defect types are classified into the defect types, where the defect types include: scratches, powder piles and missing facets. As shown in the defect type diagram of fig. 5, the number 1 is a scratch defect, which is a trace left on a powder bed in the powder laying process of a powder laying roller due to uneven shape or density of large particles or particles of metal powder, wherein the linear trace is formed in the same moving direction as the roller in the powder laying process. The number 2 is a powder pile defect, which refers to a powder pile with irregular protrusions formed by excessive local powder. Powder may shake off to the powder spreading surface due to accumulation of some powder build up on the rollers, which rubs against the raised metal surface. The number 3 indicates a defect, which is a defect that a part of the surface area is not covered by the metal powder, and may be caused by insufficient powder supply amount or a problem of a powder supply device. Specifically, the pixel values of the scratch, the powder pile and the defect surface are 1, 2 and 3 respectively, and the defect type can be judged according to the pixel values in the defect mask map, for example, if the defect mask map is formed by 0 and 2, the defect type is a powder pile defect. The scratch defect may then be written into the defect detection information. And determining the defect type of the defect area according to the defect mask map, and judging whether to continue laying powder according to the defect type.
In one embodiment, as shown in FIG. 6, the step S150 includes steps S153-S154.
S153, mapping and transforming the defect area to obtain a target defect area on the powder spreading image to be detected;
s154, acquiring the contour coordinates of the target defect area, and generating the defect detection information according to the contour coordinates.
In this embodiment, the target defect area on the to-be-detected powder-spreading image refers to a true defect area on the to-be-detected powder-spreading image. Because the defect region is a defect region on the target tensor, the target tensor is resized, the defect region needs to be mapped to obtain a true target defect region on the powder-laying image to be detected. Specifically, the process of restoring the defective area detected on the target tensor to the original image according to the scaling adopted at the time of image preprocessing, for example, the original size is 2000×2000, and the target tensor is 1000×1000, then according to 2:1, the target tensor and the original image can form a one-to-one correspondence relationship to obtain the target defect area, the coordinate system can be preset, for example, a coordinate axis is established by taking the center of a powder bed as an origin, so as to obtain the contour coordinate of the target defect area, the coordinate system is not limited, the contour coordinate of the target defect area can be unified, and the contour coordinate is written into the defect detection information, so that the follow-up equipment can know the specific position of the defect conveniently.
In one embodiment, as shown in FIG. 7, the step S150 includes steps S155-S156.
S155, determining the defect size of the target defect area according to the outline coordinates of the target defect area;
and S156, generating the defect detection information according to the defect size.
In this embodiment, the defect size refers to the size of the target defect area. And after the contour coordinates of the target defect area are obtained, determining the defect size of the target defect area according to the contour coordinates. And writing the defect size into the defect detection information to generate the defect detection information, and judging whether the defect affects the next powder spreading according to the visual defect size so as to facilitate the printing equipment to make corresponding measures according to the defect information.
In one embodiment, step S150 includes the further steps S1501-S1502 after step S150 is included as shown in FIG. 8.
S1501, judging whether the defect area affects the quality of a part to be printed according to the defect detection information;
s1502, if the quality of the part to be printed is affected, controlling the printing equipment to send out an alarm.
In this embodiment, the determining whether the defect area affects the quality of the part to be printed, specifically, the location, size and type of the defect may be known according to the defect detection information, for example, if the part to be printed is a high-precision part, a defect may affect the part to be printed, and the printing device is controlled to issue an alarm to notify a staff to perform an investigation; if the equipment to be printed is a non-high-precision part and can receive defects in a preset range, the size of the defect area is in the preset range, and the printing equipment can be controlled to continue laying powder; if the defect type is a scratch type, covering the defect when laying powder next time, and controlling the printing equipment to continue laying powder; or the defect area and the inside of the part to be printed can influence the quality of the part to be printed, and the printing equipment is controlled to send out an alarm. By judging whether the defect area affects the quality of the part to be printed according to the defect detection information, a worker can be informed in time to adjust the process parameters so as to avoid the occurrence of printing quality defects.
Fig. 9 is a schematic block diagram of a 3DP metal printing powder spreading defect detection device 200 according to an embodiment of the present invention. As shown in fig. 9, the invention further provides a 3DP metal printing powder spreading defect detection device corresponding to the above 3DP metal printing powder spreading defect detection method. The 3DP metal printing powder spreading defect detection device comprises a unit for executing the 3DP metal printing powder spreading defect detection method, and can be configured in a desktop computer, a tablet computer, a portable computer, and other terminals. Specifically, referring to fig. 9, the 3DP metal printing powder spreading defect detecting device includes an acquisition unit 210, a preprocessing unit 220, a judging unit 230, a determining unit 240, and a generating unit 250.
And the acquisition unit 210 is used for acquiring the powder paving image on the powder bed and determining the powder paving image to be detected.
The preprocessing unit 220 is configured to perform preprocessing on the powder-spread image to be detected through a preprocessing module, and obtain a target tensor.
In one embodiment, the preprocessing unit 220 includes a preprocessing subunit and a converting unit.
The preprocessing subunit is used for carrying out gray level conversion, image homogenization and image scale normalization on the powder spreading image to be detected;
the conversion unit is used for converting the processed powder paving image to be detected into the target tensor in a preset format.
The judging unit 230 is configured to input the target tensor into a preset detection algorithm model to detect whether the target tensor has a defect.
And the determining unit 240 is configured to determine a defect area according to the preset detection algorithm model if the target tensor has a defect.
In one embodiment, the determining unit 240 includes a defect generating unit and a determining subunit.
The defect generation unit is used for generating a defect mask map according to the defect and the preset detection algorithm model if the target tensor has the defect;
and the determining subunit is used for determining the defect area according to the defect mask map.
And a generating unit 250 for generating defect detection information according to the defect area.
In one embodiment, the generating unit 250 includes a type determining unit and a first generating unit.
A type determining unit, configured to determine a defect type of the defect area according to the defect mask map;
and the first generation unit is used for generating the defect detection information according to the defect type.
In one embodiment, the generating unit 250 includes a coordinate acquiring unit and a second generating unit.
The coordinate acquisition unit is used for mapping and transforming the defect area to acquire a target defect area on the powder spreading image to be detected;
and the second generation unit is used for acquiring the contour coordinates of the target defect area and generating the defect detection information according to the contour coordinates.
In an embodiment, the generating unit 250 includes a size obtaining unit and a third generating unit.
A size obtaining unit, configured to determine a defect size of the target defect area according to the contour coordinates of the target defect area;
and a third generation unit for generating the defect detection information according to the defect size.
In an embodiment, the generating unit 250 further includes a first judging unit and an alarm unit.
A first judging unit for judging whether the defect area affects the quality of the part to be printed according to the defect detection information;
and the alarm unit is used for controlling the printing equipment to send out an alarm if the quality of the part to be printed is affected.
It should be noted that, as those skilled in the art can clearly understand, the specific implementation process of the 3DP metal printing powder spreading defect detection device 200 and each unit may refer to the corresponding description in the foregoing method embodiment, and for convenience and brevity of description, the description is omitted here.
The 3DP metallic printing powder spread defect detecting device described above may be implemented in the form of a computer program that can be run on a computer device as shown in fig. 10.
Referring to fig. 10, fig. 10 is a schematic block diagram of a computer device according to an embodiment of the present application. The computer device 500 may be a server, and the server may be a stand-alone server or may be a server cluster formed by a plurality of servers.
With reference to FIG. 10, the computer device 500 includes a processor 502, memory, and a network interface 505 connected by a system bus 501, where the memory may include a non-volatile storage medium 503 and an internal memory 504.
The non-volatile storage medium 503 may store an operating system 5031 and a computer program 5032. The computer program 5032 includes program instructions that, when executed, cause the processor 502 to perform a 3DP metallic print powder spread defect detection method.
The processor 502 is used to provide computing and control capabilities to support the operation of the overall computer device 500.
The internal memory 504 provides an environment for the execution of a computer program 5032 in the non-volatile storage medium 503, which computer program 5032, when executed by the processor 502, causes the processor 502 to perform a 3DP metal print powder spread defect detection method.
The network interface 505 is used for network communication with other devices. Those skilled in the art will appreciate that the architecture shown in fig. 10 is merely a block diagram of a portion of the architecture in connection with the present application and is not intended to limit the computer device 500 to which the present application is applied, and that a particular computer device 500 may include more or fewer components than shown, or may combine certain components, or have a different arrangement of components.
Wherein the processor 502 is adapted to run a computer program 5032 stored in a memory for implementing the steps of the above method.
It should be appreciated that in embodiments of the present application, the processor 502 may be a central processing unit (Central Processing Unit, CPU), the processor 502 may also be other general purpose processors, digital signal processors (Digital Signal Processor, DSPs), application specific integrated circuits (Application Specific Integrated Circuit, ASICs), off-the-shelf programmable gate arrays (Field-Programmable Gate Array, FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. Wherein the general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
Those skilled in the art will appreciate that all or part of the flow in a method embodying the above described embodiments may be accomplished by computer programs instructing the relevant hardware. The computer program comprises program instructions, and the computer program can be stored in a storage medium, which is a computer readable storage medium. The program instructions are executed by at least one processor in the computer system to implement the flow steps of the embodiments of the method described above.
Accordingly, the present invention also provides a storage medium. The storage medium may be a computer readable storage medium. The storage medium stores a computer program, wherein the computer program includes program instructions. The program instructions, when executed by a processor, cause the processor to perform the steps of the method as described above.
The storage medium may be a U-disk, a removable hard disk, a Read-Only Memory (ROM), a magnetic disk, or an optical disk, or other various computer-readable storage media that can store program codes.
Those of ordinary skill in the art will appreciate that the elements and algorithm steps described in connection with the embodiments disclosed herein may be embodied in electronic hardware, in computer software, or in a combination of the two, and that the elements and steps of the examples have been generally described in terms of function in the foregoing description to clearly illustrate the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
In the several embodiments provided by the present invention, it should be understood that the disclosed apparatus and method may be implemented in other manners. For example, the device embodiments described above are merely illustrative. For example, the division of each unit is only one logic function division, and there may be another division manner in actual implementation. For example, multiple units or components may be combined or may be integrated into another system, or some features may be omitted, or not performed.
The steps in the method of the embodiment of the invention can be sequentially adjusted, combined and deleted according to actual needs. The units in the device of the embodiment of the invention can be combined, divided and deleted according to actual needs. In addition, each functional unit in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.
The integrated unit may be stored in a storage medium if implemented in the form of a software functional unit and sold or used as a stand-alone product. Based on such understanding, the technical solution of the present invention is essentially or a part contributing to the prior art, or all or part of the technical solution may be embodied in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a terminal, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention.
While the invention has been described with reference to certain preferred embodiments, it will be understood by those skilled in the art that various changes and substitutions of equivalents may be made and equivalents will be apparent to those skilled in the art without departing from the scope of the invention. Therefore, the protection scope of the invention is subject to the protection scope of the claims.

Claims (7)

1. A3 DP metal printing powder spreading defect detection method is characterized in that:
collecting a powder spreading image on a powder bed, and determining a powder spreading image to be detected;
preprocessing the powder spreading image to be detected through a preprocessing module to obtain a target tensor;
inputting the target tensor into a preset detection algorithm model to detect whether the target tensor has defects;
if the target tensor has defects, determining a defect area according to the preset detection algorithm model;
generating defect detection information according to the defect area;
the step of preprocessing the powder spreading image to be detected through a preprocessing module and obtaining a target tensor comprises the following steps:
carrying out gray level conversion, image homogenization and image scale normalization on the powder spreading image to be detected;
converting the processed powder spreading image to be detected into a target tensor in a preset format;
if the target tensor has a defect, determining a defect area according to the preset detection algorithm model includes:
if the target tensor has a defect, generating a defect mask diagram according to the defect and the preset detection algorithm model;
determining the defect area according to the defect mask map;
determining a defect type of the defect area according to the defect mask map, wherein the defect type comprises: scratches, powder piles and missing surfaces;
and generating the defect detection information according to the defect type.
2. The method of claim 1, wherein the step of generating defect detection information from the defect area further comprises:
mapping transformation is carried out on the defect area, and a target defect area on the powder spreading image to be detected is obtained;
and acquiring the contour coordinates of the target defect area, and generating the defect detection information according to the contour coordinates.
3. The method of claim 2, wherein after the step of obtaining the contour coordinates of the target defect area, further comprising:
determining the defect size of the target defect area according to the outline coordinates of the target defect area;
and generating the defect detection information according to the defect size.
4. The method according to claim 1, wherein after the step of generating defect detection information from the defect area, further comprising:
judging whether the defect area affects the quality of the part to be printed according to the defect detection information;
and if the quality of the part to be printed is affected, controlling the printing equipment to send out an alarm.
5. The utility model provides a 3DP metal print shop's powder defect detection device which characterized in that includes:
the collecting unit is used for collecting the powder paving image on the powder bed and determining the powder paving image to be detected;
the preprocessing unit is used for preprocessing the powder spreading image to be detected through the preprocessing module to obtain a target tensor;
the preprocessing subunit is used for carrying out gray level conversion, image homogenization and image scale normalization on the powder spreading image to be detected;
the conversion unit is used for converting the processed powder paving image to be detected into the target tensor in a preset format;
the judging unit is used for inputting the target tensor into a preset detection algorithm model to detect whether the target tensor has defects;
the determining unit is used for determining a defect area according to the preset detection algorithm model if the target tensor has a defect;
the defect generation unit is used for generating a defect mask map according to the defect and the preset detection algorithm model if the target tensor has the defect;
a determining subunit, configured to determine the defect area according to the defect mask map;
a type determining unit, configured to determine a defect type of the defect area according to the defect mask map, where the defect type includes: scratches, powder piles and missing surfaces;
a first generation unit configured to generate the defect detection information according to the defect type;
and the generating unit is used for generating defect detection information according to the defect area.
6. A computer device, characterized in that it comprises a memory on which a computer program is stored and a processor which, when executing the computer program, implements the method according to any of claims 1-4.
7. A storage medium storing a computer program comprising program instructions which, when executed by a processor, implement the method of any one of claims 1-4.
CN202311325852.3A 2023-10-13 2023-10-13 3DP metal printing powder spreading defect detection method, device, equipment and medium Active CN117058155B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202311325852.3A CN117058155B (en) 2023-10-13 2023-10-13 3DP metal printing powder spreading defect detection method, device, equipment and medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202311325852.3A CN117058155B (en) 2023-10-13 2023-10-13 3DP metal printing powder spreading defect detection method, device, equipment and medium

Publications (2)

Publication Number Publication Date
CN117058155A CN117058155A (en) 2023-11-14
CN117058155B true CN117058155B (en) 2024-03-12

Family

ID=88666756

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202311325852.3A Active CN117058155B (en) 2023-10-13 2023-10-13 3DP metal printing powder spreading defect detection method, device, equipment and medium

Country Status (1)

Country Link
CN (1) CN117058155B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117245104B (en) * 2023-11-16 2024-03-12 西安空天机电智能制造有限公司 Monitoring method, device, equipment and medium for 3DP metal printing defect identification

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113763355A (en) * 2021-09-07 2021-12-07 创新奇智(青岛)科技有限公司 Defect detection method and device, electronic equipment and storage medium
CN115829999A (en) * 2022-12-22 2023-03-21 国网新疆电力有限公司信息通信公司 Insulator defect detection model generation method, device, equipment and storage medium
WO2023087741A1 (en) * 2021-11-18 2023-05-25 上海商汤智能科技有限公司 Defect detection method and apparatus, and electronic device, storage medium and computer program product
WO2023125838A1 (en) * 2021-12-30 2023-07-06 深圳云天励飞技术股份有限公司 Data processing method and apparatus, terminal device, and computer readable storage medium
CN116542984A (en) * 2023-07-07 2023-08-04 浙江省北大信息技术高等研究院 Hardware defect detection method, device, computer equipment and storage medium
WO2023179122A1 (en) * 2022-03-23 2023-09-28 广东利元亨智能装备股份有限公司 Defect detection method and apparatus, electronic device, and readable storage medium

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113763355A (en) * 2021-09-07 2021-12-07 创新奇智(青岛)科技有限公司 Defect detection method and device, electronic equipment and storage medium
WO2023087741A1 (en) * 2021-11-18 2023-05-25 上海商汤智能科技有限公司 Defect detection method and apparatus, and electronic device, storage medium and computer program product
WO2023125838A1 (en) * 2021-12-30 2023-07-06 深圳云天励飞技术股份有限公司 Data processing method and apparatus, terminal device, and computer readable storage medium
WO2023179122A1 (en) * 2022-03-23 2023-09-28 广东利元亨智能装备股份有限公司 Defect detection method and apparatus, electronic device, and readable storage medium
CN115829999A (en) * 2022-12-22 2023-03-21 国网新疆电力有限公司信息通信公司 Insulator defect detection model generation method, device, equipment and storage medium
CN116542984A (en) * 2023-07-07 2023-08-04 浙江省北大信息技术高等研究院 Hardware defect detection method, device, computer equipment and storage medium

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
Infrared dim target detection via mode-k1k2 extension tensor tubal rank under complex ocean environment;Zhaoyang Cao等;《ISPRS Journal of Photogrammetry and Remote Sensing》;全文 *
张量化扩展变换的低秩图像修复算法;诸葛燕;徐宏辉;郑建炜;;浙江工业大学学报(03);全文 *

Also Published As

Publication number Publication date
CN117058155A (en) 2023-11-14

Similar Documents

Publication Publication Date Title
CN117058155B (en) 3DP metal printing powder spreading defect detection method, device, equipment and medium
JP2017107541A (en) Information processing apparatus, information processing method, program, and inspection system
CN115641332B (en) Method, device, medium and equipment for detecting product edge appearance defects
CN112712513A (en) Product defect detection method, device, equipment and computer readable storage medium
CN113066088A (en) Detection method, detection device and storage medium in industrial detection
CN108871185B (en) Method, device and equipment for detecting parts and computer readable storage medium
CN111539927A (en) Detection process and algorithm of automobile plastic assembly fastening buckle lack-assembly detection device
CN110378887A (en) Screen defect inspection method, apparatus and system, computer equipment and medium
JP2020087211A (en) Learning model creation device, type determination system, and learning model creation method
CN111221996B (en) Instrument screen vision detection method and system
CN114216911A (en) Powder laying quality monitoring and controlling method in metal selective laser melting forming
US20220281177A1 (en) Ai-powered autonomous 3d printer
US20210027463A1 (en) Video image processing and motion detection
US11493453B2 (en) Belt inspection system, belt inspection method, and recording medium for belt inspection program
CN101685000B (en) Computer system and method for image boundary scan
CN110632094B (en) Pattern quality detection method, device and system based on point-by-point comparison analysis
CN112488986A (en) Cloth surface flaw identification method, device and system based on Yolo convolutional neural network
CN114723728A (en) Method and system for detecting CD line defects of silk screen of glass cover plate of mobile phone camera
CN109334009B (en) Powder paving control method and device and readable storage medium
CN117058154B (en) Defect identification method, system and medium for 3DP metal printing powder spreading process
CN113379729A (en) Image tiny anomaly detection method and device and computer readable storage medium
CN111415611A (en) Brightness compensation method, brightness compensation device and display device
CN117173185B (en) Method and device for detecting area of rolled plate, storage medium and computer equipment
CN114782400B (en) Method, device, equipment, medium and program product for detecting slag point of metal material
Marković et al. Improving sub-pixel estimation of laser stripe reflection center by autoconvolution on FPGA

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant