CN117077022B - 3D printer wire feeding mechanism flow monitoring method - Google Patents

3D printer wire feeding mechanism flow monitoring method Download PDF

Info

Publication number
CN117077022B
CN117077022B CN202311331136.6A CN202311331136A CN117077022B CN 117077022 B CN117077022 B CN 117077022B CN 202311331136 A CN202311331136 A CN 202311331136A CN 117077022 B CN117077022 B CN 117077022B
Authority
CN
China
Prior art keywords
sample
printer
samples
nearest neighbor
feature vector
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
CN202311331136.6A
Other languages
Chinese (zh)
Other versions
CN117077022A (en
Inventor
李程
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.)
Shenzhen Jiexinhua Technology Co ltd
Original Assignee
Shenzhen Jiexinhua Technology 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 Shenzhen Jiexinhua Technology Co ltd filed Critical Shenzhen Jiexinhua Technology Co ltd
Priority to CN202311331136.6A priority Critical patent/CN117077022B/en
Publication of CN117077022A publication Critical patent/CN117077022A/en
Application granted granted Critical
Publication of CN117077022B publication Critical patent/CN117077022B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
    • G06F18/24147—Distances to closest patterns, e.g. nearest neighbour classification
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B29—WORKING OF PLASTICS; WORKING OF SUBSTANCES IN A PLASTIC STATE IN GENERAL
    • B29C—SHAPING OR JOINING OF PLASTICS; SHAPING OF MATERIAL IN A PLASTIC STATE, NOT OTHERWISE PROVIDED FOR; AFTER-TREATMENT OF THE SHAPED PRODUCTS, e.g. REPAIRING
    • B29C64/00—Additive manufacturing, i.e. manufacturing of three-dimensional [3D] objects by additive deposition, additive agglomeration or additive layering, e.g. by 3D printing, stereolithography or selective laser sintering
    • B29C64/30—Auxiliary operations or equipment
    • B29C64/307—Handling of material to be used in additive manufacturing
    • B29C64/321—Feeding
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B29—WORKING OF PLASTICS; WORKING OF SUBSTANCES IN A PLASTIC STATE IN GENERAL
    • B29C—SHAPING OR JOINING OF PLASTICS; SHAPING OF MATERIAL IN A PLASTIC STATE, NOT OTHERWISE PROVIDED FOR; AFTER-TREATMENT OF THE SHAPED PRODUCTS, e.g. REPAIRING
    • B29C64/00—Additive manufacturing, i.e. manufacturing of three-dimensional [3D] objects by additive deposition, additive agglomeration or additive layering, e.g. by 3D printing, stereolithography or selective laser sintering
    • B29C64/30—Auxiliary operations or equipment
    • B29C64/386—Data acquisition or data processing for additive manufacturing
    • 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
    • B33Y40/00—Auxiliary operations or equipment, e.g. for material handling
    • 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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/10—Pre-processing; Data cleansing
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
    • G06F2218/02—Preprocessing
    • G06F2218/04—Denoising
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
    • G06F2218/12—Classification; Matching
    • 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

Landscapes

  • Engineering & Computer Science (AREA)
  • Materials Engineering (AREA)
  • Chemical & Material Sciences (AREA)
  • Physics & Mathematics (AREA)
  • Manufacturing & Machinery (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Evolutionary Computation (AREA)
  • Evolutionary Biology (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Mechanical Engineering (AREA)
  • Optics & Photonics (AREA)
  • Accessory Devices And Overall Control Thereof (AREA)

Abstract

The invention particularly relates to a 3D printer wire feeder flow monitoring method, which comprises the steps of acquiring signals of a 3D printer, collecting signals capable of representing the wire feeder flow, denoising and filtering the signals, processing the signals capable of representing the wire feeder flow into feature vectors, constructing an improved k nearest neighbor algorithm model, and classifying the feature vectors based on the improved k nearest neighbor algorithm; then sequentially calculating vectors of k adjacent samples and samples to be tested, determining a substitute sample B, calculating a nearest adjacent sample B 'of the substitute sample B, and taking a class label of the nearest adjacent sample B' of the substitute sample B as a class label of the samples to be tested; and when the flow of the wire feeding mechanism is required to be monitored, firstly acquiring a signal representing the flow of the wire feeding mechanism, then processing the signal capable of representing the flow of the wire feeding mechanism into a feature vector, inputting the feature vector into a constructed improved k-nearest neighbor algorithm model for outputting classification, and further determining the state of the 3D printer.

Description

3D printer wire feeding mechanism flow monitoring method
Technical Field
The invention belongs to the field of printer control, and particularly relates to a 3D printer wire feeding mechanism flow monitoring method.
Background
The relation between the wire feeding speed and the printing speed in the 3D printer is very important, the speed relation between the wire feeding speed and the printing speed can directly influence the printing quality, so that the flow of the printer needs to be monitored in practice, the related prior art is to monitor the flow through a data processing method, for example, the flow is monitored through collecting signals of nozzle vibration, converting the signals into frequency domain signals, processing the frequency domain signals into feature vectors, analyzing and identifying feature vector clusters through a K nearest neighbor algorithm, and the working state of the printer is determined through the quantitative identification of the relation between the wire feeding speed and the printing speed.
The core of the technology is data processing and model selection, however, the technology adopts a simple K-nearest neighbor algorithm in the identification of the feature vector, the K-nearest neighbor algorithm essentially determines the class of the sample according to the degree of approach to the sample to be detected in the vector position, in actual discrimination, the classification of a large number of samples in K-nearest neighbor samples is simply determined to be used as the classification of the sample to be detected, in practice, the classification method is rough, and classification errors often occur, so that the method cannot meet the requirement of high identification accuracy.
Disclosure of Invention
The invention aims to provide a 3D printer wire feeding mechanism flow monitoring method for solving the problems in the background technology.
In order to solve the technical problems, the invention provides the following technical scheme:
the 3D printer wire feeding mechanism flow monitoring method comprises the steps of,
acquiring signals of a 3D printer, acquiring signals capable of representing the flow of a wire feeding mechanism, denoising and filtering the signals, processing the signals capable of representing the flow of the wire feeding mechanism as feature vectors, constructing an improved k-nearest neighbor algorithm model, and classifying the feature vectors based on the improved k-nearest neighbor algorithm; the improved k-nearest neighbor algorithm specifically refers to that each sample is characterized by a feature vector, a part of samples are selected as a standard sample set, the standard sample set is manually classified, category labels of each sample are determined, and k adjacent samples A of the sample to be detected are calculated 1 ，A 2 ，……A k The method comprises the steps of carrying out a first treatment on the surface of the Then sequentially calculating vectors of k adjacent samples and samples to be tested, determining a substitute sample B, calculating a nearest adjacent sample B 'of the substitute sample B, and taking a class label of the nearest adjacent sample B' of the substitute sample B as a class label of the samples to be tested; and when the flow of the wire feeding mechanism is required to be monitored, firstly acquiring a signal representing the flow of the wire feeding mechanism, then processing the signal capable of representing the flow of the wire feeding mechanism into a feature vector, inputting the feature vector into a constructed improved k-nearest neighbor algorithm model for outputting classification, and further determining the state of the 3D printer.
Further, the category label is used to distinguish categories of the sample, including fault categories of the 3D printer.
Further, the k-nearest neighbor algorithm model specifically refers to an algorithm model constructed on the basis of the improved k-nearest neighbor algorithm, and a standard sample set, feature vectors of each sample in the standard sample set and class labels of each sample in the standard sample set are stored in the algorithm model.
Further, k adjacent samples A of the sample to be measured are calculated 1 ，A 2 ，……A k The method comprises the steps of carrying out a first treatment on the surface of the Then sequentially calculating vectors of k adjacent samples and samples to be tested and determining a substitute sample B, specifically, setting the feature vector of each sample as m-dimension, and taking the feature vector of the ith sample as (i) 1 ，i 2 ，i 3 ，......，i m ) Let the feature vector of the sample to be measured be (x) 0 1 ，x 0 2 ，x 0 3 ，......，x 0 m ) The feature vectors of k neighboring samples are [ (y) 1 1 ，y 1 2 ，y 1 3 ......，y 1 m ），（y 2 1 ，y 2 2 ，y 2 3 ......，y 2 m ），......，（y k 1 ，y k 2 ，y k 3 ......，y k m ) Then the eigenvector of the substitute sample B isWhere j represents a variable in the summation function, and the nearest sample B 'of the alternative sample B is determined by calculating the distance between the other samples and the alternative sample B, and then the nearest sample B' of the alternative sample B is the sample closest to B.
Further, the distance calculation uses the euclidean distance.
A machine readable medium storing program code for data processing functions in a 3D printer wire feeder flow monitoring method.
A computer for executing program code for data processing functions in a 3D printer wire feeder flow monitoring method.
The beneficial effects are that: according to the improved k-nearest neighbor algorithm, the influence of each sample in k adjacent samples on the sample to be detected is comprehensively considered, a new substitute sample is determined on the basis of the comprehensive influence, then the corresponding classification is determined only by purposefully searching for the nearest sample close to the substitute sample, the classification of the sample to be detected can be accurately determined, and the accuracy of 3D printer state judgment is improved.
Drawings
Fig. 1 is a flowchart of a method for monitoring flow of a wire feeding mechanism of a 3D printer according to the present application.
Detailed Description
The technical solutions of the embodiments of the present invention will be clearly and completely described below in conjunction with the embodiments of the present invention, and it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. 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.
The application discloses 3D printer wire feed mechanism flow monitoring method, like fig. 1, including the step, acquire the signal of 3D printer to gather the signal that can represent wire feed mechanism flow, specifically, the signal that can represent wire feed mechanism flow is many, has the signal that gathers shower nozzle vibration signal as can represent wire feed mechanism flow like prior art.
Denoising and filtering signals, then processing the signals capable of representing the flow of the wire feeding mechanism into feature vectors, and processing the signals capable of representing the flow of the wire feeding mechanism into feature vectors in the prior art, wherein the general method is to firstly perform feature coding on the signals, and process the signals into numerical features which can be processed by a computer, such as a binary method, one-hot coding, normal distribution with a mean value of 0 and a variance of 1; the method also comprises a characteristic component, wherein a statistical calculation average value, variance, extremum and the like are generally used as new characteristics or multiple characteristics are combined into new characteristics; then normalizing and processing the features into feature vectors; for example, the prior art normalizes the measured signal, then fourier transforms the normalized signal to obtain a frequency domain signal, and extractsExtremum and the like to obtain a feature vector. Then an improved k-nearest neighbor algorithm model is constructed, and feature vectors are classified based on an improved k-nearest neighbor algorithm; the improved k-nearest neighbor algorithm specifically refers to that each sample is characterized by a feature vector, a part of samples are firstly selected as a standard sample set, the standard sample set is manually classified, category labels of each sample are determined, the category labels are mainly used for distinguishing categories of the samples, the categories comprise fault categories of a 3D printer, and k adjacent samples A of the samples to be detected are calculated 1 ，A 2 ，……A k The method comprises the steps of carrying out a first treatment on the surface of the Then sequentially calculating vectors of k adjacent samples and samples to be tested, determining a substitute sample B, calculating a nearest adjacent sample B 'of the substitute sample B, and taking a class label of the nearest adjacent sample B' of the substitute sample B as a class label of the samples to be tested;
the k-nearest neighbor algorithm model specifically refers to an algorithm model constructed on the basis of an improved k-nearest neighbor algorithm, and a standard sample set, a feature vector of each sample in the standard sample set and a class label of each sample in the standard sample set are stored in the algorithm model; for the sample to be measured, k adjacent samples A are calculated 1 ，A 2 ，……A k The method comprises the steps of carrying out a first treatment on the surface of the Then sequentially calculating vectors of k adjacent samples and samples to be tested and determining a substitute sample B, specifically, setting the feature vector of each sample as m-dimension, and taking the feature vector of the ith sample as (i) 1 ，i 2 ，i 3 ，......，i m ) Let the feature vector of the sample to be measured be (x) 0 1 ，x 0 2 ，x 0 3 ，......，x 0 m ) The feature vectors of k neighboring samples are [ (y) 1 1 ，y 1 2 ，y 1 3 ......，y 1 m ），（y 2 1 ，y 2 2 ，y 2 3 ......，y 2 m ），......，（y k 1 ，y k 2 ，y k 3 ......，y k m ) Then the eigenvector of the substitute sample B isIn the formula, the symbol "j" is an intermediate variable, used for counting, has no practical meaning, and has a mathematical name of "variable", j represents a variable in the summation function, and the nearest sample B 'of the alternative sample B is determined by calculating the distance from other samples to the alternative sample B, and then the nearest sample B' of the alternative sample B is the sample closest to B; the distance calculation can be carried out by adopting Euclidean distance or other distances such as Manhattan distance in the prior art; and when the flow of the wire feeding mechanism is required to be monitored, firstly acquiring a signal representing the flow of the wire feeding mechanism, then processing the signal capable of representing the flow of the wire feeding mechanism into a feature vector, inputting the feature vector into a constructed improved k-nearest neighbor algorithm model for outputting classification, and further determining the state of the 3D printer.
The process of calculating vectors of k adjacent samples and samples to be measured and determining one substitute sample B in sequence is illustrated in the present application,
assuming that the feature vector of each sample is 3-dimensional, the feature vector of the i-th sample is (i) 1 ，i 2 ，i 3 ) Let the feature vector of the sample to be measured be (x) 0 1 ，x 0 2 ，x 0 3 ) K is 3, then the k neighboring sample feature vectors are [ (y 1 1 ，y 1 2 ，y 1 3 ），（y 2 1 ，y 2 2 ，y 2 3 ），（y 3 1 ，y 3 2 ，y 3 3 ) Then the eigenvector of the substitute sample B isThen the eigenvector of the substitute sample B is (y 1 1 +y 2 1 +y 3 1 ，y 1 2 +y 2 2 +y 3 2 ，y 1 3 +y 2 3 +y 3 3 ) Determining the nearest neighbor sample B' of the substitute sample B by calculating the distance of other samples to the substitute sample B, then the substitute sample BThe nearest neighbor sample B' is the sample closest to B.
The improved k-nearest neighbor algorithm comprehensively considers the influence of each sample in k adjacent samples on the sample to be detected, determines a new substitute sample based on the comprehensive influence, and then determines corresponding classification only by purposefully searching a nearest adjacent sample close to the substitute sample.
Embodiments of the present application include:
the application discloses a 3D printer wire feeding mechanism flow monitoring method, which comprises the steps of,
acquiring signals of a 3D printer, acquiring signals capable of representing the flow of a wire feeding mechanism, denoising and filtering the signals, processing the signals capable of representing the flow of the wire feeding mechanism as feature vectors, constructing an improved k-nearest neighbor algorithm model, and classifying the feature vectors based on the improved k-nearest neighbor algorithm; the improved k-nearest neighbor algorithm specifically refers to that each sample is characterized by a feature vector, a part of samples are selected as a standard sample set, the standard sample set is manually classified, category labels of each sample are determined, and k adjacent samples A of the sample to be detected are calculated 1 ，A 2 ，……A k The method comprises the steps of carrying out a first treatment on the surface of the Then sequentially calculating vectors of k adjacent samples and samples to be tested, determining a substitute sample B, calculating a nearest adjacent sample B 'of the substitute sample B, and taking a class label of the nearest adjacent sample B' of the substitute sample B as a class label of the samples to be tested; and when the flow of the wire feeding mechanism is required to be monitored, firstly acquiring a signal representing the flow of the wire feeding mechanism, then processing the signal capable of representing the flow of the wire feeding mechanism into a feature vector, inputting the feature vector into a constructed improved k-nearest neighbor algorithm model for outputting classification, and further determining the state of the 3D printer.
Preferably, the class label is used to distinguish classes of the sample, the classes including failure classes of the 3D printer.
Preferably, the k-nearest neighbor algorithm model specifically refers to an algorithm model constructed on the basis of the improved k-nearest neighbor algorithm, and a standard sample set, a feature vector of each sample in the standard sample set and a class label of each sample in the standard sample set are stored in the algorithm model.
Preferably, k adjacent samples A of the sample to be measured are calculated 1 ，A 2 ，……A k The method comprises the steps of carrying out a first treatment on the surface of the Then sequentially calculating vectors of k adjacent samples and samples to be tested and determining a substitute sample B, specifically, setting the feature vector of each sample as m-dimension, and taking the feature vector of the ith sample as (i) 1 ，i 2 ，i 3 ，......，i m ) Let the feature vector of the sample to be measured be (x) 0 1 ，x 0 2 ，x 0 3 ，......，x 0 m ) The feature vectors of k neighboring samples are [ (y) 1 1 ，y 1 2 ，y 1 3 ......，y 1 m ），（y 2 1 ，y 2 2 ，y 2 3 ......，y 2 m ），......，（y k 1 ，y k 2 ，y k 3 ......，y k m ) Then the eigenvector of the substitute sample B isThe nearest neighbor sample B' of the substitute sample B is determined by calculating the distance from other samples to the substitute sample B, and is the sample closest to B.
Preferably, the distance calculation uses Euclidean distance.
Program code for data processing functions in the 3D printer wire feeder flow monitoring methods herein is stored on a machine readable medium, which may be a tangible medium that can contain, or store, a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. The machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. To provide for interaction with a user, the data processing in the 3D printer wire feeder flow monitoring method described herein may be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and pointing device (e.g., a mouse or trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.
It will be appreciated by those skilled in the art that the present invention can be carried out in other embodiments without departing from the spirit or essential characteristics thereof. The above disclosed embodiments are illustrative in all respects only and not all changes that come within the scope of the invention or are equivalent to the invention are intended to be embraced therein.

Claims (6)

  1. The 3D printer wire feeder flow monitoring method is characterized by comprising the steps of obtaining signals of a 3D printer, collecting signals capable of representing the wire feeder flow, denoising and filtering the signals, processing the signals capable of representing the wire feeder flow into feature vectors, constructing an improved k nearest neighbor algorithm model, and classifying the feature vectors based on the improved k nearest neighbor algorithm; the improved k-nearest neighbor algorithm specifically refers to that each sample is characterized by a feature vector, and a part of samples are selected as a standard sample setManually classifying the standard sample set, determining the class label of each sample, and calculating k adjacent samples A of the sample to be tested 1 ，A 2 ，……A k The method comprises the steps of carrying out a first treatment on the surface of the Then sequentially calculating vectors of k adjacent samples and samples to be tested and determining a substitute sample B, specifically, setting the feature vector of each sample as m-dimension, and taking the feature vector of the ith sample as (i) 1 ，i 2 ，i 3 ，......，i m ) Let the feature vector of the sample to be measured be (x) 0 1 ，x 0 2 ，x 0 3 ，......，x 0 m ) The feature vectors of k neighboring samples are [ (y) 1 1 ，y 1 2 ，y 1 3 ......，y 1 m ），（y 2 1 ，y 2 2 ，y 2 3 ......，y 2 m ），......，（y k 1 ，y k 2 ，y k 3 ......，y k m ) Then the eigenvector of the substitute sample B isWhere j represents a variable in the summation function, determining a nearest neighbor sample B 'of the substitute sample B by calculating the distance from other samples to the substitute sample B, and then the nearest neighbor sample B' of the substitute sample B is the sample closest to the substitute sample B; the class label of the nearest sample B' of the sample B is replaced to be used as the class label of the sample to be tested; and when the flow of the wire feeding mechanism is required to be monitored, firstly acquiring a signal representing the flow of the wire feeding mechanism, then processing the signal capable of representing the flow of the wire feeding mechanism into a feature vector, inputting the feature vector into a constructed improved k-nearest neighbor algorithm model for outputting classification, and further determining the state of the 3D printer.
  2. 2. The 3D printer wire feeder flow monitoring method of claim 1, wherein a category label is used to distinguish categories of samples, the categories including failure categories of the 3D printer.
  3. 3. The 3D printer wire feeder flow monitoring method of claim 1, wherein the k-nearest neighbor algorithm model specifically refers to an algorithm model constructed on the basis of a modified k-nearest neighbor algorithm, and a standard sample set, a feature vector of each sample in the standard sample set, and a class label of each sample in the standard sample set are stored in the algorithm model.
  4. 4. The 3D printer wire feeder flow monitoring method of claim 1, wherein the distance calculation uses euclidean distance.
  5. 5. A machine readable medium storing program code for data processing functions in the 3D printer wire feeder flow monitoring method of claim 1.
  6. 6. A computer characterized by program code for performing the 3D printer wire feeder flow monitoring method of claim 1 with respect to data processing functions.
CN202311331136.6A 2023-10-16 2023-10-16 3D printer wire feeding mechanism flow monitoring method Active CN117077022B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202311331136.6A CN117077022B (en) 2023-10-16 2023-10-16 3D printer wire feeding mechanism flow monitoring method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202311331136.6A CN117077022B (en) 2023-10-16 2023-10-16 3D printer wire feeding mechanism flow monitoring method

Publications (2)

Publication Number Publication Date
CN117077022A CN117077022A (en) 2023-11-17
CN117077022B true CN117077022B (en) 2024-01-30

Family

ID=88704622

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202311331136.6A Active CN117077022B (en) 2023-10-16 2023-10-16 3D printer wire feeding mechanism flow monitoring method

Country Status (1)

Country Link
CN (1) CN117077022B (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106778869A (en) * 2016-12-16 2017-05-31 重庆邮电大学 A kind of quick accurate nearest neighbour classification algorithm based on reference point
CN109255363A (en) * 2018-07-11 2019-01-22 齐鲁工业大学 A kind of fuzzy k nearest neighbor classification method and system based on weighted chi-square distance metric
CN111898443A (en) * 2020-06-30 2020-11-06 江苏科技大学 Flow monitoring method for wire feeding mechanism of FDM type 3D printer
CN112819047A (en) * 2021-01-22 2021-05-18 西安交通大学 Double nearest neighbor classification method and system based on two-layer neighborhood information

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9037518B2 (en) * 2012-07-30 2015-05-19 Hewlett-Packard Development Company, L.P. Classifying unclassified samples
US9378466B2 (en) * 2013-12-31 2016-06-28 Google Inc. Data reduction in nearest neighbor classification

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106778869A (en) * 2016-12-16 2017-05-31 重庆邮电大学 A kind of quick accurate nearest neighbour classification algorithm based on reference point
CN109255363A (en) * 2018-07-11 2019-01-22 齐鲁工业大学 A kind of fuzzy k nearest neighbor classification method and system based on weighted chi-square distance metric
CN111898443A (en) * 2020-06-30 2020-11-06 江苏科技大学 Flow monitoring method for wire feeding mechanism of FDM type 3D printer
CN112819047A (en) * 2021-01-22 2021-05-18 西安交通大学 Double nearest neighbor classification method and system based on two-layer neighborhood information

Also Published As

Publication number Publication date
CN117077022A (en) 2023-11-17

Similar Documents

Publication Publication Date Title
CN110807086B (en) Text data labeling method and device, storage medium and electronic equipment
CN112052813B (en) Method and device for identifying translocation between chromosomes, electronic equipment and readable storage medium
Guh Robustness of the neural network based control chart pattern recognition system to non‐normality
CN110490486B (en) Enterprise big data management system
CN113852603A (en) Method and device for detecting abnormality of network traffic, electronic equipment and readable medium
CN111898443A (en) Flow monitoring method for wire feeding mechanism of FDM type 3D printer
CN107016416B (en) Data classification prediction method based on neighborhood rough set and PCA fusion
CN111125658A (en) Method, device, server and storage medium for identifying fraudulent users
CN112639431A (en) Abnormality prediction system and abnormality prediction method
CN115758200A (en) Vibration signal fault identification method and system based on similarity measurement
CN114700587B (en) Missing welding defect real-time detection method and system based on fuzzy inference and edge calculation
CN114610561A (en) System monitoring method, device, electronic equipment and computer readable storage medium
Wen et al. A new method for identifying the ball screw degradation level based on the multiple classifier system
CN114240817A (en) Data analysis method and device, electronic equipment and storage medium
CN117077022B (en) 3D printer wire feeding mechanism flow monitoring method
CN116842330B (en) Health care information processing method and device capable of comparing histories
CN111863135B (en) False positive structure variation filtering method, storage medium and computing device
CN113553319A (en) LOF outlier detection cleaning method, device and equipment based on information entropy weighting and storage medium
CN110826616A (en) Information processing method and device, electronic equipment and storage medium
CN113393169B (en) Financial industry transaction system performance index analysis method based on big data technology
CN115690514A (en) Image recognition method and related equipment
JP5640796B2 (en) Name identification support processing apparatus, method and program
Zou et al. Development of tool wear condition on-line monitoring method for impeller milling based on new data processing approach and DAE-BP-ANN-integrated modeling
CN113962216A (en) Text processing method and device, electronic equipment and readable storage medium
CN113781239A (en) Policy determination method and device, electronic equipment and storage medium

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