CN113505960A - Printing condition online identification method and system, electronic equipment and storage medium - Google Patents
Printing condition online identification method and system, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN113505960A CN113505960A CN202110578063.5A CN202110578063A CN113505960A CN 113505960 A CN113505960 A CN 113505960A CN 202110578063 A CN202110578063 A CN 202110578063A CN 113505960 A CN113505960 A CN 113505960A
- Authority
- CN
- China
- Prior art keywords
- data
- working condition
- bottom plate
- online identification
- track
- 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.)
- Granted
Links
- 238000007639 printing Methods 0.000 title claims abstract description 120
- 238000000034 method Methods 0.000 title claims abstract description 107
- 238000003860 storage Methods 0.000 title claims abstract description 16
- 230000008569 process Effects 0.000 claims abstract description 60
- 238000012549 training Methods 0.000 claims abstract description 40
- 238000012360 testing method Methods 0.000 claims description 50
- 230000001133 acceleration Effects 0.000 claims description 31
- 238000013501 data transformation Methods 0.000 claims description 17
- 238000009825 accumulation Methods 0.000 claims description 16
- 238000004590 computer program Methods 0.000 claims description 12
- 230000006870 function Effects 0.000 claims description 9
- 230000009466 transformation Effects 0.000 claims description 5
- 230000002159 abnormal effect Effects 0.000 abstract description 15
- 238000011065 in-situ storage Methods 0.000 abstract description 5
- 238000003745 diagnosis Methods 0.000 abstract description 3
- 230000001186 cumulative effect Effects 0.000 description 9
- 238000010586 diagram Methods 0.000 description 9
- 239000000463 material Substances 0.000 description 6
- 238000012544 monitoring process Methods 0.000 description 6
- 238000004891 communication Methods 0.000 description 5
- 238000004519 manufacturing process Methods 0.000 description 5
- 238000005070 sampling Methods 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 3
- 230000007423 decrease Effects 0.000 description 3
- 230000008021 deposition Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000010146 3D printing Methods 0.000 description 2
- 230000004931 aggregating effect Effects 0.000 description 2
- 230000002950 deficient Effects 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000036541 health Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- NAWXUBYGYWOOIX-SFHVURJKSA-N (2s)-2-[[4-[2-(2,4-diaminoquinazolin-6-yl)ethyl]benzoyl]amino]-4-methylidenepentanedioic acid Chemical compound C1=CC2=NC(N)=NC(N)=C2C=C1CCC1=CC=C(C(=O)N[C@@H](CC(=C)C(O)=O)C(O)=O)C=C1 NAWXUBYGYWOOIX-SFHVURJKSA-N 0.000 description 1
- 229920000049 Carbon (fiber) Polymers 0.000 description 1
- 239000004677 Nylon Substances 0.000 description 1
- 239000004917 carbon fiber Substances 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000001125 extrusion Methods 0.000 description 1
- 229920006253 high performance fiber Polymers 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000000465 moulding Methods 0.000 description 1
- 229920001778 nylon Polymers 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- 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
- 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
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/04—Manufacturing
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C3/00—Registering or indicating the condition or the working of machines or other apparatus, other than vehicles
- G07C3/005—Registering or indicating the condition or the working of machines or other apparatus, other than vehicles during manufacturing process
-
- 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
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Manufacturing & Machinery (AREA)
- Strategic Management (AREA)
- Materials Engineering (AREA)
- Chemical & Material Sciences (AREA)
- Economics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Evolutionary Computation (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- General Business, Economics & Management (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Tourism & Hospitality (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Primary Health Care (AREA)
- General Health & Medical Sciences (AREA)
- Optics & Photonics (AREA)
- Mechanical Engineering (AREA)
- Health & Medical Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
- Inking, Control Or Cleaning Of Printing Machines (AREA)
Abstract
The invention provides a printing condition online identification method, a printing condition online identification system, electronic equipment and a storage medium, wherein the method comprises the following steps: determining vibration data of a printing process bottom plate of a working condition to be identified; inputting the printing process bottom plate vibration data of the working condition to be identified into an online identification model to obtain a working condition identification result output by the online identification model; the online identification model is obtained by calibration training based on bottom plate vibration sample data and working conditions corresponding to the sample data; and the online identification model is used for identifying the working condition of the bottom plate vibration data of the printing process of the working condition to be identified after a characteristic track library representing the working condition is extracted based on the bottom plate vibration sample data and the working condition calibration corresponding to the sample data. The invention realizes the in-situ identification of the basic working condition in the printing process and the online diagnosis of the abnormal working condition.
Description
Technical Field
The invention relates to the technical field of online monitoring, in particular to a printing condition online identification method, a printing condition online identification system, electronic equipment and a storage medium.
Background
The health of the equipment during Fused Deposition Modeling (FDM) directly affects the success or failure of the manufacturing task. As the use time is accumulated, the FDM equipment inevitably degrades, so that abnormal working conditions are generated. The abnormal working condition often causes the quality defect of the formed product, and the printing task fails. Under the condition that personnel can not be guaranteed to watch on in the whole process, if abnormal working conditions are generated and cannot be found in time, the failure of a manufacturing task can be caused, the waste of raw materials and manufacturing time is caused, the damage of manufacturing equipment can be caused, the follow-up manufacturing task is influenced, and more step by step, the equipment fault can cause the occurrence of safety accidents and cause greater damage. In view of this, it is necessary to develop a research for in-situ monitoring technology of the health condition of the FDM process equipment. However, the existing commercial FDM equipment does not have the capability of on-line identification of the working condition of the printing process equipment.
Disclosure of Invention
The embodiment of the invention provides a printing condition online identification method, a printing condition online identification system, electronic equipment and a storage medium, which are used for solving the problem that FDM equipment at the present stage does not have the printing process equipment condition online identification capability.
In a first aspect, an embodiment of the present invention provides an online identification method for a printing condition, including:
determining vibration data of a printing process bottom plate of a working condition to be identified;
inputting the printing process bottom plate vibration data of the working condition to be identified into an online identification model to obtain a working condition identification result output by the online identification model;
the online identification model is obtained by calibration training based on bottom plate vibration sample data and working conditions corresponding to the sample data;
and the online identification model is used for identifying the working condition of the bottom plate vibration data of the printing process of the working condition to be identified after a characteristic track library representing the working condition is extracted based on the bottom plate vibration sample data and the working condition calibration corresponding to the sample data.
Further, the online identification model comprises a data transformation model, a characteristic track model and a track matching model;
inputting the printing process bottom plate vibration data of the working condition to be identified into an online identification model to obtain a working condition identification result output by the online identification model, wherein the working condition identification result comprises the following steps:
inputting the printing process bottom plate vibration data of the working condition to be identified into the data transformation model, and outputting transformed test data;
inputting the transformed test data into the characteristic track model, and outputting the characteristic track of the test data;
and inputting the characteristic track of the test data into the track matching model, and outputting a working condition identification result based on the continuously expanded characteristic track library.
Further, inputting the characteristic track of the test data into the track matching model, and outputting a working condition identification result based on a continuously expanded characteristic track library, including:
carrying out track matching on a standard data unit on the characteristic track of the test data and the current characteristic track library to obtain the minimum mean square error of the standard data unit as the minimum matching error;
and judging whether to update the feature track library of this time according to the minimum matching error: if the minimum matching error is larger than the preset upper error limit, the characteristic track of the current standard data unit is used as a new working condition track to be expanded to a characteristic track library so as to carry out track matching of the next standard data unit; otherwise, determining the working condition of the current standard data unit;
and taking the working condition of the standard data unit at each time as a set to obtain a working condition identification result.
Further, the online identification model is obtained based on the bottom plate vibration sample data and the working condition calibration training corresponding to the sample data, and comprises the following steps:
performing data transformation on the bottom plate vibration sample data based on a preset amplitude intensity threshold value to obtain transformed training data;
dividing the transformed training data into a minimum continuous data set containing basic printing conditions based on the working condition calibration corresponding to the sample data to obtain a plurality of standard data units;
and after different working conditions of each standard data unit are processed based on the acceleration absolute value accumulation function, obtaining characteristic track elements in each standard data unit, gathering the characteristic track elements in each standard data unit into a characteristic track, and constructing an initial characteristic track library to obtain an online identification model.
Further, performing data transformation on the bottom plate vibration sample data based on a preset amplitude intensity threshold value to obtain transformed training data, wherein a transformation formula of the transformed training data is as follows:
X'＝{x'1,x'2,...,x'n}；
wherein X' is transformed training data, XiIs the sample data of the vibration of the bottom plate, n is the length of the sample data and the changed training data, xthreshIs a preset amplitude intensity threshold.
Further, the standard data unit is represented as follows:
StD＝{x'I+1,x'I+2,...,x'I+l}；
wherein l is the length of a standard data unit, I +1 represents the starting position of the standard data unit in X ', I + l represents the ending position of the standard data unit in X', and I is more than or equal to 1 and less than or equal to n-l.
Further, after different working conditions of each standard data unit are processed based on an acceleration absolute value accumulation function, the characteristic track elements in each standard data unit are obtained, and the characteristic track elements in each standard data unit are integrated into a characteristic track, wherein the formula is as follows:
wherein traj (StD) represents the characteristic track of a standard data unit, N is the number of basic printing conditions contained in a standard data unit, traj(s)k) N is more than or equal to 1 and less than or equal to k, the characteristic track element belonging to the working condition k in one standard data unit is represented, l is the length of one standard data unit, I + I represents the ith position of the standard data unit in X', and I is more than or equal to 1 and less than or equal to N-l.
In a second aspect, an embodiment of the present invention provides an online print condition identification system, including:
the data determining unit is used for determining the vibration data of the printing process bottom plate under the working condition to be identified;
the online identification unit is used for inputting the printing process bottom plate vibration data of the working condition to be identified into an online identification model to obtain a working condition identification result output by the online identification model;
the online identification model is obtained by calibration training based on bottom plate vibration sample data and working conditions corresponding to the sample data;
and the online identification model is used for identifying the working condition of the bottom plate vibration data of the printing process of the working condition to be identified after a characteristic track library representing the working condition is extracted based on the bottom plate vibration sample data and the working condition calibration corresponding to the sample data.
In a third aspect, an embodiment of the present invention provides an electronic device, which includes a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor executes the program to implement the steps of the print condition online identification method according to any one of the above-mentioned first aspects.
In a fourth aspect, an embodiment of the present invention provides a non-transitory computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps of the print condition online identification method according to any one of the above-mentioned first aspects.
According to the printing condition on-line identification method, the printing condition on-line identification system, the electronic equipment and the storage medium, provided by the embodiment of the invention, the printing process bottom plate vibration data is input into the on-line identification model, so that a condition identification result output by the on-line identification model is obtained. The invention introduces the vibration sensor for monitoring the vibration intensity of the bottom plate to obtain the vibration data of the bottom plate in the printing process, thereby realizing the in-situ identification of the basic working condition and the online diagnosis of the abnormal working condition in the printing process.
Drawings
In order to more clearly illustrate the technical solutions of the present invention or the prior art, the drawings needed for the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without creative efforts.
FIG. 1 is a schematic flow chart of a printing condition online identification method provided by the invention;
FIG. 2 is a block diagram of an online recognition model provided by the present invention;
FIG. 3 is an exemplary diagram of the spline basic operating condition provided by the present invention;
FIGS. 4 a-4 f are graphs of acceleration super-threshold data accumulation under different thresholds according to the present invention;
FIG. 5 is a graph of print cycle floor vibration data sampling provided by the present invention;
FIGS. 6 a-6 d are graphs of standard data cells and corresponding signatures provided by the present invention;
FIG. 7 is a graph of a fit of a super-threshold cumulative characteristic curve provided by the present invention;
FIGS. 8 a-8 b are graphs of the basic data and acceleration super-threshold accumulation provided by the present invention;
FIGS. 9 a-9 b are graphs of test data and acceleration super-threshold accumulation provided by the present invention;
10 a-10 b are graphs of the matching results of test data provided by the present invention;
FIG. 11 is a bottom plate vibration data sampling diagram under a semi-plugging condition provided by the present invention;
12 a-12 b are graphs of the semi-plugged condition track matching results provided by the present invention;
FIG. 13 is a schematic structural diagram of an on-line print condition recognition system according to the present invention;
FIG. 14 is a block diagram of an online identification unit provided by the present invention;
FIG. 15 is a block diagram of a trajectory matching module provided by the present invention;
fig. 16 is a schematic structural diagram of an electronic device provided by the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The following describes a printing condition online identification method, a printing condition online identification system, an electronic device and a storage medium provided by the invention with reference to fig. 1 to 16.
The embodiment of the invention provides a printing condition online identification method, a printing condition online identification system, electronic equipment and a storage medium. Fig. 1 is a schematic flow chart of a printing condition online identification method according to an embodiment of the present invention, as shown in fig. 1, the method includes:
the online identification model is obtained by calibration training based on bottom plate vibration sample data and working conditions corresponding to the sample data;
and the online identification model is used for identifying the working condition of the bottom plate vibration data of the printing process of the working condition to be identified after a characteristic track library representing the working condition is extracted based on the bottom plate vibration sample data and the working condition calibration corresponding to the sample data.
Specifically, it is assumed that the vibration data of the base plate is D ═ { X, Y }, where X is sample data of training and Y is test data.
According to the method provided by the embodiment of the invention, the vibration data of the bottom plate in the printing process is collected, the reference data unit for representing the printing working condition is analyzed, the characteristic for representing the working condition of the equipment is extracted, and the characteristic threshold value of the normal working condition is calculated, so that the online monitoring of the working condition of the equipment in the fused deposition molding process, the quick identification of the printing working condition and the effective identification of the abnormal working condition can be simply, effectively and economically realized.
Based on any of the above embodiments, as shown in fig. 2, the online recognition model includes a data transformation model 210, a feature trajectory model 220, and a trajectory matching model 230;
inputting the printing process bottom plate vibration data of the working condition to be identified into an online identification model to obtain a working condition identification result output by the online identification model, wherein the working condition identification result comprises the following steps:
inputting the printing process bottom plate vibration data of the working condition to be identified into the data transformation model 210, and outputting transformed test data;
specifically, 1) test data transformation
For test data Y ═ Y1,y2,...,ymEquation (1) for data transformation processing is as follows:
wherein i ═ 1, 2., m, Y ═ Y'1,y'2,...,y'mAnd the transformed test data. In order to ensure the track matching effectiveness, the length m of the test data is less than or equal to l/2, and l is the length of the standard data unit.
Inputting the transformed test data to the feature trajectory model 220, and outputting the feature trajectory of the test data;
specifically, 2) test data feature trajectories
Equation (2) for calculating the test data feature trajectory is as follows:
wherein m is less than or equal to l/2, and l is the length of the standard data unit.
The feature trajectory of the test data is input to the trajectory matching model 230, and a working condition recognition result is output based on the feature trajectory library which is continuously expanded.
Specifically, 3) trajectory matching and feature library updating
And matching the test data characteristic track with the standard data unit characteristic track, taking the minimum mean square error as a matching error, and taking the minimum matching error position as an optimal matching position, thereby determining the working condition of the test unit. When the track matching is executed, an upper error limit theta should be set, and if the minimum matching is larger than theta, the track is taken as a new working condition track and is expanded to a characteristic track library.
Based on any one of the above embodiments, inputting the characteristic trajectory of the test data to the trajectory matching model, and outputting a working condition recognition result based on a continuously expanded characteristic trajectory library, including:
carrying out track matching on a standard data unit on the characteristic track of the test data and the current characteristic track library to obtain the minimum mean square error of the standard data unit as the minimum matching error;
and judging whether to update the feature track library of this time according to the minimum matching error: if the minimum matching error is larger than the preset upper error limit, the characteristic track of the current standard data unit is used as a new working condition track to be expanded to a characteristic track library so as to carry out track matching of the next standard data unit; otherwise, determining the working condition of the current standard data unit;
and taking the working condition of the standard data unit at each time as a set to obtain a working condition identification result.
Based on any of the above embodiments, the online identification model is obtained based on the bottom plate vibration sample data and the working condition calibration training corresponding to the sample data, and includes:
performing data transformation on the bottom plate vibration sample data based on a preset amplitude intensity threshold value to obtain transformed training data;
dividing the transformed training data into a minimum continuous data set containing basic printing conditions based on the working condition calibration corresponding to the sample data to obtain a plurality of standard data units;
and after different working conditions of each standard data unit are processed based on the acceleration absolute value accumulation function, obtaining characteristic track elements in each standard data unit, gathering the characteristic track elements in each standard data unit into a characteristic track, and constructing an initial characteristic track library to obtain an online identification model.
Based on any one of the above embodiments, the data transformation is performed on the baseplate vibration sample data based on a preset amplitude intensity threshold value to obtain transformed training data, and transformation equations (3) and (4) are as follows:
X'＝{x'1,x'2,...,x'n}； (4)
wherein X' is transformed training data, XiIs the sample data of the vibration of the bottom plate, n is the length of the sample data and the changed training data, xthreshIs a preset amplitude intensity threshold.
In addition, the sample data is X ═ { X ═ X1,x2,...,xnFluctuation of bottom plate vibration data acquired by an acceleration sensor along a time axis is realized, and the lower the vibration intensity of the bottom plate is, the smaller the amplitude is, and the smaller the corresponding acceleration value is; the higher the vibration intensity of the base plate is, the larger the amplitude is, and the larger the corresponding acceleration value is. Because different working conditions can be more easily identified by the strong amplitude value, in order to effectively obtain vibration data representing different working conditions of the 3D printer and effectively reduce the calculated amount, the method carries out the transformation on the acceleration data of the bottom plate.
Based on any of the above embodiments, the formula (5) of the standard data unit is as follows:
StD＝{x'I+1,x'I+2,...,x'I+l}； (5)
wherein l is the length of a standard data unit, I +1 represents the starting position of the standard data unit in X ', I + l represents the ending position of the standard data unit in X', and I is more than or equal to 1 and less than or equal to n-l.
It should be noted that the standard data unit refers to a minimum continuous data set including data of the basic print condition. In the FDM process 3D printing apparatus, the basic printing condition generally includes two basic conditions of printing the periphery and filling the inside, and the FDM process is a layer-by-layer stacking process, so the acquired bottom plate vibration data will be periodic. Assume that the basic print condition includes N, and is expressed as State ═ s1,s2,...,sNH, a standard data unit length is l, then
length(sk) And the number of data belonging to the k-th working condition in the standard data unit is shown.
Based on any of the above embodiments, after performing different working condition processing on each standard data unit based on the acceleration absolute value cumulative function, obtaining the feature trajectory elements in each standard data unit, and aggregating the feature trajectory elements in each standard data unit into a feature trajectory, where formula (6) is as follows:
wherein traj (StD) represents the characteristic track of a standard data unit, N is the number of basic printing conditions contained in a standard data unit, traj(s)k) N is more than or equal to 1 and less than or equal to k, the characteristic track element belonging to the working condition k in one standard data unit is represented, l is the length of one standard data unit, I + I represents the ith position of the standard data unit in X', and I is more than or equal to 1 and less than or equal to N-l.
It should be noted that the characteristic trace is used to represent curves of different operating conditions in the standard data unit, and an acceleration absolute value accumulation function is used as an element of the characteristic trace.
The following explains the concrete application of the method and the system provided by the invention in practice:
1) experiment design and working condition analysis:
a vibration sensor is arranged on the bottom plate of the 3D printer, and data acquisition equipment is used for acquiring vibration data of the bottom plate in the printing process.
The printer is a Markforged high-performance fiber composite material FDM 3D printer (Mark Two), the sensor is an integrated circuit piezoelectric acceleration sensor which is a single-axial sensor, the model number of the sensor is 7251A-500, the measuring range of the sensor is +/-10 g, the sensitivity of the sensor is 500mv/g, and the frequency of the sensor is correspondingly 2kHz-10 kHz. The data acquisition equipment adopts an NI cDAQ-9174 model case and an NI 9234 model data acquisition card, and the sampling frequency is set to be 2.5 kHz.
The basic printing parameters are set as shown in table 1, the printing material is a carbon fiber reinforced nylon material (Onyx), the thermal deformation temperature is 145 ℃, the preheating temperature of the nozzle is 270 ℃, the diameter of the nozzle is 0.4mm, the height of the printing layer is 0.2mm, and the filling rate is 50%.
TABLE 1 print parameter settings
The FDM printing condition mainly comprises a filling condition and a printing peripheral condition. The vibration signal of the printing process presents different regularity according to different printing targets.
The basic operating conditions of the method of the invention are specifically analyzed as follows.
The method uses a compression spline conforming to the standard ISO 178 as a printing spline with the size of
The splines were designed by CATIA V5 and saved as STL files. The filling conditions are set to be 45 degrees and 135 degrees in a grid filling mode, the edge printing is set to be 2 layers, and the basic printing condition is shown in figure 3.
The cylindrical spline print condition can be divided into three basic conditions, namely an edge print condition (shown in fig. 3(a) (c)), a 45 ° fill condition (shown in fig. 3 (b)), and a 135 ° fill condition (shown in fig. 3 (d)). In the FDM process, the extruder and the movement mechanism have different movement modes under different printing working conditions, and the printer has different vibration conditions under different printing working conditions.
2) Training phase standard data unit feature trajectory acquisition
In FDM process 3D printing equipment, basic printing working conditions generally comprise two working conditions of printing periphery and filling inside.
In the experimental process, the data acquisition frequency of the single-axis vibration sensor arranged on the bottom plate is set to be 2500Hz, and more than 300 vibration data are acquired in the whole period from the beginning to the end of printing. The method and the case are monitored and analyzed according to the filling working condition of the printed columnar spline and the edge printing working condition. Taking the 127 th and 128 th layers as standard data units as examples, statistical feature extraction is performed.
In consideration of the effectiveness of feature extraction and the simple feasibility of calculation, the sum of the data lengths exceeding the threshold value is selected as the feature representing the printing condition. The threshold values were set to [0.02g,0.07g ] respectively]And the step length is 0.01g, and the difference degree of different threshold characteristic curves to different working conditions is compared. The corresponding acceleration super-threshold cumulative curves are shown in fig. 4a to 4f, where fig. 4(a) is the acceleration super-threshold cumulative curve when the threshold is 0.02g, and fig. 4(b) is the acceleration super-threshold when the threshold is 0.03gFig. 4(c) is an acceleration super-threshold cumulative curve when the threshold is 0.04g, fig. 4(d) is an acceleration super-threshold cumulative curve when the threshold is 0.05g, fig. 4(e) is an acceleration super-threshold cumulative curve when the threshold is 0.06g, and fig. 4(f) is an acceleration super-threshold cumulative curve when the threshold is 0.07 g. Wherein Fill1And Fill2The super-threshold acceleration sum over time is characterized for two fill states (45 ° fill and 135 ° fill), and Edge is characterized for the acceleration sum over time as the perimeter is printed.
From the analysis shown in fig. 4a to 4f, when the threshold values are 0.04g, 0.05g and 0.06g, the filling conditions and the edge conditions have obvious identification degrees, in practical application, 0.05g is selected as the threshold value, the two filling conditions are the same at the beginning end and the end, in the middle part, the filling condition (45 ° filling) data of the odd layer is lower than the filling condition (135 ° filling) data of the even layer, and when the threshold value is 0.05g, the data can be well embodied. In the idle driving state, 99% of vibration data collected by the bottom plate is within the range of [0,0.05g ]. In addition, the vibration data of the whole printing period is analyzed, as shown in fig. 5, two horizontal lines represent +/-0.05 g, which can be obtained from fig. 4 a-4 f, and 0.05g is selected as a threshold value, so that the characteristics of all working conditions can be maintained, and the calculated amount is greatly reduced.
For the vibration data of the bottom plate in the cylindrical spline printing process, taking 0.05g as a threshold value, extracting characteristic curves for standard data units (127 layers and 128 layers), as shown in fig. 6a to 6d, wherein fig. 6(a) and 6(c) are respectively an original vibration curve and an accumulated value curve with an acceleration value exceeding 0.05 g; FIGS. 6(b) and 6(d) are the original vibration curve and the accumulated value curve with acceleration value exceeding 0.05g after the working condition is divided. The obtained reference feature library includes features of the print periphery and the filling method (fig. 6 (d)).
3) Match error ceiling determination
The working condition of the cylindrical spline is divided into a filling working condition and a printing periphery, and the acceleration threshold is 0.05 g. Here, the vibration data of the two layers is also selected as a standard data unit, the sampling frequency is 2500Hz, and the standard data unit contains 38200 sampling numbers.
For the markformed printer characteristics (calibration is performed every 5 layers), 5 layers are selected as one unit, and 14 units are selected to analyze the change of characteristics along with the increase of the number of printing layers, wherein the 14 units are respectively as follows: 11-15 layers, 21-25 layers, 31-35 layers, 41-45 layers, 51-55 layers, 61-65 layers, 71-75 layers, 81-85 layers, 91-95 layers, 101-105 layers, 111-115 layers, 121-125 layers, 131-135 layers and 141-145 layers, wherein each unit randomly selects 10 standard data units. Each feature takes 10 standard data cells within each cell as shown in fig. 7. The characteristic trace has obvious trend change along with the increase of the layer number, namely the trend decreases along with the increase of the layer number. This means that as the number of print layers increases, there is a tendency for the vibration of the base plate to decrease, i.e., the influence of the print head on the base plate decreases as the number of print layers increases.
Super threshold value total length increases along with the number of printing layers and reduces, and at 71 ~ 75 layers, the vibration grow suddenly, and this is because the printing process is beaten printer head temperature height, and peripheral can adhere to partial defective material, and adnexed defective material is not in time clear away, can drop after the accumulation to a certain extent and print the target surface, causes local hourglass material, leads to extruding head and printing surperficial frictional force increase. The friction between the printing head and the printing target at the material leakage position is increased, so that the amplitude of the bottom plate is higher. At the time of analysis, the data were discarded as abnormal points.
Considering the later-stage calculation, performing linear regression on the mean value of the super-threshold total length feature to obtain a fitted curve as shown in fig. 7, where the fitting equation (7) is:
f(x)＝-1.56x+112.21,x＝1,2,…,15 (7)
equation (7) is the equation of the change rule of the vibration of the bottom plate along with the height, wherein f (x) is the accumulation of the acceleration over threshold value of a standard data unit. Equation (7) characterizes the case of 10 layers per cell, and if the number of cell layers is positioned at 1, equation (7) is expressed as the following equation (8):
f(x)＝-0.156x+112.21,,x＝1,2,…,150 (8)
here, the calculation deviation degree range formula (9) is as follows:
wherein y represents the original data, yregressRepresents fitting data according to [ yregress-y·p,yregress+y·p]The threshold range determined (as shown in fig. 7), p is the degree of deviation. p is a value which is continuously adjusted and adapted, a smaller value can be randomly set initially, and dynamic updating can be carried out subsequently according to actual conditions.
4) Printer working condition in-situ recognition and abnormal working condition on-line diagnosis
In the application of the invention, a first group of data, namely 11-15 layers of bottom plate vibration data, is taken as training data, and 81-85 layers of printing working condition data are taken as test data. Selecting a standard data cell of a first set of data comprising layer 11 infill floor vibration data (Fill)1) Layer 12 Edge and infill baseplate vibration data (Edge)1And Fill2) Layer 13 Edge baseplate vibration data (Edge)2) As a standard data unit (as shown in fig. 8 (a)), the acceleration super-threshold accumulation curve is shown in fig. 8 (b).
After the number of print layers is determined, the amplitude multiple relationship between the layer test data and the base data can be calculated according to equation (7) (or equation 8). Taking 81-85 layers of data as an example, 10 groups of data of 81-85 layers are selected for the test array, each group of data comprises 6000 data, and taking the 4 th section of data (31101-37100) as an example, the test process is described as shown in fig. 9 (a). All data of 81-85 layers are represented in dark color, the light color represents the 4 th group of test data and belongs to the 82 th layer of filling data, and the graph in FIG. 9(b) is a super-threshold curve corresponding to the test data. Next, the category and the number of layers to which the 4 th group of data belongs are determined by using a track matching method.
The Mark Two 3D printer is calibrated every time when printing 5 layers, and the calibration working condition can be obviously identified by using the vibration data of the bottom plate, so that the number of the printed layers can be counted by using the number of the over-calibration working condition, and according to the formula (7), the multiple relation between the 11 th to 15 th layers and the 81 th to 85 th layers is 1.1093 (the calculation process is 1.1093)
)，The test data super-threshold accumulation characteristic is multiplied by 1.1093, and then the test data super-threshold accumulation characteristic is matched with the training data through a super-threshold accumulation characteristic curve.
The test data characteristic curve matching process is shown in fig. 10 a-10 b. FIG. 10(a) is a graph of the match error, with dots indicating positions of minimum error and best match, and FIG. 10(b) is a graph showing the test data characteristic at the best match. The fourth set of best match initial positions is 21775, which corresponds to a Mean Square Error (MSE) of 0.6585.
The predicted result of the test data is 82 layers of filling data, and is the same as the actual result. Meanwhile, the test data is normal printing condition data, and the initial value can be updated according to the MSE value of the test data. Since 0.6585 is >0.1(0.1 is the initial randomly set MSE value), the MSE upper limit value will be adjusted to 0.6585.
In the same method, the vibration data of the other 9 groups of bottom plates of 81-85 layers are matched, and the working condition matching conforms to the actual condition, so that the improved track matching method is completely suitable for the printing working condition matching between different layers, and the improved similar track matching method is more suitable for in-situ monitoring and identification of the printing working condition in the FDM process.
In addition, the method based on improved track matching has self-adaptive capacity for identifying abnormal working conditions, and for data representing the abnormal working conditions, the error of the optimal position matched with the reference characteristic curve far exceeds the MSE upper limit value, so that the data representing the abnormal working conditions need to be analyzed, the represented abnormal working conditions are determined, and the abnormal working conditions are expanded into the characteristic library. For example, the working condition of 11-15 layers of extrusion head half plugging is shown in fig. 11. 12 layers of filling data (light color identification data) are selected as test data, and the test results are shown in fig. 12a to 12b, where fig. 12(a) is a matching error and fig. 12(b) is a matching result of the test data at a position of a minimum matching error.
The best matching position is the edge printing condition, the minimum matching error is 51.4729 and is far greater than the MSE upper limit value 0.6585, the condition is determined to be an abnormal condition, and the condition is verified to be the printing filling condition under the condition of a plug. The test data curve is expanded into a basic characteristic curve library, so that the improved track matching method has the identification capability of filling working conditions under the condition that the printing head is half-blocked.
The printing condition on-line identification system provided by the invention is described below, and the printing condition on-line identification method described below and the printing condition on-line identification method described above can be referred to correspondingly.
Fig. 13 is a schematic structural diagram of an online identification system of a printing condition according to an embodiment of the present invention, and as shown in fig. 13, the system includes a data determination unit 1310 and an online identification unit 1320;
a data determining unit 1310 for determining the vibration data of the printing process base plate of the working condition to be identified;
the online identification unit 1320 is configured to input the printing process bottom plate vibration data of the working condition to be identified into an online identification model, so as to obtain a working condition identification result output by the online identification model;
the online identification model is obtained by calibration training based on bottom plate vibration sample data and working conditions corresponding to the sample data;
and the online identification model is used for identifying the working condition of the bottom plate vibration data of the printing process of the working condition to be identified after a characteristic track library representing the working condition is extracted based on the bottom plate vibration sample data and the working condition calibration corresponding to the sample data.
According to the system provided by the embodiment of the invention, the vibration data of the bottom plate in the printing process is collected, the reference data unit for representing the printing working condition is analyzed, the characteristic for representing the working condition of the equipment is extracted, and the characteristic threshold value of the normal working condition is calculated, so that the online monitoring of the working condition of the equipment in the fused deposition forming process, the quick identification of the printing working condition and the effective identification of the abnormal working condition can be simply, effectively and economically realized.
According to any of the above embodiments, as shown in fig. 14, the online identification unit includes a data transformation module 1410, a feature trajectory module 1420, and a trajectory matching module 1430;
the data conversion module 1410 is configured to input the vibration data of the printing process base plate of the working condition to be identified, and output converted test data;
the characteristic track module 1420 is configured to input the transformed test data and output a characteristic track of the test data;
the track matching module 1430 is configured to input the standard data unit feature track, and output a working condition identification result based on the feature track library that is continuously expanded.
Based on any of the above embodiments, as shown in fig. 15, the trajectory matching module includes a standard data unit matching module 1510, a matching decision module 1520 and a condition output module 1530;
the standard data unit matching module 1510 is configured to perform track matching of a standard data unit on the feature track of the test data and the current feature track library to obtain a minimum mean square error of the standard data unit as a minimum matching error;
the matching decision module 1520 is configured to determine whether to update the feature trajectory library of this time according to the minimum matching error: if the minimum matching error is larger than the preset upper error limit, the characteristic track of the current standard data unit is used as a new working condition track to be expanded to a characteristic track library so as to carry out track matching of the next standard data unit; otherwise, determining the working condition of the current standard data unit;
the working condition output module 1530 is configured to obtain a working condition identification result by taking the working conditions where the standard data units are located each time as a set.
Based on any embodiment above, the online identification unit further comprises an online identification model;
the online identification model is obtained based on the vibration sample data of the bottom plate and the working condition calibration training corresponding to the sample data, and comprises the following steps:
performing data transformation on the bottom plate vibration sample data based on a preset amplitude intensity threshold value to obtain transformed training data;
dividing the transformed training data into a minimum continuous data set containing basic printing conditions based on the working condition calibration corresponding to the sample data to obtain a plurality of standard data units;
and after different working conditions of each standard data unit are processed based on the acceleration absolute value accumulation function, obtaining characteristic track elements in each standard data unit, gathering the characteristic track elements in each standard data unit into a characteristic track, and constructing an initial characteristic track library to obtain an online identification model.
Based on any one of the above embodiments, the data transformation is performed on the baseplate vibration sample data based on a preset amplitude intensity threshold value to obtain transformed training data, wherein a transformation formula (10) is as follows:
X'＝{x'1,x'2,...,x'n}； (11)
wherein X' is transformed training data, XiIs the sample data of the vibration of the bottom plate, n is the length of the sample data and the changed training data, xthreshIs a preset amplitude intensity threshold.
According to any of the above embodiments, the standard data unit is represented as follows:
StD＝{x'I+1,x'I+2,...,x'I+l}； (12)
wherein l is the length of a standard data unit, I +1 represents the starting position of the standard data unit in X ', I + l represents the ending position of the standard data unit in X', and I is more than or equal to 1 and less than or equal to n-l.
Based on any of the above embodiments, after performing different working condition processing on each standard data unit based on the acceleration absolute value cumulative function, obtaining the feature trajectory elements in each standard data unit, and aggregating the feature trajectory elements in each standard data unit into a feature trajectory, where the formula is as follows:
wherein traj (StD) represents the characteristic track of a standard data unit, N is the number of basic printing conditions contained in a standard data unit, traj(s)k) N is more than or equal to 1 and less than or equal to k, the characteristic track element belonging to the working condition k in one standard data unit is represented, l is the length of one standard data unit, I + I represents the ith position of the standard data unit in X', and I is more than or equal to 1 and less than or equal to N-l.
Fig. 16 is a schematic structural diagram of an electronic device according to an embodiment of the present invention, and as shown in fig. 16, the electronic device may include: a processor (processor)1610, a communication Interface (Communications Interface)1620, a memory (memory)1630 and a communication bus 1640, wherein the processor 1610, the communication Interface 1620 and the memory 1630 communicate with each other via the communication bus 1640. Processor 1610 may invoke logic instructions in memory 1630 to perform a print job online identification method comprising: determining vibration data of a printing process bottom plate of a working condition to be identified; inputting the printing process bottom plate vibration data of the working condition to be identified into an online identification model to obtain a working condition identification result output by the online identification model; the online identification model is obtained by calibration training based on bottom plate vibration sample data and working conditions corresponding to the sample data; and the online identification model is used for identifying the working condition of the printing working condition of the working condition to be identified after a characteristic track library representing the working condition is extracted based on the bottom plate vibration sample data and the working condition calibration corresponding to the sample data.
In addition, the logic instructions in the memory 1630 may be implemented in software functional units and stored in a computer readable storage medium when sold or used as a stand-alone product. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
In another aspect, an embodiment of the present invention further provides a computer program product, where the computer program product includes a computer program stored on a non-transitory computer-readable storage medium, the computer program includes program instructions, and when the program instructions are executed by a computer, the computer can execute the print condition online identification method provided by the above methods, where the method includes: determining vibration data of a printing process bottom plate of a working condition to be identified; inputting the printing process bottom plate vibration data of the working condition to be identified into an online identification model to obtain a working condition identification result output by the online identification model; the online identification model is obtained by calibration training based on bottom plate vibration sample data and working conditions corresponding to the sample data; and the online identification model is used for identifying the working condition of the printing working condition of the working condition to be identified after a characteristic track library representing the working condition is extracted based on the bottom plate vibration sample data and the working condition calibration corresponding to the sample data.
In still another aspect, an embodiment of the present invention further provides a non-transitory computer-readable storage medium, on which a computer program is stored, where the computer program is implemented by a processor to execute the above-mentioned print condition online identification methods, where the method includes: determining vibration data of a printing process bottom plate of a working condition to be identified; inputting the printing process bottom plate vibration data of the working condition to be identified into an online identification model to obtain a working condition identification result output by the online identification model; the online identification model is obtained by calibration training based on bottom plate vibration sample data and working conditions corresponding to the sample data; and the online identification model is used for identifying the working condition of the printing working condition of the working condition to be identified after a characteristic track library representing the working condition is extracted based on the bottom plate vibration sample data and the working condition calibration corresponding to the sample data.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A printing condition online identification method is characterized by comprising the following steps:
determining vibration data of a printing process bottom plate of a working condition to be identified;
inputting the printing process bottom plate vibration data of the working condition to be identified into an online identification model to obtain a working condition identification result output by the online identification model;
the online identification model is obtained by calibration training based on bottom plate vibration sample data and working conditions corresponding to the sample data;
and the online identification model is used for identifying the working condition of the bottom plate vibration data of the printing process of the working condition to be identified after a characteristic track library representing the working condition is extracted based on the bottom plate vibration sample data and the working condition calibration corresponding to the sample data.
2. The printing condition online identification method according to claim 1, wherein the online identification model comprises a data transformation model, a characteristic track model and a track matching model;
inputting the printing process bottom plate vibration data of the working condition to be identified into an online identification model to obtain a working condition identification result output by the online identification model, wherein the working condition identification result comprises the following steps:
inputting the printing process bottom plate vibration data of the working condition to be identified into the data transformation model, and outputting transformed test data;
inputting the transformed test data into the characteristic track model, and outputting the characteristic track of the test data;
and inputting the characteristic track of the test data into the track matching model, and outputting a working condition identification result based on the continuously expanded characteristic track library.
3. Print condition online identification method according to claim 1,
inputting the characteristic track of the test data into the track matching model, and outputting a working condition identification result based on a continuously expanded characteristic track library, wherein the working condition identification result comprises the following steps:
carrying out track matching on a standard data unit on the characteristic track of the test data and the current characteristic track library to obtain the minimum mean square error of the standard data unit as the minimum matching error;
and judging whether to update the feature track library of this time according to the minimum matching error: if the minimum matching error is larger than the preset upper error limit, the characteristic track of the current standard data unit is used as a new working condition track to be expanded to a characteristic track library so as to carry out track matching of the next standard data unit; otherwise, determining the working condition of the current standard data unit;
and taking the working condition of the standard data unit at each time as a set to obtain a working condition identification result.
4. The print job online identification method according to claim 2,
the online identification model is obtained based on the vibration sample data of the bottom plate and the working condition calibration training corresponding to the sample data, and comprises the following steps:
performing data transformation on the bottom plate vibration sample data based on a preset amplitude intensity threshold value to obtain transformed training data;
dividing the transformed training data into a minimum continuous data set containing basic printing conditions based on the working condition calibration corresponding to the sample data to obtain a plurality of standard data units;
and after different working conditions of each standard data unit are processed based on the acceleration absolute value accumulation function, obtaining characteristic track elements in each standard data unit, gathering the characteristic track elements in each standard data unit into a characteristic track, and constructing an initial characteristic track library to obtain an online identification model.
5. The printing condition online identification method according to claim 4, wherein the data transformation is performed on the baseplate vibration sample data based on a preset amplitude intensity threshold value to obtain transformed training data, and a transformation formula of the transformed training data is as follows:
X'＝{x'1,x'2,...,x'n}；
wherein X' is transformed training data，xiIs the sample data of the vibration of the bottom plate, n is the length of the sample data and the changed training data, xthreshIs a preset amplitude intensity threshold.
6. The print job online identification method according to claim 5, wherein the standard data unit is represented as follows:
StD＝{x'I+1,x'I+2,...,x'I+l}；
wherein l is the length of a standard data unit, I +1 represents the starting position of the standard data unit in X ', I + l represents the ending position of the standard data unit in X', and I is more than or equal to 1 and less than or equal to n-l.
7. The printing condition online identification method according to claim 6, wherein after different conditions of each standard data unit are processed based on an acceleration absolute value accumulation function, the characteristic track elements in each standard data unit are obtained, and the characteristic track elements in each standard data unit are grouped into a characteristic track, and the formula is as follows:
wherein traj (StD) represents the characteristic track of a standard data unit, N is the number of basic printing conditions contained in a standard data unit, traj(s)k) N is more than or equal to 1 and less than or equal to k, the characteristic track element belonging to the working condition k in one standard data unit is represented, l is the length of one standard data unit, I + I represents the ith position of the standard data unit in X', and I is more than or equal to 1 and less than or equal to N-l.
8. An online print condition identification system, comprising:
the data determining unit is used for determining the vibration data of the printing process bottom plate under the working condition to be identified;
the online identification unit is used for inputting the printing process bottom plate vibration data of the working condition to be identified into an online identification model to obtain a working condition identification result output by the online identification model;
the online identification model is obtained by calibration training based on bottom plate vibration sample data and working conditions corresponding to the sample data;
and the online identification model is used for identifying the working condition of the bottom plate vibration data of the printing process of the working condition to be identified after a characteristic track library representing the working condition is extracted based on the bottom plate vibration sample data and the working condition calibration corresponding to the sample data.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of the print condition on-line identification method according to any one of claims 1 to 4 when executing the program.
10. A non-transitory computer readable storage medium, on which a computer program is stored, wherein the computer program, when executed by a processor, implements the steps of the print job online identification method according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110578063.5A CN113505960B (en) | 2021-05-26 | 2021-05-26 | Printing working condition online identification method, printing working condition online identification system, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110578063.5A CN113505960B (en) | 2021-05-26 | 2021-05-26 | Printing working condition online identification method, printing working condition online identification system, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113505960A true CN113505960A (en) | 2021-10-15 |
| CN113505960B CN113505960B (en) | 2024-07-12 |
Family
ID=78008609
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110578063.5A Active CN113505960B (en) | 2021-05-26 | 2021-05-26 | Printing working condition online identification method, printing working condition online identification system, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113505960B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150328839A1 (en) * | 2014-05-13 | 2015-11-19 | Autodesk, Inc. | Dynamic real-time slice engine for 3d printing |
| CN110001065A (en) * | 2019-03-27 | 2019-07-12 | 南京梵科智能科技有限公司 | A kind of 3D printer operation process intelligent monitor system |
| CN111144548A (en) * | 2019-12-23 | 2020-05-12 | 北京寄云鼎城科技有限公司 | Method and device for identifying working condition of pumping well |
| 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 |
| US20210011457A1 (en) * | 2019-07-11 | 2021-01-14 | Institute Of Automation, Chinese Academy Of Sciences | Online monitoring device and system for a 3D printing device |
| WO2021036636A1 (en) * | 2019-04-26 | 2021-03-04 | 深圳市豪视智能科技有限公司 | Vibration detection method and apparatus for lifting device, server and storage medium |
-
2021
- 2021-05-26 CN CN202110578063.5A patent/CN113505960B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150328839A1 (en) * | 2014-05-13 | 2015-11-19 | Autodesk, Inc. | Dynamic real-time slice engine for 3d printing |
| CN110001065A (en) * | 2019-03-27 | 2019-07-12 | 南京梵科智能科技有限公司 | A kind of 3D printer operation process intelligent monitor system |
| WO2021036636A1 (en) * | 2019-04-26 | 2021-03-04 | 深圳市豪视智能科技有限公司 | Vibration detection method and apparatus for lifting device, server and storage medium |
| US20210011457A1 (en) * | 2019-07-11 | 2021-01-14 | Institute Of Automation, Chinese Academy Of Sciences | Online monitoring device and system for a 3D printing device |
| CN111144548A (en) * | 2019-12-23 | 2020-05-12 | 北京寄云鼎城科技有限公司 | Method and device for identifying working condition of pumping well |
| 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 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113505960B (en) | 2024-07-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2017008451A1 (en) | Abnormal load detecting method for cloud computing oriented online service | |
| JP6723669B2 (en) | Abnormality detection program, abnormality detection method, and abnormality detection device | |
| EP3100122B1 (en) | Method for making reliable sensor data available | |
| CN111858231B (en) | Single-index anomaly detection method based on operation and maintenance monitoring | |
| JP5459608B2 (en) | Communication network failure cause analysis system, failure cause analysis method, and failure cause analysis program | |
| CN103412542B (en) | A kind of integrated circuit technology unit exception early warning technology method of data-driven | |
| CN108664990A (en) | The stealing detection method and device of comprehensive entropy method and Density Clustering method | |
| DE102016013406A1 (en) | A method of operating a condition monitoring system of a vibrating machine and condition monitoring system | |
| CN116189349B (en) | Remote fault monitoring method and system for self-service printer | |
| CN111949496B (en) | Data detection method and device | |
| CN117111551B (en) | AMES system-based medicine production quality monitoring method and system | |
| CN110929972B (en) | Method, apparatus, device, medium and program for evaluating state of distribution transformer | |
| CN110737976A (en) | mechanical equipment health assessment method based on multi-dimensional information fusion | |
| CN114444231A (en) | Online self-adaptive prediction method, device, equipment and medium for residual life of mold | |
| CN116684878B (en) | 5G information transmission data safety monitoring system | |
| CN114637263A (en) | Method, device and equipment for monitoring abnormal working conditions in real time and storage medium | |
| DE102020203929A1 (en) | ERROR CHARGING DEVICE, ERROR CHARGING PROCEDURE AND ERROR CHARGING PROGRAM | |
| CN113505960A (en) | Printing condition online identification method and system, electronic equipment and storage medium | |
| CN113670611A (en) | Bearing early degradation evaluation method, system, medium and electronic equipment | |
| CN116030955B (en) | Medical equipment state monitoring method and related device based on Internet of things | |
| CN115330362A (en) | Engineering progress data processing method and system | |
| CN115511374A (en) | Method, device and equipment for calculating correlation of process indexes and storage medium | |
| JP5569324B2 (en) | Operating condition management device | |
| CN105931438B (en) | A kind of method and system of discriminant alarm duration statistics distributional stability | |
| DE102019003541A1 (en) | ASSESSMENT DEVICE, ESTIMATION SYSTEM, ESTIMATION METHOD AND PROGRAM |
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 |