CN111572026B - Pressure vessel mapping test system for 3D printing - Google Patents
Pressure vessel mapping test system for 3D printing Download PDFInfo
- Publication number
- CN111572026B CN111572026B CN202010387873.8A CN202010387873A CN111572026B CN 111572026 B CN111572026 B CN 111572026B CN 202010387873 A CN202010387873 A CN 202010387873A CN 111572026 B CN111572026 B CN 111572026B
- Authority
- CN
- China
- Prior art keywords
- model
- archived
- substrate
- data
- database
- 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
Links
Images
Classifications
-
- 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
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
- G01N21/31—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N27/00—Investigating or analysing materials by the use of electric, electrochemical, or magnetic means
- G01N27/72—Investigating or analysing materials by the use of electric, electrochemical, or magnetic means by investigating magnetic variables
- G01N27/82—Investigating or analysing materials by the use of electric, electrochemical, or magnetic means by investigating magnetic variables for investigating the presence of flaws
- G01N27/90—Investigating or analysing materials by the use of electric, electrochemical, or magnetic means by investigating magnetic variables for investigating the presence of flaws using eddy currents
- G01N27/9013—Arrangements for scanning
Landscapes
- Chemical & Material Sciences (AREA)
- Physics & Mathematics (AREA)
- Materials Engineering (AREA)
- Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Biochemistry (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Analytical Chemistry (AREA)
- Health & Medical Sciences (AREA)
- Pathology (AREA)
- Manufacturing & Machinery (AREA)
- Mechanical Engineering (AREA)
- Optics & Photonics (AREA)
- Chemical Kinetics & Catalysis (AREA)
- Electrochemistry (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention provides a 3D printing pressure container mapping test system which comprises an initial condition collector, a model generation component, a correction component and a database, wherein the collector is used for receiving a group of input field data and a group of archived model states, comparing the group of input field data with the group to determine a set of archived model states so as to determine that the set of archived model states is most matched with the set of input field data, and the determined set of archived model states represents predicted initial conditions; the model generation component is configured for generating raw drawing data based on the forecasted initial conditions and initial condition collector input data. According to the invention, each input node is proposed to be adopted in each image acquired by the collector, so that the model is ensured to be more complete, reliable and accurate in the construction process.
Description
Technical Field
The invention relates to the technical field of 3D printing, in particular to a pressure container mapping test system for 3D printing.
Background
The method aims to overcome the defects of inaccurate model establishment, non-standard and the like in the printing process in the prior art.
For example, the CN109590678A prior art discloses a method and an apparatus for manufacturing a metal lining of a 3D printed composite space pressure vessel, where the composite pressure vessel lining is mainly manufactured by multiple spinning and welding. Not only the manufacturing process is complex, but also the precision and the structure performance of the formed product can not be ensured. Another typical device for 3D printing is described in DE 102012000664 a1, for example, in which the printing table can be changed in its alignment with the printing plane by means of adjustable set screws in order to adjust mechanical tolerances. Another 3D printing method is described in DE 102001106614 a1, which performs a specific 3D printing of pendants or self-supporting elements by means of variable alignment, positioning and tilting of the printing table or component carriage, where the printing body is aligned by a multi-axis actuator so that the printing unit can position the printing voxels vertically on the printing plane. The position of the printing plane is known from the input data, rather than determined or verified.
The invention aims to solve the problems of single drawing generation, lack of drawing correction capability, complex inspection means, single self-correction means and the like in the field.
Disclosure of Invention
Aiming at the defects existing in the existing 3D printing, a team discovers through a large amount of researches that the defects that the generation of a drawing is single, the correction capability of a model is lack, the inspection record is complex, the self-correction means is single and the like, so that the defects are easy to occur in the printing process, and provides a 3D printing pressure container mapping test system.
In order to overcome the defects of the prior art, the invention adopts the following technical scheme:
A3D printed pressure vessel mapping test system includes an initial conditions collector, a model generation component, a correction component, and a database, the collector for receiving a set of input field data and a set of archived model states and comparing the set of input field data to the set to determine a set of archived model states to determine that the set of archived model states best matches the set of input field data, the determined set of archived model states representing predicted initial conditions; the model generation component is configured for generating raw drawing data based on the forecasted initial conditions and initial condition collector input data.
Optionally, the correcting component is configured to obtain a model category address for a device in the model generating component after completing updating of the collector part; determining that the model category address is not matched with the model category address of the corresponding model generation component in the test result; and based on the determination, initiating a corrective action in the database.
Optionally, the corrective action includes: initiating an update of a drawing data device in the database and using, in part, the test results to identify a correction of the drawing data device; issuing a notification to a display in the database, wherein content in the notification is based at least in part on the trial results.
Optionally, the initial condition collector includes: receiving a set of input field data; determining a set of model observations from the input field data; and determining a set of predicted initial conditions based on a set of actual observations and an archived model state library; determining the set of predicted initial conditions comprises: comparing the observations of the set of models to the archived model states; and selecting the optimal model state that best matches the actual observed value.
Optionally, the selecting the optimal model state includes: performing an optimization method between the archived model states with respect to an observation of the model; the archived model states are evaluated against observations of the model using a user-defined objective function or a user-defined loss function.
Optionally, comparing the raw prediction data to the selected model state to determine whether variability and range exists between the raw prediction data and the selected model state; and if variability and range are determined, updating the library or archived model state to include the raw prediction data.
The beneficial effects obtained by the invention are as follows:
1. by adopting each input node in each image collected by the collector, the model is ensured to be more complete, reliable and accurate in the constructed process;
2. the data window of the scanning camera is used for reconstructing the two-dimensional image of the partial image and collecting the substrate of the spectrum from the two-dimensional image by taking the time of acquiring the spectrum by the in-situ monitoring system as the center, so that all parameters can be completely collected in the construction process of the model, reference is provided for the subsequent printing of the model, the collected substrate of the spectrum can be selectively used or replaced by an operator, the efficient replacement can be realized in the printing process, and the application scenes of the whole system are increased;
3. the fault forecasting database is used for providing reference for similar objects stored in the database, so that the reference can be provided when the same model is modeled, the data is corrected in the data processing process, the model is corrected efficiently, and the fault data processor and the fault forecasting database are transmitted in the correcting process, so that the establishment of the whole model can be reasonably and efficiently established;
4. the automatic evaluation of the fault forecasting skills is executed by adopting the evaluation module, so that the model can be reliably and accurately constructed in the construction process, and meanwhile, the construction of the model is ensured to be more perfect by the arrangement of the evaluation module.
Drawings
The invention will be further understood from the following description in conjunction with the accompanying drawings. The components in the figures are not necessarily to scale, emphasis instead being placed upon illustrating the principles of the embodiments. Like reference numerals designate corresponding parts throughout the different views.
FIG. 1 is a schematic flow diagram of the test system.
Fig. 2 is a schematic diagram illustrating an error correction process of the correction component.
FIG. 3 is a flow chart illustrating a corrective action of the correction component.
Fig. 4 is a schematic flow chart of storing the original prediction data.
Fig. 5 is a flow chart of the vision monitoring system.
Fig. 6 is one of the schematic flow charts of modeling the characteristic values of the acquired image data.
Detailed Description
In order to make the objects and advantages of the present invention more apparent, the present invention will be further described in detail with reference to the following embodiments; it should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. Other systems, methods, and/or features of the present embodiments will become apparent to those skilled in the art upon review of the following detailed description. It is intended that all such additional systems, methods, features and advantages be included within this description, be within the scope of the invention, and be protected by the accompanying claims. Additional features of the disclosed embodiments are described in, and will be apparent from, the detailed description that follows.
The same or similar reference numerals in the drawings of the embodiments of the present invention correspond to the same or similar components; in the description of the present invention, it should be understood that if there is an orientation or positional relationship indicated by the terms "upper" and "lower" and "left" and "right" etc., it is only for convenience of description and simplification of the description based on the orientation or positional relationship shown in the drawings, but it is not indicated or implied that the device or assembly referred to must have a specific orientation.
The first embodiment is as follows: A3D printed pressure vessel mapping test system includes an initial conditions collector, a model generation component, a correction component, and a database, the collector for receiving a set of input field data and a set of archived model states and comparing the set of input field data to the set to determine a set of archived model states to determine that the set of archived model states best matches the set of input field data, the determined set of archived model states representing predicted initial conditions; the model generation component is configured for generating raw drawing data based on the forecasted initial conditions and initial condition collector input data. The correction component is configured to obtain a model class address for a device in the model generation component after completing the update of the collector part; determining that the model category address is not matched with the model category address of the corresponding model generation component in the test result; and based on the determination, initiating a corrective action in the database. The corrective action includes: initiating an update of a drawing data device in the database and using, in part, the test results to identify a correction of the drawing data device; issuing a notification to a display in the database, wherein content in the notification is based at least in part on the trial results. The initial condition collector comprises: receiving a set of input field data; determining a set of model observations from the input field data; and determining a set of predicted initial conditions based on a set of actual observations and an archived model state library; determining the set of predicted initial conditions comprises: comparing the observations of the set of models to the archived model states; and selecting the optimal model state that best matches the actual observed value. Selecting the optimal model state includes: performing an optimization method between the archived model states with respect to an observation of the model; the archived model states are evaluated against observations of the model using a user-defined objective function or a user-defined loss function. Comparing the raw prediction data to the selected model state to determine whether variability and range exists between the raw prediction data and the selected model state; and if variability and range are determined, updating the library or archived model state to include the raw prediction data.
Example two: this embodiment, which should be understood to include at least all of the features of any of the preceding embodiments and further developed therefrom, provides in particular a 3D printed pressure vessel mapping test system comprising an initial conditions collector for receiving a set of input field data and a set of archived model states and comparing the set of input field data with the set to determine a set of archived model states to determine that the set of archived model states best matches the set of input field data, the determined set of archived model states representing predicted initial conditions; the model generation component is configured to generate original drawing data based on the forecasted initial conditions and initial condition collector input data; specifically, the whole system comprises an initial condition collector for receiving and comparing a group of input field data and a group of archived model states; inputting a field data set and an archive model state set to determine which set of archive model states best matches the input field data set, wherein the determined set of archive model states represents predicted initial conditions; the model generation component is used for generating original drawing data based on the forecasted initial conditions and the input data of the initial condition collector; more data can be acquired before the model is established, and drawing of a drawing is ensured to be accurate, so that the drawing can be accurately printed in the printing process; laying a cushion for further data acquisition of a subsequent visual monitoring device, in the embodiment, the whole system further comprises the visual monitoring device, and the visual monitoring machine is used for separating the set of initial input data of the model into characteristic quantities of each element; in addition, the characteristic values of the respective elements are stored in a database of archived model states; in this embodiment, the database can be dynamically updated, that is: acquiring input data according to the acquisition of the data of the visual monitoring system, and ensuring that the database can be dynamically updated; additionally, the vision monitoring system comprises a first in-situ monitoring system and a second in-situ imaging system; in this embodiment, the in-situ monitoring system and the in-situ imaging system may be used to control model parameters, the first in-situ monitoring system includes a sensor that generates a raw signal depending on the thickness of the model being constructed, which instructs the first in-situ monitoring system to construct the model, which may also be constructed according to data input by an operator in this embodiment; the first in situ monitoring system includes, but is not limited to, several systems listed below, including: a science monitoring system, a spectrum monitoring system, etc.;
in this embodiment, the vision monitoring system includes a substrate supported for inspection and disposed on the substrate, and the sensor is configured to sweep across a base of the model to be constructed, the sensor divides coordinates of the base into a plurality of regions and selects the region according to the size of the model to be constructed, so that the base can be constructed to form a proper model drawing; the substrate and the base are arranged in parallel, the bottom of a printed model is arranged on the base, and the substrate is arranged right above or laterally above the base; in addition, the vision system is also arranged on the substrate and extends out towards one side of the base; in this embodiment, the sensor may be fixed to the substrate and rotate with the central axis of the substrate such that with each rotation of the substrate, the sensor sweeps across the base in an arc; during the scanning, the sensor builds a model from the base towards the direction close to the substrate step by step; in addition, in the embodiment, a focusing system is further provided, and the focusing system is configured to control the focal length of the sensor to gradually build the model from far to near;
the first in-situ monitoring system may include a light source, a light detector, and circuitry for sending and receiving signals between a controller of a computer and the light source; the light detector employs one or more optical fibers operable to transmit light from the light source to the window and to transmit light reflected from the base to the detector; a bifurcated optical fiber may be used in this embodiment to transmit light from the light source to the window and back to the detector; in this embodiment, one end of the bifurcated fiber may provide a photosensor that sweeps across the base; if the optical monitoring system employed in this embodiment is a spectroscopic system, the light source may be operable such that the entire device emits white light and the detector may be a spectrometer; emitting white light to the spectrometers to enable pairing;
the build system includes position sensors including, but not limited to, several devices listed below: including an optical interrupter configured to sense when a sensor of the first in-situ monitoring system is below the substrate and when the sensor is off the substrate; for example, a position sensor may be mounted in a fixed position relative to the carrier head to mark the periphery to which the platen may be attached, select the attachment point and length of the mark so that when the sensor sweeps over the base, it can send a signal to the position sensor; in another embodiment, a build system includes an encoder configured to determine an angular position of a platen such that spectra are obtained from different locations on a substrate after one rotation of the platen; in particular, some spectra may be obtained from locations closer to the center of the substrate, and some spectra may be obtained from locations closer to the edge; the controller may be configured to calculate the radial position from each measurement from the scan based on timing, motor encoder information, platen rotation or position sensor data, and/or optical detection of the edge, i.e.: position acquisition with respect to the center position of the substrate, the thickness of the substrate or the retaining ring; thus, the controller may associate various measurements to various regions on the substrate; in this embodiment, the measured time may be used as an alternative to an accurate calculation of the radial position; in addition, the in-situ imaging system to generate an image of substantially the same portion of the substrate being measured by the first in-situ monitoring system, in other words, the camera of the imaging system is co-located with the sensor of the in-situ monitoring system, which in this embodiment includes a light source, a light detector, and circuitry for sending and receiving signals between the controller and the light source and light detector; the light source is operable to emit white light, including light having a wavelength of-nanometers, suitable light sources include a white Light Emitting Diode (LED) array, a xenon lamp, or a xenon mercury lamp; the light source is oriented to direct light onto an exposed surface of a substrate at a non-zero angle of incidence α; the angle of incidence α may be, for example, between about 45 ° and 150 °, for example at 135 ° and 45 ° the light source may illuminate an elongate substantially linear region which may span the width of the substrate; the light source is disposed in a light source canister, the light source canister including optics including a beam expander to spread light from the light source into the elongated area; the light source itself, as well as the area illuminated on the substrate, may be elongated and have a longitudinal axis parallel to the substrate surface; a diffuser may also be placed in the path of the light or it may be provided to diffuse the light before it reaches the substrate; the detector is a camera sensitive to light from the light source, which may be a financial institution camera, and which camera comprises an array of detector elements, in this embodiment a CCD array; the array is a single row of detector elements, the camera may be a line scan camera and the rows of detector elements of the scan camera may extend parallel to the longitudinal axis of the elongate area illuminated by the light source, in which case the light source comprises a row of light emitting elements, the row of detector elements may extend along a first axis parallel to the longitudinal axis of the light source; a row of detector elements may comprise one or more elements, the detector being configured with suitable focusing optics to project the field of view of the substrate onto an array of detector elements of the detector; the field of view may be long enough to view the entire width of the substrate, and the detector may also be configured so that the pixel width is comparable to the pixel length; for example, line scan cameras have the advantage that their frame rate is very fast; the frame frequency can be at least 10 kHz; the frame rate may be set to a frequency such that when the imaging area is scanned over the substrate, the pixel width is comparable to the pixel length, a possible advantage of the line scan camera moving with the light source over the entire substrate may therefore be that artefacts caused by variations in viewing angle may be reduced or eliminated; in addition, the line scan camera can eliminate perspective distortion, while the conventional camera shows inherent perspective distortion and needs to be corrected through image transformation; the polarizing filter may be positioned in the path of the light during the calibration by being positioned in the light path, the position of the positioning being between the substrate and the detector; additionally, the polarizing filter may be a circular polarizer, typically a combination of a linear polarizer and a quarter wave plate, such that proper orientation of the polarization axis of the polarizing filter may reduce haze in the image and sharpen or enhance desired visual features;
in addition, the controller may convert raw signals from the in-situ monitoring system into useful measurements, in this embodiment the entire system is further provided with a first in-situ monitoring system and a second in-situ imaging system, such that the controller calculates measurements using both signals from the first in-situ monitoring system and image data from the second in-situ imaging system and images collected from the in-situ imaging system may be synchronized with the data stream collected from the first in-situ monitoring system, ensuring that the controller feeds images from the in-situ imaging system to the vision system configured to derive characteristic values for a portion of the substrate measured by the first in-situ monitoring system; the vision system may include, for example, a neural network, which may be a convolutional neural network, including a plurality of input nodes from each pixel in an image acquired by the in situ imaging system; each acquired image comprises input nodes Ti, T. The neural network further comprises a plurality of hidden nodes, a representation value and an output node corresponding to the representation value; in the present embodiment, the hidden node outputs a value of a weighted sum nonlinear function of values from nodes connected to the hidden node;
in the modeling process, modeling is carried out according to the following formula: tan (0.5 a/ci (ii) + a/c2(l2) +. a. + akm (lm) + bk), where tan is hyperbolic tangent, a/Vis is the connecting weight intermediate node between k and the xth input node (the first of M input nodes), IM is the value at the M < ft > input node, T is the eigenvalue or the output node corresponding to the eigenvalue; in addition, in this embodiment, other non-linear functions may be used instead of the tanT, such as: a rectified linear unit function and variants thereof;
the architecture of the neural network may vary in depth and width; although the neural network is shown with one column of intermediate nodes, in practice the neural network will comprise many columns, which may have various connections; the convolutional neural network may perform multiple iterations of convolution and merging, then perform classification; back propagation with the acquired sample image and sample feature values; thus, in the data acquisition operation, the vision system generates characteristic values based on images from the in situ imaging system, which may be performed for each value of the raw signal received from the in situ monitoring system; inputting a raw signal from the in-situ monitoring system and a characteristic value synchronized with the raw signal into a conversion algorithm module; the conversion algorithm module calculates a measured value according to the characteristic value and the raw signal, where the measured value is usually a parameter such as the thickness of the outer layer of the model, and may also be adjusted according to actual needs, or a parameter that a person skilled in the art wants to collect, for example: height isoparametric of the model; in addition, the measurement value may be a more general representation of the progress of the substrate during the model building process, specifically, an index value of the platen rotation time or the number of times of the turntable rotation during which the measurement value is expected to be observed, following a predetermined progress; additionally, the measurements are fed to a process control subsystem to adjust the model build process based on a series of detecting a model build endpoint and stopping polishing and/or adjusting a model build pressure during the model build process to reduce non-uniformity, a characterization value of the model build; the process control module may output process parameters including a pressure for a chamber in the carrier head or a signal to stop the model build; the first function of the process control module may be adapted to the sequence of measured values of the first region and the second function of the process control module may be adapted to the sequence of characteristic values of the second region; the process controller may calculate times T and T at which the first function of the process control module and the second function of the process control module are projected to reach a target value V, and may calculate adjusted process parameters that will result in a change in one of the zones, the adjusted carrier head pressure, at a rate that modifies the model build, so that the zones reach the target at about the same time; combining the plurality of measurements at a conversion algorithm module or a process control module; if the system generates multiple measurements from a single scan of the sensor across the substrate, the conversion algorithm module can combine the multiple measurements from the single scan to generate a single measurement per scan or a single measurement per radial region of the substrate;
the in-situ monitoring system may be a spectroscopic monitoring system; the sensors of the spectral monitoring system and the in-situ imaging system are configured to use the same window so that the data window of the line scanning camera from the in-situ imaging system is centered on the time of acquiring the spectrum by the in-situ monitoring system, and is used for reconstructing the two-dimensional image of the partial image and collecting the substrate of the spectrum, so that during the construction process of the model, all parameters can be completely collected to provide reference for the subsequent printing of the model; in the embodiment, the collected substrate of the spectrum can be selectively used or replaced by an operator, so that efficient replacement can be realized in the printing process; in the replacement process, only the substrate needs to be replaced in the same type, so that the conversion efficiency is ensured, and the application scenes of the whole system are increased; the visual system may include a convolutional neural network, while for training the neural network, the relevant classes may include: arrays, scribes, peripheries, contact pads, etc. automatically identify a series of images from one or more reference substrates; assigning a classification to the image may use back propagation in a training mode to input the image and the classification from the reference substrate to a neural network to train the neural network as an image classifier; this is well known to those skilled in the art and, therefore, is not described in detail;
in addition, in the embodiment, an inspection system is further provided, where the inspection system includes an eddy current inspection system, and the eddy current inspection system is configured to perform a verification operation on the constructed model, so that the probability of occurrence of defects is reduced and the efficiency of model construction is improved in the whole model construction process; the scanning sensor of the eddy current monitoring system and the sensor of the in-situ imaging system are in the same position; a line scan camera of the in-situ imaging system generates a time-synchronized image covering the entire scan of the sensor over the entire substrate; in particular, in operation, during modeling of the substrate, the images are fed to the neural network and used simultaneously by the output of the neural network in real time to correlate each measurement from the eddy current monitoring system with the geometric value of the portion of the substrate from which the spectrum was obtained; and the geometry values generated by the neural network may be used by the conversion algorithm module; the mapping from eddy current signals to resistance depends on the relative direction and location of features on the substrate, and the sensitivity of the scanning sensor to conductive loops on the substrate may depend on the orientation of the loops; the controller may include functionality to calculate a gain based on a geometric value, such as orientation, which may then be applied to the signal, multiplying the signal value by the gain; thus, the geometric values may be used to adjust how eddy current sensor data is interpreted;
in addition, the Zhenge system also comprises a fault forecast database and a fault data processor; once the field sensor and remote sensing data has been processed by the initial condition collector and the model state space has been initialized and the parameters have been adjusted for use with the fully integrated model simulator, production of the model, generation of fault or raw forecast data can begin and the raw forecast data can then be stored in a fault forecast database; the fault forecasting database is used for storing similar things in the database to provide references, so that the references can be provided when the same model is modeled, the data is corrected in the data processing process, the model is efficiently corrected, and the fault data processor and the fault forecasting database are transmitted in the correcting process, so that the establishment of the whole model can be reasonably and efficiently established;
the fault data processor may include an evaluation module that performs automatic evaluation of fault prediction skills; evaluating the forecasting skills requires a posterior analysis of the match between the forecasting model conditions and the model building; the post-analysis may be performed at any time increment within the total prediction length; skill assessment can be based on a number of criteria including, but not limited to, bias, so that the model can be reliably and accurately constructed in the process of building, and meanwhile, the construction of the model is ensured to be more complete through the arrangement of the assessment module;
the model state library hosts or stores preconfigured sets of digitally stable model state space descriptions, which can be derived from initializing a fully integrated initial condition collector and the updated database; because these state space descriptions are numerically stable, a powerful start-up of fault simulation can be facilitated without the need for the traditional simulation acceleration period required after data assimilation;
the correction component is configured to obtain a model class address for a device in the model generation component after the update of the collector part is completed; determining that the model category address is not matched with the model category address of the corresponding model generation component in the test result; and based on the determination, initiating a corrective action in the database; the corrective action includes: initiating an update of a drawing data device in the database and using, in part, the test results to identify a correction of the drawing data device; issuing a notification to a display in the database, wherein content in the notification is based at least in part on the trial results; specifically, in the correction process, the control unit updates the model, so that the whole model performs drawing production or printing operation according to the latest model, and the effectiveness of the whole experiment system is effectively ensured; in addition, the correction component records the model category addresses respectively in the correction process, and meanwhile, after model primary experience is carried out, the model category addresses of the model generation component are compared and matched, if the matching condition exists, correction measures are initiated;
the initial condition collector comprises: receiving a set of input field data; determining a set of model observations from the input field data; and determining a set of predicted initial conditions based on a set of actual observations and an archived model state library; determining the set of predicted initial conditions comprises: comparing the observations of the set of models to the archived model states; and selecting the optimal model state which is most matched with the actual observed value; selecting the optimal model state includes: performing an optimization method between the archived model states with respect to an observation of the model; evaluating the archived model state against observations of the model using a user-defined objective function or a user-defined loss function; comparing the raw prediction data to the selected model state to determine whether variability and range exists between the raw prediction data and the selected model state; and if variability and range are determined, updating the library or archived model state to include the raw prediction data; specifically, in this embodiment, a method for storing original prediction data is provided, where the method is used to store the original prediction data, and the method includes: performing a check to determine whether the raw prediction data adds variability and range to the model state used to generate the predicted initial conditions; if it is determined that variability and range are increased, updating the model state library with relevant information from the original prediction data so as to maintain a current model state library for future predictions or simulations; in addition, the model state library is periodically updated with model states that are more relevant to generating predictions or models rather than relying on previously determined or sensed model states; all raw prediction data is stored in a model state library so that open loop simulations can be performed without checking variability or range and the model state library can be periodically evaluated to determine uniqueness of the stored information; if the model states are similar, some of them may be deleted; in addition, in the embodiment, in the selection, an optimal optimization method is used for storing the original prediction data, and during the storage, an optimal model state is stored, so that the optimal model replaces the model stored in the database.
In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and reference may be made to the related descriptions of other embodiments for parts that are not described or illustrated in a certain embodiment.
In summary, according to the pressure container mapping test system for 3D printing provided by the invention, each input node is provided in each image acquired by the collector, so that the model is ensured to be more complete in the process of being constructed; the data window of the scanning camera is used for reconstructing the two-dimensional image of the partial image and collecting the substrate of the spectrum from the two-dimensional image by taking the time of acquiring the spectrum by the in-situ monitoring system as the center, so that all parameters can be completely collected in the construction process of the model, reference is provided for the subsequent printing of the model, the collected substrate of the spectrum can be selectively used or replaced by an operator, the efficient replacement can be realized in the printing process, and the application scenes of the whole system are increased; the fault forecasting database is used for providing reference for similar objects stored in the database, so that the reference can be provided when the same model is modeled, the data is corrected in the data processing process, the model is corrected efficiently, and the fault data processor and the fault forecasting database are transmitted in the correcting process, so that the establishment of the whole model can be reasonably and efficiently established; the automatic evaluation of the fault forecasting skills is executed by adopting the evaluation module, so that the model can be reliably and accurately constructed in the construction process, and meanwhile, the construction of the model is ensured to be more perfect by the arrangement of the evaluation module.
Although the invention has been described above with reference to various embodiments, it should be understood that many changes and modifications may be made without departing from the scope of the invention. That is, the methods, systems, and devices discussed above are examples. Various configurations may omit, substitute, or add various procedures or components as appropriate. For example, in alternative configurations, the methods may be performed in an order different than that described, and/or various components may be added, omitted, and/or combined. Moreover, features described with respect to certain configurations may be combined in various other configurations, as different aspects and elements of the configurations may be combined in a similar manner. Further, elements therein may be updated as technology evolves, i.e., many elements are examples and do not limit the scope of the disclosure or claims.
Specific details are given in the description to provide a thorough understanding of the exemplary configurations including implementations. However, configurations may be practiced without these specific details, for example, well-known circuits, processes, algorithms, structures, and techniques have been shown without unnecessary detail in order to avoid obscuring the configurations. This description provides example configurations only, and does not limit the scope, applicability, or configuration of the claims. Rather, the foregoing description of the configurations will provide those skilled in the art with an enabling description for implementing the described techniques. Various changes may be made in the function and arrangement of elements without departing from the spirit or scope of the disclosure.
In conclusion, it is intended that the foregoing detailed description be regarded as illustrative rather than limiting, and that it be understood that these examples are illustrative only and are not intended to limit the scope of the invention. After reading the description of the invention, the skilled person can make various changes or modifications to the invention, and these equivalent changes and modifications also fall into the scope of the invention defined by the claims.
Claims (1)
1. A3D printed pressure vessel mapping test system is characterized by comprising an initial condition collector, a model generation component, a correction component and a database, wherein the initial condition collector is used for receiving a group of input field data and a group of archived model states, comparing the group of input field data with the group of archived model states to determine that a set of archived model states is the best matched with the set of input field data, and the determined set of archived model states represents predicted initial conditions; the model generation component is configured to generate prediction data based on the predicted initial conditions and input field data of the initial condition collector;
the correction component is configured to obtain a model class address for a device in the model generation component after completing the update of the collector part; determining that the model category address is not matched with the model category address of the corresponding model generation component in the test result; and based on the determination, initiating a corrective action in the database;
the corrective action includes: initiating an update of a drawing data device in the database and using, in part, the test results to identify a correction of the drawing data device; issuing a notification to a display in the database, wherein content in the notification is based at least in part on the trial results;
the initial condition collector comprises: receiving a set of input field data; determining a set of model observations from the input field data; and determining a set of predicted initial conditions based on a set of actual observations and an archived model state library; determining initial conditions for the set of predictions comprises: comparing the observations of the set of models to the archived model states; selecting the optimal model state which is most matched with the actual observed value;
selecting the optimal model state includes: performing an optimization method between the archived model states with respect to an observation of the model; evaluating the archived model state against observations of the model using a user-defined objective function or a user-defined loss function;
comparing the prediction data to the selected model state to determine whether variability and range exists between the prediction data and the selected model state; and if variability and range are determined, updating the database or archived model state to include the prediction data;
the system also comprises a visual monitoring device, wherein the visual monitoring device is used for separating the set of initial input data of the archived model into characteristic quantities of each element; the feature quantities of the respective elements are stored in a database of archived model states; the database can be dynamically updated; the visual monitoring device comprises a first in-situ monitoring system and a second in-situ imaging system; the first in-situ monitoring system comprises a sensor, a light source, a light detector, and circuitry for sending and receiving signals between a controller of a computer and the light source;
the visual monitoring device comprises a supporting substrate, wherein the sensor for detecting is arranged on the substrate, the sensor is configured to sweep a base of a constructed model, the sensor divides the coordinates of the base into a plurality of areas and selects the areas according to the size of the constructed model, so that the base can be constructed to form a proper model drawing; the second in situ imaging system includes a camera, a light source, a light detector, and circuitry for sending and receiving signals between the controller and the light source and light detector; the camera of the second in-situ imaging system is co-located with the sensor of the first in-situ monitoring system, the second in-situ imaging system generating an image of the same portion of the substrate being measured by the first in-situ monitoring system;
the substrate and the base are arranged in parallel, the bottom of a printed model is arranged on the base, and the substrate is arranged right above or laterally above the base; the sensor is fixed to the substrate and rotates with the central axis of the substrate, such that with each rotation of the substrate, the sensor sweeps across the pedestal in an arc; during scanning, the sensor approaches the base gradually towards the substrate to build a model; the vision monitoring device is further provided with a focusing system, and the focusing system is configured to control the focal distance of the sensor to gradually build the model from far to near.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010387873.8A CN111572026B (en) | 2020-05-09 | 2020-05-09 | Pressure vessel mapping test system for 3D printing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010387873.8A CN111572026B (en) | 2020-05-09 | 2020-05-09 | Pressure vessel mapping test system for 3D printing |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111572026A CN111572026A (en) | 2020-08-25 |
| CN111572026B true CN111572026B (en) | 2021-10-19 |
Family
ID=72120720
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010387873.8A Active CN111572026B (en) | 2020-05-09 | 2020-05-09 | Pressure vessel mapping test system for 3D printing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111572026B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102007042922A1 (en) * | 2007-09-08 | 2009-03-12 | Phacon Gmbh | Method for preparing anatomical models in human and veterinary medicine, involves acquisitioning of image of patient data through two-dimension or three-dimension ultrasound, and exporting image data from ultrasound device |
| CN104400998A (en) * | 2014-05-31 | 2015-03-11 | 福州大学 | 3D printing detection method based on infrared spectroscopic analysis |
| CN105157590A (en) * | 2015-05-28 | 2015-12-16 | 张家港江苏科技大学产业技术研究院 | Construction health monitoring system based on three-dimensional laser scanning technology |
| CN107729582A (en) * | 2016-08-11 | 2018-02-23 | 张家港江苏科技大学产业技术研究院 | Component defect inspection and forecasting system based on TLS |
| CN107839240A (en) * | 2017-11-16 | 2018-03-27 | 杭州捷诺飞生物科技股份有限公司 | The 3 D-printing method and device monitored in real time |
| CN110370649A (en) * | 2019-07-11 | 2019-10-25 | 中国科学院自动化研究所 | On-Line Monitor Device, the system of 3D printing equipment |
-
2020
- 2020-05-09 CN CN202010387873.8A patent/CN111572026B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102007042922A1 (en) * | 2007-09-08 | 2009-03-12 | Phacon Gmbh | Method for preparing anatomical models in human and veterinary medicine, involves acquisitioning of image of patient data through two-dimension or three-dimension ultrasound, and exporting image data from ultrasound device |
| CN104400998A (en) * | 2014-05-31 | 2015-03-11 | 福州大学 | 3D printing detection method based on infrared spectroscopic analysis |
| CN105157590A (en) * | 2015-05-28 | 2015-12-16 | 张家港江苏科技大学产业技术研究院 | Construction health monitoring system based on three-dimensional laser scanning technology |
| CN107729582A (en) * | 2016-08-11 | 2018-02-23 | 张家港江苏科技大学产业技术研究院 | Component defect inspection and forecasting system based on TLS |
| CN107839240A (en) * | 2017-11-16 | 2018-03-27 | 杭州捷诺飞生物科技股份有限公司 | The 3 D-printing method and device monitored in real time |
| CN110370649A (en) * | 2019-07-11 | 2019-10-25 | 中国科学院自动化研究所 | On-Line Monitor Device, the system of 3D printing equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111572026A (en) | 2020-08-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP1364226B1 (en) | Apparatus and method for obtaining three-dimensional positional data from a two-dimensional captured image | |
| EP2752657B1 (en) | System and methods for stand-off inspection of aircraft structures | |
| US11448498B2 (en) | Three-dimensional reconstruction system and three-dimensional reconstruction method | |
| US20030038933A1 (en) | Calibration apparatus, system and method | |
| CN106338244A (en) | 3d measuring machine | |
| CN114323571B (en) | Multi-optical-axis consistency detection method for photoelectric aiming system | |
| US11629957B2 (en) | Surveying apparatus | |
| JP2016519757A (en) | Three-dimensional coordinate scanner and operation method | |
| CN106500843B (en) | A kind of imaging spectrometer optimum image plane calibration method and device | |
| CN104034352B (en) | Method for measuring field curvature of space camera by adopting laser tracker and interference check | |
| US11168976B2 (en) | Measuring device for examining a specimen and method for determining a topographic map of a specimen | |
| CN109683168A (en) | A kind of geometric method laser imaging range unit and its measurement method | |
| CN110260889B (en) | Automatic calibrating device and method for handheld range finder | |
| CN111572026B (en) | Pressure vessel mapping test system for 3D printing | |
| CN110567920B (en) | Detection system for haze of transparent or semitransparent glass | |
| CN111060029A (en) | Curvature radius measuring device and measuring method thereof | |
| US20200278203A1 (en) | A method, a system and a computer program for measuring a distance to a target | |
| US7117047B1 (en) | High accuracy inspection system and method for using same | |
| US20160131526A1 (en) | Spectroscopic Analysis System and Method | |
| CN109813531A (en) | The debugging apparatus and its adjustment method of optical system | |
| US10191163B2 (en) | Method for the absolute calibration of the location and orientation of large-format detectors using laser radar | |
| CN105717502A (en) | High speed laser distance measuring device based on linear array CCD and method | |
| Rangel et al. | Characterization and calibration of a stereo gas camera system for obtaining spatial information of gas structures | |
| JP4651550B2 (en) | Three-dimensional coordinate measuring apparatus and method | |
| US20230113768A1 (en) | Chromatic range sensor system with spherical calibration object and method |
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 |