CN116277952A

CN116277952A - 3D printing equipment, method, device and medium

Info

Publication number: CN116277952A
Application number: CN202310364024.4A
Authority: CN
Inventors: 王香港
Original assignee: Suzhou Atech New Material Technology Co ltd; Suzhou Yizhe Intelligent Technology Co ltd
Current assignee: Suzhou Atech New Material Technology Co ltd; Suzhou Yizhe Intelligent Technology Co ltd
Priority date: 2023-04-07
Filing date: 2023-04-07
Publication date: 2023-06-23
Anticipated expiration: 2043-04-07
Also published as: CN116277952B

Abstract

The embodiment of the specification provides 3D printing equipment, a method, a device and a medium, comprising the following steps: the device comprises a printing module, a movable base, a wireless remote control module and a feeding module; the feeding module comprises an automatic feeding module, a stirring module and a pumping module; the wireless remote control module comprises an interaction module and a control system; the control system is respectively in communication connection with the interaction module, the printing module, the movable base and the feeding module, and is used for: in 3D printing of the target building component, in response to satisfaction of a preset condition: and determining a control parameter and transmitting the control parameter to at least one of the printing module, the movable base and the feeding module, wherein the control parameter at least comprises a movement parameter, the movement parameter at least comprises a movement speed, and the movement parameter is at least used for enabling the movable base to move at the movement speed.

Description

3D printing equipment, method, device and medium

Technical Field

The present disclosure relates to the field of 3D printing technologies, and in particular, to a 3D printing device, method, apparatus, and medium under a complex construction environment.

Background

The 3D printing technology is a technology for constructing objects by using bondable materials such as plastic or powdered metal based on a digital model through a rapid prototyping technology in a layer-by-layer printing and stacking manner. The 3D printing technology has high automation degree, can reduce labor force requirements, reduce building materials and energy consumption, lighten environmental pollution of building engineering, and can manufacture the appearance which cannot be manufactured by the traditional production technology.

CN103967276B discloses a construction engineering construction device based on 3D printing technology, which omits the work of assembling and disassembling the template, decorating the outer surface of the structure, etc. by adopting the template integrated printing and fiber concrete synchronous pouring technology of the 3D printing technology as the bearing material, thereby improving the construction efficiency, reducing the labor force investment and controlling the construction quality. However, the device does not relate to the problem of how to improve the printing efficiency of the 3D printing device according to the printing condition and the site condition under the complex construction environment (for example, printing large building components).

Accordingly, it is desirable to provide a 3D printing apparatus and method to achieve an improvement in construction printing efficiency according to printing conditions and site conditions under a complex construction environment (e.g., printing of large building members).

Disclosure of Invention

One or more embodiments of the present specification provide a 3D printing apparatus. The 3D printing apparatus includes: the device comprises a printing module, a movable base, a wireless remote control module and a feeding module; the feeding module comprises an automatic feeding module, a stirring module and a pumping module; the wireless remote control module comprises an interaction module and a control system; the control system is respectively in communication connection with the interaction module, the printing module, the movable base and the feeding module, and is used for: in 3D printing of the target building component, in response to satisfaction of a preset condition: determining a control parameter and sending the control parameter to at least one of the printing module, the mobile base and the feeding module, wherein the control parameter at least comprises a movement parameter, the movement parameter at least comprises a movement speed, and the movement parameter is at least used for enabling the mobile base to move at the movement speed.

One or more embodiments of the present specification provide a 3D printing method implemented by a control system of a 3D printing apparatus; the 3D printing apparatus includes: the device comprises a printing module, a movable base, a wireless remote control module and a feeding module; the feeding module comprises an automatic feeding module, a stirring module and a pumping module; the wireless remote control module comprises an interaction module and the control system; the control system is respectively in communication connection with the interaction module, the printing module, the movable base and the feeding module; the method comprises the following steps: in 3D printing of the target building component, in response to satisfaction of a preset condition: determining a control parameter and sending the control parameter to at least one of the printing module, the mobile base and the feeding module, wherein the control parameter at least comprises a movement parameter, the movement parameter at least comprises a movement speed, and the movement parameter is at least used for enabling the mobile base to move at the movement speed.

One or more embodiments of the present specification provide a 3D printing apparatus comprising at least one storage medium for storing computer instructions and at least one processor; the at least one processor is configured to execute the computer instructions to implement a 3D printing method.

One or more embodiments of the present specification provide a computer-readable storage medium storing computer instructions that, when read by a computer in the storage medium, perform a 3D printing method.

Drawings

The present specification will be further elucidated by way of example embodiments, which will be described in detail by means of the accompanying drawings. The embodiments are not limiting, in which like numerals represent like structures, wherein:

FIG. 1 is a block diagram of a 3D printing device according to some embodiments of the present description;

FIG. 2 is an exemplary flow chart of determining the print rate and print thickness of a current slice according to some embodiments of the present description;

FIG. 3 is an exemplary flow chart of determining a feed rate over a future preset time period according to some embodiments of the present description;

FIG. 4 is a diagram of a model of material prediction according to some embodiments of the present description.

Detailed Description

In order to more clearly illustrate the technical solutions of the embodiments of the present specification, the drawings that are required to be used in the description of the embodiments will be briefly described below. It is apparent that the drawings in the following description are only some examples or embodiments of the present specification, and it is possible for those of ordinary skill in the art to apply the present specification to other similar situations according to the drawings without inventive effort. Unless otherwise apparent from the context of the language or otherwise specified, like reference numerals in the figures refer to like structures or operations.

It will be appreciated that "system," "apparatus," "unit" and/or "module" as used herein is one method for distinguishing between different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the words can be replaced by other expressions.

As used in this specification and the claims, the terms "a," "an," "the," and/or "the" are not specific to a singular, but may include a plurality, unless the context clearly dictates otherwise. In general, the terms "comprises" and "comprising" merely indicate that the steps and elements are explicitly identified, and they do not constitute an exclusive list, as other steps or elements may be included in a method or apparatus.

A flowchart is used in this specification to describe the operations performed by the system according to embodiments of the present specification. It should be appreciated that the preceding or following operations are not necessarily performed in order precisely. Rather, the steps may be processed in reverse order or simultaneously. Also, other operations may be added to or removed from these processes.

Fig. 1 is a block diagram of a 3D printing device according to some embodiments of the present description.

In some embodiments, the 3D printing device 100 may include a printing module 110, a mobile base 120, a wireless remote control module 130, and a feeding module 140.

The printing module 110 refers to a module that performs 3D printing. In some embodiments, the print module 110 may include a robotic arm and binocular vision.

The mobile base 120 refers to a base that can drive the 3D printing device to move. In some embodiments, the mobile base may be crawler-type or wheeled.

The supply module 140 refers to a module that provides raw materials required for 3D printing. In some embodiments, the feed modules may include an automatic feed module 140-1, a stirring module 140-2, and a pumping module 140-3.

The pumping module refers to a module that pumps raw materials through screw extrusion.

The wireless remote control module 130 refers to a module for remotely controlling the 3D printing apparatus. In some embodiments, the wireless remote control module 130 may include an interaction module 130-1 and a control system 130-2.

The interaction module 130-1 refers to a module that performs interaction between a user and a device. For example, the interaction module may be a user terminal. In some embodiments, the interaction module may be configured to obtain movement control instructions of the 3D printing device and send the control system.

The control system 130-2 may process data and/or information obtained from other modules of the 3D printing device to execute program instructions based on the data, information, and/or processing results to perform one or more functions described herein.

In some embodiments, the control system may be communicatively coupled to the interactive module, the printing module, the mobile base, and the feed module, respectively.

In some embodiments, the control system may be configured to determine control parameters in response to satisfaction of preset conditions during 3D printing of the target building component, and send the control parameters to at least one of the printing module, the mobile base, and the feeding module.

The target building element refers to a large building element to be 3D printed. For example, the target building element may include one or more of a floor, wall, column, etc. to be 3D printed.

The preset condition refers to a condition to be satisfied by a preset control parameter. For example, the preset condition may include that the road surface roughness satisfies a preset requirement. The road surface roughness refers to the degree of roughness of the road surface. The preset requirements may be preset empirically by those skilled in the art.

The control parameters may refer to any parameters used by the 3D printing device in 3D printing of the target building element.

In some embodiments, the control parameters include at least a movement parameter.

The movement parameters refer to parameters for controlling movement of a robotic arm or a mobile base on the 3D printing device.

In some embodiments, the movement parameters may include at least a movement speed. The movement parameters may be at least for moving the mobile base at a movement speed.

In some embodiments, the control system may determine movement parameters of the mobile base based on the 3D print job schedule or the road surface relief. For example, since the target building elements are constructed by stacking layers in the 3D printing process, the 3D printing has a printing sequence, and when a certain layer structure is to be printed, the control system can determine the movement parameters of the mobile base according to the 3D printing task arrangement. For another example, when the road surface is depressed and the predetermined road surface roughness requirement is satisfied, the moving speed of the movable base may be set to be slightly slower.

In some embodiments of the present disclosure, a control system on a 3D printing apparatus can adjust control parameters (e.g., movement parameters of a mobile base) of a target building component in a 3D printing process in real time according to preset conditions (e.g., road surface roughness), and send the control parameters to at least one of a printing module, the mobile base, and a feeding module, so as to implement 3D printing on the target building component.

In some embodiments, the control parameters may also include printing parameters. The printing parameters may be sent by the control system to the printing module to cause the printing module to perform 3D printing based on the printing parameters.

The print parameters refer to parameters related to slice printing.

In some embodiments, the printing parameters may include at least one of a printing rate and a printing thickness of the current slice.

The slicing refers to slicing the target building member layer by layer according to a preset slicing thickness, and each layer is obtained by slicing a three-dimensional model (which can be expressed as stl file, obj file, etc. in a computer) of the target building member into a series of two-dimensional planes (i.e. slicing, which can be expressed as files which can be identified by a 3D printer, such as slc file, cli file, etc.) according to the slicing thickness. The current slice refers to a slice in which 3D printing is being performed.

In some embodiments, the control system may determine the print rate and print thickness of the current cut sheet based on the characteristic information of the target building element.

In some embodiments, the characteristic information of the target building component may include one or more of a component type, a component structural feature, a component application scenario, a component strength requirement, a component accuracy requirement, and the like of the target building component.

The component type refers to the type of the target building component. For example, the component types may include one or more of walls, posts, floors (floors), stairways, doors, windows, and the like.

Component structural features refer to features related to the structure of the target building component. For example, one or more of the solidity of the target building component, the number of support posts, the average roughness of the edges, post structural features, face structural features, and the like. Solidity refers to the ratio of the volume of a target building element to the volume of the smallest circumsphere (or smallest circumcuboid, etc.) that can encase the target building element. Post structural characteristics refer to characteristics of the posts (e.g., number of posts, average thickness, etc.) in the target building element. The surface structural features refer to the number of vertical surfaces, average thickness, etc. in the target building element.

The component application scenario refers to an application scenario of a target building component.

The component strength requirement refers to the mechanical strength requirement of the target building component, such as tensile property, earthquake resistance and the like.

Component accuracy requirements refer to requirements on the accuracy of the target building component.

In some embodiments, the control system may automatically determine the component strength requirements and the component accuracy requirements based on the component application scenario.

In some embodiments, the control system may determine the print rate and print thickness of the current slice from the vector database based on the characteristic information of the target building element. Specifically, the control system may determine a first target feature vector based on the feature information of the target building element; determining, by the vector database, a first associated feature vector based on the first target feature vector; and determining the printing speed and the printing thickness of the reference slice corresponding to the first associated feature vector as the printing speed and the printing thickness of the current slice.

The vector database contains a plurality of first reference feature vectors, wherein each first reference feature vector has a print rate and print thickness of a corresponding reference slice. The first reference feature vector is a feature vector constructed based on feature information of the historical target building element.

In some embodiments, the control system may determine a first reference feature vector meeting a preset condition in the vector database based on the first target feature vector, and determine the first reference feature vector meeting the preset condition as the first associated feature vector. In some embodiments, the preset conditions may include vector distance minimum, and the like.

In some embodiments, the control system may determine the print rate and print thickness of the current slice based on the determined print rate and print thickness of the reference slice corresponding to the first associated feature vector.

In some embodiments, the control system may also determine the print rate of the current slice based on the characteristic information of the target building element and the environmental characteristic information.

The environmental characteristic information refers to information about the construction environment of the target building element.

In some embodiments, the environmental characteristic information may include an ambient temperature value and an ambient humidity value.

In some embodiments, the control system may determine the print rate and print thickness of the current slice from the vector database based on the characteristic information of the target building element and the environmental characteristic information. Specifically, the control system may determine a second target feature vector based on feature information and environmental feature information of the target building element, where each element in the second target feature vector corresponds to feature information and environmental feature information of one target building element, respectively; determining, by the vector database, a second associated feature vector based on the second target feature vector; and determining the printing speed and the printing thickness of the reference slice corresponding to the second associated feature vector as the printing speed and the printing thickness of the current slice.

The vector database contains a plurality of second reference feature vectors, wherein each second reference feature vector has a print rate and print thickness of a corresponding reference slice. The second reference feature vector is a feature vector constructed based on feature information of the historical target building element and environmental feature information. For a description of how to determine the second associated feature vector based on the second reference feature vector, reference may be made to the description of determining the first associated feature vector previously described.

In some embodiments of the present disclosure, since the temperature value and the humidity value of the construction environment of the target building element affect the solidification rate of the 3D printing material, in determining the printing rate of the current slice, considering the environmental characteristic information, the accuracy of determining the printing rate of the current slice can be improved, so that the situation that the printing rate of the current slice is set too slowly, which causes solidification of the previous layer slice, affects adhesion between two adjacent slices is avoided.

In some embodiments, the environmental characteristic information may also include field flatness.

Site flatness refers to the flatness of a site in the working environment of a 3D printing device. In some embodiments, field flatness may affect the print rate of the current slice. For example, field flatness is positively correlated with the print rate of the current slice.

In some embodiments of the present disclosure, when the field flatness of the working environment of the 3D printing device is too small and the printing speed of the current slice is too fast, the 3D printing may be unstable (such as occurrence of printing dislocation, etc.), so in the process of determining the printing speed of the current slice, the scene flatness is also considered, so as to further improve the accuracy of determining the printing speed of the current slice, and in the process of implementing 3D printing on the target building component, the printing parameters are adjusted in real time according to the real-time printing condition, so as to better perform 3D printing.

In some embodiments, the control system may also process the feature information of the target building element and the positional and structural feature information of the current slice through the print parameter determination model to determine the print rate and print thickness of the current slice. The print parameter determination model is a machine learning model. For more details on this part, see fig. 2 below and its contents.

In some embodiments, the printing parameters may also include the duplicate positioning accuracy of the current slice.

The repeated positioning accuracy refers to the degree of coincidence of the positional accuracy obtained by repeatedly running the same program code on the same 3D printing apparatus. In some embodiments, the higher the repeated positioning accuracy, the more times the positioning, correction that needs to be repeatedly performed when the 3D printing device performs the positioning, correction.

In some embodiments, the control system may determine the duplicate positioning accuracy of the current slice based on the print thickness, print rate, and structural feature information of the current slice, as well as the field flatness.

In some embodiments, the control system may determine the accuracy of the repeated positioning of the current slice from the vector database based on the print thickness, print rate, and structural feature information of the current slice, as well as the field flatness. Specifically, the control system may determine a third target feature vector based on the print thickness, the print rate, the structural feature information, and the field flatness of the current slice, where each element in the third target feature vector corresponds to the print thickness, the print rate, the structural feature information, and the field flatness of one current slice, respectively; determining a third associated feature vector from the vector database based on the third target feature vector; and determining the repeated positioning precision of the reference slice corresponding to the third associated feature vector as the repeated positioning precision of the current slice.

The vector database contains a plurality of third reference feature vectors, wherein each third reference feature vector has a repetitive positioning accuracy of a corresponding reference slice. The third reference feature vector is a feature vector constructed based on the print thickness, print rate, and structural feature information of the history slice. For a description of how to determine the third associated feature vector based on the third reference feature vector, reference may be made to the description of determining the first associated feature vector described above.

In some embodiments of the present disclosure, by determining the repeated positioning accuracy in the printing parameters of the current slice more accurately based on the printing thickness, the printing rate, the structural feature information, and the field flatness of the current slice, the printing parameters are adjusted in real time according to the real-time printing condition in the process of performing 3D printing on the target building member, so as to perform 3D printing better.

In some embodiments, the control parameters may also include feed parameters. The feed parameters may be sent to the feed module by the control system to cause the feed module to feed the print module based on the feed parameters.

The feeding parameters refer to parameters related to feeding of the 3D printing device.

In some embodiments, the feed parameters may include a feed rate.

The feed rate refers to the rate at which raw materials are added during 3D printing.

In some embodiments, the control system may determine the feed rate based on the print job sequence. For more details on this part, see fig. 3 below and the contents thereof.

In some embodiments, the feed parameters may also include agitation parameters. The blending parameter may be sent by the control system to the blending module to cause the blending module to blend the raw components of the target building element based on the blending parameter.

The stirring parameter refers to a parameter used in the process of stirring the raw material components by the 3D printing equipment. For example, the agitation parameters may include one or more of an agitation rate, an agitation start time, an agitation duration, and the like.

In some embodiments, the control system may determine the agitation parameters based on the raw material composition and feed rate used by the target building element.

In some embodiments, the control system may predict the agitation parameters based on the raw material composition and feed rate used by the target building element via a first preset lookup table. In some embodiments, the first predetermined look-up table includes a plurality of different raw material compositions of the reference target building element and a correspondence of feed rates to reference agitation parameters. In some embodiments, the first preset lookup table may be constructed based on a priori knowledge or historical data.

In some embodiments of the present disclosure, the target building component obtained by 3D printing is capable of meeting component strength requirements and component accuracy requirements through the determined agitation parameters of the raw material components and feed rates used by the target building component.

In some embodiments, the agitation parameter may also be related to the feed rate over a future preset period of time. In some embodiments, the agitation rate and the agitation start time in the agitation parameter may be positively correlated with the feed rate over a future preset time period, and the agitation duration in the agitation parameter may be negatively correlated with the feed rate over the future preset time period. For example, the faster the feed rate, the earlier the stirring start time can be set.

In some embodiments of the present disclosure, by relating the agitation parameter to the feed rate in a future preset time period, the agitation is advanced according to the feed rate in the future preset time period, so as to prevent the occurrence of a slow 3D printing rhythm caused by the fact that the feed is not completed yet when the feed demand is suddenly generated.

In some embodiments, the agitation parameters may also be related to the strength requirements of the target building component and the accuracy of the repeated positioning. For a description of the accuracy of the repeated positioning, please refer to the above description.

The strength requirement refers to the mechanical strength requirement of the target building element, such as tensile property, earthquake resistance and the like.

In some embodiments, the control system may determine the agitation parameters based on the strength requirements of the target building element and the repeated positioning accuracy via a second preset lookup table. In some embodiments, the second preset lookup table includes a plurality of different strength requirements of the reference target building element and correspondence between the repeated positioning accuracy and the reference stirring parameter. In some embodiments, the second preset lookup table may be constructed based on a priori knowledge or historical data. For example, under the condition of a certain stirring parameter, the strength requirement of the finally printed 3D model is good, and the repeated positioning accuracy is good, so that the stirring parameter can be used as the stirring parameter for printing a certain 3D model.

In some embodiments of the present disclosure, by determining the agitation parameters according to the strength requirement and the repeated positioning accuracy of the target building member, the agitation parameters are adjusted in real time according to the real-time printing condition during the 3D printing of the target building member, so as to better perform the 3D printing.

In some embodiments, the control parameters may also include pumping parameters.

The pumping parameters refer to parameters related to the screw extrusion pumping of the feedstock. In some embodiments, the pumping parameters may include one or more of pumping flow rate, pumping frequency, pumping pressure, and the like.

In some embodiments, the pumping parameter may be the discharge rate of the pumping module.

In some embodiments, the control system may determine the pumping parameters based on the print rate and print thickness of the current slice.

In some embodiments, the control system may predict the pumping parameters based on the printing rate and printing thickness of the current slice through a third preset lookup table. In some embodiments, the third preset lookup table includes a plurality of different print rates and print thicknesses of the reference slices in correspondence with the reference pumping parameters. In some embodiments, the third preset lookup table may be constructed based on a priori knowledge or historical data.

In some embodiments of the present disclosure, by determining the pumping parameters according to the printing rate and the printing thickness of the current slice, the pumping parameters are adjusted in real time according to the real-time printing condition in the process of performing 3D printing on the target building component, so as to perform 3D printing better.

It should be noted that the above description of the 3D printing apparatus and the modules thereof is for convenience of description only, and is not intended to limit the present description to the scope of the illustrated embodiments. It will be appreciated by those skilled in the art that, given the principles of the system, various modules may be combined arbitrarily or a subsystem may be constructed in connection with other modules without departing from such principles. In some embodiments, the printing module, the feeding module, and the wireless remote control module disclosed in fig. 1 may be different modules in one system, or may be one module to implement the functions of two or more modules described above. For example, each module may share one memory module, or each module may have a respective memory module. Such variations are within the scope of the present description.

FIG. 2 is an exemplary flow chart of determining the print rate and print thickness of a current slice, according to some embodiments of the present description. In some embodiments, the process 200 may be performed by a control system of a 3D printing device.

In some embodiments, the control system may determine the print rate 270 and print thickness 280 of the current slice by processing the feature information 210-1 of the target building element and the positional feature information 220-2 and structural feature information 220-3 of the current slice by the print parameter determination model 200.

The positional characteristic information of the current slice may refer to the number of layers in which the current slice is located in the target building element. For example, if the target building element is divided into 1000 slices, if the current slice is 3 rd layer, the position feature information of the current slice may be 3.

The structural feature information of the current slice refers to feature information related to the structure of the current slice.

For a description of the characteristic information of the target building element, please refer to the relevant contents in fig. 1.

In some embodiments, the print parameter determination model may be a machine learning model. In some embodiments, the print parameter determination model may include a Neural network model (NN), a deep Neural network (Deep Neural Networks, DNN), or the like.

In some embodiments, the input to the print parameter determination model 200 may also include a feature sequence 220-4 of the printed slice.

A feature sequence of a printed slice may refer to a set of features that are linearly arranged together by features that correspond to each of a plurality of printed slices.

In some embodiments, the feature sequence of the printed slice may include a print parameter sequence of the printed slice. The printing parameter sequence refers to a group of printing parameters which are respectively corresponding to a plurality of printed slices and are linearly arranged together.

In some embodiments of the present specification, since the feature sequence of the printed slice may reflect the setting condition of the printing parameters of the printed slice, by considering the feature sequence of the printed slice as a reference in the input of the printing parameter determination model, the accuracy of the printing parameter determination model to predict the printing parameters of the current slice may be improved.

In some embodiments, the print parameter determination model may be trained based on a plurality of first training samples with first labels.

In some embodiments, the first training sample of the print parameter determination model may be obtained based on historical data. The first training label may be obtained based on an actual printing rate and an actual printing thickness of a historical sample slice in the historical data corresponding to the input data, or based on a manual annotation.

In some embodiments, a first training sample with a first label may be input into the initial printing parameter determination model, a loss function is constructed according to the first label and a prediction result of the initial printing parameter determination model, parameters of the model are iteratively updated based on the loss function until the loss function converges, the number of iterations reaches a threshold value, and the like, training is completed, and a trained printing parameter determination model is obtained.

In some embodiments of the present disclosure, since the feature information of the target building element and the slices of different positions and structures affect the determination of the printing parameters of the final target building element, the feature information of the target building element and the position feature information and the structure feature information of the current slice are considered in the input of the printing parameter determination model, so that the printing parameters can be quickly and accurately determined, and better used for 3D printing of the target building element.

In some embodiments, the print parameter determination model 200 may include an embedded processing layer 210, an evaluation determination layer 220, an influence determination layer 230, and a print rate determination layer 260. In some embodiments, the evaluation determination layer 220, the influence determination layer 230, and the print rate determination layer 260 may each be a neural network model NN, a deep neural network model DNN, or the like, or any combination thereof.

In some embodiments, the embedded treatment layer 210 may be used to process the characteristic information 210-1 of the target building component to determine at least one candidate print thickness 220-1.

In some embodiments, the inline processing layer 210 may include an inline vector database and a candidate print thickness generation layer. Specifically, the control system may determine a safe layer thickness range based on the embedded vector database; at least one candidate print thickness is then generated by the candidate print thickness generation layer based on the secure layer thickness range.

The safe layer thickness range refers to the safe thickness range of the current slice for 3D printing.

In some embodiments, the control system may determine the safe layer thickness range from the characteristic information of the target building element via an embedded vector database. Specifically, the control system may determine a fourth target feature vector based on the feature information of the target building element; determining a fourth associated feature vector from the embedded vector database based on the fourth target feature vector; and determining the reference safe layer thickness range corresponding to the fourth association characteristic vector as the safe layer thickness range.

The embedded vector database comprises a plurality of fourth reference feature vectors, wherein each fourth reference feature vector has a corresponding reference security layer thickness range. The fourth reference feature vector is a feature vector constructed based on the feature information of the historical target building element. For a description of how the fourth associated feature vector is determined based on the fourth reference feature vector, reference may be made to the description of determining the first associated feature vector described above.

The candidate print thickness generation layer may be configured to generate at least one candidate print thickness based on the secure layer thickness range. The candidate print thickness refers to the print thickness of the current slice to be selected.

In some embodiments, the candidate print thickness generation layer may generate at least one candidate print thickness generation layer by a preset algorithm based on the secure layer thickness range. The preset algorithm may be any feasible algorithm. For example, the preset algorithm may be to generate at least one candidate print thickness at a preset thickness spacing based on a safe layer thickness range.

In some embodiments, the evaluation determination layer 220 may be configured to process the at least one candidate print thickness 220-1 and the positional feature information 220-2 and the structural feature information 220-3 of the current slice to determine an evaluation value 240 for each of the at least one candidate print thickness.

The evaluation value of the candidate print thickness refers to an evaluation value of whether or not the current slice satisfies the member strength requirement and the member accuracy requirement when the current slice is printed based on the candidate print thickness.

In some embodiments, the greater the evaluation value of the candidate print thickness, the greater the probability that the candidate print thickness meets the component strength requirements and the component accuracy requirements.

In some embodiments, to make the overall 3D printing time faster and more efficient, the thicker the printed thickness of the slice may be, the better the component strength requirements and component accuracy requirements are met.

In some embodiments, the evaluation determination layer may be trained based on a plurality of second training samples with second labels.

In some embodiments, the second training sample of the evaluation determination layer may include at least one historical sample candidate print thickness and location feature information and structural feature information of the historical sample slice, and the second label may include an evaluation value of the at least one historical sample candidate print thickness.

In some embodiments, at least one historical sample candidate print thickness may be obtained by the embedded treatment layer based on characteristic information of the historical sample target building component.

In some embodiments, the second label may be obtained by manual labeling, and the specific labeling method is as follows: the method can be used for carrying out pre-modeling through a preset method (such as physical software simulation and the like) based on the characteristic information of the target building component, obtaining the slices of different positions and structures in the modeling, and obtaining the evaluation value of each slice based on the performance of the slice in terms of strength and precision when printing is carried out by using a certain candidate printing thickness.

In some embodiments, the influence determination layer 230 may be configured to process the position characteristic information 220-2 and the structural characteristic information 220-3 of the current slice to determine the strength influence value 250 of the current slice on the target building element.

The strength influence value refers to an influence value of the cut piece on the strength of the target building element. In some embodiments, the strength impact values of the slices of different locations and structures in the target building element on the target building element may be different. For example, the initial print swatch of the target building element may have a greater value of impact on the strength of the target building element. For another example, some structurally complex slices in the middle of the target building element may have a greater impact on the strength of the target building element.

In some embodiments, the influence determination layer may be trained based on a number of third training samples with third labels.

In some embodiments, the third training sample of the influence determination layer may include location feature information and structural feature information of the historical sample slice, and the third tag may include an intensity influence value of the historical sample slice on the target building component.

In some embodiments, the third training sample may be obtained from historical data.

In some embodiments, the third tag may be obtained by manual labeling, and a specific labeling method is as follows: the method can be used for carrying out pre-modeling through a preset method (such as physical software simulation and the like) based on the characteristic information of the target building component, so as to obtain slices of different positions and structures in the modeling, and the strength influence value of the target building component is obtained.

In some embodiments, the print thickness of the current slice may be determined based on an evaluation value of each of the at least one candidate print thickness and a strength impact value of the current slice on the target building component. For example, when the strength influence value of the current cut piece on the target building member is equal to or greater than a preset threshold value, the candidate print thickness having the optimal evaluation value is selected as the print thickness of the current cut piece. For another example, when the strength influence value of the current slice on the target building member is smaller than the preset threshold value, the printing thickness of the current slice with the largest thickness is selected as the candidate printing thickness in the evaluation value which is better than the preset threshold value. The preset threshold may be empirically preset by one skilled in the art.

In some embodiments, the print rate determination layer 260 may be configured to process the feature information 210-1 of the target building component and the print thickness 280, location feature information 220-2, and structural feature information 220-3 of the current slice to determine the print rate 270 of the current slice.

In some embodiments, the print rate determination layer may be trained based on a number of fourth training samples with fourth labels.

In some embodiments, the fourth training sample of the print rate determination layer may include characteristic information of the historical target building element, positional characteristic information and structural characteristic information of the historical sample slice, a print thickness of the historical sample slice, and the fourth label may include a print rate of the historical sample slice.

In some embodiments, the fourth training sample may be obtained from historical data.

In some embodiments, the fourth tag may be obtained by adopting an inverse solution, and a specific obtaining method is as follows: the optimal printing rate may be determined from the plurality of candidate printing rates according to an evaluation value of the candidate printing thickness corresponding to each of the plurality of candidate printing rates.

In some embodiments, the input to one or more of the print rate determination layer, the assessment determination layer, and the influence determination layer may further include a sequence of features of the printed slice.

In some embodiments, the training samples of one or more of the print rate determination layer, the assessment determination layer, and the influence determination layer may further include a feature sequence of the historical sample printed slice.

In some embodiments, the print parameter determination model may be based on a number of fifth training samples with fifth labels, and derived by joint training of the assessment determination layer, the influence determination layer, and the print rate determination layer.

In some embodiments, each set of fifth training samples may include characteristic information of the historical sample target building element, positional characteristic information of the historical sample slice, and structural characteristic information. The fifth label may be the print rate and print thickness of the historical sample slice. In some embodiments, the fifth tag may be obtained by historical data acquisition or manual annotation.

In some embodiments, the characteristic information of the historical sample target building member in the fifth training sample with the fifth label may be input into the embedded processing layer, then at least one historical sample candidate print thickness, the position characteristic information and the structural characteristic information of the historical sample slice output by the embedded processing layer are input into the initial evaluation determining layer, meanwhile, the position characteristic information and the structural characteristic information of the historical sample slice are input into the initial influence degree determining layer, then the evaluation value of each historical sample candidate print thickness in the at least one historical sample candidate print thickness output by the initial evaluation determining layer and the strength influence value of the historical sample slice output by the influence degree determining layer on the historical sample target building member are input into the initial print rate determining layer, the determined print thickness of the historical sample slice and the characteristic information of the historical sample target building member are input into the initial print rate determining layer, the parameters of the initial evaluation determining layer, the initial influence degree determining layer and the initial print rate determining layer are iteratively updated based on the loss function until the loss function converges, the number of iterations reaches a threshold value and the like, and the training is finished, so that the trained parameters are determined.

In some embodiments, each set of fifth training samples may further comprise a feature sequence of the printed slices of the history samples. The feature sequence of the historical sample printed slice may be input to one or more of an initial print rate determination layer, an initial evaluation determination layer, and an initial impact level determination layer.

In some embodiments of the present disclosure, in the prediction process of the print parameter determination model, feature information of a target building component, position feature information and structural feature information of a current slice are considered, so that in a complex construction environment (for example, printing a large building component), according to a printing condition and a field condition, a printing rate and a printing thickness of the current slice are accurately determined, 3D printing of the target building component is performed, and construction printing efficiency is improved. In addition, in the model training process, a reverse solution method is adopted in the training process of the printing rate determining layer to obtain training labels, so that the defect that enough training labels cannot be obtained due to forward training is avoided.

FIG. 3 is an exemplary flow chart of determining a feed rate over a future preset time period according to some embodiments of the present description. In some embodiments, the process 300 may be performed by a control system of a 3D printing device. As shown in fig. 3, the flow 300 may include steps 310-320 as follows.

Step 310, predicting the material characteristic information in the future preset time period according to the current print task and at least one print task behind the current print task in the print task sequence.

The print job refers to printing the current slice at a preset print rate. The preset printing rate may be the printing rate of the current slice determined by the printing parameter determination model.

The print job sequence is a slice sequence obtained by uniformly slicing the target building member according to a preset slice thickness. In some embodiments, the printing of each slice may be a print job. Each print job may contain a print rate (preset value) for that print job (slice).

The material characteristic information refers to characteristic information related to the material used in the 3D printing process of the target building element. For example, the material usage characteristic information may include material usage speed, material usage temperature, and the like.

In some embodiments, the control system may determine the material characteristic information for a future preset time period based on the print job sequence via a fourth preset lookup table. In some embodiments, the fourth preset lookup table includes correspondence between a plurality of different reference print job sequences and the usage feature information within a reference preset time period. In some embodiments, the fourth predetermined look-up table may be constructed based on a priori knowledge or historical data.

In some embodiments, the control system may predict the material characteristic information within a future preset time period by processing the remaining print amount of the current slice, the print parameters of the current slice, and the print parameters of the subsequent slice in the print job sequence through the material prediction model. The material prediction model is a machine learning model. For more details on this part, see fig. 4 below and its contents.

Step 320, determining a feed rate for a future preset time period based on the material characteristic information.

The future preset time period refers to a preset time period from the current time period to the future. The future preset time period may be empirically set by those skilled in the art.

In some embodiments, the control system may determine the feed rate for the future preset time period based on the material information for the future preset time period via a fifth preset lookup table. In some embodiments, the fifth preset lookup table includes correspondence between the material information in the plurality of different reference preset time periods and the feed rate in the reference future preset time period. In some embodiments, the fifth preset lookup table may be constructed based on a priori knowledge or historical data.

In some embodiments of the present disclosure, by printing a sequence of tasks, it is possible to accurately predict the feed rate for a future time period, and then stir in advance according to the predicted feed rate for the future time period, so as to prevent slow 3D printing cadence caused by the fact that when a feed demand is suddenly generated, the feed has not been stirred.

It should be noted that the above description of the process 300 is for purposes of example and illustration only and is not intended to limit the scope of applicability of the present disclosure. Various modifications and changes to flow 300 will be apparent to those skilled in the art in light of the present description. However, such modifications and variations are still within the scope of the present description.

In some embodiments, the materials prediction model 400 may predict the materials characteristic information 420 over a future preset period of time based on processing the remaining print amount 410-1 of the current slice, the print parameters 410-2 of the current slice, and the print parameters 410-3 of the subsequent slice in the sequence of print tasks. The material prediction model may be a machine learning model. In some embodiments, the materials prediction model may include a neural network model NN, a deep neural network DNN, or the like.

The remaining print amount of the current slice refers to the remaining print amount of the portion of the current slice that has not yet been printed.

The print parameters of the subsequent slices refer to print parameters corresponding to the slices located after the current slice in the print job sequence.

For a description of the material characteristic information within the future preset time period, please refer to the description in step 310 of fig. 3.

In some embodiments, the control system may process the feature sequence of the printed cut sheet, the feature information of the target building element, the position feature information and the structural feature information of the subsequent cut sheet by the print parameter determination model 200, and predict the print parameters 410-3 of the subsequent cut sheet. The print parameter determination model may be a machine learning model.

For a description of the feature sequence of the printed cut sheet and the feature information of the target building element, please refer to the relevant description above in fig. 2.

The position feature information of the subsequent slice refers to feature information related to the position of a slice located after the current slice in the print job sequence.

The structural feature information of the subsequent slice refers to structural-related feature information of a slice located after the current slice in the print job sequence.

For more specific details of the print parameter determination model, please refer to fig. 3 and its contents above.

In some embodiments of the present description, the accuracy of the print parameter determination model in predicting print parameters of a subsequent print job is further improved by considering the feature sequence of the printed cut, the feature information of the target building element, the position feature information and the structural feature information of the subsequent cut in the input of the print parameter determination model.

In some embodiments, the materials prediction model 400 may be trained based on a number of sixth training samples with sixth labels.

In some embodiments, a sixth training sample of the stock prediction model may be obtained based on historical data. The sixth training label can be obtained based on the material characteristic information in the known preset time period of the historical sample corresponding to the input data in the historical data or based on manual labeling.

In some embodiments, a sixth training sample with a sixth label may be input into the initial material prediction model, a loss function is constructed according to the prediction results of the sixth label and the initial material prediction model, parameters of the model are updated based on the loss function iteration until the loss function converges, the number of iterations reaches a threshold value, and the training is completed, and a trained material prediction model is obtained.

In some embodiments of the present disclosure, the feed rate for a future time period is determined by quickly and accurately determining the material characteristic information within the future preset time period by considering the remaining print amount of the current slice, the print parameters of the current slice, and the print parameters of the subsequent slice in the input of the material prediction model, which is better for 3D printing of the target building member.

One of one or more embodiments of the present description provides a 3D printing method. The method is implemented by the control system 130-2 of the 3D printing device 100. The 3D printing apparatus may include a printing module, a mobile base, a wireless remote control module, and a feeding module. The feed module may include an automatic feed module, a stirring module, and a pumping module. The wireless remote control module may include an interactive module and a control system. The control system is respectively in communication connection with the interaction module, the printing module, the movable base and the feeding module. The method may include, during 3D printing of the target building component, in response to satisfaction of a preset condition: control parameters are determined and sent to at least one of the printing module, the mobile base, and the feed module.

In some embodiments, the control parameters may include printing parameters. The printing parameters are sent to the printing module by the control system so that the printing module performs 3D printing based on the printing parameters. The printing parameters may include at least one of a printing rate and a printing thickness of the current slice. The control system determining the printing parameters may include: and determining the printing speed and the printing thickness of the current slice according to the characteristic information of the target building component. For a more detailed description of this section, please refer to the control system section of fig. 1.

In some embodiments, the control parameters further comprise feed parameters. The feed parameters are sent by the control system to the feed module to cause the feed module to feed the print module based on the feed parameters. The feed parameters may include a feed rate. The control system determining the feed rate may include: the feed rate is determined based on the print job sequence. For a more detailed description of this section, please refer to the control system section description of FIG. 1 and the description of FIG. 2.

In some embodiments, the control system may further predict the usage characteristic information for a future preset time period based on the current print job and at least one print job subsequent to the current print job in the sequence of print jobs, and determine the feed rate for the future preset time period based on the usage characteristic information. For a more detailed description of this part, please refer to the description in fig. 3 and 4.

In some embodiments of the present disclosure, various control parameters in the process of 3D printing on a target building component are timely adjusted according to the printing condition and the site condition, so as to improve the construction printing efficiency.

While the basic concepts have been described above, it will be apparent to those skilled in the art that the foregoing detailed disclosure is by way of example only and is not intended to be limiting. Although not explicitly described herein, various modifications, improvements, and adaptations to the present disclosure may occur to one skilled in the art. Such modifications, improvements, and modifications are intended to be suggested within this specification, and therefore, such modifications, improvements, and modifications are intended to be included within the spirit and scope of the exemplary embodiments of the present invention.

Meanwhile, the specification uses specific words to describe the embodiments of the specification. Reference to "one embodiment," "an embodiment," and/or "some embodiments" means that a particular feature, structure, or characteristic is associated with at least one embodiment of the present description. Thus, it should be emphasized and should be appreciated that two or more references to "an embodiment" or "one embodiment" or "an alternative embodiment" in various positions in this specification are not necessarily referring to the same embodiment. Furthermore, certain features, structures, or characteristics of one or more embodiments of the present description may be combined as suitable.

Furthermore, the order in which the elements and sequences are processed, the use of numerical letters, or other designations in the description are not intended to limit the order in which the processes and methods of the description are performed unless explicitly recited in the claims. While certain presently useful inventive embodiments have been discussed in the foregoing disclosure, by way of various examples, it is to be understood that such details are merely illustrative and that the appended claims are not limited to the disclosed embodiments, but, on the contrary, are intended to cover all modifications and equivalent arrangements included within the spirit and scope of the embodiments of the present disclosure. For example, while the system components described above may be implemented by hardware devices, they may also be implemented solely by software solutions, such as installing the described system on an existing server or mobile device.

Likewise, it should be noted that in order to simplify the presentation disclosed in this specification and thereby aid in understanding one or more inventive embodiments, various features are sometimes grouped together in a single embodiment, figure, or description thereof. This method of disclosure, however, is not intended to imply that more features than are presented in the claims are required for the present description. Indeed, less than all of the features of a single embodiment disclosed above.

In some embodiments, numbers describing the components, number of attributes are used, it being understood that such numbers being used in the description of embodiments are modified in some examples by the modifier "about," approximately, "or" substantially. Unless otherwise indicated, "about," "approximately," or "substantially" indicate that the number allows for a 20% variation. Accordingly, in some embodiments, numerical parameters set forth in the specification and claims are approximations that may vary depending upon the desired properties sought to be obtained by the individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and employ a method for preserving the general number of digits. Although the numerical ranges and parameters set forth herein are approximations that may be employed in some embodiments to confirm the breadth of the range, in particular embodiments, the setting of such numerical values is as precise as possible.

Each patent, patent application publication, and other material, such as articles, books, specifications, publications, documents, etc., referred to in this specification is incorporated herein by reference in its entirety. Except for application history documents that are inconsistent or conflicting with the content of this specification, documents that are currently or later attached to this specification in which the broadest scope of the claims to this specification is limited are also. It is noted that, if the description, definition, and/or use of a term in an attached material in this specification does not conform to or conflict with what is described in this specification, the description, definition, and/or use of the term in this specification controls.

Finally, it should be understood that the embodiments described in this specification are merely illustrative of the principles of the embodiments of this specification. Other variations are possible within the scope of this description. Thus, by way of example, and not limitation, alternative configurations of embodiments of the present specification may be considered as consistent with the teachings of the present specification. Accordingly, the embodiments of the present specification are not limited to only the embodiments explicitly described and depicted in the present specification.

Claims

1. A 3D printing apparatus, comprising: the device comprises a printing module, a movable base, a wireless remote control module and a feeding module;

the feeding module comprises an automatic feeding module, a stirring module and a pumping module;

the wireless remote control module comprises an interaction module and a control system;

the control system is respectively in communication connection with the interaction module, the printing module, the movable base and the feeding module, and is used for:

in 3D printing of the target building component, in response to satisfaction of a preset condition:

determining a control parameter and sending the control parameter to at least one of the printing module, the mobile base and the feeding module, wherein the control parameter at least comprises a movement parameter, the movement parameter at least comprises a movement speed, and the movement parameter is at least used for enabling the mobile base to move at the movement speed.

2. The 3D printing device of claim 1, wherein the control parameters further comprise printing parameters, the printing parameters being sent by the control system to the printing module to cause the printing module to perform 3D printing based on the printing parameters;

wherein the printing parameters comprise at least one of a printing rate and a printing thickness of the current slice;

the control system is further configured to:

and determining the printing speed and the printing thickness of the current slice according to the characteristic information of the target building component.

3. The 3D printing apparatus of claim 1, wherein the control parameters further comprise a feed parameter that is sent by the control system to the feed module to cause the feed module to feed the printing module based on the feed parameter;

wherein the feed parameters include a feed rate;

the control system is further configured to:

the feed rate is determined based on a print job sequence.

4. A printing device according to claim 3, wherein the control system is further configured to:

predicting material characteristic information in a future preset time period according to a current printing task and at least one printing task behind the current printing task in the printing task sequence; and

And determining the feeding rate in the future preset time period based on the material characteristic information.

5. A 3D printing method, characterized in that the method is implemented by a control system of a 3D printing apparatus; the 3D printing apparatus includes: the device comprises a printing module, a movable base, a wireless remote control module and a feeding module;

the feeding module comprises an automatic feeding module, a stirring module and a pumping module; the wireless remote control module comprises an interaction module and the control system;

the control system is respectively in communication connection with the interaction module, the printing module, the movable base and the feeding module;

the method comprises the following steps:

6. The method of claim 5, wherein the control parameters further comprise print parameters that are sent by the control system to the print module to cause the print module to perform 3D printing based on the print parameters;

Wherein the printing parameters include at least one of a printing rate and a printing thickness of the current slice, and determining the printing parameters includes:

7. The method of claim 5, wherein the control parameters further comprise feed parameters that are sent by the control system to the feed module to cause the feed module to feed the print module based on the feed parameters;

wherein the feed parameters include a feed rate; determining the feed rate includes:

the feed rate is determined based on a print job sequence.

8. The method of claim 7, wherein determining the feed rate from a print job sequence comprises:

9. A 3D printing apparatus, the apparatus comprising at least one processor and at least one memory;

the at least one memory is configured to store computer instructions;

the at least one processor is configured to execute at least some of the computer instructions to implement the 3D printing method of any of claims 5-8.

10. A computer readable storage medium storing computer instructions which, when read by a computer in the storage medium, perform the 3D printing method according to any one of claims 5 to 8.