Mould forming Lingnan grey sculpture embossment construction method based on AI generative design
Through the mold forming method based on AI-generated design, the problem of lack of drawing guidance and relying on craftsmen's experience in gray plastic relief construction is solved, and efficient, safe and personalized gray plastic relief construction is achieved, reducing labor costs.
Patent Information
- Application Number
- CN202510175290.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-02-18
- Publication Date
- 2025-03-18
AI Technical Summary
In the prior art, gray plastic relief construction lacks construction drawing guidance, relies too much on the experience of craftsmen, and is difficult to meet the personalized needs of users. The construction efficiency is low, the safety is insufficient, and the labor cost is high.
The mold forming method based on AI generative design is adopted, and through model training, material performance testing and 3D printing technology, gray plastic relief design that meets user needs is generated, molds are manufactured and constructed, reducing dependence on craftsmen's experience.
It improves the design efficiency of gray plastic relief construction and restoration work, meets users' personalized needs, improves the safety of components, saves labor costs, and reduces construction difficulty.
Smart Images

Figure CN119636290A_ABST
Abstract
Description
Technical Field
[0001] The invention relates to the technical field of building decoration construction, and in particular to a method for constructing a Lingnan gray sculpture relief by mold forming based on AI generative design. Background Art
[0002] Gray plastic relief is a kind of architectural decoration component and ornament in Lingnan area, and is widely used as traditional architectural decoration in Lingnan new-style residential buildings, ancestral hall renovation and other projects. In the prior art, the Chinese invention patent application with publication number CN114635527A discloses a kind of antique building ridge structure and its construction method, and proposes a construction method of antique building structure including ridge and gray plastic structure. However, the gray plastic structure in this construction method still needs to be constructed manually layer by layer. The Chinese invention patent application with publication number CN117021336A discloses a method for making a kind of gray plastic prefabricated component of Lingnan cultural relics and ancient buildings, and proposes gray plastic construction in the form of a base combined with prefabricated components. However, this construction method does not solve the problem that the traditional gray plastic construction method lacks construction drawing guidance and relies too much on the experience of craftsmen during the construction and design process.
[0003] Therefore, for new plaster reliefs, there is a lack of a construction method that can better meet the personalized needs of users, improve the safety of plaster components, improve construction efficiency and save labor costs. Summary of the invention
[0004] The purpose of the present invention is to provide a mold-forming Lingnan gray plastic relief construction method based on AI generative design, which improves the design efficiency of traditional gray plastic relief construction and restoration work, better meets the personalized needs of users, improves the safety of gray plastic components, saves labor costs and reduces dependence on craftsmen's experience.
[0005] To achieve the above object, the present invention provides a method for constructing a Lingnan gray sculpture relief by mold forming based on AI generative design, comprising the following steps: S1. Prepare paper-reinforced ash test blocks and straw-reinforced ash test blocks, and test material parameters; S2, model training: obtain a flat gray sculpture relief image, match the prompt words, set model training parameters for training and select a model; S3, gray plastic relief design and adjustment: The gray plastic relief pattern is generated using the model obtained in S2 and converted into a 3D gray plastic relief model. The stress analysis is performed based on the material parameters obtained in S1 to ensure that the normal use load is met. S4, mold manufacturing: designing a mold according to the 3D gray plastic relief model obtained in S3, and obtaining a 3D printed mold using a 3D printer; S5, on-site construction: fill the 3D printed mold obtained in S4 with straw ash and fix it to the wall. After hardening and demoulding, apply paper ash and color it.
[0006] Preferably, S1 is specifically: S11, preparing straw tendon ash and paper tendon ash, and setting aside for later use; S12, casting test blocks: filling paper reinforced ash into compression test block molds and flexural test block molds, respectively, filling straw reinforced ash into compression test block molds and flexural test block molds, respectively, vibrating and tamping evenly, to obtain a number of paper reinforced ash test blocks and straw reinforced ash test blocks; S13, test block curing: place the paper reinforced ash test block and the straw reinforced ash test block obtained in S12 in a ventilated and water-proof place for curing, and demould and store for 90 days after hardening; S14. Mechanical property test: Perform mechanical test on the paper-reinforced ash test blocks and straw-reinforced ash test blocks obtained in S13, and calculate the material parameters.
[0007] Preferably, in S1, the material parameters include compressive strength, flexural strength, elastic modulus and Poisson's ratio.
[0008] Preferably, S2 is specifically: S21. Material collection: obtain pictures of flat gray plastic reliefs and organize and classify them; S22, image preprocessing: adjust the image obtained in S21 to a uniform resolution, assign prompt words through BLIP or deepboru, check whether the prompt words are consistent with the subject matter, adjust the prompt words and save; S23, model training: determine the batch size, learning rate, and training parameters of the optimization algorithm, perform Lora model training, and obtain models with different training steps; S24, model selection: using the model obtained in S23 to generate a corresponding plaster relief pattern, and selecting a model whose image style matching and clarity of the plaster relief pattern meet the design requirements.
[0009] Preferably, S3 is specifically: S31, image acquisition: using the model obtained in S2, generating a number of gray sculpture relief patterns according to the prompt words; S32, design selection: select the gray plastic relief pattern obtained in S31 according to the design requirements to obtain a 2D plastic pattern; S33, model conversion: giving height to the 2D plastic pattern obtained in S32, converting it into a 3D gray plastic relief model, and designing a corresponding skeleton; S34, mechanical analysis: using the material parameters obtained in S1 and the 3D gray plastic relief model obtained in S33 as the object, perform self-weight and wind load force analysis to obtain stress and displacement distribution; S35, judging whether the normal use load is met, if not, proceeding to S36; S36. Model modification: Adjust the local height of the 3D gray plastic relief model.
[0010] Preferably, S4 is specifically: S41. Mold design: Modeling software is used to model the model according to the actual construction size to obtain the mold of the 3D gray plastic relief model. The mold is split as a whole and bolt holes are set according to the construction size of the 3D printer, and then saved as a printable model file; S42, determining printing parameters: importing the model file obtained in S41 into the slicing software, determining parameters, including printing consumables, layer height, printing speed and printing temperature, and generating the printing file required for printing; S43, mold 3D printing: using the print file obtained in S42 to perform 3D printing on a 3D printer to manufacture various parts of the mold; S44, mold post-processing: remove the support, polish the mold surface evenly, and obtain a 3D printed mold.
[0011] Preferably, S5 is specifically: S51. Wall surface treatment: Grind the wall surface to be constructed flat, apply primer after hanging the mesh, and drill expansion bolt holes at the designed hole positions; S52, Frame binding: Pre-embed steel nails on the wall to be constructed according to the designed frame, and bind the frame with copper wire; S53, grass reinforcement ash pouring: using the 3D printed mold obtained in S4 to pour the grass reinforcement ash, and vibrating and compacting it; S54, mold installation: install the mold with cast grass reinforcement ash as a whole on the wall to be constructed; S55, demoulding: after the grass tendon ash hardens, the mold is removed and compacted to obtain the grass tendon ash matrix; S56, applying paper tendon ash surface layer: applying paper tendon ash on the straw tendon ash base to obtain an uncolored ash sculpture relief; S57, modifying and coloring: applying color gray on the surface of the uncolored gray sculpture relief, and coloring with pigment after the surface of the gray sculpture relief is hardened and dried, so as to obtain a completed gray sculpture relief; S58. Maintenance: The completed gray plastic relief should be maintained in natural conditions away from water.
[0012] Therefore, the present invention adopts the above-mentioned mold forming Lingnan gray plastic relief construction method based on AI generative design, and the beneficial effects are as follows: (1) In view of the problem that the design of gray plastic relief structure is highly dependent on experience and the current situation that the learning cost of gray plastic relief design is high and there is a lack of inheritance, the present invention introduces AI generative design to reduce the acquisition cost of gray plastic modeling. The gray plastic relief design is generated with the help of a pre-trained model to better meet the personalized needs of users and reduce the rework phenomenon in actual construction. It is conducive to promoting the digitization and intelligence of gray plastic relief design, saving labor costs, and reducing dependence on the experience of craftsmen.
[0013] (2) The present invention conducts mechanical analysis and optimization of the plaster relief structure through material performance testing, thereby ensuring the rationality and safety of the plaster relief construction and improving the safety of the plaster relief components.
[0014] (3) The present invention utilizes 3D printing technology to manufacture molds and perform construction, which reduces the construction difficulty of plaster molding, improves the design efficiency of traditional plaster relief construction and restoration work, further saves labor costs, and provides a new solution for the construction of plaster structures.
[0015] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS
[0016] Figure 1 It is an overall flow chart of an embodiment of a method for constructing a Lingnan gray sculpture relief by mold forming based on AI generative design of the present invention; Figure 2 It is a flow chart S1 of an embodiment of a method for constructing a Lingnan gray sculpture relief by mold forming based on AI generative design of the present invention; Figure 3 It is a flow chart S2 of an embodiment of a method for constructing a Lingnan gray sculpture relief by mold forming based on AI generative design of the present invention; Figure 4 It is a flow chart S3 of an embodiment of a method for constructing a Lingnan gray sculpture relief by mold forming based on AI generative design of the present invention; Figure 5 It is a flow chart S4 of an embodiment of a method for constructing a Lingnan gray sculpture relief by mold forming based on AI generative design of the present invention; Figure 6 It is a flow chart S5 of an embodiment of a method for constructing a Lingnan gray sculpture relief by mold forming based on AI generative design of the present invention; Figure 7 It is a structural front view of a 3D printing mold of a second embodiment of a method for constructing a Lingnan gray plastic relief by a mold forming method based on AI generative design of the present invention; Figure 8 It is a structural side view of a 3D printing mold of a second embodiment of a method for constructing a Lingnan gray plastic relief by a mold forming method based on AI generative design of the present invention; Fig. 9 It is a schematic diagram of the inner surface of a 3D printing mold of a second embodiment of a method for constructing a Lingnan gray plastic relief by a mold forming method based on AI generative design of the present invention; Fig.10 It is a schematic diagram of the first module unit of Embodiment 2 of a method for constructing a Lingnan gray plastic relief by mold forming based on AI generative design of the present invention; Fig.11 It is a schematic diagram of the second module unit of the second embodiment of the method for constructing Lingnan gray plastic relief by mold forming based on AI generative design of the present invention; Fig.12 It is a schematic diagram of the third module unit of the second embodiment of the method for constructing Lingnan gray plastic relief by mold forming based on AI generative design of the present invention; Fig.13 It is a schematic diagram of the fourth module unit of Embodiment 2 of a method for constructing Lingnan gray plastic relief by mold forming based on AI generative design of the present invention; Fig.14 It is a cross-sectional schematic diagram of on-site construction of Example 2 of a Lingnan gray plastic relief construction method using a mold formed based on AI generative design according to the present invention.
[0017] Reference numerals 1. First expansion bolt hole; 2. Tension bolt hole; 3. First module unit; 4. Second module unit; 5. Third module unit; 6. Fourth module unit; 7. Wall; 8. Bottom ash; 9. Second expansion bolt hole; 10. Frame; 11. Straw reinforcement ash matrix; 12. Paper reinforcement ash; 13. Hanging net. DETAILED DESCRIPTION
[0018] The technical solution of the present invention is further described below through the accompanying drawings and embodiments.
[0019] Unless otherwise defined, technical or scientific terms used in the present invention shall have the common meanings understood by one having ordinary skills in the field to which the present invention belongs.
[0020] Embodiment 1 The present invention selects the training method of the generative model, the existing computer three-dimensional modeling software, and the available 3D printing equipment according to the needs, and adopts the existing technology and materials for implementation. In this embodiment, Stable Diffusion1.5 is used as the base (generative) model to train the gray plastic relief Lora generation model, the Zbrush modeling software is used to convert the two-dimensional image into a 3D model, the Rhinoceros modeling software is used to complete the mold design, the finite element analysis software is used to analyze the overall stress of the gray plastic relief, and the desktop 3D printer is used to make the gray plastic relief template component, and the construction is carried out on the wall.
[0021] like Figure 1 As shown, a method for constructing a Lingnan gray sculpture relief by mold forming based on AI generative design includes the following steps: S1. Preparation and testing of paper tendon ash and straw tendon ash.
[0022] S11. Preparation of straw ash: Put 5cm long dry straw soaked in water into a large container such as a large vat or barrel, and spread it to 5cm thick. Use lime and medium sand with a sand-ash ratio of 2:1 to make lime paste, then spread a layer of lime paste and cover the lower straw completely. Then slowly pour clean water along the inner wall of the large container (the amount of water should exceed the straw and lime paste layer by 30cm). Open it after sealing, soaking and fermenting for at least 15 days. After a long period of soaking and fermentation, filter out the upper layer of light yellow and clear lime water after opening to keep it for color adjustment in the future. Then stir it according to the ratio of kilograms of straw ash to kilograms of brown sugar.
[0023] Preparation of paper tendon ash: Soak 100kg of quicklime in 300kg of clean water, and then filter it with a fine sieve to make it lime oil. Then add 2.5kg of brown sugar and 3kg of glutinous rice flour in proportion and stir to make it smooth and delicate. Then soak and mash 15kg of Yuanbao paper to make paper tendons. Finally, mix the lime oil and paper tendons and seal them for about 20 days. Take them out and mix them before use. After the paper tendon ash is mixed with the pigment, it becomes color ash.
[0024] The above method is only a reference for preparing grass tendon ash and paper tendon ash. The specific production method can be adjusted according to the region and materials.
[0025] S12. Use a cubic compression test block mold with a side length of 70.7mm to cast the (compression) test blocks of paper-reinforced ash material and straw-reinforced ash material. Use a ash shovel to tamp evenly during pouring. The number of test blocks of each material should be no less than 3. After pouring, vibrate mechanically for more than 2 minutes.
[0026] Use a square flexural test block mold with a cross-sectional side length of 40mm and a length of 160mm to cast the (flexural) test blocks of paper-reinforced ash material and straw-reinforced ash material. Use a ash shovel to tamp evenly during pouring. The number of test blocks of each material should be no less than 3. After pouring, vibrate mechanically for more than 2 minutes.
[0027] S13. Curing under natural conditions at a temperature not exceeding 35°C, compacting with a trowel every 12 hours until it is completely hardened, then demoulding and storing for 90 days.
[0028] S14. Use a universal testing machine for test loading. The loading system can be selected as 25N / s or 1.5mm / s. Due to the shrinkage of the test block, the compressive area, cross-sectional height and other dimensions of the test block should be remeasured before the test loading. If the surface of the test block is uneven, it can be polished flat by hand, or plaster can be filled between the loading head and the test block to ensure that the test block and the loading head are in full contact. During the test loading process, the elastic modulus and Poisson's ratio can be measured by sticking strain gauges or digital image recognition. After the test, calculate the compressive strength, flexural strength, elastic modulus and Poisson's ratio.
[0029] S2. Model training.
[0030] S21. Material collection: obtain pictures of flat gray plastic reliefs.
[0031] S22. Image preprocessing: unify the resolution, use deepboru in the Stable Diffusion webUI platform to match the prompt words, save the prompt words as a txt file with the same name, check whether the prompt word content matches the image content, and add a unique field "huisu" to the prompt word.
[0032] S23, model training: After the prompt words are set, the Lora model is used for training. Among the model parameters, the batch size is determined to be 2, the learning rate is determined to be 0.0001, the optimization algorithm is Adam, the maximum epoch is 8, and the model file is saved every two epochs for model training.
[0033] S24, model selection: Use the model obtained in S23 to generate several gray plastic relief patterns, select the model whose image style matching and clarity of the gray plastic relief pattern meet the design requirements, and select the model with better generation effect of 7396 training steps and 14972 training steps.
[0034] S3. Design and adjustment of gray sculpture relief.
[0035] S31, image acquisition: using the model obtained in S2, taking Stable Diffusion 1.5 as the base model, using landscape and plaster painting as prompt words, to generate a plaster relief pattern.
[0036] S32, design selection: select the appropriate S31 obtained gray plastic relief pattern (2D plastic pattern) according to the design requirements.
[0037] S33. Model conversion: Use Zbrush modeling software to convert the alpha mask generated by the 2D plastic pattern obtained in S32 into height information, model it into a 3D gray plastic relief model, design the shape and relative position of its skeleton according to the graphic features and actual size, and save it as a drawing.
[0038] S34. Mechanical analysis: Import the 3D gray plastic relief model and the skeleton into the finite element analysis software, assign the material parameters obtained in S1 to the 3D gray plastic relief model, use copper wire and steel nails for the skeleton, and assign their material parameters respectively, calculate the self-weight according to the measured apparent density, and calculate the stress and displacement distribution of the structure under self-weight and wind load.
[0039] S35: Determine whether the normal load is met. If the normal load is met, proceed to S4; if the normal load is not met, proceed to S36.
[0040] S36. Model modification: If the local stress of the material exceeds its compressive strength, adjust the local height of the 3D gray plastic relief model, or use a more densely distributed skeleton to meet the normal use load.
[0041] S4. Mould manufacturing.
[0042] S41. Mould design: Rhinoceros modeling software is used to model according to the actual construction size to obtain the mould of the 3D grey plastic relief model. The mould is split as a whole according to the construction size of the 3D printer, and bolt holes for installation and fixation are set around the mould. After splitting, the parts are connected with tension bolts.
[0043] S42, determine printing parameters: import the model file into the slicing software, determine the parameters such as printing consumables, layer height, printing speed, printing temperature, etc., and generate the printing file required for printing.
[0044] S43, mold 3D printing: use the print file obtained in S42 to perform 3D printing on a 3D printer to manufacture various parts of the mold.
[0045] S44, mold post-processing: remove the support, polish the mold surface evenly, and try to assemble it to ensure that there is no damage or missing, so as to obtain a 3D printed mold for construction.
[0046] S5. On-site construction.
[0047] S51. Wall surface treatment: Grind the wall to be constructed flat, hang a mesh, apply a layer of primer, and drill expansion bolt holes at the designed hole positions.
[0048] S52. Frame binding: Pre-embed steel nails on the wall to be constructed according to the designed frame, and bind the frame with copper wire with a diameter of 6mm.
[0049] S53, pouring of grass reinforcement ash: the 3D printed mold obtained in S4 is assembled with bolts, and grass reinforcement ash is poured in the mold. It is vibrated evenly with a vibrating rod or a vibration platform, and compacted with an ash shovel so that the surface of the grass reinforcement ash is slightly higher than the mold plane after pouring, and forms a certain degree of adhesion with the mold surface.
[0050] S54. Mould installation: Install the mould with cast grass reinforcement ash as a whole on the wall surface, fix it with expansion bolts, and scrape off the excess ash paste.
[0051] S55, demoulding: After about a week, check whether the grass reinforcement ash has hardened. If the grass reinforcement ash in the mold has been completely hardened, remove the expansion bolts, dismantle the mold, and further compact it with an ash shovel to obtain a preliminarily completed grass reinforcement ash matrix.
[0052] S56. Apply paper reinforced ash surface layer: Apply a layer of paper reinforced ash on the straw reinforced ash base after demoulding to obtain an uncolored ash sculpture with a smoother surface.
[0053] S57, finishing and coloring: on the uncolored surface of the gray sculpture relief, apply colored gray according to the designed gray sculpture relief pattern. Wait for 3 days until the surface of the gray sculpture relief hardens and dries, and use pigments to complete the remaining coloring to obtain the completed gray sculpture relief. Its cross-sectional structure is as follows: Figure 8 shown.
[0054] S58. Maintenance: The completed plaster relief should be maintained in natural conditions away from water. You can cover it with waterproof cloth, straw mats and other measures. After it is completely dry, continue to water it for a week to prevent it from cracking due to external high temperature. Finally, the plaster relief is completed.
[0055] Embodiment 2 Using the construction method of embodiment 1, Figure 7 and Figure 8 As shown in the figure, a 3D printing mold was made, and the size of the molded component was 1m long, 0.75m wide, and 50mm thick. Fig. 9 As shown, the inner surface of the plaster relief mold is a 3D plaster relief pattern. The outer surface of the plaster relief mold is provided with a first expansion bolt hole 1 and a tension bolt hole 2. The plaster relief mold is composed of a plurality of four types of module units, namely, a first module unit 3 ( Fig.10 As shown), a second module unit 4 with tension bolt holes 2 on adjacent sides (as shown Fig.11 As shown), a third module unit 5 having tension bolt holes 2 arranged on three adjacent sides (as shown Fig.12 As shown) and the fourth module unit 6 (as Fig.13 As shown). The module units are fixedly connected and assembled into a gray plastic relief mold as a whole through the tension bolt holes 2. The sides of the second module unit 4, the third module unit 5 and the fourth module unit 6 that are not provided with the tension bolt holes 2 are all fixedly connected to the wall surface to be constructed by providing the first expansion bolt holes 1.
[0056] The cross-section diagram of the final completed gray sculpture is as follows: Fig.14As shown, after setting the hanging mesh 13 on the surface of the wall 7, the base ash 8 is applied, a second expansion bolt hole 9 is provided in the wall 7, steel nails are embedded, and the frame 10 is tied with copper wire. After demolding, the straw reinforcement ash matrix 11 is fixed on the surface of the wall 7, and paper reinforcement ash 12, color ash and pigment are applied in sequence on the straw reinforcement ash matrix 11 after demolding, and the construction is completed.
[0057] Therefore, the present invention adopts the above-mentioned AI generative design-based mold forming Lingnan gray plastic relief construction method, generates gray plastic relief design with the help of a pre-trained model, conducts material mechanics test optimization design, and uses 3D printing technology to manufacture molds and construct them, thereby improving the design efficiency of traditional gray plastic relief construction and restoration work, better meeting user personalized needs, improving the safety of gray plastic components, saving labor costs and reducing dependence on craftsmen's experience.
[0058] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that they can still modify or replace the technical solution of the present invention with equivalents, and these modifications or equivalent replacements cannot cause the modified technical solution to deviate from the spirit and scope of the technical solution of the present invention.
Claims
1. A method for constructing Lingnan gray sculpture relief by mold forming based on AI generative design, characterized in that: The following steps are involved: S1. Prepare paper-reinforced ash test blocks and straw-reinforced ash test blocks, and test material parameters; S2, model training: obtain a flat gray sculpture relief image, match the prompt words, set model training parameters for training and select a model; S3, gray plastic relief design and adjustment: The gray plastic relief pattern is generated using the model obtained in S2 and converted into a 3D gray plastic relief model. The stress analysis is performed based on the material parameters obtained in S1 to ensure that the normal use load is met. S4, mold manufacturing: designing a mold according to the 3D gray plastic relief model obtained in S3, and obtaining a 3D printed mold using a 3D printer; S5, on-site construction: fill the 3D printed mold obtained in S4 with straw ash and fix it to the wall. After hardening and demoulding, apply paper ash and color it.
2. According to the AI generative design-based mold forming Lingnan gray sculpture relief construction method according to claim 1, it is characterized in that: S1 is specifically: S11, preparing straw tendon ash and paper tendon ash, and setting aside for later use; S12, casting test blocks: filling paper reinforced ash into compression test block molds and flexural test block molds, respectively, filling straw reinforced ash into compression test block molds and flexural test block molds, respectively, vibrating and tamping evenly, to obtain a number of paper reinforced ash test blocks and straw reinforced ash test blocks; S13, test block curing: place the paper reinforced ash test block and the straw reinforced ash test block obtained in S12 in a ventilated and water-proof place for curing, and demould and store for 90 days after hardening; S14. Mechanical property test: Perform mechanical test on the paper-reinforced ash test blocks and straw-reinforced ash test blocks obtained in S13, and calculate the material parameters.
3. According to the AI generative design-based mold forming Lingnan gray sculpture relief construction method of claim 1, it is characterized in that: In S1, the material parameters include compressive strength, flexural strength, elastic modulus and Poisson's ratio.
4. The method for constructing Lingnan gray sculpture relief by mold forming based on AI generative design according to claim 1 is characterized in that: S2 is specifically: S21. Material collection: obtain pictures of flat gray plastic reliefs and organize and classify them; S22, image preprocessing: adjust the image obtained in S21 to a uniform resolution, assign prompt words through BLIP or deepboru, check whether the prompt words are consistent with the subject matter, adjust the prompt words and save; S23, model training: determine the batch size, learning rate, and training parameters of the optimization algorithm, perform Lora model training, and obtain models with different training steps; S24, model selection: using the model obtained in S23 to generate a corresponding plaster relief pattern, and selecting a model whose image style matching and clarity of the plaster relief pattern meet the design requirements.
5. According to the AI generative design-based mold forming Lingnan gray sculpture relief construction method of claim 1, it is characterized in that: S3 is specifically: S31, image acquisition: using the model obtained in S2, generating a number of gray sculpture relief patterns according to the prompt words; S32, design selection: select the gray plastic relief pattern obtained in S31 according to the design requirements to obtain a 2D plastic pattern; S33, model conversion: giving height to the 2D plastic pattern obtained in S32, converting it into a 3D gray plastic relief model, and designing a corresponding skeleton; S34, mechanical analysis: using the material parameters obtained in S1 and the 3D gray plastic relief model obtained in S33 as the object, perform self-weight and wind load force analysis to obtain stress and displacement distribution; S35, judging whether the normal use load is met, if not, proceeding to S36; S36. Model modification: Adjust the local height of the 3D gray plastic relief model.
6. The method for constructing Lingnan gray sculpture relief by mold forming based on AI generative design according to claim 1 is characterized in that: S4 is specifically: S41. Mold design: Modeling software is used to model according to the actual construction size to obtain a mold of a 3D gray plastic relief model. The mold is split as a whole and bolt holes are set according to the construction size of the 3D printer, and then saved as a printable model file; S42, determining printing parameters: importing the model file obtained in S41 into the slicing software, determining parameters, including printing consumables, layer height, printing speed and printing temperature, and generating the printing file required for printing; S43, mold 3D printing: using the print file obtained in S42 to perform 3D printing on a 3D printer to manufacture various parts of the mold; S44, mold post-processing: remove the support, polish the mold surface evenly, and obtain a 3D printed mold.
7. The method for constructing Lingnan gray sculpture relief by mold forming based on AI generative design according to claim 1 is characterized in that: S5 is as follows: S51. Wall surface treatment: Grind the wall surface to be constructed flat, apply primer after hanging the mesh, and drill expansion bolt holes at the designed hole positions; S52, Frame binding: Pre-embed steel nails on the wall to be constructed according to the designed frame, and bind the frame with copper wire; S53, grass reinforcement ash pouring: using the 3D printed mold obtained in S4 to pour the grass reinforcement ash, and vibrating and compacting it; S54, mold installation: install the mold with cast grass reinforcement ash as a whole on the wall to be constructed; S55, demoulding: after the grass tendon ash hardens, the mold is removed and compacted to obtain the grass tendon ash matrix; S56, applying paper tendon ash surface layer: applying paper tendon ash on the straw tendon ash base to obtain an uncolored ash sculpture relief; S57, modifying and coloring: applying color gray on the surface of the uncolored gray sculpture relief, and coloring with pigment after the surface of the gray sculpture relief is hardened and dried, so as to obtain a completed gray sculpture relief; S58. Maintenance: The completed gray plastic relief should be maintained in natural conditions away from water.
Citation Information
Patent Citations
Archaized building ridge structure and construction method thereof
CN114635527A
Manufacturing method of Lingnan cultural relic ancient building grey sculpture prefabricated part
CN117021336A
Method for manufacturing large-scale cement sculpture with assistance of 3D printing
CN111605355A
Lingnan grey sculpture material, preparation method thereof, grey sculpture product and manufacturing process of grey sculpture product
CN118908681A
Optimizing 3D printed large-scale structures under worst-case loads
US20190366703A1