DLP (Digital Light Processing) equipment and material collaborative process
By constructing a multi-objective generative AI model and an intelligent production line, combined with an online evaluation system, the problem of insufficient synergy between DLP equipment and fluorinated electronic resins was solved, achieving high-precision and high-efficiency material processing, and improving the quality of molded parts and material utilization.
Patent Information
- Application Number
- CN202511876274.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-12-12
- Publication Date
- 2026-03-03
AI Technical Summary
Traditional DLP equipment suffers from poor matching between material and light source control and exposure parameters when processing fluorinated electronic resins. This leads to difficulties in controlling printing accuracy, poor quality of molded parts, low material utilization, lack of intelligent parameter adjustment capabilities, and insufficient process coordination.
A multi-objective generative AI model is constructed using high-throughput computing, machine learning, and materials genome engineering. Combined with an intelligent production line and an online real-time evaluation system, it achieves synergistic optimization of intelligent material design and DLP equipment through precise catalytic synthesis and high-purity separation technology. The AI model is used for dynamic parameter adjustment and closed-loop feedback.
It has achieved high-precision and high-efficiency material processing, improved the dimensional accuracy, surface quality and performance consistency of molded parts, shortened the R&D cycle, reduced trial and error costs, and formed a transferable software platform and a high-quality material database.
Smart Images
Figure CN121590031A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of high-end electronic material design and intelligent manufacturing technology, and in particular to a DLP equipment and material synergy process. Background Technology
[0002] DLP (Digital Micromirror Processing) equipment is a 3D printing system based on digital micromirror elements (DMD). It uses an ultraviolet light source to project digitally sliced patterns layer by layer onto the surface of a photosensitive resin, allowing specific areas to be precisely cured and formed. This equipment features high printing accuracy, good surface quality, and fast forming efficiency, and is widely used in the manufacture of complex structures in fields such as precision medical devices, jewelry casting, and microfluidic chips.
[0003] Currently, fluorinated electronic resins, as key materials in high-end fields, face multiple challenges in their development, including complex molecular design, a disconnect between synthesis processes and theoretical designs, and stringent quality control. Traditional DLP equipment lacks an effective synergistic mechanism between light source control, exposure parameters, and the photocuring characteristics of the material during material processing, resulting in insufficient process coordination. Furthermore, the poor matching degree between key parameters such as light source intensity and exposure time and the curing behavior of special materials like fluorinated electronic resins makes it difficult to control printing accuracy, easily leading to defects such as interlayer delamination and shrinkage warping. Simultaneously, the optimization between material properties and equipment parameters is not perfect, affecting not only the quality of molded parts but also resulting in low material utilization. In addition, existing systems lack intelligent parameter adaptive adjustment capabilities based on real-time feedback, making process parameter adjustment complex, reliant on manual experience, and difficult to achieve efficient, stable, and replicable manufacturing processes. Summary of the Invention
[0004] The purpose of this invention is to provide a collaborative process between DLP equipment and materials, which solves the problem of insufficient synergy between equipment and materials in existing DLP technologies, and provides a novel collaborative process between DLP equipment and materials to achieve high-precision and high-efficiency material processing.
[0005] To achieve the above-mentioned objectives, the technical solution adopted by this invention is as follows:
[0006] A DLP device and material co-process includes the following steps: Based on high-throughput computing, machine learning and materials genome engineering technology, a multi-objective generative AI model integrating a polymerization activity discriminator and printability scoring is constructed to intelligently screen and virtually design key parameters such as molecular structure, polymerization mode and microstructure of fluorinated electronic resins;
[0007] Step 2: Design and synthesize novel high-efficiency catalysts to achieve precise control of the polymerization process by accurately regulating catalytic reaction conditions;
[0008] Step 3: Use separation and purification methods such as supercritical fluid extraction, ion exchange, precision distillation, and membrane separation to ensure that the product reaches ppb-level cleanliness.
[0009] Step 4: Construct an intelligent production workshop, integrating automated production lines, intelligent sensors, machine vision inspection, and industrial robots to achieve intelligent control of the production process;
[0010] Step 5: Develop an online real-time evaluation system that integrates spectral analysis, chromatographic analysis, mass spectrometry, dielectric spectroscopy, thermal analysis, and mechanical property testing.
[0011] Step 6: Based on online evaluation data, continuously optimize and improve the entire process through data analysis algorithms and artificial intelligence models.
[0012] As an improvement, the multi-objective generative AI model is constructed using graph neural networks and diffusion models, embedding key feature parameters such as electronegativity and steric hindrance.
[0013] As an improvement, the precise catalytic synthesis step obtains fluoropolymer precursors with narrow molecular weight distribution and regular structure by controlling parameters such as temperature, pressure, reaction time, and monomer ratio.
[0014] As an improvement, the high-purity polymerization process uses methods such as supercritical fluid extraction, ion exchange, precision distillation, and membrane separation to control the content of impurities such as metal ions, chloride ions, moisture, and volatile organic compounds to the ppb level.
[0015] As an improvement, the intelligent manufacturing process monitors, collects and analyzes key process parameters such as temperature, pressure, flow rate, liquid level and purity in real time, and optimizes the production process by using industrial internet platforms and big data analysis technology.
[0016] As an improvement, the online evaluation process monitors the material's chemical composition, molecular weight and distribution, glass transition temperature, thermal decomposition temperature, dielectric constant, dielectric loss, tensile strength, elastic modulus, and other performance parameters in real time.
[0017] As an improvement, the closed-loop optimization process achieves optimal performance across multiple objectives, such as dielectric constant <2.5, glass transition temperature >200℃, breakdown strength >400 kV / mm, and water absorption rate <0.3%, through a closed-loop feedback mechanism of "design-synthesis-manufacturing-evaluation-optimization" within 30 iterations.
[0018] A system for implementing the method of any one of claims 1 to 7, characterized in that it comprises: a generative AI design module, a printability scoring submodule, a DLP equipment control module, an online characterization module, and a closed-loop optimization module; wherein the generative AI design module, based on the multi-objective generative AI model of claim 1, realizes intelligent design of material molecular structure; the printability scoring submodule evaluates the 3D printing manufacturability of materials; the DLP equipment control module dynamically optimizes the photocurable resin formulation based on an AI prediction model and controls parameters such as light source intensity and exposure time of the DLP equipment; the online characterization module integrates multiple detection technologies to realize real-time monitoring of material performance; and the closed-loop optimization module, based on the correlation analysis of material performance data and process parameters, realizes intelligent adjustment of process parameters.
[0019] As an improvement, the printability scoring submodule introduces uncertainty quantification and active learning mechanisms to ensure that the generated structure has both chemical rationality and process feasibility.
[0020] As an improvement, the platform combines advanced printing technologies such as DLP and SLA, and dynamically optimizes the photocurable resin formulation through AI prediction models to effectively suppress interlayer peeling and shrinkage warping caused by low surface energy, ensuring that the samples have high dimensional accuracy and surface quality.
[0021] The beneficial effects of this invention are as follows: By integrating a generative AI model with physical constraints and a dual-threshold screening for printability, it fundamentally solves the industry problem of balancing the rationality of material chemistry and the feasibility of DLP processes; by combining dynamically optimized intelligent manufacturing with online real-time evaluation integrating multiple technologies, it significantly improves the dimensional accuracy, surface quality, and performance consistency of printed samples (such as achieving high-performance indicators like ε<2.5, Tg>200℃, and Eb>400kV / mm); finally, through a data-driven closed-loop feedback mechanism, multi-objective synergistic optimization can be achieved within 30 iterations, greatly shortening the R&D cycle, reducing trial-and-error costs, and forming a transferable software platform and a high-quality material database, providing full-chain technical support for the independent control and industrial application of high-end electronic materials. Attached Figure Description
[0022] Figure 1 This is a flowchart of a DLP equipment and material co-process according to the present invention. Detailed Implementation
[0023] To make the content of this invention easier to understand, the technical solutions of the embodiments of this invention will be clearly and completely described below with reference to the accompanying drawings. Identical components are represented by the same reference numerals. It should be noted that the terms "front," "rear," "left," "right," "up," and "down" used in the following description refer to directions in the accompanying drawings, while the terms "inner" and "outer" refer to directions toward or away from the geometric center of a specific component, respectively.
[0024] like Figure 1 As shown, a DLP device and material synergistic process includes the following steps: Step 1: Based on high-throughput computing, machine learning, and materials genome engineering technologies, a multi-objective generative AI model integrating a polymerization activity discriminator and printability scoring is constructed to intelligently screen and virtually design key parameters such as the molecular structure, polymerization mode, and microstructure of fluorinated electronic resins; Step 2: Design and synthesize novel high-efficiency catalysts, and achieve precise control of the polymerization process by accurately regulating catalytic reaction conditions; Step 3: Use separation and purification methods such as supercritical fluid extraction, ion exchange, precision distillation, and membrane separation to ensure that the product reaches ppb-level cleanliness; Step 4: Construct an intelligent production workshop, integrating automated production lines, intelligent sensors, machine vision inspection, and industrial robots to achieve intelligent control of the production process; Step 5: Develop an online real-time evaluation system integrating spectral analysis, chromatographic analysis, mass spectrometry, dielectric spectroscopy, thermal analysis, and mechanical property testing; Step 6: Based on the online evaluation data, continuously optimize and improve the entire process through data analysis algorithms and artificial intelligence models.
[0025] like Figure 1 As shown, the multi-objective generative AI model is constructed using graph neural networks and diffusion models, embedding key characteristic parameters such as electronegativity and steric hindrance. The precise catalytic synthesis step obtains fluoropolymer precursors with narrow molecular weight distribution and regular structure by controlling parameters such as temperature, pressure, reaction time, and monomer ratio. The high-purity polymerization process controls the content of impurities such as metal ions, chloride ions, moisture, and volatile organic compounds to the ppb level through methods such as supercritical fluid extraction, ion exchange, precision distillation, and membrane separation. The intelligent manufacturing step monitors, collects, and analyzes key process parameters such as temperature, pressure, flow rate, liquid level, and purity in real time, optimizing the production process using an industrial internet platform and big data analysis technology. The online evaluation step monitors the chemical composition, molecular weight and distribution, glass transition temperature, thermal decomposition temperature, dielectric constant, dielectric loss, tensile strength, and elastic modulus of the material in real time. The closed-loop optimization process achieves optimal performance across multiple objectives, including dielectric constant <2.5, glass transition temperature >200℃, breakdown strength >400 kV / mm, and water absorption rate <0.3%, through a closed-loop feedback mechanism of "design-synthesis-manufacturing-evaluation-optimization" within 30 iterations.
[0026] A system for implementing the method of any one of claims 1 to 7, characterized in that it comprises: a generative AI design module, a printability scoring submodule, a DLP equipment control module, an online characterization module, and a closed-loop optimization module. The generative AI design module, based on the multi-objective generative AI model of claim 1, realizes intelligent design of the material's molecular structure. The printability scoring submodule evaluates the 3D printing manufacturability of the material. The DLP equipment control module dynamically optimizes the photocurable resin formulation based on an AI prediction model, controlling parameters such as the light source intensity and exposure time of the DLP equipment. The online characterization module integrates multiple detection technologies to achieve real-time monitoring of material properties. The closed-loop optimization module, based on the correlation analysis between material property data and process parameters, realizes intelligent adjustment of process parameters. The printability scoring submodule, by introducing uncertainty quantification and active learning mechanisms, ensures that the generated structure possesses both chemical rationality and process feasibility. The platform, combining advanced printing technologies such as DLP and SLA, dynamically optimizes the photocurable resin formulation through an AI prediction model, effectively suppressing interlayer delamination and shrinkage warping caused by low surface energy, ensuring that the sample has high dimensional accuracy and surface quality.
[0027] In the process of use, firstly, a generative AI model that integrates physical constraints is used to intelligently design fluorinated resin molecules, and structural feasibility is ensured through dual threshold screening for printability; then, ppb-level high-purity resin is obtained through precise catalytic synthesis and combinatorial purification technology; in the DLP intelligent manufacturing process, printing parameters and resin formulation are dynamically optimized and monitored in real time through an AI model; finally, performance data is collected through an online evaluation system that integrates multiple technologies, and the optimal performance of multiple objectives is achieved within 30 iterations through a closed-loop optimization module, forming a data-driven closed loop from molecular design to finished product manufacturing.
[0028] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.
Claims
1. A DLP equipment and material co-process, characterized in that, Includes the following steps: Based on high-throughput computing, machine learning, and materials genome engineering technologies, a multi-objective generative AI model integrating a polymerization activity discriminator and printability scoring is constructed to intelligently screen and virtually design key parameters such as molecular structure, polymerization mode, and microstructure of fluorinated electronic resins. Step 2: Design and synthesize novel high-efficiency catalysts to achieve precise control of the polymerization process by accurately regulating catalytic reaction conditions; Step 3: Use separation and purification methods such as supercritical fluid extraction, ion exchange, precision distillation, and membrane separation to ensure that the product reaches ppb-level cleanliness. Step 4: Construct an intelligent production workshop, integrating automated production lines, intelligent sensors, machine vision inspection, and industrial robots to achieve intelligent control of the production process; Step 5: Develop an online real-time evaluation system that integrates spectral analysis, chromatographic analysis, mass spectrometry, dielectric spectroscopy, thermal analysis, and mechanical property testing. Step 6: Based on online evaluation data, continuously optimize and improve the entire process through data analysis algorithms and artificial intelligence models.
2. The DLP equipment and material synergy process according to claim 1, characterized in that, The multi-objective generative AI model is constructed using graph neural networks and diffusion models, embedding key feature parameters such as electronegativity and steric hindrance.
3. The DLP equipment and material synergy process according to claim 1, characterized in that, The precise catalytic synthesis process obtains fluoropolymer precursors with narrow molecular weight distribution and regular structure by controlling parameters such as temperature, pressure, reaction time, and monomer ratio.
4. The DLP equipment and material synergy process according to claim 1, characterized in that, The high-purity polymerization process uses methods such as supercritical fluid extraction, ion exchange, precision distillation, and membrane separation to control the content of impurities such as metal ions, chloride ions, moisture, and volatile organic compounds to the ppb level.
5. The DLP equipment and material synergy process according to claim 1, characterized in that, The intelligent manufacturing process involves real-time monitoring, data collection, and analysis of key process parameters such as temperature, pressure, flow rate, liquid level, and purity, and utilizes industrial internet platforms and big data analytics to optimize production processes.
6. The DLP equipment and material synergy process according to claim 1, characterized in that, The online evaluation process monitors the material's chemical composition, molecular weight and distribution, glass transition temperature, thermal decomposition temperature, dielectric constant, dielectric loss, tensile strength, elastic modulus, and other performance parameters in real time.
7. The DLP equipment and material synergy process according to claim 1, characterized in that, The closed-loop optimization process achieves optimal performance across multiple objectives, including dielectric constant <2.5, glass transition temperature >200℃, breakdown strength >400 kV / mm, and water absorption rate <0.3%, through a closed-loop feedback mechanism of "design-synthesis-manufacturing-evaluation-optimization" within 30 iterations.
8. A system for implementing the method according to any one of claims 1 to 7, as described in claim 1, characterized in that, include: The system comprises a generative AI design module, a printability scoring submodule, a DLP equipment control module, an online characterization module, and a closed-loop optimization module. The generative AI design module, based on the multi-objective generative AI model described in claim 1, enables intelligent design of the material's molecular structure. The printability scoring submodule evaluates the 3D printing manufacturability of the material. The DLP equipment control module dynamically optimizes the photocurable resin formulation based on an AI prediction model and controls parameters such as the light source intensity and exposure time of the DLP equipment. The online characterization module integrates multiple detection technologies to achieve real-time monitoring of material properties. The closed-loop optimization module, based on the correlation analysis between material property data and process parameters, enables intelligent adjustment of process parameters.
9. The system according to claim 8, characterized in that, The printability scoring submodule ensures that the generated structure is both chemically sound and technologically feasible by introducing uncertainty quantification and active learning mechanisms.
10. The system according to claim 9, characterized in that, The platform combines advanced printing technologies such as DLP and SLA, and dynamically optimizes the photocurable resin formulation through AI prediction models. This effectively suppresses interlayer peeling and shrinkage warping caused by low surface energy, ensuring that the samples have high dimensional accuracy and surface quality.