A rapid forming method and system of an environment-friendly packaging box based on a biodegradable material

Abstract

The application relates to the field of 3D printing technology and discloses an environment-friendly packaging box rapid forming method and system based on biodegradable materials, the method comprising the following steps: establishing a thermal-structure coupling finite element model; based on the thermal-structure coupling model, a multi-objective optimization model is constructed to obtain structure design parameters and initial printing path configuration; a printing control strategy is trained by using a strategy optimization algorithm; according to the structure design parameters, the printing path configuration and the printing control strategy, a layer-by-layer printing path and a support structure configuration scheme matched with a printing object are generated; a 3D printing process is executed, and closed-loop adjustment is carried out according to the control strategy. Through the construction of the thermal-structure coupling finite element model based on the biodegradable materials, the changes of the temperature field, the stress field and the thermal strain field in the printing process are accurately simulated, so that the printing path and the support structure configuration are optimized, the printing precision is improved, the structural instability caused by thermal deformation and interlayer stress is avoided, and the object strength and stability are ensured.

Description

Technical Field

[0001] This invention relates to the field of 3D printing technology, specifically to a rapid prototyping method and system for environmentally friendly packaging boxes based on biodegradable materials. Background Technology

[0002] With increasing environmental awareness, biodegradable materials have gradually become a focus in the field of eco-friendly packaging. Against this backdrop, 3D printing technology, due to its high efficiency, flexibility, and customizability, is widely used in the design and manufacture of eco-friendly packaging boxes. Biodegradable materials, as a new type of green consumable for 3D printing, can decompose under natural conditions, reducing plastic pollution and meeting the needs of sustainable development.

[0003] First, the thermophysical properties of biodegradable materials in 3D printing are quite complex. Compared to traditional plastic materials, parameters such as thermal conductivity, specific heat capacity, and elastic modulus of biodegradable materials exhibit significant nonlinearity with temperature changes during the printing process. This characteristic makes the distribution of temperature and stress fields during printing difficult to predict, which can easily lead to problems such as thermal deformation and warping of the printed object, seriously affecting the quality and stability of environmentally friendly packaging boxes.

[0004] Secondly, traditional methods often rely on simple slicing algorithms or empirical design, failing to fully consider the thermal stress distribution and thermal conductivity characteristics of biodegradable materials. When printing complex structures or environmentally friendly packaging boxes with overhangs, existing technologies struggle to effectively generate support structures that meet mechanical performance requirements, leading to insufficient or unstable support during the printing process, which in turn affects the final print quality. Summary of the Invention

[0005] To address the shortcomings of existing technologies, this invention provides a rapid prototyping method and system for environmentally friendly packaging boxes based on biodegradable materials. This solves the problems of complex thermophysical properties of materials, thermal deformation and warping during printing, and the inability of existing path planning and support structure design to effectively handle the printing of complex structures.

[0006] To achieve the above objectives, the present invention provides the following technical solution: a rapid prototyping method for environmentally friendly packaging boxes based on biodegradable materials, comprising the following steps:

[0007] The thermal conductivity, specific heat capacity, elastic modulus, and density parameters of the selected biodegradable material were collected, and a thermal-structural coupled finite element model was established based on the material.

[0008] Based on the thermal-structural coupling model, a multi-objective optimization model is constructed. The objective function of the multi-objective optimization model is expressed as follows:

[0009] ;

[0010] In the formula, Objective 1: Minimize printing time, expressed by the formula:

[0011] ;

[0012] in, The print time objective function is used to measure the current design parameters. The total time required to complete all print paths; Design parameters represent the set of printing parameters to be optimized, including but not limited to: print layer thickness, infill density, local wall thickness, and ventilation structure layout parameters; To match the design parameters The corresponding total length of the print path, This is a function of the instantaneous printing speed of the print head as it moves along the path. The integral variable represents the path length from the starting point 0 to the end point of the printed path. Path coordinates;

[0013] Objective 2: Minimize the interlayer temperature difference, expressed by the formula:

[0014] ;

[0015] in, The objective function for thermal field uniformity represents the maximum temperature difference between layers during the printing process. This objective function reflects the stability of the heat conduction process during printing and needs to be minimized. and These represent the current design parameters. Next, the Layer and First The instantaneous temperature of the layer, which is obtained from the results of thermal-structural coupling simulation, and the calculation point can be a critical moment in the printing process; and Indicates structural layer numbering;

[0016] Objective 3: Maximizing structural stiffness, expressed by the formula:

[0017] ;

[0018] in, Let be the objective function for structural stiffness, representing the overall average load-bearing capacity of the structure. It is to maximize the goal; It refers to the three-dimensional volume region of the printed structure, corresponding to the geometric boundary range of the structure; It is the equivalent stress distribution function, which is often calculated using the von-Mises equal strength criterion, and reflects the stress response of the structure under a given load; For spatial volume infinitesimal elements, used to represent structural domains Integrate the stress results at all points;

[0019] Objective 4: Minimize material usage, expressed by the formula:

[0020] ;

[0021] in, Let be the objective function for material usage, representing the total mass or volume of material consumed in printing the current structure, which is the objective function to be minimized. It is a local material density function, which usually depends on the filling density, whether the structure is a support, cavity, solid, or other geometric features, and can be a constant or a function related to location and design parameters. Definition and In the formula The definitions are the same. Represents the volume region of a structural entity; The volume element represents the infinitesimal volume element in the integral, and the sum of these elements yields the total material distribution within the entire structure.

[0022] Based on structural design parameters, a reinforcement learning environment is constructed. The state variables in the printing process are used as inputs, and the control variables are used as actions. The printing control strategy is trained using a policy optimization algorithm to achieve dynamic control of the printing process.

[0023] Based on the structural design parameters, print path configuration, and print control strategy, generate a layer-by-layer print path and support structure configuration scheme that matches the print object.

[0024] The 3D printing process is executed according to the layer-by-layer printing path and support structure configuration scheme. During the process, printing status data is collected in real time, and closed-loop adjustment is performed according to the control strategy.

[0025] Preferably, the thermal-structural coupled finite element model considers the thermal conductivity, specific heat capacity, and elastic modulus of the biodegradable material as a function of temperature during the printing process, and outputs the temperature field, stress field, and thermal strain field.

[0026] Preferably, the design parameters of the optimization model include printing layer thickness, fill density, local wall thickness variation, and ventilation structure layout parameters, and the packaging structure parameters include printing thickness, support structure layout, wall thickness, and ventilation structure configuration.

[0027] Preferably, the state variables include the real-time temperature of the printhead, the material extrusion rate, the printing speed, the heated bed temperature, and the printed layer height; the control variables include the printhead heating power, the air cooling rate, the printhead speed, and the feed rate.

[0028] Preferably, the reinforcement learning control strategy is trained using a proximal policy optimization algorithm, and policy convergence is achieved through iterative simulation of the printing process.

[0029] Preferably, the printing path is generated based on the structural topology optimization results and thermal simulation feedback, and the support structure is preferentially arranged in the thermal deformation sensitive area and the overhanging structure area.

[0030] Preferably, the closed-loop regulation reduces the risk of interlayer cracking and warping by real-time acquisition of printing temperature, pressure, extrusion flow rate and interlayer misalignment, and adjusting printing parameters based on the printing control strategy.

[0031] Preferably, the data collected for printing status includes a thermocouple sensor, an infrared thermometer, and a displacement sensor.

[0032] A rapid prototyping system for environmentally friendly packaging boxes based on biodegradable materials includes:

[0033] The materials modeling module establishes a thermal-structural coupled finite element model based on the thermal conductivity, specific heat capacity, elastic modulus, and density parameters of biodegradable materials.

[0034] The structural optimization module constructs a multi-objective optimization model based on the thermal-structural coupling model and outputs the optimization results of the structural parameters and the initial path configuration.

[0035] The control strategy training module constructs a reinforcement learning environment based on the optimization results and trains a control strategy for dynamically regulating the printing process.

[0036] The path and support generation module generates a layer-by-layer printing path and support structure configuration based on optimization results and control strategies.

[0037] The printing execution and closed-loop control module executes the 3D printing process based on the support structure configuration and the layer-by-layer printing path, collects printing status data, and makes real-time adjustments according to the control strategy.

[0038] This invention provides a rapid prototyping method and system for environmentally friendly packaging boxes based on biodegradable materials. It offers the following advantages:

[0039] 1. This invention constructs a thermo-structural coupled finite element model based on biodegradable materials, which can accurately simulate the changes in temperature, stress, and thermal strain fields during the printing process. Therefore, it can predict the material's performance under heat conduction and mechanical loading during the design phase, thereby optimizing the printing path and support structure configuration, significantly improving printing accuracy, avoiding structural instability caused by thermal deformation and interlayer stress, and ensuring the overall strength and stability of the printed object.

[0040] 2. This invention employs a multi-objective optimization algorithm, comprehensively considering factors such as printing time, thermal uniformity, structural stiffness, and material usage, to achieve coordinated optimization of the printing path and structural design. While ensuring printing quality and structural strength, it maximizes resource utilization and printing efficiency by precisely controlling material usage and printing time, reducing material waste and aligning with environmentally friendly design principles.

[0041] 3. By introducing a reinforcement learning control strategy, this invention can collect data in real time and make dynamic adjustments during the printing process. Specifically, the system adjusts printing parameters in real time based on state variables such as the real-time temperature of the print head, the material extrusion rate, and the printing speed. Therefore, it can cope with complex changes in the printing environment and adjust key parameters in the printing process, such as heating power and printing speed, in a timely manner, reducing the risk of interlayer cracking and warping, and ensuring that each layer is printed accurately.

[0042] 4. This invention innovates in the configuration of the support structure by combining structural topology optimization and thermal simulation feedback. The layout of the support structure prioritizes thermal deformation-sensitive areas and overhanging structures, and can be dynamically adjusted based on real-time data. This not only improves printing stability but also effectively reduces waste of support materials, lowers energy and material consumption during the printing process, and further enhances the overall economic efficiency and sustainability of printing. Attached Figure Description

[0043] Figure 1 This is a schematic diagram of the method flow of the present invention;

[0044] Figure 2 This is a schematic diagram of the system architecture of the present invention. Detailed Implementation

[0045] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0046] To better understand the present invention, the above content will be described in detail below with reference to specific embodiments.

[0047] Please see the appendix Figure 1 This invention provides a rapid prototyping method for environmentally friendly packaging boxes based on biodegradable materials, comprising the following steps:

[0048] The thermal conductivity, specific heat capacity, elastic modulus, and density parameters of the selected biodegradable material were collected, and a thermal-structural coupled finite element model was established based on the material.

[0049] In this embodiment, to address the issue of complex heating behavior and easy deformation of biodegradable materials during the rapid prototyping process of environmentally friendly packaging boxes, thermophysical parameter modeling is first carried out based on the selected biodegradable materials.

[0050] Specifically, thermophysical parameters include, but are not limited to, thermal conductivity, specific heat capacity, elastic modulus, and density. Thermal conductivity and specific heat capacity are key parameters in heat transfer calculations, describing a material's ability to transfer heat per unit time and its temperature rise after absorbing heat per unit mass. Elastic modulus characterizes a material's deformation capacity under stress, while density is used for heat capacity calculations and mass-related quantity analysis. All of these parameters can be obtained through material databases, literature, or experimental measurements.

[0051] It should be noted that, due to the drastic temperature changes during the printing process, the thermophysical parameters of biodegradable materials often exhibit significant temperature dependence. Therefore, in this embodiment, a temperature-dependent material constitutive relation is introduced when establishing the thermo-structural coupled finite element model. For example, parameters such as thermal conductivity, specific heat capacity, and elastic modulus are all constructed as functions that change with temperature. This functional relation can be constructed through polynomial fitting, experimental interpolation, or table lookup, offering a degree of flexibility.

[0052] The thermo-structural coupled finite element model constructed in this embodiment integrates steady-state and transient heat conduction equations, structural mechanical response models, and material thermal strain models. Specifically, in the thermal analysis module, the following heat conduction control equations are used to simulate the temperature field:

[0053] ;

[0054] in:

[0055] For temperature variables;

[0056] For the selected biodegradable material at temperature Density at time;

[0057] For the selected biodegradable material at temperature Specific heat capacity at time;

[0058] For the selected biodegradable material at temperature Thermal conductivity at that time;

[0059] For internal heat source items;

[0060] The above equations can be solved by finite element discretization to obtain the transient temperature field distribution within the entire printing domain.

[0061] In the structural mechanics section, to achieve coupling with the thermal field, a structural statics model dominated by thermal strain is adopted. Its fundamental governing equations are:

[0062] ;

[0063] in, For stress tensor, For the body force term, the stress-strain relationship is established based on the thermoelastic constitutive model:

[0064] ;

[0065] in, The temperature-dependent stiffness matrix, For total strain, Thermal strain is defined as:

[0066] ;

[0067] in, For the selected biodegradable material at temperature The coefficient of thermal expansion at that time, For reference temperature, It is a unit tensor.

[0068] In the actual calculation process, thermal analysis and structural analysis are calculated synchronously through time steps, forming a two-way thermal-structural coupling. Specifically, in each time step, the current temperature field is first solved, and the elastic modulus and thermal strain are updated based on this temperature field. Then, the structural module is input to solve for the current structural response, and finally, the corresponding stress field and thermal strain field are output.

[0069] By simulating and solving this model, the temperature field evolution, internal thermal stress distribution, and thermal deformation trend induced by temperature difference of the structure to be printed during the 3D printing process can be obtained. The output temperature field, stress field, and thermal strain field provide the input basis for subsequent path optimization and support structure generation, and also provide a state variable simulation environment for training reinforcement learning control strategies.

[0070] Furthermore, the finite element model can be implemented in a commercial simulation platform (such as ANSYS or COMSOL) or discretely solved based on a self-developed code framework. The model discretization method can be linear or nonlinear elements, and the mesh can be locally refined for key areas to improve simulation accuracy.

[0071] Therefore, the thermal-structural coupled finite element model in this embodiment not only fully considers the nonlinear variation characteristics of material properties under temperature changes, but also provides calculable physical field outputs, laying a solid foundation for subsequent structural optimization and control strategy construction.

[0072] Based on the thermal-structure coupling model, a multi-objective optimization model is constructed with printing time, thermal field uniformity, molding strength and material usage as objectives. The structural parameters of the packaging to be printed are optimized to obtain the structural design parameters and the initial printing path configuration.

[0073] In this embodiment, after completing the construction of the thermal-structural coupled finite element model of the biodegradable material, multi-objective optimization modeling for the target structure is further carried out based on the model to achieve comprehensive and coordinated design of the 3D printing parameters of the environmentally friendly packaging box.

[0074] This multi-objective optimization model comprehensively considers four factors: printing efficiency, temperature control stability, structural performance, and material consumption. The optimization objectives include: minimizing printing time, maximizing thermal uniformity, maximizing the stiffness of the formed structure, and minimizing material usage. These objectives characterize the need for fast, stable, and low-resource-consumption printing, and seek the optimal combination of solutions within the printing parameter space.

[0075] The evaluation of printing time is calculated by dividing the total length of the printing path by the printing speed per unit time, and is usually related to the printing layer thickness and infill rate.

[0076] Thermal field uniformity is quantified by the maximum interlayer temperature difference in the model prediction results, which is derived from the transient temperature field output by the thermal-structure coupled finite element model.

[0077] Structural stiffness is measured by the effective modal stiffness or equivalent elastic modulus of the target structure under given boundary conditions, and is derived from the structural field output.

[0078] Material usage is calculated by integrating the volume of the filling area and the volume of the supporting structure, combined with density, and is an important indicator for controlling printing resource costs.

[0079] There are potential conflicts among the above-mentioned optimization objectives. For example, increasing the layer thickness may shorten the printing time, but it will also affect the heat transfer efficiency and printing intensity. In order to achieve a balance between the objectives, this embodiment uses an optional multi-objective optimization algorithm to solve the model, such as the Non-Dominated Sorting Genetic Algorithm (NSGA-II) or the Multi-Objective Particle Swarm Optimization Algorithm (MOPSO). The specific algorithm can be flexibly selected according to the implementation platform and the scale of the test case.

[0080] In the optimization model, the design parameters are the key construction parameters that constitute the printed structure, mainly including:

[0081] The printing layer thickness, as a printing step control parameter along the Z-axis, affects the printing rate and the structural connection strength.

[0082] Fill density, representing the proportion of material in non-solid areas, has a significant impact on weight and material consumption;

[0083] Localized wall thickness variations can be used to enhance the rigidity of critical stress areas and suppress thermal deformation.

[0084] Ventilation structure layout parameters, including the location and size of ventilation holes or heat conduction auxiliary structures, directly affect the heat conduction path and heat release rate.

[0085] In addition, for specific packaging structures, other structural parameters can be optionally introduced as design parameters, such as the layout of the support structure (including support type, spacing between support contact points, etc.) and overall geometric contour features (such as corner radius, connection slope, etc.). The range and initial values ​​of the above design parameters can be set according to the structure type, printing material, and printer parameters.

[0086] The optimization problem can be formally represented as follows:

[0087] Four optimization objective functions are constructed as follows:

[0088] ;

[0089] in, The objective vector contains multiple sub-objective functions, i.e. .

[0090] Specifically, it includes:

[0091] Objective 1: Minimize printing time:

[0092] ;

[0093] in, The print time objective function is used to measure the current design parameters. The total time required to complete all print paths; Design parameters represent the set of printing parameters to be optimized, including but not limited to: print layer thickness, infill density, local wall thickness, and ventilation structure layout parameters; To match the design parameters The corresponding total length of the print path, This is a function of the instantaneous printing speed of the print head as it moves along the path. The integral variable represents the path length from the starting point 0 to the end point of the printed path. The path coordinates.

[0094] Objective 2: Minimize interlayer temperature difference:

[0095] ;

[0096] in, The objective function for thermal field uniformity represents the maximum temperature difference between layers during the printing process. This objective function reflects the stability of the heat conduction process during printing and needs to be minimized. and These represent the current design parameters. Next, the Layer and First The instantaneous temperature of the layer, which is obtained from the results of thermal-structural coupling simulation, and the calculation point can be a critical moment in the printing process; and This indicates the structural layer numbering.

[0097] Objective 3: Maximize structural stiffness:

[0098] ;

[0099] in, Let be the objective function for structural stiffness, representing the overall average load-bearing capacity of the structure. It is to maximize the goal; It refers to the three-dimensional volume region of the printed structure, corresponding to the geometric boundary range of the structure; It is the equivalent stress distribution function, which is often calculated using the von-Mises equal strength criterion, and reflects the stress response of the structure under a given load; For spatial volume infinitesimal elements, used to represent structural domains Integrate the stress results at all points.

[0100] Objective 4: Minimize material usage:

[0101] ;

[0102] in, Let be the objective function for material usage, representing the total mass or volume of material consumed in printing the current structure, which is the objective function to be minimized. It is a local material density function, which usually depends on the filling density, whether the structure is a support, cavity, solid, or other geometric features, and can be a constant or a function related to location and design parameters. Definition and In the formula The definitions are the same. Represents the volume region of a structural entity; This represents the infinitesimal volume element in the integral, which, when accumulated, yields the total material distribution within the entire structure.

[0103] Therefore, by constructing a thermo-structural coupling analysis model, the interaction between the temperature field and structural response during the printing process is systematically characterized. Then, using printing time, thermal field uniformity, structural stiffness, and material usage as optimization objectives, a multi-objective optimization model is established to collaboratively solve the design parameters and path configuration of the packaging structure to be printed. This model not only fully considers the coupled balance between printing efficiency, thermal conductivity stability, molding strength, and resource consumption, but also introduces key variables such as layer thickness, filler density, wall thickness variation, and ventilation structure layout into the optimization dimension, achieving parameter collaborative optimization oriented towards printing performance, structural function, and environmental constraints. Finally, the model can output a set of structural design solutions and initial printing path configuration schemes that meet comprehensive performance requirements, providing a clear parameter basis and model support for subsequent path refinement, printing control strategy formulation, and structural function realization.

[0104] Based on structural design parameters, a reinforcement learning environment is constructed. The state variables in the printing process are used as inputs, and the control variables are used as actions. The printing control strategy is trained using a policy optimization algorithm to achieve dynamic control of the printing process.

[0105] In this embodiment, based on the solution results of the aforementioned thermo-structural coupled finite element model and multi-objective optimization model of biodegradable materials, an intelligent dynamic control system for 3D printing of packaging structures is further constructed to achieve fine control and real-time optimization of the printing process.

[0106] The dynamic control system employs reinforcement learning (RL) as its core intelligent decision-making tool. By simulating the layer-by-layer printing behavior of biodegradable materials, it optimizes the adjustment strategies of key parameters during the printing process. The reinforcement learning environment is constructed based on multi-physics coupled simulation results, systematically describing the transient evolution characteristics of the temperature and stress fields during the printing process, ensuring the physical consistency and prediction accuracy of the model.

[0107] In this embodiment, the state space design of the reinforcement learning environment fully considers multi-source state information during the printing process, including but not limited to the following five main state variables:

[0108] Real-time printhead temperature:

[0109] The instantaneous temperature reflects the current operating state of the printhead and is affected by the coupling effect of printhead heating power and printing speed. Dynamic temperature changes directly affect material flowability and interlayer bonding quality.

[0110] Material extrusion rate:

[0111] The linear velocity of the printing material extruded from the nozzle describes the speed at which the printing material is extruded. This rate is related to the printing path, nozzle diameter, and material viscosity, and is a key indicator for controlling printing thickness and density.

[0112] Printing speed:

[0113] This indicates the linear velocity of the print head as it moves along the path. Adjusting the printing speed directly affects the uniformity of material spreading and its thermal conductivity.

[0114] heated bed temperature:

[0115] The temperature control of the heated bed, as the printing substrate, directly affects the material cooling rate and the adhesion of the underlying layer, preventing warping and interlayer delamination.

[0116] Print layer height:

[0117] The Z-axis step height refers to the height of the single-layer print, which is directly related to path planning and infill density. Too large or too small a layer height will affect printing accuracy and material accumulation.

[0118] The above state variables serve as the observation inputs to the reinforcement learning model. Through real-time monitoring and updating of the thermal-structure coupling model, they accurately reflect the evolution of material heating, flow, solidification, and mechanical characteristics during the printing process.

[0119] In reinforcement learning strategies, based on the observations of the aforementioned state variables, a corresponding control action space is defined, including:

[0120] Nozzle heating power:

[0121] The output power of the heating element inside the nozzle is controlled to determine the melting state of the material and the extrusion flow rate;

[0122] Air cooling speed:

[0123] The cooling rate of the printed area is adjusted by an external fan, which affects the curing time of the material and the interlayer bonding effect.

[0124] Print head speed:

[0125] Dynamically adjust the printhead's movement speed along the path to achieve precise control over printing accuracy and thermal accumulation effects;

[0126] Feed rate:

[0127] Adjust the material supply speed from the feed end to the nozzle, and adjust it synchronously with the nozzle extrusion to ensure the uniformity of the printed layer.

[0128] The aforementioned control variables are used as adjustable actions in real time by the policy network during the optimization process of the reinforcement learning strategy. Through the adaptive exploration and learning of the reinforcement learning algorithm, various parameters are continuously adjusted to optimize printing quality and efficiency.

[0129] Specifically, the training of the reinforcement learning control policy employs the proximal-policy-optimization (PPO) algorithm, whose main optimization objective is to maximize the cumulative reward function. That is, to maximize the long-term expected reward of the agent in a given state:

[0130] ;

[0131] in, These are the parameters of the policy network;

[0132] For time step The immediate reward is defined as the feedback obtained from the transition from the current state to the next state;

[0133] It is a discount factor, representing the weight of future reward decay;

[0134] This represents the maximum number of steps in a training cycle (Episode).

[0135] The PPO algorithm maximizes cumulative reward by adjusting the policy network. Specifically, in each training iteration, the AI ​​selects an action based on the current policy and receives a reward based on environmental feedback. Based on this reward information, the policy update process is as follows:

[0136] ;

[0137] in, Indicates at time step Strategy parameters at that time;

[0138] Indicates at time step Strategy parameters at that time;

[0139] It is the learning rate, used to control the step size of policy parameter updates;

[0140] It is the loss function of the policy. Regarding strategy parameters The gradient.

[0141] The loss function for strategy optimization is... Defined as:

[0142] ;

[0143] in, It is the strategy update rate; It is the advantage-function, which measures the superiority of the current action and reflects the difference between the reward in the current state and the average expected reward. These are pruning parameters used to limit the range of policy changes.

[0144] Advantage function It is composed of the value function and the reward difference, and is estimated using the following formula:

[0145] ;

[0146] in, In strategy Under, state The state-value function represents the expected cumulative reward obtained by executing the policy starting from this state;

[0147] Therefore, through continuous iterative calculation and updates, the PPO algorithm effectively balances exploration and exploitation in each round of training, enabling the strategy to achieve dynamic optimization and adaptive adjustment of parameters during the printing process.

[0148] Through multiple rounds of simulation iterations, the reinforcement learning agent continuously selects the optimal action based on the current state (i.e., optimizing control parameters such as printhead heating power, air cooling speed, printing speed, and feed rate), and updates the strategy based on feedback rewards. This process is enhanced and verified with the support of a thermal-structural coupling simulator, thereby ensuring high efficiency and stability in complex printing environments.

[0149] Ultimately, after thorough strategy convergence and simulation verification, this embodiment successfully implemented a highly efficient, stable, and adaptive 3D printing control strategy. This strategy can dynamically adjust multiple key parameters during the printing process, thereby optimizing print quality, improving material utilization, and effectively reducing instability factors during printing.

[0150] Based on the structural design parameters, print path configuration, and print control strategy, generate a layer-by-layer print path and support structure configuration scheme that matches the print object.

[0151] In this embodiment, based on the comprehensive calculation results of the aforementioned thermo-structural coupled finite element model, multi-objective parameter optimization model, and reinforcement learning strategy optimization model of the biodegradable material, a path generation module and an automatic support structure configuration module for the execution of 3D printing tasks are further constructed to generate a layer-by-layer printing path and support structure configuration scheme that is adapted to the structural morphology and process characteristics of the printed object.

[0152] Specifically, to ensure the rationality of the printing path and the stability of the overall structural performance, the path generation process first performs preliminary layering based on the structural design parameters and the 3D geometric model. Specifically, a slicing algorithm is used to cut the 3D model into equally spaced layers along the construction direction (usually the Z-axis), and the cross-sectional profile of each layer is extracted as the basic data for path planning. This cross-sectional data is preprocessed using path adjustment and continuity reconstruction algorithms to remove path discontinuities, sharp corners, and invalid closed segments, thereby ensuring path smoothness and improving printing stability.

[0153] During path generation, considering the synergy between overall structural performance and local process response, this embodiment introduces structural topology optimization results as the basis for path correction. Structural topology optimization is a material distribution reconstruction method based on objective and constraint functions, capable of identifying the main load-bearing paths and unnecessary structural regions where stress concentration occurs under load conditions. Combining this optimization result, the path planning module can locally densify or sparse the printing path, making the path distribution more consistent with mechanical response requirements, especially achieving a more reasonable material stacking scheme in areas of concentrated stress.

[0154] Furthermore, to eliminate thermal stress concentration and structural deformation caused by interlayer temperature gradients, path generation also needs to comprehensively consider thermal simulation feedback information. In this embodiment, based on a thermal-structural coupled simulation model, multi-time-step transient analysis is performed on the layer-by-layer printing process to extract high-gradient temperature zones and potential deformation areas that appear in each layer during heat conduction, heat convection, and material curing. High-gradient regions are usually accompanied by a significant thermal shrinkage trend, which can easily lead to warping of the printed structure or residual internal stress.

[0155] Therefore, this embodiment incorporates thermal simulation feedback results into the path layout strategy for guided optimization. Specifically, in areas sensitive to thermal deformation, the path generation strategy prioritizes methods such as reducing path spacing and altering the direction of stacked paths to create temperature relief zones and reduce the rate of heat accumulation. Furthermore, in the arrangement of path turning points and starting points, an asymmetric path sequencing strategy is implemented in conjunction with thermal and cold boundary conditions to mitigate stress concentration caused by thermal convection.

[0156] Regarding the configuration of the support structure, this embodiment intelligently infers and adjusts the spatial distribution and contact method of the support structure by integrating the geometric features of the printed structure, the results of topology optimization, and the feedback results of thermal simulation. First, in areas where there are overhanging structures (i.e., the overhang angle exceeds the material's self-supporting critical value), the system automatically generates linear or planar support components. The support components are connected to the main structure using a controllable gap or anchoring method to facilitate later dismantling or structural linkage.

[0157] Secondly, in areas highly sensitive to thermal deformation, such as sharp corners, protrusions, and thin-walled sections, thermal warping is prone to occur due to insufficient heat convection. To suppress this problem, the support structure in this embodiment prioritizes forming a constraint system in such areas. Specifically, this includes applying structural support in the main direction of thermal stress and arranging heat dissipation channels or forced cooling auxiliary components at key locations to guide a balanced distribution of heat flow paths.

[0158] Furthermore, the configuration of the support structure does not use a static template, but is generated iteratively layer by layer based on the dynamic generation results of the printing path. After each layer of the path is generated, it can be determined whether to add, continue, or terminate support components based on the topological changes and thermal conductivity boundary changes between that layer and the next layer. This layer-by-layer feedback method achieves the "adaptive evolution" of the support structure, improving overall matching and printing stability.

[0159] In the above process, the coordinated configuration of the printing path and the support structure is calculated in parallel by the path planning module and the support configuration module, and coordinated and synchronized by the printing control strategy optimization module. The reinforcement learning control strategy adopted in this embodiment can provide predictive input based on historical thermal stress variation trends during the path generation stage, which is used to evaluate the impact of different path layouts on subsequent temperature distribution, and thus serve as an auxiliary control reference for path planning.

[0160] For example, when the control strategy identifies that a specific path will cause heat to concentrate at the boundary, the printing order or segmentation strategy of that path can be adjusted in advance to avoid the problem of thermal stress accumulation at the source. The support configuration module can also adjust the activation time and density of supports based on this thermal evolution trend, thereby realizing dynamic scheduling and optimization of support use.

[0161] In summary, the layer-by-layer path generated in this embodiment not only matches the structural design parameters and the geometric features of the printed object, but also possesses the ability to respond and adjust to changes in thermal stress distribution and structural stability. While fulfilling its printing support function, the support structure places greater emphasis on its compatibility with thermally sensitive areas and its integration with thermal feedback, thereby achieving a high degree of adaptability and process stability in the overall printing process.

[0162] The 3D printing process is executed according to the layer-by-layer printing path and support structure configuration scheme. During the process, printing status data is collected in real time, and closed-loop adjustment is performed according to the control strategy.

[0163] In this embodiment, during the 3D printing process, printing status data is collected in real time, and closed-loop adjustment is performed according to the control strategy. This closed-loop adjustment process mainly includes real-time monitoring and feedback control. By dynamically adjusting parameters such as temperature, pressure, extrusion flow rate, and interlayer misalignment, the stability of the printing process and the final print quality are ensured.

[0164] Real-time data acquisition

[0165] During the printing process, the system collects key printing status data in real time through multiple sensors, including thermocouple sensors, infrared thermometers, and displacement sensors. Specifically:

[0166] Thermocouple sensors are used to detect the temperature of the printhead and print bed to ensure temperature stability during each layer of printing.

[0167] Infrared thermometers are used to detect the temperature distribution between each layer, especially in areas with large heat accumulation.

[0168] Displacement sensors monitor the misalignment between layers during the printing process, detecting potential interlayer misalignment or structural instability.

[0169] Closed-loop control and regulation formula

[0170] After acquiring this data, the printing process is adjusted in a closed-loop manner based on a control strategy to reduce potential printing defects, especially interlayer cracking and warping. To achieve this goal, the system adjusts key parameters in the printing process according to the following formula:

[0171] Temperature adjustment formula:

[0172] For the temperature of each printed layer, the control system regulates heat flow by adjusting the printer's heating parameters. The temperature adjustment formula can be expressed as:

[0173] ;

[0174] in, This is the temperature adjustment value. It is the target temperature. This is the current temperature of the printed layer. It is the temperature control gain coefficient, which controls the heat input. By adjusting... The system can control the temperature of the printhead or bed to reduce thermal stress problems caused by excessively high or low temperature differences.

[0175] Interlayer misalignment adjustment formula:

[0176] Displacement sensors monitor interlayer misalignment in real time during the printing process. For example, if misalignment occurs in a certain layer... During the printing process, interlayer misalignment is If misalignment is found, adjust the printing speed or extrusion flow rate to reduce it. The formula for adjusting interlayer misalignment is:

[0177] ;

[0178] in, It is the misalignment value of the current printing layer. It is the expected misalignment value of the next layer. It is the extrusion flow rate. It is the printing time step. It is a control coefficient, which reduces the misalignment value by adjusting the flow rate in real time.

[0179] Extrusion flow rate adjustment formula:

[0180] The extrusion flow rate directly affects the deposition rate and uniformity of the printing material. When interlayer misalignment occurs, the control system adjusts the extrusion flow rate accordingly. To correct the material deposition rate. The flow rate adjustment formula is as follows:

[0181] ;

[0182] in, This is the adjusted extrusion flow rate. It is the actual interlayer misalignment of the current printing layer. It is the target misalignment value. It is an adjustment coefficient. By optimizing the adjustment range of the flow rate, the deposition of each layer is more uniform, and the occurrence of misalignment is reduced.

[0183] In actual printing, based on the above formula, the system continuously performs closed-loop adjustments according to the real-time collected data. For example, when the infrared thermometer detects that the temperature of a certain layer is too low, the system increases the heating power of the print head; if the displacement sensor detects excessive interlayer misalignment, it adjusts the extrusion flow rate or printing speed to reduce the misalignment problem. Simultaneously, the adjustment of printing parameters is based on the control gain coefficient (e.g., ...). , , These coefficients are dynamically adjusted based on feedback data during the printing process.

[0184] Through real-time feedback control, the system can continuously adjust key parameters during the printing process, ensuring that each layer is printed as expected, thereby reducing interlayer cracking, warping, and other printing defects. Especially in complex structures or high-precision printing tasks, the closed-loop control scheme can significantly improve print quality and avoid structural instability caused by inaccurate temperature or flow control.

[0185] Therefore, this embodiment introduces a closed-loop adjustment mechanism, combined with real-time data acquisition and intelligent control strategies, to dynamically adjust key parameters during the 3D printing process, thereby optimizing the printing process, improving printing accuracy, and effectively reducing problems such as interlayer cracking and warping.

[0186] Please see the appendix Figure 2 This embodiment also provides a rapid prototyping system for environmentally friendly packaging boxes based on biodegradable materials, including:

[0187] The materials modeling module establishes a thermal-structural coupled finite element model based on the thermal conductivity, specific heat capacity, elastic modulus, and density parameters of biodegradable materials.

[0188] The structural optimization module constructs a multi-objective optimization model based on the thermal-structural coupling model and outputs the optimization results of the structural parameters and the initial path configuration.

[0189] The control strategy training module builds a reinforcement learning environment based on the optimization results and trains a control strategy for dynamically regulating the printing process.

[0190] The path and support generation module generates a layer-by-layer printing path and support structure configuration based on optimization results and control strategies.

[0191] The printing execution and closed-loop control module executes the 3D printing process based on the support structure configuration and the layer-by-layer printing path, collects printing status data, and makes real-time adjustments according to the control strategy.

[0192] This embodiment provides a rapid prototyping system for environmentally friendly packaging boxes based on biodegradable materials. This system effectively improves the accuracy and efficiency of the 3D printing process by comprehensively utilizing advanced thermo-structural coupled finite element models, multi-objective optimization algorithms, reinforcement learning control strategies, and real-time closed-loop control. The system mainly includes the following modules:

[0193] Materials Modeling Module: This module establishes a thermo-structural coupled finite element model based on the fundamental physical properties of biodegradable materials, such as thermal conductivity, specific heat capacity, elastic modulus, and density. This model can accurately simulate the heat conduction and mechanical behavior of materials during the printing process, predict the deformation and stress distribution of materials under different temperature fields, and provide accurate data support for subsequent optimization design.

[0194] Structural Optimization Module: This module further constructs a multi-objective optimization model through a thermo-structural coupling model, aiming to optimize the design parameters of the printed structure. Multi-objective optimization considers not only performance indicators such as structural strength and stiffness, but also factors such as thermal stress and thermal shrinkage, thereby generating a printed structure design with excellent performance and outputting the optimized results of the initial path configuration. These results provide a foundation for subsequent path planning and support structure design.

[0195] Control Strategy Training Module: Based on the optimization results, the system constructs a reinforcement learning environment. By training the control strategy, printing parameters can be dynamically adjusted during the printing process. The reinforcement learning model is continuously optimized in this environment, learning from feedback on historical printing states to gradually improve its adaptability to complex changes during printing, ensuring print quality and process stability.

[0196] Path and Support Generation Module: This module generates layer-by-layer printing paths and support structure configurations based on optimization results and control strategies. The printing path design not only considers the rationality of material deposition but also adjusts it according to the mechanical requirements and thermal stress distribution of the structure to ensure the stability and adhesion of each printed layer. The support structures, based on the model optimization results, are precisely positioned in potentially suspended areas and thermally sensitive areas during printing, providing necessary support to prevent warping or structural instability during the printing process.

[0197] Printing Execution and Closed-Loop Control Module: During the printing process, the system executes 3D printing based on the generated support structure configuration and layer-by-layer printing path. During printing, real-time printing status data is collected, including key parameters such as temperature, displacement, and extrusion flow rate, and adjustments are made in real-time according to preset control strategies. The core function of this module is to dynamically adjust printing parameters, such as extrusion flow rate and printing speed, based on real-time data feedback during the printing process, ensuring that each layer reaches its optimal state and reducing risks such as interlayer misalignment and thermal deformation.

[0198] Through the collaborative work of the above modules, the entire system achieves full-process optimization and control from material modeling and structural optimization to printing execution, which can significantly improve the printing accuracy, stability and efficiency of environmentally friendly packaging boxes, meeting the needs of modern environmentally friendly design and rapid production.

[0199] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A rapid prototyping method for environmentally friendly packaging boxes based on biodegradable materials, characterized in that, Includes the following steps: The thermal conductivity, specific heat capacity, elastic modulus, and density parameters of the selected biodegradable material were collected, and a thermal-structural coupled finite element model was established based on the material. Based on the thermal-structural coupling model, a multi-objective optimization model is constructed. The objective function of the multi-objective optimization model is expressed as follows: ； In the formula, Objective 1: Minimize printing time, expressed by the formula: ； in, The print time objective function is used to measure the current design parameters. The total time required to complete all print paths; Design parameters represent the set of printing parameters to be optimized, including but not limited to: print layer thickness, infill density, local wall thickness, and ventilation structure layout parameters; To match the design parameters The corresponding total length of the print path, This is a function of the instantaneous printing speed of the print head as it moves along the path. The integral variable represents the path length from the starting point 0 to the end point of the printed path. Path coordinates; Objective 2: Minimize the interlayer temperature difference, expressed by the formula: ； in, The objective function for thermal field uniformity represents the maximum temperature difference between layers during the printing process. This objective function reflects the stability of the heat conduction process during printing and needs to be minimized. and These represent the current design parameters. Next, the Layer and First The instantaneous temperature of the layer, which is obtained from the results of thermal-structural coupling simulation, and the calculation point can be a critical moment in the printing process; and Indicates structural layer numbering; Objective 3: Maximizing structural stiffness, expressed by the formula: ； in, Let be the objective function for structural stiffness, representing the overall average load-bearing capacity of the structure, which is the objective to maximize. It refers to the three-dimensional volume region of the printed structure, corresponding to the geometric boundary range of the structure; It is the equivalent stress distribution function, which is often calculated using the von-Mises equal strength criterion, and reflects the stress response of the structure under a given load; For spatial volume elements, used to define structural domains Integrate the stress results at all points; Objective 4: Minimize material usage, expressed by the formula: ； in, Let be the objective function for material usage, representing the total mass or volume of material consumed in printing the current structure, which is the objective function to be minimized. It is a local material density function, which usually depends on the filling density, whether the structure is a support, cavity, solid, or other geometric features, and can be a constant or a function related to location and design parameters. Definition and In the formula The definitions are the same. Represents the volume region of a structural entity; The volume element represents the infinitesimal element in the integral, and the sum of these elements yields the total material distribution within the entire structure. Based on structural design parameters, a reinforcement learning environment is constructed. The state variables in the printing process are used as inputs, and the control variables are used as actions. The printing control strategy is trained using a policy optimization algorithm to achieve dynamic control of the printing process. Based on the structural design parameters, print path configuration, and print control strategy, generate a layer-by-layer print path and support structure configuration scheme that matches the print object. The 3D printing process is executed according to the layer-by-layer printing path and support structure configuration scheme. During the process, printing status data is collected in real time, and closed-loop adjustment is performed according to the control strategy.

2. The rapid prototyping method for environmentally friendly packaging boxes based on biodegradable materials according to claim 1, characterized in that, The thermal-structure coupled finite element model considers the thermal conductivity, specific heat capacity, and elastic modulus of biodegradable materials as they change with temperature during the printing process, and outputs temperature field, stress field, and thermal strain field.

3. The rapid prototyping method for environmentally friendly packaging boxes based on biodegradable materials according to claim 1, characterized in that, The design parameters of the optimization model include printing layer thickness, fill density, local wall thickness variation, and ventilation structure layout parameters. The packaging structure parameters include printing thickness, support structure layout, wall thickness, and ventilation structure configuration.

4. The rapid prototyping method for environmentally friendly packaging boxes based on biodegradable materials according to claim 1, characterized in that, The state variables include the real-time temperature of the printhead, the material extrusion rate, the printing speed, the heated bed temperature, and the printed layer height; the control variables include the printhead heating power, the air cooling rate, the printhead speed, and the feed rate.

5. The rapid prototyping method for environmentally friendly packaging boxes based on biodegradable materials according to claim 4, characterized in that, The reinforcement learning control strategy is trained using a proximal policy optimization algorithm, and policy convergence is achieved through iterative simulation of the printing process.

6. The rapid prototyping method for environmentally friendly packaging boxes based on biodegradable materials according to claim 4, characterized in that, The printing path is generated based on the structural topology optimization results and thermal simulation feedback, with the support structure preferentially placed in the thermal deformation sensitive area and the overhanging structure area.

7. The rapid prototyping method for environmentally friendly packaging boxes based on biodegradable materials according to claim 1, characterized in that, The closed-loop regulation reduces the risk of interlayer cracking and warping by real-time acquisition of printing temperature, pressure, extrusion flow rate and interlayer misalignment, and adjusting printing parameters based on the printing control strategy.

8. The rapid prototyping method for environmentally friendly packaging boxes based on biodegradable materials according to claim 7, characterized in that, The collected printing status data includes thermocouple sensors, infrared thermometers, and displacement sensors.

9. A rapid prototyping system for environmentally friendly packaging boxes based on biodegradable materials, and a rapid prototyping method for environmentally friendly packaging boxes based on biodegradable materials according to any one of claims 1-8, characterized in that, include: The materials modeling module establishes a thermal-structural coupled finite element model based on the thermal conductivity, specific heat capacity, elastic modulus, and density parameters of biodegradable materials. The structural optimization module constructs a multi-objective optimization model based on the thermal-structural coupling model and outputs the optimization results of the structural parameters and the initial path configuration. The control strategy training module constructs a reinforcement learning environment based on the optimization results and trains a control strategy for dynamically regulating the printing process. The path and support generation module generates a layer-by-layer printing path and support structure configuration based on optimization results and control strategies. The printing execution and closed-loop control module executes the 3D printing process based on the support structure configuration and the layer-by-layer printing path, collects printing status data, and makes real-time adjustments according to the control strategy.

Images