Intelligent laser power control method and system for 3D printing

Abstract

The invention relates to the field, and discloses a laser power intelligent control method and system for 3D printing, and the method comprises the steps: building a 3D model information database, and collecting printing original data in real time; performing laser power pre-calculation by adopting a prediction model constructed based on finite element analysis and a convolutional neural network to obtain a prediction result; taking the initial laser power set value of each layer and each region given by the prediction result as initial power input, and driving a laser generator to start printing operation of the current layer or region according to the set value; the state of a molten pool and the forming quality information of a printed layer are collected in real time to obtain actual forming quality parameters, the actual forming quality parameters are analyzed, the laser power is dynamically adjusted according to the deviation size and direction, and 3D printing forming is achieved; accurate and intelligent control over the 3D printing laser power is achieved, the printing quality and stability are effectively improved, and the rejection rate is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of 3D printing, and particularly to an intelligent control method and system for laser power used in 3D printing. Background Art

[0002] As a rapid prototyping technology, 3D printing has been widely used in many fields such as aerospace, medical, and automotive manufacturing. In the 3D printing process based on laser sintering or melting, the laser power plays a crucial role in the forming quality. At present, most traditional 3D printing laser power control methods adopt a fixed power mode or a simple open-loop control method, which are difficult to meet complex printing requirements. On the one hand, different printing materials, model structures, and printing stages have different absorptions and requirements for laser energy. On the other hand, factors such as temperature changes and material property fluctuations that may occur during the printing process will also affect the laser action effect. These situations often lead to problems such as poor interlayer bonding, large surface roughness, poor dimensional accuracy, and even internal defects in the printed products, severely restricting the development of 3D printing technology towards higher precision and higher quality. Summary of the Invention

[0003] The purpose of the present invention is to solve the above problems and design an intelligent control method and system for laser power used in 3D printing.

[0004] The first aspect of the present invention provides an intelligent control method for laser power used in 3D printing. The intelligent control method for laser power used in 3D printing includes the following steps:

[0005] Obtain the thermophysical parameters of the 3D printing material and the structural characteristics of different types of 3D models, and establish a 3D model information database;

[0006] Real-time collect the printing environment temperature, the energy distribution in the laser action area, and the material composition change information through sensors arranged around the printing platform to obtain the original printing data;

[0007] Read the 3D model information database, combine the original printing data, and perform pre-calculation of the laser power using a prediction model constructed based on finite element analysis and convolutional neural network to obtain a prediction result;

[0008] Take the preliminary laser power setting value for each layer and each area given by the prediction result as the starting power input, and drive the laser generator to start the printing operation of the current layer or area according to this setting value;

[0009] The actual forming quality parameters are obtained by collecting the molten pool state and the forming quality information of the printed layers in real time. The actual forming quality parameters are analyzed, and the laser power is dynamically adjusted according to the magnitude and direction of the deviation to achieve 3D printing forming. The forming quality information includes at least the molten pool size, solidification rate, and interlayer flatness.

[0010] Optionally, in the first implementation manner of the first aspect of the present invention, the printing environment temperature, the energy distribution in the laser action area, and the material composition change information are collected in real time by sensors arranged around the printing platform to obtain the original printing data, including:

[0011] A thermistor is used as the temperature sensor. By applying a constant current to the thermistor and measuring the voltage across the thermistor, the current ambient temperature is obtained according to Ohm's law, and the temperature data is continuously collected.

[0012] An optical power meter based on the photoelectric effect is used as the energy sensor. The laser scanning area is divided into multiple small squares. The optical power meter quickly moves to the center position of each square in turn and stays briefly for 0.1 second to measure and record the laser power value at that point. This is repeated in a cycle to construct the energy distribution matrix of the entire laser action area.

[0013] A material composition monitor is used to monitor the real-time change of the material composition. For metal powder materials, X-ray fluorescence spectroscopy is used, and for organic polymer materials, infrared spectroscopy is used. The data of each monitored material composition change is recorded.

[0014] The printing environment temperature, the energy distribution in the laser action area, and the material composition change information are obtained in real time to obtain the original printing data.

[0015] Optionally, in the second implementation manner of the first aspect of the present invention, the 3D model information database is read, and in combination with the original printing data, a prediction model based on finite element analysis and convolutional neural network is used to pre-calculate the laser power to obtain the prediction result, including:

[0016] The 3D printing model is discretized. The 3D printing model is divided into multiple tiny units, and corresponding heat conduction properties are assigned to each unit according to the thermophysical parameters of the 3D printing material.

[0017] Laser is used as the input of the point heat source. According to the law of conservation of energy, within the time interval Δt, the heat entering the unit, the change in the heat stored in the unit itself, and the heat flowing out of the unit satisfy the following relationship:

[0018]

[0019] where ρ is the density, c is the specific heat capacity, V is the unit volume, ΔT is the change in the unit temperature within Δt, is the heat flux flowing in from j adjacent units, m is the number of adjacent units from which the heat flux flows in, is the heat flux flowing towards k adjacent units, n is the number of adjacent units to which the heat flux flows out, and Δx is the distance in the heat conduction direction;

[0020] Obtain the energy distribution from the energy distribution in the laser action area of the printed raw data, and determine the heat flux input of each unit at different times according to the laser scanning path, speed, and energy distribution;

[0021] By iteratively simulating the heat transfer process in the model during the laser scanning process based on heat balance, calculate the energy input required for different regions of the model to reach the expected melting temperature, and obtain the energy density requirement E corresponding to each unit d :

[0022]

[0023] where t is the time required to reach the melting temperature, is the heat entering the unit within the i-th time interval;

[0024] Obtain the calculated energy density requirement values to form the preliminary output result of the finite element analysis, determine the energy distribution required based on the physical heat conduction process, and perform preliminary calculation of the laser power in combination with the prediction model to obtain the prediction result.

[0025] Optionally, in the third implementation manner of the first aspect of the present invention, the obtaining the calculated energy density requirement values to form the preliminary output result of the finite element analysis, determining the energy distribution required based on the physical heat conduction process, and performing preliminary calculation of the laser power in combination with the prediction model to obtain the prediction result includes:

[0026] Preprocess the historical printing data to obtain sample data, organize each sample data into a multi-dimensional array including model structure features, environmental parameters, material properties, and the corresponding laser power value required for successful printing, train through the sample data and optimize the construction of the prediction model using the bat algorithm, where the model structure features at least include the model volume, surface area, and layer thickness distribution, the environmental parameters at least include the printing environment temperature and humidity, and the material properties at least include the thermal conductivity, specific heat capacity, and the corresponding laser power value;

[0027] In the convolutional layer of the prediction model, slide the convolutional kernel on the input data for feature extraction, continuously reduce the data dimension through multiple layers of convolution and pooling, extract higher-level features, and finally map these features to an output value through the fully connected layer to obtain the predicted laser power adjustment coefficient;

[0028] The energy density requirement obtained from the finite element analysis is combined with the laser power adjustment coefficient output by the prediction model to calculate the final predicted laser power, and the prediction result is obtained.

[0029] Optionally, in the fourth implementation manner of the first aspect of the present invention, the construction of the prediction model by training with sample data and optimizing with the bat algorithm includes:

[0030] Initialize the parameters of the population, including at least position, velocity, frequency, loudness, and population size. The initial position value for the first time is a random initial solution generated using a uniform distribution;

[0031] Calculate the fitness of each initial solution for the parameters of each bat individual, and find the solution with the best fitness, where the objective function is the training error rate of the convolutional neural network;

[0032] The pulse rate is a parameter set during initialization. In each iteration, update the position and velocity of the bat, and generate a new frequency for each bat. If the random number is greater than the pulse rate, the bat will generate a new solution around the current optimal solution. If the fitness of the new solution is better than the current solution and the random number is less than the loudness, take the new solution;

[0033] Evaluate the fitness of the new solution. If the fitness of the new solution is better than the current best solution, update the current best solution and the minimum fitness value;

[0034] When the maximum number of iterations is reached, return the found optimal solution and the corresponding minimum fitness value, and use the bat algorithm to optimize the hyperparameter of the number of convolutional kernels of the convolutional neural network to construct the prediction model.

[0035] Optionally, in the fifth implementation manner of the first aspect of the present invention, using the preliminary laser power setting value of each layer and each region given by the prediction result as the starting power input to drive the laser generator to start the printing operation of the current layer or region includes:

[0036] Extract the preliminary laser power setting values corresponding to the current layer to be printed and each region within the layer from the prediction result;

[0037] Control the output light intensity to control the laser power by adjusting the applied voltage. Given the required laser power setting value P pre , and the opto - electrical conversion efficiency η of the laser generator, obtain the required input light intensity I according to the relationship between power and light intensity pre :

[0038]

[0039] where A is the cross - sectional area of the laser beam;

[0040] According to the Pockels effect formula, calculate the corresponding applied voltage V pre :

[0041]

[0042] where V π is the half-wave voltage, I0 is the reference light intensity, and arcsin(·) converts the light intensity ratio into the corresponding voltage value;

[0043] Apply the calculated voltage value to the electro-optic modulation element of the laser generator, drive the laser generator to output laser according to the power setting value, and start printing the current layer or area.

[0044] Optionally, in the sixth implementation manner of the first aspect of the present invention, the preliminary laser power setting value of each layer and each area given by the prediction result is used as the starting power input, and the laser generator is driven to start the printing operation of the current layer or area, and further includes:

[0045] While driving the laser generator to start printing, start a synchronous clock signal. If the scanning speed of the printing device is v scan , and the resolution is r res , then the frequency f sync of the synchronous clock signal can be set to:

[0046] f sync = v scan ·r res ;

[0047] During the printing process, use the sensor to continuously collect real-time data, including at least the actual output power of the laser and the ambient temperature of the current printing area, and calculate the power error by comparing the actual output power with the set power;

[0048] Judge whether the power error exceeds the pre-set allowable error range. If so, trigger the alarm mechanism and perform power compensation according to the error magnitude.

[0049] Monitor the ambient temperature of the printing area. If the temperature change exceeds the temperature threshold, pause printing and wait until the temperature is lower than the temperature threshold before continuing printing.

[0050] The second aspect of the present invention provides a laser power intelligent control system for 3D printing. The laser power intelligent control system for 3D printing includes a database establishment module, a data acquisition module, a laser power prediction module, a printing operation module, and a dynamic adjustment module. Among them,

[0051] The database establishment module is used to obtain the thermophysical parameters of the 3D printing material and the structural characteristics of different types of 3D models, and establish a 3D model information database;

[0052] A data acquisition module, which is used to collect the printing environment temperature, the energy distribution of the laser action area, and the material composition change information in real time through sensors arranged around the printing platform, so as to obtain the original printing data;

[0053] A laser power prediction module, which is used to read the 3D model information database, combine the original printing data, and perform pre-calculation of the laser power by using a prediction model constructed based on finite element analysis and convolutional neural network to obtain a prediction result;

[0054] A printing operation module, which is used to take the initial laser power setting value of each layer and each area given by the prediction result as the starting power input, and drive the laser generator to start the printing operation of the current layer or area according to this setting value;

[0055] A dynamic adjustment module, which is used to collect the molten pool state and the forming quality information of the printed layer in real time to obtain the actual forming quality parameters, analyze the actual forming quality parameters, and dynamically adjust the laser power according to the deviation magnitude and direction to realize 3D printing forming, where the forming quality information at least includes the molten pool size, solidification rate, and interlayer flatness.

[0056] Optionally, in the first implementation manner of the second aspect of the present invention, the data acquisition module includes a temperature measurement sub-module, an energy measurement sub-module, a material monitoring sub-module, and an acquisition sub-module, where

[0057] The temperature measurement sub-module is used to use a thermistor as a temperature sensor, measure the voltage across the thermistor by applying a constant current to the thermistor, and obtain the current ambient temperature according to Ohm's law, and continuously collect temperature data;

[0058] The energy measurement sub-module is used to use an optical power meter based on the photoelectric effect as an energy sensor, divide the laser scanning area into multiple small squares, the optical power meter quickly moves to the center position of each square in turn and stays briefly for 0.1 second, measures and records the laser power value at this point, and repeats the process to construct an energy distribution matrix of the entire laser action area;

[0059] The material monitoring sub-module is used to perform real-time monitoring of the material composition change by using a material composition monitor, use X-ray fluorescence spectroscopy for metal powder materials, and use infrared spectroscopy for organic polymer materials, and record the material composition change data monitored each time;

[0060] The acquisition sub-module is used to obtain the printing environment temperature, the energy distribution of the laser action area, and the material composition change information in real time to obtain the original printing data.

[0061] Optionally, in the second implementation manner of the second aspect of the present invention, the laser power prediction module includes a discretization processing sub-module, an adoption sub-module, a determination sub-module, a first calculation sub-module, and a second calculation sub-module, where,

[0062] The discretization processing sub-module is used to perform discretization processing on the 3D printing model, divide the 3D printing model into multiple tiny units, and assign corresponding heat conduction properties to each unit according to the thermophysical parameters of the 3D printing material;

[0063] The adoption sub-module is used to input laser as a point heat source. According to the law of conservation of energy, within the time interval Δt, the heat entering the unit, the change in the heat stored in the unit itself, and the heat flowing out of the unit satisfy the following relationship:

[0064]

[0065] where ρ is the density, c is the specific heat capacity, V is the unit volume, ΔT is the change in the unit temperature within Δt, is the heat flow flowing in from j adjacent units, m is the number of adjacent units with inflowing heat flow, is the heat flow flowing to k adjacent units, n is the number of adjacent units with outflowing heat flow, and Δx is the distance in the heat conduction direction;

[0066] The determination sub-module is used to obtain the energy distribution from the energy distribution in the laser action area in the printing original data, and determine the heat flow input situation of each unit at different times according to the laser scanning path, speed, and energy distribution;

[0067] The first calculation sub-module is used to calculate the energy input required for different regions of the model to reach the expected melting temperature by iteratively simulating the heat transfer process in the model during laser scanning, and obtain the energy density requirement E corresponding to each unit d :

[0068]

[0069] where t is the time required to reach the melting temperature, is the heat entering the unit in the i-th time interval;

[0070] The second calculation sub-module is used to obtain the calculated energy density requirement values to form the preliminary output result of the finite element analysis, determine the energy distribution situation required based on the physical heat conduction process, and perform pre-calculation of the laser power in combination with the prediction model to obtain the prediction result.

[0071] In the technical solution provided by the present invention, the thermophysical parameters of the 3D printing material and the structural characteristics of different types of 3D models are obtained to establish a 3D model information database; the printing ambient temperature, the energy distribution in the laser action area, and the information on the change of material composition are collected in real time by sensors arranged around the printing platform to obtain the original printing data; the 3D model information database is read, and in combination with the original printing data, a prediction model constructed based on finite element analysis and convolutional neural network is used for pre-calculating the laser power to obtain a prediction result; the initial laser power setting value for each layer and each area given by the prediction result is used as the starting power input to drive the laser generator to start the printing operation of the current layer or area according to this setting value; the molten pool state and the forming quality information of the printed layer are collected in real time to obtain the actual forming quality parameters, the actual forming quality parameters are analyzed, and the laser power is dynamically adjusted according to the magnitude and direction of the deviation to achieve 3D printing forming, where the forming quality information at least includes the molten pool size, solidification rate, and interlayer flatness; the present invention realizes precise and intelligent control of the 3D printing laser power, effectively improves the printing quality and stability, reduces the scrap rate, and meets the requirements of high precision and high performance of 3D printing in different fields. Description of the Drawings

[0072] By reading the detailed description of the preferred embodiments below, various other advantages and benefits will become clear to those of ordinary skill in the art. The drawings are only for the purpose of showing the preferred embodiments and are not considered to be a limitation of the present invention.

[0073] Figure 1 Schematic diagram of the first embodiment of the intelligent control method for the laser power used in 3D printing provided by the embodiment of the present invention;

[0074] Figure 2 Schematic diagram of the second embodiment of the intelligent control method for the laser power used in 3D printing provided by the embodiment of the present invention;

[0075] Figure 3 Schematic diagram of the third embodiment of the intelligent control method for the laser power used in 3D printing provided by the embodiment of the present invention;

[0076] Figure 4 Schematic diagram of the structure of the intelligent control system for the laser power used in 3D printing provided by the embodiment of the present invention. Detailed Embodiments

[0077] In the description, claims and the above drawings of the present invention, the terms "first", "second", "third", "fourth", etc. (if any) are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the term "comprising" or "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, device, product or equipment comprising a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or equipment.

[0078] For ease of understanding, the specific process of the embodiments of the present invention will be described below. Please refer to Figure 1 The schematic diagram of the first embodiment of the intelligent laser power control method for 3D printing provided by the embodiments of the present invention. The method specifically includes the following steps:

[0079] Step 101: Obtain the thermophysical parameters of the 3D printing material and the structural characteristics of different types of 3D models, and establish a 3D model information database;

[0080] Step 102: Real-time collect the printing environment temperature, the energy distribution in the laser action area, and the material composition change information through the sensors arranged around the printing platform to obtain the original printing data;

[0081] Step 103: Read the 3D model information database, combine it with the original printing data, and perform pre-calculation of the laser power using a prediction model constructed based on finite element analysis and convolutional neural network to obtain a prediction result;

[0082] In this embodiment, reading the 3D model information database, combining it with the original printing data, and performing pre-calculation of the laser power using a prediction model constructed based on finite element analysis and convolutional neural network to obtain a prediction result includes:

[0083] Perform discretization processing on the 3D printing model, divide the 3D printing model into multiple tiny units, and assign corresponding heat conduction properties to each unit according to the thermophysical parameters of the 3D printing material;

[0084] Use the laser as a point heat source input. According to the law of conservation of energy, within the time interval Δt, the heat entering the unit, the change in the heat stored in the unit itself, and the heat flowing out of the unit satisfy the following relationship:

[0085]

[0086] Among them, ρ is the density, c is the specific heat capacity, V is the unit volume, and ΔT is the change in the unit temperature within Δt. is the heat flux flowing in from j adjacent units, m is the number of adjacent units with the inflowing heat flux. is the heat flux flowing to k adjacent units, n is the number of adjacent units with the outflowing heat flux, and Δx is the distance in the heat conduction direction.

[0087] Obtain the energy distribution from the energy distribution in the laser action area of the printed original data, and determine the heat flux input of each unit at different times according to the laser scanning path, speed, and energy distribution.

[0088] Through iterative heat balance to simulate the heat transfer process in the model during laser scanning, calculate the energy input required for different regions of the model to reach the expected melting temperature, and obtain the energy density requirement E corresponding to each unit d :

[0089]

[0090] Among them, t is the time required to reach the melting temperature. is the heat entering the unit within the i-th time interval.

[0091] Obtain the calculated energy density requirement values to form the preliminary output result of the finite element analysis, determine the energy distribution required based on the physical heat conduction process, and combine with the prediction model to perform pre-calculation of the laser power to obtain the prediction result.

[0092] Step 104: Use the preliminary laser power setting values for each layer and each region given by the prediction result as the starting power input, and drive the laser generator to start the printing operation of the current layer or region according to this setting value.

[0093] In this embodiment, extract the preliminary laser power setting values for the current layer to be printed and each region within this layer from the prediction result.

[0094] Control the laser power by adjusting the applied voltage to control the output light intensity. Given the required laser power setting value P pre , and the opto-electronic conversion efficiency η of the laser generator, obtain the required input light intensity I according to the relationship between power and light intensity pre :

[0095]

[0096] Among them, A is the cross-sectional area of the laser beam.

[0097] Then, according to the Pockels effect formula, calculate the corresponding applied voltage V pre :

[0098]

[0099] Among them, V π is the half-wave voltage, I0 is the reference light intensity, and arcsin(·) converts the light intensity ratio into the corresponding voltage value;

[0100] Apply the calculated voltage value to the electro-optic modulation element of the laser generator, drive the laser generator to output laser according to the power setting value, and start printing the current layer or area.

[0101] In this embodiment, while driving the laser generator to start printing, a synchronous clock signal is started. If the scanning speed of the printing device is v scan , and the resolution is r res , then the frequency f sync of the synchronous clock signal can be set as:

[0102] f sync = v scan ·r res ;

[0103] During the printing process, use the sensor to continuously collect real-time data, including at least the actual output power of the laser and the ambient temperature of the current printing area, and calculate the power error by comparing the actual output power with the set power;

[0104] Judge whether the power error exceeds the pre-set allowable error range. If so, trigger the alarm mechanism and perform power compensation according to the error magnitude.

[0105] Monitor the ambient temperature of the printing area. If the temperature change exceeds the temperature threshold, pause printing and wait until the temperature is lower than the temperature threshold before continuing printing.

[0106] Step 105: Collect the molten pool state and the forming quality information of the printed layer in real time to obtain the actual forming quality parameters, analyze the actual forming quality parameters, and dynamically adjust the laser power according to the deviation magnitude and direction to achieve 3D printing forming.

[0107] In this embodiment, the forming quality information includes at least the molten pool size, solidification rate, and interlayer flatness.

[0108] Please refer to Figure 2 , the schematic diagram of the second embodiment of the laser power intelligent control method for 3D printing provided by the embodiment of the present invention. This method includes:

[0109] Step 201: Use a thermistor as the temperature sensor, measure the voltage across the thermistor by applying a constant current to the thermistor, and obtain the current ambient temperature according to Ohm's law, and continuously collect temperature data;

[0110] Step 202: Use a light power meter based on the photoelectric effect as an energy sensor. Divide the laser scanning area into multiple small squares. The light power meter quickly moves to the center position of each square in turn and stays briefly for 0.1 seconds, measures and records the laser power value at this point, and repeats in a loop to construct an energy distribution matrix of the entire laser action area;

[0111] Step 203: Use a material composition monitor to monitor the real-time change of the material composition. For metal powder materials, use X-ray fluorescence spectroscopy analysis, and for organic polymer materials, use infrared spectroscopy analysis, and record the data of the material composition change monitored each time;

[0112] Step 204: Obtain the printing environment temperature, the energy distribution of the laser action area, and the material composition change information in real time to obtain the original printing data.

[0113] Please refer to Figure 3 , the schematic diagram of the third embodiment of the intelligent laser power control method for 3D printing provided by the embodiment of the present invention. The method includes:

[0114] Step 301: Preprocess the historical printing data to obtain sample data. Organize each sample data into a multi-dimensional array containing model structure features, environmental parameters, material characteristics, and the corresponding laser power value required for successful printing. Train through the sample data and use the bat algorithm to optimize and construct a prediction model;

[0115] In this embodiment, the model structure features at least include model volume, surface area, and layer thickness distribution. The environmental parameters at least include printing environment temperature and humidity. The material characteristics at least include thermal conductivity, specific heat capacity, and the corresponding laser power value;

[0116] In this embodiment, the parameters for initializing the population at least include position, velocity, frequency, loudness, and population size. The initial position value is a random initial solution generated using a uniform distribution; calculate the fitness of each initial solution for each bat individual, and find the solution with the optimal fitness, where the objective function is the training error rate of the convolutional neural network; the pulse rate is a parameter set during initialization. In each iteration, update the position and velocity of the bat, and generate a new frequency for each bat. If the random number is greater than the pulse rate, the bat will generate a new solution around the current optimal solution. If the fitness of the new solution is better than the current solution and the random number is less than the loudness, take the new solution; perform fitness evaluation on the new solution. If the fitness of the new solution is better than the current best solution, update the current best solution and the minimum fitness value; when the maximum number of iterations is reached, return the found optimal solution and the corresponding minimum fitness value, and use the bat algorithm to optimize the hyperparameter of the number of convolutional kernels of the convolutional neural network to construct a prediction model.

[0117] Step 302: Use a convolution kernel to slide on the input data in the convolutional layer of the prediction model for feature extraction. Through multiple layers of convolution and pooling, continuously reduce the data dimension, extract higher-level features, and finally map these features to an output value through a fully connected layer to obtain the predicted laser power adjustment coefficient.

[0118] Step 303: Combine the energy density requirement obtained from finite element analysis with the laser power adjustment coefficient output by the prediction model to calculate the final predicted laser power and obtain the prediction result.

[0119] Please refer to Figure 4 , the structural schematic diagram of the intelligent laser power control system for 3D printing provided by the embodiment of the present invention. The system includes a database establishment module, a data acquisition module, a laser power prediction module, a printing operation module, and a dynamic adjustment module. Among them,

[0120] The database establishment module is used to obtain the thermophysical parameters of 3D printing materials and the structural characteristics of different types of 3D models, and establish a 3D model information database.

[0121] The data acquisition module is used to collect the printing environment temperature, the energy distribution in the laser action area, and the material composition change information in real time through sensors arranged around the printing platform to obtain the original printing data.

[0122] The laser power prediction module is used to read the 3D model information database, combine the original printing data, and perform pre-calculation of the laser power using a prediction model based on finite element analysis and convolutional neural network to obtain the prediction result.

[0123] The printing operation module is used to take the preliminary laser power setting value of each layer and each area given by the prediction result as the starting power input, and drive the laser generator to start the printing operation of the current layer or area according to this setting value.

[0124] The dynamic adjustment module is used to collect the molten pool state and the forming quality information of the printed layer in real time to obtain the actual forming quality parameters, analyze the actual forming quality parameters, and dynamically adjust the laser power according to the deviation size and direction to achieve 3D printing forming, where the forming quality information at least includes the molten pool size, solidification rate, and interlayer flatness.

[0125] In this embodiment, the data acquisition module includes a temperature measurement sub-module, an energy measurement sub-module, a material monitoring sub-module, and an acquisition sub-module. Among them,

[0126] The temperature measurement sub-module is used to use a thermistor as a temperature sensor, measure the voltage across the thermistor by applying a constant current to the thermistor, and obtain the current ambient temperature according to Ohm's law, and continuously collect temperature data.

[0127] An energy measurement sub-module, which uses a light power meter based on the photoelectric effect as an energy sensor, divides the laser scanning area into multiple small squares, quickly moves the light power meter to the center position of each square in turn and stays briefly for 0.1 second, measures and records the laser power value at this point, and repeats the process to construct an energy distribution matrix of the entire laser action area;

[0128] A material monitoring sub-module, which is used to monitor the real-time change of material composition by using a material composition monitor, uses X-ray fluorescence spectroscopy for metal powder materials and infrared spectroscopy for organic polymer materials, and records the data of material composition changes monitored each time;

[0129] An acquisition sub-module, which is used to acquire the printing environment temperature, the energy distribution of the laser action area and the material composition change information in real time to obtain the original printing data.

[0130] In this embodiment, the laser power prediction module includes a discretization processing sub-module, an adoption sub-module, a determination sub-module, a first calculation sub-module and a second calculation sub-module, where,

[0131] The discretization processing sub-module is used to discretize the 3D printing model, divide the 3D printing model into multiple tiny units, and assign corresponding heat conduction properties to each unit according to the thermophysical parameters of the 3D printing material;

[0132] The adoption sub-module is used to use a laser as a point heat source input. According to the law of conservation of energy, within the time interval Δt, the heat entering the unit, the change in the heat stored in the unit itself, and the heat flowing out of the unit satisfy the following relationship:

[0133]

[0134] where ρ is the density, c is the specific heat capacity, V is the unit volume, ΔT is the change in the unit temperature within Δt, is the heat flow flowing in from j adjacent units, m is the number of adjacent units with inflowing heat flow, is the heat flow flowing to k adjacent units, n is the number of adjacent units with outflowing heat flow, and Δx is the distance in the heat conduction direction;

[0135] The determination sub-module is used to obtain the energy distribution from the energy distribution of the laser action area in the original printing data, and determine the heat flow input situation of each unit at different times according to the laser scanning path, speed and energy distribution;

[0136] The first calculation sub-module is used to simulate the heat transfer process in the model during laser scanning by iterative heat balance, calculate the energy input required for different regions of the model to reach the expected melting temperature, and obtain the energy density requirement E corresponding to each unitd :

[0137]

[0138] where t is the time required to reach the melting temperature, is the heat entering the unit within the i-th time interval;

[0139] A second calculation sub-module, configured to obtain the calculated energy density requirement value to form a preliminary output result of the finite element analysis, determine the energy distribution required based on the physical heat conduction process, and perform a preliminary calculation of the laser power in combination with the prediction model to obtain a prediction result.

[0140] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above embodiments. The above embodiments and the descriptions in the specification are only preferred examples of the present invention and are not used to limit the present invention. Without departing from the spirit and scope of the present invention, the present invention will have various changes and improvements, and these changes and improvements all fall within the scope of the present invention claimed. The scope of protection claimed by the present invention is defined by the appended claims and their equivalents.

Claims

1. A laser power intelligent control method for 3D printing, characterized in that: The laser power intelligent control method for 3D printing comprises the following steps: Obtain the thermophysical parameters of 3D printing materials and the structural characteristics of different types of 3D models, and establish a 3D model information database; The sensors arranged around the printing platform collect the printing environment temperature, energy distribution in the laser action area, and material composition change information in real time to obtain the original printing data; Reading the 3D model information database, combining the original printing data, using a prediction model based on finite element analysis and a convolutional neural network to pre-calculate the laser power, and obtaining a prediction result; The initial laser power setting value for each layer or each area given by the prediction result is used as the initial power input, and the laser generator is driven to start the printing operation of the current layer or area according to the setting value; The molten pool status and the molding quality information of the printed layers are collected in real time to obtain the actual molding quality parameters, and the actual molding quality parameters are analyzed. The laser power is dynamically adjusted according to the deviation size and direction to achieve 3D printing molding, where the molding quality information at least includes the molten pool size, solidification rate and interlayer flatness.

2. The laser power intelligent control method for 3D printing according to claim 1, characterized in that: The sensors arranged around the printing platform collect the printing environment temperature, the energy distribution in the laser action area, and the material composition change information in real time to obtain the printing raw data, including: Thermistors are used as temperature sensors. A constant current is applied to the thermistor, the voltage across the thermistor is measured, and the current ambient temperature is obtained according to Ohm's law, and temperature data is continuously collected. An optical power meter based on the photoelectric effect is used as an energy sensor. The laser scanning area is divided into multiple small squares. The optical power meter quickly moves to the center of each square and stays there for 0.1 second. The laser power value at that point is measured and recorded. This process is repeated to construct an energy distribution matrix of the entire laser action area. Use material composition monitors to monitor material composition changes in real time. For metal powder materials, X-ray fluorescence spectroscopy is used, and for organic polymer materials, infrared spectroscopy is used. The material composition change data monitored each time is recorded; The printing environment temperature, energy distribution in the laser action area, and material composition change information are acquired in real time to obtain the original printing data.

3. The laser power intelligent control method for 3D printing according to claim 1, characterized in that: The 3D model information database is read, combined with the original printing data, and a prediction model based on finite element analysis and convolutional neural network is used to pre-calculate the laser power to obtain a prediction result, including: Discretize the 3D printing model, divide the 3D printing model into multiple small units, and assign corresponding thermal conductivity properties to each unit according to the thermophysical parameters of the 3D printing material; Using laser as a point heat source input, according to the law of conservation of energy, within the time interval Δt, the heat entering the unit, the change in the unit's own stored heat, and the heat flowing out of the unit satisfy the following relationship: Where ρ is the density, c is the specific heat, V is the unit volume, ΔT is the change in unit temperature within Δt, is the heat flow from j neighboring cells, m is the number of neighboring cells into which the heat flow flows, is the heat flow to k neighboring cells, n is the number of neighboring cells from which the heat flow flows, and Δx is the distance in the direction of heat conduction; Obtain energy distribution from the energy distribution of the laser action area in the original printing data, and determine the heat flow input of each unit at different times according to the laser scanning path, speed and energy distribution; The heat transfer process in the model during laser scanning is simulated by iterative thermal balance, and the energy input required for different areas of the model to reach the expected melting temperature is calculated to obtain the energy density requirement E corresponding to each unit. d : Where t is the time required to reach the melting temperature, is the heat entering the unit during the i-th time interval; The calculated energy density requirement value is obtained to form the preliminary output result of the finite element analysis, and the energy distribution required based on the physical heat conduction process is determined. The laser power is pre-calculated in combination with the prediction model to obtain the prediction result.

4. The laser power intelligent control method for 3D printing according to claim 3, characterized in that: The energy density requirement value obtained and calculated constitutes the preliminary output result of the finite element analysis, determines the energy distribution required based on the physical heat conduction process, and performs laser power pre-calculation in combination with the prediction model to obtain the prediction result, including: Preprocess the historical printing data to obtain sample data, organize each sample data into a multidimensional array containing model structure characteristics, environmental parameters, material properties and the corresponding laser power value required for successful printing, train the prediction model through the sample data and use the bat algorithm to optimize and build the prediction model, wherein the model structure characteristics at least include the model volume, surface area and layer thickness distribution, the environmental parameters at least include the printing environment temperature and humidity, and the material properties at least include thermal conductivity, specific heat capacity and the corresponding laser power value; In the convolution layer of the prediction model, the convolution kernel is used to slide on the input data to extract features. Through multiple layers of convolution and pooling, the data dimension is continuously reduced to extract more advanced features. Finally, these features are mapped to an output value through the fully connected layer to obtain the predicted laser power adjustment coefficient. The energy density requirement obtained by finite element analysis is combined with the laser power adjustment coefficient output by the prediction model to calculate the final laser power prediction and obtain the prediction result.

5. The laser power intelligent control method for 3D printing according to claim 4, characterized in that: The method of training with sample data and optimizing the prediction model using the bat algorithm includes: Initialize the population parameters, including at least position, speed, frequency, loudness, and population size. The first position value is a random initial solution generated using a uniform distribution. Calculate the fitness of each initial solution for the parameters of each individual bat and find the solution with the best fitness, where the objective function is the training error rate of the convolutional neural network; The pulse rate is the parameter set by the initialization. The position and speed of the bat are updated in each iteration, and a new frequency is generated for each bat. If the random number is greater than the pulse rate, the bat will generate a new solution around the current optimal solution. If the fitness of the new solution is better than the current solution and the random number is less than the loudness, the new solution is taken. Evaluate the fitness of the new solution. If the fitness of the new solution is better than the current best solution, update the current best solution and the minimum fitness value. When the maximum number of iterations is reached, the optimal solution and the corresponding minimum fitness value are returned, and the bat algorithm is used to optimize the convolution kernel number hyperparameter of the convolutional neural network to build a prediction model.

6. The laser power intelligent control method for 3D printing according to claim 1, characterized in that: The method uses the initial laser power setting value of each layer or each area given by the prediction result as the initial power input, and drives the laser generator to start the printing operation of the current layer or area according to the setting value, including: Extracting preliminary laser power setting values ​​corresponding to the current printing layer and each area in the layer from the prediction results; The laser power is controlled by adjusting the applied voltage to control the output light intensity. The required laser power setting value P is known. pre , and the light-to-electricity conversion efficiency η of the laser generator, the required input light intensity I is obtained according to the relationship between power and light intensity pre : Where A is the cross-sectional area of ​​the laser beam; Then, according to the Pockels effect formula, the corresponding applied voltage V is calculated. pre : Among them, V π is the half-wave voltage, I0 is the reference light intensity, and arcsin(·) converts the light intensity ratio into the corresponding voltage value; The calculated voltage value is applied to the electro-optical modulation element of the laser generator, driving the laser generator to output laser according to the power setting value to start printing the current layer or area.

7. The laser power intelligent control method for 3D printing according to claim 1, characterized in that: The method further comprises: using the initial laser power setting value of each layer or each area given by the prediction result as the initial power input, and driving the laser generator to start the printing operation of the current layer or area according to the setting value; When driving the laser generator to start printing, a synchronous clock signal is started. If the scanning speed of the printing device is v scan , with a resolution of r res , then the synchronous clock signal frequency f sync Can be set to: f sync =v scan ·r res ; During the printing process, sensors are used to continuously collect real-time data, including at least the actual output power of the laser and the ambient temperature of the current printing area. The power error is calculated by comparing the actual output power with the set power. Determine whether the power error exceeds the preset allowable error range. If so, trigger the alarm mechanism and perform power compensation according to the error size; Monitor the ambient temperature of the printing area. If the temperature changes beyond the temperature threshold, printing is paused and the printing is continued after the temperature drops below the temperature threshold.

8. Laser power intelligent control system for 3D printing, characterized in that: The laser power intelligent control system for 3D printing includes a database establishment module, a data acquisition module, a laser power prediction module, a printing operation module and a dynamic adjustment module, wherein: Establish a database module to obtain the thermophysical parameters of 3D printing materials and the structural characteristics of different types of 3D models, and establish a 3D model information database; The data acquisition module is used to collect the printing environment temperature, energy distribution in the laser action area, and material composition change information in real time through sensors arranged around the printing platform to obtain the original printing data; A laser power prediction module is used to read the 3D model information database, combine the original printing data, and use a prediction model based on finite element analysis and convolutional neural network to pre-calculate the laser power to obtain a prediction result; A printing operation module, used to use the preliminary laser power setting value of each layer and each area given by the prediction result as the initial power input, and drive the laser generator to start the printing operation of the current layer or area according to the setting value; The dynamic adjustment module is used to collect the molten pool status and the molding quality information of the printed layer in real time to obtain the actual molding quality parameters, analyze the actual molding quality parameters, and dynamically adjust the laser power according to the deviation size and direction to achieve 3D printing molding, wherein the molding quality information at least includes the molten pool size, solidification rate and interlayer flatness.

9. The laser power intelligent control system for 3D printing according to claim 8, characterized in that: The data acquisition module includes a temperature measurement submodule, an energy measurement submodule, a material monitoring submodule and an acquisition submodule, wherein: The temperature measurement submodule is used to use a thermistor as a temperature sensor, apply a constant current to the thermistor, measure the voltage across the thermistor, obtain the current ambient temperature according to Ohm's law, and continuously collect temperature data; The energy measurement submodule is used to use an optical power meter based on the photoelectric effect as an energy sensor to divide the laser scanning area into multiple small squares. The optical power meter quickly moves to the center of each square and stays there for 0.1 seconds to measure and record the laser power value at that point. This cycle is repeated to construct an energy distribution matrix of the entire laser action area. The material monitoring submodule is used to monitor the changes in material composition in real time using a material composition monitor. For metal powder materials, X-ray fluorescence spectroscopy is used, and for organic polymer materials, infrared spectroscopy is used. The material composition change data monitored each time is recorded; The acquisition submodule is used to obtain the printing environment temperature, the energy distribution of the laser action area and the material composition change information in real time to obtain the original printing data.

10. The laser power intelligent control system for 3D printing according to claim 8, characterized in that: The laser power prediction module includes a discretization processing submodule, an adoption submodule, a determination submodule, a first calculation submodule and a second calculation submodule, wherein: The discretization processing submodule is used to discretize the 3D printing model, divide the 3D printing model into multiple small units, and assign corresponding thermal conductivity properties to each unit according to the thermophysical parameters of the 3D printing material; A submodule is used to use laser as a point heat source input. According to the law of conservation of energy, within the time interval Δt, the heat entering the unit, the change in the unit's own stored heat, and the heat flowing out of the unit satisfy the following relationship: Where ρ is the density, c is the specific heat, V is the unit volume, ΔT is the change in unit temperature within Δt, is the heat flow from j neighboring cells, m is the number of neighboring cells into which the heat flow flows, is the heat flow to k neighboring cells, n is the number of neighboring cells from which the heat flow flows, and Δx is the distance in the direction of heat conduction; A determination submodule is used to obtain energy distribution from the energy distribution of the laser action area in the original printing data, and determine the heat flow input of each unit at different times according to the laser scanning path, speed and energy distribution; The first calculation submodule is used to simulate the heat transfer process in the model during laser scanning through iterative thermal balance, calculate the energy input required for different areas of the model to reach the expected melting temperature, and obtain the energy density requirement E corresponding to each unit. d : Where t is the time required to reach the melting temperature, is the heat entering the unit during the i-th time interval; The second calculation submodule is used to obtain the calculated energy density requirement value to constitute the preliminary output result of the finite element analysis, determine the energy distribution required based on the physical heat conduction process, and perform laser power pre-calculation in combination with the prediction model to obtain the prediction result.

Images