3D printer visual leveling method and system

Abstract

The application discloses a 3D printer visual leveling method and system, and the method comprises the following steps: a camera is used to shoot a hot bed platform of a 3D printer to obtain image data of the surface of the hot bed platform, the image data comprises a plurality of visual leveling bars printed on the hot bed platform as a reference datum, a set of orthogonal intersecting line grids are formed, the visual leveling bars comprise a series of position reference lines and correspond to a preset coordinate system on the hot bed platform; the image data is processed to extract a reference line feature point set in the image; the deviation of each feature point in the reference line feature point set relative to a preset reference line is calculated, and a hot bed deformation model for describing the vertical height deviation of the hot bed platform is fitted and generated; the adjustment amount for leveling is determined according to the deviation and the hot bed deformation model; the adjustment amount is transmitted to a leveling execution mechanism through a communication interface to drive corresponding mechanical structures to realize automatic leveling of the hot bed platform. According to the embodiment of the application, the state of the hot bed platform can be comprehensively monitored and automatically leveled, and the reliability and printing quality of 3D printing are significantly improved.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of 3D printing, in particular to a 3D printer visual leveling method and system. BACKGROUND

[0002] With the rapid development of 3D printing technology, the application range of 3D printers is continuously expanding, covering industrial manufacturing, artistic creation, medical models, architectural design and other fields. The printing quality and efficiency of 3D printers largely depend on the flatness and stability of their hot bed platforms. Accurate leveling of the hot bed platform is one of the core factors to ensure the quality of printed products, especially in large-size and high-precision printing tasks, the accuracy of leveling directly affects the printing effect and the physical properties of the finished product.

[0003] Traditional hot bed leveling methods mainly rely on manual adjustment, which not only consumes time and effort, but also is easily affected by the skill level of the operator, resulting in inaccurate leveling. In addition, manual leveling is difficult to realize real-time monitoring and feedback, and may cause hot bed deformation or deviation during the printing process, leading to printing failure or unqualified finished products. Especially in long-time and large-scale printing processes, temperature changes of the hot bed, material shrinkage and external environmental factors can all cause uneven deformation of the hot bed, which makes the traditional leveling method more inadequate. SUMMARY

[0004] The purpose of the present application is to provide a 3D printer visual leveling method and system to solve the problems in the prior art, which can realize comprehensive monitoring and automatic leveling of the hot bed platform state, and significantly improve the reliability and printing quality of 3D printing.

[0005] One embodiment of the present application provides a 3D printer visual leveling method, the method comprising:

[0006] The hot bed platform of the 3D printer is photographed by a camera to obtain image data of the hot bed platform surface, the image data including a plurality of visual leveling bars printed on the hot bed platform as reference datum, forming a set of orthogonal intersecting line grids, the visual leveling bars including a series of position reference lines and corresponding to a preset coordinate system on the hot bed platform;

[0007] The image data is processed to extract a set of reference line feature points in the image;

[0008] The deviation of each feature point in the set of reference line feature points relative to the preset reference line is calculated, and a hot bed deformation model for describing the vertical height deviation of the hot bed platform is fitted and generated;

[0009] According to the deviation and the hot bed deformation model, the adjustment amount for leveling is determined;

[0010] transmit the adjustment amount to a leveling actuator through a communication interface to drive a corresponding mechanical structure to realize automatic leveling of the hot bed platform.

[0011] Optionally, the set of reference line feature points includes intersection points, end points or other specific salient points on the reference line.

[0012] Optionally, the calculation of the deviation amount of each feature point in the set of reference line feature points relative to the preset reference line includes:

[0013] According to the actual measurement position coordinates of each feature point, the offset amount of each feature point in the x-axis and y-axis directions relative to the preset ideal reference position of the feature point is calculated respectively.

[0014] Optionally, the fitting generates a hot bed deformation model, including:

[0015] The quadratic equation fitting generates a hot bed deformation model, wherein the quadratic equation contains fitting parameters and hot bed center coordinates, and the fitting parameters are obtained by least squares fitting.

[0016] Optionally, the determination of the adjustment amount for leveling according to the deviation amount and the hot bed deformation model includes:

[0017] The gradient information of the hot bed deformation model is calculated, and the adjustment component of each spatial axis is derived using the gradient information and the deviation amount.

[0018] Another embodiment of the present application provides a 3D printer visual leveling system, the system comprising:

[0019] The acquisition module is configured to capture the hot bed platform of the 3D printer through the camera, and acquire image data of the surface of the hot bed platform, wherein the image data includes a plurality of visual leveling bars printed on the hot bed platform as a reference datum, forming a set of orthogonal intersecting line grids, and the visual leveling bars include a series of position reference lines and correspond to a preset coordinate system on the hot bed platform.

[0020] The extraction module is configured to process the image data and extract a set of reference line feature points in the image.

[0021] The fitting module is configured to calculate the deviation amount of each feature point in the set of reference line feature points relative to the preset reference line, and fit to generate a hot bed deformation model for describing the vertical height deviation of the hot bed platform.

[0022] The determination module is configured to determine the adjustment amount for leveling according to the deviation amount and the hot bed deformation model.

[0023] A leveling module is configured to transmit the adjustment amount to a leveling actuator through a communication interface to drive a corresponding mechanical structure to realize automatic leveling of the hot bed platform.

[0024] Yet another embodiment of the present application provides a storage medium having a computer program stored therein, wherein the computer program is configured to execute the method described in any of the above embodiments when running.

[0025] Yet another embodiment of the present application provides an electronic device comprising a memory having a computer program stored therein and a processor configured to execute the computer program to perform the method described in any of the above embodiments.

[0026] Compared with the prior art, the 3D printer visual leveling method provided by the present application can realize comprehensive monitoring and automatic leveling of the hot bed platform by shooting the hot bed platform of the 3D printer through a camera, obtaining image data of the surface of the hot bed platform, the image data comprising a plurality of visual leveling bars printed on the hot bed platform as a reference datum, forming a set of orthogonal intersecting line grids, the visual leveling bars comprising a series of position reference lines and corresponding to a preset coordinate system on the hot bed platform, processing the image data, extracting a reference line feature point set in the image, calculating the deviation of each feature point in the reference line feature point set relative to a preset reference line, and fitting to generate a hot bed deformation model for describing the vertical height deviation of the hot bed platform, determining an adjustment amount for leveling according to the deviation and the hot bed deformation model, and transmitting the adjustment amount to a leveling actuator through a communication interface, thereby realizing comprehensive monitoring and automatic leveling of the hot bed platform, and significantly improving the reliability and printing quality of 3D printing. BRIEF DESCRIPTION OF DRAWINGS

[0027] Figure 1 A hardware structure block diagram of a computer terminal for the 3D printer visual leveling method provided by the embodiment of the present application is provided.

[0028] Figure 2 A flowchart of the 3D printer visual leveling method provided by the embodiment of the present application is provided.

[0029] Figure 3 A structure diagram of the 3D printer visual leveling system provided by the embodiment of the present application is provided. DETAILED DESCRIPTION

[0030] The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present application, and cannot be interpreted as a limitation of the present application.

[0031] The embodiment of the present application first provides a 3D printer visual leveling method, which can be applied to an electronic device such as a computer terminal, specifically a general computer, etc.

[0032] The following detailed explanation uses a computer terminal as an example. Figure 1 This is a hardware structure block diagram of a computer terminal for a 3D printer visual leveling method provided in an embodiment of the present invention. (See diagram below.) Figure 1 As shown, a computer terminal may include one or more ( Figure 1 Only one is shown in the diagram. A processor 102 (which may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.) and a memory 104 for storing data are also shown. Optionally, the computer terminal may further include a transmission device 106 for communication functions and an input / output device 108. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the computer terminal described above. For example, the computer terminal may also include components that are more complex than those described above. Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0033] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / modules corresponding to the 3D printer visual leveling method in this embodiment. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, thereby implementing the above-described method. The memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to a computer terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0034] The transmission device 106 is used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by a communication provider for the computer terminal. In one example, the transmission device 106 includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission device 106 may be a Radio Frequency (RF) module, used for wireless communication with the Internet.

[0035] See Figure 2 The present invention provides a visual leveling method for a 3D printer, which may include the following steps:

[0036] S201, capturing the hot bed platform of the 3D printer through a camera to obtain image data of the surface of the hot bed platform, the image data including a plurality of visual leveling bars printed on the hot bed platform as reference bases, forming a set of orthogonal intersecting line grids, the visual leveling bars including a series of position reference lines corresponding to a preset coordinate system on the hot bed platform;

[0037] The 3D printer visual leveling method of the present application first captures the hot bed platform of the 3D printer through a high-resolution camera to obtain image data of the hot bed surface. These image data contain a plurality of visual leveling bars printed on the hot bed platform to form a set of orthogonal intersecting line grids. Each visual leveling bar is provided with a series of position reference lines, which form visible marks in the image and can be used as reference bases for subsequent image processing. In this way, the geometric characteristics of the hot bed surface can be accurately determined to make necessary measurements and calculations for subsequent leveling.

[0038] The image data is used to obtain the state information of the hot bed platform, laying the foundation for automatic leveling. This visual-based monitoring method can effectively identify and analyze the geometric shape and deformation of the hot bed. Compared with the traditional manual leveling method, this method can provide higher accuracy and faster feedback, so that the 3D printer can automatically adjust the flatness of the hot bed during printing, thereby significantly improving the printing quality and accuracy of the finished product. The design of this step also provides a reliable data source for subsequent feature extraction and deviation calculation, which is a key link in the entire leveling process.

[0039] In actual implementation, a high-definition camera can be used to capture images of the hot bed platform from multiple angles, and after image acquisition, geometric feature recognition is performed through image processing software. Image recognition technology is used to locate the visual leveling bars and identify their intersection points and end points, and coordinate conversion is performed based on the image data to compare the real coordinate system of the hot bed platform with the preset coordinate system. This process can use existing image processing libraries such as OpenCV for image preprocessing, feature point extraction, and coordinate calculation to finally generate an accurate data set for subsequent deviation calculation.

[0040] Specifically, the reference line feature point set includes intersection points, end points or other specific significant points on the reference line. These feature points play a key role in the image and can provide accurate geometric positioning information. The intersection point is a point formed by the intersection of two or more reference lines, which has high stability and recognition degree; the end point is the starting or ending position of each reference line, which is also an important positioning reference; and the other specific significant points can be key positions set according to the shape or printing features of the leveling bar.

[0041] The presence of these feature points makes the geometric deformation analysis of the hot bed platform more accurate. By extracting the salient points on the reference lines, the deviation of these points from the ideal reference position can be effectively calculated, providing the necessary data support for the modeling and leveling calculation of the hot bed deformation. Accurate feature point extraction can reduce calculation errors, improve the reliability of the leveling process, and thus ensure the quality and accuracy of the finished product in the 3D printing process. The selection of feature points also provides a good foundation for subsequent fitting and offset adjustment, ensuring efficient and stable leveling effect in different printing environments and conditions. By identifying these salient points, the reliability and accuracy of the entire visual leveling system are effectively improved.

[0042] S202, processing the image data to extract a set of reference line feature points in the image;

[0043] After obtaining the image data of the hot bed platform, the next step is to process these image data to extract a set of reference line feature points. This processing process usually includes image preprocessing, feature detection and feature point extraction. The image preprocessing step may include denoising, contrast enhancement, etc. to improve the accuracy of subsequent feature detection. The feature detection algorithm will identify the reference lines in the image, analyze the geometric shape and arrangement of the lines, and finally extract important points such as intersection points and endpoints to form a set of reference line feature points. These feature points will be used for subsequent deviation calculation and fitting of the hot bed deformation model.

[0044] The purpose of extracting the set of reference line feature points is to obtain the relationship between the hot bed surface geometry and the preset coordinate system. This set provides key information that allows the system to calculate the deviation between each feature point and the ideal reference line. With accurate feature point data, the system can efficiently identify the deformation and errors of the hot bed, providing a reliable data foundation for subsequent automatic leveling algorithms. This step is the core link to achieve high-precision automatic leveling, which helps to improve the printing quality and overall performance of the 3D printer.

[0045] In specific implementation, image processing libraries such as OpenCV can be used for feature point extraction. First, the image is converted to grayscale to reduce computational complexity. Then, edge detection algorithms such as Canny operator are used to identify the lines on the hot bed platform surface. Next, the straight line segments identified by Hough transform and other techniques are converted into line models. By analyzing the geometric relationship of these lines, the intersection points and endpoints are located, and these salient points are organized into a set of feature points. Finally, these feature points are stored and prepared for subsequent deviation calculation and hot bed deformation model generation to complete the entire automatic leveling process.

[0046] S203, calculate the deviation of each feature point in the reference line feature point set relative to the preset reference line, and generate a hot bed deformation model for describing the vertical height deviation of the hot bed platform by fitting;

[0047] After extracting the reference line feature point set, the next step is to calculate the deviation of each feature point relative to the preset reference line. The core of this process is to compare the actual measured feature point coordinates with the preset ideal reference position to quantify the difference between them. Through these calculations, the specific deformation of the hot bed platform can be determined. Then, further fitting of the hot bed deformation model is carried out, which can describe the vertical height deviation of the hot bed platform by reflecting its morphological changes through mathematical expressions.

[0048] By calculating the deviation and generating the hot bed deformation model, a comprehensive analysis of the current situation of the hot bed can be achieved, providing a scientific basis for subsequent leveling operations. The implementation of this step ensures high precision and high reliability in the printing process, so that the quality of 3D printing products can be guaranteed. Determining the deviation of the hot bed platform and combining the model can help the system accurately calculate the adjustment amount that should be applied, thereby realizing automatic leveling, reducing manual intervention, and improving leveling efficiency and accuracy.

[0049] Specifically, according to the actual measurement position coordinates of each feature point, the deviation of each feature point in the x-axis and y-axis directions relative to the preset ideal reference position of the feature point can be calculated respectively.

[0050] In this process, according to the actual measurement position coordinates of each feature point, the deviation of the two positions in the x-axis and y-axis directions relative to the preset ideal reference position of the feature point is calculated respectively. The main goal of this step is to provide an accurate deviation value for each feature point to quantify their position changes in the two-dimensional plane. By comparing the actual coordinates of each feature point with the ideal coordinates, the deformation of the hot bed surface in these two directions can be clearly shown.

[0051] By calculating the deviation, the state of the hot bed platform can be effectively described, so that the system can accurately identify which areas have deviations. This quantification of deviation provides data support for subsequent leveling decisions, ensuring that the system can respond quickly and make adjustments. Ultimately, the overall leveling accuracy will be significantly improved, resulting in an improvement in printing quality. A deviation can be:

[0052]

[0053]

[0054] where, is the x-coordinate of the i-th feature point The x-coordinate relative to the preset ideal reference position of this feature point The offset, The ordinate of the i-th feature point The ordinate of the feature point relative to its preset ideal reference position. The offset.

[0055] Specifically, a hotbed deformation model can be generated by fitting a quadratic equation, wherein the quadratic equation includes fitting parameters and the coordinates of the hotbed center, and the fitting parameters are obtained by fitting using the least squares method. A hotbed deformation model can be expressed as:

[0056]

[0057] This formula is designed to flexibly represent the deformation characteristics of a hot bed using a quadratic function. In a three-dimensional coordinate system, the changes in a hot bed can be nonlinear; therefore, using a quadratic function can accurately capture complex deformation patterns. This form can reflect both the local curvature changes of the hot bed and can be flexibly adapted to various actual situations through parameter adjustments, making it an effective means of describing hot bed deformation. Among these, For fitting parameters, The coordinates are the center coordinates of the heated bed.

[0058] Z(x,y): Represents the height value at a specific point (x, y). It is the output of the model and reflects the height of the hotbed surface at a given location. a: Represents the curvature of the hotbed along the x-axis, controlling the degree of curvature of the hotbed surface relative to the x-axis. If a is positive, the hotbed exhibits an upward convex shape in this direction; if negative, it is downward concave. This parameter is crucial for describing the spatial shape of the hotbed. b: Represents the curvature of the hotbed along the y-axis. Similar to a, it controls the degree of curvature of the hotbed surface along the y-axis. Positive and negative values ​​have the same meaning as in a, affecting the representation of the hotbed's curvature. (x_0, y_0): The coordinates of the hotbed center, serving as a reference point for the model to align offset calculations with the actual coordinate system. Setting this parameter allows the model to exhibit deformation around the hotbed center and provides a basis for offset calculations. c: Reference height, representing the height value of the hotbed in a flat state. It is equivalent to a constant term in the model, providing a reference for the height of the entire model, making comparisons convenient during measurement.

[0059] In the present invention, the step of generating the hot bed deformation model by quadratic equation fitting is mainly to mathematically model the extracted offset of the reference line feature points. The required quadratic equation form is as follows, where Z represents the height value at a specific coordinate point (x, y). The fitting parameters a and b here represent the curvature of the hot bed in the x and y axis directions, and c represents the reference height of the hot bed. These parameters are estimated by the least squares method, which aims to minimize the squared error between the predicted value and the actual measured value, thereby obtaining a set of optimal fitting parameters.

[0060] The purpose of generating the hot bed deformation model is to accurately describe the height change of the hot bed through mathematical expressions, and to convert the leveling requirement into a specific mathematical problem. This model can fully reflect the overall deformation state of the hot bed, facilitating subsequent leveling decisions and adjustment amount calculations. Through the fitted model, a height prediction value can be provided for each point, so that in actual leveling operations, the adjustment amount required for leveling can be quickly judged based on the relationship between the model output and the actual measured value. This not only improves the accuracy of automatic leveling, but also effectively avoids inaccurate leveling caused by human experience errors, thereby significantly improving the success rate of 3D printing.

[0061] In the specific implementation process, data processing software such as MATLAB or Python's NumPy can be used to fit the hot bed deformation model. First, collect the coordinates (x_i, y_i) and corresponding height offsets Z_i of the extracted feature points. Then, construct a target function about (a, b, c), which is the sum of squared errors between the offset and the model prediction value. Then, use the optimization algorithm of the least squares method to solve this target function, thereby obtaining the best fitting parameters. Finally, the obtained quadratic equation can effectively reflect the actual deformation of the hot bed, providing the necessary mathematical basis for subsequent adjustment amount calculations.

[0062] S204, determining an adjustment amount for leveling according to the offset and the hot bed deformation model;

[0063] According to the calculated offset and the hot bed deformation model, the system can determine the adjustment amount required for leveling. The core of this step is to compare the actual measured data with the constructed model to quantify the differences between the current hot bed state and the ideal state. By analyzing these differences, the system can calculate the specific adjustment value required to restore the hot bed to the ideal level. The adjustment amount is usually output in the form of x, y, z direction change, so as to be adjusted by the leveling actuator.

[0064] By determining the adjustment amount of leveling, the 3D printer can realize automatic leveling in actual operation, ensuring that the height and level state of the hot bed always remain within the predetermined standard. In this way, the printing quality can be significantly improved, and the printing failure or product quality variation caused by uneven hot bed can be reduced. At the same time, the automation of the leveling process can reduce the need for manual intervention and improve work efficiency.

[0065] Specifically, the gradient information of the hot bed deformation model can be calculated, and the adjustment component of each spatial axis can be derived using the gradient information and the deviation amount.

[0066] In this process, by calculating the gradient information of the hot bed deformation model, the system can extract the change trend of the hot bed surface in each coordinate direction. The key to this step is to calculate the partial derivative of the hot bed deformation model to obtain the change rate of each spatial axis (x, y, z). Then, combined with the gradient information and the deviation amount calculated before, the system can derive the adjustment component in each direction. These adjustment components will be used to guide the leveling actuator to accurately move the hot bed to achieve the ideal flatness. An adjustment component can include:

[0067]

[0068]

[0069]

[0070] These formulas are designed to derive the actual adjustment amount from the hot bed deformation model. By combining the offset amount with the gradient information of the model, the required adjustment direction and amplitude can be more accurately determined. This method considers the influence of each feature point on the overall leveling, ensuring the scientificity and rationality of the leveling process.

[0071] wherein, v_x is the adjustment component of the hot bed platform in the x-axis, which reflects how to compensate for the overall deviation in the x direction by moving the hot bed to achieve flatness. xi is the horizontal coordinate of the i-th feature point dev_x is the offset of the horizontal coordinate of the feature point relative to the preset ideal reference position, is the hot bed deformation model, v_y is the adjustment component of the hot bed platform in the y-axis, which represents the adjustment component of the hot bed in the y-axis direction, and its meaning is similar to v_x, ensuring compensation in the y direction. yi is the vertical coordinate of the i-th feature point dev_y is the offset of the vertical coordinate of the feature point relative to the preset ideal reference position, v_z is the adjustment component of the hot bed platform in the z-axis, , , The corresponding adjustment ratio coefficient affects the magnitude of the adjustment component when actually applied to the actuator. This coefficient is used to adjust the response sensitivity to ensure smooth and effective adjustment process.

[0072] By utilizing the gradient information of the thermal bed deformation model, the system can more accurately judge and reflect the local changes of the thermal bed, thereby achieving fine leveling. This method significantly improves the accuracy of leveling, ensuring that it can effectively cope with the height differences that may exist in different areas of the thermal bed, avoiding excessive compensation or insufficient compensation caused by overall adjustment. Ultimately, it improves the quality and efficiency of 3D printing.

[0073] S205, transmitting the adjustment amount to the leveling actuator through the communication interface to drive the corresponding mechanical structure to realize automatic leveling of the thermal bed platform.

[0074] After determining the adjustment amount for leveling, the system transmits these adjustment amounts to the leveling actuator through the communication interface. The communication interface can be established through cable, wireless network or other appropriate communication means to ensure the real-time and accuracy of data transmission. After receiving these adjustment amounts, the leveling actuator will make corresponding adjustments to the thermal bed platform according to specific settings and parameters in a mechanical manner. This process usually involves driving devices such as servo motors or stepper motors, which control the height and angle of the thermal bed to achieve automatic leveling of the thermal bed. The leveling process not only provides real-time feedback on the adjustment, but also dynamically monitors the state of the thermal bed to ensure that the final position meets the preset standards.

[0075] Specifically, the communication interface can use serial communication protocols (such as UART), CAN bus or wireless communication protocols (such as Wi-Fi, Bluetooth, etc.) to realize connection with the leveling actuator. At the hardware level, the leveling actuator may be equipped with a servo motor, combined with high-precision sensors (such as photoelectric sensors or ultrasonic sensors), to perform fine tuning of the thermal bed through a closed-loop control system (i.e. real-time adjustment of output according to feedback signals). One implementation can include:

[0076] 11. Obtain adjustment amount: After completing the calculation of the thermal bed deformation model, the system transmits the calculated leveling adjustment amounts v_x, v_y, v_z to the leveling actuator. These adjustment amounts represent the specific adjustment requirements of the thermal bed on the three spatial axes.

[0077] 12. Set up mechanical drive system: Typically, the leveling actuator will use a servo motor or a stepper motor to control the movement of the thermal bed. To ensure the accuracy of the adjustment, the motor needs to be calibrated to ensure a known range of motion and a corresponding height change for each step of rotation. This can be configured through the motor controller.

[0078] 13. Calculate motor steps: Based on the transmitted adjustment, the system needs to convert these amounts into the number of steps the motor needs to rotate. For example, if v_x needs to be adjusted by 0.5mm, and the motor can lift 0.01mm per 1° rotation, then the required steps can be calculated using the following formula: v_x divided by the step size per 1° rotation, which is 50 steps.

[0079] 14. Perform leveling: Based on the calculated steps, the system sends a signal to the motor controller, instructing it to rotate the required number of steps in the corresponding direction. For example, if v_x = 0.5mm, then the servo motor moves 50 steps up on the x-axis, and if v_y = -0.3mm, then it moves 30 steps down on the y-axis.

[0080] 5. Feedback adjustment: After completing the initial adjustment, the system performs a feedback collection. This can be done by measuring the current height of the hot bed using sensors such as height sensors, laser sensors, etc. Based on the latest height and the pre-set ideal position, it calculates again whether further adjustment is needed. If needed, steps 13 and 14 are repeated until the ideal state is reached.

[0081] For example, suppose during a printing process, after image processing and model fitting, the system calculates the adjustment amounts as follows: v_x = 0.5mm, v_y = -0.3mm, and v_z = 0.

[0082] 21. First, the system determines that the motor lifts 0.01mm per 1° rotation, and then calculates:

[0083] For v_x: steps = 0.5mm / 0.01mm = 50;

[0084] For v_y: steps = -0.3mm / 0.01mm = -30;

[0085] 22. Next, the system sends instructions to the motor:

[0086] x-axis motor: move 50 steps up;

[0087] y-axis motor: move 30 steps down;

[0088] z-axis motor remains stationary because v_z = 0.

[0089] 23. The motor begins to perform leveling, and after completing these motor steps, the system measures the current height of the hot bed using sensors, assuming the measured height is Z_{current}.

[0090] 24. The system compares the new height with the ideal height Z_{ideal} and checks if the preset standard is reached. If Z_{current} has not yet reached Z_{ideal}, a new adjustment amount is calculated and steps 21 to 24 are re-executed. In this way, with the precise control of the servo motor, the 3D printer can achieve fast and accurate hot bed leveling. The automatic leveling process before each print significantly improves the reliability and quality of printing, reducing human error and burden.

[0091] By transmitting the adjustment amount to the leveling actuator and achieving automatic leveling, the 3D printer can significantly improve its work efficiency and printing quality. The automated leveling process avoids errors caused by human intervention, so that each print can be carried out in an ideal hot bed state, reducing the risk of printing failure due to hot bed inequality. In addition, the real-time adjustment and feedback mechanism can also enhance the adaptive ability of the system, so that the printer can always maintain efficient and stable printing quality under different environmental conditions and usage. This is particularly important for industrial applications or complex model printing that require high precision, which can improve overall production efficiency and consistency of finished products.

[0092] As can be seen, by shooting the hot bed platform of the 3D printer with a camera, image data of the hot bed platform surface is obtained, the image data including a plurality of visual leveling bars printed on the hot bed platform as reference datum, forming a set of orthogonal intersecting line grids, the visual leveling bars including a series of position reference lines and corresponding to a preset coordinate system on the hot bed platform; the image data is processed to extract a set of reference line feature points in the image; the deviation of each feature point in the set of reference line feature points relative to the preset reference line is calculated, and a hot bed deformation model for describing the vertical height deviation of the hot bed platform is fitted and generated; the adjustment amount for leveling is determined according to the deviation and the hot bed deformation model; the adjustment amount is transmitted to the leveling actuator through a communication interface, so that comprehensive monitoring and automatic leveling of the hot bed platform state can be achieved, significantly improving the reliability and printing quality of 3D printing.

[0093] Another embodiment of the present application provides a 3D printer visual leveling system, referring to Figure 3 , the system can include:

[0094] The acquisition module 301 shoots the hot bed platform of the 3D printer with a camera to obtain image data of the hot bed platform surface, the image data including a plurality of visual leveling bars printed on the hot bed platform as reference datum, forming a set of orthogonal intersecting line grids, the visual leveling bars including a series of position reference lines and corresponding to a preset coordinate system on the hot bed platform;

[0095] An extraction module 302 is configured to process the image data and extract a reference line feature point set in the image.

[0096] A fitting module 303 is configured to calculate a deviation of each feature point in the reference line feature point set relative to a preset reference line, and fit to generate a hot bed deformation model for describing a vertical height deviation of the hot bed platform.

[0097] A determination module 304 is configured to determine an adjustment amount for leveling according to the deviation and the hot bed deformation model.

[0098] A leveling module 305 is configured to transmit the adjustment amount to a leveling actuator through a communication interface, so as to drive a corresponding mechanical structure to realize automatic leveling of the hot bed platform.

[0099] It can be seen that the hot bed platform of the 3D printer is photographed by the camera to obtain image data of the hot bed platform surface, the image data includes a plurality of visual leveling bars printed on the hot bed platform as a reference datum, forms a set of orthogonal intersecting line grids, the visual leveling bar includes a series of position reference lines and corresponds to a preset coordinate system on the hot bed platform; the image data is processed to extract a reference line feature point set in the image; a deviation of each feature point in the reference line feature point set relative to a preset reference line is calculated, and a hot bed deformation model for describing a vertical height deviation of the hot bed platform is fitted; an adjustment amount for leveling is determined according to the deviation and the hot bed deformation model; the adjustment amount is transmitted to a leveling actuator through a communication interface, so as to realize comprehensive monitoring and automatic leveling of the hot bed platform state, and significantly improve the reliability and printing quality of 3D printing.

[0100] The embodiment of the present application also provides a storage medium, and the storage medium stores a computer program, wherein the computer program is set to execute the steps in any one of the method embodiments.

[0101] Specifically, in the embodiment, the storage medium can be set to store a computer program for executing the following steps:

[0102] S201, the hot bed platform of the 3D printer is photographed by the camera to obtain image data of the hot bed platform surface, the image data includes a plurality of visual leveling bars printed on the hot bed platform as a reference datum, forms a set of orthogonal intersecting line grids, the visual leveling bar includes a series of position reference lines and corresponds to a preset coordinate system on the hot bed platform;

[0103] S202, the image data is processed to extract a reference line feature point set in the image.

[0104] S203, calculate the deviation of each feature point in the reference line feature point set relative to the preset reference line, and generate a hot bed deformation model for describing the vertical height deviation of the hot bed platform by fitting;

[0105] S204, determine the adjustment amount for leveling according to the deviation and the hot bed deformation model;

[0106] S205, transmit the adjustment amount to the leveling actuator through the communication interface to drive the corresponding mechanical structure to realize the automatic leveling of the hot bed platform.

[0107] It can be seen that the camera is used to shoot the hot bed platform of the 3D printer to obtain image data of the hot bed platform surface, the image data includes a plurality of visual leveling bars printed on the hot bed platform as reference datum, forming a set of orthogonal intersecting line grids, the visual leveling bar includes a series of position reference lines and corresponds to a preset coordinate system on the hot bed platform; the image data is processed to extract a reference line feature point set in the image; the deviation of each feature point in the reference line feature point set relative to the preset reference line is calculated, and a hot bed deformation model for describing the vertical height deviation of the hot bed platform is generated by fitting; the adjustment amount for leveling is determined according to the deviation and the hot bed deformation model; the adjustment amount is transmitted to the leveling actuator through the communication interface, so that the overall monitoring and automatic leveling of the hot bed platform state can be realized, and the reliability and printing quality of 3D printing are significantly improved.

[0108] The embodiment of the application also provides an electronic device including a memory and a processor, the memory stores a computer program, and the processor is configured to run the computer program to execute the steps in any of the above method embodiments.

[0109] Specifically, the above electronic device can further include a transmission device and an input / output device, wherein the transmission device is connected to the above processor, and the input / output device is connected to the above processor.

[0110] Specifically, in the embodiment, the processor can be configured to execute the following steps through the computer program:

[0111] S201, the camera is used to shoot the hot bed platform of the 3D printer to obtain image data of the hot bed platform surface, the image data includes a plurality of visual leveling bars printed on the hot bed platform as reference datum, forming a set of orthogonal intersecting line grids, the visual leveling bar includes a series of position reference lines and corresponds to a preset coordinate system on the hot bed platform;

[0112] S202, the image data is processed to extract a reference line feature point set in the image;

[0113] S203, calculating a deviation amount of each feature point in the reference line feature point set relative to a preset reference line, and fitting to generate a hot bed deformation model for describing the vertical height deviation of the hot bed platform;

[0114] S204, determining an adjustment amount for leveling according to the deviation amount and the hot bed deformation model;

[0115] S205, transmitting the adjustment amount to a leveling execution mechanism through a communication interface to drive the corresponding mechanical structure to realize automatic leveling of the hot bed platform.

[0116] It can be seen that the hot bed platform of the 3D printer is photographed by the camera, and image data of the hot bed platform surface is obtained, the image data including a plurality of visual leveling bars printed on the hot bed platform as a reference datum, forming a set of orthogonal intersecting line grids, the visual leveling bars including a series of position reference lines and corresponding to a preset coordinate system on the hot bed platform; the image data is processed to extract a reference line feature point set in the image; a deviation amount of each feature point in the reference line feature point set relative to a preset reference line is calculated, and a hot bed deformation model for describing the vertical height deviation of the hot bed platform is fitted; an adjustment amount for leveling is determined according to the deviation amount and the hot bed deformation model; the adjustment amount is transmitted to a leveling execution through a communication interface, so that comprehensive monitoring and automatic leveling of the hot bed platform state can be realized, and the reliability and printing quality of 3D printing are significantly improved.

[0117] The above embodiments according to the drawings illustrate the structure, features and effects of the present application, and the above description is only the preferred embodiment of the present application, but the present application is not limited by the drawings, any change or modification within the concept of the present application, or equivalent embodiment within the scope of the description and drawings, should be within the protection scope of the present application.

Claims

1. A visual leveling method for a 3D printer, characterized in that, The method includes: The heated bed platform of the 3D printer is photographed by a camera to obtain image data of the heated bed platform surface. The image data includes multiple visual leveling strips printed on the heated bed platform as reference benchmarks to form a set of orthogonal intersecting line grids. The visual leveling strips include a series of position reference lines and correspond to a preset coordinate system on the heated bed platform. The image data is processed to extract a set of reference line feature points from the image; Calculate the deviation of each feature point in the reference line feature point set relative to the preset reference line, and fit and generate a hot bed deformation model to describe the hot bed platform's vertical displacement. Based on the deviation and the hot bed deformation model, determine the adjustment amount for leveling; The adjustment amount is transmitted to the leveling actuator through the communication interface to drive the corresponding mechanical structure to achieve automatic leveling of the heated bed platform; The process of generating a thermal bed deformation model by fitting includes: generating a thermal bed deformation model by fitting a quadratic equation, wherein the quadratic equation includes fitting parameters and thermal bed center coordinates, and the fitting parameters are obtained by fitting using the least squares method; The step of determining the adjustment amount for leveling based on the deviation and the thermal bed deformation model includes: calculating the gradient information of the thermal bed deformation model, and deriving the adjustment component of each spatial axis using the gradient information and the deviation.

2. The method according to claim 1, characterized in that, The set of reference line feature points includes: intersections, endpoints, or other specific salient points on the reference line.

3. The method according to claim 2, characterized in that, The calculation of the deviation of each feature point in the set of feature points of the reference line relative to the preset reference line includes: Based on the actual measured coordinates of each feature point, calculate the offset of each feature point relative to its preset ideal reference position in the x-axis and y-axis directions.

4. A 3D printer visual leveling system, characterized in that, The system includes: The acquisition module is used to capture images of the heated bed platform of the 3D printer using a camera, and acquire image data of the heated bed platform surface. The image data includes multiple visual leveling strips printed on the heated bed platform as reference benchmarks, forming a set of orthogonal intersecting line grids. The visual leveling strips include a series of position reference lines, which correspond to a preset coordinate system on the heated bed platform. The extraction module is used to process the image data and extract a set of reference line feature points from the image; The fitting module is used to calculate the deviation of each feature point in the set of feature points of the reference line relative to the preset reference line, and to fit and generate a hot bed deformation model to describe the hot bed platform's vertical displacement. The determining module is used to determine the adjustment amount for leveling based on the deviation amount and the hot bed deformation model; The leveling module is used to transmit the adjustment amount to the leveling actuator through a communication interface, so as to drive the corresponding mechanical structure to realize the automatic leveling of the heated bed platform; The process of generating a thermal bed deformation model by fitting includes: generating a thermal bed deformation model by fitting a quadratic equation, wherein the quadratic equation includes fitting parameters and thermal bed center coordinates, and the fitting parameters are obtained by fitting using the least squares method; The step of determining the adjustment amount for leveling based on the deviation and the thermal bed deformation model includes: calculating the gradient information of the thermal bed deformation model, and deriving the adjustment component of each spatial axis using the gradient information and the deviation.

5. The system according to claim 4, characterized in that, The set of reference line feature points includes: intersections, endpoints, or other specific salient points on the reference line.

6. The system according to claim 4, characterized in that, The calculation of the deviation of each feature point in the set of feature points of the reference line relative to the preset reference line includes: Based on the actual measured coordinates of each feature point, calculate the offset of each feature point relative to its preset ideal reference position in the x-axis and y-axis directions.

7. A storage medium, characterized in that, The storage medium stores a computer program, wherein the computer program is configured to execute the method of any one of claims 1-3 when it is run.

8. An electronic device comprising a memory and a processor, characterized in that, The memory stores a computer program, and the processor is configured to run the computer program to perform the method of any one of claims 1-3.

Images