Self-adaptive binder jet printing compensation method and device

Abstract

The invention discloses a self-adaptive binder jet printing compensation method and device, and relates to the technical field of additive manufacturing. The method comprises the following steps: preparing a test sample piece, measuring an actual characteristic size in the test sample piece, and calculating a size deviation value; calculating a target compensation amount corresponding to each preset design feature size according to the size deviation value, and establishing a compensation function; receiving a three-dimensional model of a to-be-printed part, performing hierarchical slicing processing on the three-dimensional model, and extracting contour geometric data of each layer; identifying a target feature size of a target region corresponding to each line segment unit extracted from the contour geometric data; inputting the target feature size into the compensation function to obtain a dynamic compensation value; the corresponding line segment units are subjected to offset processing according to the dynamic compensation values, and a compensated printing contour is generated; and planning a printing path according to the printing contour and controlling the printing equipment to execute printing operation. By implementing the technical scheme provided by the invention, the printing qualification rate and the production efficiency are effectively improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of additive manufacturing, and in particular to a self-adaptive binder jetting printing compensation method and device. BACKGROUND

[0002] Binder jetting metal printing is a technology that forms a green part by selectively jetting liquid binder to a powder bed through a nozzle, layer by layer, and then obtains a final part through post-processing. The dimensional accuracy of the green part directly determines the accuracy of the final sintered part. At present, in order to improve the accuracy of the green part, the industry generally uses a fixed offset compensation technology. That is, when generating a printing path, a fixed value offset (such as 0.2mm outward compensation) is performed on the design contour of the part to offset the edge distortion, shrinkage or expansion that may occur during printing and solidification.

[0003] However, this fixed value compensation strategy has significant defects. The binder penetration behavior, capillary effect and drying and solidification shrinkage of parts or features of different sizes (especially different feature sizes and volumes) are not the same. For example: large size solid part: the binder penetration path is long, the internal saturation is greatly different from the edge, and the drying shrinkage is relatively uniform but the total amount is large. Small features (such as thin-walled, sharp corners): the binder is easy to quickly penetrate to the bottom, and even penetrate into the powder, resulting in the actual size of the feature being smaller due to excessive soaking, or deforming due to too high binder content. Therefore, a method is needed to compensate for binder jetting printing based on size. SUMMARY

[0004] In order to solve the above technical problems, the present application provides a self-adaptive binder jetting printing compensation method and device.

[0005] In a first aspect of the present application, a self-adaptive binder jetting printing compensation method is provided, which adopts the following technical solution: Prepare test samples with multiple preset design feature sizes, measure the actual feature sizes of the green parts after printing and solidification of each feature region in the test samples, and calculate the size deviation values between each actual feature size and the corresponding preset design feature size; According to the size deviation values, calculate the target compensation amounts corresponding to each preset design feature size, and based on the preset design feature sizes and the target compensation amounts, establish a compensation function; Receive a three-dimensional model of a part to be printed and perform layer slicing processing on the three-dimensional model, and extract the contour geometry data of each layer after the layer slicing processing; Identify the target feature sizes of the target regions corresponding to each line segment unit from the contour geometry data; inputting the target feature size into the compensation function to obtain a dynamic compensation value; performing bias processing on the corresponding line segment unit according to the dynamic compensation value to generate a compensated printing contour; planning a printing path according to the printing contour and controlling a printing device to perform a printing task.

[0006] By adopting the above technical solution, the inherent defects of fixed compensation value unable to simultaneously adapt to different size features are effectively solved: according to the characteristics of long binder penetration path and large shrinkage total amount of large size entity part, appropriate compensation is given through size-compensation amount function to avoid insufficient compensation; according to the difficult problem of easy excessive penetration and deformation of small features, accurate compensation is provided through dynamic calculation to prevent excessive compensation. This method fundamentally overcomes the contradiction between insufficient compensation and excessive compensation of traditional method on a single part, significantly improves the size consistency of green part, makes different size features meet the design precision requirements, and greatly improves the printing qualified rate and production efficiency.

[0007] Optionally, the compensation function is established based on the preset design feature size and the target compensation amount corresponding to each preset design feature size, and the method comprises the following steps: obtaining the target compensation amount corresponding to the preset design feature size by taking the inverse of the size deviation value; using a linear regression algorithm to perform function fitting on the independent variable and the dependent variable, and obtaining the compensation function.

[0008] By adopting the above technical solution, the measured deviation is directly converted into a target compensation amount with clear physical meaning by using the inverse operation, ensuring the correctness of the compensation direction; further, the linear regression algorithm is used for function fitting, which can objectively extract the internal linear relationship between the feature size and the compensation amount from the experimental data, thereby establishing a robust and quantifiable compensation model. This method replaces the traditional manual experience setting in a data-driven manner, significantly improves the scientificity and prediction accuracy of the compensation function, provides a reliable theoretical basis for subsequent adaptive compensation, and fundamentally ensures that different size features can obtain optimal compensation values, and finally realizes the improvement of the overall precision of the green body.

[0009] Optionally, the three-dimensional model of the part to be printed is received and the three-dimensional model is subjected to layering and slicing processing, and the contour geometric data of each layer after the layering and slicing processing comprises: a plurality of two-dimensional cross-sectional layers are generated by layering the three-dimensional model along a pre-constructed direction according to a preset printing layer thickness parameter using a slicing algorithm; The target two-dimensional cross-section layer is subjected to contour recognition and extraction operation, and a closed contour line in the target two-dimensional cross-section layer is calculated, the target two-dimensional cross-section layer being any one of a plurality of two-dimensional cross-section layers; The geometric properties of the closed contour line are analyzed, and a plurality of line segment units contained in the closed contour line, a sequence of vertex coordinates of each line segment unit, and a connection topological relationship between each line segment unit are extracted; The plurality of line segment units, the sequence of vertex coordinates, and the connection topological relationship are combined to obtain the contour geometric data of the target two-dimensional cross-section layer.

[0010] By adopting the above technical solution, accurate and automatic conversion from a three-dimensional model to two-dimensional contour geometric data is realized. The process ensures the integrity and accuracy of the contour information of each cross-section layer through standardized slicing algorithm and contour extraction operation, and further analyzes and obtains the accurate coordinates and topological relationship of the line segment unit, thereby laying a solid data foundation for subsequent accurate identification of local feature sizes. This high-precision geometric data processing flow is a key prerequisite for realizing adaptive dynamic compensation, which ensures the reliability of the basis for compensation value calculation, thereby finally significantly improving the overall printing precision and shape fidelity of the green part.

[0011] Optionally, the target feature size of the target region corresponding to each line segment unit extracted from the contour geometric data includes: determining the geometric property type of the target printing region corresponding to the first target line segment unit, the geometric property type including width, diameter, or inner diameter, the first target line segment unit being any one of all line segment units extracted from the contour geometric data; calculating the specific size value of the target printing region under the geometric property type according to the first start point coordinate and the first end point coordinate of the first target line segment unit, the orientation of the adjacent line segment unit adjacent to the first target line segment unit, and the connection topological relationship; record the specific size value as the target feature size of the target region corresponding to the first target line segment unit.

[0012] By adopting the technical scheme, automatic and high-precision identification of local feature sizes of the contour is realized. The method can accurately adapt to diversified geometric features such as thin walls, holes and bosses by intelligently judging geometric attribute types and comprehensively utilizing line segment coordinates, adjacent line segment orientations and topological relations for accurate calculation. This process discards the traditional single or manually set size determination mode, dynamically calculates a representation size of each tiny feature most in line with the physical printing behavior, thereby providing accurate and reliable input data for subsequent dynamic compensation based on the size, and fundamentally guarantees effective execution of the adaptive compensation algorithm and size precision of the final green part.

[0013] Optionally, the offset processing of the corresponding line segment unit according to the dynamic compensation value to generate the compensated printing contour comprises: performing contour offset calculation on the second target line segment unit according to the dynamic compensation value corresponding to the second target line segment unit, to generate a new line segment unit after offset; connecting the new line segment unit after offset according to the connection topological relation in the contour geometric data, to obtain a closed compensation contour; combining all the compensation contours to obtain the compensated printing contour.

[0014] By adopting the technical scheme, accurate and adaptive geometric correction of the original design contour is realized. This process performs independent offset calculation according to the unique dynamic compensation value of each line segment unit, ensuring the local accuracy of the compensation amount; then, the offset line segments are reconnected into a smooth and closed contour according to the original connection topological relation, effectively avoiding problems such as contour self-intersection, breakage or redundant fragments that may be caused by traditional offset methods, and ensuring the geometric correctness and continuity of the compensated contour. The finally generated high-fidelity printing contour lays a solid foundation for planning a collision-free and efficient printing path, thereby directly guaranteeing the final printing quality and size precision of the green part.

[0015] Optionally, the contour offset calculation on the second target line segment unit according to the dynamic compensation value corresponding to the second target line segment unit to generate a new line segment unit after offset comprises: calculating a direction vector of the second target line segment unit according to a second starting point coordinate and a second end point coordinate of the second target line segment unit; calculating a normal vector of the second target line segment unit according to the direction vector; performing offset transformation on the second starting point coordinate and the second end point coordinate according to the normal vector and the dynamic compensation value, to obtain a new starting point coordinate and a new end point coordinate after offset; generating the new line segment unit after offset according to the new starting point coordinate and the new end point coordinate after offset.

[0016] By adopting the technical scheme, high-precision and direction-controllable offset transformation of a line segment unit is realized. The method provides an accurate mathematical basis for coordinate offset by calculating the direction vector and normal vector of the line segment, ensuring that the compensation direction is always perpendicular to the original contour, thereby strictly following the physical requirements of the adhesive jetting process. Based on the coordinate transformation of the dynamic compensation value and the normal vector, new line segment units with correct geometric positions can be accurately generated, thereby fundamentally avoiding contour distortion, deformation or precision loss caused by incorrect offset direction or calculation deviation, laying a precise geometric foundation for subsequent construction of a smooth and continuous compensation contour, and ultimately significantly improving the contour printing precision and size consistency of the green part.

[0017] Optionally, the method further comprises: acquiring a top image of the green part in real time through a visual sensing device during execution of the printing task; performing feature extraction on the top image to identify a contour size deviation between the actual contour of the green part and the preset contour; converting the contour size deviation into a parameter correction amount for the compensation function; adjusting the function parameters of the compensation function based on the parameter correction amount, and calculating a dynamic compensation value according to the adjusted compensation function.

[0018] By adopting the technical scheme, online monitoring of the printing process and dynamic self-correction of the compensation parameters are realized. The method acquires a green part image in real time during printing and identifies a contour deviation, compares the actual printing state with the theoretical model, and further converts the identified size deviation into a precise correction of the compensation function parameters, so that the preset linear compensation model can be adaptively adjusted and optimized according to the real-time printing effect. This process effectively suppresses systematic errors caused by differences in powder batches, changes in environmental temperature and humidity, or fluctuations in the state of the nozzle, so that the compensation strategy always matches the current process state, thereby significantly improving the size consistency of green parts and long-term process stability of printing tasks of different batches and different time periods.

[0019] In a second aspect of the present application, an adaptive adhesive jetting printing compensation system is provided, specifically comprising: a calibration module configured to prepare test samples with a plurality of preset design feature sizes, measure actual feature sizes of the green part after printing and solidification of each feature region in the test samples, and calculate size deviation values between each actual feature size and the corresponding preset design feature size; a function generation module configured to calculate a target compensation amount corresponding to each preset design feature size according to the size deviation values, and establish a compensation function based on the preset design feature sizes and the target compensation amounts; a model processing module, configured to receive a three-dimensional model of a part to be printed and perform layering and slicing processing on the three-dimensional model, and extract contour geometry data of each layer after the layering and slicing processing; a feature size identification module, configured to identify a target feature size of a target region corresponding to each line segment unit from the contour geometry data; a dynamic compensation calculation module, configured to input the target feature size into the compensation function to obtain a dynamic compensation value; a contour offset processing module, configured to perform offset processing on the corresponding line segment unit according to the dynamic compensation value, and generate a compensated printing contour; a printing control module, configured to plan a printing path according to the printing contour and control a printing device to perform a printing task.

[0020] In a third aspect of the present application, an electronic device is provided, including a processor, a memory, a user interface and a network interface, the memory is configured to store instructions, the user interface and the network interface are configured to communicate with other devices, and the processor is configured to execute the instructions stored in the memory to enable the electronic device to perform the method of any one of the above aspects.

[0021] In a fourth aspect of the present application, a computer readable storage medium is provided, which stores instructions, when the instructions are executed, the method of any one of the above aspects is performed.

[0022] To sum up, the one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: By establishing an adaptive compensation function based on feature size, precise control of the binder jetting printing process is achieved, effectively solving the problem of poor adaptability of fixed compensation values on different size features. Through the whole process data processing from three-dimensional model analysis, local feature recognition to dynamic offset generation, the calculation accuracy of compensation amount and the integrity of contour geometry are guaranteed. Further introducing online image detection and parameter self-correction mechanism, the anti-interference ability and long-term stability of the printing process are significantly improved, thereby realizing the overall improvement of green size precision, qualification rate and production efficiency in complex part printing. BRIEF DESCRIPTION OF DRAWINGS

[0023] Figure 1 is a system architecture schematic diagram of an embodiment of an adaptive binder jetting printing compensation method or an adaptive binder jetting printing compensation system according to the present application; Figure 2 is a flowchart of an adaptive binder jetting printing compensation method disclosed in an embodiment of the present application; Figure 3is a module schematic diagram of an adaptive binder jetting printing compensation system disclosed by an embodiment of the present application. Figure 4 is a structural schematic diagram of an electronic device disclosed by an embodiment of the present application.

[0024] Label explanation: 100, system architecture; 101, first terminal device; 102, second terminal device; 103, third terminal device; 104, network; 105, server; 301, calibration module; 302, function generation module; 303, model processing module; 304, feature size identification module; 305, dynamic compensation calculation module; 306, contour bias processing module; 307, printing control module; 308, monitoring correction module; 401, processor; 402, communication bus; 403, user interface; 404, network interface; 405, memory. DETAILED DESCRIPTION

[0025] In order for those skilled in the art to better understand the technical solutions in the specification, the technical solutions in the specification will be clearly and completely described below in combination with the drawings in the embodiments of the specification. Obviously, the described embodiments are only some of the embodiments of the present application, not all the embodiments.

[0026] In the description of the embodiments of the present application, the words such as "for example" or "for instance" are used to represent an example, illustration or description. Any embodiment or design scheme described as "for example" or "for instance" in the embodiments of the present application should not be interpreted as more preferred or more advantageous than other embodiments or design schemes. Rather, the words such as "for example" or "for instance" are intended to present the relevant concept in a specific way.

[0027] In the description of the embodiments of the present application, the term "a plurality of" means two or more. For example, a plurality of systems means two or more systems, and a plurality of screen terminals means two or more screen terminals. In addition, the terms "first" and "second" are only for the purpose of description, and should not be understood as indicating or implying relative importance or implicitly indicating the indicated technical features. Therefore, the features limited by "first" and "second" can explicitly or implicitly include one or more of the features. The terms "include", "contain", "have" and their variants mean "include but are not limited to", unless otherwise specifically emphasized.

[0028] As Figure 1As shown, the system architecture 100 can include terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 is a medium for providing a communication link between the terminal devices 101, 102, 103 and the server 105. The network 104 can include various connection types, such as wired, wireless communication links, or fiber optic cables, and the like.

[0029] A user can use the terminal devices 101, 102, 103 to interact with the server 105 through the network 104 to receive or send messages, and the like. Various communication client applications can be installed on the terminal devices 101, 102, 103, such as model training applications, video recognition applications, web browser applications, social platform software, and the like.

[0030] The terminal devices 101, 102, 103 can be hardware or software. When the terminal devices 101, 102, 103 are hardware, they can be various electronic devices with a display screen, including but not limited to smartphones, tablet computers, e-book readers, MP3 (Moving Picture Experts Group Audio Layer III) players, MP4 (Moving Picture Experts Group Audio Layer IV) players, laptop computers, desktop computers, and the like. When the terminal devices 101, 102, 103 are software, they can be installed in the above-listed electronic devices. They can be implemented as multiple software or software modules (such as multiple software or software modules for providing distributed services) or as a single software or software module. No specific limitation is made herein.

[0031] The embodiment discloses a self-adaptive binder jet printing compensation method, Figure 2 is a flowchart of a self-adaptive binder jet printing compensation method disclosed by the embodiment of the present application, as Figure 2 As shown, the method includes the following steps: S201, a test sample with multiple preset design feature sizes is prepared, the actual feature size of the green body after printing and curing of each feature region in the test sample is measured, and the size deviation value between each actual feature size and the corresponding preset design feature size is calculated.

[0032] Specifically, according to the selected printing process parameters (including powder material type, binder saturation and layer thickness), a three-dimensional model of a test sample containing a plurality of different feature size structures is designed and prepared, which needs to systematically cover the size range from small features (such as thin-walled walls with a width of 0.3mm to 0.8mm) to larger entities (such as thick-walled blocks with a width of 5mm to 15mm); after printing and curing of the test sample using the same process parameters, repeated measurements of each feature area are performed using high-precision optical measurement equipment, and the average value of the actual size is calculated to ensure that the measurement error is controlled within ±5μm; the size deviation value of each feature is calculated by the formula ΔD_i=D_actual_i-D_design_i, where ΔD_i represents the size deviation value of the i-th feature area (unit: mm), D_actual_i represents the average value of the measured green body actual size of the area (unit: mm), and D_design_i represents the preset design size of the area (unit: mm); all deviation value data are recorded and stored for subsequent analysis.

[0033] S202, calculate a target compensation amount corresponding to each of the preset design feature sizes according to the size deviation values, and establish a compensation function based on the preset design feature sizes and the target compensation amounts.

[0034] Specifically, based on the size deviation data of each feature area obtained by the previous measurement, each size deviation value is converted into a corresponding target compensation amount through mathematical negation operation, which ensures the correct compensation direction that large size negative deviation produces positive compensation value and positive deviation produces negative compensation value. Subsequently, using all preset design feature size values as horizontal coordinate data and corresponding target compensation amounts as vertical coordinate data, a least squares linear regression algorithm is used for function fitting, which finds the optimal solution that minimizes the sum of squared perpendicular distances of all data points to the fitted straight line through iterative calculation, and finally determines the slope parameter and intercept parameter of the compensation function: the slope parameter quantitatively represents the rate of change of the compensation amount with the feature size, and the intercept parameter represents the basic compensation amount required for a theoretical zero-size feature, thereby constructing a linear compensation model that completely describes the corresponding relationship between feature size and optimal compensation amount. The entire process is executed through standard data processing software to ensure calculation accuracy and reproducibility.

[0035] Optionally, the calculation of the target compensation amount corresponding to each of the preset design feature sizes according to the size deviation values, and the establishment of the compensation function based on the preset design feature sizes and the target compensation amounts include: negating the size deviation value to obtain the target compensation amount corresponding to the preset design feature size; The preset design feature sizes are taken as independent variables, and the target compensation amounts are taken as dependent variables, and a linear regression algorithm is used to perform function fitting on the independent variables and the dependent variables, to obtain the compensation function.

[0036] Specifically, the size deviation value obtained by measurement is converted into a target compensation amount through a mathematical negation operation. In specific implementation, for each measured feature region, the size deviation value ΔD_i (unit: mm) thereof is substituted into a conversion formula O_i = -ΔD_i for calculation, where O_i is the target compensation amount (unit: mm) corresponding to the feature region. This operation has a clear physical meaning: when the green body actual size is smaller than the design value (ΔD_i is negative), the obtained positive compensation amount (O_i is positive) indicates that the system needs to expand the contour outward; when the green body actual size is larger than the design value (ΔD_i is positive), the obtained negative compensation amount (O_i is negative) indicates that the system needs to shrink the contour inward, thereby ensuring the accuracy of the compensation direction and providing a reliable data basis for subsequent establishment of an accurate compensation function.

[0037] Further, a quantitative relationship model between feature sizes and compensation amounts is established through a linear regression algorithm. In specific implementation, the preset design sizes D_design_i (unit: mm) of n test feature points are taken as independent variables X_i, and the target compensation amounts O_i (unit: mm) corresponding thereto are taken as dependent variables Y_i, to form a data set { (X_i, Y_i) | i = 1, 2,..., n}; the data set is linearly fitted through a least square method, a slope k (dimensionless) is calculated through a formula k = [n·∑ (X_i·Y_i) - ∑X_i·∑Y_i] / [n·∑ (X_i)² - (∑X_i)²], and the physical meaning thereof is a sensitivity coefficient of the compensation amount with respect to the feature size; an intercept b (unit: mm) is calculated through a formula b = (∑Y_i - k·∑X_i) / n, and represents a basic compensation amount when the feature size approaches zero; and finally, a linear compensation function Y = k·X + b is obtained, which quantitatively describes the optimal compensation amount required by different feature sizes and provides a mathematical model basis for subsequent adaptive compensation.

[0038] S203, receiving a three-dimensional model of a part to be printed and performing layer-by-layer slicing processing on the three-dimensional model to extract contour geometry data of each layer after the layer-by-layer slicing processing.

[0039] Specifically, a three-dimensional model file stored in STL (Stereolithography) format is received through a system data interface, a slicing algorithm based on triangle intersection is used to perform layering and discretization processing along the Z-axis direction with layer thickness as the step size according to a layer thickness setting value (such as 0.05 mm) in the preset process parameters, and a series of two-dimensional cross-section layers with accurate Z coordinate values are generated; a contour tracing algorithm based on a scan line is used for each cross-section layer, a geometric tolerance of 0.001 mm is set to judge the connectivity of line segments, and all closed contour rings (including outer contours and inner hole contours) are extracted; each contour ring is discretized into a set of straight line segment units, the starting point coordinates (X_s, Y_s, Z) and the end point coordinates (X_e, Y_e, Z) of each line segment unit are recorded in double-precision floating point type, and a topological connection mapping table of line segment units is established to record the index relationship of adjacent units; finally, all geometric data and topological information are integrated through a structured data packaging format (such as JSON or a self-defined binary format) to form a complete cross-section layer data set containing layer height, contour quantity, vertex coordinate sequence and topological relationship.

[0040] Optionally, the receiving a three-dimensional model of a part to be printed and performing layering and slicing processing on the three-dimensional model, and extracting contour geometric data of each layer after the layering and slicing processing comprises: performing layering processing on the three-dimensional model along a pre-construction direction using a slicing algorithm according to a preset printing layer thickness parameter, to generate a plurality of two-dimensional cross-section layers; performing contour recognition and extraction operation on a target two-dimensional cross-section layer to calculate a closed contour line in the target two-dimensional cross-section layer, the target two-dimensional cross-section layer being any one of the plurality of two-dimensional cross-section layers; analyzing geometric properties of the closed contour line, and extracting a plurality of line segment units included in the closed contour line, a vertex coordinate sequence of each line segment unit, and a connection topological relationship between the line segment units; combining the plurality of line segment units, the vertex coordinate sequence, and the connection topological relationship to obtain the contour geometric data of the target two-dimensional cross-section layer.

[0041] Specifically, a cutting plane is generated layer by layer with layer thickness as the step size along a pre-construction direction (usually the Z-axis) starting from the bottom of the model according to a printing layer thickness parameter (such as 0.05 mm) set in the process file; the intersection of each cutting plane and the triangle patches of the three-dimensional model is calculated, the intersection line of the plane and the triangle boundary is calculated, and the continuous intersection points are connected to form a closed polygon ring; finally, a series of two-dimensional cross-section layer data containing cross-section contour information are generated, each cross-section layer contains the elevation value of the layer and the corresponding cross-section contour set, laying a foundation for subsequent contour geometric data processing.

[0042] Further, when the target two-dimensional cross-section layer is profile-identified and extracted, the discrete line segment set obtained after processing the slice is processed. A boundary tracking algorithm based on endpoint coordinate matching is used to determine the connectivity of the line segments by setting the endpoint distance tolerance (0.001 mm), and the adjacent line segment endpoints are sequentially traversed and connected to form a closed polygon ring. Each ring needs to be verified for closure by calculating its vector area: the vertices of the outer contour ring are arranged in a counterclockwise direction and the area is positive, and the vertices of the inner contour ring are arranged in a clockwise direction and the area is negative. The structured geometric data containing the ordered vertex coordinate sequence of each contour ring and the hierarchical relationship is obtained.

[0043] Further, when the closed contour line is geometrically analyzed, a piecewise linearization processing method is used: each closed contour ring is discretized into continuous straight line segment units in the order of the vertices, and each line segment unit is uniquely determined by its start point and end point three-dimensional coordinates; the vertex coordinate sequence of all line segment units is accurately recorded, and the coordinate values are retained to six decimal places to meet the micron-level precision requirement; at the same time, a connection topological relationship mapping table between line segment units is established, and the predecessor unit and successor unit number of each line segment unit is recorded to form a complete contour topological chain structure. The structured data set containing geometric coordinates and topological relationships is generated to provide a data basis for subsequent feature size identification.

[0044] Further, when the discrete line segment units, vertex coordinate sequences and connection topological relationships are integrated, a hierarchical data structure is used for organization: taking the two-dimensional cross-section layer as a unit, a hierarchical header information containing the layer height identifier and the contour number is created; all line segment units of each closed contour are stored as an ordered set in topological connection order, and each line segment unit object contains start point coordinates, end point coordinates and adjacent unit pointers; at the same time, a global vertex coordinate pool is established, all vertices are stored using double-precision floating-point numbers and share references to reduce data redundancy; the geometric data and topological relationship sequence are serialized and packaged in XML (Extensible Markup Language) or binary format to form a structured contour data file containing complete geometric and topological information.

[0045] S204, identifying the target feature size of the target region corresponding to each line segment unit extracted from the contour geometric data.

[0046] Specifically, when identifying the feature size of the target region corresponding to each line segment unit in the contour geometry data, first, the geometry data of the line segment unit and its topological relationship are obtained, and the feature type is determined by calculating the angle between the normal vectors of adjacent line segment units: when parallel opposite line segments are detected and the angle is greater than 150 degrees, it is determined as a width feature, and the minimum vertical distance is calculated using the point-line distance algorithm; when the contour point set satisfies the circularity threshold of 0.99, the diameter value is calculated by fitting a circular curve using the least squares method. The obtained size value is stored in the feature size data table in double-precision floating-point format together with the line segment unit ID, feature type code, and timestamp to establish a complete size identification record. It should be noted that for a contour composed of curves (such as circular arcs and spline curves), it can be discretized into multiple line segment units connected at the head and tail to perform the above steps. Alternatively, the normal vector and local curvature of any point on the curve can be directly calculated and applied as input to a compensation function to achieve direct compensation of the curve contour. For sharp corners or isolated protrusions that cannot directly find parallel opposite line segments, the target feature size can be determined by calculating the diameter of the inscribed circle or the diameter of the circumscribed circle of the local region.

[0047] Optionally, the identifying the target feature size of the target region corresponding to each line segment unit extracted from the contour geometry data comprises: determining the geometric attribute type of the target printing region corresponding to the first target line segment unit, the geometric attribute type including width, diameter, or inner diameter, the first target line segment unit being any one of all line segment units extracted from the contour geometry data; calculating the specific size value of the target printing region under the geometric attribute type according to the first start point coordinate and the first end point coordinate of the first target line segment unit, the orientation of the adjacent line segment unit adjacent to the first target line segment unit, and the connection topological relationship; recording the specific size value as the target feature size of the target region corresponding to the first target line segment unit.

[0048] Specifically, when determining the geometric attribute type of the target printing region corresponding to the first target line segment unit, the system intelligently identifies by analyzing the local geometric features of the line segment unit and its topological environment: calculating the angle between the normal vectors of the line segment unit and its adjacent line segment units, when parallel opposite line segments are detected and the angle is greater than 150 degrees, it is determined that the region belongs to a thin-walled feature, and the geometric attribute type is marked as "width"; when the contour point set satisfies the circularity threshold (such as 0.99) and is an outer contour by fitting using the least squares method, it is determined as a "diameter" feature; when the circularity requirement is met and it is also identified as an internal closed loop, it is determined as an "inner diameter" feature, and the geometric attribute classification result corresponding to the line segment unit is output.

[0049] Further, when calculating the specific size value of the target printing area, the following operations are performed according to the geometric attribute type: for the width feature, the minimum vertical distance between the target line segment unit and its opposite parallel line segment unit is calculated, and the spatial distance between the two parallel line segments is calculated by the vector cross product formula; for the diameter / inner diameter feature, the least square circle fitting algorithm is used to construct a contour vertex coordinate matrix, and the center coordinates and radius value are obtained by solving the equation set, and finally the size value is taken as the diameter value (2 times the radius). All calculation processes use millimeter system double-precision floating point number operation, and the calculation result is kept to 6 decimal places.

[0050] Further, an independent feature size record is created for each line segment unit, and the following data structure is used for storage: the globally unique ID of the line segment unit is used as the primary key, the size value calculated is stored in the "size value" field in the form of double-precision floating point number (keeping 6 decimal places), the "unit" field is marked as "mm", the "geometric type" field is filled with the corresponding enumeration value (1: width, 2: diameter, 3: inner diameter) according to the feature type, and the time stamp and algorithm version number used during calculation are recorded; finally, these structured data are written into the feature size database table corresponding to the current layer, and an index association with the original geometric data is established.

[0051] S205, input the target feature size into the compensation function to obtain a dynamic compensation value.

[0052] Specifically, when the target feature size is substituted into the compensation function to calculate the dynamic compensation value, the corresponding compensation function parameters are queried according to the feature size value, and the feature size value (unit: mm) is input as the independent variable X into the linear compensation function Y=kX+b, where the slope k and the intercept b come from the pre-established size-compensation amount relationship model, and the corresponding dynamic compensation value Y (unit: mm) is calculated in real time through double-precision floating point number operation, the calculation result is kept to 6 decimal places, and the mapping relationship between the compensation value and the corresponding line segment unit ID is stored in the cache queue.

[0053] It should be noted that in some embodiments, when a certain target feature size of the part to be printed exceeds the size range calibrated by the test sample, a preset strategy can be adopted for processing, for example: using the compensation value corresponding to the boundary size closest in the calibration range, or performing extrapolation value calculation based on the function model, or applying a fixed safety compensation value, to ensure the stability and robustness of the printing process.

[0054] S206, bias processing is performed on the corresponding line segment unit according to the dynamic compensation value to generate a compensated printing contour.

[0055] Specifically, when the corresponding line segment unit is offset according to the dynamic compensation value, a normal direction-based coordinate offset method is adopted: a unit normal vector is calculated for each line segment unit according to its dynamic compensation value, with the positive direction for the outer contour and the negative direction for the inner contour; the compensation value is multiplied by the normal vector to obtain an offset, which is applied to the start and end coordinates of the line segment unit to generate a new offset line segment unit; the original contour geometry data is used to connect the new offset line segment units in sequence to form a closed contour; and all the compensation contours are combined according to the original hierarchical structure to generate complete compensated printing contour data.

[0056] Optionally, the offset processing of the corresponding line segment unit according to the dynamic compensation value to generate the compensated printing contour comprises: performing contour offset calculation according to the dynamic compensation value corresponding to a second target line segment unit to generate a new offset line segment unit, the second target line segment unit being any one line segment unit; connecting the new offset line segment units according to the connection topological relationship in the contour geometry data to obtain a closed compensation contour; combining all the compensation contours to obtain the compensated printing contour.

[0057] Specifically, when the contour offset calculation is performed according to the dynamic compensation value corresponding to a second target line segment unit, the start and end coordinates of the line segment unit are obtained, a unit normal vector is calculated by rotating the unit direction vector of the line segment unit by 90 degrees, with the positive direction for the outer contour and the negative direction for the inner contour; the dynamic compensation value is multiplied by the unit normal vector to obtain an offset vector, which is added to the start and end coordinates to obtain new offset coordinates; the new offset line segment unit is generated according to the new start and end coordinates, and the original line segment properties and topological relationship are maintained unchanged.

[0058] Further, in the contour offset process, the new offset line segment units are connected into a closed contour according to the topological relationship of the original contour. For example, an original rectangular contour is composed of four line segment units (AB, BC, CD, DA), and four new line segment units (A'B', B'C', C'D', D'A') are obtained after offsetting. According to the original topological relationship, it is known that line segment AB connects BC, BC connects CD, CD connects DA, and DA connects AB. According to this connection order, the offset new line segments are sequentially connected end to end: the end point of A'B' is automatically aligned with the start point of B'C' within a tolerance range, the end point of B'C' is aligned with the start point of C'D', and so on, to finally ensure that the end point of D'A' is closed with the start point of A'B', forming a complete closed new rectangular contour. The entire process ensures the correctness of the connection by maintaining the original topological relationship, and eliminates calculation errors by using a geometric tolerance (0.001 mm).

[0059] Further, when combining all the compensation contours to generate the final printing contour, the geometric hierarchy of the original cross-section layers is integrated. For example, a cross-section layer contains a rectangular outer contour and a circular inner hole contour, and after the offset processing, a new rectangular compensation contour and a circular compensation contour are obtained respectively. According to the original topological data, the rectangular compensation contour is marked as an outer contour, and the circular compensation contour is marked as an inner contour, and the inclusion relationship between them is established. Through the geometric nesting algorithm, the relative positions of the inner and outer contours are ensured to be correct (the circle is completely inside the rectangle), and the vertex coordinates and topological relationships of all the compensation contours are encapsulated into a unified printing contour dataset to form a compensated model that can be directly used for path planning.

[0060] Optionally, the method further comprises: calculating a direction vector of the second target line segment unit according to a second start point coordinate and a second end point coordinate of the second target line segment unit; calculating a normal vector of the second target line segment unit according to the direction vector; performing offset transformation on the second start point coordinate and the second end point coordinate according to the normal vector and the dynamic compensation value, to obtain a new start point coordinate and a new end point coordinate after offset; generating the new line segment unit after offset according to the new start point coordinate and the new end point coordinate.

[0061] Specifically, when calculating the direction vector of the second target line segment unit, an endpoint coordinate difference normalization method is adopted: based on the start point coordinate (X_s, Y_s) and the end point coordinate (X_e, Y_e), the horizontal difference ΔX = X_e - X_s and the vertical difference ΔY = Y_e - Y_s are calculated, and the line segment length L is obtained by square sum and square root operation , and finally ΔX and ΔY are divided by the length L to obtain the unit direction vector (V_x, V_y). For example, for a line segment with a start point (1, 2) and an end point (4, 5), first calculate ΔX = 3 and ΔY = 3, and according to the formula, the length L ≈ 4.243, and the direction vector (0.707, 0.707) is obtained.

[0062] Further, according to the calculated direction vector (V_x, V_y), the normal vector is calculated by rotating the vector by 90 degrees: exchange the positions of the two components of the direction vector and take the negative of one of the components, specifically using the formula N_x = -V_y, N_y = V_x to obtain the unit normal vector. For example, the direction vector (0.707, 0.707) calculated in the previous step is calculated by exchanging components and taking the negative: N_x = -0.707 ≈ -0.707, N_y = 0.707 ≈ 0.707, to obtain the normal vector (-0.707, 0.707). The normal vector always maintains the unit length characteristic and is perpendicular to the original direction vector, and can be directly used for subsequent offset calculation.

[0063] Further, according to the calculated unit normal vector (N_x, N_y) and the dynamic compensation value O, the start point coordinate (P_s) and the end point coordinate (P_e) of the line segment are transformed by offsetting: the dynamic compensation value O is multiplied by the X and Y components of the normal vector respectively to obtain the X direction offset component ΔX = O × N_x and the Y direction offset component ΔY = O × N_y; the start point coordinate (P_sx, P_sy) is added to the offset component (ΔX, ΔY) to obtain the new start point coordinate (P_sx + ΔX, P_sy + ΔY); the end point coordinate (P_ex, P_ey) is added to the same offset component (ΔX, ΔY) to obtain the new end point coordinate (P_ex + ΔX, P_ey + ΔY). For example, when the normal vector is (-0.707, 0.707) and the compensation value O = 0.1 mm, ΔX = 0.1 × (-0.707) = -0.0707 mm and ΔY = 0.1 × 0.707 = 0.0707 mm are calculated; the original start point (1, 2) is offset to (0.9293, 2.0707) and the original end point (4, 5) is offset to (3.9293, 5.0707), and the offset line segment maintains the original length and direction characteristics.

[0064] Further, when creating a new line segment unit after offsetting according to the obtained new start point coordinate and new end point coordinate, the two coordinate points are directly used to define the geometric position of the line segment, while all properties of the original line segment unit (including line segment type, layer information, material properties, etc.) are completely inherited, and an independent topology index number is assigned to the new line segment unit, the connection relationship with adjacent line segment units is established, and finally the newly generated line segment unit data is stored in the geometry database of the current layer to complete the generation of the offset line segment unit. For example, the new start point (0.9293, 2.0707) and the new end point (3.9293, 5.0707) are used as end point coordinates, the process parameters and topology pointers of the original line segment are retained, and a new line segment unit after offsetting is generated with new coordinates but maintaining all other properties.

[0065] S207, according to the printing contour, a printing path is planned and a printing device is controlled to perform a printing job.

[0066] Specifically, according to the compensated printing contour data, a scan line filling algorithm is used to generate a printing path: taking the contour boundary as a constraint condition, parallel and equidistant scan lines are generated according to a set path interval (usually 1.2 times the diameter of the nozzle, such as 0.06 mm); a zigzag path optimization algorithm is used, a filling angle of 45 degrees is set, and adjacent layers are rotated by 90 degrees to enhance the structural strength; the path data is converted into a standard G code format, including motion instructions (G0 / G1), coordinate parameters (X, Y, Z), feed rate (F value), and ejection control commands (M code); the instructions are transmitted in real time to the printing equipment through the EtherCAT industrial Ethernet protocol, the three-axis motion platform moves according to the planned path, the piezoelectric nozzle is triggered to eject the binder at the specified coordinate point (ejection duration 0.5 ms, frequency 8 kHz) at the same time, and a real-time position verification function is integrated to ensure that the positioning accuracy error is less than ±5 μm, and a printing quality report is automatically generated after the printing job is completed layer by layer.

[0067] Optionally, the method further comprises: During the execution of the printing job, the top image of the green body is collected in real time by a visual sensing device; The feature of the top image is extracted, and the contour size deviation between the actual contour of the green body and the preset contour is identified; The contour size deviation is converted into a parameter correction amount of the compensation function; The function parameters of the compensation function are adjusted based on the parameter correction amount, and the dynamic compensation value is calculated according to the adjusted compensation function.

[0068] Specifically, during the execution of the printing job, when each layer of printing is completed and the powder is laid, a 50 million pixel industrial CCD camera installed on the Z-axis gantry is used to collect the top image of the green body in a 200 ms time window when the printing platform is paused, with a vertical overhead angle, an image resolution of 2592x1944 pixels, and RAW format storage Further, when the collected top image of the green body is feature-extracted, first, Gaussian filtering is used to remove image noise, and then Canny edge detection algorithm is used to extract the actual contour boundary of the green body; the obtained actual contour coordinates are aligned with the preset contour theoretical coordinates, and the nearest point iteration algorithm is used to calculate the corresponding relationship between them; finally, the Hausdorff distance algorithm is used to calculate the maximum and minimum distance values between the corresponding point sets of the actual contour and the preset contour, and the contour size deviation data is obtained, with a precision of pixel level (about ±5 μm).

[0069] Further, the detected profile size deviation dataset {ΔD_i} and the corresponding feature size {X_i} are input into a least square parameter estimation algorithm, and a compensation function parameter correction amount is calculated by solving a normal equation set: wherein Δk represents a slope correction amount (sensitivity adjustment of the compensation amount with respect to size change), and Δb represents an intercept correction amount (offset adjustment of the basic compensation amount). The original compensation function parameters are then updated as follows: k_new=k_old+α·Δk (α is a learning rate, and a default value is 0.1), and b_new=b_old+α·Δb. The updated parameters are substituted into the compensation function Y=k_new·X+b_new, wherein X is a real-time identified feature size, and Y is an output dynamic compensation value, so as to realize closed-loop control based on real-time printing state.

[0070] The embodiment further discloses a self-adaptive binder jetting printing compensation system, Figure 3 is a module schematic diagram of a self-adaptive binder jetting printing compensation system disclosed by the embodiment of the application, as Figure 3 indicated, the system comprises: a calibration module 301 configured to prepare test samples with a plurality of preset design feature sizes, measure actual feature sizes of green bodies after printing and solidification of feature regions in the test samples, and calculate size deviation values between the actual feature sizes and corresponding preset design feature sizes; a function generation module 302 configured to calculate target compensation amounts corresponding to the preset design feature sizes according to the size deviation values, and establish a compensation function based on the preset design feature sizes and the target compensation amounts; a model processing module 303 configured to receive a three-dimensional model of a part to be printed and perform layering and slicing processing on the three-dimensional model, and extract contour geometry data of each layer after the layering and slicing processing; a feature size identification module 304 configured to identify target feature sizes of target regions corresponding to each line segment unit from the contour geometry data; a dynamic compensation calculation module 305 configured to input the target feature sizes into the compensation function to obtain a dynamic compensation value; a contour offset processing module 306 configured to offset process the corresponding line segment unit according to the dynamic compensation value, and generate a compensated printing contour; a printing control module 307 configured to plan a printing path according to the printing contour and control a printing device to perform a printing task.

[0071] Optionally, the function generation module 302 is specifically configured to: take the inverse of the size deviation value to obtain the target compensation amount corresponding to the preset design feature size; The preset design feature sizes are taken as independent variables, and the target compensation amounts are taken as dependent variables, a linear regression algorithm is used to perform function fitting on the independent variables and the dependent variables, and the compensation function is obtained.

[0072] Optionally, the model processing module 303 is specifically configured to: According to the preset printing layer thickness parameter, a slicing algorithm is used to perform layering processing on the three-dimensional model along the pre-construction direction, and a plurality of two-dimensional cross-section layers are generated; The contour recognition and extraction operation is performed on the target two-dimensional cross-section layer, and the closed contour line in the target two-dimensional cross-section layer is calculated, the target two-dimensional cross-section layer being any one of the plurality of two-dimensional cross-section layers; The geometric properties of the closed contour line are analyzed, and the plurality of line segment units, the vertex coordinate sequences of the line segment units, and the connection topological relations between the line segment units contained in the closed contour line are extracted; The plurality of line segment units, the vertex coordinate sequences, and the connection topological relations are combined to obtain the contour geometric data of the target two-dimensional cross-section layer.

[0073] Optionally, the feature size identification module 304 is specifically configured to: The geometric property type of the target printing area corresponding to the first target line segment unit is determined, the geometric property type including width, diameter, or inner diameter, the first target line segment unit being any one of all line segment units extracted from the contour geometric data; According to the first start point coordinate and the first end point coordinate of the first target line segment unit, the orientation of the adjacent line segment unit adjacent to the first target line segment unit, and the connection topological relation, the specific size value of the target printing area under the geometric property type is calculated; The specific size value is recorded as the target feature size of the target area corresponding to the first target line segment unit.

[0074] Optionally, the contour offset processing module 306 is specifically configured to: According to the dynamic compensation value corresponding to the second target line segment unit, contour offset calculation is performed to generate a new line segment unit after offset, the second target line segment unit being any one line segment unit; According to the connection topological relation in the contour geometric data, the new line segment units after offset are connected to obtain a closed compensation contour; All the compensation contours are combined to obtain the compensated printing contour.

[0075] Optionally, the contour offset processing module 306 is specifically configured to: According to the second starting point coordinate and the second end point coordinate of the second target line segment unit, a direction vector of the second target line segment unit is calculated; According to the direction vector, a normal vector of the second target line segment unit is calculated; According to the normal vector and the dynamic compensation value, the second starting point coordinate and the second end point coordinate are transformed by bias to obtain a new starting point coordinate and a new end point coordinate after bias; According to the new starting point coordinate and the new end point coordinate, the new line segment unit after bias is generated.

[0076] Optionally, the system further includes a monitoring and correction module 308, specifically configured to: During the execution of the printing task, the top image of the green body is collected in real time by the visual sensing device; The top image is subjected to feature extraction to identify the contour size deviation between the actual contour of the green body and the preset contour; The contour size deviation is converted into a parameter correction amount for the compensation function; The function parameter of the compensation function is adjusted based on the parameter correction amount, and a dynamic compensation value is calculated according to the adjusted compensation function.

[0077] It should be noted that: the apparatus provided in the above embodiments, when realizing its functions, is only exemplified by the division of the above functional modules, and in actual application, the above functions can be completed by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the above described functions. In addition, the apparatus and method embodiments provided in the above embodiments belong to the same concept, and the specific implementation process is detailed in the method embodiments, which will not be repeated here.

[0078] The embodiment also discloses an electronic device, which refers to Figure 4 The electronic device can include at least one processor 401, at least one communication bus 402, a user interface 403, a network interface 404, and at least one memory 405.

[0079] The communication bus 402 is used to realize the connection and communication between the components.

[0080] The user interface 403 can include a display screen (Display) and a camera (Camera), and the optional user interface 403 can further include a standard wired interface and a wireless interface.

[0081] The network interface 404 can optionally include a standard wired interface and a wireless interface (such as a WI-FI interface).

[0082] The processor 401 can include one or more processing cores. The processor 401 connects various parts within the server through various interfaces and lines, performs various functions of the server and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 405, and calling data stored in the memory 405. Alternatively, the processor 401 can be implemented in at least one of a hardware form of a digital signal processing (DSP), a field-programmable gate array (FPGA), and a programmable logic array (PLA). The processor 401 can integrate a combination of one or more of a central processing unit (CPU), a graphics processing unit (GPU), and a modem. Among them, the CPU mainly processes operating systems, user interfaces, and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; and the modem is used for processing wireless communication. It can be understood that the above-mentioned modem can also not be integrated into the processor 401, but can be realized by a separate chip.

[0083] The memory 405 can include a random access memory (RAM) and a read-only memory (ROM). Alternatively, the memory 405 includes a non-transitory computer-readable storage medium. The memory 405 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 405 can include a program storage area and a data storage area, wherein the program storage area can store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playing function, an image playing function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area can store data involved in the above-mentioned various method embodiments, etc. The memory 405 can also be at least one storage device located away from the aforementioned processor 401. As shown, the memory 405 as a computer storage medium can include an operating system, a network communication module, a user interface module, and an application program of an adaptive adhesive jet printing compensation method. Figure 4 As shown, the memory 405 as a computer storage medium can include an operating system, a network communication module, a user interface module, and an application program of an adaptive adhesive jet printing compensation method.

[0084] In Figure 4In the electronic device shown, the user interface 403 is mainly used to provide an interface for the user to input, and obtain data input by the user; and the processor 401 can be used to call an application program of an adaptive adhesive jet printing compensation method stored in the memory 405, which, when executed by one or more processors 401, causes the electronic device to perform the method of one or more of the above embodiments.

[0085] It should be noted that, for the foregoing method embodiments, in order to simply describe, they are all described as a combination of a series of actions, but those skilled in the art should know that the present application is not limited to the order of the actions described, because according to the present application, certain steps can be performed in other order or at the same time. Secondly, those skilled in the art should know that the embodiments described in the specification all belong to preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0086] In several embodiments provided in the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are only schematic, and the division of units is only a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some service interface, device or unit, and can be electrical or other forms.

[0087] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed on a plurality of network units. According to actual needs, part or all of the units can be selected to achieve the purpose of the present embodiment scheme.

[0088] In addition, each of the functional units in the various embodiments of the present application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The integrated unit, if implemented in the form of a software functional unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on such an understanding, the technical solutions of the present application, essentially or in other words, the part that contributes to the prior art or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium 405 and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the various embodiments of the method of the present application. The aforementioned storage medium 405 includes: U disk, mobile hard disk, magnetic disk or optical disk, and various media that can store program codes.

[0089] The above is only exemplary embodiments of the present disclosure, and cannot limit the scope of the present disclosure. That is, any equivalent changes and modifications made in accordance with the teachings of the present disclosure are still within the scope of the present disclosure. Other embodiments of the present disclosure will be readily apparent to those skilled in the art upon considering the disclosure. The present application is intended to cover any variations, uses, or adaptive changes of the present disclosure that follow the general principles of the present disclosure and include common knowledge or conventional technical means in the art that are not described in the present disclosure. The specification and examples are only considered to be exemplary, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. An adaptive adhesive jetting printing compensation method, characterized in that, Applied to a server, the method includes: Prepare test specimens with multiple preset design feature dimensions, measure the actual feature dimensions of the green blanks after printing and curing each feature area in the test specimens, and calculate the dimensional deviation values ​​between each actual feature dimension and the corresponding preset design feature dimension; Calculate the target compensation amount corresponding to each of the preset design feature dimensions based on the size deviation value, and establish a compensation function based on the preset design feature dimensions and each of the target compensation amounts; Receive the 3D model of the part to be printed and perform layer slicing on the 3D model, and extract the contour geometry data of each layer after the layer slicing process; Identify the target feature dimensions of the target region corresponding to each line segment unit extracted from the contour geometry data; The target feature size is input into the compensation function to obtain the dynamic compensation value; The corresponding line segment unit is offset according to the dynamic compensation value to generate the compensated print outline. The printing path is planned according to the printing outline, and the printing equipment is controlled to execute the printing job.

2. The method according to claim 1, characterized in that, The step of calculating the target compensation amount corresponding to each of the preset design feature dimensions based on the size deviation value, and establishing a compensation function based on the preset design feature dimensions and each of the target compensation amounts, includes: Invert the dimensional deviation value to obtain the target compensation amount corresponding to the preset design feature size; Using each of the preset design feature dimensions as independent variables and each of the target compensation amounts as dependent variables, a linear regression algorithm is used to fit the independent and dependent variables to obtain the compensation function.

3. The method according to claim 1, characterized in that, The process of receiving the 3D model of the part to be printed and performing layer-by-layer slicing on the 3D model, and extracting the contour geometry data of each layer after the layer-by-layer slicing process includes: Based on the preset printing layer thickness parameters, the three-dimensional model is layered along the pre-construction direction using a slicing algorithm to generate multiple two-dimensional cross-sectional layers; Contour recognition and extraction operations are performed on the target two-dimensional cross-sectional layer to calculate the closed contour line in the target two-dimensional cross-sectional layer, wherein the target two-dimensional cross-sectional layer is any one of the multiple two-dimensional cross-sectional layers; The geometric properties of the closed contour line are analyzed, and the multiple line segment units contained in the closed contour line, the vertex coordinate sequence of each line segment unit, and the connection topology between each line segment unit are extracted. The contour geometric data of the target two-dimensional cross-sectional layer are obtained by combining multiple line segment units, each vertex coordinate sequence and the connection topology.

4. The method according to claim 3, characterized in that, The identification of target feature dimensions corresponding to each line segment unit extracted from the contour geometry data includes: Determine the geometric attribute type of the target printing area corresponding to the first target line segment unit. The geometric attribute type includes width, diameter or inner diameter. The first target line segment unit is any one of all line segment units extracted from the contour geometric data. Based on the first starting point coordinates and the first ending point coordinates of the first target line segment unit, the orientation of the adjacent line segment units adjacent to the first target line segment unit, and the connection topology, calculate the specific size value of the target printing area under the geometric attribute type. The specific size value is recorded as the target feature size of the target region corresponding to the first target line segment unit.

5. The method according to claim 1, characterized in that, The step of biasing the corresponding line segment units according to the dynamic compensation value to generate the compensated print outline includes: Based on the dynamic compensation value corresponding to the second target line segment unit, the contour offset is calculated to generate a new line segment unit after offset. The second target line segment unit can be any line segment unit. Based on the connection topology in the contour geometry data, each of the offset new line segment units is connected to obtain a closed compensation contour. All the compensated contours are combined to obtain the compensated printed contour.

6. The method according to claim 5, characterized in that, The step of calculating the contour offset based on the dynamic compensation value corresponding to the second target line segment unit to generate the offset new line segment unit includes: Calculate the direction vector of the second target line segment unit based on the second starting point coordinates and the second ending point coordinates of the second target line segment unit; Calculate the normal vector of the second target line segment unit based on the direction vector; Based on the normal vector and the dynamic compensation value, the second starting point coordinates and the second ending point coordinates are subjected to offset transformation to obtain the offset new starting point coordinates and new ending point coordinates; Based on the new starting point coordinates and the new ending point coordinates, the new offset line segment unit is generated.

7. The method according to claim 1, characterized in that, The method further includes: During the printing process, a visual sensing device is used to capture a real-time image of the top of the green blank. Feature extraction is performed on the top image to identify the contour size deviation between the actual contour of the green blank and the preset contour; The contour size deviation is converted into a parameter correction amount for the compensation function; The function parameters of the compensation function are adjusted based on the parameter correction amount, and the dynamic compensation value is calculated based on the adjusted compensation function.

8. An adaptive adhesive jetting printing compensation system, characterized in that, Specifically, it includes: The calibration module is used to prepare test specimens with multiple preset design feature dimensions, measure the actual feature dimensions of the green blank after printing and curing each feature area in the test specimen, and calculate the dimensional deviation value between each actual feature dimension and the corresponding preset design feature dimension; The function generation module is used to calculate the target compensation amount corresponding to each of the preset design feature dimensions based on the size deviation value, and to establish a compensation function based on the preset design feature dimensions and each of the target compensation amounts; The model processing module is used to receive the three-dimensional model of the part to be printed and to perform layer slicing processing on the three-dimensional model, and to extract the contour geometric data of each layer after the layer slicing processing. The feature size recognition module is used to identify the target feature size of the target region corresponding to each line segment unit extracted from the contour geometry data; The dynamic compensation calculation module is used to input the target feature size into the compensation function to obtain the dynamic compensation value; The contour offset processing module is used to offset the corresponding line segment units according to the dynamic compensation value and generate the compensated print contour. The printing control module is used to plan the printing path according to the printing outline and control the printing device to execute the printing job.

9. An electronic device, characterized in that, The device includes a processor, a memory, a user interface, and a network interface. The memory is used to store instructions. The user interface and the network interface are both used to communicate with other devices. The processor is used to execute the instructions stored in the memory to cause the electronic device to perform the method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores instructions that, when executed, perform the method as described in any one of claims 1-7.

Images