A Leveling Method and System for 3D Printing Platforms Based on Time-Series Data

Abstract

This invention discloses a 3D printing platform leveling method and system based on time-series data. The method includes: after the 3D printing platform executes a leveling command, acquiring height parameters corresponding to multiple platform positions of the 3D printing platform; determining whether the 3D printing platform needs leveling based on the height parameters, and obtaining a determination result; if the determination result is yes, forming a parameter sequence by combining the historical height parameters of the 3D printing platform and the height parameters; and inputting the parameter sequence into a trained LSTM model to determine the leveling command corresponding to the 3D printing platform. Therefore, this invention can achieve precise platform leveling control based on height analysis and time-series prediction, improving the flatness and printing quality stability of the 3D printing platform, and reducing the risk of printing failure due to platform unevenness.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a 3D printing platform leveling method and system based on time-series data. Background Technology

[0002] With the rapid popularization of 3D printing technology in high-precision manufacturing, enterprises and users are increasingly emphasizing the improvement of printing platform stability and print quality through intelligent leveling control. Among these challenges, how to generate accurate leveling commands to avoid printing failures has become a key technical issue. Existing technologies typically collect single or a few positional height parameters of the 3D printing platform after executing the leveling command, use fixed threshold judgments or simple averaging calculations to assess the platform's balance, and generate control commands based on standard leveling rules to maintain platform level. However, existing solutions lack weighted analysis of height differences across multiple platforms, serialization of historical height parameters, and dynamic prediction using LSTM models. This makes it difficult to accurately determine whether leveling is needed and generate leveling commands adapted to future conditions, resulting in insufficient leveling accuracy. Platform tilt can easily lead to printing defects or failures, limiting the stability of the 3D printing process and the quality of the finished product. Therefore, existing technologies have shortcomings that urgently need to be addressed. Summary of the Invention

[0003] The technical problem to be solved by the present invention is to provide a 3D printing platform leveling method and system based on time-series data, which can realize precise platform leveling control based on height analysis and time-series prediction, improve the flatness and printing quality stability of the 3D printing platform, and reduce the risk of printing failure caused by platform unevenness.

[0004] To address the aforementioned technical problems, the first aspect of this invention discloses a 3D printing platform leveling method based on time-series data, the method comprising: After the 3D printing platform executes the leveling command, the height parameters corresponding to multiple platform positions of the 3D printing platform are obtained; Based on the height parameter, determine whether the 3D printing platform needs to be leveled, and obtain the determination result; When the determination result is yes, the historical height parameters of the 3D printing platform and the height parameters are combined into a parameter sequence; The parameter sequence is input into the trained LSTM model to determine the leveling command corresponding to the 3D printing platform.

[0005] As an optional implementation, in the first aspect of the present invention, determining whether the 3D printing platform needs to be leveled based on the height parameter and obtaining the determination result includes: For each platform location, a reference height corresponding to that platform location is determined from a preset database; Calculate the height difference between the height parameter of the platform location and the reference height; Calculate the height balance parameter corresponding to the 3D printing platform based on the height difference of all the platform locations; Determine whether the height balance parameter is less than a preset parameter threshold, and obtain the determination result.

[0006] As an optional implementation, in the first aspect of the invention, calculating the height balance parameter corresponding to the 3D printing platform based on the height difference of all the platform positions includes: The platform locations where the height difference is greater than a preset difference threshold are selected to obtain multiple height difference locations; Calculate the weighted average of the height differences at all the height difference locations to obtain the height balance parameter corresponding to the 3D printing platform.

[0007] As an optional implementation, in the first aspect of the present invention, when calculating the height balance parameter, the summation weight corresponding to each height difference is proportional to the position distance parameter corresponding to the corresponding height difference position; the position distance parameter is the reciprocal of the average position distance between the height difference position and all other height difference positions.

[0008] As an optional implementation, in the first aspect of the present invention, the step of assembling a parameter sequence from the historical height parameters of the 3D printing platform and the height parameters includes: Obtain the historical height parameters of multiple historical platform positions when the judgment result is yes in the historical time period corresponding to the 3D printing platform; Based on the filtering rules related to the height difference, a parameter sequence is determined according to the historical height parameters and the height parameters.

[0009] As an optional implementation, in the first aspect of the invention, the step of filtering out multiple dangerous platform locations based on the sound data includes: Calculate the height difference between the historical height parameter and the corresponding reference height for each historical platform location; Filter out the historical platform locations where the height difference is greater than the difference threshold to obtain multiple historical height difference locations; Based on the parameter acquisition time point, all historical elevation difference locations and the elevation differences of the elevation difference locations are sorted and combined from early to late to obtain a parameter sequence.

[0010] As an optional implementation, in the first aspect of the invention, the step of inputting the parameter sequence into a trained LSTM model to determine the leveling command corresponding to the 3D printing platform includes: The parameter sequence is input into the trained LSTM model to obtain the output predicted future height parameters; the predicted future height parameters include the future height parameters of multiple platform locations; Based on the future height parameters and the preset leveling parameter correspondence, the leveling command corresponding to the 3D printing platform is determined.

[0011] As an optional implementation, in the first aspect of the invention, the LSTM model is trained on a training dataset that includes a plurality of training continuous height parameter sequences; the training continuous height parameter sequences include a plurality of height parameters of a specific platform location of the 3D printing platform, sorted from early to late according to time points.

[0012] A second aspect of this invention discloses a 3D printing platform leveling system based on time-series data, the system comprising: The acquisition module is used to acquire the height parameters corresponding to multiple platform positions of the 3D printing platform after the 3D printing platform executes the leveling command; The judgment module is used to determine whether the 3D printing platform needs to be leveled based on the height parameter, and to obtain the judgment result; The component module is used to combine the historical height parameters of the 3D printing platform and the height parameters into a parameter sequence when the judgment result is yes; The control module is used to input the parameter sequence into the trained LSTM model to determine the leveling command corresponding to the 3D printing platform.

[0013] As an optional implementation, in a second aspect of the invention, the specific method by which the determining module determines whether the 3D printing platform needs leveling based on the height parameter, and obtains the determination result, includes: For each platform location, a reference height corresponding to that platform location is determined from a preset database; Calculate the height difference between the height parameter of the platform location and the reference height; Calculate the height balance parameter corresponding to the 3D printing platform based on the height difference of all the platform locations; Determine whether the height balance parameter is less than a preset parameter threshold, and obtain the determination result.

[0014] As an optional implementation, in a second aspect of the invention, the specific method by which the determining module calculates the height balance parameter corresponding to the 3D printing platform based on the height difference of all the platform positions includes: The platform locations where the height difference is greater than a preset difference threshold are selected to obtain multiple height difference locations; Calculate the weighted average of the height differences at all the height difference locations to obtain the height balance parameters corresponding to the 3D printing platform.

[0015] As an optional implementation, in a second aspect of the invention, when calculating the height balance parameter, the summation weight corresponding to each height difference is proportional to the position distance parameter corresponding to the corresponding height difference position; the position distance parameter is the reciprocal of the average position distance between the height difference position and all other height difference positions.

[0016] As an optional implementation, in a second aspect of the invention, the specific method by which the component module combines the historical height parameters of the 3D printing platform and the height parameters into a parameter sequence includes: Obtain the historical height parameters of multiple historical platform positions when the judgment result is yes in the historical time period corresponding to the 3D printing platform; Based on the filtering rules related to the height difference, a parameter sequence is determined according to the historical height parameters and the height parameters.

[0017] As an optional implementation, in a second aspect of the invention, the specific method by which the component module filters out multiple dangerous platform locations based on the sound data includes: Calculate the height difference between the historical height parameter and the corresponding reference height for each historical platform location; Filter out the historical platform locations where the height difference is greater than the difference threshold to obtain multiple historical height difference locations; Based on the parameter acquisition time point, all historical elevation difference locations and the elevation differences of the elevation difference locations are sorted and combined from early to late to obtain a parameter sequence.

[0018] As an optional implementation, in a second aspect of the invention, the control module inputs the parameter sequence into a trained LSTM model to determine the specific method of the leveling command corresponding to the 3D printing platform, including: The parameter sequence is input into the trained LSTM model to obtain the output predicted future height parameters; the predicted future height parameters include the future height parameters of multiple platform locations; Based on the future height parameters and the preset leveling parameter correspondence, the leveling command corresponding to the 3D printing platform is determined.

[0019] As an optional implementation, in a second aspect of the invention, the LSTM model is trained on a training dataset that includes a plurality of training continuous height parameter sequences; the training continuous height parameter sequences include a plurality of height parameters of a specific platform location of the 3D printing platform, ordered from early to late according to time points.

[0020] A third aspect of this invention discloses another 3D printing platform leveling system based on time-series data, the system comprising: Memory containing executable program code; A processor coupled to the memory; The processor calls the executable program code stored in the memory to execute some or all of the steps in the 3D printing platform leveling method based on time-series data disclosed in the first aspect of the present invention.

[0021] The fourth aspect of the present invention discloses a computer storage medium storing computer instructions, which, when invoked, are used to execute some or all of the steps in the 3D printing platform leveling method based on time-series data disclosed in the first aspect of the present invention.

[0022] Compared with the prior art, the embodiments of the present invention have the following beneficial effects: This invention obtains height parameters of multiple platform positions after the 3D printing platform executes a leveling command and determines whether leveling is needed. When needed, the historical and current height parameters are combined into a sequence and input into an LSTM model to determine the leveling command. This enables precise platform leveling control based on height analysis and time-series prediction, improving the flatness of the 3D printing platform and the stability of printing quality, and reducing the risk of printing failure due to platform unevenness. Attached Figure Description

[0023] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1 This is a flowchart illustrating a 3D printing platform leveling method based on time-series data disclosed in an embodiment of the present invention.

[0025] Figure 2 This is a schematic diagram of the structure of a 3D printing platform leveling system based on time-series data disclosed in an embodiment of the present invention.

[0026] Figure 3This is a schematic diagram of another 3D printing platform leveling system based on time-series data disclosed in an embodiment of the present invention. Detailed Implementation

[0027] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0028] The terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this invention are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, apparatus, product, or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or devices.

[0029] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0030] This invention discloses a 3D printing platform leveling method and system based on time-series data. After executing a leveling command on the 3D printing platform, it acquires height parameters at multiple platform positions and determines whether leveling is necessary. When needed, it inputs a sequence of historical and current height parameters into an LSTM model to determine the leveling command. This enables precise platform leveling control based on height analysis and time-series prediction, improving the flatness of the 3D printing platform and the stability of printing quality, and reducing the risk of printing failures due to platform unevenness. Detailed explanations follow.

[0031] Example 1 Please see Figure 1 , Figure 1 This is a flowchart illustrating a 3D printing platform leveling method based on time-series data disclosed in an embodiment of the present invention. Figure 1The described time-series data-based 3D printing platform leveling method can be applied to data processing systems / data processing equipment / data processing servers (including local processing servers or cloud processing servers). For example... Figure 1 As shown, the 3D printing platform leveling method based on time-series data may include the following operations: 101. After the 3D printing platform executes the leveling command, obtain the height parameters corresponding to multiple platform positions of the 3D printing platform.

[0032] Optionally, the leveling command can be an automatic leveling command, a manual triggering command, or a periodic execution command; the present invention does not impose any limitations on this.

[0033] Optionally, the multiple platform positions can be four corner positions, five-point positions, nine-square grid positions, or custom grid positions; this invention does not impose any limitations.

[0034] Optionally, the height parameter can be the original sensor reading, the filtered height value, the relative reference deviation, or the normalized height data; this invention does not impose any limitations on this parameter.

[0035] 102. Based on the height parameters, determine whether the 3D printing platform needs to be leveled, and obtain the judgment result. Optionally, this determination can be based on height balance parameters, maximum height difference, plane fitting residuals, or statistical biases, and this invention does not limit it.

[0036] 103. When the judgment result is yes, combine the historical height parameters and height parameters of the 3D printing platform into a parameter sequence. Optionally, the historical height parameter can be the most recent N leveling records, sliding time window data, or time-stamped sequence data; this invention does not impose any limitations.

[0037] Optionally, the parameter sequence can be a fixed-length sequence, a variable-length sequence, or a multi-channel sequence (one channel per position), and this invention does not impose any limitations.

[0038] Optionally, this composition process can be implemented based on time alignment, missing value imputation, or normalization processing, and the present invention does not limit it.

[0039] 104. Input the parameter sequence into the trained LSTM model to determine the leveling instructions corresponding to the 3D printing platform.

[0040] Optionally, the LSTM model can be a single-layer LSTM, a multi-layer LSTM, a bidirectional LSTM, or an LSTM with an attention mechanism; this invention does not impose any limitations.

[0041] Optionally, the leveling command can be a motor step count command, a Z-axis compensation value, a multi-point independent adjustment command, or an execution sequence; the present invention does not impose any limitations on this.

[0042] As can be seen, the above-described embodiments of the invention obtain height parameters of multiple platform positions after the 3D printing platform executes a leveling command and determine whether leveling is required. When necessary, the historical and current height parameters are combined into a sequence and input into the LSTM model to determine the leveling command. This enables precise platform leveling control based on height analysis and time-series prediction, improves the flatness of the 3D printing platform and the stability of printing quality, and reduces the risk of printing failure caused by platform unevenness.

[0043] As an optional embodiment, the step above, determining whether the 3D printing platform needs leveling based on the height parameter and obtaining the determination result, includes: For each platform location, the reference height corresponding to that platform location is determined from a pre-set database; Calculate the height difference between the platform's location height parameter and the reference height; Calculate the height balance parameters of the 3D printing platform based on the height differences of all platform locations; Determine whether the height balance parameter is less than the preset parameter threshold, and obtain the determination result.

[0044] Optionally, the preset database can be a calibration database, a historical best database, or a factory calibration database; this invention does not impose any limitations.

[0045] Optionally, the reference height can be the ideal plane height, the historical flattest state height, or the theoretical zero point height; this invention does not limit this.

[0046] Optionally, the process of determining the reference height can be based on location indexing, interpolation calculation, or nearest neighbor search, and this invention does not limit it.

[0047] Optionally, the height balance parameter can be the weighted average height difference, root mean square error (RMSE), maximum deviation, or a custom balance index; this invention does not impose any limitations on this parameter.

[0048] Optionally, the threshold parameter can be a fixed threshold, a dynamic threshold, or a threshold adjusted based on the printing task accuracy; this invention does not impose any limitations on this.

[0049] As can be seen, through the above optional embodiments, by calculating the height difference between the platform position height parameter and the reference height and determining the height balance parameter based on the weighted average value to determine whether leveling is required, the accuracy and sensitivity of platform balance assessment are improved through height difference analysis on the basis of precise leveling control, providing a reliable basis for leveling decisions and reducing the risk of leveling omissions caused by misjudgment of balance parameters.

[0050] As an optional embodiment, the step above, calculating the height balance parameters corresponding to the 3D printing platform based on the height differences of all platform positions, includes: Platform locations with height differences greater than a preset threshold are selected to obtain multiple height difference locations; Calculate the weighted average of the height differences at all elevation locations to obtain the height balance parameters corresponding to the 3D printing platform.

[0051] Optionally, the difference threshold can be a fixed threshold, a dynamic threshold, or a threshold that is adaptively adjusted based on the noise level; this invention does not impose any limitations on this.

[0052] As can be seen, through the above optional embodiments, by screening height difference locations that exceed the threshold and calculating a weighted average value as the height balance parameter with a weight proportional to the position distance parameter, the pertinence and accuracy of parameter evaluation are improved through position weighting optimization on the basis of accurate balance parameter calculation, providing high-quality balance data for leveling judgment and reducing the risk of evaluation deviation caused by improper position weight.

[0053] As an optional embodiment, in the above steps, when calculating the height balance parameter, the summation weight corresponding to each height difference is proportional to the position distance parameter corresponding to the height difference position; the position distance parameter is the reciprocal of the average position distance between the height difference position and all other height difference positions.

[0054] Optionally, the location distance can be Euclidean distance, three-dimensional spatial distance, or projection distance; this invention does not limit the distance.

[0055] Optionally, the average distance of the location can be an arithmetic mean, a harmonic mean, or a weighted average, and this invention does not limit it.

[0056] As can be seen, through the above optional embodiments, by using the reciprocal of the average position distance as the position distance parameter to determine the weight, the scientificity and fairness of the weight allocation are improved through distance analysis on the basis of accurate height balance parameter calculation, providing a reasonable basis for weighted summation of elevation difference positions and reducing the risk of balance parameter error caused by ignoring distance.

[0057] As an optional embodiment, the step described above, which involves assembling the historical height parameters and height parameters of the 3D printing platform into a parameter sequence, includes: Obtain the historical height parameters of multiple historical platform positions when the judgment result of the 3D printing platform is "yes" in a historical time period; Based on the screening rules related to height difference, the parameter sequence is determined according to historical height parameters and height parameters.

[0058] Optionally, the historical time period can be the most recent N balances, the past M hours, or a sliding window; this invention does not impose any limitations.

[0059] Optionally, the historical height parameter can be stored in local logs, cloud databases, or embedded storage; this invention does not impose any limitations on this.

[0060] As can be seen, through the above optional embodiments, the 3D printing platform generates a parameter sequence by combining the historical height parameters of multiple historical platform positions that need to be leveled in the historical time period with the current height parameters. Thus, based on the accurate leveling instruction, the continuity and representativeness of the parameter sequence are improved through time series filtering and combination optimization, providing high-quality time series data for LSTM model input and reducing the risk of prediction bias caused by incomplete historical data.

[0061] As an optional embodiment, the step above, filtering out multiple hazardous platform locations based on sound data, includes: Calculate the height difference between the historical height parameter and the corresponding reference height for each historical platform location; Historical platform locations with height differences greater than the difference threshold were filtered out to obtain multiple historical height difference locations; Based on the parameter acquisition time points from morning to night, all historical elevation difference locations and their height differences are sorted and combined to obtain the parameter sequence.

[0062] Optionally, this calculation process can be kept consistent with the current height difference calculation to ensure sequence consistency; however, this invention does not impose any limitations on this process.

[0063] Optionally, the historical height difference can be used for trend analysis, periodic detection, or drift prediction, and this invention does not limit it.

[0064] Optionally, the calculation of this height difference can be combined with historical sensor calibration records for deviation correction, which is not limited in this invention.

[0065] Optionally, the sorting combination can form a single-channel sequence (e.g., all positional height differences are cascaded), a multi-channel sequence (e.g., fixed channels according to position), or a mixed sequence, and the present invention does not limit this.

[0066] Optionally, the time point can be an absolute timestamp, a relative time difference, or a leveling event number; this invention does not impose any limitations on this.

[0067] As can be seen, through the above optional embodiments, by filtering the historical and current height difference locations that exceed the threshold and sorting and combining them according to time points to generate a parameter sequence, the continuity and representativeness of the parameter sequence are improved through time-series filtering and combination optimization based on the accurate leveling instruction. This provides high-quality time-series data for the input of the LSTM model and reduces the risk of prediction bias caused by incomplete historical data.

[0068] As an optional embodiment, the step described above, inputting the parameter sequence into the trained LSTM model to determine the leveling instructions corresponding to the 3D printing platform, includes: The parameter sequence is input into the trained LSTM model to obtain the output predicted future height parameters; optionally, the predicted future height parameters include future height parameters for multiple platform locations. Based on the future height parameters and the pre-defined leveling parameter correspondence, the leveling command corresponding to the 3D printing platform is determined.

[0069] Optionally, the predicted future height parameter can be the height at the next moment, the height in the next N steps, or a trend prediction value; this invention does not impose any limitations.

[0070] Optionally, the LSTM model supports multi-step prediction, confidence interval output, or anomaly warning; this invention does not impose any limitations on this.

[0071] Optionally, the parameter sequence can be enhanced by combining sequence normalization, embedding encoding, or external variable fusion (such as temperature) before input, and this invention does not limit this.

[0072] Optionally, the correspondence of the leveling parameters can be a mapping table, a regression function, an inverse kinematics model, or an optimization solver; this invention does not impose any limitations.

[0073] As can be seen, through the above optional embodiments, by inputting the parameter sequence into the trained LSTM model to predict future height parameters and determining the leveling command based on the correspondence of leveling parameters, the predictability and accuracy of leveling commands are improved through time-series prediction and correspondence mapping on the basis of precise leveling control, providing intelligent support for the maintenance of 3D printing platform and reducing the risk of leveling failure caused by unpredicted future height changes.

[0074] As an optional embodiment, in the above steps, the LSTM model is trained based on a training dataset that includes multiple training continuous height parameter sequences; the training continuous height parameter sequences include multiple height parameters of a specific platform location of the 3D printing platform, sorted from early to late according to time points.

[0075] Optionally, the training dataset can be derived from real printer leveling logs, simulated platform data, or data augmentation; this invention does not impose any limitations on this.

[0076] Optionally, the training can employ supervised learning (inputting a historical sequence and outputting the future height), sequence-to-sequence learning, or a teacher-mandated strategy; this invention does not impose any limitations.

[0077] Optionally, the training process can be optimized by combining early stopping, learning rate scheduling, or gradient clipping, but this invention does not limit it.

[0078] As can be seen, by training an LSTM model based on a sequence of continuous height parameters, the robustness and prediction accuracy of the model are improved through time-series data modeling, thereby providing reliable model support for the generation of leveling instructions on the platform and reducing the risk of prediction errors caused by insufficient training data.

[0079] Example 2 Please see Figure 2 , Figure 2 This is a schematic diagram of a 3D printing platform leveling system based on time-series data disclosed in an embodiment of the present invention. Figure 2 The described time-series data-based 3D printing platform leveling system can be applied to data processing systems / data processing equipment / data processing servers (including local processing servers or cloud processing servers). For example... Figure 2 As shown, the 3D printing platform leveling system based on time-series data may include: The acquisition module 201 is used to acquire the height parameters corresponding to multiple platform positions of the 3D printing platform after the 3D printing platform executes the leveling command.

[0080] The judgment module 202 is used to determine whether the 3D printing platform needs to be leveled based on the height parameter, and obtain the judgment result. Module 203 is used to assemble the historical height parameters and height parameters of the 3D printing platform into a parameter sequence when the judgment result is yes. The control module 204 is used to input the parameter sequence into the trained LSTM model in order to determine the leveling command corresponding to the 3D printing platform.

[0081] As can be seen, the above-described embodiments of the invention obtain height parameters of multiple platform positions after the 3D printing platform executes a leveling command and determine whether leveling is required. When necessary, the historical and current height parameters are combined into a sequence and input into the LSTM model to determine the leveling command. This enables precise platform leveling control based on height analysis and time-series prediction, improves the flatness of the 3D printing platform and the stability of printing quality, and reduces the risk of printing failure caused by platform unevenness.

[0082] As an optional embodiment, the determination module determines whether the 3D printing platform needs leveling based on the height parameter, and the specific method for obtaining the determination result includes: For each platform location, the reference height corresponding to that platform location is determined from a pre-set database; Calculate the height difference between the platform's location height parameter and the reference height; Calculate the height balance parameters of the 3D printing platform based on the height differences of all platform locations; Determine whether the height balance parameter is less than the preset parameter threshold, and obtain the determination result.

[0083] As can be seen, through the above optional embodiments, by calculating the height difference between the platform position height parameter and the reference height and determining the height balance parameter based on the weighted average value to determine whether leveling is required, the accuracy and sensitivity of platform balance assessment are improved through height difference analysis on the basis of precise leveling control, providing a reliable basis for leveling decisions and reducing the risk of leveling omissions caused by misjudgment of balance parameters.

[0084] As an optional embodiment, the specific method by which the determination module calculates the height balance parameters corresponding to the 3D printing platform based on the height differences of all platform positions includes: Platform locations with height differences greater than a preset threshold are selected to obtain multiple height difference locations; Calculate the weighted average of the height differences at all elevation locations to obtain the height balance parameters corresponding to the 3D printing platform.

[0085] As can be seen, through the above optional embodiments, by screening height difference locations that exceed the threshold and calculating a weighted average value as the height balance parameter with a weight proportional to the position distance parameter, the pertinence and accuracy of parameter evaluation are improved through position weighting optimization on the basis of accurate balance parameter calculation, providing high-quality balance data for leveling judgment and reducing the risk of evaluation deviation caused by improper position weight.

[0086] As an optional embodiment, when calculating the height balance parameter, the summation weight corresponding to each height difference is proportional to the position distance parameter corresponding to the height difference position; the position distance parameter is the reciprocal of the average position distance between the height difference position and all other height difference positions.

[0087] As can be seen, through the above optional embodiments, by using the reciprocal of the average position distance as the position distance parameter to determine the weight, the scientificity and fairness of the weight allocation are improved through distance analysis on the basis of accurate height balance parameter calculation, providing a reasonable basis for weighted summation of elevation difference positions and reducing the risk of balance parameter error caused by ignoring distance.

[0088] As an optional embodiment, the specific method by which the component module combines the historical height parameters and height parameters of the 3D printing platform into a parameter sequence includes: Obtain the historical height parameters of multiple historical platform positions when the judgment result of the 3D printing platform is "yes" in a historical time period; Based on the screening rules related to height difference, the parameter sequence is determined according to historical height parameters and height parameters.

[0089] As can be seen, through the above optional embodiments, the 3D printing platform generates a parameter sequence by combining the historical height parameters of multiple historical platform positions that need to be leveled in the historical time period with the current height parameters. Thus, based on the accurate leveling instruction, the continuity and representativeness of the parameter sequence are improved through time series filtering and combination optimization, providing high-quality time series data for LSTM model input and reducing the risk of prediction bias caused by incomplete historical data.

[0090] As an optional embodiment, the specific method by which the component module filters out multiple hazardous platform locations based on sound data includes: Calculate the height difference between the historical height parameter and the corresponding reference height for each historical platform location; Historical platform locations with height differences greater than the difference threshold were filtered out to obtain multiple historical height difference locations; Based on the parameter acquisition time points from morning to night, all historical elevation difference locations and their height differences are sorted and combined to obtain the parameter sequence.

[0091] As can be seen, through the above optional embodiments, by filtering the historical and current height difference locations that exceed the threshold and sorting and combining them according to time points to generate a parameter sequence, the continuity and representativeness of the parameter sequence are improved through time-series filtering and combination optimization based on the accurate leveling instruction. This provides high-quality time-series data for the input of the LSTM model and reduces the risk of prediction bias caused by incomplete historical data.

[0092] As an optional embodiment, the control module inputs the parameter sequence into the trained LSTM model to determine the specific method of the leveling instructions corresponding to the 3D printing platform, including: The parameter sequence is input into the trained LSTM model to obtain the output predicted future height parameters; optionally, the predicted future height parameters include future height parameters for multiple platform locations. Based on the future height parameters and the pre-defined leveling parameter correspondence, the leveling command corresponding to the 3D printing platform is determined.

[0093] As can be seen, through the above optional embodiments, by inputting the parameter sequence into the trained LSTM model to predict future height parameters and determining the leveling command based on the correspondence of leveling parameters, the predictability and accuracy of leveling commands are improved through time-series prediction and correspondence mapping on the basis of precise leveling control, providing intelligent support for the maintenance of 3D printing platform and reducing the risk of leveling failure caused by unpredicted future height changes.

[0094] As an optional embodiment, the LSTM model is trained on a training dataset that includes multiple training continuous height parameter sequences; the training continuous height parameter sequences include multiple height parameters of a specific platform location of the 3D printing platform, sorted from early to late according to time points.

[0095] As can be seen, by training an LSTM model based on a sequence of continuous height parameters, the robustness and prediction accuracy of the model are improved through time-series data modeling, thereby providing reliable model support for the generation of leveling instructions on the platform and reducing the risk of prediction errors caused by insufficient training data.

[0096] Example 3 Please see Figure 3 , Figure 3 This is another 3D printing platform leveling system based on time-series data disclosed in the embodiments of the present invention. Figure 3 The described time-series data-based 3D printing platform leveling system is applied in a data processing system / data processing equipment / data processing server (wherein, the server includes a local processing server or a cloud processing server). For example... Figure 3 As shown, the 3D printing platform leveling system based on time-series data may include: Memory 301 storing executable program code; Processor 302 coupled to memory 301; The processor 302 calls the executable program code stored in the memory 301 to execute the steps of the 3D printing platform leveling method based on time-series data described in Embodiment 1.

[0097] Example 4 This invention discloses a computer read storage medium that stores a computer program for electronic data interchange, wherein the computer program causes a computer to execute the steps of the 3D printing platform leveling method based on time-series data described in Embodiment 1.

[0098] Example 5 This invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to perform the steps of the 3D printing platform leveling method based on time-series data described in Embodiment 1.

[0099] The foregoing has described specific embodiments of this specification; other embodiments are within the scope of the appended claims. In some cases, the actions or steps described in the claims may be performed in a different order than those shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily have to follow the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0100] The systems, devices, modules, or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, a computer can be, for example, a personal computer, laptop computer, cellular phone, camera phone, smartphone, personal digital assistant, media player, navigation device, email device, game console, tablet computer, wearable device, or any combination of these devices.

[0101] For ease of description, the above devices are described in terms of function, divided into various units. Of course, in implementing this specification, the functions of each unit can be implemented in one or more software and / or hardware components.

[0102] Those skilled in the art will understand that the embodiments of this specification can be provided as methods, systems, or computer program products. Therefore, the embodiments of this specification can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the embodiments of this specification can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0103] This specification is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this specification. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a machine for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0104] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0105] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0106] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0107] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0108] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0109] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0110] This specification can be described in the general context of computer-executable instructions that are executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform a specific task or implement a specific abstract data type. This specification can also be practiced in distributed computing environments, where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0111] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to interchangeably. Each embodiment focuses on describing the differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

[0112] Finally, it should be noted that the 3D printing platform leveling method and system based on time-series data disclosed in the embodiments of the present invention are merely preferred embodiments of the present invention and are only used to illustrate the technical solutions of the present invention, not to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A 3D printing platform leveling method based on time-series data, characterized in that, The method includes: After the 3D printing platform executes the leveling command, the height parameters corresponding to multiple platform positions of the 3D printing platform are obtained; Based on the height parameter, determine whether the 3D printing platform needs to be leveled, and obtain the determination result; When the determination result is yes, the historical height parameters of the 3D printing platform and the height parameters are combined into a parameter sequence; The parameter sequence is input into the trained LSTM model to determine the leveling command corresponding to the 3D printing platform.

2. The 3D printing platform leveling method based on time-series data according to claim 1, characterized in that, The step of determining whether the 3D printing platform needs leveling based on the height parameter and obtaining the determination result includes: For each platform location, a reference height corresponding to that platform location is determined from a preset database; Calculate the height difference between the height parameter of the platform location and the reference height; Calculate the height balance parameter corresponding to the 3D printing platform based on the height difference of all the platform locations; Determine whether the height balance parameter is less than a preset parameter threshold, and obtain the determination result.

3. The 3D printing platform leveling method based on time-series data according to claim 2, characterized in that, The step of calculating the height balance parameter corresponding to the 3D printing platform based on the height difference of all the platform positions includes: The platform locations where the height difference is greater than a preset difference threshold are selected to obtain multiple height difference locations; Calculate the weighted average of the height differences at all the height difference locations to obtain the height balance parameters corresponding to the 3D printing platform.

4. The 3D printing platform leveling method based on time-series data according to claim 3, characterized in that, When calculating the height balance parameter, the summation weight corresponding to each height difference is proportional to the position distance parameter corresponding to the height difference position; the position distance parameter is the reciprocal of the average position distance between the height difference position and all other height difference positions.

5. The 3D printing platform leveling method based on time-series data according to claim 2, characterized in that, The step of assembling a parameter sequence from the historical height parameters of the 3D printing platform and the height parameters includes: Obtain the historical height parameters of multiple historical platform positions when the judgment result is yes in the historical time period corresponding to the 3D printing platform; Based on the filtering rules related to the height difference, a parameter sequence is determined according to the historical height parameters and the height parameters.

6. The 3D printing platform leveling method based on time-series data according to claim 5, characterized in that, The step of filtering out multiple dangerous platform locations based on the sound data includes: Calculate the height difference between the historical height parameter and the corresponding reference height for each historical platform location; Filter out the historical platform locations where the height difference is greater than the difference threshold to obtain multiple historical height difference locations; Based on the parameter acquisition time point, all historical elevation difference locations and the elevation differences of the elevation difference locations are sorted and combined from early to late to obtain a parameter sequence.

7. The 3D printing platform leveling method based on time-series data according to claim 1, characterized in that, The step of inputting the parameter sequence into the trained LSTM model to determine the leveling command corresponding to the 3D printing platform includes: The parameter sequence is input into the trained LSTM model to obtain the output predicted future height parameters; the predicted future height parameters include the future height parameters of multiple platform locations; Based on the future height parameters and the preset leveling parameter correspondence, the leveling command corresponding to the 3D printing platform is determined.

8. The 3D printing platform leveling method based on time-series data according to claim 7, characterized in that, The LSTM model is trained on a training dataset that includes multiple training continuous height parameter sequences; the training continuous height parameter sequences include multiple height parameters of a specific platform location of the 3D printing platform, sorted from early to late according to time points.

9. A 3D printing platform leveling system based on time-series data, characterized in that, The system includes: The acquisition module is used to acquire the height parameters corresponding to multiple platform positions of the 3D printing platform after the 3D printing platform executes the leveling command; The judgment module is used to determine whether the 3D printing platform needs to be leveled based on the height parameter, and to obtain the judgment result; The component module is used to combine the historical height parameters of the 3D printing platform and the height parameters into a parameter sequence when the judgment result is yes; The control module is used to input the parameter sequence into the trained LSTM model to determine the leveling command corresponding to the 3D printing platform.

10. A 3D printing platform leveling system based on time-series data, characterized in that, The system includes: Memory containing executable program code; A processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the 3D printing platform leveling method based on time-series data as described in any one of claims 1-8.

Images