3D printing success rate prediction method and system based on multi-source data

Abstract

The invention discloses a 3D printing success rate prediction method and system based on multi-source data. The method comprises the steps that historical multi-source sensing data of 3D printing equipment and to-be-printed three-dimensional model data are obtained; determining historical sensing data corresponding to each model part of the three-dimensional model data in the historical multi-source sensing data; based on the historical sensing data, calculating a printing risk parameter corresponding to each model part; and according to the printing risk parameters corresponding to all the model parts, the printing success rate of printing of the three-dimensional model data through the 3D printing equipment is predicted. It can be seen that accurate printing success rate evaluation based on multi-source association and risk quantification can be achieved, the reliability and resource utilization efficiency of 3D printing tasks are improved, and the printing failure risk caused by misjudgment of part of risks of the model is reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, and in particular to a 3D printing success rate prediction method and system based on multi-source data. BACKGROUND

[0002] With the rapid popularization of 3D printing technology in high-precision and batch production, enterprises and users pay more and more attention to optimizing task planning and resource allocation through accurate success rate evaluation. The existing technology usually collects historical sensing data of 3D printing equipment or basic features of the to-be-printed model, and uses overall statistical analysis or fixed risk threshold method to evaluate the printing feasibility to support task execution. The existing solution is difficult to accurately predict the overall printing success rate due to the lack of accurate matching of each part of the three-dimensional model with historical multi-source sensing data and dynamic quantitative calculation of risk parameters, resulting in insufficient reliability of success rate evaluation, which is easy to cause printing failure or resource waste due to partial risk misjudgment, limiting the efficiency and stability of 3D printing tasks. It can be seen that the existing technology has defects and needs to be solved. SUMMARY

[0003] The technical problem to be solved by the present application is to provide a 3D printing success rate prediction method and system based on multi-source data, which can realize accurate printing success rate evaluation based on multi-source association and risk quantification, improve the reliability and resource utilization efficiency of 3D printing tasks, and reduce the risk of printing failure caused by model partial risk misjudgment.

[0004] In order to solve the above technical problems, the first aspect of the present application discloses a 3D printing success rate prediction method based on multi-source data, which comprises: obtaining historical multi-source sensing data of a 3D printing device and three-dimensional model data to be printed; determining the historical sensing data corresponding to each model part of the three-dimensional model data in the historical multi-source sensing data; based on the historical sensing data, calculating the printing risk parameters corresponding to each model part; according to the printing risk parameters corresponding to all the model parts, predicting the printing success rate of the three-dimensional model data printed by the 3D printing device.

[0005] As an optional implementation, in the first aspect of the present application, the historical multi-source sensing data includes multi-source sensing data of the 3D printing device when performing printing tasks at multiple historical time points; the multi-source sensing data includes at least one of sound data, image data, temperature data, light reflection data and motion data.

[0006] As an optional implementation, in the first aspect of the present application, the historical sensor data corresponding to each model part of the three-dimensional model data in the historical multi-source sensor data comprises: For each model part of the three-dimensional model data, obtain model part data and model part parameters corresponding to the model part; According to the model part data and the model part parameters, determine the matching degree between the model part and each multi-source sensor data; The multi-source sensor data with a matching degree greater than a preset matching degree threshold is determined as the historical sensor data corresponding to the model part.

[0007] As an optional implementation, in the first aspect of the present application, the matching degree between the model part and each multi-source sensor data is determined according to the model part data and the model part parameters, comprising: For each multi-source sensor data, determine the historical model data of the 3D printing device performing printing when the multi-source sensor data is obtained; Input the multi-source sensor data into a trained model parameter prediction model to obtain historical model parameters corresponding to each multi-source sensor data; Calculate the first similarity between the model part data and the historical model data; Calculate the second similarity between the model part parameters and the historical model parameters; Calculate the product of the first similarity and the second similarity to obtain the matching degree between the model part and the multi-source sensor data.

[0008] As an optional implementation, in the first aspect of the present application, the model parameter prediction model is trained by a training data set comprising a plurality of training multi-source sensor data and corresponding model parameters of a model being printed; the model part parameters, the historical model parameters, or the model parameter annotations comprise at least one of model size, model shape, model purpose, model type, model creator, and model volume.

[0009] As an optional implementation, in the first aspect of the present application, the printing risk parameter corresponding to each model part is calculated based on the historical sensor data, comprising: For each model part, estimate a predicted printing time parameter corresponding to the model part based on the historical sensor data; Input the historical sensor data corresponding to the model part into a trained print head wear risk prediction model to obtain a print head wear risk corresponding to the model part; multiplying the print head wear risk and the time weight to obtain a print risk parameter corresponding to the model part; the time weight is proportional to the predicted print time parameter.

[0010] As an optional implementation, in the first aspect of the application, the estimating of the predicted print time parameter corresponding to the model part based on the historical sensing data comprises: clustering all the multi-source sensing data in the historical sensing data corresponding to the model part to obtain a plurality of sensing data sets; the time difference between the time points of obtaining any two multi-source sensing data in each sensing data set is less than a preset time difference threshold; calculating the maximum time difference between all two multi-source sensing data in each sensing data set; calculating the average value of the maximum time difference of all the sensing data sets to obtain the predicted print time parameter corresponding to the model part.

[0011] As an optional implementation, in the first aspect of the application, the predicting of the print success rate of the three-dimensional model data printed by the 3D printing equipment comprises: calculating the weighted sum value of all the print risk parameters corresponding to the model parts to obtain the overall print risk corresponding to the three-dimensional model; wherein the calculation weight corresponding to each print risk parameter is proportional to the print precedence of the corresponding model part in a preset three-dimensional model printing process; obtaining all the risk print records in the historical print records of the 3D printing equipment corresponding to the predicted print risk greater than or equal to the overall print risk; calculating the ratio of the number of successfully printed records in all the risk print records to the total number of records to obtain the print success rate of the three-dimensional model data printed by the 3D printing equipment.

[0012] The second aspect of the embodiment of the application discloses a 3D print success rate prediction system based on multi-source data, which comprises: an acquisition module for acquiring historical multi-source sensing data of a 3D printing equipment and three-dimensional model data to be printed; a determination module for determining historical sensing data corresponding to each model part of the three-dimensional model data in the historical multi-source sensing data; a calculation module for calculating a print risk parameter corresponding to each model part based on the historical sensing data; a prediction module for predicting a print success rate of the three-dimensional model data printed by the 3D printing equipment according to the print risk parameters corresponding to all the model parts.

[0013] As an optional implementation, in the second aspect of the present application, the historical multi-source sensing data comprises multi-source sensing data of the 3D printing device when performing a printing task at a plurality of historical time points; the multi-source sensing data comprises at least one of sound data, image data, temperature data, light reflection data and motion data.

[0014] As an optional implementation, in the second aspect of the present application, the specific manner of the determining module for determining the historical sensing data corresponding to each model part of the three-dimensional model data in the historical multi-source sensing data comprises: for each model part of the three-dimensional model data, obtaining model part data and model part parameters corresponding to the model part; determining a matching degree between the model part and each of the multi-source sensing data according to the model part data and the model part parameters; determining the multi-source sensing data with a matching degree greater than a preset matching degree threshold as the historical sensing data corresponding to the model part.

[0015] As an optional implementation, in the second aspect of the present application, the specific manner of the determining module for determining the matching degree between the model part and each of the multi-source sensing data according to the model part data and the model part parameters comprises: for each of the multi-source sensing data, determining historical model data of the 3D printing device when the multi-source sensing data is acquired; inputting the multi-source sensing data into a trained model parameter prediction model to obtain historical model parameters corresponding to each of the multi-source sensing data; calculating a first similarity between the model part data and the historical model data; calculating a second similarity between the model part parameters and the historical model parameters; calculating a product of the first similarity and the second similarity to obtain the matching degree between the model part and the multi-source sensing data.

[0016] As an optional implementation, in the second aspect of the present application, the model parameter prediction model is trained by a training data set comprising a plurality of training multi-source sensing data and corresponding model parameters of a model being printed; the model part parameters, the historical model parameters or the model parameter annotations comprise at least one of model size, model shape, model purpose, model type, model creator and model volume.

[0017] As an optional implementation, in a second aspect of the invention, the specific method by which the calculation module calculates the printing risk parameters corresponding to each model part based on the historical sensing data includes: For each of the model parts, the predicted printing time parameters corresponding to that model part are estimated based on the historical sensor data; The historical sensor data corresponding to this model part is input into the trained printhead wear risk prediction model to obtain the printhead wear risk corresponding to this model part. The product of the printhead wear risk and the time weight is calculated to obtain the printing risk parameter corresponding to this part of the model; the time weight is proportional to the predicted printing time parameter.

[0018] As an optional implementation, in a second aspect of the invention, the specific method by which the calculation module estimates the predicted printing time parameters corresponding to the model portion based on the historical sensor data includes: Cluster all the multi-source sensor data in the historical sensor data corresponding to the model part to obtain multiple sensor data sets; the time difference between the acquisition time points of any two multi-source sensor data in each sensor data set is less than a preset time difference threshold; Calculate the maximum time difference between any two of the multi-source sensor data in each of the said sensor data sets; Calculate the average of the maximum time difference across all the sensor data sets to obtain the predicted printing time parameter corresponding to this part of the model.

[0019] As an optional implementation, in a second aspect of the invention, the specific method by which the prediction module predicts the printing success rate of the 3D model data through the 3D printing device based on the printing risk parameters corresponding to all the model parts includes: Calculate the weighted sum of the printing risk parameters corresponding to all the model parts to obtain the overall printing risk corresponding to the 3D model; wherein, the calculation weight of each printing risk parameter is proportional to the degree of priority of the corresponding model part in the preset 3D model printing process; Obtain all risky printing records from the historical printing records of the 3D printing equipment whose predicted printing risk is greater than or equal to the total printing risk; Calculate the ratio of the number of successfully printed records out of all risky printing records to the total number of records, and obtain the printing success rate of the three-dimensional model data when printed by the 3D printing equipment.

[0020] A third aspect of this invention discloses another 3D printing success rate prediction system based on multi-source 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 success rate prediction method based on multi-source 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 success rate prediction method based on multi-source 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 acquires historical multi-source sensor data of 3D printing equipment and data of the 3D model to be printed, determines the historical sensor data corresponding to each part of the model and calculates printing risk parameters, predicts the overall printing success rate, thereby enabling accurate printing success rate assessment based on multi-source correlation and risk quantification, improving the reliability and resource utilization efficiency of 3D printing tasks, and reducing the risk of printing failure caused by misjudgment of risks in part of the model. 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 method for predicting the success rate of 3D printing based on multi-source data, as disclosed in an embodiment of the present invention.

[0025] Figure 2 This is a schematic diagram of the structure of a 3D printing success rate prediction system based on multi-source data disclosed in an embodiment of the present invention.

[0026] Figure 3 This is a schematic diagram of another 3D printing success rate prediction system based on multi-source 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 method and system for predicting 3D printing success rate based on multi-source data. By acquiring historical multi-source sensor data from the 3D printing equipment and the data of the 3D model to be printed, the method determines the historical sensor data corresponding to each part of the model and calculates printing risk parameters to predict the overall printing success rate. This enables accurate printing success rate assessment based on multi-source correlation and risk quantification, improving the reliability and resource utilization efficiency of 3D printing tasks and reducing the risk of printing failure due to misjudgment of risks in parts of the model. Detailed explanations follow.

[0031] Example 1 Please see Figure 1 , Figure 1 This is a flowchart illustrating a 3D printing success rate prediction method based on multi-source data disclosed in an embodiment of the present invention. Figure 1 The described 3D printing success rate prediction method based on multi-source data can be applied to data processing systems / data processing equipment / data processing servers (including local processing servers or cloud processing servers). Figure 1 As shown, this 3D printing success rate prediction method based on multi-source data may include the following operations: 101. Obtain historical multi-source sensor data of the 3D printing equipment and the 3D model data to be printed.

[0032] Optionally, the historical multi-source sensor data may include printhead temperature data, extrusion motor current data, platform vibration data, ambient temperature and humidity data, nozzle pressure data, or photopolymerization exposure intensity data; this invention does not limit the data.

[0033] Optionally, the 3D model data to be printed can be in STL format, OBJ format, AMF format, or sliced ​​G-code file; this invention does not impose any limitations.

[0034] Optionally, this acquisition process can be implemented based on a device log database, a cloud model library, printer local storage, or real-time streaming acquisition; this invention does not limit this.

[0035] 102. Determine the historical sensor data corresponding to each model part of the 3D model data from the historical multi-source sensor data. Optionally, the model can be a functional module, support structure, suspended feature, thin-walled structure, key geometric feature, or user-defined partition; this invention does not impose any limitations on this.

[0036] Optionally, the historical sensor data may be sensor data that overlaps with the printing period of the model section, data marked as related, or data that has been time-aligned; the present invention does not impose any limitations on this.

[0037] 103. Based on historical sensor data, calculate the printing risk parameters corresponding to each model part. Optionally, the printing risk parameters may include warping risk, blockage risk, layer displacement risk, support failure risk, or dimensional deviation risk, which are not limited in this invention.

[0038] Optionally, the calculation process can be implemented based on statistical analysis, machine learning models, or physical simulation, and this invention does not limit it.

[0039] 104. Based on the printing risk parameters corresponding to all model parts, predict the printing success rate of 3D model data when printed using 3D printing equipment.

[0040] Optionally, the printing success rate can be a success probability, success level, or confidence interval of 0-100%, and this invention does not limit it.

[0041] As can be seen, the above-mentioned embodiments of the invention obtain historical multi-source sensor data of the 3D printing equipment and the data of the 3D model to be printed, determine the historical sensor data corresponding to each part of the model and calculate the printing risk parameters, predict the overall printing success rate, thereby achieving accurate printing success rate assessment based on multi-source correlation and risk quantification, improving the reliability and resource utilization efficiency of 3D printing tasks, and reducing the risk of printing failure caused by misjudgment of risk in part of the model.

[0042] As an optional embodiment, the historical multi-source sensor data in the above steps includes multi-source sensor data when the 3D printing device performs printing tasks at multiple historical time points; the multi-source sensor data includes at least one of sound data, image data, temperature data, light reflection data, and motion data.

[0043] As can be seen, the above optional embodiments limit the content of historical multi-source sensor data to comprehensively characterize the historical printing characteristics of 3D printing equipment, assist in achieving accurate printing success rate assessment based on multi-source correlation and risk quantification, improve the reliability and resource utilization efficiency of 3D printing tasks, and reduce the risk of printing failure caused by partial risk misjudgment in the model.

[0044] As an optional embodiment, the step of determining the historical sensing data corresponding to each model portion of the 3D model data in the historical multi-source sensing data in the above steps includes: For each part of the 3D model data, obtain the corresponding model part data and model part parameters; Based on the model part data and model part parameters, determine the matching degree between the model part and each multi-source sensor data; Multi-source sensor data with a matching degree greater than a preset matching degree threshold are identified as the historical sensor data corresponding to this model.

[0045] Optionally, some data in the model can be geometric meshes, slice layer data, voxel representations, or feature vectors; this invention does not impose any limitations.

[0046] Optionally, some parameters of the model may include local volume, surface area, suspension angle, wall thickness, support density, or material requirements; this invention does not impose any limitations on these parameters.

[0047] Optionally, the matching degree can be a comprehensive similarity, a time-feature joint matching degree, or a weighted matching score; this invention does not impose any limitations.

[0048] Optionally, the matching degree calculation can be optimized by combining data quality weights or time decay factors, which is not limited in this invention.

[0049] Optionally, the matching threshold can be a fixed threshold, a dynamic threshold, or a threshold that is adaptively adjusted based on model complexity; this invention does not impose any limitations on this.

[0050] As can be seen, through the above optional embodiments, by calculating the model data and model parameters of the model part, and using them to calculate the matching degree between them and each multi-source sensor data, historical sensor data is accurately screened out. Thus, based on the accurate determination of historical sensor data, the accuracy and comprehensiveness of data matching are improved through matching degree analysis, providing high-quality historical data support for the calculation of printing risk parameters and reducing the risk of risk assessment deviation caused by data mismatch.

[0051] As an optional embodiment, the step above, determining the matching degree between the model part and each multi-source sensing data based on the model part data and model part parameters, includes: For each multi-source sensor data, determine the historical model data of the 3D printing device when it was printing at the time the multi-source sensor data was acquired; The multi-source sensor data is input into the trained model parameter prediction model to obtain the historical model parameters corresponding to each multi-source sensor data. Calculate the first similarity between the model's partial data and the historical model data; Calculate the second similarity between some parameters of the model and the parameters of the historical model; The product of the first similarity and the second similarity is calculated to obtain the matching degree between the model part and the multi-source sensing data.

[0052] Optionally, the historical model data can be extracted from print logs, G-code files, or task metadata; this invention does not limit this.

[0053] Optionally, the model parameter prediction model can be a reverse inference model, a sequence-to-parameter decoder, or a multi-task learning model; this invention does not impose any limitations.

[0054] Optionally, the historical model parameters may include model size, shape complexity, usage classification, or creator identifier, which are not limited in this invention.

[0055] Optionally, the first similarity can be geometric similarity (Hausdorff distance), slice layer similarity, or feature vector cosine similarity; this invention does not impose any limitations.

[0056] Optionally, the second similarity can be the Euclidean distance of the parameter vectors, the normalized distance, or the weighted similarity; this invention does not impose any limitation on this.

[0057] Optionally, the model parameter prediction model can support online updates or periodic retraining to adapt to new device behavior, which is not limited in this invention.

[0058] As can be seen, through the above optional embodiments, historical sensor data is screened by calculating the product of the first similarity between the model partial data and the historical model data and the second similarity between the model partial parameters and the predicted historical model parameters. Based on the accurate determination of historical sensor data, the accuracy and comprehensiveness of data matching are improved by two-dimensional similarity analysis, providing high-quality historical data support for the calculation of printing risk parameters and reducing the risk of risk assessment deviation caused by data mismatch.

[0059] As an optional embodiment, in the above steps, the model parameter prediction model is trained using a training dataset that includes multiple training multi-source sensor data and corresponding model parameter annotations of the model being printed; the model partial parameters, historical model parameters, or model parameter annotations include at least one of model size, model shape, model purpose, model type, model creator, and model volume.

[0060] Optionally, the training dataset can be derived from real print records, simulated print data, or augmented generated data; this invention does not impose any limitations.

[0061] Optionally, the training of the model parameter prediction model can employ supervised learning, weakly supervised learning, or transfer learning strategies, and this invention does not impose any limitations.

[0062] Optionally, the model size can be the file size, bounding box volume, or printing material usage; this invention does not impose any limitations on this.

[0063] Optionally, the model shape can be a complexity index, topological feature, or style classification; this invention does not impose any limitations on this.

[0064] Optionally, the model can be used for industrial parts, consumer products, medical devices, or works of art; this invention does not limit its application.

[0065] As can be seen, the training details and model parameter content of the model parameter prediction model are defined through the above optional embodiments, so as to accurately predict and fully characterize the parameters of the 3D model, assist in realizing accurate printing success rate assessment based on multi-source correlation and risk quantification, improve the reliability and resource utilization efficiency of 3D printing tasks, and reduce the risk of printing failure caused by partial risk misjudgment of the model.

[0066] As an optional embodiment, the step above, calculating the printing risk parameters corresponding to each model part based on historical sensor data, includes: For each model part, the predicted printing time parameter corresponding to that model part is estimated based on historical sensor data; Input the historical sensor data corresponding to this part of the model into the trained printhead wear risk prediction model to obtain the printhead wear risk corresponding to this part of the model; The product of printhead wear risk and time weight is calculated to obtain the printing risk parameters corresponding to this part of the model; the time weight is proportional to the predicted printing time parameter.

[0067] Optionally, the predicted printing time parameter can be the estimated printing duration, number of layers, path length, or material consumption time; this invention does not impose any limitations.

[0068] Optionally, the estimation process can be based on cluster analysis, statistical averaging, or time series regression, and this invention does not limit it.

[0069] Optionally, this time parameter can be used for risk weighting or scheduling optimization, and this invention does not limit it.

[0070] Optionally, the printhead wear risk can be scored based on clogging probability, wear index, or maintenance requirements; this invention does not limit this.

[0071] Optionally, the printhead wear risk prediction model can be a CNN model, an LSTM model, or an ensemble model; this invention does not limit the specific model.

[0072] Optionally, the proportional relationship can be expressed as a linear mapping, a normalized mapping, or a sigmoid function mapping; this invention does not impose any limitations on this.

[0073] Optionally, this weighting design emphasizes the cumulative impact of long-term printing on equipment load, but this invention does not limit it.

[0074] As can be seen, through the above optional embodiments, by inputting historical sensor data into the printhead wear risk prediction model to obtain wear risk and multiplying it with the time weight as the printing risk parameter, a composite assessment of "high risk + long time = high total risk" is achieved. Thus, based on the accurate determination of risk parameters, the risk assessment is improved in terms of pertinence and sensitivity through wear prediction and time weighting, providing accurate partial risk for overall success rate prediction and reducing the risk of misjudgment caused by reliance on a single factor.

[0075] As an optional embodiment, the step of estimating the predicted printing time parameter corresponding to the model based on historical sensor data in the above steps includes: Cluster all the multi-source sensor data in the historical sensor data corresponding to the model part to obtain multiple sensor data sets; optionally, the time difference between the acquisition time points of any two multi-source sensor data in each sensor data set is less than a preset time difference threshold. Calculate the maximum time difference between any two multi-source sensor data points in each sensor dataset; Calculate the average of the maximum time difference across all sensor datasets to obtain the predicted printing time parameter for this part of the model.

[0076] Optionally, the clustering can be based on timestamp-based DBSCAN clustering, sliding time window, or fixed interval grouping; this invention does not impose any limitations.

[0077] Optionally, the sensor data set may represent a continuous printing segment or a stable state segment; this invention does not limit the specific data set.

[0078] Optionally, the clustering process can be optimized by combining noise filtering or minimum set size constraints, which is not limited in this invention.

[0079] Optionally, the maximum time difference can be the span of the set, the time difference between the first and last ends, or the diameter; this invention does not impose any limitations on this.

[0080] Optionally, the calculation process can be implemented based on sorting or traversal, and this invention does not limit it.

[0081] Optionally, the maximum time difference reflects the duration of the printed segment, which is not limited in this invention.

[0082] As can be seen, through the above optional embodiments, the average of the maximum time difference is calculated by clustering historical sensor data as a parameter for predicting printing time. Thus, based on the accurate calculation of printing risk parameters, the continuity and representativeness of time estimation are improved by time clustering analysis, providing scientific time data for weighted risk parameters and reducing the risk of risk deviation caused by improper time estimation.

[0083] As an optional embodiment, the step above, predicting the printing success rate of the 3D model data through a 3D printing device based on the printing risk parameters corresponding to all model parts, includes: Calculate the weighted sum of the printing risk parameters corresponding to all model parts to obtain the overall printing risk of the 3D model; optionally, the calculation weight of each printing risk parameter is proportional to the degree of priority of the corresponding model part in the preset 3D model printing process. Obtain all risky printing records from the historical printing records of the 3D printing equipment whose predicted printing risk is greater than or equal to the overall printing risk; Calculate the ratio of the number of successfully printed records out of all risky printing records to the total number of records, and obtain the printing success rate of 3D model data printed by 3D printing equipment.

[0084] Optionally, the priority of printing can be based on printing order, layer height, path priority, or criticality score; this invention does not limit this.

[0085] Optionally, this proportional weighting emphasizes that early failures have a greater impact on the overall success rate (such as first-layer adhesion), but this invention does not limit this.

[0086] Optionally, the historical print record can be stored in a local database, cloud logs, or a blockchain evidence storage system; this invention does not limit this.

[0087] Optionally, the risk printout may include success / failure labels, fault type, or maintenance records; this invention does not impose any limitations on this.

[0088] As can be seen, through the above optional embodiments, the weighted sum of the printing risk parameters of the model is calculated based on a weight rule proportional to the priority of printing as the overall printing risk, and the printing success rate is predicted based on the success rate ratio of historical risk printing records. Thus, on the basis of accurate success rate prediction, the dynamics and reliability of the assessment are improved by weighting the process sequence and comparing with history, providing forward-looking support for 3D printing decisions and reducing the risk of success rate deviation caused by ignoring historical records.

[0089] Example 2 Please see Figure 2 , Figure 2 This is a schematic diagram of the structure of a 3D printing success rate prediction system based on multi-source data disclosed in an embodiment of the present invention. Figure 2 The described 3D printing success rate prediction system based on multi-source data can be applied to data processing systems / data processing equipment / data processing servers (wherein, the server includes local processing servers or cloud processing servers). For example... Figure 2 As shown, this 3D printing success rate prediction system based on multi-source data may include: The acquisition module 201 is used to acquire historical multi-source sensor data of the 3D printing equipment and the 3D model data to be printed.

[0090] The determination module 202 is used to determine the historical sensing data corresponding to each model part of the three-dimensional model data in the historical multi-source sensing data. The calculation module 203 is used to calculate the printing risk parameters corresponding to each model part based on historical sensor data. The prediction module 204 is used to predict the printing success rate of the 3D model data when printed by a 3D printing device based on the printing risk parameters corresponding to all model parts.

[0091] As can be seen, the above-mentioned embodiments of the invention obtain historical multi-source sensor data of the 3D printing equipment and the data of the 3D model to be printed, determine the historical sensor data corresponding to each part of the model and calculate the printing risk parameters, predict the overall printing success rate, thereby achieving accurate printing success rate assessment based on multi-source correlation and risk quantification, improving the reliability and resource utilization efficiency of 3D printing tasks, and reducing the risk of printing failure caused by misjudgment of risk in part of the model.

[0092] As an optional embodiment, historical multi-source sensor data includes multi-source sensor data when the 3D printing device performs printing tasks at multiple historical time points; the multi-source sensor data includes at least one of sound data, image data, temperature data, light reflection data, and motion data.

[0093] As can be seen, the above optional embodiments limit the content of historical multi-source sensor data to comprehensively characterize the historical printing characteristics of 3D printing equipment, assist in achieving accurate printing success rate assessment based on multi-source correlation and risk quantification, improve the reliability and resource utilization efficiency of 3D printing tasks, and reduce the risk of printing failure caused by partial risk misjudgment in the model.

[0094] As an optional embodiment, the specific method by which the determining module determines the historical sensing data corresponding to each model portion of the 3D model data in historical multi-source sensing data includes: For each part of the 3D model data, obtain the corresponding model part data and model part parameters; Based on the model part data and model part parameters, determine the matching degree between the model part and each multi-source sensor data; Multi-source sensor data with a matching degree greater than a preset matching degree threshold are identified as the historical sensor data corresponding to this model.

[0095] As can be seen, through the above optional embodiments, by calculating the model data and model parameters of the model part, and using them to calculate the matching degree between them and each multi-source sensor data, historical sensor data is accurately screened out. Thus, based on the accurate determination of historical sensor data, the accuracy and comprehensiveness of data matching are improved through matching degree analysis, providing high-quality historical data support for the calculation of printing risk parameters and reducing the risk of risk assessment deviation caused by data mismatch.

[0096] As an optional embodiment, the determining module determines the specific method by which it determines the matching degree between the model part and each multi-source sensing data based on the model part data and model part parameters, including: For each multi-source sensor data, determine the historical model data of the 3D printing device when it was printing at the time the multi-source sensor data was acquired; The multi-source sensor data is input into the trained model parameter prediction model to obtain the historical model parameters corresponding to each multi-source sensor data. Calculate the first similarity between the model's partial data and the historical model data; Calculate the second similarity between some parameters of the model and the parameters of the historical model; The product of the first similarity and the second similarity is calculated to obtain the matching degree between the model part and the multi-source sensing data.

[0097] As can be seen, through the above optional embodiments, historical sensor data is screened by calculating the product of the first similarity between the model partial data and the historical model data and the second similarity between the model partial parameters and the predicted historical model parameters. Based on the accurate determination of historical sensor data, the accuracy and comprehensiveness of data matching are improved by two-dimensional similarity analysis, providing high-quality historical data support for the calculation of printing risk parameters and reducing the risk of risk assessment deviation caused by data mismatch.

[0098] As an optional embodiment, the model parameter prediction model is trained on a training dataset that includes multiple training multi-source sensor data and corresponding model parameter annotations of the model being printed; the model partial parameters, historical model parameters, or model parameter annotations include at least one of model size, model shape, model purpose, model type, model creator, and model volume.

[0099] As can be seen, the training details and model parameter content of the model parameter prediction model are defined through the above optional embodiments, so as to accurately predict and fully characterize the parameters of the 3D model, assist in realizing accurate printing success rate assessment based on multi-source correlation and risk quantification, improve the reliability and resource utilization efficiency of 3D printing tasks, and reduce the risk of printing failure caused by partial risk misjudgment of the model.

[0100] As an optional embodiment, the calculation module calculates the specific method for the printing risk parameters corresponding to each model part based on historical sensor data, including: For each model part, the predicted printing time parameter corresponding to that model part is estimated based on historical sensor data; Input the historical sensor data corresponding to this part of the model into the trained printhead wear risk prediction model to obtain the printhead wear risk corresponding to this part of the model; The product of printhead wear risk and time weight is calculated to obtain the printing risk parameters corresponding to this part of the model; the time weight is proportional to the predicted printing time parameter.

[0101] As can be seen, through the above optional embodiments, by inputting historical sensor data into the printhead wear risk prediction model to obtain wear risk and multiplying it with the time weight as the printing risk parameter, the risk assessment is improved in terms of pertinence and sensitivity by wear prediction and time weighting based on the accurate determination of risk parameters, providing accurate partial risk for overall success rate prediction and reducing the risk of misjudgment caused by reliance on a single factor.

[0102] As an optional embodiment, the calculation module estimates the specific method by which the predicted printing time parameters corresponding to this model part are based on historical sensor data, including: Cluster all the multi-source sensor data in the historical sensor data corresponding to the model part to obtain multiple sensor data sets; optionally, the time difference between the acquisition time points of any two multi-source sensor data in each sensor data set is less than a preset time difference threshold. Calculate the maximum time difference between any two multi-source sensor data points in each sensor dataset; Calculate the average of the maximum time difference across all sensor datasets to obtain the predicted printing time parameter for this part of the model.

[0103] As can be seen, through the above optional embodiments, the average of the maximum time difference is calculated by clustering historical sensor data as a parameter for predicting printing time. Thus, based on the accurate calculation of printing risk parameters, the continuity and representativeness of time estimation are improved by time clustering analysis, providing scientific time data for weighted risk parameters and reducing the risk of risk deviation caused by improper time estimation.

[0104] As an optional embodiment, the prediction module predicts the success rate of printing the 3D model data using a 3D printing device based on the printing risk parameters corresponding to all model parts, including: Calculate the weighted sum of the printing risk parameters corresponding to all model parts to obtain the overall printing risk of the 3D model; optionally, the calculation weight of each printing risk parameter is proportional to the degree of priority of the corresponding model part in the preset 3D model printing process. Obtain all risky printing records from the historical printing records of the 3D printing equipment whose predicted printing risk is greater than or equal to the overall printing risk; Calculate the ratio of the number of successfully printed records out of all risky printing records to the total number of records, and obtain the printing success rate of 3D model data printed by 3D printing equipment.

[0105] As can be seen, through the above optional embodiments, the weighted sum of the printing risk parameters of the model is calculated based on a weight rule proportional to the priority of printing as the overall printing risk, and the printing success rate is predicted based on the success rate ratio of historical risk printing records. Thus, on the basis of accurate success rate prediction, the dynamics and reliability of the assessment are improved by weighting the process sequence and comparing with history, providing forward-looking support for 3D printing decisions and reducing the risk of success rate deviation caused by ignoring historical records.

[0106] Example 3 Please see Figure 3 , Figure 3 This is another 3D printing success rate prediction system based on multi-source data disclosed in the embodiments of the present invention. Figure 3The described 3D printing success rate prediction system based on multi-source data 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, this 3D printing success rate prediction system based on multi-source 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 success rate prediction method based on multi-source data described in Embodiment 1.

[0107] 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 success rate prediction method based on multi-source data described in Embodiment 1.

[0108] 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 success rate prediction method based on multi-source data described in Embodiment 1.

[0109] 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.

[0110] 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.

[0111] 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.

[0112] 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.

[0113] 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.

[0114] 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.

[0115] 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.

[0116] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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.

[0121] 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.

[0122] Finally, it should be noted that the 3D printing success rate prediction method and system based on multi-source 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 method for predicting the success rate of 3D printing based on multi-source data, characterized in that, The method includes: Acquire historical multi-source sensor data of the 3D printing equipment and the 3D model data to be printed; Determine the historical sensing data corresponding to each model part of the three-dimensional model data from the historical multi-source sensing data; Based on the historical sensor data, calculate the printing risk parameters corresponding to each part of the model. Based on the printing risk parameters corresponding to all the model parts, predict the printing success rate of the 3D model data when printed by the 3D printing equipment.

2. The 3D printing success rate prediction method based on multi-source data according to claim 1, characterized in that, The historical multi-source sensor data includes multi-source sensor data when the 3D printing device performs printing tasks at multiple historical time points; the multi-source sensor data includes at least one of sound data, image data, temperature data, light reflection data, and motion data.

3. The 3D printing success rate prediction method based on multi-source data according to claim 1, characterized in that, The step of determining the historical sensing data corresponding to each model portion of the 3D model data from the historical multi-source sensing data includes: For each part of the three-dimensional model data, obtain the corresponding model part data and model part parameters; Based on the model part data and model part parameters, determine the matching degree between the model part and each of the multi-source sensing data; The multi-source sensing data whose matching degree is greater than a preset matching degree threshold are identified as the historical sensing data corresponding to the model part.

4. The 3D printing success rate prediction method based on multi-source data according to claim 3, characterized in that, The step of determining the matching degree between the model part and each of the multi-source sensing data based on the model part data and model part parameters includes: For each of the multi-source sensor data, determine the historical model data of the 3D printing device when it was printing at the time the multi-source sensor data was acquired; The multi-source sensor data is input into the trained model parameter prediction model to obtain the historical model parameters corresponding to each of the multi-source sensor data. Calculate the first similarity between the model partial data and the historical model data; Calculate the second similarity between the partial parameters of the model and the parameters of the historical model; The product of the first similarity and the second similarity is calculated to obtain the matching degree between the model part and the multi-source sensing data.

5. The 3D printing success rate prediction method based on multi-source data according to claim 4, characterized in that, The model parameter prediction model is trained using a training dataset that includes multiple training multi-source sensor data and corresponding model parameter annotations of the model being printed; the model partial parameters, the historical model parameters, or the model parameter annotations include at least one of model size, model shape, model purpose, model type, model creator, and model volume.

6. The 3D printing success rate prediction method based on multi-source data according to claim 1, characterized in that, The step of calculating the printing risk parameters corresponding to each model part based on the historical sensor data includes: For each of the model parts, the predicted printing time parameters corresponding to that model part are estimated based on the historical sensor data; The historical sensor data corresponding to this model part is input into the trained printhead wear risk prediction model to obtain the printhead wear risk corresponding to this model part. The product of the printhead wear risk and the time weight is calculated to obtain the printing risk parameter corresponding to this part of the model; the time weight is proportional to the predicted printing time parameter.

7. The 3D printing success rate prediction method based on multi-source data according to claim 6, characterized in that, The estimation of the predicted printing time parameters corresponding to the model based on the historical sensor data includes: Cluster all the multi-source sensor data in the historical sensor data corresponding to the model part to obtain multiple sensor data sets; the time difference between the acquisition time points of any two multi-source sensor data in each sensor data set is less than a preset time difference threshold; Calculate the maximum time difference between any two of the multi-source sensor data in each of the said sensor data sets; Calculate the average of the maximum time difference across all the sensor data sets to obtain the predicted printing time parameter corresponding to this part of the model.

8. The 3D printing success rate prediction method based on multi-source data according to claim 1, characterized in that, The step of predicting the printing success rate of the 3D model data through the 3D printing equipment based on the printing risk parameters corresponding to all the model parts includes: Calculate the weighted sum of the printing risk parameters corresponding to all the model parts to obtain the overall printing risk corresponding to the 3D model; wherein, the calculation weight of each printing risk parameter is proportional to the degree of priority of the corresponding model part in the preset 3D model printing process; Obtain all risky printing records from the historical printing records of the 3D printing equipment whose predicted printing risk is greater than or equal to the total printing risk; Calculate the ratio of the number of successfully printed records out of all risky printing records to the total number of records, and obtain the printing success rate of the three-dimensional model data when printed by the 3D printing equipment.

9. A 3D printing success rate prediction system based on multi-source data, characterized in that, The system includes: The acquisition module is used to acquire historical multi-source sensor data of the 3D printing equipment and the 3D model data to be printed. The determination module is used to determine the historical sensing data corresponding to each model part of the three-dimensional model data in the historical multi-source sensing data; The calculation module is used to calculate the printing risk parameters corresponding to each part of the model based on the historical sensing data. The prediction module is used to predict the printing success rate of the 3D model data when printed by the 3D printing equipment, based on the printing risk parameters corresponding to all the model parts.

10. A 3D printing success rate prediction system based on multi-source 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 success rate prediction method based on multi-source data as described in any one of claims 1-8.

Images