Printhead management method and system based on historical data analysis

Abstract

The application discloses a kind of printing head management method and system based on historical data analysis, which comprises the following steps: obtaining the historical sensing data of the printing head of additive manufacturing equipment when executing multiple historical tasks;According to the corresponding historical task, all the historical sensing data are classified to obtain multiple sensing data sets;Based on the working state prediction algorithm, the working state corresponding to each sensing data set is predicted;According to the working state corresponding to all the sensing data sets, based on the stability analysis algorithm, the working stability of the printing head is analyzed.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a print head management method and system based on historical data analysis. Background Art

[0002] With the widespread application of additive manufacturing technology in high-precision production, companies and users are increasingly focusing on improving equipment reliability and printing quality by optimizing print head stability. Existing technologies typically collect sensor data from the print head of additive manufacturing equipment and use simple threshold analysis or manual inspection methods to evaluate the print head status to ensure a smooth printing process. Existing solutions lack the ability to classify and analyze historical sensor data and dynamically predict working conditions, making it difficult to accurately assess print head stability. Commonly used static monitoring strategies are unable to adapt to complex printing task scenarios, resulting in insufficient stability analysis accuracy. Print head instability can easily lead to printing defects or equipment failures, limiting the operational reliability and production efficiency of additive manufacturing equipment. It can be seen that existing technologies have defects that need to be addressed urgently. Summary of the Invention

[0003] The technical problem to be solved by the present invention is to provide a print head management method and system based on historical data analysis, which can realize accurate print head stability analysis based on historical data classification and state prediction, improve the operating reliability and printing quality of additive manufacturing equipment, and reduce the risk of printing defects caused by print head instability.

[0004] In order to solve the above technical problems, the first aspect of the present invention discloses a print head management method based on historical data analysis, the method comprising:

[0005] Acquire historical sensor data of a print head of an additive manufacturing device when performing multiple historical tasks;

[0006] Classifying all the historical sensor data according to the corresponding historical tasks to obtain multiple sensor data sets;

[0007] Predicting the working state corresponding to each of the sensor data sets based on a working state prediction algorithm;

[0008] The working stability of the print head is analyzed based on a stability analysis algorithm according to the working states corresponding to all the sensor data sets.

[0009] As an optional embodiment, in the first aspect of the present invention, the historical sensing data includes at least one of temperature data, pressure data, displacement data, velocity data, acceleration data, sound data and image data.

[0010] As an optional embodiment, in the first aspect of the present invention, the classifying all the historical sensor data according to the corresponding historical tasks to obtain multiple sensor data sets includes:

[0011] Obtaining task parameters corresponding to each of the historical tasks;

[0012] According to the task parameters, all the historical sensor data are classified based on a clustering algorithm to obtain multiple sensor data sets.

[0013] As an optional embodiment, in the first aspect of the present invention, the step of classifying all the historical sensor data based on the task parameters based on a clustering algorithm to obtain multiple sensor data sets includes:

[0014] The objective function is set to minimize the number of sensor data sets in the classification results and maximize the amount of data in each sensor data set;

[0015] Setting restrictions includes:

[0016] The parameter similarity between the task parameters corresponding to any two of the historical sensor data in each sensor data set is greater than a first similarity threshold;

[0017] The parameter similarity between the task parameters corresponding to any two pieces of historical sensor data belonging to different sensor data sets is less than a second similarity threshold; the second similarity threshold is less than the first similarity threshold;

[0018] According to the objective function and the constraint conditions, all the historical sensor data are iteratively classified and calculated based on a clustering algorithm until convergence, thereby obtaining a plurality of sensor data sets.

[0019] As an optional embodiment, in the first aspect of the present invention, the task parameters include at least one of printing time point, printing data volume, printing model parameters, printing location, printing time and printing device parameters.

[0020] As an optional embodiment, in the first aspect of the present invention, predicting the working state corresponding to each of the sensor data sets based on the working state prediction algorithm includes:

[0021] For each sensor data set, each piece of historical sensor data in the sensor data set and the corresponding task parameter are input into a trained work failure prediction algorithm model to obtain a predicted failure and a predicted probability corresponding to each piece of historical sensor data in the sensor data set; the work failure prediction algorithm model is trained using a training data set including a plurality of training sensor data and corresponding work failure labels;

[0022] The working state corresponding to the sensor data set is determined based on the predicted fault and the predicted probability corresponding to each of the historical sensor data.

[0023] As an optional embodiment, in the first aspect of the present invention, determining the working state corresponding to the sensor data set based on the predicted fault and predicted probability corresponding to each historical sensor data includes:

[0024] For each of the historical sensor data, determining a fault score corresponding to the predicted fault corresponding to the historical sensor data according to a preset fault scoring rule;

[0025] Calculating a credibility weight proportional to the predicted probability corresponding to the historical sensor data;

[0026] Calculating the inverse of the product of the fault score and the credibility weight to obtain a status score corresponding to the historical sensor data;

[0027] The sum of the status scores corresponding to all the historical sensor data is calculated to obtain the working status corresponding to the sensor data set.

[0028] As an optional embodiment, in the first aspect of the present invention, analyzing the operating stability of the print head based on the operating states corresponding to all the sensor data sets and a stability analysis algorithm includes:

[0029] For each of the sensor data sets, calculating an average value of the parameter similarities between the task parameters corresponding to all two of the historical sensor data in the sensor data set to obtain the data similarity corresponding to the sensor data set;

[0030] Calculating a correction weight proportional to the similarity of the data;

[0031] Calculating the product of the working state corresponding to the sensor data set and the correction weight to obtain a correction state score;

[0032] Calculating the product of the variance value and the average value of the correction state scores corresponding to all the sensor data sets to obtain the working stability parameter of the print head;

[0033] When the working stability parameter is less than a preset parameter threshold, it is determined that the print head is in an working instability state.

[0034] A second aspect of an embodiment of the present invention discloses a print head management system based on historical data analysis, the system comprising:

[0035] an acquisition module, for acquiring historical sensor data of a print head of an additive manufacturing device when performing a plurality of historical tasks;

[0036] a classification module, configured to classify all the historical sensor data according to the corresponding historical tasks to obtain a plurality of sensor data sets;

[0037] A prediction module, configured to predict the working state corresponding to each of the sensor data sets based on a working state prediction algorithm;

[0038] An analysis module is used to analyze the working stability of the print head based on a stability analysis algorithm according to the working states corresponding to all the sensor data sets.

[0039] As an optional embodiment, in the second aspect of the present invention, the historical sensing data includes at least one of temperature data, pressure data, displacement data, velocity data, acceleration data, sound data and image data.

[0040] As an optional embodiment, in the second aspect of the present invention, the classification module classifies all the historical sensor data according to the corresponding historical tasks to obtain multiple sensor data sets, including:

[0041] Obtaining task parameters corresponding to each of the historical tasks;

[0042] According to the task parameters, all the historical sensor data are classified based on a clustering algorithm to obtain multiple sensor data sets.

[0043] As an optional embodiment, in the second aspect of the present invention, the classification module classifies all the historical sensor data based on the clustering algorithm according to the task parameters to obtain multiple sensor data sets, including:

[0044] The objective function is set to minimize the number of sensor data sets in the classification results and maximize the amount of data in each sensor data set;

[0045] Setting restrictions includes:

[0046] The parameter similarity between the task parameters corresponding to any two of the historical sensor data in each sensor data set is greater than a first similarity threshold;

[0047] The parameter similarity between the task parameters corresponding to any two pieces of historical sensor data belonging to different sensor data sets is less than a second similarity threshold; the second similarity threshold is less than the first similarity threshold;

[0048] According to the objective function and the constraint conditions, all the historical sensor data are iteratively classified and calculated based on a clustering algorithm until convergence, thereby obtaining a plurality of sensor data sets.

[0049] As an optional embodiment, in the second aspect of the present invention, the task parameters include at least one of printing time point, printing data volume, printing model parameters, printing location, printing time and printing device parameters.

[0050] As an optional embodiment, in the second aspect of the present invention, the prediction module predicts the specific manner of the working state corresponding to each of the sensor data sets based on the working state prediction algorithm, including:

[0051] For each sensor data set, each piece of historical sensor data in the sensor data set and the corresponding task parameter are input into a trained work failure prediction algorithm model to obtain a predicted failure and a predicted probability corresponding to each piece of historical sensor data in the sensor data set; the work failure prediction algorithm model is trained using a training data set including a plurality of training sensor data and corresponding work failure labels;

[0052] The working state corresponding to the sensor data set is determined based on the predicted fault and the predicted probability corresponding to each of the historical sensor data.

[0053] As an optional embodiment, in the second aspect of the present invention, the prediction module determines the specific manner in which the working state corresponding to the sensor data set is determined based on the predicted fault and predicted probability corresponding to each of the historical sensor data, including:

[0054] For each of the historical sensor data, determining a fault score corresponding to the predicted fault corresponding to the historical sensor data according to a preset fault scoring rule;

[0055] Calculating a credibility weight proportional to the predicted probability corresponding to the historical sensor data;

[0056] Calculating the inverse of the product of the fault score and the credibility weight to obtain a status score corresponding to the historical sensor data;

[0057] The sum of the status scores corresponding to all the historical sensor data is calculated to obtain the working status corresponding to the sensor data set.

[0058] As an optional embodiment, in the second aspect of the present invention, the specific manner in which the analysis module analyzes the operating stability of the print head based on the stability analysis algorithm according to the operating states corresponding to all the sensor data sets includes:

[0059] For each of the sensor data sets, calculating an average value of the parameter similarities between the task parameters corresponding to all two of the historical sensor data in the sensor data set to obtain the data similarity corresponding to the sensor data set;

[0060] Calculating a correction weight proportional to the similarity of the data;

[0061] Calculating the product of the working state corresponding to the sensor data set and the correction weight to obtain a correction state score;

[0062] Calculating the product of the variance value and the average value of the correction state scores corresponding to all the sensor data sets to obtain the working stability parameter of the print head;

[0063] When the working stability parameter is less than a preset parameter threshold, it is determined that the print head is in an working instability state.

[0064] A third aspect of the present invention discloses another print head management system based on historical data analysis, the system comprising:

[0065] a memory storing executable program code;

[0066] a processor coupled to the memory;

[0067] The processor calls the executable program code stored in the memory to execute part or all of the steps in the print head management method based on historical data analysis disclosed in the first aspect of the present invention.

[0068] The fourth aspect of the present invention discloses a computer storage medium, which stores computer instructions. When the computer instructions are called, they are used to execute some or all of the steps in the print head management method based on historical data analysis disclosed in the first aspect of the present invention.

[0069] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0070] The present invention obtains the sensor data of the print head of the additive manufacturing equipment in historical tasks and classifies it into multiple sensor data sets. The working status of each set is determined based on the working status prediction algorithm and the working stability of the print head is evaluated through the stability analysis algorithm. Thus, accurate print head stability analysis based on historical data classification and status prediction can be achieved, thereby improving the operational reliability and printing quality of the additive manufacturing equipment and reducing the risk of printing defects caused by unstable print heads. BRIEF DESCRIPTION OF THE DRAWINGS

[0071] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0072] Figure 1This is a flow chart of a print head management method based on historical data analysis disclosed in an embodiment of the present invention.

[0073] Figure 2 This is a schematic structural diagram of a print head management system based on historical data analysis disclosed in an embodiment of the present invention.

[0074] Figure 3 This is a schematic structural diagram of another print head management system based on historical data analysis disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0075] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0076] The terms "first," "second," and so on, in the description and claims of the present invention and the accompanying drawings are used to distinguish between different objects, not to describe a specific order. Furthermore, the terms "including," "having," and any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, apparatus, product, or device comprising a series of steps or elements is not limited to the listed steps or elements but may optionally include steps or elements not listed, or may optionally include other steps or elements inherent to the process, method, product, or device.

[0077] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present invention. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute a separate or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0078] This invention discloses a printhead management method and system based on historical data analysis. By acquiring sensor data from the printhead of an additive manufacturing device during historical tasks and classifying it into multiple sensor data sets, the operating state of each set is determined using an operating state prediction algorithm, and the operating stability of the printhead is evaluated using a stability analysis algorithm. This enables accurate printhead stability analysis based on historical data classification and state prediction, improving the operational reliability and print quality of the additive manufacturing device and reducing the risk of print defects caused by printhead instability. These are described in detail below.

[0079] Example 1

[0080] See also Figure 1 , Figure 1 This is a flow chart of a print head management method based on historical data analysis disclosed in an embodiment of the present invention. Figure 1 The print head management method based on historical data analysis described above can be applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 1 As shown, the print head management method based on historical data analysis may include the following operations:

[0081] 101. Obtain historical sensor data of a print head of an additive manufacturing device when performing multiple historical tasks.

[0082] Optionally, the historical task may be a 3D printing task, a material deposition task, or a multi-material printing task, which is not limited in the present invention.

[0083] Optionally, the acquisition process may be implemented based on sensor acquisition, device log extraction, or database query, which is not limited in the present invention.

[0084] 102. According to corresponding historical tasks, classify all historical sensor data to obtain multiple sensor data sets.

[0085] Optionally, the classification may be based on task type, task parameter or time period, which is not limited in the present invention.

[0086] Optionally, the sensing data set may be a single-task data set, a mixed-task data set, or a dynamic data set, which is not limited in the present invention.

[0087] 103. Based on the working state prediction algorithm, predict the working state corresponding to each sensor data set.

[0088] Optionally, the working status prediction algorithm may be a neural network algorithm, a classification algorithm or a regression algorithm, which is not limited in the present invention.

[0089] Optionally, the working state may include a normal state, an abnormal state or a fault state, which is not limited in the present invention.

[0090] 104. Analyze the working stability of the print head based on the stability analysis algorithm according to the working status corresponding to all sensor data sets.

[0091] Optionally, the stability analysis algorithm may be a statistical analysis algorithm, a time series analysis algorithm, or a machine learning algorithm, which is not limited in the present invention.

[0092] Optionally, the working stability may be a stability score, a variance index or a risk level, which is not limited in the present invention.

[0093] It can be seen that the above-mentioned invention embodiment obtains the sensor data of the print head of the additive manufacturing equipment in historical tasks and classifies it into multiple sensor data sets, determines the working status of each set based on the working status prediction algorithm, and evaluates the working stability of the print head through the stability analysis algorithm, thereby realizing accurate print head stability analysis based on historical data classification and status prediction, improving the operating reliability and printing quality of the additive manufacturing equipment, and reducing the risk of printing defects caused by unstable print head.

[0094] As an optional embodiment, in the above steps, the historical sensing data includes at least one of temperature data, pressure data, displacement data, velocity data, acceleration data, sound data and image data.

[0095] It can be seen that through the above optional embodiments, the content of historical sensor data is limited to comprehensively characterize the sensor characteristics of the additive manufacturing equipment when performing printing tasks, assist in realizing accurate print head stability analysis based on historical data classification and state prediction, improve the operating reliability and printing quality of the additive manufacturing equipment, and reduce the risk of printing defects caused by unstable print heads.

[0096] As an optional embodiment, in the above steps, all historical sensor data are classified according to corresponding historical tasks to obtain multiple sensor data sets, including:

[0097] Get the task parameters corresponding to each historical task;

[0098] According to the task parameters, all historical sensor data are classified based on the clustering algorithm to obtain multiple sensor data sets.

[0099] Optionally, the task parameters may include printing speed, material type, printing accuracy or task duration, which is not limited in the present invention.

[0100] Optionally, the clustering algorithm may be a K-means algorithm, a hierarchical clustering algorithm, or a DBSCAN algorithm, which is not limited in the present invention.

[0101] Optionally, the classification process may be implemented based on feature similarity, task relevance, or data distribution, which is not limited in the present invention.

[0102] It can be seen that through the above optional embodiments, by using the clustering algorithm to classify historical sensor data according to historical task parameters to generate a sensor data set, the targetedness and accuracy of data classification are improved through clustering optimization driven by task parameters on the basis of precise print head stability analysis, providing a high-quality data foundation for subsequent working status prediction and reducing the risk of stability assessment errors caused by improper data classification.

[0103] As an optional embodiment, in the above steps, all historical sensor data are classified based on the task parameters using a clustering algorithm to obtain multiple sensor data sets, including:

[0104] The objective function is set to minimize the number of sensor data sets in the classification results and maximize the amount of data in each sensor data set;

[0105] Setting restrictions includes:

[0106] The parameter similarity between the task parameters corresponding to any two historical sensor data in each sensor data set is greater than a first similarity threshold;

[0107] The parameter similarity between the task parameters corresponding to any two pieces of historical sensor data belonging to different sensor data sets is less than a second similarity threshold; optionally, the second similarity threshold is less than the first similarity threshold;

[0108] According to the objective function and constraints, all historical sensor data are iteratively classified based on the clustering algorithm until convergence, and multiple sensor data sets are obtained.

[0109] Optionally, the parameter similarity may be cosine similarity, Euclidean distance, or Jaccard coefficient, which is not limited in the present invention.

[0110] Optionally, the first similarity threshold or the second similarity threshold may be a fixed threshold, a dynamic threshold, or a threshold adjusted based on task characteristics, which is not limited in the present invention.

[0111] Optionally, the convergence condition may be cluster stability, objective function convergence, or iteration number limit, which is not limited in the present invention.

[0112] It can be seen that through the above optional embodiments, by setting the objective function to minimize the number of sensor data sets and maximize the amount of data in the set, combined with the parameter similarity constraint, the sensor data set is generated by iterative classification based on the clustering algorithm, thereby improving the accuracy and consistency of data classification through multi-objective optimization and similarity constraints on the basis of precise print head stability analysis, providing more reliable data support for working status prediction, and reducing the analysis risk caused by classification deviation.

[0113] As an optional embodiment, in the above steps, the task parameters include at least one of printing time point, printing data volume, printing model parameters, printing location, printing time and printing device parameters.

[0114] It can be seen that through the above optional embodiments, the content of the task parameters is limited to comprehensively characterize the task characteristics of the additive manufacturing equipment when performing printing tasks, assist in realizing accurate print head stability analysis based on historical data classification and state prediction, improve the operating reliability and printing quality of the additive manufacturing equipment, and reduce the risk of printing defects caused by unstable print heads.

[0115] As an optional embodiment, in the above step, predicting the working state corresponding to each sensor data set based on the working state prediction algorithm includes:

[0116] For each sensor data set, each historical sensor data and corresponding task parameters in the sensor data set are input into a trained work failure prediction algorithm model to obtain a predicted failure and a predicted probability corresponding to each historical sensor data in the sensor data set; optionally, the work failure prediction algorithm model is trained using a training data set including a plurality of training sensor data and corresponding work failure labels;

[0117] According to the predicted fault and predicted probability corresponding to each historical sensor data, the working state corresponding to the sensor data set is determined.

[0118] Optionally, the working fault prediction algorithm model may be a neural network model, a classification model or a regression model, which is not limited in the present invention.

[0119] Optionally, the predicted fault may include temperature anomaly, pressure anomaly or mechanical failure, which is not limited in the present invention.

[0120] Optionally, the training data set may include historical fault data, simulation data, or labeled data, which is not limited in the present invention.

[0121] It can be seen that through the above-mentioned optional embodiments, by inputting the historical sensor data and task parameters in the sensor data set into the working fault prediction algorithm model to predict faults and probabilities and determine the working status, the accuracy and refinement of the working status assessment are improved through the fault prediction model on the basis of accurate print head stability analysis, providing accurate status data for stability analysis, and reducing the risk of print head failure caused by misjudgment of status.

[0122] As an optional embodiment, in the above step, determining the working state corresponding to the sensor data set according to the predicted fault and predicted probability corresponding to each historical sensor data includes:

[0123] For each historical sensor data, determine the fault score corresponding to the predicted fault corresponding to the historical sensor data according to the preset fault scoring rules;

[0124] Calculating a credibility weight proportional to the predicted probability corresponding to the historical sensor data;

[0125] Calculate the inverse of the product of the fault score and the credibility weight to obtain the status score corresponding to the historical sensor data;

[0126] The sum of the status scores corresponding to all historical sensor data is calculated to obtain the working status corresponding to the sensor data set.

[0127] Optionally, the fault scoring rule may be a scoring table based on the fault type, a weighted scoring rule, or a dynamic scoring model, which is not limited in the present invention.

[0128] Optionally, the fault score may be a numerical score, a grade score, or a risk index, which is not limited in the present invention.

[0129] Optionally, the credibility weight may be a linear weight, an exponential weight, or a logarithmic weight, which is not limited in the present invention.

[0130] Optionally, the calculation process of the credibility weight may be implemented based on probability normalization, weight adjustment, or data analysis, which is not limited in the present invention.

[0131] It can be seen that through the above optional embodiments, by determining the status score of historical sensor data according to the fault scoring rules and predicted probability and calculating the total score in the set as the working status, the accuracy and reliability of the working status judgment are improved through score weighting and comprehensive evaluation on the basis of precise print head stability analysis, providing a more accurate status basis for print head stability analysis and reducing the risk of status assessment deviation.

[0132] As an optional embodiment, in the above steps, analyzing the working stability of the print head based on the working status corresponding to all sensor data sets and using a stability analysis algorithm includes:

[0133] For each sensor data set, calculate the average value of the parameter similarities between the task parameters corresponding to all pairwise historical sensor data in the sensor data set to obtain the data similarity corresponding to the sensor data set;

[0134] Calculate the correction weight proportional to the data similarity;

[0135] Calculate the product of the working state corresponding to the sensor data set and the correction weight to obtain a correction state score;

[0136] Calculate the product of the variance and the average value of the correction state scores corresponding to all sensor data sets to obtain the working stability parameter of the print head;

[0137] When the working stability parameter is less than a preset parameter threshold, it is determined that the print head is in an working instability state.

[0138] Optionally, the parameter threshold may be a fixed threshold, a dynamic threshold, or a threshold adjusted based on device performance, which is not limited in the present invention.

[0139] Optionally, the determination process may be implemented based on threshold comparison, classification model or anomaly detection, which is not limited in the present invention.

[0140] Optionally, the unstable working situation may trigger an alarm, record a log, or automatically adjust an operation, which is not limited in the present invention.

[0141] It can be seen that through the above optional embodiments, the correction weight is determined and the correction status score is generated by calculating the average similarity of the task parameters in the sensor data set, and the product of the variance and the average value of the correction status score is combined to evaluate the working stability of the print head. Therefore, on the basis of precise print head stability analysis, the accuracy and robustness of the stability evaluation are further optimized through similarity weighting and statistical analysis, thereby reducing the risk of misjudgment of stability due to data fluctuations.

[0142] Example 2

[0143] See also Figure 2 , Figure 2 This is a schematic diagram of the structure of a print head management system based on historical data analysis disclosed in an embodiment of the present invention. Figure 2 The print head management system based on historical data analysis described above can be applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 2 As shown, the print head management system based on historical data analysis may include:

[0144] The acquisition module 201 is used to acquire historical sensor data of a print head of an additive manufacturing device when performing multiple historical tasks.

[0145] The classification module 202 is configured to classify all historical sensor data according to corresponding historical tasks to obtain multiple sensor data sets.

[0146] The prediction module 203 is configured to predict the working state corresponding to each sensor data set based on a working state prediction algorithm.

[0147] The analysis module 204 is configured to analyze the working stability of the print head based on the working states corresponding to all sensor data sets and a stability analysis algorithm.

[0148] It can be seen that the above-mentioned invention embodiment obtains the sensor data of the print head of the additive manufacturing equipment in historical tasks and classifies it into multiple sensor data sets, determines the working status of each set based on the working status prediction algorithm, and evaluates the working stability of the print head through the stability analysis algorithm, thereby realizing accurate print head stability analysis based on historical data classification and status prediction, improving the operating reliability and printing quality of the additive manufacturing equipment, and reducing the risk of printing defects caused by unstable print head.

[0149] As an optional embodiment, the historical sensing data includes at least one of temperature data, pressure data, displacement data, velocity data, acceleration data, sound data and image data.

[0150] It can be seen that through the above optional embodiments, the content of historical sensor data is limited to comprehensively characterize the sensor characteristics of the additive manufacturing equipment when performing printing tasks, assist in realizing accurate print head stability analysis based on historical data classification and state prediction, improve the operating reliability and printing quality of the additive manufacturing equipment, and reduce the risk of printing defects caused by unstable print heads.

[0151] As an optional embodiment, the classification module classifies all historical sensor data according to the corresponding historical tasks to obtain multiple sensor data sets in a specific manner including:

[0152] Get the task parameters corresponding to each historical task;

[0153] According to the task parameters, all historical sensor data are classified based on the clustering algorithm to obtain multiple sensor data sets.

[0154] It can be seen that through the above optional embodiments, by using the clustering algorithm to classify historical sensor data according to historical task parameters to generate a sensor data set, the targetedness and accuracy of data classification are improved through clustering optimization driven by task parameters on the basis of precise print head stability analysis, providing a high-quality data foundation for subsequent working status prediction and reducing the risk of stability assessment errors caused by improper data classification.

[0155] As an optional embodiment, the classification module classifies all historical sensor data based on the clustering algorithm according to the task parameters to obtain multiple sensor data sets, including:

[0156] The objective function is set to minimize the number of sensor data sets in the classification results and maximize the amount of data in each sensor data set;

[0157] Setting restrictions includes:

[0158] The parameter similarity between the task parameters corresponding to any two historical sensor data in each sensor data set is greater than a first similarity threshold;

[0159] The parameter similarity between the task parameters corresponding to any two pieces of historical sensor data belonging to different sensor data sets is less than a second similarity threshold; optionally, the second similarity threshold is less than the first similarity threshold;

[0160] According to the objective function and constraints, all historical sensor data are iteratively classified based on the clustering algorithm until convergence, and multiple sensor data sets are obtained.

[0161] It can be seen that through the above optional embodiments, by setting the objective function to minimize the number of sensor data sets and maximize the amount of data in the set, combined with the parameter similarity constraint, the sensor data set is generated by iterative classification based on the clustering algorithm, thereby improving the accuracy and consistency of data classification through multi-objective optimization and similarity constraints on the basis of precise print head stability analysis, providing more reliable data support for working status prediction, and reducing the analysis risk caused by classification deviation.

[0162] As an optional embodiment, the task parameters include at least one of a printing time point, a printing data volume, a printing model parameter, a printing location, a printing time, and a printing device parameter.

[0163] It can be seen that through the above optional embodiments, the content of the task parameters is limited to comprehensively characterize the task characteristics of the additive manufacturing equipment when performing printing tasks, assist in realizing accurate print head stability analysis based on historical data classification and state prediction, improve the operating reliability and printing quality of the additive manufacturing equipment, and reduce the risk of printing defects caused by unstable print heads.

[0164] As an optional embodiment, the prediction module predicts the specific manner of the working state corresponding to each sensor data set based on the working state prediction algorithm, including:

[0165] For each sensor data set, each historical sensor data and corresponding task parameters in the sensor data set are input into a trained work failure prediction algorithm model to obtain a predicted failure and a predicted probability corresponding to each historical sensor data in the sensor data set; optionally, the work failure prediction algorithm model is trained using a training data set including a plurality of training sensor data and corresponding work failure labels;

[0166] According to the predicted fault and predicted probability corresponding to each historical sensor data, the working state corresponding to the sensor data set is determined.

[0167] It can be seen that through the above-mentioned optional embodiments, by inputting the historical sensor data and task parameters in the sensor data set into the working fault prediction algorithm model to predict faults and probabilities and determine the working status, the accuracy and refinement of the working status assessment are improved through the fault prediction model on the basis of accurate print head stability analysis, providing accurate status data for stability analysis, and reducing the risk of print head failure caused by misjudgment of status.

[0168] As an optional embodiment, the prediction module determines the specific manner in which the working state corresponding to the sensor data set is determined based on the predicted fault and predicted probability corresponding to each historical sensor data set, including:

[0169] For each historical sensor data, determine the fault score corresponding to the predicted fault corresponding to the historical sensor data according to the preset fault scoring rules;

[0170] Calculating a credibility weight proportional to the predicted probability corresponding to the historical sensor data;

[0171] Calculate the inverse of the product of the fault score and the credibility weight to obtain the status score corresponding to the historical sensor data;

[0172] The sum of the status scores corresponding to all historical sensor data is calculated to obtain the working status corresponding to the sensor data set.

[0173] It can be seen that through the above optional embodiments, by determining the status score of historical sensor data according to the fault scoring rules and predicted probability and calculating the total score in the set as the working status, the accuracy and reliability of the working status judgment are improved through score weighting and comprehensive evaluation on the basis of precise print head stability analysis, providing a more accurate status basis for print head stability analysis and reducing the risk of status assessment deviation.

[0174] As an optional embodiment, the analysis module analyzes the working stability of the print head based on the working status corresponding to all sensor data sets and the stability analysis algorithm, including:

[0175] For each sensor data set, calculate the average value of the parameter similarities between the task parameters corresponding to all pairwise historical sensor data in the sensor data set to obtain the data similarity corresponding to the sensor data set;

[0176] Calculate the correction weight proportional to the data similarity;

[0177] Calculate the product of the working state corresponding to the sensor data set and the correction weight to obtain a correction state score;

[0178] Calculate the product of the variance and the average value of the correction state scores corresponding to all sensor data sets to obtain the working stability parameter of the print head;

[0179] When the working stability parameter is less than a preset parameter threshold, it is determined that the print head is in an working instability state.

[0180] It can be seen that through the above optional embodiments, the correction weight is determined and the correction status score is generated by calculating the average similarity of the task parameters in the sensor data set, and the product of the variance and the average value of the correction status score is combined to evaluate the working stability of the print head. Therefore, on the basis of precise print head stability analysis, the accuracy and robustness of the stability evaluation are further optimized through similarity weighting and statistical analysis, thereby reducing the risk of misjudgment of stability due to data fluctuations.

[0181] Example 3

[0182] See also Figure 3 , Figure 3 This is another print head management system based on historical data analysis disclosed in an embodiment of the present invention. Figure 3 The print head management system based on historical data analysis is applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 3 As shown, the print head management system based on historical data analysis may include:

[0183] A memory 301 storing executable program code;

[0184] a processor 302 coupled to the memory 301;

[0185] The processor 302 calls the executable program code stored in the memory 301 to execute the steps of the print head management method based on historical data analysis described in the first embodiment.

[0186] Example 4

[0187] An embodiment of the present invention discloses a computer-readable storage medium storing a computer program for electronic data exchange, wherein the computer program enables a computer to execute the steps of the print head management method based on historical data analysis described in the first embodiment.

[0188] Example 5

[0189] An embodiment of the present 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 enable a computer to execute the steps of the print head management method based on historical data analysis described in the first embodiment.

[0190] The foregoing description of specific embodiments of the present disclosure is intended to illustrate a method for performing a multi-tasking process. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in an order different from that described in the embodiments and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order shown or the sequential order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0191] The systems, devices, modules, or units described in the above embodiments may be implemented by computer chips or entities, or by products having certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0192] For the convenience of description, the above devices are described as being divided into various units according to their functions. Of course, when implementing this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0193] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems, or computer program products. Therefore, the embodiments of this specification may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the embodiments of this specification may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0194] This specification is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of this specification. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0195] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0196] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0197] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0198] Memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0199] Computer-readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, program modules 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 technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory media such as modulated data signals and carrier waves.

[0200] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0201] This specification may be described in the general context of computer-executable instructions, such as program modules, executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, and the like that perform specific tasks or implement specific abstract data types. This specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media, including storage devices.

[0202] The various embodiments in this specification are described in a progressive manner. Similar parts between the various embodiments can be referred to in conjunction with each other. Each embodiment focuses on the differences between the other embodiments. In particular, the system embodiments are generally similar to the method embodiments, so the description is relatively simple. For relevant parts, refer to the description of the method embodiments.

[0203] Finally, it should be noted that the print head management method and system based on historical data analysis disclosed in the embodiments of the present invention are only preferred embodiments of the present invention, and are only used to illustrate the technical solutions of the present invention, rather than to limit them. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments can still be modified, or some of the technical features therein can be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A print head management method based on historical data analysis, characterized in that: The method comprises: Acquire historical sensor data of a print head of an additive manufacturing device when performing multiple historical tasks; Classifying all the historical sensor data according to the corresponding historical tasks to obtain multiple sensor data sets; Predicting the working state corresponding to each of the sensor data sets based on a working state prediction algorithm; Analyzing the working stability of the print head based on a stability analysis algorithm according to the working states corresponding to all the sensor data sets includes: For each of the sensor data sets, calculating an average of the parameter similarities between all task parameters corresponding to each pair of the historical sensor data in the sensor data set to obtain the data similarity corresponding to the sensor data set; Calculating a correction weight proportional to the similarity of the data; Calculating the product of the working state corresponding to the sensor data set and the correction weight to obtain a correction state score; Calculating the product of the variance value and the average value of the correction state scores corresponding to all the sensor data sets to obtain the working stability parameter of the print head; When the working stability parameter is less than a preset parameter threshold, it is determined that the print head is in an working instability state.

2. The print head management method based on historical data analysis according to claim 1, characterized in that: The historical sensing data includes at least one of temperature data, pressure data, displacement data, velocity data, acceleration data, sound data, and image data.

3. The print head management method based on historical data analysis according to claim 1, characterized in that: The classifying all the historical sensor data according to the corresponding historical tasks to obtain multiple sensor data sets includes: Obtaining task parameters corresponding to each of the historical tasks; According to the task parameters, all the historical sensor data are classified based on a clustering algorithm to obtain multiple sensor data sets.

4. The print head management method based on historical data analysis according to claim 3, characterized in that: The step of classifying all the historical sensor data based on the task parameters and a clustering algorithm to obtain a plurality of sensor data sets includes: The objective function is set to minimize the number of sensor data sets in the classification results and maximize the amount of data in each sensor data set; Setting restrictions includes: The parameter similarity between the task parameters corresponding to any two of the historical sensor data in each sensor data set is greater than a first similarity threshold; The parameter similarity between the task parameters corresponding to any two pieces of historical sensor data belonging to different sensor data sets is less than a second similarity threshold; the second similarity threshold is less than the first similarity threshold; According to the objective function and the constraint conditions, all the historical sensor data are iteratively classified and calculated based on a clustering algorithm until convergence, thereby obtaining a plurality of sensor data sets.

5. The print head management method based on historical data analysis according to claim 3, characterized in that: The task parameters include at least one of a printing time point, a printing data volume, a printing model parameter, a printing location, a printing time, and a printing device parameter.

6. The print head management method based on historical data analysis according to claim 4, characterized in that: The predicting of the working state corresponding to each set of sensor data based on the working state prediction algorithm includes: For each sensor data set, each piece of historical sensor data in the sensor data set and the corresponding task parameter are input into a trained work failure prediction algorithm model to obtain a predicted failure and a predicted probability corresponding to each piece of historical sensor data in the sensor data set; the work failure prediction algorithm model is trained using a training data set including a plurality of training sensor data and corresponding work failure labels; The working state corresponding to the sensor data set is determined based on the predicted fault and the predicted probability corresponding to each of the historical sensor data.

7. The print head management method based on historical data analysis according to claim 6, characterized in that: Determining the working state corresponding to the sensor data set based on the predicted fault and predicted probability corresponding to each historical sensor data includes: For each of the historical sensor data, determining a fault score corresponding to the predicted fault corresponding to the historical sensor data according to a preset fault scoring rule; Calculating a credibility weight proportional to the predicted probability corresponding to the historical sensor data; Calculating the inverse of the product of the fault score and the credibility weight to obtain a status score corresponding to the historical sensor data; The sum of the status scores corresponding to all the historical sensor data is calculated to obtain the working status corresponding to the sensor data set.

8. A print head management system based on historical data analysis, characterized in that: The system comprises: an acquisition module, for acquiring historical sensor data of a print head of an additive manufacturing device when performing a plurality of historical tasks; a classification module, configured to classify all the historical sensor data according to the corresponding historical tasks to obtain a plurality of sensor data sets; A prediction module, configured to predict the working state corresponding to each of the sensor data sets based on a working state prediction algorithm; An analysis module is configured to analyze the working stability of the print head based on the working status corresponding to all the sensor data sets and a stability analysis algorithm, including: For each of the sensor data sets, calculating an average of the parameter similarities between all task parameters corresponding to each pair of the historical sensor data in the sensor data set to obtain the data similarity corresponding to the sensor data set; Calculating a correction weight proportional to the similarity of the data; Calculating the product of the working state corresponding to the sensor data set and the correction weight to obtain a correction state score; Calculating the product of the variance value and the average value of the correction state scores corresponding to all the sensor data sets to obtain the working stability parameter of the print head; When the working stability parameter is less than a preset parameter threshold, it is determined that the print head is in an working instability state.

9. A print head management system based on historical data analysis, characterized in that: The system comprises: a memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the print head management method based on historical data analysis according to any one of claims 1 to 7.

Images