Method and system for processing abnormal operation of photocuring 3D printing

Abstract

The invention discloses a processing method and system for abnormal operation of photocuring 3D printing. The method comprises the steps that parameter values of all operation parameters in the printing process of photocuring printing equipment are collected; according to the parameter values, abnormal operation parameters in all the operation parameters are searched for; if the abnormal operation parameters are not found, inputting all the operation parameters and parameter values thereof into a pre-trained AI-based first printing fault prediction model, and predicting a potential printing fault type and a fault degree thereof; according to the printing fault type and the fault degree of the printing fault type, the parameter value of each operation parameter is adjusted, so that the predicted printing fault type is free of faults, and abnormal operation parameters do not exist in the operation parameters. By utilizing the embodiment of the invention, the timeliness and accuracy of fault detection can be improved by acquiring the real-time operation parameters, identifying abnormal conditions and predicting the fault type and degree based on the AI model, the automatic adjustment of the printing parameters is realized, and the stability and reliability of the printing process are ensured.

Description

Technical Field

[0001] The present invention belongs to the technical field of 3D printing, and in particular to a method and system for processing abnormal operation of photocuring 3D printing. Background Art

[0002] With the rapid development of 3D printing technology, light-curing 3D printing, as an important branch, has been widely used in the fields of medical, aerospace, automobile manufacturing and consumer goods due to its high precision and high efficiency. However, various printing devices often face various potential failures in actual operation, which not only affect the printing quality, but also may cause equipment damage, material waste, and even production stagnation, bringing huge economic losses to enterprises.

[0003] Traditional fault detection methods rely heavily on experience and manual monitoring, and usually make judgments and handle problems after they occur. This passive management method is unable to detect and prevent problems in a timely manner, resulting in inefficient troubleshooting and high maintenance costs. Summary of the invention

[0004] The purpose of the present invention is to provide a method and system for processing abnormal operation of photocuring 3D printing to address the deficiencies in the prior art. The method can collect real-time operating parameters, identify abnormal conditions, and predict the type and degree of faults based on AI models, thereby not only improving the timeliness and accuracy of fault detection, but also realizing automatic adjustment of printing parameters to ensure a stable and reliable printing process.

[0005] An embodiment of the present application provides a method for processing abnormal operation of photo-curing 3D printing, the method comprising:

[0006] Collect parameter values ​​of various operating parameters of the light-curing printing equipment during the printing process;

[0007] According to the parameter values, searching for abnormal operating parameters among the operating parameters;

[0008] If no abnormal operating parameters are found, all operating parameters and their parameter values ​​are input into a pre-trained AI-based first printing fault prediction model to predict the potential printing fault type and fault degree of the light-curing printing device, wherein the first printing fault prediction model is trained based on all historical operating parameters and their parameter values, corresponding historical actual fault modes and fault degrees;

[0009] According to the printing fault type and the fault degree thereof, the parameter value of each operating parameter is adjusted so that the predicted printing fault type reaches no fault and there is no abnormal operating parameter in each operating parameter.

[0010] Optionally, the method further includes:

[0011] Before adjusting the parameter values ​​of various operating parameters according to the printing fault type and the fault degree thereof, if abnormal operating parameters are found, the abnormal operating parameters and their parameter values ​​are input into a pre-trained AI-based second printing fault prediction model to predict the current printing fault type and the fault degree of the light-curing printing device, wherein the second printing fault prediction model is trained based on historical abnormal operating parameters and their parameter values, and corresponding historical actual failure modes and their failure degrees.

[0012] Optionally, adjusting the parameter value of each operating parameter according to the printing fault type and fault degree thereof includes:

[0013] Searching, from a printing device database, a number of historical actual printing fault types and fault degrees whose similarity with the printing fault type and fault degree is higher than a preset threshold;

[0014] Obtaining historical parameter values ​​of operating parameters before fault adjustment and historical parameter values ​​of operating parameters after fault adjustment corresponding to several historical actual printing fault types and fault degrees as historical fault adjustment strategies;

[0015] Based on each group of historical fault adjustment strategies, current operating parameters of the light-curing printing device are adjusted, wherein the parameter values ​​of each operating parameter after adjustment are within a normal range;

[0016] Input all adjusted operating parameters and their parameter values ​​into a pre-trained AI-based first printing fault prediction model to predict the potential printing fault type and fault degree of the light-curing printing device, and determine whether the predicted printing fault type reaches no fault;

[0017] If the predicted printing fault type does not reach the state of no fault, the process returns to the step of adjusting the current operating parameters of the light-curing printing device based on the historical fault adjustment strategies of each group until the predicted printing fault type reaches the state of no fault.

[0018] Optionally, adjusting the current operating parameters of the light-curing printing device based on each group of historical fault adjustment strategies includes:

[0019] Determine the weight of each group of historical fault adjustment strategies according to the similarity between the historical actual printing fault type and fault degree in each group of historical fault adjustment strategies and the printing fault type and fault degree;

[0020] According to the historical parameter values ​​and weights of the operating parameters after fault adjustment in each group of historical fault adjustment strategies, the parameter values ​​of the operating parameters of the light-curing printing device after adjustment are calculated.

[0021] Optionally, adjusting the current operating parameters of the light-curing printing device based on each group of historical fault adjustment strategies includes:

[0022] The average value or median value of the historical parameter value of each operating parameter after the fault adjustment in each group of historical fault adjustment strategies is calculated as the parameter value of the operating parameter of the light-curing printing device after adjustment.

[0023] Another embodiment of the present application provides a system for processing abnormal operation of photo-curing 3D printing, the system comprising:

[0024] The acquisition module is used to acquire the parameter values ​​of various operating parameters of the light-curing printing device during the printing process;

[0025] A search module, used for searching abnormal operating parameters among various operating parameters according to the parameter values;

[0026] A first prediction module is used for inputting all the operating parameters and their parameter values ​​into a pre-trained AI-based first printing fault prediction model to predict the potential printing fault type and fault degree of the light-curing printing device if no abnormal operating parameters are found, wherein the first printing fault prediction model is trained based on all historical operating parameters and their parameter values, corresponding historical actual fault modes and fault degrees;

[0027] The adjustment module is used to adjust the parameter value of each operating parameter according to the printing fault type and the fault degree, so that the predicted printing fault type reaches no fault and there is no abnormal operating parameter in each operating parameter.

[0028] Yet another embodiment of the present application provides a storage medium, wherein the storage medium stores a computer program, wherein the computer program is configured to execute any of the above methods when running.

[0029] Yet another embodiment of the present application provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute any of the methods described above.

[0030] Compared with the prior art, the present invention provides a method for processing abnormal operation of photocuring 3D printing, which collects parameter values ​​of various operating parameters during the printing process of the photocuring printing device; searches for abnormal operating parameters in each operating parameter according to the parameter values; if no abnormal operating parameter is found, inputs all operating parameters and their parameter values ​​into a pre-trained first AI-based printing fault prediction model to predict the potential printing fault type and fault degree of the photocuring printing device; according to the printing fault type and fault degree, adjusts the parameter value of each operating parameter to make the predicted printing fault type reach no fault and there is no abnormal operating parameter in each operating parameter, so that by collecting real-time operating parameters, identifying abnormal conditions and predicting the fault type and degree based on the AI ​​model, not only the timeliness and accuracy of fault detection are improved, but also automatic adjustment of printing parameters is achieved to ensure a stable and reliable printing process. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 A hardware structure block diagram of a computer terminal for a method for processing abnormal operation of a light-curing 3D printing provided by an embodiment of the present invention;

[0032] Figure 2 A flowchart of a method for processing abnormal operation of photo-curing 3D printing provided by an embodiment of the present invention;

[0033] Figure 3 A schematic diagram of the structure of a system for processing abnormal operation of photo-curing 3D printing provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0034] The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, but should not be construed as limiting the present invention.

[0035] The embodiment of the present invention first provides a method for processing abnormal operation of photo-curing 3D printing, which can be applied to electronic devices such as computer terminals, specifically ordinary computers, etc.

[0036] The following describes it in detail by taking running on a computer terminal as an example. Figure 1 The hardware structure block diagram of a computer terminal for a method for handling abnormal operation of a light-curing 3D printing provided by an embodiment of the present invention. Figure 1As shown, the computer device includes multiple computer devices 2000. In the embodiment, the components of the processing terminal for abnormal operation of light-curing 3D printing can be dispersed in different computer devices 2000. The computer device 2000 can be a smart phone, tablet computer, laptop computer, desktop computer, rack server, blade server, tower server or cabinet server (including independent server, or server cluster composed of multiple servers) that executes the program. The computer device 2000 of this embodiment includes at least but is not limited to: a memory 2001 and a processor 2002 that can be interconnected through a system bus. However, it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead.

[0037] In this embodiment, the memory 2001 (i.e., a readable storage medium) includes a flash memory, a hard disk, a multimedia card, a card-type memory (e.g., an SD or DX memory, etc.), a random access memory (RAM), a static random access memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, an optical disk, etc. In some embodiments, the memory 2001 may be an internal storage unit of the computer device 2000, such as a hard disk or a memory of the computer device 2000. In other embodiments, the memory 2001 may also be an external storage device of the computer device 2000, such as a plug-in hard disk equipped on the computer device 2000, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), etc. Of course, the memory 2001 may also include both the internal storage unit of the computer device 2000 and its external storage device. In this embodiment, the memory 2001 is generally used to store the operating system and various application software installed on the computer device, such as the processing service platform for abnormal operation of the light-curing 3D printing in the embodiment, etc. In addition, the memory 2001 can also be used to temporarily store various data that have been output or will be output.

[0038] In some embodiments, the processor 2002 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chips. The processor 2002 is generally used to control the overall operation of the computer device 2000. In this embodiment, the processor 2002 is used to run the program code stored in the memory 2001 or process data. When the processors 2002 of multiple computer devices 2000 of the computer device of this embodiment jointly execute the computer program, the method for processing abnormal operation of the light-curing 3D printing of the embodiment is implemented.

[0039] See also Figure 2 The embodiment of the present invention provides a method for processing abnormal operation of light-curing 3D printing, which may include the following steps:

[0040] S201, collecting parameter values ​​of various operating parameters of the light-curing printing device during the printing process;

[0041] In the process of light-curing 3D printing, real-time monitoring and collection of various operating parameters are the key to ensuring printing quality and equipment stability. These operating parameters include but are not limited to temperature, light intensity, printing speed, material flow rate, interlayer adhesion, ambient humidity, etc. Effective parameter collection can provide a data basis for subsequent fault prediction and is the first step in realizing intelligent fault management.

[0042] By dynamically tracking these parameters, abnormal conditions in the printing process can be discovered in time, so that measures can be taken in advance to avoid failures. Effective parameter value collection not only improves the reliability of the printing process, but also provides rich data support for the intelligent prediction system, greatly enhancing the accuracy of the fault prediction model.

[0043] Specifically, a multi-sensor system can be configured, including temperature sensors, light intensity sensors, flow meters, humidity sensors, and speed sensors, and these sensors can be connected to the central control unit for real-time data collection and processing. Sensors are used to monitor various operating parameters in the printing process in real time. The frequency of data collection needs to be configured once per second to ensure the timeliness of the data. The collected data is preliminarily screened and cleaned to remove instantaneous noise and illogical data points. This can be done by setting a reasonable threshold range and using the Kalman filter algorithm to remove outliers.

[0044] Normalize the collected operating parameter values ​​to eliminate the impact of dimension and facilitate the subsequent learning of the AI ​​model. Min-Max normalization or Z-score normalization method can be used to convert the data to a unified standard. Store the operating parameters and their parameter values ​​collected and processed in real time in a high-performance database (for example, NoSQL database) to facilitate subsequent query and analysis. At the same time, build a data integration framework to ensure that real-time data can be connected with historical data to provide complete data support for the fault prediction model.

[0045] After data collection is completed, each operating parameter and its corresponding parameter value can be organized into a structured data format and used in subsequent fault prediction processes (i.e., input into the AI-based first printing fault prediction model), etc., to ensure the continuity and efficiency of data flow.

[0046] S202, searching for abnormal operating parameters among the operating parameters according to the parameter values;

[0047] Abnormal operating parameters refer to operating parameters whose parameter values ​​exceed the preset normal value range during the light-curing 3D printing process. These parameters may include temperature, light intensity, printing speed, etc. Since accurate control of various parameters is crucial in the 3D printing process, abnormal fluctuations in any parameters may lead to reduced printing quality, finished product defects, and even equipment failure. Therefore, timely identification and processing of these abnormal operating parameters is an important part of the entire fault prediction mechanism. By systematically analyzing the parameter values ​​collected in real time, parameters that are beyond the normal range can be quickly identified, providing a reliable basis for subsequent fault prediction and equipment maintenance. Effective detection of abnormal parameters can not only avoid direct production losses, but also improve the operating efficiency of the equipment.

[0048] Specifically, the normal value range of each operating parameter can be set by analyzing historical data. It can be determined based on statistical methods, such as mean ± standard deviation, while taking into account the differences in the performance settings of the equipment itself, material characteristics and printing processes, and dynamically adjusting the normal value range. Using real-time data stream processing technology, a data monitoring pipeline is established to continuously collect and monitor various operating parameters. After each data collection, its value is immediately compared with the corresponding normal value range. For each parameter, the test results are recorded and marked as "normal" or "abnormal".

[0049] It is also possible to trigger an alarm mechanism in time for parameters marked as abnormal. The alarm content should include the name of the abnormal parameter, the specific value that exceeds the range, and related information so that operators can take quick action. All detected abnormal parameters and their corresponding time, value, and other information are recorded in the database for subsequent data analysis and model training. By analyzing historical abnormal data, potential failure modes can be found and future failure prediction models can be optimized.

[0050] S203, if no abnormal operating parameters are found, input all operating parameters and their parameter values ​​into a pre-trained AI-based first printing fault prediction model to predict potential printing fault types and fault degrees of the light-curing printing device, wherein the first printing fault prediction model is trained based on all historical operating parameters and their parameter values, corresponding historical actual fault modes and fault degrees;

[0051] In the process of photocuring 3D printing, if no abnormal operating parameters are found, it is an important step to input all current operating parameters and their corresponding values ​​into the pre-trained AI-based first printing fault prediction model. This model can identify potential failure modes in the printing process and predict the type and degree of failure by learning from historical data. The training basis of the model is rich historical data. It takes into account the correlation between various operating parameters, failure modes and their severity, providing a scientific basis for real-time warning and decision-making. Through this process, the printing equipment can identify potential failure risks in a timely manner, reduce production losses, and assist operators to take preventive measures before problems occur. This step is a crucial part of the intelligent fault management system and lays the foundation for the smooth progress of the entire printing process.

[0052] Specifically, the historical operating parameter data of the photocuring printing equipment and its corresponding fault records can be collected. These data should include the changes in each parameter before and after the fault occurs, as well as the corresponding fault type and degree. Use data warehouse technology to integrate the data into a structured format for subsequent analysis; extract features from the collected historical data, and use principal component analysis (PCA) or other dimensionality reduction techniques to extract key features. Identify which operating parameters are most critical when a fault occurs, and use these features for subsequent model training; select appropriate machine learning algorithms (such as random forests, support vector machines, or deep learning models) for fault prediction. Use historical parameter data as input and historical fault types and their degrees as output for model training. During the training process, use cross-validation methods to evaluate the performance of the model, and adjust hyperparameters to improve the generalization ability of the model and ensure its adaptability.

[0053] During the operation, all currently collected operating parameter values ​​are standardized to ensure that they are consistent with the input format of the training model. Use Min-Max scaling or Z-score standardization methods to ensure that the data is within the same scale range; input the standardized operating parameter values ​​into the trained first printing fault prediction model, and the model performs real-time calculations to output the type of printing fault and its possible fault degree; evaluate the results based on the fault type and degree output by the model. Compare with fault instances in historical data to determine the accuracy of the prediction results and evaluate the risk level.

[0054] If the predicted fault type and its degree reach the preset risk threshold, an alarm is issued and necessary maintenance or parameter adjustment is recommended. The model is continuously optimized based on real-time data and historical fault feedback. The training data set is updated regularly and the model is retrained to improve its prediction accuracy and adaptability.

[0055] S204, adjusting the parameter values ​​of various operating parameters according to the printing fault type and the fault degree thereof, so that the predicted printing fault type reaches no fault and there is no abnormal operating parameter in the various operating parameters.

[0056] This step aims to eliminate the identified fault risks and ensure the normal progress of the printing process by optimizing parameter settings. In this process, according to the fault information predicted by the model, corresponding adjustment strategies are formulated to ensure that the printing equipment achieves optimal performance during operation. This adjustment is not limited to simple numerical modifications, but usually involves comprehensive consideration of the operating environment and material properties. Through real-time feedback and adjustment, dynamic control of the printing process can be achieved, thereby maintaining the stability and efficiency of the equipment in a complex production environment.

[0057] Specifically, a number of historical actual printing fault types and fault degrees whose similarity with the printing fault type and fault degree is higher than a preset threshold may be searched from the printing device database;

[0058] By extracting historical fault cases similar to the current fault from the equipment history database, an empirical basis can be provided for the current fault. This process involves similarity calculation, such as using cosine similarity or Euclidean distance, or using human experience to ensure that the most relevant historical fault type is selected. By using historical data, the fault analysis process can be accelerated, experience dependence can be reduced, and processing efficiency can be improved.

[0059] Obtaining historical parameter values ​​of operating parameters before fault adjustment and historical parameter values ​​of operating parameters after fault adjustment corresponding to several historical actual printing fault types and fault degrees as historical fault adjustment strategies;

[0060] Recording and organizing the operating parameter changes related to the selected historical fault type can provide specific historical data support for parameter adjustment. These data include the values ​​of various parameters before and after the fault. The historical fault adjustment strategy provides a practical case reference for the current adjustment, ensuring that effective measures can be taken when facing similar problems and reducing the possibility of errors.

[0061] Based on each group of historical fault adjustment strategies, current operating parameters of the light-curing printing device are adjusted, wherein the parameter values ​​of each operating parameter after adjustment are within a normal range;

[0062] Use the historical fault adjustment strategy to correct the current parameters to ensure that their values ​​are within the normal operating range. This step involves a systematic evaluation of the parameters to ensure that they are adjusted within the preset reasonable range and that the adjusted operating parameters will not cause new faults or anomalies, providing a reliable basis for subsequent printing jobs and improving the overall efficiency and quality of printing.

[0063] In one implementation, the weight of each group of historical fault adjustment strategies may be determined according to the similarity between the historical actual printing fault type and fault degree in each group of historical fault adjustment strategies and the printing fault type and fault degree;

[0064] Weights are assigned to different fault adjustment strategies based on the similarity between the current fault and the historical fault. The weight setting can be based on the similarity level, and the weights are obtained by normalizing each similarity to ensure that the more relevant fault strategy dominates the adjustment. After the weight is determined, historical data can be applied more accurately, the processing effect can be enhanced, the adjustment strategy can be more targeted and effective, and the adjustment result can be more in line with the actual situation.

[0065] According to the historical parameter values ​​and weights of the operating parameters after fault adjustment in each group of historical fault adjustment strategies, the parameter values ​​of the operating parameters of the light-curing printing device after adjustment are calculated.

[0066] According to the determined weights, the parameter values ​​in each group of historical adjustment strategies are weighted and summed to obtain new adjustment parameter values. This process needs to consider the historical performance of all influencing parameters and the corresponding weights. Through weighted calculation, it is ensured that after adjustment, the new parameter values ​​are reasonable and effective, which can effectively reduce the risk of failure and provide a stable parameter basis for subsequent printing tasks.

[0067] In another implementation, the average value or median value of the historical parameter value of each operating parameter after fault adjustment in each group of historical fault adjustment strategies may be calculated as the parameter value of the operating parameter of the light-curing printing device after adjustment.

[0068] When determining new operating parameter values, you can also calculate the average or median value of each parameter adjusted in the historical fault adjustment strategy and use it as a reference value for the current parameter. This will balance the impact of extreme values ​​and ensure the stability of parameter settings. Using the historical average or median calculation method helps avoid the deviation of a single data point and ensures that the adjusted parameters are more stable and reasonable, thereby reducing the possibility of faults and improving the reliability of printing quality.

[0069] Input all adjusted operating parameters and their parameter values ​​into a pre-trained AI-based first printing fault prediction model to predict the potential printing fault type and fault degree of the light-curing printing device, and determine whether the predicted printing fault type reaches no fault;

[0070] The adjusted parameters are re-entered into the AI ​​model and predicted again to ensure that the adjustment is effective. This step is to verify the rationality of the final parameter settings and ensure that the device can work normally under the new parameter environment. Through model verification, the impact of parameter adjustments can be quickly evaluated to ensure that potential problems are not missed during operation, providing a feedback mechanism to optimize the adjustment process.

[0071] If the predicted printing fault type does not reach the state of no fault, the process returns to the step of adjusting the current operating parameters of the light-curing printing device based on the historical fault adjustment strategies of each group until the predicted printing fault type reaches the state of no fault.

[0072] After the initial prediction, if the potential fault is still found, it is necessary to return to the previous step and continue to apply the historical fault adjustment strategy to further optimize the parameters until the predetermined fault-free state is reached. This feedback mechanism ensures continuous improvement of the printing process, emphasizes the importance of dynamic adjustment and real-time optimization, and enables the fault management process to self-correct, providing guarantee for the stable operation of the equipment.

[0073] Furthermore, before adjusting the parameter values ​​of various operating parameters according to the printing fault type and the degree of the fault, if abnormal operating parameters are found, the abnormal operating parameters and their parameter values ​​are input into a pre-trained AI-based second printing fault prediction model to predict the current printing fault type and the degree of the fault of the photocuring printing device, wherein the second printing fault prediction model is trained based on historical abnormal operating parameters and their parameter values, and corresponding historical actual failure modes and their degrees of failure.

[0074] In this step, the abnormal operating parameters need to be detected first, which is a prerequisite for ensuring that the printing equipment is in a safe operating state. If an abnormality is found, these abnormal parameters and their parameter values ​​are input into the pre-trained AI-based second printing fault prediction model. This model is specially trained for historical abnormal operating parameters and their parameter values ​​and corresponding failure modes, so it can efficiently analyze the current status of the equipment and predict the type and degree of related printing failures. This process not only predicts faults based on existing data, but also takes into account specific operating environments and equipment status, providing data support for subsequent fault handling strategies. The goal of this step is to obtain accurate fault predictions by analyzing the root causes of the abnormalities in detail, and to provide guidance for further parameter adjustments and fault handling.

[0075] Specifically, various operating parameters of the printing equipment can be monitored in real time through sensors. When values ​​outside the normal range are detected, they are marked as abnormal parameters. These abnormal parameters are then preprocessed, including denoising, standardization, and normalization, to facilitate the input of subsequent models; feature engineering is performed on multiple abnormal parameters to extract key information. This can include using principal component analysis (PCA) to reduce dimensions and identify the parameters most relevant to fault prediction. Next, correlation analysis is performed, using Pearson or Spearman correlation coefficients to evaluate the correlation between different parameters to help understand how these abnormal parameters affect the overall printing quality; a deep learning framework (such as LSTM or CNN) is used to build a prediction model for abnormal parameters. The model not only considers a single abnormal parameter, but also captures the complex relationship between parameters, and learns and identifies potential failure modes through historical data. The model needs to be optimized using historical abnormal parameters and their corresponding fault types during training; new abnormal parameter data is continuously input into the model for dynamic updating. Transfer learning can be used to combine newly collected data with existing training data to optimize the parameters of the model to improve its predictive ability and adaptability; multi-model fusion is performed based on model prediction. Multiple trained models (such as random forests, support vector machines, etc.) can be combined to generate the final fault prediction results through a weighted voting mechanism. Each model is assigned different weights based on its performance on historical data to improve the accuracy of the prediction; the prediction results are monitored and compared with the actual printing effects to establish a feedback mechanism. Any new fault data will be fed back to the model for retraining to enhance the accuracy of its subsequent predictions. At the same time, real-time monitoring and display can allow operators to instantly understand the status of the equipment and further optimize decisions. In summary, the difference between the first printing fault prediction model and the second printing fault prediction model is:

[0076] 1. Differences in basic data for model training:

[0077] The first printing fault prediction model: training is based on all historical operating parameters and their parameter values, corresponding to the actual historical fault mode and its fault degree. It aims to comprehensively analyze the relationship between the performance of each operating parameter and the fault during the entire printing process; the second printing fault prediction model: training is based on historical abnormal operating parameters and their parameter values, corresponding to the actual historical fault mode and its fault degree. It focuses on analyzing those parameters that have been marked as abnormal, helping to identify possible faults under specific abnormal conditions.

[0078] 2. Different prediction focuses: The first printing fault prediction model aims to predict the potential printing fault type and fault degree, and is usually used when the equipment operating parameters are normal or no obvious abnormalities are found. It emphasizes overall performance and stability; the second printing fault prediction model focuses on known abnormal parameters and predicts the type and degree of faults in specific situations. Its application scenario is to further analyze the potential faults caused by the abnormality after the abnormality is found.

[0079] 3. Different application scenarios: The first printing fault prediction model is suitable for predicting faults under normal operating conditions, helping operators to be aware of potential risks in advance. The second printing fault prediction model is suitable for conducting in-depth analysis of equipment after an abnormality is detected, quickly locating the cause of the abnormality, and providing adjustment suggestions.

[0080] The design significance lies in:

[0081] 1. Targetedness and accuracy: By training two models separately, we can conduct in-depth analysis on different fault prediction scenarios. The first model can predict faults based on the overall operating status, while the second model focuses on handling abnormal situations, enhancing the accuracy and targeting of predictions.

[0082] 2. Improve the level of fault detection: This design ensures analysis from macro to micro levels. The first model has a global perspective and can identify potential risks to overall operating efficiency and long-term performance; the second model goes deep into the specific abnormal level, can respond quickly and provide targeted solutions.

[0083] 3. Improve the robustness of the system: By using two different models, the system can reliably predict faults under various operating conditions. Even in abnormal situations, timely measures can be taken to reduce the impact of faults on production efficiency.

[0084] 4. Flexibility and adaptability: This design allows the model to flexibly adjust the prediction strategy according to the changes in different operating parameters and equipment status. The comprehensiveness of the first model and the professionalism of the second model complement each other, making the entire fault prediction system more robust.

[0085] 5. Promote continuous improvement of the system: By analyzing the matching degree between the prediction effect of the two models and the actual faults, the algorithm and data collection strategy can be continuously optimized, so that the system can self-learn and adapt to new fault modes, and improve the overall intelligence level.

[0086] It can be seen that the parameter values ​​of various operating parameters in the printing process of the light-curing printing device are collected; according to the parameter values, abnormal operating parameters in each operating parameter are searched; if the abnormal operating parameter is not found, all operating parameters and their parameter values ​​are input into a pre-trained AI-based first printing fault prediction model to predict the potential printing fault type and fault degree of the light-curing printing device; according to the printing fault type and fault degree, the parameter value of each operating parameter is adjusted to make the predicted printing fault type reach no fault and there is no abnormal operating parameter in each operating parameter, so that by collecting real-time operating parameters, identifying abnormal situations and predicting the fault type and degree based on the AI ​​model, not only the timeliness and accuracy of fault detection are improved, but also the automatic adjustment of printing parameters is realized to ensure the stability and reliability of the printing process.

[0087] Another embodiment of the present invention provides a system for processing abnormal operation of light-curing 3D printing, see Figure 3 , the system may include:

[0088] The acquisition module 301 is used to acquire the parameter values ​​of various operating parameters of the light-curing printing device during the printing process;

[0089] A search module 302, used for searching abnormal operating parameters among the operating parameters according to the parameter values;

[0090] The first prediction module 303 is used for inputting all the operating parameters and their parameter values ​​into a pre-trained AI-based first printing fault prediction model to predict the potential printing fault type and fault degree of the light-curing printing device if no abnormal operating parameters are found, wherein the first printing fault prediction model is trained based on all historical operating parameters and their parameter values, corresponding historical actual fault modes and fault degrees;

[0091] The adjustment module 304 is used to adjust the parameter value of each operating parameter according to the printing fault type and the fault degree, so that the predicted printing fault type reaches no fault and there is no abnormal operating parameter in each operating parameter.

[0092] It can be seen that the parameter values ​​of various operating parameters in the printing process of the light-curing printing device are collected; according to the parameter values, abnormal operating parameters in each operating parameter are searched; if the abnormal operating parameter is not found, all operating parameters and their parameter values ​​are input into a pre-trained AI-based first printing fault prediction model to predict the potential printing fault type and fault degree of the light-curing printing device; according to the printing fault type and fault degree, the parameter value of each operating parameter is adjusted to make the predicted printing fault type reach no fault and there is no abnormal operating parameter in each operating parameter, so that by collecting real-time operating parameters, identifying abnormal situations and predicting the fault type and degree based on the AI ​​model, not only the timeliness and accuracy of fault detection are improved, but also the automatic adjustment of printing parameters is realized to ensure the stability and reliability of the printing process.

[0093] An embodiment of the present invention further provides a storage medium, in which a computer program is stored, wherein the computer program is configured to execute the steps of any of the above method embodiments when running.

[0094] Specifically, in this embodiment, the above storage medium may be configured to store a computer program for performing the following steps:

[0095] S201, collecting parameter values ​​of various operating parameters of the light-curing printing device during the printing process;

[0096] S202, searching for abnormal operating parameters among the operating parameters according to the parameter values;

[0097] S203, if no abnormal operating parameters are found, input all operating parameters and their parameter values ​​into a pre-trained AI-based first printing fault prediction model to predict potential printing fault types and fault degrees of the light-curing printing device, wherein the first printing fault prediction model is trained based on all historical operating parameters and their parameter values, corresponding historical actual fault modes and fault degrees;

[0098] S204, adjusting the parameter values ​​of various operating parameters according to the printing fault type and the fault degree thereof, so that the predicted printing fault type reaches no fault and there is no abnormal operating parameter in the various operating parameters.

[0099] It can be seen that the parameter values ​​of various operating parameters in the printing process of the light-curing printing device are collected; according to the parameter values, abnormal operating parameters in each operating parameter are searched; if the abnormal operating parameter is not found, all operating parameters and their parameter values ​​are input into a pre-trained AI-based first printing fault prediction model to predict the potential printing fault type and fault degree of the light-curing printing device; according to the printing fault type and fault degree, the parameter value of each operating parameter is adjusted to make the predicted printing fault type reach no fault and there is no abnormal operating parameter in each operating parameter, so that by collecting real-time operating parameters, identifying abnormal situations and predicting the fault type and degree based on the AI ​​model, not only the timeliness and accuracy of fault detection are improved, but also the automatic adjustment of printing parameters is realized to ensure the stability and reliability of the printing process.

[0100] An embodiment of the present invention further provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0101] Specifically, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0102] Specifically, in this embodiment, the processor may be configured to perform the following steps through a computer program:

[0103] S201, collecting parameter values ​​of various operating parameters of the light-curing printing device during the printing process;

[0104] S202, searching for abnormal operating parameters among the operating parameters according to the parameter values;

[0105] S203, if no abnormal operating parameters are found, input all operating parameters and their parameter values ​​into a pre-trained AI-based first printing fault prediction model to predict potential printing fault types and fault degrees of the light-curing printing device, wherein the first printing fault prediction model is trained based on all historical operating parameters and their parameter values, corresponding historical actual fault modes and fault degrees;

[0106] S204, adjusting the parameter values ​​of various operating parameters according to the printing fault type and the fault degree thereof, so that the predicted printing fault type reaches no fault and there is no abnormal operating parameter in the various operating parameters.

[0107] It can be seen that the parameter values ​​of various operating parameters in the printing process of the light-curing printing device are collected; according to the parameter values, abnormal operating parameters in each operating parameter are searched; if the abnormal operating parameter is not found, all operating parameters and their parameter values ​​are input into a pre-trained AI-based first printing fault prediction model to predict the potential printing fault type and fault degree of the light-curing printing device; according to the printing fault type and fault degree, the parameter value of each operating parameter is adjusted to make the predicted printing fault type reach no fault and there is no abnormal operating parameter in each operating parameter, so that by collecting real-time operating parameters, identifying abnormal situations and predicting the fault type and degree based on the AI ​​model, not only the timeliness and accuracy of fault detection are improved, but also the automatic adjustment of printing parameters is realized to ensure the stability and reliability of the printing process.

[0108] The above describes in detail the structure, features and effects of the present invention based on the embodiments shown in the drawings. The above is only a preferred embodiment of the present invention, but the present invention is not limited to the scope of implementation shown in the drawings. Any changes made according to the concept of the present invention, or modifications to equivalent embodiments with equivalent changes, which still do not exceed the spirit covered by the description and drawings, should be within the protection scope of the present invention.

Claims

1. A method for processing abnormal operation of light-curing 3D printing, characterized in that: The method comprises: Collect parameter values ​​of various operating parameters of the light-curing printing equipment during the printing process; According to the parameter values, searching for abnormal operating parameters among the operating parameters; If no abnormal operating parameters are found, all operating parameters and their parameter values ​​are input into a pre-trained AI-based first printing fault prediction model to predict the potential printing fault type and fault degree of the light-curing printing device, wherein the first printing fault prediction model is trained based on all historical operating parameters and their parameter values, corresponding historical actual fault modes and fault degrees; According to the printing fault type and the fault degree thereof, the parameter value of each operating parameter is adjusted so that the predicted printing fault type reaches no fault and there is no abnormal operating parameter in each operating parameter.

2. The method according to claim 1, characterized in that The method further comprises: Before adjusting the parameter values ​​of various operating parameters according to the printing fault type and the fault degree thereof, if abnormal operating parameters are found, the abnormal operating parameters and their parameter values ​​are input into a pre-trained AI-based second printing fault prediction model to predict the current printing fault type and the fault degree of the light-curing printing device, wherein the second printing fault prediction model is trained based on historical abnormal operating parameters and their parameter values, and corresponding historical actual failure modes and their failure degrees.

3. The method according to claim 2, characterized in that The adjusting of the parameter values ​​of various operating parameters according to the printing fault type and fault degree thereof includes: Searching, from a printing device database, a number of historical actual printing fault types and fault degrees whose similarity with the printing fault type and fault degree is higher than a preset threshold; Obtaining historical parameter values ​​of operating parameters before fault adjustment and historical parameter values ​​of operating parameters after fault adjustment corresponding to several historical actual printing fault types and fault degrees as historical fault adjustment strategies; Based on each group of historical fault adjustment strategies, current operating parameters of the light-curing printing device are adjusted, wherein the parameter values ​​of each operating parameter after adjustment are within a normal range; Input all adjusted operating parameters and their parameter values ​​into a pre-trained AI-based first printing fault prediction model to predict the potential printing fault type and fault degree of the light-curing printing device, and determine whether the predicted printing fault type reaches no fault; If the predicted printing fault type does not reach the state of no fault, the process returns to the step of adjusting the current operating parameters of the light-curing printing device based on the historical fault adjustment strategies of each group until the predicted printing fault type reaches the state of no fault.

4. The method according to claim 3, characterized in that The adjusting of the current operating parameters of the light-curing printing device based on each group of historical fault adjustment strategies includes: Determine the weight of each group of historical fault adjustment strategies according to the similarity between the historical actual printing fault type and fault degree in each group of historical fault adjustment strategies and the printing fault type and fault degree; According to the historical parameter values ​​and weights of the operating parameters after fault adjustment in each group of historical fault adjustment strategies, the parameter values ​​of the operating parameters of the light-curing printing device after adjustment are calculated.

5. The method according to claim 3, characterized in that: The adjusting of the current operating parameters of the light-curing printing device based on each group of historical fault adjustment strategies includes: The average value or median value of the historical parameter value of each operating parameter after the fault adjustment in each group of historical fault adjustment strategies is calculated as the parameter value of the operating parameter of the light-curing printing device after adjustment.

6. A system for processing abnormal operation of light-curing 3D printing, characterized in that: The system comprises: The acquisition module is used to acquire the parameter values ​​of various operating parameters of the light-curing printing device during the printing process; A search module, used for searching abnormal operating parameters among various operating parameters according to the parameter values; A first prediction module is used for inputting all the operating parameters and their parameter values ​​into a pre-trained AI-based first printing fault prediction model to predict the potential printing fault type and fault degree of the light-curing printing device if no abnormal operating parameters are found, wherein the first printing fault prediction model is trained based on all historical operating parameters and their parameter values, corresponding historical actual fault modes and fault degrees; The adjustment module is used to adjust the parameter value of each operating parameter according to the printing fault type and the fault degree, so that the predicted printing fault type reaches no fault and there is no abnormal operating parameter in each operating parameter.

7. The system according to claim 6, characterized in that The system further comprises: The second prediction module is used for, before adjusting the parameter values ​​of various operating parameters according to the printing fault type and the fault degree, if abnormal operating parameters are found, inputting the abnormal operating parameters and their parameter values ​​into a pre-trained AI-based second printing fault prediction model to predict the current printing fault type and the fault degree of the light-curing printing device, wherein the second printing fault prediction model is trained based on historical abnormal operating parameters and their parameter values, and corresponding historical actual failure modes and their failure degrees.

8. The system according to claim 7, characterized in that The adjustment module is specifically used for: Searching, from a printing device database, a number of historical actual printing fault types and fault degrees whose similarity with the printing fault type and fault degree is higher than a preset threshold; Obtaining historical parameter values ​​of operating parameters before fault adjustment and historical parameter values ​​of operating parameters after fault adjustment corresponding to several historical actual printing fault types and fault degrees as historical fault adjustment strategies; Based on each group of historical fault adjustment strategies, current operating parameters of the light-curing printing device are adjusted, wherein the parameter values ​​of each operating parameter after adjustment are within a normal range; Input all adjusted operating parameters and their parameter values ​​into a pre-trained AI-based first printing fault prediction model to predict the potential printing fault type and fault degree of the light-curing printing device, and determine whether the predicted printing fault type reaches no fault; If the predicted printing fault type does not reach the state of no fault, the process returns to the step of adjusting the current operating parameters of the light-curing printing device based on the historical fault adjustment strategies of each group until the predicted printing fault type reaches the state of no fault.

9. A storage medium, characterized in that: The storage medium stores a computer program, wherein the computer program is configured to execute the method according to any one of claims 1 to 5 when executed.

10. An electronic device comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to run the computer program to perform the method according to any one of claims 1 to 5.

Images