A method and system for handling abnormal operation of a light-cured 3D printer
By collecting data in real time and using AI models to predict the operating parameters of photopolymer 3D printing equipment, the system automatically adjusts these parameters to address the issues of timeliness and accuracy in fault detection, ensuring a stable and reliable printing process and reducing equipment damage and material waste.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- SHENZHEN ELEGOO TECH CO LTD
- Filing Date
- 2024-10-12
- Publication Date
- 2026-05-12
AI Technical Summary
Existing photopolymer 3D printing equipment relies on manual monitoring for fault detection, resulting in low fault diagnosis efficiency, high maintenance costs, and an inability to detect and prevent problems in a timely manner.
By collecting real-time operating parameters, identifying abnormal situations, and using AI models to predict the type and extent of faults, printing parameters are automatically adjusted to ensure stable equipment operation.
It improves the timeliness and accuracy of fault detection, achieves stability and reliability in the printing process, reduces equipment damage and material waste, and lowers the risk of production stoppage.
Smart Images
Figure CN119502355B_ABST
Abstract
Description
Technical Field
[0001] This invention belongs to the field of 3D printing technology, and in particular to a method and system for handling abnormal operation of photopolymer 3D printing. Background Technology
[0002] With the rapid development of 3D printing technology, photopolymer 3D printing, as an important branch, has been widely used in fields such as medical, aerospace, automotive manufacturing, and consumer goods due to its high precision and efficiency. However, various printing equipment often faces potential malfunctions during actual operation. These malfunctions not only affect print quality but may also lead to equipment damage, material waste, and even production stoppages, causing huge economic losses to enterprises.
[0003] Traditional fault detection methods rely heavily on experience and manual monitoring, and are usually judged and dealt with after a fault occurs. This passive management approach cannot detect and prevent problems in a timely manner, resulting in low fault diagnosis efficiency and high maintenance costs. Summary of the Invention
[0004] The purpose of this invention is to provide a method and system for handling abnormal operation of photopolymer 3D printing, in order to overcome the shortcomings of the prior art. By collecting real-time operating parameters, identifying abnormal situations, and predicting the type and degree of faults based on AI models, it can not only improve the timeliness and accuracy of fault detection, but also realize the automatic adjustment of printing parameters to ensure the stability and reliability of the printing process.
[0005] One embodiment of this application provides a method for handling abnormal operation of photopolymer 3D printing, the method comprising:
[0006] Collect the parameter values of various operating parameters during the printing process of the photopolymerization printing equipment;
[0007] Based on the parameter values, identify any abnormal operating parameters among the operating parameters;
[0008] If no abnormal operating parameters are found, all operating parameters and their values are input into a pre-trained AI-based first printing fault prediction model to predict the potential printing fault types and their severity of the light-curing printing device. The first printing fault prediction model is trained based on all historical operating parameters and their values, corresponding historical actual fault modes and their severity.
[0009] Based on the type and severity of the printing fault, the values of each operating parameter are adjusted to ensure that the predicted printing fault type is fault-free and that there are no abnormal operating parameters among the operating parameters.
[0010] Optionally, the method further includes:
[0011] Before adjusting the values of each operating parameter according to the type and severity of the printing failure, if an abnormal operating parameter is found, the abnormal operating parameter and its value are input into a pre-trained AI-based second printing failure prediction model to predict the current printing failure type and severity of the photopolymerization printing device. The second printing failure prediction model is trained based on historical abnormal operating parameters and their values, corresponding historical actual failure modes and their severity.
[0012] Optionally, adjusting the parameter values of each operating parameter according to the type and severity of the printing fault includes:
[0013] From the printing device database, find several historical actual printing fault types and their degrees of similarity that are higher than a preset threshold with respect to the printing fault type and its degree of similarity.
[0014] Obtain historical parameter values of operating parameters before and after fault adjustment for several historical actual printing fault types and their fault severity, as well as historical parameter values of operating parameters before fault adjustment, as historical fault adjustment strategies;
[0015] Based on the historical fault adjustment strategies of each group, the current operating parameters of the photopolymerization printing equipment were adjusted. After the adjustment, the values of each operating parameter were all within the normal range.
[0016] All adjusted operating parameters and their values are input into a pre-trained AI-based first printing fault prediction model to predict the potential printing fault types and their severity of the photopolymerization printing equipment, and to determine whether the predicted printing fault types have reached the level of fault-free operation.
[0017] If the predicted printing fault type does not reach fault-free status, return to the step of adjusting the current operating parameters of the photopolymer printer based on the historical fault adjustment strategy for each group, until the predicted printing fault type reaches fault-free status.
[0018] Optionally, adjusting the current operating parameters of the photopolymerization printing equipment based on each group of historical fault adjustment strategies includes:
[0019] The weight of each group of historical fault adjustment strategies is determined based on the similarity between the actual historical printing fault types and their severity in each group and the printing fault types and their severity.
[0020] Based on the historical parameter values and weights of the operating parameters after fault adjustment in each group's historical fault adjustment strategy, the parameter values of the operating parameters of the photopolymerization printing equipment after adjustment are calculated.
[0021] Optionally, adjusting the current operating parameters of the photopolymerization printing equipment based on each group of historical fault adjustment strategies includes:
[0022] Calculate the average or median value of the historical parameter values of each operating parameter after fault adjustment in each group of historical fault adjustment strategies, and use it as the parameter value of the operating parameters of the light-curing printing equipment after adjustment.
[0023] Another embodiment of this application provides a system for handling abnormal operation of photopolymer 3D printing, the system comprising:
[0024] The data acquisition module is used to collect the parameter values of various operating parameters during the printing process of the photopolymerization printing equipment;
[0025] The search module is used to search for abnormal operating parameters among the operating parameters based on the parameter values.
[0026] The first prediction module is used to input all operating parameters and their values into a pre-trained AI-based first printing fault prediction model if no abnormal operating parameters are found, and predict the potential printing fault types and their severity of the light-curing printing device. The first printing fault prediction model is trained based on all historical operating parameters and their values, corresponding historical actual fault modes and their severity.
[0027] The adjustment module is used to adjust the parameter values of each operating parameter according to the type and severity of the printing fault, so that the predicted printing fault type is fault-free and there are no abnormal operating parameters among the operating parameters.
[0028] Another embodiment of this application provides a storage medium storing a computer program, wherein the computer program is configured to execute the method described in any of the preceding claims when running.
[0029] Another embodiment of this 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 perform the method described in any of the preceding claims.
[0030] Compared with existing technologies, the present invention provides a method for handling abnormal operation of photopolymer 3D printing. This method involves collecting parameter values of various operating parameters during the printing process of the photopolymer printing equipment; identifying abnormal operating parameters based on these parameter values; if no abnormal operating parameters are found, inputting all operating parameters and their values into a pre-trained AI-based first printing fault prediction model to predict the potential printing fault types and their severity; and adjusting the parameter values of each operating parameter according to the predicted printing fault types and their severity to ensure that the predicted printing fault types are fault-free and that no abnormal operating parameters exist. This method improves the timeliness and accuracy of fault detection by collecting real-time operating parameters, identifying abnormal situations, and predicting fault types and severity based on an AI model. It also enables automatic adjustment of printing parameters, ensuring a stable and reliable printing process. Attached Figure Description
[0031] Figure 1 Hardware structure block diagram of a computer terminal for a method of handling abnormal operation of photopolymer 3D printing provided in an embodiment of the present invention;
[0032] Figure 2 A flowchart illustrating a method for handling abnormal operation of photopolymer 3D printing provided in an embodiment of the present invention;
[0033] Figure 3 This is a schematic diagram of a system for handling abnormal operation of photopolymer 3D printing, provided in an embodiment of the present invention. Detailed Implementation
[0034] The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and should not be construed as limiting the present invention.
[0035] This invention first provides a method for handling abnormal operation of photopolymer 3D printing. This method can be applied to electronic devices, such as computer terminals, specifically ordinary computers.
[0036] The following detailed explanation uses a computer terminal as an example. Figure 1 This is a hardware structure block diagram of a computer terminal for a method of handling abnormal operation of photopolymer 3D printing provided in an embodiment of the present invention. Figure 1As shown, the computer device includes multiple computer devices 2000. In this embodiment, the components of the processing terminal for abnormal operation of photopolymer 3D printing can be distributed among different computer devices 2000. The computer devices 2000 can be smartphones, tablets, laptops, desktop computers, rack servers, blade servers, tower servers, or cabinet servers (including standalone servers or server clusters composed of multiple servers), etc., that execute programs. The computer device 2000 in this embodiment includes, but is not limited to, a memory 2001 and a processor 2002 that can be interconnected via a system bus. However, it should be understood that it is not required to implement all the components shown; more or fewer components can be implemented alternatively.
[0037] In this embodiment, the memory 2001 (i.e., the readable storage medium) includes flash memory, hard disk, multimedia card, card-type memory (e.g., SD or DX memory), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 2001 may be an internal storage unit of the computer device 2000, such as the hard disk or 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, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the computer device 2000. Of course, the memory 2001 may also include both the internal storage unit and the external storage device of the computer device 2000. In this embodiment, the memory 2001 is typically 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 photopolymer 3D printing in this embodiment. In addition, the memory 2001 can also be used to temporarily store various types of data that have been output or will be output.
[0038] In some embodiments, processor 2002 may be a central processing unit (CPU), controller, microcontroller, microprocessor, or other data processing chip. This processor 2002 is typically used to control the overall operation of computer device 2000. In this embodiment, processor 2002 is used to run program code stored in memory 2001 or process data. In this embodiment, when the processors 2002 of multiple computer devices 2000 jointly execute a computer program, the method for handling abnormal operation of photopolymer 3D printing according to this embodiment is implemented.
[0039] See Figure 2 The present invention provides a method for handling abnormal operation of photopolymer 3D printing, which may include the following steps:
[0040] S201, collects the parameter values of various operating parameters during the printing process of the photopolymerization printing equipment;
[0041] In the process of photopolymer 3D printing, real-time monitoring and acquisition of various operating parameters are crucial to ensuring print quality and equipment stability. These operating parameters include, but are not limited to, temperature, light intensity, printing speed, material flow rate, interlayer adhesion, and ambient humidity. Effective parameter acquisition provides a data foundation for subsequent fault prediction and is the first step towards achieving intelligent fault management.
[0042] By dynamically tracking these parameters, abnormal situations during the printing process can be detected in a timely manner, allowing for proactive measures to prevent malfunctions. Effective parameter value acquisition not only improves the reliability of the printing process but also provides rich data support for the intelligent prediction system, significantly 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. These sensors are connected to the central control unit for real-time data acquisition and processing. The sensors monitor various operating parameters during the printing process in real time. The data acquisition frequency should be configured to once per second to ensure data timeliness. The acquired data undergoes initial screening and cleaning to remove transient noise and illogical data points. This can be achieved by setting a reasonable threshold range and using a Kalman filter algorithm to eliminate outliers.
[0044] The collected operational parameter values are normalized to eliminate the influence of units, facilitating subsequent learning by the AI model. Min-Max normalization or Z-score normalization methods can be used to convert the data to a unified standard. The real-time collected and processed operational parameters and their values are stored in a high-performance database (e.g., a NoSQL database) for convenient subsequent querying and analysis. Simultaneously, a data integration framework is constructed to ensure that real-time data can be connected with historical data, providing complete data support for the fault prediction model.
[0045] After data collection is completed, the various operating parameters and their corresponding values can be organized into a structured data format and used in subsequent fault prediction processes (i.e., input into the AI-based first-print fault prediction model), etc., to ensure the continuity and efficiency of data flow.
[0046] S202, based on the parameter values, find the abnormal operating parameters among the operating parameters;
[0047] Abnormal operating parameters refer to parameters whose values exceed the preset normal range during the photopolymer 3D printing process. These parameters may include temperature, light intensity, and printing speed. Since accurate control of each parameter is crucial in 3D printing, any abnormal fluctuation can lead to decreased print quality, product defects, or even equipment malfunction. Therefore, timely identification and handling of these abnormal operating parameters is a vital part of the overall fault prediction mechanism. By systematically analyzing the real-time collected parameter values, parameters exceeding the normal range can be quickly identified, providing a reliable basis for subsequent fault prediction and equipment maintenance. Effective detection of abnormal parameters not only avoids direct production losses but also improves equipment operating efficiency.
[0048] Specifically, normal ranges for each operating parameter can be established by analyzing historical data. These ranges can be determined using statistical methods, such as mean ± standard deviation, while also considering differences in equipment performance settings, material properties, and printing processes, dynamically adjusting the normal ranges. Real-time data stream processing technology is used to establish a data monitoring pipeline to continuously collect and monitor various operating parameters. After each data collection, the value is immediately compared to the corresponding normal range. For each parameter, the detection result is recorded and marked as "normal" or "abnormal".
[0049] An alarm mechanism can be triggered promptly for parameters marked as abnormal. The alarm should include the name of the abnormal parameter, the specific value exceeding the range, and related information to enable operators to take quick action. All detected abnormal parameters and their corresponding time and value information are recorded in a database for subsequent data analysis and model training. By analyzing historical abnormal data, potential fault modes can be identified, and future fault prediction models can be optimized.
[0050] S203, if no abnormal operating parameters are found, input all operating parameters and their values into a pre-trained AI-based first printing fault prediction model to predict the potential printing fault types and their severity of the light-curing printing device. The first printing fault prediction model is trained based on all historical operating parameters and their values, corresponding historical actual fault modes and their severity.
[0051] In the photopolymer 3D printing process, if no abnormal operating parameters are found, a crucial step is to input all current operating parameters and their corresponding values into a pre-trained AI-based first printing fault prediction model. This model, through learning from historical data, can identify potential fault modes during the printing process and predict their fault types and severity. The model's training is based on rich historical data, considering the correlation between various operating parameters, fault modes, and their severity, providing a scientific basis for real-time early warning and decision-making. Through this process, the printing equipment can promptly identify potential fault risks, reduce production losses, and assist operators in taking preventative measures before problems occur. This step is a vital component of the intelligent fault management system, laying the foundation for the smooth operation of the entire printing process.
[0052] Specifically, historical operating parameter data and corresponding fault records of the photopolymerization printing equipment can be collected. This data should include the changes in each parameter before and after a fault, as well as the corresponding fault type and severity. Data warehousing technology should be used to integrate the data into a structured format for easier subsequent analysis. Feature extraction should be performed on the collected historical data using principal component analysis (PCA) or other dimensionality reduction techniques to extract key features. Identify which operating parameters are most critical during a fault 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 severity as output for model training. During training, cross-validation should be used to evaluate model performance, and hyperparameters should be adjusted to improve the model's generalization ability and ensure its adaptability.
[0053] During operation, all collected runtime parameter values are standardized to ensure consistency with the input format of the training model. Min-Max scaling or Z-score standardization methods are used to ensure the data is within the same scale range. The standardized runtime parameter values are then input into the trained first printing fault prediction model. The model performs real-time calculations, outputting the type of printing fault and its possible severity. The results are evaluated based on the fault type and severity output by the model. Comparison with fault instances in historical data is used to determine the accuracy of the prediction results and assess the risk level.
[0054] If the predicted fault type and its severity reach a preset risk threshold, an alarm is issued, and necessary maintenance or parameter adjustments are recommended. The model is continuously optimized based on real-time data and historical fault feedback. The training dataset is updated regularly, and the model is retrained to improve its predictive accuracy and adaptability.
[0055] S204, Based on the type and severity of the printing fault, adjust the parameter values of each operating parameter to ensure that the predicted printing fault type is fault-free and that there are no abnormal operating parameters among the operating parameters.
[0056] This step aims to eliminate identified fault risks and ensure the normal operation of the printing process by optimizing parameter settings. During this process, corresponding adjustment strategies are developed based on fault information predicted by the model to ensure the printing equipment achieves optimal performance during operation. This adjustment is not limited to simple numerical modifications but typically involves a comprehensive consideration of the operating environment and material properties. Through real-time feedback and adjustments, dynamic control of the printing process can be achieved, thereby maintaining the stability and efficiency of the equipment in complex production environments.
[0057] Specifically, the printing equipment database can be used to search for several historical actual printing fault types and their severity that have a similarity to the aforementioned printing fault type and its severity that is higher than a preset threshold.
[0058] By extracting historical fault cases similar to the current fault from the equipment's historical database, an empirical basis can be provided for the current fault. This process involves similarity calculations, such as using cosine similarity or Euclidean distance methods, or relying on human experience to ensure that the most relevant historical fault type is selected. Using historical data can accelerate the fault analysis process, reduce reliance on experience, and improve processing efficiency.
[0059] Obtain historical parameter values of operating parameters before and after fault adjustment for several historical actual printing fault types and their fault severity, as well as historical parameter values of operating parameters before fault adjustment, as historical fault adjustment strategies;
[0060] Recording and organizing changes in operating parameters related to selected historical fault types provides concrete historical data support for parameter adjustments. This data includes parameter values before and after the fault. Historical fault adjustment strategies provide practical case references for current adjustments, ensuring that effective measures can be taken when facing similar problems, reducing the possibility of errors.
[0061] Based on the historical fault adjustment strategies of each group, the current operating parameters of the photopolymerization printing equipment were adjusted. After the adjustment, the values of each operating parameter were all within the normal range.
[0062] The current parameters are calibrated using historical fault adjustment strategies to ensure their values are within the normal operating range. This step involves a systematic evaluation of the parameters to ensure adjustments are made within a preset reasonable range. It also ensures that the adjusted operating parameters will not cause new faults or anomalies, providing a reliable foundation for subsequent printing jobs and improving overall printing efficiency and quality.
[0063] In one implementation, the weight of each group of historical fault adjustment strategies can be determined based on the similarity between the actual historical printing fault types and their severity in each group of historical fault adjustment strategies and the printing fault types and their severity.
[0064] Weights are assigned to different fault adjustment strategies based on the similarity between current and historical faults. Weights can be set by normalizing the similarity scores to ensure that more relevant fault adjustment strategies dominate the process. Determining the weights allows for more precise application of historical data, enhancing processing effectiveness and making adjustment strategies more targeted and effective, ensuring that the results better reflect the actual situation.
[0065] Based on the historical parameter values and weights of the operating parameters after fault adjustment in each group's historical fault adjustment strategy, the parameter values of the operating parameters of the photopolymerization printing equipment after adjustment are calculated.
[0066] Based on the established 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 and corresponding weights of all influencing parameters. Through weighted calculation, it is ensured that the new parameter values are reasonable and effective after adjustment, effectively reducing the risk of failure and providing a stable parameter basis for subsequent printing tasks.
[0067] In another implementation, the average or median value of the historical parameter values of each operating parameter after fault adjustment in each group of historical fault adjustment strategies can be calculated as the parameter values of the operating parameters of the adjusted photopolymerization printing equipment.
[0068] When determining new operating parameter values, the average or median of each parameter's historical values after adjustment in the historical fault adjustment strategy can be calculated and directly used as a reference value for the current parameter. This balances the impact of extreme values and ensures the stability of parameter settings. Using historical averages or medians helps avoid bias from a single data point, ensuring that the adjusted parameters are more stable and reasonable, thereby reducing the likelihood of faults and improving the reliability of print quality.
[0069] All adjusted operating parameters and their values are input into a pre-trained AI-based first printing fault prediction model to predict the potential printing fault types and their severity of the photopolymerization printing equipment, and to determine whether the predicted printing fault types have reached the level of fault-free operation.
[0070] The adjusted parameters are re-input into the AI model for another prediction to ensure the adjustment is effective. This step verifies the rationality of the final parameter settings and ensures the device functions properly under the new parameters. Model validation allows for rapid assessment of the impact of parameter adjustments, ensuring no potential problems are overlooked during operation and providing a feedback mechanism to optimize the adjustment process.
[0071] If the predicted printing fault type does not reach fault-free status, return to the step of adjusting the current operating parameters of the photopolymer printer based on the historical fault adjustment strategy for each group, until the predicted printing fault type reaches fault-free status.
[0072] If potential faults persist after the initial prediction, the process must return to the previous step and continue applying historical fault adjustment strategies to further optimize parameters until the predetermined fault-free state is achieved. This feedback mechanism ensures continuous improvement of the printing process, emphasizing the importance of dynamic adjustment and real-time optimization, enabling the fault management process to self-correct and guaranteeing stable equipment operation.
[0073] Furthermore, before adjusting the parameter values of each operating parameter according to the printing fault type and its severity, if an abnormal operating parameter is found, the abnormal operating parameter and its value are input into a pre-trained AI-based second printing fault prediction model to predict the current printing fault type and its severity of the photopolymerization printing device. The second printing fault prediction model is trained based on historical abnormal operating parameters and their values, corresponding historical actual fault modes and their severity.
[0074] This step begins with detecting abnormal operating parameters, a prerequisite for ensuring the printing equipment is operating safely. If an anomaly is detected, these abnormal parameters and their values are input into a pre-trained AI-based second printing fault prediction model. This model is specifically trained on historical abnormal operating parameters, their values, and corresponding fault modes, enabling it to efficiently analyze the current equipment status and predict the type and severity of related printing faults. This process not only predicts faults based on existing data but also considers specific operating environments and equipment states, 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 anomalies in detail, thereby guiding further parameter adjustments and fault handling.
[0075] Specifically, sensors can monitor various operating parameters of the printing equipment in real time, and values exceeding the normal range are marked as anomalous parameters. These anomalous parameters are then preprocessed, including denoising, standardization, and normalization, to facilitate input into subsequent models. Feature engineering is performed on multiple anomalous parameters to extract key information. This may include using Principal Component Analysis (PCA) to reduce dimensionality and identify parameters most relevant to fault prediction. Next, correlation analysis is performed using parameters such as Pearson or Spearman correlation coefficients to assess the association between different parameters, helping to understand how these anomalous parameters affect overall print quality. A predictive model for the anomalous parameters is built using deep learning frameworks (such as LSTM or CNN). This model not only considers single anomalous parameters but also captures complex relationships between parameters, learning from historical data and identifying potential fault patterns. The model needs to be optimized during training using historical anomalous parameters and their corresponding fault types; new anomalous parameter data is continuously input into the model for dynamic updates. Transfer learning can be used to combine newly collected data with existing training data to optimize model parameters, improving its predictive power and adaptability; and multi-model fusion is performed based on the model's predictions. Multiple trained models (such as random forests and support vector machines) can be combined, and a weighted voting mechanism can be used to generate the final fault prediction result. Each model is assigned different weights based on its performance on historical data, thereby improving the accuracy of the prediction. The prediction results are monitored and compared with the actual printing results, establishing a feedback mechanism. Any new fault data will be fed back into the model for retraining, enhancing the accuracy of its subsequent predictions. Simultaneously, real-time monitoring allows operators to understand the equipment status immediately and further optimize decision-making. In summary, the difference between the first and second printing fault prediction models is:
[0076] 1. Differences in the base data for model training:
[0077] The first printing fault prediction model is trained based on all historical operating parameters and their values, corresponding historical actual fault modes and their severity. It aims to comprehensively analyze the relationship between the performance of various operating parameters and faults throughout the printing process. The second printing fault prediction model is trained based on historical abnormal operating parameters and their values, corresponding historical actual fault modes and their severity. It focuses on analyzing parameters that have been marked as abnormal, helping to identify faults that may occur under specific abnormal conditions.
[0078] 2. Different Prediction Focuses: The first printing failure prediction model aims to predict the type and severity of potential printing failures, typically used when equipment operating parameters are normal or no obvious abnormalities are found. It emphasizes overall performance and stability. The second printing failure prediction model focuses on known abnormal parameters to predict the type and severity of failures under specific conditions. Its application scenario is after an anomaly is discovered, further analyzing the potential failures caused by the anomaly.
[0079] 3. Different application scenarios: The first printing fault prediction model is suitable for fault prediction under normal operating conditions, helping operators to be aware of potential risks in advance; the second printing fault prediction model is suitable for in-depth analysis of equipment after an anomaly is detected, quickly locating the cause of the anomaly and providing adjustment suggestions.
[0080] The significance of the design lies in:
[0081] 1. Targeted and accurate: By training two models separately, in-depth analysis can be performed 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 targetedness of the prediction.
[0082] 2. Enhanced hierarchical fault detection: This design ensures analysis from macro to micro levels. The first model has a global perspective, capable of identifying potential risks to overall operational efficiency and long-term performance; the second model delves into specific anomaly levels, enabling rapid response and providing targeted solutions.
[0083] 3. Enhanced system robustness: By using two different models, the system can reliably predict failures under various operating conditions. Even in abnormal situations, timely measures can still be taken to reduce the impact of failures on production efficiency.
[0084] 4. Flexibility and Adaptability: This design allows the model to flexibly adjust its prediction strategy based on changes in different operating parameters and equipment status. The comprehensiveness of the first model and the specialization of the second model complement each other, making the entire fault prediction system more robust.
[0085] 5. Promote continuous system improvement: By analyzing the matching degree between the prediction effect of the two models and the actual faults, the algorithm and data acquisition strategy can be continuously optimized, enabling the system to learn and adapt to new fault modes and improve the overall intelligence level.
[0086] As can be seen, the system collects the parameter values of various operating parameters during the printing process of the photopolymerization printing equipment; based on these parameter values, it searches for abnormal operating parameters; if no abnormal operating parameters are found, it inputs all operating parameters and their values into a pre-trained AI-based first printing fault prediction model to predict the potential printing fault types and their severity; based on the printing fault types and their severity, it adjusts the parameter values of each operating parameter to ensure that the predicted printing fault types are fault-free and that there are no abnormal operating parameters. This allows for the collection of real-time operating parameters, identification of abnormal situations, and prediction of fault types and severity based on an AI model, thereby improving the timeliness and accuracy of fault detection and enabling automatic adjustment of printing parameters to ensure a stable and reliable printing process.
[0087] Another embodiment of the present invention provides a system for handling abnormal operation of photopolymer 3D printing, see [link to relevant documentation]. Figure 3 The system may include:
[0088] The acquisition module 301 is used to acquire the parameter values of various operating parameters during the printing process of the photopolymerization printing equipment;
[0089] The lookup module 302 is used to look up abnormal operating parameters among the operating parameters based on the parameter values.
[0090] The first prediction module 303 is used to input all operating parameters and their values into a pre-trained AI-based first printing fault prediction model if no abnormal operating parameters are found, to predict the potential printing fault types and their severity of the light-curing printing device. The first printing fault prediction model is trained based on all historical operating parameters and their values, corresponding historical actual fault modes and their severity.
[0091] The adjustment module 304 is used to adjust the parameter values of each operating parameter according to the type and severity of the printing fault, so that the predicted printing fault type is fault-free and there are no abnormal operating parameters among the operating parameters.
[0092] As can be seen, the system collects the parameter values of various operating parameters during the printing process of the photopolymerization printing equipment; based on these parameter values, it searches for abnormal operating parameters; if no abnormal operating parameters are found, it inputs all operating parameters and their values into a pre-trained AI-based first printing fault prediction model to predict the potential printing fault types and their severity; based on the printing fault types and their severity, it adjusts the parameter values of each operating parameter to ensure that the predicted printing fault types are fault-free and that there are no abnormal operating parameters. This allows for the collection of real-time operating parameters, identification of abnormal situations, and prediction of fault types and severity based on an AI model, thereby improving the timeliness and accuracy of fault detection and enabling automatic adjustment of printing parameters to ensure a stable and reliable printing process.
[0093] This invention also provides a storage medium storing a computer program, wherein the computer program is configured to execute the steps in any of the above method embodiments when running.
[0094] Specifically, in this embodiment, the storage medium can be configured to store a computer program for performing the following steps:
[0095] S201, collects the parameter values of various operating parameters during the printing process of the photopolymerization printing equipment;
[0096] S202, based on the parameter values, find the abnormal operating parameters among the operating parameters;
[0097] S203, if no abnormal operating parameters are found, input all operating parameters and their values into a pre-trained AI-based first printing fault prediction model to predict the potential printing fault types and their severity of the light-curing printing device. The first printing fault prediction model is trained based on all historical operating parameters and their values, corresponding historical actual fault modes and their severity.
[0098] S204, Based on the type and severity of the printing fault, adjust the parameter values of each operating parameter to ensure that the predicted printing fault type is fault-free and that there are no abnormal operating parameters among the operating parameters.
[0099] As can be seen, the system collects the parameter values of various operating parameters during the printing process of the photopolymerization printing equipment; based on these parameter values, it searches for abnormal operating parameters; if no abnormal operating parameters are found, it inputs all operating parameters and their values into a pre-trained AI-based first printing fault prediction model to predict the potential printing fault types and their severity; based on the printing fault types and their severity, it adjusts the parameter values of each operating parameter to ensure that the predicted printing fault types are fault-free and that there are no abnormal operating parameters. This allows for the collection of real-time operating parameters, identification of abnormal situations, and prediction of fault types and severity based on an AI model, thereby improving the timeliness and accuracy of fault detection and enabling automatic adjustment of printing parameters to ensure a stable and reliable printing process.
[0100] This invention also 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 perform the steps in any of the above method embodiments.
[0101] Specifically, the aforementioned electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the aforementioned processor, and the input / output device is connected to the aforementioned processor.
[0102] Specifically, in this embodiment, the processor can be configured to perform the following steps via a computer program:
[0103] S201, collects the parameter values of various operating parameters during the printing process of the photopolymerization printing equipment;
[0104] S202, based on the parameter values, find the abnormal operating parameters among the operating parameters;
[0105] S203, if no abnormal operating parameters are found, input all operating parameters and their values into a pre-trained AI-based first printing fault prediction model to predict the potential printing fault types and their severity of the light-curing printing device. The first printing fault prediction model is trained based on all historical operating parameters and their values, corresponding historical actual fault modes and their severity.
[0106] S204, Based on the type and severity of the printing fault, adjust the parameter values of each operating parameter to ensure that the predicted printing fault type is fault-free and that there are no abnormal operating parameters among the operating parameters.
[0107] As can be seen, the system collects the parameter values of various operating parameters during the printing process of the photopolymerization printing equipment; based on these parameter values, it searches for abnormal operating parameters; if no abnormal operating parameters are found, it inputs all operating parameters and their values into a pre-trained AI-based first printing fault prediction model to predict the potential printing fault types and their severity; based on the printing fault types and their severity, it adjusts the parameter values of each operating parameter to ensure that the predicted printing fault types are fault-free and that there are no abnormal operating parameters. This allows for the collection of real-time operating parameters, identification of abnormal situations, and prediction of fault types and severity based on an AI model, thereby improving the timeliness and accuracy of fault detection and enabling automatic adjustment of printing parameters to ensure a stable and reliable printing process.
[0108] The above description, based on the embodiments shown in the figures, details the structure, features, and effects of the present invention. The above description is only a preferred embodiment of the present invention, but the present invention is not limited to the scope of implementation shown in the figures. Any changes made in accordance with the concept of the present invention, or equivalent embodiments modified to have equivalent changes, that do not exceed the spirit covered by the specification and figures, should be within the protection scope of the present invention.
Claims
1. A method for handling abnormal operation of photopolymer 3D printing, characterized in that, The method includes: Collect the parameter values of various operating parameters during the printing process of the photopolymerization printing equipment; Based on the parameter values, identify any abnormal operating parameters among the operating parameters; If no abnormal operating parameters are found, all operating parameters and their values are input into a pre-trained AI-based first printing fault prediction model to predict the potential printing fault types and their severity of the light-curing printing device. The first printing fault prediction model is trained based on all historical operating parameters and their values, corresponding historical actual fault modes and their severity. Based on the type and severity of the printing fault, the parameter values of each operating parameter are adjusted to ensure that the predicted printing fault type is fault-free and that there are no abnormal operating parameters among the operating parameters; the adjustment of the parameter values of each operating parameter based on the type and severity of the printing fault includes: From the printing equipment database, find several historical actual printing fault types and their degrees that have a similarity higher than a preset threshold with the printing fault type and its degree; obtain the historical parameter values of the operating parameters before fault adjustment and the historical parameter values of the operating parameters after fault adjustment corresponding to several historical actual printing fault types and their degrees, as historical fault adjustment strategies; based on each set of historical fault adjustment strategies, adjust the current operating parameters of the photopolymerization printing equipment, wherein the parameter values of each operating parameter after adjustment are all within the normal range; All adjusted operating parameters and their values are input into a pre-trained AI-based first printing fault prediction model to predict the potential printing fault types and their severity of the photopolymer printing device, and to determine whether the predicted printing fault types have reached the fault-free level. If the predicted printing fault types have not reached the fault-free level, the process returns to the step of adjusting the current operating parameters of the photopolymer printing device based on the historical fault adjustment strategies of each group, until the predicted printing fault types reach the fault-free level.
2. The method according to claim 1, characterized in that, The method further includes: Before adjusting the values of each operating parameter according to the type and severity of the printing failure, if an abnormal operating parameter is found, the abnormal operating parameter and its value are input into a pre-trained AI-based second printing failure prediction model to predict the current printing failure type and severity of the photopolymerization printing device. The second printing failure prediction model is trained based on historical abnormal operating parameters and their values, corresponding historical actual failure modes and their severity.
3. The method according to claim 2, characterized in that, The adjustment of the current operating parameters of the photopolymerization printing equipment based on the historical fault adjustment strategies of each group includes: The weight of each group of historical fault adjustment strategies is determined based on the similarity between the actual historical printing fault types and their severity in each group and the printing fault types and their severity. Based on the historical parameter values and weights of the operating parameters after fault adjustment in each group's historical fault adjustment strategy, the parameter values of the operating parameters of the photopolymerization printing equipment after adjustment are calculated.
4. The method according to claim 2, characterized in that, The adjustment of the current operating parameters of the photopolymerization printing equipment based on the historical fault adjustment strategies of each group includes: Calculate the average or median value of the historical parameter values of each operating parameter after fault adjustment in each group of historical fault adjustment strategies, and use it as the parameter value of the operating parameters of the light-curing printing equipment after adjustment.
5. A system for handling abnormal operation of photopolymer 3D printing, characterized in that, The system includes: The data acquisition module is used to collect the parameter values of various operating parameters during the printing process of the photopolymerization printing equipment; The search module is used to search for abnormal operating parameters among the operating parameters based on the parameter values. The first prediction module is used to input all operating parameters and their values into a pre-trained AI-based first printing fault prediction model if no abnormal operating parameters are found, and predict the potential printing fault types and their severity of the light-curing printing device. The first printing fault prediction model is trained based on all historical operating parameters and their values, corresponding historical actual fault modes and their severity. The adjustment module is used to adjust the parameter values of each operating parameter according to the printing fault type and its severity, so that the predicted printing fault type reaches fault-free and there are no abnormal operating parameters among the operating parameters; the adjustment of the parameter values of each operating parameter according to the printing fault type and its severity includes: From the printing equipment database, find several historical actual printing fault types and their degrees that have a similarity higher than a preset threshold with the printing fault type and its degree; obtain the historical parameter values of the operating parameters before fault adjustment and the historical parameter values of the operating parameters after fault adjustment corresponding to several historical actual printing fault types and their degrees, as historical fault adjustment strategies; based on each set of historical fault adjustment strategies, adjust the current operating parameters of the photopolymerization printing equipment, wherein the parameter values of each operating parameter after adjustment are all within the normal range; All adjusted operating parameters and their values are input into a pre-trained AI-based first printing fault prediction model to predict the potential printing fault types and their severity of the photopolymer printing device, and to determine whether the predicted printing fault types have reached the fault-free level. If the predicted printing fault types have not reached the fault-free level, the process returns to the step of adjusting the current operating parameters of the photopolymer printing device based on the historical fault adjustment strategies of each group, until the predicted printing fault types reach the fault-free level.
6. The system according to claim 5, characterized in that, The system also includes: The second prediction module is used to, before adjusting the parameter values of each operating parameter according to the printing fault type and its degree, if an abnormal operating parameter is found, input the abnormal operating parameter and its value into a pre-trained AI-based second printing fault prediction model to predict the current printing fault type and its degree of the light-curing printing device. The second printing fault prediction model is trained based on historical abnormal operating parameters and their values, corresponding historical actual fault modes and their degrees of fault.
7. A storage medium, characterized in that, The storage medium stores a computer program, wherein the computer program is configured to execute the method of any one of claims 1-4 when it is run.
8. An electronic device comprising a memory and a processor, characterized in that, The memory stores a computer program, and the processor is configured to run the computer program to perform the method of any one of claims 1-4.