Extrusion flow data processing method and system based on prediction algorithm

Abstract

The invention discloses an extrusion flow data processing method and system based on a prediction algorithm. The method comprises the following steps: acquiring current printing parameter data of printing equipment; according to the current printing parameter data, predicted extrusion flow data of the printing equipment in the next time period are predicted through a pre-trained flow prediction model, and the flow prediction model is obtained through training based on printing parameter data of the printing equipment in the previous time period and corresponding actual extrusion flow data; the predicted extrusion flow data are compared with preset planned extrusion flow data, and the extrusion flow deviation and the printing stability index of the printing equipment are calculated; and determining the printing state of the printing equipment according to the extrusion flow deviation and the printing stability index. By utilizing the embodiment of the invention, efficient prediction and control of the extrusion flow can be realized, a reliable basis is provided for judgment of a printing state, the stability of a printing process and the product quality are further improved, and more scientific decision support is provided for subsequent printing production.

Description

Technical Field

[0001] The invention belongs to the field of printing technology, and in particular to an extrusion flow data processing method and system based on a prediction algorithm. Background Art

[0002] 3D printing technology, also known as additive manufacturing, is a manufacturing technology that creates three-dimensional objects by adding materials layer by layer. Unlike traditional subtractive manufacturing (such as turning and milling), 3D printing can build complex shapes and structures directly from computer three-dimensional models. Due to its design flexibility and production efficiency, 3D printing technology has been widely used in many fields such as medicine, aerospace, automobiles, consumer products, etc.

[0003] In the 3D printing process, extrusion flow is one of the key factors that determine the printing quality and accuracy. Extrusion flow refers to the amount of material extruded by the printer nozzle per unit time, which directly affects the structure and appearance quality of the printed object. If the extrusion flow is unstable or inaccurate, it will cause defects in the printed object, such as poor inter-layer adhesion, uneven surface or dimensional deviation. Therefore, ensuring the accuracy and stability of the extrusion flow is one of the core challenges of 3D printing technology. Summary of the invention

[0004] The purpose of the present invention is to provide an extrusion flow data processing method and system based on a prediction algorithm to solve the deficiencies in the prior art, to achieve efficient prediction and control of the extrusion flow, to provide a reliable basis for judging the printing status, thereby improving the stability of the printing process and product quality, and to provide more scientific decision support for subsequent printing production.

[0005] An embodiment of the present application provides a method for processing extrusion flow data based on a prediction algorithm, the method comprising:

[0006] Get the current printing parameter data of the printing device;

[0007] According to the current printing parameter data, using a pre-trained flow prediction model, predicting the predicted extrusion flow data of the printing device in the next time period, wherein the flow prediction model is trained based on the printing parameter data of the printing device in the previous time period and the corresponding actual extrusion flow data;

[0008] Compare the predicted extrusion flow data with the preset planned extrusion flow data, and calculate the extrusion flow deviation and printing stability index of the printing device;

[0009] The printing state of the printing device is determined according to the extrusion flow deviation and the printing stability index.

[0010] Optionally, the calculation formula for the extrusion flow deviation is:

[0011]

[0012] Among them, the EFDD is the extrusion flow deviation, the X_{t,i} is the predicted extrusion flow at the i-th time point in the next time period t, the hat{X}_{t,i} is the planned extrusion flow at the i-th time point, the mean(X_t) is the mean of the predicted extrusion flow data in the next time period t, the min(X_t) is the minimum value of the predicted extrusion flow data in the next time period t, the std(X_t) is the standard deviation of the predicted extrusion flow data in the next time period t, and n is the number of time points.

[0013] Optionally, the calculation formula of the printing stability index is:

[0014]

[0015] Wherein, the PSI is the printing stability index, the X_{t,i-1} is the predicted extrusion flow rate at the (i-1)th time point in the next time period t, and the It represents the average absolute change of the predicted extrusion flow rate, and the lambda_1 and lambda_2 are the corresponding weight coefficients.

[0016] Optionally, determining the printing state of the printing device according to the extrusion flow deviation and the printing stability index includes:

[0017] If the extrusion flow deviation is less than or equal to the preset deviation threshold, and the printing stability index is greater than or equal to the preset stability threshold, it is determined that the printing device is in a normal printing state; otherwise, it is determined that the printing device is in an abnormal printing state.

[0018] Optionally, the method further includes:

[0019] After determining that the printing device is in an abnormal printing state, adjust the current printing parameter data of the printing device, and return to execute the step of predicting the extrusion flow data of the printing device in the next time period based on the current printing parameter data using a pre-trained flow prediction model, until the extrusion flow deviation is less than or equal to the preset deviation threshold, and the printing stability index is greater than or equal to the preset stability threshold.

[0020] Another embodiment of the present application provides an extrusion flow data processing system based on a prediction algorithm, the system comprising:

[0021] An acquisition module is used to acquire current printing parameter data of a printing device;

[0022] A prediction module, used to predict the predicted extrusion flow data of the printing device in the next time period according to the current printing parameter data and using a pre-trained flow prediction model, wherein the flow prediction model is trained based on the printing parameter data of the printing device in the previous time period and the corresponding actual extrusion flow data;

[0023] A calculation module, used for comparing the predicted extrusion flow data with the preset planned extrusion flow data, and calculating the extrusion flow deviation and printing stability index of the printing device;

[0024] The determination module is used to determine the printing state of the printing device according to the extrusion flow deviation and the printing stability index.

[0025] 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.

[0026] 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.

[0027] Compared with the prior art, the present invention provides an extrusion flow data processing method based on a prediction algorithm, which obtains current printing parameter data of a printing device; according to the current printing parameter data, a pre-trained flow prediction model is used to predict the predicted extrusion flow data of the printing device in the next time period, wherein the flow prediction model is trained based on the printing parameter data of the printing device in the previous time period and the corresponding actual extrusion flow data; the predicted extrusion flow data is compared with the preset planned extrusion flow data, and the extrusion flow deviation and the printing stability index of the printing device are calculated; according to the extrusion flow deviation and the printing stability index, the printing status of the printing device is determined, thereby achieving efficient prediction and control of the extrusion flow, providing a reliable basis for judging the printing status, thereby improving the stability of the printing process and product quality, and providing more scientific decision support for subsequent printing production. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 A hardware structure block diagram of a computer terminal for a method for processing extrusion flow data based on a prediction algorithm provided by an embodiment of the present invention;

[0029] Figure 2 A schematic flow chart of a method for processing extrusion flow data based on a prediction algorithm provided by an embodiment of the present invention;

[0030] Figure 3A schematic structural diagram of an extrusion flow data processing system based on a prediction algorithm provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0031] 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.

[0032] The embodiment of the present invention firstly provides a method for processing extrusion flow data based on a prediction algorithm. The method can be applied to electronic devices, such as computer terminals, specifically ordinary computers, etc.

[0033] 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 processing extrusion flow data based on a prediction algorithm provided by an embodiment of the present invention. Figure 1 As shown, the computer terminal may include one or more ( Figure 1 Only one is shown in the figure) a processor 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data. Optionally, the computer terminal may also include a transmission device 106 for communication functions and an input and output device 108. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above-mentioned computer terminal. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations shown.

[0034] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / modules corresponding to the extrusion flow data processing method based on the prediction algorithm in the embodiment of the present application. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, that is, realizing the above method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the computer terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0035] The transmission device 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of a computer terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0036] See also Figure 2 The embodiment of the present invention provides a method for processing extrusion flow data based on a prediction algorithm, which may include the following steps:

[0037] S201, obtaining current printing parameter data of a printing device; specifically, one implementation may include:

[0038] 1. Printing parameter configuration system integration

[0039] - Configuration management module: A configuration management module is implemented in the printing device, which is responsible for managing and storing the printing parameters of the device. These parameters usually include nozzle temperature, printing speed, layer height, filling density, etc. The configuration management module needs to provide an interface that allows users to set and adjust these parameters through the device's control panel, software interface or remote management system.

[0040] - Real-time parameter acquisition: Implement a real-time parameter acquisition interface that can extract the current printing parameter data from the configuration management module. This interface can be a software-based API (application programming interface) or a hardware-based communication protocol (such as CAN bus, RS-232 serial communication, etc.). Ensure that the response time of the interface is fast enough to support real-time acquisition of printing parameter data.

[0041] 2. Data acquisition and recording

[0042] - Data capture: Extract the current printing parameter data from the configuration management module of the printing device. This can be achieved by the following methods:

[0043] - Configuration file reading: If the printing parameters are stored in configuration files, the system can read these files periodically or in real time to obtain the latest parameter data.

[0044] - Database query: If the parameter data is stored in the database, obtain the current parameter settings through database query (SQL query). Use transaction management and locking mechanisms to ensure the accuracy and consistency of parameters during data reading.

[0045] - Data recording: Store the acquired printing parameter data in a local cache or persistent storage system. The storage structure can be in the form of key-value pairs to ensure fast retrieval and update. The recorded data includes:

[0046] - Nozzle temperature: the current working temperature of the nozzle.

[0047] - Print speed: Print speed per minute.

[0048] - Layer height: the printing thickness of each layer.

[0049] - Filling density: The density ratio of the internal filling of the print.

[0050] - Other parameters: such as printing material type, extruder settings, material viscosity and print head pressure, etc.

[0051] 3. Data format and standardization

[0052] - Data formatting: Format the acquired print parameter data to ensure that the data types and units of different parameters are consistent. Common formats include JSON, XML or CSV formats. This helps maintain consistency in subsequent data processing and analysis.

[0053] - Standardization: Standardize different types of parameters. For example, convert temperature to degrees Celsius, convert speed to millimeters per second, etc. This can avoid data processing errors caused by different units.

[0054] 4. Data verification and validation

[0055] - Data integrity verification: Implement data integrity verification mechanism when extracting and recording printing parameter data. For example, check whether the parameter value is within a reasonable range to prevent abnormal data input caused by configuration errors or failures.

[0056] - Verification and validation: Verify and validate parameter data to ensure data accuracy. For example, by comparing with the preset parameter range, verify whether the current parameters meet the equipment specifications and operating requirements. If abnormal data is found, an alarm should be triggered or error information should be recorded for subsequent processing.

[0057] 5. User interface and feedback

[0058] - User interface design: Provide a user-friendly interface that allows operators to view and modify current printing parameters. This interface can be a touch screen on the device, a desktop application, or a web interface. The interface should provide clear parameter display and intuitive editing functions.

[0059] - Feedback mechanism: After setting or adjusting parameters, a real-time feedback mechanism is provided. The current printing parameter setting status and any possible errors or warnings are fed back to the operator through system messages, status indicators or interface prompts.

[0060] 6.Data transmission and interface

[0061] - Data transmission protocol: Design a data transmission protocol to transfer the acquired printing parameter data to other systems or modules (such as traffic prediction models). You can use network protocols (such as HTTP, WebSocket) or local communication protocols (such as USB, Bluetooth).

[0062] - API interface: Design a unified API interface to allow different system modules (such as prediction algorithm, status monitoring module) to access the current printing parameter data. The API interface should support efficient data transmission and low-latency response.

[0063] Through the above steps, it is possible to ensure that the current printing parameter data is accurately and effectively obtained from the configuration system of the printing device. These data are not only the basis for flow prediction and status judgment, but also provide necessary information support for the overall printing process control and optimization.

[0064] S202, predicting the predicted extrusion flow data of the printing device in the next time period according to the current printing parameter data using a pre-trained flow prediction model, wherein the flow prediction model is trained based on the printing parameter data of the printing device in the previous time period and the corresponding actual extrusion flow data; specifically, an implementation method may include:

[0065] Step 1: Data preparation and preprocessing

[0066] 1. Collect historical data:

[0067] - Data source: Collect the printing parameter data of the previous time period and the corresponding actual extrusion flow data from the database or log system of the printing device.

[0068] - Data type: including nozzle temperature, printing speed, layer height, filling density, actual extrusion flow, etc.

[0069] 2. Data cleaning:

[0070] - Outlier processing: Identify and process outliers in the data, and use median filtering or other robust statistical methods to remove extreme values.

[0071] - Missing value filling: Use interpolation methods (such as linear interpolation or spline interpolation) to fill in missing data to ensure data integrity.

[0072] 3. Feature Engineering:

[0073] - Feature selection: Select features that have a significant impact on flow prediction, such as nozzle temperature change rate, printing speed fluctuation, etc.

[0074] - Feature extraction: Extract features through time series analysis, such as calculating moving averages, differences, etc., to capture trends and periodic changes in the data.

[0075] Step 2: Training of traffic prediction model

[0076] 1. Model selection:

[0077] - Model type: Choose a model suitable for time series data, such as Long Short-Term Memory (LSTM) or Gated Recurrent Unit (GRU), which are good at handling long-term dependencies in time series data.

[0078] - Model architecture: Design the number of layers and the number of neurons in each layer of the LSTM or GRU model, and adjust them according to the actual data volume and complexity.

[0079] 2. Training data preparation:

[0080] - Time window division: historical data is divided into training set and validation set. For example, use the data of the past 90 minutes to predict the traffic of the next 10 minutes.

[0081] - Input format: Format the historical printing parameter data and actual extrusion flow data into model input data according to the time window. The input data includes historical parameters and flow, and the target data is the extrusion flow in the future time period.

[0082] 3. Model training:

[0083] - Training process: Use a gradient descent optimization algorithm (such as Adam optimizer) to train the model to minimize the mean square error (MSE) between the predicted value and the actual value.

[0084] - Regularization: Use Dropout or L2 regularization to prevent overfitting, and use early stopping techniques to monitor model performance on the validation set.

[0085] Step 3: Real-time prediction

[0086] 1. Real-time data acquisition:

[0087] - Interface call: Get the printing parameter data of the current time period through the device interface, including nozzle temperature, printing speed, etc.

[0088] 2. Data formatting:

[0089] - Input data preprocessing: The real-time acquired printing parameter data is preprocessed in the same format as the training data, including feature normalization (such as Z-score normalization) and time window segmentation.

[0090] 3. Traffic prediction:

[0091] - Model inference: Input the formatted real-time data into the pre-trained LSTM or GRU model to obtain the predicted value of the squeeze flow in the next time period.

[0092] - Output processing: Denormalize the output of the model and convert the predicted value back to the original dimension for subsequent use and analysis.

[0093] Step 4: Evaluate and adjust forecast results

[0094] 1. Forecast accuracy evaluation:

[0095] - Comparison with actual values: Compare the predicted values ​​with the actual measured flow data, and calculate the prediction accuracy index (such as root mean square error RMSE) to evaluate the accuracy of the model.

[0096] 2. Model update:

[0097] - Continuous learning: Update the model based on the latest actual extrusion flow data and printing parameter data, and retrain using online learning or incremental learning methods to maintain the timeliness and accuracy of the model.

[0098] - Feedback mechanism: When there is a large deviation between the predicted results and the actual data, record the abnormal situation and analyze the cause, and adjust the model's training strategy or parameter settings. ###

[0099] Through the above steps, the pre-trained flow prediction model can be used to predict the extrusion flow data of the printing device in the next time period. The key to this method is to select an appropriate time series model (such as LSTM or GRU) and combine it with real-time data for accurate prediction. Data preprocessing, model reasoning, and prediction result evaluation in the real-time prediction process are key steps to ensure the accuracy of flow prediction and equipment stability.

[0100] S203, comparing the predicted extrusion flow data with the preset planned extrusion flow data, and calculating the extrusion flow deviation and printing stability index of the printing device;

[0101] Specifically, a calculation formula for extrusion flow deviation can be:

[0102]

[0103] The EFD is the extrusion flow deviation, which is used to measure the difference between the actual extrusion flow and the planned extrusion flow. The smaller the EFD is, the closer the actual flow is to the planned flow.

[0104] The X_{t,i} is the predicted squeeze flow at the i-th time point in the next time period t, and the hat{X}_{t,i} is the planned squeeze flow at the i-th time point, which is the preset expected flow value. The mean(X_t) is the mean of the predicted squeeze flow data in the next time period t, reflecting the overall level of the predicted flow. The min(X_t) is the minimum value of the predicted squeeze flow data in the next time period t, which is used for the minimum value adjustment in the standardization process. The std(X_t) is the standard deviation of the predicted squeeze flow data in the next time period t, which quantifies the volatility of the flow forecast. The n is the number of time points, which determines the size of the sample when calculating the squeeze flow deviation.

[0105] This formula takes into account the overall level and volatility of flow data by standardizing the deviation between actual flow and planned flow to the ratio of mean and standard deviation, making the calculation of squeezed flow deviation relatively consistent and comparable.

[0106] Specifically, a calculation formula for the printing stability index may be:

[0107]

[0108] The PSI is a printing stability index, which measures the stability of the printing process. A higher index indicates better stability and less fluctuation.

[0109] The X_{t,i-1} is the predicted extrusion flow at the (i-1)th time point in the next time period t. It indicates the average absolute change of the predicted extrusion flow rate, reflecting the fluctuation of the flow rate prediction over time. The lambda_1 and lambda_2 are corresponding weight coefficients, which are used to adjust the contribution ratio of the standard deviation and the absolute change to the printing stability index.

[0110] This formula comprehensively considers the volatility of the predicted flow and its change over time, and evaluates the stability of the printing process by weighted average, so that the index can effectively reflect the actual status of the printing process.

[0111] The above formula can be used to compare and analyze the predicted extrusion flow data and the planned flow data in detail. The calculation of the extrusion flow deviation and the printing stability index not only provides quantitative indicators of the equipment's operating status, but also helps the system maintain the stability and accuracy of the printing process by conducting in-depth analysis of the actual performance and stability of the flow.

[0112] - Predicted extrusion flow data: The flow data obtained by the prediction algorithm represents the actual flow expected by the equipment in the future time period. These data are predicted based on the current printing parameters and historical data.

[0113] - Planned squeeze flow data: This is the preset ideal flow data, which is the target value that the equipment should reach under ideal conditions and is used as a benchmark for evaluating the actual flow. Comparison purpose:

[0114] - Measure accuracy: By comparing the predicted flow and planned flow, evaluate the accuracy of the prediction model and whether the operating status of the equipment is in line with expectations.

[0115] - Identify problems: Comparison results help identify the extent to which actual traffic deviates from planned traffic, thereby understanding whether there are anomalies or performance issues with the device.

[0116] S204, determining the printing state of the printing device according to the extrusion flow deviation and the printing stability index.

[0117] The main purpose of this step is to accurately determine the current performance status of the printing device by quantifying the extrusion flow deviation and printing stability index during the printing process. By comparing the theoretical prediction with the actual output, it is possible to effectively identify whether the printing device is working within the normal range, thereby discovering potential problems in advance and ensuring the optimization of printing quality and efficiency. This is particularly important in fields such as industrial production and 3D printing, as any deviation may lead to material waste, unqualified products or production stagnation.

[0118] Specifically, if the extrusion flow deviation is less than or equal to a preset deviation threshold, and the printing stability index is greater than or equal to a preset stability threshold, it is determined that the printing device is in a normal printing state; otherwise, it is determined that the printing device is in an abnormal printing state.

[0119] The core function of this step is to evaluate the operating status of the printing equipment based on the calculated extrusion flow deviation (EFD) and printing stability index (PSI). Specifically:

[0120] 1. Extrusion flow deviation (EFD): By comparing the actual predicted extrusion flow data with the preset planned extrusion flow data, evaluate whether the actual output of the equipment is consistent with expectations. If the EFD value is less than or equal to the preset deviation threshold, it indicates that the extrusion flow output of the equipment is close to the target value and the error is within an acceptable range.

[0121] 2. Print Stability Index (PSI): Measures the flow stability during the printing process. The higher the PSI value, the smaller the fluctuation of the extrusion flow and the more stable the printing process. If the PSI value is greater than or equal to the preset stability threshold, it means that the flow fluctuation of the device within the specified time period is within an acceptable range and the stability is good. Through the comprehensive evaluation of these two indicators:

[0122] - If EFD ≤ preset deviation threshold and PSI ≥ preset stability threshold, the printing device is considered to be in normal printing state. This means that the actual extrusion flow of the device is consistent with the plan, and the device is running stably and meets the expected operating standards.

[0123] - If EFD> preset deviation threshold and / or PSI< preset stability threshold, the printing device is identified as abnormal printing state. This indicates that there is a significant gap between the actual output of the device and the target, or the stability of the device is poor and may need adjustment or maintenance.

[0124] This step plays the following important roles in the overall data processing method:

[0125] 1. Quality control: By determining the status of the equipment as normal or abnormal, the printing process can be monitored and adjusted in real time to ensure that the quality of the final product meets the standards.

[0126] 2. Fault warning: If the equipment is in an abnormal state, potential faults or problems can be detected in time, so that measures can be taken to avoid production interruptions or substandard quality.

[0127] 3. Optimize operation: Through real-time evaluation of equipment status, equipment settings and operations can be optimized to improve production efficiency and reduce resource waste.

[0128] 4. Maintenance decision: Judging the status of the equipment can also help decide whether further maintenance or adjustments are needed to ensure long-term stable operation of the equipment.

[0129] In general, this step helps ensure the normal operation of the printing equipment through accurate indicator evaluation and provides timely feedback when the equipment status is abnormal, which helps maintain the overall performance and production quality of the equipment.

[0130] Furthermore, after determining that the printing device is in an abnormal printing state, the current printing parameter data of the printing device may be adjusted; step description:

[0131] - Adjust the current printing parameter data: When the system detects that the status of the printing device is abnormal (for example, the extrusion flow deviation is too large or the printing stability index is too low), the system needs to adjust the device's setting parameters, such as nozzle temperature, printing speed, etc. Function and significance:

[0132] - Optimize print quality: By adjusting parameters, the actual flow rate can be made closer to the planned flow rate, thereby improving print quality.

[0133] - Restore device status: Adjusting parameters helps restore the device to normal working state and reduce the impact of abnormalities on the printing process.

[0134] Return to the step of predicting the extrusion flow data of the printing device in the next time period according to the current printing parameter data using the pre-trained flow prediction model; step description:

[0135] - Re-forecast flow: After adjusting the equipment parameters, use the forecast model to recalculate the extrusion flow data for the next time period. This step ensures that the model uses the latest parameter configuration to obtain accurate forecast results. Function and significance:

[0136] - Update forecast: Re-forecasting traffic based on adjusted parameters can more accurately assess the working status of the equipment under the new parameters.

[0137] - Continuous Optimization: Provides a feedback mechanism that enables the device to verify the effect of each adjustment after each adjustment, thereby gradually optimizing the printing process.

[0138] Until the extrusion flow deviation is less than or equal to the preset deviation threshold, and the printing stability index is greater than or equal to the preset stability threshold. Step description:

[0139] - Repeated adjustment: The system will continuously adjust the equipment parameters, and make predictions and evaluations until the extrusion flow deviation and printing stability index reach the preset threshold.

[0140] - Ensure stability: Through continuous adjustments, the system ensures that the equipment will not stop or continue to run before reaching a stable printing state, thereby reducing potential problems in production.

[0141] - Improve printing quality: Ensure that in the final state, the actual printing parameters and flow rate of the equipment fully meet the preset standards, thereby improving printing quality and consistency.

[0142] Through the above steps, when an abnormal printing state is detected, the device parameters can be adjusted in time and the extrusion flow rate can be re-predicted to ensure the stable operation of the printing device. This iterative adjustment and verification mechanism can not only effectively improve the printing quality, but also ensure the stability of the device under various operating conditions.

[0143] It can be seen that the current printing parameter data of the printing device is obtained; according to the current printing parameter data, the predicted extrusion flow data of the printing device in the next time period is predicted using a pre-trained flow prediction model, wherein the flow prediction model is trained based on the printing parameter data of the printing device in the previous time period and the corresponding actual extrusion flow data; the predicted extrusion flow data is compared with the preset planned extrusion flow data, and the extrusion flow deviation and the printing stability index of the printing device are calculated; according to the extrusion flow deviation and the printing stability index, the printing status of the printing device is determined, thereby achieving efficient prediction and control of the extrusion flow, providing a reliable basis for judging the printing status, thereby improving the stability of the printing process and product quality, and providing more scientific decision support for subsequent printing production.

[0144] Another embodiment of the present invention provides an extrusion flow data processing system based on a prediction algorithm, see Figure 3 , the system may include:

[0145] An acquisition module 301 is used to acquire current printing parameter data of a printing device;

[0146] A prediction module 302 is used to predict the predicted extrusion flow data of the printing device in the next time period according to the current printing parameter data using a pre-trained flow prediction model, wherein the flow prediction model is trained based on the printing parameter data of the printing device in the previous time period and the corresponding actual extrusion flow data;

[0147] A calculation module 303, for comparing the predicted extrusion flow data with the preset planned extrusion flow data, and calculating the extrusion flow deviation and printing stability index of the printing device;

[0148] The determination module 304 is used to determine the printing state of the printing device according to the extrusion flow deviation and the printing stability index.

[0149] It can be seen that the current printing parameter data of the printing device is obtained; according to the current printing parameter data, the predicted extrusion flow data of the printing device in the next time period is predicted using a pre-trained flow prediction model, wherein the flow prediction model is trained based on the printing parameter data of the printing device in the previous time period and the corresponding actual extrusion flow data; the predicted extrusion flow data is compared with the preset planned extrusion flow data, and the extrusion flow deviation and the printing stability index of the printing device are calculated; according to the extrusion flow deviation and the printing stability index, the printing status of the printing device is determined, thereby achieving efficient prediction and control of the extrusion flow, providing a reliable basis for judging the printing status, thereby improving the stability of the printing process and product quality, and providing more scientific decision support for subsequent printing production.

[0150] 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.

[0151] Specifically, in this embodiment, the above storage medium may be configured to store a computer program for performing the following steps:

[0152] S201, obtaining current printing parameter data of the printing device;

[0153] S202, predicting the predicted extrusion flow data of the printing device in the next time period according to the current printing parameter data using a pre-trained flow prediction model, wherein the flow prediction model is trained based on the printing parameter data of the printing device in the previous time period and the corresponding actual extrusion flow data;

[0154] S203, comparing the predicted extrusion flow data with the preset planned extrusion flow data, and calculating the extrusion flow deviation and printing stability index of the printing device;

[0155] S204, determining the printing state of the printing device according to the extrusion flow deviation and the printing stability index.

[0156] It can be seen that the current printing parameter data of the printing device is obtained; according to the current printing parameter data, the predicted extrusion flow data of the printing device in the next time period is predicted using a pre-trained flow prediction model, wherein the flow prediction model is trained based on the printing parameter data of the printing device in the previous time period and the corresponding actual extrusion flow data; the predicted extrusion flow data is compared with the preset planned extrusion flow data, and the extrusion flow deviation and the printing stability index of the printing device are calculated; according to the extrusion flow deviation and the printing stability index, the printing status of the printing device is determined, thereby achieving efficient prediction and control of the extrusion flow, providing a reliable basis for judging the printing status, thereby improving the stability of the printing process and product quality, and providing more scientific decision support for subsequent printing production.

[0157] 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.

[0158] 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.

[0159] Specifically, in this embodiment, the processor may be configured to perform the following steps through a computer program:

[0160] S201, obtaining current printing parameter data of the printing device;

[0161] S202, predicting the predicted extrusion flow data of the printing device in the next time period according to the current printing parameter data using a pre-trained flow prediction model, wherein the flow prediction model is trained based on the printing parameter data of the printing device in the previous time period and the corresponding actual extrusion flow data;

[0162] S203, comparing the predicted extrusion flow data with the preset planned extrusion flow data, and calculating the extrusion flow deviation and printing stability index of the printing device;

[0163] S204, determining the printing state of the printing device according to the extrusion flow deviation and the printing stability index.

[0164] It can be seen that the current printing parameter data of the printing device is obtained; according to the current printing parameter data, the predicted extrusion flow data of the printing device in the next time period is predicted using a pre-trained flow prediction model, wherein the flow prediction model is trained based on the printing parameter data of the printing device in the previous time period and the corresponding actual extrusion flow data; the predicted extrusion flow data is compared with the preset planned extrusion flow data, and the extrusion flow deviation and the printing stability index of the printing device are calculated; according to the extrusion flow deviation and the printing stability index, the printing status of the printing device is determined, thereby achieving efficient prediction and control of the extrusion flow, providing a reliable basis for judging the printing status, thereby improving the stability of the printing process and product quality, and providing more scientific decision support for subsequent printing production.

[0165] 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 extrusion flow data based on prediction algorithm, It is characterized in that The method comprises: Get the current printing parameter data of the printing device; According to the current printing parameter data, using a pre-trained flow prediction model, predicting the predicted extrusion flow data of the printing device in the next time period, wherein the flow prediction model is trained based on the printing parameter data of the printing device in the previous time period and the corresponding actual extrusion flow data; Compare the predicted extrusion flow data with the preset planned extrusion flow data, and calculate the extrusion flow deviation and printing stability index of the printing device; The printing state of the printing device is determined according to the extrusion flow deviation and the printing stability index.

2. The method according to claim 1, It is characterized in that The calculation formula of the extrusion flow deviation is: Among them, the EFD is the extrusion flow deviation, the X_{t, i} is the predicted extrusion flow at the i-th time point in the next time period t, the hat{X}_{t, i} is the planned extrusion flow at the i-th time point, the mean(X_t) is the mean of the predicted extrusion flow data in the next time period t, the min(X_t) is the minimum value of the predicted extrusion flow data in the next time period t, the std(X_t) is the standard deviation of the predicted extrusion flow data in the next time period t, and n is the number of time points.

3. The method according to claim 2, It is characterized in that The calculation formula of the printing stability index is: Wherein, the PSI is the printing stability index, the X_{t, i-1} is the predicted extrusion flow rate at the (i-1)th time point in the next time period t, and the It represents the average absolute change of the predicted extrusion flow rate, and the lambda_1 and lambda_2 are the corresponding weight coefficients.

4. The method according to claim 3, It is characterized in that Determining the printing state of the printing device according to the extrusion flow deviation and the printing stability index includes: If the extrusion flow deviation is less than or equal to the preset deviation threshold, and the printing stability index is greater than or equal to the preset stability threshold, it is determined that the printing device is in a normal printing state; otherwise, it is determined that the printing device is in an abnormal printing state.

5. The method according to claim 4, It is characterized in that The method further comprises: After determining that the printing device is in an abnormal printing state, adjust the current printing parameter data of the printing device, and return to execute the step of predicting the extrusion flow data of the printing device in the next time period based on the current printing parameter data using a pre-trained flow prediction model, until the extrusion flow deviation is less than or equal to the preset deviation threshold, and the printing stability index is greater than or equal to the preset stability threshold.

6. An extrusion flow data processing system based on prediction algorithm, It is characterized in that The system comprises: An acquisition module is used to acquire current printing parameter data of a printing device; A prediction module, used to predict the predicted extrusion flow data of the printing device in the next time period according to the current printing parameter data and using a pre-trained flow prediction model, wherein the flow prediction model is trained based on the printing parameter data of the printing device in the previous time period and the corresponding actual extrusion flow data; A calculation module, used for comparing the predicted extrusion flow data with the preset planned extrusion flow data, and calculating the extrusion flow deviation and printing stability index of the printing device; The determination module is used to determine the printing state of the printing device according to the extrusion flow deviation and the printing stability index.

7. The system according to claim 6, It is characterized in that The calculation formula of the extrusion flow deviation is: Among them, the EFD is the extrusion flow deviation, the X_{t, i} is the predicted extrusion flow at the i-th time point in the next time period t, the hat{X}_{t, i} is the planned extrusion flow at the i-th time point, the mean(X_t) is the mean of the predicted extrusion flow data in the next time period t, the min(X_t) is the minimum value of the predicted extrusion flow data in the next time period t, the std(X_t) is the standard deviation of the predicted extrusion flow data in the next time period t, and n is the number of time points.

8. The system according to claim 7, It is characterized in that The calculation formula of the printing stability index is: Wherein, the PSI is the printing stability index, the X_{t, i-1} is the predicted extrusion flow rate at the (i-1)th time point in the next time period t, and the It represents the average absolute change of the predicted extrusion flow rate, and the lambda_1 and lambda_2 are the corresponding weight coefficients.

9. A storage medium, It is 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, It is 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