Extrusion flow data processing method and system based on dynamic calibration

Abstract

The application provides an extrusion flow data processing method and system based on dynamic calibration, and relates to the technical field of flow measurement. The method establishes a baseline relationship between sensor output and actual flow through initial calibration; real-time acquisition of extrusion flow data and environmental parameter data in the production process; dynamic calibration of sensor data using a preset process variable regression model; determination of calibration flow points according to rated section flow threshold and reduced working condition section flow threshold, acquisition of the standard volume of the extrusion container, screening of abnormal change data and normal change data, and volume correction; filtering, fusion and abnormality detection processing of the calibrated sensor data, real-time adjustment of the operating parameters of the extrusion equipment according to the processed flow data through a closed-loop control system, effective improvement of the precision and consistency of extrusion flow measurement, improvement of measurement precision and system stability, and strong support for optimization of the extrusion process and improvement of production efficiency.

Description

Technical Field

[0001] The present invention relates to the technical field of flow measurement, and in particular to an extrusion flow data processing method and system based on dynamic calibration. Background Art

[0002] In industrial production, flow measurement is a key component in controlling and managing material flow. In extrusion processes, in particular, accurate flow measurement is crucial for ensuring product quality, optimizing process parameters, improving production efficiency, and reducing energy consumption. Precise control of extrusion flow directly impacts physical properties such as product uniformity, strength, and density. Therefore, high-precision flow measurement methods and systems are a pressing need in modern industrial production.

[0003] However, due to factors such as environmental changes and equipment wear, traditional flow measurement methods often suffer from large errors and are unable to adjust and compensate for measurement errors in real time. This leads to inconsistent measurement results under different operating conditions and makes it difficult to meet high-precision requirements. Therefore, a flow data processing method and system that can dynamically calibrate and adjust in real time is urgently needed to improve measurement accuracy and system adaptability. Summary of the Invention

[0004] In view of this, the present invention proposes an extrusion flow data processing method and system based on dynamic calibration. Through dynamic volume calibration and data processing, the accuracy and consistency of extrusion flow measurement are effectively improved, the limitations of traditional flow measurement methods are effectively solved, the measurement accuracy and system stability are improved, and strong support is provided for the optimization of extrusion process and the improvement of production efficiency.

[0005] The present invention is achieved by adopting the following technical solutions:

[0006] In a first aspect, the present invention provides a method for processing extrusion flow data based on dynamic calibration, the method comprising the following steps:

[0007] Perform initial calibration of the extrusion system's sensors under standard environmental conditions and establish a baseline relationship between sensor output and actual flow rate;

[0008] Real-time acquisition of extrusion flow data during the production process, and simultaneous acquisition of environmental parameter data during flow measurement;

[0009] Based on the real-time collected extrusion flow data and environmental parameter data, the preset process variable regression model is used to dynamically calibrate the sensor data. The dynamic calibration results are used to compensate for the measurement errors caused by the environmental parameter data.

[0010] According to the rated section flow threshold and the reduced condition section flow threshold, a calibration flow point is determined, effective calibration data is recorded according to a preset dynamic calibration time interval, a standard volume of the extrusion container is obtained, abnormal change data and normal change data are screened, volume correction is performed, and dynamic compensation of flow is performed according to corrected data and a process variable regression model;

[0011] The calibrated sensor data is filtered to remove noise, and the flow data from different sensors is fused, abnormal data points are removed, and processed flow data is generated;

[0012] According to the processed flow data, the operating parameters of the extrusion device are adjusted in real time through a closed-loop control system.

[0013] As a further scheme of the present application, the step of performing initial calibration on the sensors of the extrusion system under standard environmental conditions includes:

[0014] Before initial calibration, check whether the sensors and measuring devices are normal, and set the temperature, humidity and electromagnetic environment free from interference according to the standard environmental conditions;

[0015] Select distilled water as the standard liquid, keep the temperature consistent with the standard ambient temperature, use a standard volume calibration device to measure the volume of the extrusion system container, and record the standard volume value;

[0016] According to the design flow range of the extrusion device, select at least three calibration points for calibration, wherein the selected calibration points include the calibration points of the lowest flow, the medium flow and the highest flow;

[0017] By adjusting the rotation speed of the extrusion gear and the operating parameters of the nozzle temperature in the extruder, the first calibration flow point is set and stabilized;

[0018] Use a standard flowmeter to measure the set flow, record the standard flow value, and simultaneously read the flow data output by the extruder sensor to record the original reading of the sensor;

[0019] At each calibration point, repeat the collection of sensor readings and standard flow values, calculate the error between the sensor readings and the standard flow values, and obtain the error data of each calibration point;

[0020] According to the collected sensor readings and actual flow data, a calibration curve of the relationship between the sensor output and the actual flow is drawn, and a linear regression is used to determine the mathematical model of the sensor output and the actual flow;

[0021] The linear regression is used to fit the data to determine the calibration coefficient between the sensor output and the actual flow;

[0022] Under different flow conditions, the flow data is measured again for the flow points that have not been calibrated, and the calibration curve is verified to evaluate whether the measurement error after calibration is within the acceptable range. If it is within the acceptable range, the baseline relationship between the sensor output and the actual flow is determined according to the calibration curve. If it is not within the acceptable range, recalibration is performed.

[0023] As a further solution of the present invention, when calculating the error between the sensor reading and the standard flow value, at each calibration point, the flow data is collected multiple times by the standard flow meter and the sensor. For each data point, when calculating the error, , calculate the sensor reading ( ) and standard flow value ( ) between the error ( ), the error calculation formula is:

[0024]

[0025] All The error data collected are counted to obtain the error data set of each calibration point .

[0026] As a further solution of the present invention, when a linear regression is used to determine the mathematical model of the sensor output and the actual flow rate, the sensor output reading and the corresponding standard flow rate value are collected at each calibration point. calibration points, the data set is: ;

[0027] The sensor output reading As the horizontal axis, the standard flow value As the vertical axis, draw a scatter plot;

[0028] Use linear regression analysis to fit the scatter plot, and the equation of the fitted line is:

[0029]

[0030] in, is the slope, is the intercept.

[0031] As a further embodiment of the present invention, linear regression is used to fit the data to determine the calibration coefficient between the sensor output and the actual flow rate. The sensor output readings of all calibration points are And the corresponding standard flow value Construct a matrix form and perform regression analysis; use the least squares method to calculate the linear regression parameters and , among which, first calculate Average value and Average value ; Then calculate the slope :

[0032]

[0033] Then, calculate the intercept :

[0034]

[0035] The calibration factor is the calculated slope and intercept , the final calibration formula is: .

[0036] As a further solution of the present invention, the flow data output by the sensor of the extrusion system is collected in real time when the sensor data is dynamically calibrated using the preset process variable regression model. , and collect environmental parameter data related to flow: temperature ,humidity and electromagnetic interference ;

[0037] According to the established process variable regression model, the environmental parameters are used as input variables and the flow data output by the sensor is used as the target variable; wherein, the preset process variable regression model is:

[0038]

[0039] in, to is the regression coefficient, is the error term;

[0040] Use historical data to train the regression model and determine the regression coefficients to ;

[0041] Input the real-time sensor output flow data and environmental parameter data into the dynamic calibration model to calculate the calibrated flow value , the calculation formula of the calibrated flow value is:

[0042]

[0043] According to the calibrated flow value Compensate for measurement errors caused by environmental parameters.

[0044] As a further solution of the present invention, according to the calibrated flow value The compensation process for the measurement error caused by environmental parameters is:

[0045] Calculate the flow error before calibration ;

[0046] Calculate the flow error after calibration ;

[0047] Use calibrated flow rate value As the final measured flow value.

[0048] As a further solution of the present invention, when filtering the calibrated sensor data, a mean filter is used to take the data mean within a time window to smooth data fluctuations. The formula for calculating the data mean is:

[0049]

[0050] in, is the time window size.

[0051] As a further solution of the present invention, when fusing traffic data from different sensors, the data from different sensors are aligned in time and synchronized using timestamps; and the data from different sensors are weightedly fused, wherein the calculation formula for weighted fusion is:

[0052]

[0053] Where, It is The flow data of each sensor, is the corresponding weight, satisfy:

[0054]

[0055] As a further solution of the present invention, anomaly detection is implemented to remove abnormal data points, and the mean and standard deviation of the flow data are calculated. Principle for anomaly detection. When judging anomalies, if:

[0056]

[0057] It is believed that is an abnormal data point;

[0058] Among them, the mean The calculation formula is:

[0059]

[0060] Standard deviation The calculation formula is:

[0061]

[0062] In a second aspect, the present application further comprises an extrusion flow data processing system based on dynamic calibration, which comprises:

[0063] a sensor calibration module, configured to perform initial calibration on the sensors of the extrusion system under standard environmental conditions, and establish a baseline relationship between the sensor output and the actual flow;

[0064] a sensor acquisition module, configured to acquire extrusion flow data in the production process in real time, and synchronously acquire environmental parameter data at the time of flow measurement;

[0065] a dynamic calibration module, configured to perform dynamic calibration on the sensor data based on the real-time acquired extrusion flow data and environmental parameter data, using a preset process variable regression model, and compensate for measurement errors caused by the environmental parameter data using the dynamic calibration result;

[0066] a calibration flow point determination module, configured to determine calibration flow points according to the rated section flow threshold and the reduced condition section flow threshold, record effective calibration data according to a preset dynamic calibration time interval, acquire the standard volume of the extrusion container, screen abnormal change data and normal change data, perform volume correction, and perform dynamic compensation of flow according to the corrected data and the process variable regression model;

[0067] a data processing module, configured to filter the calibrated sensor data to remove noise, and fuse flow data from different sensors, implement anomaly detection, eliminate abnormal data points, and generate processed flow data;

[0068] a closed-loop control module, configured to adjust the operating parameters of the extrusion equipment in real time through a closed-loop control system according to the processed flow data.

[0069] The present application further comprises a computer device, comprising at least one processor, and a memory in communication connection with the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to cause the at least one processor to execute the extrusion flow data processing method based on dynamic calibration.

[0070] The present application further comprises a computer readable storage medium, which stores computer instructions for causing the computer to execute the extrusion flow data processing method based on dynamic calibration.

[0071] Compared with the prior art, the extrusion flow data processing method and system based on dynamic calibration provided by the present application have the following beneficial effects:

[0072] 1. Improved measurement accuracy. By initially calibrating the sensor under standard environmental conditions and establishing a baseline relationship between sensor output and actual flow, the initial accuracy of the measurement is ensured. The dynamic calibration module uses real-time collected environmental parameter data to calibrate and compensate the sensor data, effectively reducing the impact of environmental changes on measurement accuracy.

[0073] 2. Enhanced data stability. The filtered sensor data after calibration effectively removes noise, ensuring the stability and reliability of the flow data. By fusing data from different sensors and using a weighted average method, the accuracy and stability of the data are further improved.

[0074] 3. Improved anomaly detection capability. The system can collect and analyze extrusion flow data in real time, and through the preset threshold and dynamic calibration time interval, it can timely find and eliminate abnormal data points, ensuring the authenticity and reliability of the data. Using statistical methods and machine learning algorithms, it accurately identifies abnormal change data, effectively preventing flow measurement errors caused by abnormal data.

[0075] 4. Improved system response speed. Real-time data collection and dynamic calibration enable the system to quickly respond to environmental changes and adjust calibration parameters in a timely manner, ensuring the continuity and accuracy of flow measurement. The closed-loop control module adjusts the operating parameters of the extrusion equipment in real time based on processed flow data, optimizing the production process and improving the overall response speed of the system.

[0076] 5. Ensures the continuity of the production process. Through real-time collection, dynamic calibration and closed-loop control, the system can continuously monitor and adjust the operating state of the extrusion equipment, reducing production stagnation and quality problems caused by data errors. The standard volume of the extrusion container and the record of effective calibration data ensure the continuity and consistency of the production process.

[0077] 6. Improved system adaptability and flexibility. The preset process variable regression model can be adjusted according to different production conditions and environmental parameters, improving the system's adaptability to different production environments. The application of data fusion and anomaly detection modules enables the system to flexibly respond to changes in sensor data, ensuring the accuracy and stability of data processing.

[0078] 7. Optimized resource utilization. Through accurate measurement and real-time adjustment of flow data, the system can optimize the operating parameters of the extrusion equipment, improve resource utilization efficiency, and reduce production costs. The elimination of abnormal data and the use of effective data reduce resource waste in the data processing process, improving the overall efficiency of the system.

[0079] In summary, the extrusion flow data processing method and system based on dynamic calibration of the present invention realizes high-precision measurement, stability enhancement, anomaly detection and real-time control of flow data through various technical means such as initial calibration, real-time data acquisition, dynamic calibration, data fusion, anomaly detection and closed-loop control, effectively improves the measurement accuracy, response speed and adaptability of the system, ensures the continuity and consistency of the production process, optimizes resource utilization, and has significant technical advantages and practical value.

[0080] These and other aspects of the present invention will become more readily apparent in the following description of the embodiments. It should be understood that the above general description and the following detailed description are merely exemplary and explanatory and are not intended to limit the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0081] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or related technologies, the following briefly introduces the drawings required for the exemplary embodiments or related technical descriptions. The drawings are used to provide a further understanding of the present invention and constitute part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the drawings:

[0082] Figure 1 The figure is a flow chart of an extrusion flow data processing method based on dynamic calibration according to an embodiment of the present invention. DETAILED DESCRIPTION

[0083] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0084] In some of the processes described in the specification and claims of the present invention and the above-mentioned figures, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this article or may be executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish between different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., and do not represent the order of precedence, nor do they limit "first" and "second" to be different types.

[0085] The technical solutions in the exemplary embodiments of the present application will be clearly and completely described below with reference to the drawings in the exemplary embodiments of the present application. Obviously, the described exemplary embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative efforts fall within the scope of the present application.

[0086] In order to solve the problem that the error is large in the traditional flow measurement method, the measurement error cannot be adjusted and compensated in real time, the measurement results are inconsistent under different working conditions, and it is difficult to meet the high-precision requirement, the present application provides an extrusion flow data processing method and system based on dynamic calibration. Through dynamic volume calibration and data processing, the precision and consistency of extrusion flow measurement are effectively improved, the limitations of the traditional flow measurement method are effectively solved, the measurement precision and the stability of the system are improved, and strong support is provided for optimization of the extrusion process and improvement of production efficiency.

[0087] The technical solutions of the present application will be further described below with reference to specific embodiments:

[0088] Referring to Figure 1 as shown, Figure 1 A flow chart of an extrusion flow data processing method based on dynamic calibration provided by the present application. The extrusion flow data processing method based on dynamic calibration provided in an embodiment of the present application comprises the following steps:

[0089] Step S10, under standard environmental conditions, performing initial calibration on the sensors of the extrusion system, and establishing a baseline relationship between the sensor output and the actual flow.

[0090] In this step, the step of performing initial calibration on the sensors of the extrusion system under standard environmental conditions comprises the following steps:

[0091] Before initial calibration, check whether the sensors and measurement devices are normal, and set the temperature, humidity and electromagnetic environment without interference according to the standard environmental conditions; wherein, before initial calibration, ensure that all sensors and measurement devices are working normally without failure. Check the power supply of the sensor connection and calibration device; ensure that the initial calibration is carried out under standard environmental conditions, including stable temperature (such as 25℃±2℃), humidity (such as 50%±10%) and electromagnetic environment without interference.

[0092] Select distilled water as the standard liquid, keep the temperature consistent with the standard environmental temperature, use a standard volume calibration device, measure the volume of the extrusion system container, and record the standard volume value;

[0093] According to the design flow range of the extrusion equipment, at least three calibration points are selected for calibration, wherein the selected calibration points include the lowest flow, the medium flow and the highest flow calibration points;

[0094] For the FDM 3D printer, the first calibration flow point is set and stabilized by adjusting the operation parameters of the rotation speed of the extrusion gear in the extruder and the nozzle temperature, wherein the rotation speed of the extrusion gear is adjusted to control the feeding speed of the consumables, and the nozzle temperature is adjusted to ensure that the consumables maintain the required viscosity and fluidity during the flow.

[0095] The set flow is measured by using a standard flow meter, and the standard flow value is recorded, and the flow data output by the sensor of the extruder is read synchronously, and the original reading of the sensor is recorded, wherein in the FDM 3D printer, the standard flow meter is an optical flow meter, which measures the speed and volume of the extruded material by using an optical sensor, and the feeding speed and the extrusion volume of the consumables are measured in real time by the optical sensor installed on the extrusion path, so as to determine the flow, and the standard flow meter is installed on the extrusion path, close to the position of the extrusion gear or the nozzle, to ensure that the feeding speed and the extrusion volume can be accurately measured;

[0096] At each calibration point, the sensor reading and the standard flow value are repeatedly collected, the error between the sensor reading and the standard flow value is calculated, and the error data of each calibration point is obtained;

[0097] According to the collected sensor reading and the actual flow data, a calibration curve of the relationship between the sensor output and the actual flow is drawn, and a linear regression is used to determine the mathematical model of the sensor output and the actual flow;

[0098] The linear regression is used to fit the data to determine the calibration coefficient between the sensor output and the actual flow;

[0099] Under different flow conditions, the flow data of the calibration points which have not been calibrated are measured again, the calibration curve is verified, and whether the measurement error after calibration is within an acceptable range is evaluated, if it is within the acceptable range, the baseline relationship between the sensor output and the actual flow is determined according to the calibration curve, if it is not within the acceptable range, the calibration is re-performed.

[0100] Wherein, when calculating the error between the sensor reading and the standard flow value, at each calibration point, the flow data is collected by the standard flow meter and the sensor multiple times, and if the flow data is collected times at each calibration point, the error is calculated, for each collection point , the error ( ) between the sensor reading ( ) and the standard flow value ( ) is calculated, and the error calculation formula is:

[0101]

[0102] All the error data collected in each calibration point is counted to obtain the error data set of each calibration point .

[0103] In this step, when determining the mathematical model of sensor output and actual flow by linear regression, the sensor output reading and the corresponding standard flow value are collected at each calibration point. If there are calibration points, the data set is: ;

[0104] The sensor output reading is taken as the abscissa, and the standard flow value is taken as the ordinate to draw a scatter plot.

[0105] The scatter plot is fitted using linear regression analysis, and the straight line equation obtained by fitting is:

[0106]

[0107] Wherein, is the slope, is the intercept.

[0108] When fitting the data using linear regression to determine the calibration coefficient between the sensor output and the actual flow, the sensor output readings and the corresponding standard flow values of all calibration points are constructed in matrix form for regression analysis; the linear regression parameters and are calculated using the least squares method, wherein the average value of and the average value of are calculated first; then the slope is calculated:

[0109]

[0110] Then, the intercept is calculated:

[0111]

[0112] The calibration coefficient is the calculated slope and intercept , and the final calibration formula is: .

[0113] Step S20, real-time acquisition of extrusion flow data in the production process, and synchronous acquisition of environmental parameter data during flow measurement.

[0114] In this step, a flow sensor is installed on the extrusion equipment to monitor the extrusion flow data in real time, and environmental parameter sensors are installed around the extrusion equipment, including but not limited to temperature sensors, humidity sensors, and pressure sensors, to synchronously collect environmental parameter data.

[0115] When initializing the sensor, calibrate the sensor to ensure its accuracy under standard environmental conditions, record the baseline data of the sensor for subsequent dynamic calibration, configure the data acquisition system, connect all sensors to the data acquisition system, set the data acquisition frequency, collect the flow sensor data in real time through the data acquisition system, and synchronously collect the environmental parameter sensor data to ensure that each flow data point has corresponding environmental parameter data. Finally, store the collected flow data and environmental parameter data in the data storage system, and perform preliminary processing on the data to remove obvious outliers and ensure data validity.

[0116] Step S30, based on the real-time collected extrusion flow data and environmental parameter data, using the preset process variable regression model, dynamically calibrating the sensor data, using the dynamic calibration result to compensate for the measurement error caused by the environmental parameter data.

[0117] In this step, when dynamically calibrating the sensor data using the preset process variable regression model, the flow data output by the sensors of the extrusion system is collected in real time , and the environmental parameter data related to the flow are collected: temperature , humidity , and electromagnetic interference ;

[0118] According to the established process variable regression model, the environmental parameters are taken as input variables, and the flow data output by the sensors are taken as target variables; wherein the preset process variable regression model is:

[0119]

[0120] wherein, to are regression coefficients, is an error term;

[0121] Use historical data to train the regression model to determine the regression coefficients to ;

[0122] Input the real-time collected sensor output flow data and environmental parameter data into the dynamic calibration model to calculate the calibrated flow value , and the formula for calculating the calibrated flow value is:

[0123]

[0124] According to the calibrated flow value Compensate for measurement errors caused by environmental parameters.

[0125] According to the calibrated flow value The compensation process for compensating for measurement errors caused by environmental parameters is:

[0126] Calculate the flow error before calibration ;

[0127] Calculate the flow error after calibration ;

[0128] Use the calibrated flow value As the final measured flow value.

[0129] Step S40, according to the rated section flow threshold and the reduced working condition section flow threshold, determine the calibration flow point, record the effective calibration data according to the preset dynamic calibration time interval, obtain the standard volume of the extrusion container, screen the abnormal change data and the normal change data, correct the volume, and perform dynamic compensation of the flow according to the corrected data and the process variable regression model.

[0130] According to the rated section flow threshold (for example, 80%-100% of the maximum working flow) and the reduced working condition section flow threshold (for example, 20%-40% of the maximum working flow) to select several calibration points. For example:

[0131] (1) Rated section flow point: 80%, 90%, 100%

[0132] (2) Reduced working condition section flow point: 20%, 30%, 40%.

[0133] When the preset dynamic calibration time interval, according to the equipment running stability and calibration demand, preset dynamic calibration time interval, for example, calibration is carried out once every hour or every working shift. In each calibration time interval, record the output flow data of the extrusion system sensor and the flow data of the standard flowmeter, ensure that the data collected each time calibration is carried out in a stable working state. Then, using the standard volume calibration device, periodically measure the standard volume of the extrusion container, and record the measurement results, screen the abnormal change data and the normal change data.

[0134] When filtering data for abnormal and normal changes, the collected data is preprocessed and statistical methods are used to filter out abnormal data. For example, the mean and standard deviation of the flow data are calculated to determine whether the data is within a reasonable range. Normal data is defined as data within the range of the mean ±2 times the standard deviation. Abnormal data is defined as data outside the range of the mean ±2 times the standard deviation.

[0135] Next, volume correction is performed. Based on the filtered normal data, the difference between the actual flow rate and the standard flow rate is calculated, and the volume of the extrusion container is corrected. The calculation formula is: Corrected volume = Standard volume + Flow rate difference. Finally, dynamic compensation is performed. Based on the corrected data and the preset fitting relationship, measurement errors caused by environmental changes or equipment aging are dynamically compensated. Flow compensation is performed using a dynamic calibration model (such as the process variable regression model mentioned above) to ensure more accurate measured flow data.

[0136] Step S50: Filter the calibrated sensor data to remove noise, fuse the flow data from different sensors, perform anomaly detection, remove abnormal data points, and generate processed flow data.

[0137] In this step, when filtering the calibrated sensor data, a mean filter is used to take the data mean within a time window to smooth data fluctuations. The formula for calculating the data mean is:

[0138]

[0139] in, is the time window size.

[0140] In this step, when fusing traffic data from different sensors, the data from different sensors are aligned in time and synchronized using timestamps. The data from different sensors are then weighted and fused. The calculation formula for weighted fusion is:

[0141]

[0142] Where, It is The flow data of each sensor, is the corresponding weight, satisfy:

[0143]

[0144] In this step, anomaly detection is implemented to remove abnormal data points, and the mean and standard deviation of the flow data are calculated. Principle for anomaly detection. When judging anomalies, if:

[0145]

[0146] It is believed that is an abnormal data point;

[0147] Among them, the mean The calculation formula is:

[0148]

[0149] Standard deviation The calculation formula is:

[0150] .

[0151] Step S60: According to the processed flow data, the operating parameters of the extrusion equipment are adjusted in real time through the closed-loop control system.

[0152] In this step, the target parameters are used as input signals in a closed-loop control system. The closed-loop control system comprises a controller, an actuator, and a feedback system. The controller calculates adjustment values ​​based on the target parameters and sends these values ​​to the actuator. The actuator receives these adjustment signals and adjusts the extruder's operating parameters (such as extrusion speed, temperature, and pressure) in real time. A feedback system is also configured to monitor the extruder's operating status in real time and transmit this feedback data to the controller, which then makes secondary adjustments based on this data to ensure system stability and accuracy.

[0153] The present invention provides a method for processing extrusion flow data based on dynamic calibration. This method ensures initial measurement accuracy by initially calibrating the sensor under standard environmental conditions and establishing a baseline relationship between the sensor output and the actual flow rate. The dynamic calibration module uses real-time collected environmental parameter data to calibrate and compensate the sensor data, effectively reducing the impact of environmental changes on measurement accuracy. Filtering the calibrated sensor data effectively removes noise, ensuring the stability and reliability of the flow data. By fusing data from different sensors and utilizing a weighted averaging method, the accuracy and stability of the data are further improved. The system can collect and analyze extrusion flow data in real time. Using preset thresholds and dynamic calibration intervals, it promptly detects and removes anomalous data points, ensuring the authenticity and reliability of the data. Statistical methods and machine learning algorithms are used to accurately identify data with anomalous variations, effectively preventing flow measurement errors caused by anomalous data. The combination of real-time data acquisition and dynamic calibration enables the system to rapidly respond to environmental changes and promptly adjust calibration parameters, ensuring the continuity and accuracy of flow measurement. The closed-loop control module uses the processed flow data to adjust the operating parameters of the extrusion equipment in real time, optimizing the production process and improving the overall response speed of the system. Through real-time data acquisition, dynamic calibration, and closed-loop control, the system continuously monitors and adjusts the operating status of extrusion equipment, reducing production downtime and quality issues caused by data errors. Recording the standard volume of extrusion vessels and valid calibration data ensures continuity and consistency in the production process.

[0154] The present invention provides a method for processing extrusion flow rate data based on dynamic calibration. The preset process variable regression model can be adjusted according to different production conditions and environmental parameters, thereby improving the system's adaptability to different production environments. The application of data fusion and anomaly detection modules enables the system to flexibly respond to changes in various sensor data, ensuring the accuracy and stability of data processing. Through the precise measurement and real-time adjustment of flow rate data, the system can optimize the operating parameters of the extrusion equipment, improve resource utilization efficiency, and reduce production costs. The elimination of abnormal data and the utilization of valid data reduce resource waste during the data processing process and improve the overall efficiency of the system.

[0155] It should be understood that, although the above is described in a certain order, these steps are not necessarily performed in sequence according to the above order. Unless there is clear explanation in this article, the execution of these steps does not have strict order restriction, and these steps can be performed in other orders. Moreover, a part of the steps of the present embodiment may include multiple steps or multiple stages, and these steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be performed in turn or alternately with at least a portion of the steps or stages in other steps or other steps.

[0156] In one embodiment, the present invention provides an extrusion flow rate data processing system based on dynamic calibration, which is used to execute the above-mentioned extrusion flow rate data processing method based on dynamic calibration. The system includes:

[0157] A sensor calibration module is used to perform initial calibration of the extrusion system's sensors under standard environmental conditions and establish a baseline relationship between the sensor output and the actual flow rate;

[0158] The sensor acquisition module is used to collect and obtain the extrusion flow data during the production process in real time, and simultaneously collect the environmental parameter data during flow measurement;

[0159] The dynamic calibration module is used to dynamically calibrate the sensor data based on the real-time collected extrusion flow data and environmental parameter data using a preset process variable regression model, and use the dynamic calibration results to compensate for the measurement error caused by the environmental parameter data;

[0160] The calibration flow point determination module is used to determine the calibration flow point based on the rated section flow threshold and the reduced operating condition section flow threshold, record the valid calibration data according to the preset dynamic calibration time interval, obtain the standard volume of the extrusion container, screen the abnormal change data and the normal change data, perform volume correction, and perform dynamic compensation of the flow based on the corrected data and the process variable regression model;

[0161] The data processing module is used to filter the calibrated sensor data, remove noise, fuse the flow data from different sensors, implement anomaly detection, eliminate abnormal data points, and generate processed flow data;

[0162] The closed-loop control module is used to adjust the operating parameters of the extrusion equipment in real time through a closed-loop control system based on the processed flow data.

[0163] In this embodiment, the extrusion flow data processing system based on dynamic calibration adopts the steps of the extrusion flow data processing method based on dynamic calibration as described above during execution. Therefore, the operation process of the extrusion flow data processing system based on dynamic calibration is not described in detail in this embodiment. The extrusion flow data processing method and system based on dynamic calibration of the present invention realizes high-precision measurement, stability enhancement, anomaly detection and real-time control of flow data through various technical means such as initial calibration, real-time data acquisition, dynamic calibration, data fusion, anomaly detection and closed-loop control, effectively improves the measurement accuracy, response speed and adaptability of the system, ensures the continuity and consistency of the production process, optimizes resource utilization, and has significant technical advantages and practical value.

[0164] In one embodiment, a computer device is also provided in the embodiments of the present application, comprising at least one processor, and a memory connected with the at least one processor in communication, the memory stores instructions executable by the at least one processor, the instructions are executed by the at least one processor to make the at least one processor execute the steps of the dynamic calibration based extrusion flow data processing method.

[0165] In one embodiment, the present application also provides a computer readable storage medium, which stores computer instructions for making the computer execute the steps of the dynamic calibration based extrusion flow data processing method.

[0166] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be completed by computer program instructions instructing related hardware, and the computer program can be stored in a non-volatile computer readable storage medium. When the computer program is executed, it can include the processes of the above-mentioned embodiments. Any reference to memory, storage, database or other medium used in the embodiments of the present application can include at least one of non-volatile and volatile memory.

[0167] The non-volatile memory can include read-only memory, magnetic tape, floppy disk, flash memory or optical memory, etc. The volatile memory can include random access memory or external cache memory. As an illustration but not limitation, the RAM can be in various forms, such as static random access memory or dynamic random access memory, etc.

[0168] The above only describes the preferred embodiments of the present application and is not intended to limit the present application. Any modification, equivalent replacement and improvement made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method for processing extrusion flow data based on dynamic calibration, characterized in that: The method comprises the following steps: Perform initial calibration of the extrusion system's sensors under standard environmental conditions and establish a baseline relationship between sensor output and actual flow rate; Real-time acquisition of extrusion flow data during the production process, and simultaneous acquisition of environmental parameter data during flow measurement; Based on the real-time collected extrusion flow data and environmental parameter data, the preset process variable regression model is used to dynamically calibrate the sensor data. The dynamic calibration results are used to compensate for the measurement errors caused by the environmental parameter data. Based on the rated flow threshold and the reduced operating condition flow threshold, the calibration flow point is determined. According to the preset dynamic calibration time interval, the valid calibration data is recorded, the standard volume of the extrusion container is obtained, the abnormal change data and the normal change data are screened, the volume correction is performed, and the dynamic compensation of the flow is performed based on the corrected data and the process variable regression model; Filter the calibrated sensor data to remove noise, fuse the flow data from different sensors, perform anomaly detection, remove abnormal data points, and generate processed flow data; According to the processed flow data, the operating parameters of the extrusion equipment are adjusted in real time through the closed-loop control system; Using the preset process variable regression model, the sensor data is dynamically calibrated to collect the flow data output by the sensor of the extrusion system in real time. , and collect environmental parameter data related to flow: temperature ,humidity and electromagnetic interference ; According to the established process variable regression model, the environmental parameters are used as input variables and the flow data output by the sensor is used as the target variable; wherein, the preset process variable regression model is: in, to is the regression coefficient, is the error term; Use historical data to train the regression model and determine the regression coefficients to ; Input the real-time sensor output flow data and environmental parameter data into the dynamic calibration model to calculate the calibrated flow value , the calculation formula of the calibrated flow value is: According to the calibrated flow value Compensate for measurement errors caused by environmental parameters; According to the calibrated flow value The compensation process for the measurement error caused by environmental parameters is: Calculate the flow error before calibration ; Calculate the flow error after calibration ;in, express Standard flow value at the moment; Use calibrated flow rate value As the final measured flow value.

2. The method for processing extrusion flow rate data based on dynamic calibration according to claim 1, characterized in that: The steps for performing an initial calibration of the sensors on an extrusion system under standard environmental conditions include: Before initial calibration, check whether the sensors and measuring equipment are normal, and set the temperature, humidity and interference-free electromagnetic environment according to standard environmental conditions; Select distilled water as the standard liquid, keep the temperature consistent with the standard ambient temperature, use the standard volume calibration device to measure the volume of the extrusion system container, and record the standard volume value; According to the design flow range of the extrusion equipment, at least three calibration points are selected for calibration, wherein the selected calibration points include the calibration points of the lowest flow rate, the middle flow rate, and the highest flow rate; By adjusting the operating parameters of the extruder, set and stabilize at the first calibration flow point; Use a standard flow meter to measure the set flow rate, record the standard flow value, synchronously read the flow data output by the extruder sensor, and record the original reading of the sensor; At each calibration point, the sensor readings and the standard flow values ​​are repeatedly collected, and the error between the sensor readings and the standard flow values ​​is calculated to obtain the error data of each calibration point; Based on the collected sensor readings and actual flow data, a calibration curve is drawn to show the relationship between the sensor output and the actual flow, and a linear regression is used to determine the mathematical model of the sensor output and the actual flow; Fit the data using linear regression to determine the calibration coefficient between the sensor output and the actual flow rate; Under different flow conditions, the flow data is measured again for the flow points that have not been calibrated, and the calibration curve is verified to evaluate whether the measurement error after calibration is within the acceptable range. If it is within the acceptable range, the baseline relationship between the sensor output and the actual flow is determined according to the calibration curve. If it is not within the acceptable range, recalibration is performed.

3. The extrusion flow rate data processing method based on dynamic calibration according to claim 2, characterized in that: When calculating the error between the sensor reading and the standard flow value, at each calibration point, the flow data is collected multiple times by the standard flow meter and sensor. For each data point, when calculating the error, , calculate the sensor reading With standard flow value The error between , the error calculation formula is: All The error data collected is counted to obtain the error data set of each calibration point .

4. The method for processing extrusion flow rate data based on dynamic calibration according to claim 3, wherein: When linear regression is used to determine the mathematical model of sensor output and actual flow, the sensor output readings and the corresponding standard flow values ​​are collected at each calibration point. calibration points, the data set is: ； The sensor output reading As the horizontal axis, the standard flow value As the vertical axis, draw a scatter plot; Use linear regression analysis to fit the scatter plot, and the equation of the fitted line is: in, is the slope, is the intercept.

5. The method for processing extrusion flow rate data based on dynamic calibration according to claim 4, characterized in that: When fitting the data using linear regression to determine the calibration factor between the sensor output and the actual flow rate, the sensor output readings at all calibration points are taken into account. And the corresponding standard flow value Construct a matrix form and perform regression analysis; use the least squares method to calculate the linear regression parameters and , among which, first calculate Average value and Average value ; Then calculate the slope : Then, calculate the intercept : The calibration factor is the calculated slope and intercept , the final calibration formula is: .

6. The method for processing extrusion flow rate data based on dynamic calibration according to claim 1, characterized in that: When filtering the calibrated sensor data, a mean filter is used to take the data mean within a time window to smooth data fluctuations. The formula for calculating the data mean is: in, is the time window size.

7. The method for processing extrusion flow rate data based on dynamic calibration according to claim 1, characterized in that: When fusing traffic data from different sensors, the data from different sensors are aligned in time and synchronized using timestamps. The data from different sensors are then weighted and fused. The calculation formula for weighted fusion is: Where, It is The flow data of each sensor, is the corresponding weight, satisfy: 。 8. An extrusion flow data processing system based on dynamic calibration, characterized in that: The method for processing extrusion flow rate data based on dynamic calibration according to any one of claims 1 to 7 is used, wherein the extrusion flow rate data processing system based on dynamic calibration comprises: A sensor calibration module is used to perform initial calibration of the extrusion system's sensors under standard environmental conditions and establish a baseline relationship between the sensor output and the actual flow rate; The sensor acquisition module is used to collect and obtain the extrusion flow data during the production process in real time, and simultaneously collect the environmental parameter data during flow measurement; The dynamic calibration module is used to dynamically calibrate the sensor data based on the real-time collected extrusion flow data and environmental parameter data using a preset process variable regression model, and use the dynamic calibration results to compensate for the measurement error caused by the environmental parameter data; The calibration flow point determination module is used to determine the calibration flow point based on the rated section flow threshold and the reduced operating condition section flow threshold, record the valid calibration data according to the preset dynamic calibration time interval, obtain the standard volume of the extrusion container, screen the abnormal change data and the normal change data, perform volume correction, and perform dynamic compensation of the flow based on the corrected data and the process variable regression model; The data processing module is used to filter the calibrated sensor data, remove noise, fuse the flow data from different sensors, implement anomaly detection, eliminate abnormal data points, and generate processed flow data; Closed-loop control module, used to adjust the operating parameters of the extrusion equipment in real time through a closed-loop control system based on the processed flow data; Using the preset process variable regression model, the sensor data is dynamically calibrated to collect the flow data output by the sensor of the extrusion system in real time. , and collect environmental parameter data related to flow: temperature ,humidity and electromagnetic interference ; According to the established process variable regression model, the environmental parameters are used as input variables and the flow data output by the sensor is used as the target variable; wherein, the preset process variable regression model is: in, to is the regression coefficient, is the error term; Use historical data to train the regression model and determine the regression coefficients to ; Input the real-time sensor output flow data and environmental parameter data into the dynamic calibration model to calculate the calibrated flow value , the calculation formula of the calibrated flow value is: According to the calibrated flow value Compensate for measurement errors caused by environmental parameters; According to the calibrated flow value The compensation process for the measurement error caused by environmental parameters is: Calculate the flow error before calibration ; Calculate the flow error after calibration ;in, express Standard flow value at the moment; Use calibrated flow rate value As the final measured flow value.

Images