Feeding control method for plastic product production

Abstract

The invention relates to the technical field of feeding control methods, and discloses a feeding control method for plastic product production, which is characterized by comprising the following steps: S1, establishing a data acquisition system: monitoring various raw materials in real time by using a sensor, and sending data to a central processing unit; s2, data preprocessing: carrying out denoising processing on the collected data to eliminate environmental interference; an algorithm: Dpre = Draw-mean (Dnoise) is used, Dpre is the preprocessed data, Draw is the original data, and mean (Dnoise) is the average value of the noise data. According to the method, through real-time monitoring, dynamic adjustment and an optimization algorithm, the utilization rate of raw materials and the consistency of products are greatly improved, meanwhile, the uncertainty caused by human factors can be remarkably reduced, and the automation level of the whole production process is improved. In addition, through a closed-loop feedback mechanism, deviation can be corrected in time, and therefore it is guaranteed that the product quality reaches the expected standard. Resource waste is reduced, and enterprise competitiveness can be improved.

Description

Technical Field

[0001] The present invention relates to the field of feeding control methods, and in particular to a feeding control method for producing plastic products. Background Art

[0002] Plastic products are widely used in daily life and industrial production, covering packaging, automotive parts, electronic products and other fields. The production process usually involves the supply control of raw materials, and the stability and accuracy of the feeding system directly affect the quality and production efficiency of plastic products. At present, there are several major problems in the feeding control process of plastic products: Uneven material flow: In actual production, due to differences in material properties and equipment failures, uneven material feeding can affect the molding process.

[0003] Insufficient metering accuracy: Existing metering systems often cannot achieve high-precision real-time monitoring, resulting in waste of raw materials or substandard quality of finished products.

[0004] Lack of feedback mechanism: When multiple materials are mixed, there is a lack of an effective feedback mechanism to adjust the supply ratio of each material, resulting in large fluctuations in the performance of the final product.

[0005] In order to solve the above problems, this application proposes a feeding control method for plastic product production. Summary of the invention

[0006] 1. Purpose of the invention In order to solve the technical problems existing in the background technology, the present invention proposes a feeding control method for plastic product production. The present invention greatly improves the utilization rate of raw materials and product consistency through real-time monitoring, dynamic adjustment and optimization algorithm. At the same time, the method can significantly reduce the uncertainty caused by human factors and improve the automation level of the entire production process. In addition, through the closed-loop feedback mechanism, it is helpful to correct deviations in time, so as to ensure that the product quality meets the expected standards. Reducing resource waste can also enhance the competitiveness of enterprises.

[0007] (II) Technical solution To solve the above problems, the present invention provides a feeding control method for producing plastic products, comprising the following steps: S1. Establish data collection system Use sensors (such as weighing sensors, flow sensors) to monitor various raw materials in real time and send the data to the central processing unit; S2. Data preprocessing De-noise the collected data to eliminate environmental interference. Algorithm used: D pre =D raw -mean(D noise) Among them, D pre is the preprocessed data, D raw is the original data, mean (D noise ) is the average value of noise data; S3. Establish mathematical model A linear regression model is established based on the required ratio to predict the required amount of each raw material: Y=a1X1+a2X2+…+a n X n +b Where Y is the target variable (such as product characteristics), Xi is the input variable (different types of raw materials), a i is the regression coefficient, b is the intercept; S4. Implement dynamic adjustment According to the real-time feedback results, the supply rate of various materials is adjusted through the PID control algorithm: Where u(t) is the control output (supply rate), e(t) is the error value (the difference between the set value and the actual value), Kp, Ki, Kd are the proportional, integral and differential gains respectively; S5. When mixing multiple substances, perform optimization calculations based on expected performance indicators. Use genetic algorithms to optimize the formula: Initial population generation Fitness function evaluation Among them, F(x) is the fitness function with a total weight of 1; f i (x) is the function of each performance index; S6. Implement closed-loop control Compare the actual output with the set target, and re-enter the PID control loop through feedback adjustment to achieve closed-loop control; S7. Recording and Analysis Record the data of each production in real time, including raw material usage, production speed and finished product quality, and conduct statistical analysis to identify potential problems; S8. Regularly review supply chain management and production processes, formulate improvement measures for problems found, and continuously improve overall efficiency.

[0008] Preferably, S1 specifically includes: Select sensor: Use load cells (such as electronic scales) to monitor the weight of raw materials; Use flow sensors (such as electromagnetic flow meters or ultrasonic flow meters) to monitor the flow rate of liquid raw materials; Build a data transmission network: Connect all sensors to the central processing unit (CPU) using industry standard communication protocols such as Modbus, CAN, etc.

[0009] Software Development: Develop data acquisition software to display the status of various raw materials in real time and store them in the database for subsequent analysis.

[0010] Preferably, S2 specifically includes: De-noising algorithm implementation: The real-time collected data is filtered, for example, using a Kalman filter or a mean filter.

[0011] The specific formula is as follows: Where α is the smoothing factor (0 < α < 1), D previous , is the data of the previous moment; Outlier Detection: Outliers were detected and removed using the Z-score or IQR method to ensure data quality for subsequent analysis.

[0012] Preferably, S3 specifically includes: Linear regression model construction: Collect historical production data, including the relationship between the amount of various materials and the characteristics of the final product, and use the least squares method to calculate the regression coefficient: ; Model validation and adjustment: Use cross-validation to assess model accuracy and adjust variable selection and model parameters based on the results.

[0013] Preferably, S4 specifically includes: PID control algorithm implementation: Write a PID control program in a PLC or embedded system to perform feedback control by setting the error between the target supply rate and the actual supply rate; Gain Adjustment: Determine the appropriate K through experiments based on the production environment and equipment response characteristics. p ,K i ,K d , to achieve the best control effect.

[0014] Preferably, S5 specifically includes: Genetic algorithm design process: Initialize the population to generate different recipe combinations; Fitness function definition: Define the fitness function to evaluate the performance of each formula combination, which can include multiple indicators, such as the weighted sum of performance indicators such as strength and toughness; Fitness function: After each iteration, excellent individuals are selected according to fitness for crossover and mutation operations.

[0015] Preferably, S6 specifically includes: Feedback mechanism design: The output product characteristics are monitored in real time and compared with the set targets. If there is a deviation, the supply rate is adjusted again through PID control to achieve closed-loop control.

[0016] Preferably, S7 specifically includes: Data recording system construction: Establish a database to archive key parameters of each production process (such as raw material usage, production time, finished product quality, etc.); Application of statistical analysis tools: Use statistical software (such as R, Python pandas library, etc.) to analyze trends in historical data, identify potential problems and make suggestions for improvement.

[0017] Preferably, S8 specifically includes: Regular review plan development: Develop a quarterly or annual review plan to comprehensively evaluate the collected data and feedback results and summarize the lessons learned.

[0018] Improvement measures implementation tracking For the problems found, formulate corresponding improvement plans and assign responsible persons to track the implementation. The PDCA cycle management model can be used to continuously optimize the production process.

[0019] The above technical solution of the present invention has the following beneficial technical effects: The present invention relies on data collection and intelligent algorithms to analyze and process real-time data to achieve dynamic adjustment in the raw material supply process. This process combines automation control theories, such as PID control and genetic algorithms, which not only enables the supply system to have self-learning capabilities, but also can flexibly adjust the formula according to changes in market demand. On this basis, this solution constructs a complete information feedback mechanism to achieve integrated management from data collection to decision-making execution, providing strong support for the plastic products manufacturing industry. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 The present invention is a flow chart of a feeding control method for plastic product production proposed by the present invention. DETAILED DESCRIPTION

[0021] In order to make the purpose, technical scheme and advantages of the present invention clearer, the present invention is further described in detail below in conjunction with specific embodiments and with reference to the accompanying drawings. It should be understood that these descriptions are only exemplary and are not intended to limit the scope of the present invention. In addition, in the following description, the description of well-known structures and technologies is omitted to avoid unnecessary confusion of the concept of the present invention.

[0022] like Figure 1 As shown, a feeding control method for plastic product production proposed by the present invention comprises the following steps: S1. Establish data collection system Use sensors (such as weighing sensors, flow sensors) to monitor various raw materials in real time and send the data to the central processing unit; Specifically include: Select sensor: Use load cells (such as electronic scales) to monitor the weight of raw materials; Use flow sensors (such as electromagnetic flow meters or ultrasonic flow meters) to monitor the flow rate of liquid raw materials; Build a data transmission network: Connect all sensors to the central processing unit (CPU) using industry standard communication protocols such as Modbus, CAN, etc.

[0023] Software Development: Develop data acquisition software to display the status of various raw materials in real time and store them in the database for subsequent analysis.

[0024] S2. Data preprocessing De-noise the collected data to eliminate environmental interference. Algorithm used: D pre =D raw -mean(D noise ) Among them, D pre is the preprocessed data, D raw is the original data, mean (D noise ) is the average value of noise data; Specifically include: De-noising algorithm implementation: The real-time collected data is filtered, for example, using a Kalman filter or a mean filter.

[0025] The specific formula is as follows: Where α is the smoothing factor (0 < α < 1), D previous , is the data of the previous moment; Outlier Detection: Outliers were detected and removed using the Z-score or IQR method to ensure data quality for subsequent analysis.

[0026] S3. Establish mathematical model A linear regression model is established based on the required ratio to predict the required amount of each raw material: Y=a1X1+a2X2+…+a n Xn +b Where Y is the target variable (such as product characteristics), Xi is the input variable (different types of raw materials), a i is the regression coefficient, b is the intercept; Specifically include: Linear regression model construction: Collect historical production data, including the relationship between the amount of various materials and the characteristics of the final product, and use the least squares method to calculate the regression coefficient: ; Model validation and adjustment: Use cross-validation to assess model accuracy and adjust variable selection and model parameters based on the results.

[0027] S4. Implement dynamic adjustment According to the real-time feedback results, the supply rate of various materials is adjusted through the PID control algorithm: Where u(t) is the control output (supply rate), e(t) is the error value (the difference between the set value and the actual value), Kp, Ki, Kd are the proportional, integral and differential gains respectively; Specifically, S4 includes: PID control algorithm implementation: Write a PID control program in a PLC or embedded system to perform feedback control by setting the error between the target supply rate and the actual supply rate; Gain Adjustment: Determine the appropriate K through experiments based on the production environment and equipment response characteristics. p ,K i ,K d , to achieve the best control effect.

[0028] S5. When mixing multiple substances, perform optimization calculations based on expected performance indicators. Use genetic algorithms to optimize the formula: Initial population generation Fitness function evaluation Among them, F(x) is the fitness function with a total weight of 1; f i (x) is the function of each performance index; Specifically include: Genetic algorithm design process: Initialize the population to generate different recipe combinations; Fitness function definition: Define the fitness function to evaluate the performance of each formula combination, which can include multiple indicators, such as the weighted sum of performance indicators such as strength and toughness; Fitness function: After each iteration, excellent individuals are selected according to fitness for crossover and mutation operations.

[0029] S6. Implement closed-loop control Compare the actual output with the set target, and re-enter the PID control loop through feedback adjustment to achieve closed-loop control; Specifically include: Feedback mechanism design: The output product characteristics are monitored in real time and compared with the set targets. If there is a deviation, the supply rate is adjusted again through PID control to achieve closed-loop control.

[0030] S7. Recording and Analysis Record the data of each production in real time, including raw material usage, production speed and finished product quality, and conduct statistical analysis to identify potential problems; Specifically include: Data recording system construction: Establish a database to archive key parameters of each production process (such as raw material usage, production time, finished product quality, etc.); Application of statistical analysis tools: Use statistical software (such as R, Python pandas library, etc.) to analyze trends in historical data, identify potential problems and make suggestions for improvement.

[0031] S8. Regularly review supply chain management and production processes, formulate improvement measures for problems found, and continuously improve overall efficiency.

[0032] Specifically include: Regular review plan development: Develop a quarterly or annual review plan to comprehensively evaluate the collected data and feedback results and summarize the lessons learned.

[0033] Improvement measures implementation tracking For the problems found, formulate corresponding improvement plans and assign responsible persons to track the implementation. The PDCA cycle management model can be used to continuously optimize the production process.

[0034] It should be understood that the above specific embodiments of the present invention are only used to illustrate or explain the principles of the present invention, and do not constitute a limitation of the present invention. Therefore, any modifications, equivalent substitutions, improvements, etc. made without departing from the spirit and scope of the present invention should be included in the protection scope of the present invention. In addition, the appended claims of the present invention are intended to cover all changes and modifications that fall within the scope and boundaries of the appended claims, or the equivalent forms of such scope and boundaries.

Claims

1. A feeding control method for plastic product production, characterized in that: The following steps are involved: S1. Establish data collection system Use sensors to monitor various raw materials in real time and send data to the central processing unit; S2. Data preprocessing De-noise the collected data to eliminate environmental interference; Using algorithm: D pre =D raw -mean(D noise ) where D pre is the preprocessed data, D raw is the original data, mean (D noise ) is the average value of noise data; S3. Establish mathematical model A linear regression model is established based on the required ratio to predict the required amount of each raw material: Y=a1X1+a2X2+…+a n X n +b, where Y is the target variable, X i is the input variable, a i is the regression coefficient, b is the intercept; S4. Implement dynamic adjustment According to the real-time feedback results, the supply rate of various materials is adjusted through the PID control algorithm: Among them, u(t) is the control output, e(t) is the error value, Kp, Ki, Kd are proportional, integral and differential gains respectively; S5. When multiple substances are mixed, optimization calculations are performed based on the expected performance indicators; Using genetic algorithm to optimize the recipe: Initial population generation Fitness function evaluation Among them, F(x) is the fitness function with a total weight of 1; f i (x) is the function of each performance index; S6. Implement closed-loop control Compare the actual output with the set target, and re-enter the PID control loop through feedback adjustment to achieve closed-loop control; S7. Recording and Analysis Record the data of each production in real time, including raw material usage, production speed and finished product quality, and conduct statistical analysis to identify potential problems; S8. Regularly review supply chain management and production processes, formulate improvement measures for problems found, and continuously improve overall efficiency.

2. A feeding control method for plastic product production according to claim 1, characterized in that: S1 specifically includes: Select sensor: Use load cells to monitor the weight of raw materials; Use flow sensors to monitor the flow rate of liquid raw materials; Build a data transmission network: Connect all sensors to the central processing unit; Software Development: Develop data acquisition software to display the status of various raw materials in real time and store them in the database for subsequent analysis.

3. A feeding control method for plastic product production according to claim 2, characterized in that: Specifically, S2 includes: De-noising algorithm implementation: Filter the data collected in real time; The specific formula is as follows: Among them, α is the smoothing factor (0 < α < 1), D previous , is the data of the previous moment; Outlier Detection: Use Z-score or IQR method to detect and remove outliers.

4. A feeding control method for plastic product production according to claim 1, characterized in that: Specifically in S3: Linear regression model construction: Collect historical production data, including the relationship between the amount of various materials and the characteristics of the final product, and use the least squares method to calculate the regression coefficient: ； Model validation and adjustment: Use cross-validation to assess model accuracy and adjust variable selection and model parameters based on the results.

5. A feeding control method for plastic product production according to claim 4, characterized in that: Specifically, S4 includes: PID control algorithm implementation: Write a PID control program in a PLC or embedded system to perform feedback control by setting the error between the target supply rate and the actual supply rate; Gain Adjustment: Determine the appropriate K through experiments based on the production environment and equipment response characteristics. p ,K i ,K d .

6. A feeding control method for plastic product production according to claim 1, characterized in that: S5 specifically includes: Genetic algorithm design process: Initialize the population to generate different recipe combinations; Fitness function definition: Define a fitness function to evaluate the performance of each recipe combination, which can include multiple indicators; Fitness function: After each iteration, excellent individuals are selected according to fitness for crossover and mutation operations.

7. A feeding control method for plastic product production according to claim 6, characterized in that , specifically including in S6: Feedback mechanism design: The output product characteristics are monitored in real time and compared with the set targets. If there is a deviation, the supply rate is adjusted again through PID control to achieve closed-loop control.

8. A feeding control method for plastic product production according to claim 1, characterized in that: Specifically in S7: Data recording system construction: Establish a database to archive the key parameters of each production process; Application of statistical analysis tools: Use statistical software to analyze trends in historical data, identify potential problems, and make recommendations for improvements.

9. A feeding control method for plastic product production according to claim 1, characterized in that: Specifically included in S8: Regular review plan development: Develop a quarterly or annual review plan to comprehensively evaluate the collected data and feedback results and summarize the lessons learned; Follow-up on the implementation of improvement measures: Develop corresponding improvement plans based on the problems found, and assign responsible persons to follow up on the implementation.

Images