A method and system for controlling injection speed of a die-casting machine based on data analysis

Abstract

The present invention relates to the field of metal processing technology, and in particular to a method and system for controlling the injection speed of a die-casting machine based on data analysis, comprising the following steps: S1: deploying a multifunctional sensor network in a die-casting machine for real-time monitoring of key parameters; S2: calculating the optimal fluidity temperature of molten metal and predicting the cooling rate of the metal under current environmental conditions; S3: adjusting the heating system of the die-casting machine through a preset temperature control algorithm; S4: controlling the speed during the injection process to adapt to the actual flow characteristics of the metal; S5: identifying the specific impact of environmental factors on the injection process, and automatically adjusting the injection parameters to compensate for the impact; S6: finally adjusting the injection speed of the die-casting machine according to the injection parameters adjusted by S5. The present invention significantly improves the consistency and quality of die-cast products by real-time monitoring and dynamic adjustment of the injection speed and the temperature of the molten metal, while optimizing production efficiency and reducing energy consumption.

Description

Technical Field

[0001] The present invention relates to the technical field of metal processing, and in particular to a method and system for controlling the injection speed of a die-casting machine based on data analysis. Background Art

[0002] Die casting is an efficient metal forming process that is widely used in the manufacturing industry to produce metal parts with complex shapes. In the die casting process, the injection speed and the temperature of the molten metal are two key parameters that directly affect the quality and forming effect of the product. Traditional die casting machines usually rely on the operator's experience to adjust the injection speed and temperature. This method is not only inefficient, but also easily affected by environmental factors and changes in metal properties, resulting in unstable product quality. In addition, traditional control systems lack real-time data analysis and intelligent adjustment capabilities, and cannot effectively respond to dynamic changes in the production process.

[0003] In the existing technology, there are many challenges in the injection speed control and molten metal temperature management of the die-casting machine. Due to changes in ambient temperature and humidity, the fluidity and cooling rate of the metal will change significantly, which puts higher requirements on the precise control of the injection speed. However, traditional methods make it difficult to monitor and adjust these key parameters in real time, resulting in increased uncertainty in the production process and a high product defect rate.

[0004] Therefore, it is particularly necessary to develop a die-casting machine injection speed control method and system based on data analysis to achieve precise control of the injection speed and metal temperature and adapt to different production environments and conditions. Summary of the invention

[0005] Based on the above objectives, the present invention provides a method and system for controlling the injection speed of a die-casting machine based on data analysis.

[0006] A method for controlling the injection speed of a die-casting machine based on data analysis comprises the following steps:

[0007] S1: Deploy a multifunctional sensor network in the die casting machine to monitor key parameters in real time, including injection speed, molten metal temperature, and temperature and humidity of the die casting environment;

[0008] S2: Using the data collected by S1, the theoretical fluidity temperature of the molten metal is calculated through a preset thermodynamic model, and the cooling rate of the metal under the current environmental conditions is predicted, providing a theoretical basis for temperature control;

[0009] S3: Based on the output of S2, the heating system of the die-casting machine is adjusted through a preset temperature control algorithm to ensure that the molten metal reaches the theoretical fluidity temperature before being injected into the mold;

[0010] S4: Compare the real-time monitored molten metal temperature with the theoretical fluidity temperature in S3, and use a dynamic adjustment algorithm based on rheological principles to control the speed during the injection process to adapt to the actual flow characteristics of the metal;

[0011] S5: Based on real-time injection data and environmental data, through a preset data processing framework, identify the specific impact of environmental factors on the injection process and automatically adjust injection parameters to compensate for the impact;

[0012] S6: According to the injection parameters adjusted in S5, the injection speed of the die-casting machine is finally adjusted to achieve the best die-casting quality and efficiency.

[0013] Furthermore, the S1 specifically includes:

[0014] S11: Deploy a multifunctional sensor network, including speed sensors, thermocouple sensors, and humidity sensors. The speed sensor is used to measure the injection speed, the thermocouple sensor is used to determine the temperature of the molten metal, and the humidity sensor is used to monitor the humidity in the die casting environment.

[0015] S12: Install sensors at predetermined positions of the die-casting machine. The speed sensor is installed at the nozzle outlet to measure the metal outflow speed. The thermocouple sensor directly contacts the molten metal to ensure the accuracy of temperature measurement. The humidity sensor is deployed in the environment of the die-casting machine to monitor the humidity changes of the environment in real time.

[0016] S13: connecting each sensor to a central data processing unit, specifically using a wired or wireless network to ensure real-time data transmission, wherein the wireless network uses Wi-Fi or Bluetooth technology;

[0017] S14: Preprocess the collected data and use data processing algorithms for preliminary screening and noise reduction. Specifically, use moving average or low-pass filter to smooth the data, improve data quality, and provide input for subsequent in-depth analysis.

[0018] Furthermore, the S2 specifically includes:

[0019] S21: Acquire the real-time data collected by the sensor network in S1, including the parameters of molten metal temperature, temperature and humidity of the die-casting environment, and provide basic data for subsequent calculations;

[0020] S22: inputting the data obtained in S21 into a preset thermodynamic model, which calculates the theoretical fluidity temperature of the molten metal under current environmental conditions based on the physical properties of the metal and the principle of heat conduction;

[0021] S23: Predict the cooling rate of molten metal by combining the heat conduction equation in the thermodynamic model with the ambient temperature and humidity data;

[0022] S24: The calculated theoretical fluidity temperature and cooling rate data are transmitted to the temperature control system to ensure that the heating system can adjust the temperature of the molten metal according to the real-time data.

[0023] Furthermore, the S22 specifically includes:

[0024] S221: First determine the basic physical properties of metals, including density ρ, specific heat capacity c p and thermal conductivity λ; where ρ represents the mass of metal per unit volume, c p It indicates the ability of metal to increase unit temperature after absorbing unit heat, and λ indicates the ability of metal to conduct heat;

[0025] S222: Then collect environmental condition data, including ambient temperature T env and humidity RH, where T env Indicates the current ambient temperature, and RH indicates the current ambient humidity;

[0026] S223: Using the improved heat balance equation to calculate the theoretical fluidity temperature T of the molten metal opt , which takes into account the heat conduction, convection and radiation loss factors of the metal for calculation. The specific formula is:

[0027] Among them, Q in It represents the total heat provided by the heating system to the metal in joules, Q out represents the total heat loss due to environmental conditions and radiation from the metal surface in joules, m represents the mass of the molten metal in kilograms, T init It represents the initial temperature of the molten metal in degrees Celsius;

[0028] S224: To calculate Q more accurately out , the ambient temperature and humidity adjustment coefficient α will be introduced T and α RH , used to adjust the heat loss calculation, the specific formula is:

[0029] Q out =α T ·f(T env )+α RH g(RH) λ A (T metal -T env ), where α T is the ambient temperature adjustment coefficient, dimensionless, indicating the influence of ambient temperature on heat loss; α RH is the environmental humidity adjustment coefficient, dimensionless, indicating the degree of influence of environmental humidity on heat loss; f(T env) is the effect of ambient temperature on heat loss; g(RH) is the effect of ambient humidity on heat loss; λ is the thermal conductivity of metal, in watts per meter per Kelvin; A is the surface area of ​​metal, in square meters; T metal Indicates the current temperature of the metal in degrees Celsius;

[0030] S225: T calculated in S223 opt This will be used as the target temperature setting for the die casting machine's heating system during the shot process.

[0031] Furthermore, the S23 specifically includes:

[0032] S231: Obtain current values ​​of ambient temperature and humidity from the real-time environmental data collected by S1;

[0033] S232: Apply the heat conduction equation to calculate the heat exchange between the molten metal surface and the environment. The equation is based on Newton's law of cooling and the formula is: Q = h·A·(T metal -T env ), where Q represents the amount of heat transferred from the metal surface to the environment per unit time; h represents the heat exchange coefficient in watts per square meter per degree Celsius; A represents the metal surface area in square meters; T metal Indicates the current temperature of the metal in degrees Celsius; T env Indicates the ambient temperature in degrees Celsius;

[0034] S233: Calculate cooling rate That is, the rate of change of metal temperature with time, which is solved by the energy conservation equation, the formula is: Where m represents the metal mass in kilograms; c p It represents the specific heat capacity of metals in joules per kilogram per degree Celsius;

[0035] S234: Based on the effect of ambient humidity on the cooling rate, adjust the heat exchange coefficient h. In a high humidity environment, due to the increase in the thermal conductivity of the air, h will increase accordingly, thereby accelerating the heat exchange. The formula is: h adjusted =h·(1+β·RH), where β represents the humidity adjustment coefficient, which is used to adjust the heat exchange coefficient to adapt to environments with different humidity;

[0036] S235: Use the adjusted heat exchange coefficient h adjusted Recalculate Q and To obtain more accurate cooling rate predictions.

[0037] Furthermore, the S3 specifically includes:

[0038] S31: Receive the output from S2, including the calculated theoretical fluidity temperature T of the molten metal opt and the predicted cooling rate

[0039] S32: Set the target temperature of the heating system, the target temperature T target According to the theoretical fluidity temperature T opt The setting is based on the actual cooling conditions of the metal in the mold to ensure that the metal maintains optimal fluidity during the injection molding process. The calculation formula is: T target =T opt +ΔT, where ΔT is the temperature difference adjusted for the predicted cooling rate;

[0040] S33: Apply a temperature control algorithm to adjust the heating system. The temperature control algorithm specifically uses a PID control strategy to adjust the temperature according to the target temperature T target and the actual molten metal temperature T metal The difference between the two automatically adjusts the heating power. The expression of the PID control algorithm is: Where u(t) is the control input of the heating system, i.e., the heating power; K p ,K i ,K d are the proportional, integral and differential coefficients of the PID controller respectively; e(t) = T target -T metal , that is, the deviation between the target temperature and the actual temperature; the heating system is adjusted according to the heating power calculated by the PID algorithm to ensure that the output of the heating system can quickly and accurately reach and maintain the target temperature.

[0041] Furthermore, the S4 specifically includes:

[0042] S41: First obtain the molten metal temperature T monitored in real time real , and obtain the theoretical fluidity temperature T calculated in S2 opt ;

[0043] S42: Calculate the actual temperature T real and the theoretical fluidity temperature T opt The deviation between T ;

[0044] S43: Based on rheological principles, according to the temperature deviation e T Adjust the injection speed. The following relationship describes the temperature dependence of metal viscosity η: Where η0 is the viscosity of the molten metal at the reference temperature; E is the activation energy of the viscosity; R is the gas constant; T real is the real-time temperature;

[0045] S44: According to the actual viscosity η of the metal, the injection speed v is adjusted by applying a dynamic adjustment algorithm to ensure optimal metal fluidity. The formula of the adjustment algorithm is: Among them, v0 is the reference injection speed; η0 and η are the reference viscosity and real-time viscosity respectively; based on the dynamic adjustment algorithm, the injection speed is adjusted in real time through the control system of the die-casting machine to adapt it to the actual flow characteristics of the metal, ensuring that the metal can be injected at the optimal speed under different temperature conditions.

[0046] Furthermore, the S5 specifically includes:

[0047] S51: acquiring real-time injection data and environmental data, wherein the injection data includes injection speed and injection pressure, and the environmental data includes environmental temperature and environmental humidity;

[0048] S52: input the data obtained in S51 into a preset data processing framework, which is based on multivariate regression analysis and machine learning algorithms and is intended to identify and quantify the specific impact of environmental factors on the injection process;

[0049] S53: Perform multivariate regression analysis to establish a relationship model between injection parameters and environmental factors. The specific formula is: P adjusted =β0+β1T env +β2RH+β3v real +∈, where P adjusted represents the adjusted injection pressure; β0, β1, β2, β3 are regression coefficients obtained through historical data training; T env is the ambient temperature; RH is the ambient humidity; v real is the actual injection speed; ∈ is the error term; v real is the current injection speed;

[0050] S54: Use machine learning algorithms to optimize the relationship model to identify nonlinear effects and complex interactions. The machine learning model continuously learns and improves through historical data and real-time data to improve prediction accuracy.

[0051] S55: Based on the optimized model, the adjusted injection parameters, including injection pressure and injection speed, are calculated in real time to compensate for the influence of environmental factors. The specific adjustment formula is:

[0052] v adjusted =v real +Δv;

[0053] Δv=γ1(T env -T ref )+γ2(RH-RH ref ), where v adjustedis the adjusted injection speed; Δv is the speed adjustment amount; γ1, γ2 are the environmental adjustment coefficients; T ref and RH ref They are the reference ambient temperature and reference humidity respectively.

[0054] Furthermore, the S6 specifically includes:

[0055] S61: Obtain the adjusted injection parameters from S5, including the adjusted injection speed v adjusted and injection pressure P adjusted ;

[0056] S62: The adjusted injection speed v is set by the control system of the die casting machine. adjusted and injection pressure P adjusted Input to the control unit of the die casting machine;

[0057] S63: Start the injection speed adjustment module in the control unit to adjust the speed during the injection process in real time. During the process, the current injection speed is continuously monitored and compared with the adjusted injection speed v adjusted Compare; if the current injection speed is lower than the adjusted injection speed, the control unit increases the injection speed; if the current injection speed is higher than the adjusted injection speed, the control unit reduces the injection speed;

[0058] S64: After the injection process is completed, the finished product quality data is analyzed; if the finished product quality meets the standard, the current injection speed and pressure parameters are saved as a reference for future production; if the finished product quality does not meet the standard, the parameter settings are adjusted and the data is recorded.

[0059] A die-casting machine injection speed control system based on data analysis, used to implement the above-mentioned die-casting machine injection speed control method based on data analysis, includes the following modules:

[0060] Data acquisition module: used to collect real-time data on the die-casting machine’s injection speed, molten metal temperature, injection pressure, and the temperature and humidity of the die-casting environment;

[0061] Data processing module: Based on the data collected by the data acquisition module, the preset thermodynamic model and rheological model are used to analyze the data, calculate the theoretical fluidity temperature of the molten metal and predict the cooling rate of the metal, and adjust the baseline values ​​of the injection speed and pressure according to the environmental data;

[0062] Temperature control module: Based on the theoretical fluidity temperature output by the data processing module, the PID control algorithm is used to adjust the heating power according to the difference between the real-time and theoretical temperatures to maintain the metal temperature at the optimal state;

[0063] Injection speed adjustment module: receives the output of the data processing module and dynamically adjusts the injection speed according to the injection speed adjustment requirements to adapt to the actual flow characteristics of the metal;

[0064] Feedback and optimization module: monitors the entire injection process, collects quality data and injection parameters of finished products in real time, and uses machine learning technology to analyze data in the production process to automatically optimize injection speed and temperature control parameters;

[0065] User interface module: provides an interactive interface through which users can view real-time data, alarm information, and historical analysis results, while allowing manual input of adjustment parameters.

[0066] Beneficial effects of the present invention:

[0067] The present invention monitors the key operating parameters of the die-casting machine, such as injection speed, molten metal temperature, ambient temperature and humidity, in real time by integrating an advanced sensor network. Compared with the traditional method of adjusting parameters relying on operator experience, this comprehensive monitoring method can more accurately control the die-casting conditions, significantly improve product consistency and reduce the incidence of defects.

[0068] The present invention applies thermodynamic models and rheological principles to dynamically adjust the injection speed. By accurately controlling the molten metal temperature and injection speed, it can ensure that the molten metal reaches the optimal fluidity temperature and speed when injected into the mold, which directly affects the molding quality and material utilization rate. This control strategy based on scientific calculation models not only improves product quality, but also provides technical support for the refined management of the die-casting process.

[0069] The present invention continuously learns from real-time operation data through machine learning technology, automatically adjusts injection parameters to adapt to changes in production conditions, and thus optimizes the entire die-casting process. This intelligent optimization not only improves operating efficiency, but also ensures high-quality output under changing production environments, greatly improving the reliability and economic benefits of the production process. Through this method, the die-casting process has been significantly improved, the automation and intelligence of the process have been realized, and the transformation of the die-casting industry to a higher technical level has been facilitated. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0071] Figure 1 Schematic diagram of a method for controlling the injection speed of a die-casting machine according to an embodiment of the present invention;

[0072] Figure 2 Schematic diagram of a die-casting machine injection speed control system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0073] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with specific embodiments.

[0074] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0075] like Figure 1 As shown, a method for controlling the injection speed of a die-casting machine based on data analysis comprises the following steps:

[0076] S1: Deploy a multifunctional sensor network in the die-casting machine to monitor key parameters in real time, including injection speed, molten metal temperature, and temperature and humidity of the die-casting environment, providing basic information for data-driven decision-making;

[0077] S2: Using the data collected by S1, the theoretical fluidity temperature of the molten metal is calculated through a preset thermodynamic model, and the cooling rate of the metal under the current environmental conditions is predicted, providing a theoretical basis for temperature control;

[0078] S3: Based on the output of S2, the heating system of the die-casting machine is adjusted through a preset temperature control algorithm to ensure that the molten metal reaches the theoretical fluidity temperature before being injected into the mold, thereby optimizing the setting of the injection speed;

[0079] S4: Compare the real-time monitored molten metal temperature with the theoretical fluidity temperature in S3, and use a dynamic adjustment algorithm based on rheological principles to control the speed during the injection process to adapt to the actual flow characteristics of the metal;

[0080] S5: Based on real-time injection data and environmental data, through a preset data processing framework, identify the specific impact of environmental factors on the injection process and automatically adjust injection parameters to compensate for the impact;

[0081] S6: According to the injection parameters adjusted in S5, the injection speed of the die-casting machine is finally adjusted to achieve the best die-casting quality and efficiency.

[0082] S1 specifically includes:

[0083] S11: Deploy a multifunctional sensor network, including speed sensors, thermocouple sensors, and humidity sensors. The speed sensor is used to measure the injection speed, the thermocouple sensor is used to determine the temperature of the molten metal, and the humidity sensor is used to monitor the humidity in the die casting environment.

[0084] S12: Sensors are installed at predetermined locations of the die-casting machine. The speed sensor is installed at the nozzle outlet to measure the metal outflow speed. The thermocouple sensor is in direct contact with the molten metal to ensure the accuracy of temperature measurement. The humidity sensor is deployed in the environment of the die-casting machine, especially in the area close to the mold, to monitor the humidity changes in the environment in real time.

[0085] S13: connecting each sensor to a central data processing unit, specifically using a wired or wireless network to ensure real-time data transmission, wherein the wireless network uses Wi-Fi or Bluetooth technology to reduce installation complexity and improve the flexibility of data transmission;

[0086] S14: Preprocess the collected data and use data processing algorithms for preliminary screening and noise reduction. Specifically, use moving average or low-pass filter to smooth the data, improve data quality, and provide input for subsequent in-depth analysis. Through the above detailed sensor deployment and data processing steps, ensure the effectiveness and accuracy of the multifunctional sensor network in the die-casting machine, thereby providing solid data support for the precise control of injection speed and environmental factors.

[0087] S2 specifically includes:

[0088] S21: Acquire the real-time data collected by the sensor network in S1, including the parameters of molten metal temperature, temperature and humidity of the die-casting environment, and provide basic data for subsequent calculations;

[0089] S22: Input the data obtained in S21 into a preset thermodynamic model. The model calculates the theoretical fluidity temperature of the molten metal under the current environmental conditions based on the physical properties of the metal and the principle of heat conduction, so as to ensure that the metal can be injected with optimal fluidity during the actual production process;

[0090] S23: The cooling rate of molten metal is predicted by combining the heat conduction equation in the thermodynamic model with the ambient temperature and humidity data. The model takes into account the heat loss of the metal during the cooling process in the mold and the influence of environmental factors, providing an accurate theoretical basis for temperature control.

[0091] S24: The calculated theoretical fluidity temperature and cooling rate data are transmitted to the temperature control system to ensure that the heating system can adjust the temperature of the molten metal according to the real-time data to keep it within the theoretical fluidity temperature range.

[0092] S22 specifically includes:

[0093] S221: First determine the basic physical properties of metals, including density ρ, specific heat capacity c p and thermal conductivity λ; where ρ represents the mass of metal per unit volume, c p It indicates the ability of metal to increase unit temperature after absorbing unit heat, and λ indicates the ability of metal to conduct heat. These data can be obtained from the standard physical property database or determined experimentally;

[0094] S222: Then collect environmental condition data, including ambient temperature T env and humidity RH, where T env represents the current ambient temperature, and RH represents the current ambient humidity. The above data are provided in real time by the sensor network in step S1;

[0095] S223: Using the improved heat balance equation to calculate the theoretical fluidity temperature T of the molten metal opt , which takes into account the heat conduction, convection and radiation loss factors of the metal for calculation. The specific formula is:

[0096] Among them, Q in It represents the total heat provided by the heating system to the metal in joules, Q out represents the total heat loss due to environmental conditions and radiation from the metal surface in joules, m represents the mass of the molten metal in kilograms, T init It represents the initial temperature of the molten metal in degrees Celsius;

[0097] S224: To calculate Q more accurately out , the ambient temperature and humidity adjustment coefficient α will be introduced T and α RH , this coefficient is obtained through historical data analysis and is used to adjust the heat loss calculation. The specific formula is:

[0098] Q out =α T ·f(T env )+αRH g(RH) λ A (T metal -T env ), where α T is the ambient temperature adjustment coefficient, dimensionless, indicating the influence of ambient temperature on heat loss; α RH is the environmental humidity adjustment coefficient, dimensionless, indicating the degree of influence of environmental humidity on heat loss; f(T env ) is the effect of ambient temperature on heat loss; g(RH) is the effect of ambient humidity on heat loss; λ is the thermal conductivity of metal, in watts per meter per Kelvin; A is the surface area of ​​metal, in square meters; T metal Indicates the current temperature of the metal in degrees Celsius;

[0099] S225: T calculated in S223 opt It will be used as the target temperature setting of the die-casting machine heating system during the injection process to ensure that the molten metal has optimal fluidity and filling performance; through the above-mentioned improved heat balance calculation method, the theoretical fluidity temperature of the molten metal can be determined more accurately to adapt to various environmental changes, thereby optimizing the die-casting process and improving product consistency and quality. At the same time, this method makes temperature control more scientific and precise by comprehensively considering the specific impact of environmental factors on heat loss, which helps to reduce energy consumption and improve production efficiency.

[0100] S23 specifically includes:

[0101] S231: Obtain current values ​​of ambient temperature and humidity from the real-time environmental data collected by S1;

[0102] S232: Apply the heat conduction equation to calculate the heat exchange between the molten metal surface and the environment. The equation is based on Newton's law of cooling and the formula is: Q = h·A·(T metal -T env ), where Q represents the amount of heat transferred from the metal surface to the environment per unit time, in joules per second, or watts (W); h represents the heat exchange coefficient, in watts per square meter per degree Celsius (W / m 2 ℃), which depends on the metal material and surface characteristics; A represents the metal surface area in square meters; T metal Indicates the current temperature of the metal in degrees Celsius; T env Indicates the ambient temperature in degrees Celsius;

[0103] S233: Calculate cooling rate That is, the rate of change of metal temperature with time, which is solved by the energy conservation equation, the formula is: Where m represents the metal mass in kilograms; c pIt represents the specific heat capacity of metals in joules per kilogram per degree Celsius;

[0104] S234: Based on the effect of ambient humidity on the cooling rate, adjust the heat exchange coefficient h. In a high humidity environment, due to the increase in the thermal conductivity of the air, h will increase accordingly, thereby accelerating the heat exchange. The formula is: h adjusted =h·(1+β·RH), where β represents the humidity adjustment coefficient, which is used to adjust the heat exchange coefficient to adapt to environments with different humidity;

[0105] S235: Use the adjusted heat exchange coefficient h adjusted Recalculate Q and To obtain a more accurate prediction of the cooling rate; the above method can accurately calculate and predict the cooling rate of the molten metal, help the die-casting process to better control the metal temperature, and avoid product defects caused by improper cooling. In addition, considering the adjustment of ambient humidity, it can adapt to different production environments and ensure the consistency and reliability of product quality. Through scientific cooling rate management, the production process can be optimized, energy can be saved and waste can be reduced.

[0106] S3 specifically includes:

[0107] S31: Receive the output from S2, including the calculated theoretical fluidity temperature T of the molten metal opt and the predicted cooling rate

[0108] S32: Set the target temperature of the heating system, the target temperature T target According to the theoretical fluidity temperature T opt The setting is based on the actual cooling conditions of the metal in the mold to ensure that the metal maintains optimal fluidity during the injection molding process. The calculation formula is: T target =T opt +ΔT, where ΔT is the temperature difference adjusted according to the predicted cooling rate to compensate for the expected heat loss and ensure metal fluidity;

[0109] S33: Apply a temperature control algorithm to adjust the heating system. The temperature control algorithm specifically uses a PID (proportional-integral-differential) control strategy to adjust the heating system according to the target temperature T target and the actual molten metal temperature T metal The difference between the two automatically adjusts the heating power. The expression of the PID control algorithm is: Where u(t) is the control input of the heating system, i.e., the heating power; K p ,K i ,K d are the proportional, integral and differential coefficients of the PID controller respectively; e(t) = T target -T metal, that is, the deviation between the target temperature and the actual temperature; adjust the heating system according to the heating power calculated by the PID algorithm to ensure that the output of the heating system can quickly and accurately reach and maintain the target temperature; by accurately controlling the heating system of the die-casting machine, ensure that the molten metal can be maintained at the theoretical fluidity temperature during the entire injection process, thereby improving the molding quality and consistency of the product. The use of PID control strategy can achieve precise temperature adjustment, fast response, avoid overheating or insufficient temperature, thereby improving product quality, reducing material waste, and optimizing energy use. This temperature control strategy not only improves production efficiency, but also helps to reduce production costs.

[0110] S4 specifically includes:

[0111] S41: First obtain the molten metal temperature T monitored in real time real , which is provided by the sensor network in step S1, and the theoretical fluidity temperature T calculated in step S2 opt ;

[0112] S42: Calculate the actual temperature T real and the theoretical fluidity temperature T opt The deviation between T , the formula is: e T =T real -T opt ;

[0113] S43: Based on rheological principles, according to the temperature deviation e T Adjust the injection speed. Specifically, the rheological principle shows that the viscosity η of the metal melt is closely related to the temperature. Temperature changes will affect the fluidity of the metal. The following relationship describes the temperature dependence of the metal viscosity η: Where η0 is the viscosity of the molten metal at the reference temperature; E is the activation energy of the viscosity in joules; R is the gas constant in joules per mole per Kelvin; T real is the real-time temperature in Kelvin;

[0114] S44: According to the actual viscosity η of the metal, the injection speed v is adjusted by applying a dynamic adjustment algorithm to ensure optimal metal fluidity. The formula of the adjustment algorithm is: Among them, v0 is the reference injection speed; η0 and η are the reference viscosity and real-time viscosity respectively; based on the dynamic adjustment algorithm, the injection speed is adjusted in real time through the control system of the die-casting machine to adapt it to the actual flow characteristics of the metal, ensuring that the metal can be injected at the optimal speed under different temperature conditions to achieve the ideal molding effect; by comparing the real-time monitored molten metal temperature with the theoretical fluidity temperature, and using the dynamic adjustment algorithm based on rheological principles, the injection speed is accurately controlled so that the metal can be die-cast under optimal fluidity, which not only improves the consistency of product quality and molding accuracy, but also effectively reduces the defect rate caused by temperature fluctuations.

[0115] S5 specifically includes:

[0116] S51: acquiring real-time injection data and environmental data, wherein the injection data includes injection speed and injection pressure, and the environmental data includes environmental temperature and environmental humidity;

[0117] S52: input the data obtained in S51 into a preset data processing framework, which is based on multivariate regression analysis and machine learning algorithms and is intended to identify and quantify the specific impact of environmental factors on the injection process;

[0118] S53: Perform multivariate regression analysis to establish a relationship model between injection parameters and environmental factors. The specific formula is: P adjusted =β0+β1T env +β2RH+β3v real +∈, where P adjusted represents the adjusted injection pressure; β0, β1, β2, β3 are regression coefficients obtained through historical data training; T env is the ambient temperature; RH is the ambient humidity; v real is the actual injection speed; ∈ is the error term; v real is the current injection speed;

[0119] S54: Use machine learning algorithms (such as random forest regression or support vector regression) to optimize the relationship model to identify nonlinear effects and complex interactions. The machine learning model continuously learns and improves through historical data and real-time data to improve prediction accuracy.

[0120] S55: Based on the optimized model, the adjusted injection parameters, including injection pressure and injection speed, are calculated in real time to compensate for the influence of environmental factors. The specific adjustment formula is:

[0121] v adjusted =v real +Δv;

[0122] Δv=γ1(T env -T ref)+γ2(RH-RH ref ), where v adjusted is the adjusted injection speed; Δv is the speed adjustment amount; γ1, γ2 are the environmental adjustment coefficients; T ref and RH ref They are reference ambient temperature and reference humidity respectively; through the above steps and methods, using real-time data and a preset data processing framework, the impact of environmental factors on the injection process can be accurately identified, and the injection parameters can be automatically adjusted for compensation, which can ensure the stability and consistency of the die-casting process under different environmental conditions, thereby improving product quality, reducing defect rates, optimizing production efficiency and reducing production costs.

[0123] S6 specifically includes:

[0124] S61: Obtain the adjusted injection parameters from S5, including the adjusted injection speed v adjusted and injection pressure P adjusted ;

[0125] S62: The adjusted injection speed v is set by the control system of the die casting machine. adjusted and injection pressure P adjusted Input to the control unit of the die casting machine; the control unit receives these parameters and prepares to make corresponding adjustments;

[0126] S63: Start the injection speed adjustment module in the control unit to adjust the speed during the injection process in real time. During the process, the current injection speed is continuously monitored and compared with the adjusted injection speed v adjusted Compare; if the current injection speed is lower than the adjusted injection speed, the control unit increases the injection speed; if the current injection speed is higher than the adjusted injection speed, the control unit reduces the injection speed. The adjustment process adopts the incremental adjustment method to ensure that the speed changes smoothly and accurately;

[0127] S64: After the injection process is completed, the quality data of the finished product is analyzed; if the quality of the finished product meets the standard, the current injection speed and pressure parameters are saved as a reference for future production; if the quality of the finished product does not meet the standard, the parameter settings are adjusted and the data is recorded to optimize the subsequent production process; through the above steps, the injection speed of the die-casting machine is accurately controlled using the adjusted injection parameters to ensure that the molten metal is injected under the best fluidity, thereby improving the molding quality and consistency of the product.

[0128] like Figure 2 As shown, a die-casting machine injection speed control system based on data analysis is used to implement the above-mentioned die-casting machine injection speed control method based on data analysis, including the following modules:

[0129] Data acquisition module: used to collect real-time data on the die-casting machine’s injection speed, molten metal temperature, injection pressure, and the temperature and humidity of the die-casting environment;

[0130] Data processing module: Based on the data collected by the data acquisition module, the preset thermodynamic model and rheological model are used to analyze the data, calculate the theoretical fluidity temperature of the molten metal and predict the cooling rate of the metal, and adjust the baseline values ​​of the injection speed and pressure according to the environmental data;

[0131] Temperature control module: Based on the theoretical fluidity temperature output by the data processing module, the PID control algorithm is used to adjust the heating power according to the difference between the real-time and theoretical temperatures to maintain the metal temperature at the optimal state;

[0132] Injection speed adjustment module: receives the output of the data processing module and dynamically adjusts the injection speed according to the injection speed adjustment requirements to adapt to the actual flow characteristics of the metal;

[0133] Feedback and optimization module: monitors the entire injection process, collects quality data and injection parameters of finished products in real time, and uses machine learning technology to analyze data in the production process to automatically optimize injection speed and temperature control parameters;

[0134] User interface module: provides an interactive interface through which users can view real-time data, alarm information and historical analysis results, while allowing manual input of adjustment parameters; the injection speed control system integrates multiple functional modules to achieve precise control and real-time optimization of key parameters in the injection process, thereby improving the consistency and quality of die-casting products.

[0135] Those skilled in the art should understand that the discussion of any of the above embodiments is merely illustrative and is not intended to imply that the scope of the present invention is limited to these examples. Under the concept of the present invention, the technical features in the above embodiments or different embodiments may be combined, the steps may be implemented in any order, and there are many other variations of the different aspects of the present invention as described above, which are not provided in detail for the sake of simplicity.

[0136] The present invention is intended to cover all such substitutions, modifications and variations that fall within the broad scope of the claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for controlling the injection speed of a die-casting machine based on data analysis, characterized in that: The following steps are involved: S1: Deploy a multifunctional sensor network in the die casting machine to monitor key parameters in real time, including injection speed, molten metal temperature, and temperature and humidity of the die casting environment; The S1 specifically includes: S11: Deploy a multifunctional sensor network, including speed sensors, thermocouple sensors, and humidity sensors. The speed sensor is used to measure the injection speed, the thermocouple sensor is used to determine the temperature of the molten metal, and the humidity sensor is used to monitor the humidity in the die casting environment. S12: Install sensors at predetermined positions of the die-casting machine. The speed sensor is installed at the nozzle outlet to measure the metal outflow speed. The thermocouple sensor directly contacts the molten metal to ensure the accuracy of temperature measurement. The humidity sensor is deployed in the environment of the die-casting machine to monitor the humidity changes of the environment in real time. S13: connecting each sensor to a central data processing unit, specifically using a wired or wireless network to ensure real-time data transmission, wherein the wireless network uses Wi-Fi or Bluetooth technology; S14: Preprocess the collected data and use data processing algorithms to perform preliminary screening and noise reduction. Specifically, a moving average or low-pass filter is used to smooth the data, improve data quality, and provide input for subsequent in-depth analysis; S2: Using the data collected by S1, the theoretical fluidity temperature of the molten metal is calculated through a preset thermodynamic model, and the cooling rate of the metal under the current environmental conditions is predicted, providing a theoretical basis for temperature control; The S2 specifically includes: S21: Acquire the real-time data collected by the sensor network in S1, including the parameters of molten metal temperature, temperature and humidity of the die-casting environment, and provide basic data for subsequent calculations; S22: inputting the data obtained in S21 into a preset thermodynamic model, which calculates the theoretical fluidity temperature of the molten metal under current environmental conditions based on the physical properties of the metal and the principle of heat conduction; S23: Predict the cooling rate of molten metal by combining the heat conduction equation in the thermodynamic model with the ambient temperature and humidity data; S24: transmitting the calculated theoretical fluidity temperature and cooling rate data to the temperature control system to ensure that the heating system can adjust the temperature of the molten metal according to the real-time data; S3: Based on the output of S2, the heating system of the die-casting machine is adjusted through a preset temperature control algorithm to ensure that the molten metal reaches the theoretical fluidity temperature before being injected into the mold; The S3 specifically includes: S31: Receive the output from S2, including the calculated theoretical fluidity temperature T of the molten metal opt and the predicted cooling rate S32: Set the target temperature of the heating system, the target temperature T target According to the theoretical fluidity temperature T opt The setting is based on the actual cooling conditions of the metal in the mold to ensure that the metal maintains optimal fluidity during the injection molding process. The calculation formula is: T target =T opt +ΔT, where ΔT is the temperature difference adjusted for the predicted cooling rate; S33: Apply a temperature control algorithm to adjust the heating system. The temperature control algorithm specifically uses a PID control strategy to adjust the temperature according to the target temperature T target and the actual molten metal temperature T metal The difference between the two automatically adjusts the heating power. The expression of the PID control algorithm is: Where u(t) is the control input of the heating system, i.e., the heating power; K p ,K i ,K d are the proportional, integral and differential coefficients of the PID controller respectively; e(t) = T target -T metal , that is, the deviation between the target temperature and the actual temperature; the heating system is adjusted according to the heating power calculated by the PID algorithm to ensure that the output of the heating system can quickly and accurately reach and maintain the target temperature; S4: Compare the real-time monitored molten metal temperature with the theoretical fluidity temperature in S3, and use a dynamic adjustment algorithm based on rheological principles to control the speed during the injection process to adapt to the actual flow characteristics of the metal; The S4 specifically includes: S41: First obtain the molten metal temperature T monitored in real time real , and obtain the theoretical fluidity temperature T calculated in S2 opt ; S42: Calculate the actual temperature T real and the theoretical fluidity temperature T opt The deviation between T ; S43: Based on rheological principles, according to the temperature deviation e T Adjust the injection speed. The following relationship describes the temperature dependence of metal viscosity η: Where η0 is the viscosity of the molten metal at the reference temperature; E is the activation energy of the viscosity; R is the gas constant; T real is the real-time temperature; S44: According to the actual viscosity η of the metal, the injection speed v is adjusted by applying a dynamic adjustment algorithm to ensure optimal metal fluidity. The formula of the adjustment algorithm is: Among them, v0 is the reference injection speed; η0 and η are the reference viscosity and real-time viscosity respectively; based on the dynamic adjustment algorithm, the injection speed is adjusted in real time through the control system of the die-casting machine to adapt it to the actual flow characteristics of the metal, ensuring that the metal can be injected at the optimal speed under different temperature conditions; S5: Based on real-time injection data and environmental data, through a preset data processing framework, identify the specific impact of environmental factors on the injection process and automatically adjust injection parameters to compensate for the impact; The S5 specifically includes: S51: acquiring real-time injection data and environmental data, wherein the injection data includes injection speed and injection pressure, and the environmental data includes environmental temperature and environmental humidity; S52: input the data obtained in S51 into a preset data processing framework, which is based on multivariate regression analysis and machine learning algorithms and is intended to identify and quantify the specific impact of environmental factors on the injection process; S53: Perform multivariate regression analysis to establish a relationship model between injection parameters and environmental factors. The specific formula is: P adjusted =β0+β1T env +β2RH+β3v real +∈, where P adjusted represents the adjusted injection pressure; β0, β1, β2, β3 are regression coefficients obtained through historical data training; T env is the ambient temperature; RH is the ambient humidity; v real is the actual injection speed; ∈ is the error term; v real is the current injection speed; S54: Use machine learning algorithms to optimize the relationship model to identify nonlinear effects and complex interactions. The machine learning model continuously learns and improves through historical data and real-time data to improve prediction accuracy. S55: Based on the optimized model, the adjusted injection parameters, including injection pressure and injection speed, are calculated in real time to compensate for the influence of environmental factors. The specific adjustment formula is: v adjusted =v real +Δv; Δv=γ1(T env -T ref )+γ2(RH-RH ref ), where v adjusted is the adjusted injection speed; Δv is the speed adjustment amount; γ1, γ2 are the environmental adjustment coefficients; T ref and RH ref They are the reference ambient temperature and reference humidity respectively; S6: According to the injection parameters adjusted in S5, the injection speed of the die-casting machine is finally adjusted to achieve the best die-casting quality and efficiency; The S6 specifically includes: S61: Obtain the adjusted injection parameters from S5, including the adjusted injection speed v adjusted and injection pressure P adjusted ; S62: The adjusted injection speed v is set by the control system of the die casting machine. adjusted and injection pressure P adjusted Input to the control unit of the die casting machine; S63: Start the injection speed adjustment module in the control unit to adjust the speed during the injection process in real time. During the process, the current injection speed is continuously monitored and compared with the adjusted injection speed v adjusted Compare; if the current injection speed is lower than the adjusted injection speed, the control unit increases the injection speed; if the current injection speed is higher than the adjusted injection speed, the control unit reduces the injection speed; S64: After the injection process is completed, the finished product quality data is analyzed; if the finished product quality meets the standard, the current injection speed and pressure parameters are saved as a reference for future production; if the finished product quality does not meet the standard, the parameter settings are adjusted and the data is recorded.

2. A method for controlling the injection speed of a die-casting machine based on data analysis according to claim 1, characterized in that: The S22 specifically includes: S221: First determine the basic physical properties of metals, including density ρ, specific heat capacity c p and thermal conductivity λ; where ρ represents the mass of metal per unit volume, c p It indicates the ability of metal to increase unit temperature after absorbing unit heat, and λ indicates the ability of metal to conduct heat; S222: Then collect environmental condition data, including ambient temperature T env and humidity RH, where T env Indicates the current ambient temperature, and RH indicates the current ambient humidity; S223: Using the improved heat balance equation to calculate the theoretical fluidity temperature T of the molten metal opt , which takes into account the heat conduction, convection and radiation loss factors of the metal for calculation. The specific formula is: Among them, Q in It represents the total heat provided by the heating system to the metal in joules, Q out represents the total heat loss due to environmental conditions and radiation from the metal surface in joules, m represents the mass of the molten metal in kilograms, T init It represents the initial temperature of the molten metal in degrees Celsius; S224: To calculate Q more accurately out , the ambient temperature and humidity adjustment coefficient α will be introduced T and α RH , used to adjust the heat loss calculation, the specific formula is: Q out =α T ·f(T env )+α RH g(RH) λ A (T metal -T env ), where α T is the ambient temperature adjustment coefficient, dimensionless, indicating the influence of ambient temperature on heat loss; α RH is the environmental humidity adjustment coefficient, dimensionless, indicating the degree of influence of environmental humidity on heat loss; f(T env ) is the effect of ambient temperature on heat loss; g(RH) is the effect of ambient humidity on heat loss; λ is the thermal conductivity of metal, in watts per meter per Kelvin; A is the surface area of ​​metal, in square meters; T metal Indicates the current temperature of the metal in degrees Celsius; S225: T calculated in S223 opt This will be used as the target temperature setting for the die casting machine's heating system during the shot process.

3. The method for controlling the injection speed of a die-casting machine based on data analysis according to claim 2, characterized in that: The S23 specifically includes: S231: Obtain current values ​​of ambient temperature and humidity from the real-time environmental data collected by S1; S232: Apply the heat conduction equation to calculate the heat exchange between the molten metal surface and the environment. The equation is based on Newton's law of cooling and the formula is: Q = h·A·(T metal -T env ), where Q represents the amount of heat transferred from the metal surface to the environment per unit time; h represents the heat exchange coefficient in watts per square meter per degree Celsius; A represents the metal surface area in square meters; T metal Indicates the current temperature of the metal in degrees Celsius; T env Indicates the ambient temperature in degrees Celsius; S233: Calculate cooling rate That is, the rate of change of metal temperature with time, which is solved by the energy conservation equation, the formula is: Where m represents the metal mass in kilograms; c p It represents the specific heat capacity of metals in joules per kilogram per degree Celsius; S234: Based on the effect of ambient humidity on the cooling rate, adjust the heat exchange coefficient h. In a high humidity environment, due to the increase in the thermal conductivity of the air, h will increase accordingly, thereby accelerating the heat exchange. The formula is: h adjusted =h·(1+β·RH), where β represents the humidity adjustment coefficient, which is used to adjust the heat exchange coefficient to adapt to environments with different humidity; S235: Use the adjusted heat exchange coefficient h adjusted Recalculate Q and To obtain more accurate cooling rate predictions.

4. A die-casting machine injection speed control system based on data analysis, used to implement a die-casting machine injection speed control method based on data analysis as described in any one of claims 1 to 3, characterized in that: Includes the following modules: Data acquisition module: used to collect real-time data on the die-casting machine’s injection speed, molten metal temperature, injection pressure, and the temperature and humidity of the die-casting environment; Data processing module: Based on the data collected by the data acquisition module, the preset thermodynamic model and rheological model are used to analyze the data, calculate the theoretical fluidity temperature of the molten metal and predict the cooling rate of the metal, and adjust the baseline values ​​of the injection speed and pressure according to the environmental data; Temperature control module: Based on the theoretical fluidity temperature output by the data processing module, the PID control algorithm is used to adjust the heating power according to the difference between the real-time and theoretical temperatures to maintain the metal temperature at the optimal state; Injection speed adjustment module: receives the output of the data processing module and dynamically adjusts the injection speed according to the injection speed adjustment requirements to adapt to the actual flow characteristics of the metal; Feedback and optimization module: monitors the entire injection process, collects quality data and injection parameters of finished products in real time, and uses machine learning technology to analyze data in the production process to automatically optimize injection speed and temperature control parameters; User interface module: provides an interactive interface through which users can view real-time data, alarm information, and historical analysis results, while allowing manual input of adjustment parameters.

Images