A Dynamic Temperature Regulation Method for Preparing Ester-Based Metalworking Fluids

Abstract

The present invention relates to the technical field of temperature regulation, and particularly to a method for dynamically adjusting the preparation temperature of an ester-based metal working fluid. The ester-based metal working fluid includes a low-carbon ester-based base oil, an environmentally friendly emulsifier, an extreme pressure and anti-wear agent, a low-carbon preservative, a corrosion inhibitor, and an auxiliary additive. The method for dynamically adjusting the temperature includes: setting a basic heating power for the low-carbon ester-based base oil, and heating the low-carbon ester-based base oil to a first set temperature range through PID control; respectively performing the addition processes of the environmentally friendly emulsifier and the extreme pressure and anti-wear agent, and adjusting the temperature based on a neural network and an image monitoring system during the addition processes. After the addition is completed, control the temperature to reach a third set temperature range; simultaneously add the low-carbon preservative and the corrosion inhibitor, and adjust the temperature through PID control during the addition process; this method can achieve real-time temperature feedback and adaptive adjustment to ensure that the temperature in each stage is maintained within the optimal range required by the material.

Description

Technical Field

[0001] The present invention relates to the technical field of temperature regulation, and particularly to a method for dynamically adjusting the preparation temperature of an ester-based metal working fluid. Background Art

[0002] With the increasing global awareness of environmental protection, low-carbon environmental protection has become an important development direction for all industries. In the field of metal processing, although traditional working fluids can meet certain processing requirements, their production raw materials mostly contain non-renewable resources, and they are prone to generate volatile organic compounds (VOCs) during use, and may also cause secondary pollution to the environment during waste treatment, which is contrary to the concept of low-carbon environmental protection. Therefore, developing a low-carbon environmental protection type metal working fluid is of great significance for promoting the sustainable development of the metal processing industry.

[0003] The low-carbon environmental protection type metal working fluid has the following characteristics: First, the raw material selection tends to renewable resources or chemicals with low environmental impact; second, the preparation process should reduce energy consumption and carbon emissions; third, during use, the emission of VOCs should be reduced, and at the same time, it should have good lubrication, rust prevention and cooling performance; fourth, during waste treatment, it should be easily degradable or recyclable, reducing the impact on the environment.

[0004] During the preparation of the low-carbon environmental protection type metal working fluid, precise temperature control is particularly important; specifically, since the low-carbon environmental protection type metal working fluid uses renewable resources or chemicals with low environmental impact, such as bio-based ester compounds, the molecular structures of these materials are relatively complex, and temperature changes may cause decomposition or performance degradation. In addition, the precision of temperature control can not only improve the reaction efficiency, but also reduce unnecessary energy consumption. For example, during the heating or cooling process, if the temperature can be strictly controlled within the range required by the process, the energy waste caused by overheating or overcooling can be avoided, thereby reducing carbon emissions. From the perspective of uniform mixing of components, various additives in the metal working fluid need to be fully dissolved and uniformly dispersed at an appropriate temperature. Improper temperature control may lead to uneven emulsification, stratification or additive failure. Based on the above importance, how to achieve precise control of the preparation temperature of the ester-based metal working fluid has become an important technology to promote the wide application of related low-carbon environmental protection type metal working fluids. Summary of the Invention

[0005] To solve the above technical problems, the present invention provides a method for dynamically adjusting the preparation temperature of an ester-based metal working fluid, which can achieve real-time temperature feedback and adaptive adjustment to ensure that the temperature in each stage is maintained within the optimal range required by the material.

[0006] In the first aspect, the present invention provides a method for dynamically adjusting the preparation temperature of an ester-based metal working fluid, where the ester-based metal working fluid includes a low-carbon ester-based base oil, an environmentally friendly emulsifier, an extreme pressure and anti-wear agent, a low-carbon preservative, a corrosion inhibitor, and an auxiliary additive. The temperature dynamic adjustment method includes:

[0007] Set a basic heating power for the low-carbon ester-based base oil, and heat the low-carbon ester-based base oil to a first set temperature range through PID control;

[0008] Respectively execute the addition processes of the environmentally friendly emulsifier and the extreme pressure and anti-wear agent, and perform temperature adjustment based on a neural network and an image monitoring system during the addition process. After the addition is completed, control the temperature to reach a third set temperature range;

[0009] Add the low-carbon preservative and the corrosion inhibitor simultaneously, perform temperature adjustment through PID control during the addition process, and control the temperature to reach room temperature after the addition is completed;

[0010] Execute room temperature control to complete the temperature control for the addition of the auxiliary additive.

[0011] Furthermore, setting a basic heating power for the low-carbon ester-based base oil and heating the low-carbon ester-based base oil to a first set temperature range through PID control includes:

[0012] Determine the first set temperature range according to the physical properties and process requirements of the low-carbon ester-based base oil; and extract the heating time requirement corresponding to the first set temperature range from the process requirements;

[0013] Calculate the basic heating power based on the first set temperature range and the heating time requirement;

[0014] Debug the proportional, integral, and derivative parameters of the PID controller, monitor the temperature of the low-carbon ester-based base oil in real time through a temperature sensor, and feed the real-time monitored temperature back to the PID controller;

[0015] Turn on the heating equipment and gradually heat the base oil to the first set temperature range according to the instructions of the PID controller.

[0016] Furthermore, debug the proportional, integral, and derivative parameters of the PID controller by using one of the empirical method, the Ziegler-Nichols method, or an automatic tuning algorithm.

[0017] Furthermore, respectively execute the addition processes of the environmentally friendly emulsifier and the extreme pressure and anti-wear agent, and perform temperature adjustment based on a neural network and an image monitoring system during the addition process, including:

[0018] Load the neural network model into the control system and initialize the image monitoring device;

[0019] Add the environmentally friendly emulsifier. During the process, the characteristic set of dispersed phase particles after adding the environmentally friendly emulsion is detected in real time by an image monitoring system. The neural network model predicts the change trend of the emulsification state in real time according to the data fed back by the image monitoring system, and adjusts the temperature according to the change trend.

[0020] After the addition of the environmentally friendly emulsifier is completed, adjust the solution temperature to the second set temperature range.

[0021] Add the extreme pressure and anti-wear agent. During the process, the distribution state of the extreme pressure and anti-wear agent in the solution is detected in real time by an image monitoring system. The neural network model predicts the dispersion trend of the extreme pressure and anti-wear agent in the solution according to the data fed back by the image monitoring system, and adjusts the temperature according to the dispersion trend.

[0022] After the addition of the extreme pressure and anti-wear agent is completed, adjust the solution temperature to the third set temperature range.

[0023] Further, when adding the environmentally friendly emulsifier, during the process, the characteristic set of dispersed phase particles after adding the environmentally friendly emulsion is detected in real time by an image monitoring system. The neural network model predicts the change trend of the emulsification state in real time according to the data fed back by the image monitoring system, and adjusts the temperature according to the change trend, including:

[0024] Set the monitoring frequency of the image monitoring system according to the first set temperature range and the addition speed of the emulsifier.

[0025] Based on the monitoring frequency, obtain the liquid microscopic image after adding the environmentally friendly emulsifier in real time through the image monitoring system.

[0026] Perform feature recognition on the liquid microscopic image to obtain the characteristic set of dispersed phase particles.

[0027] Input the characteristic set of dispersed phase particles into a pre-constructed neural network model to obtain a dispersion indication result.

[0028] Calculate the dispersion fluctuation vector between the dispersion indication results obtained from two adjacent monitoring operations. The dispersion fluctuation vector is the dispersion indication result obtained from the latest monitoring operation minus the dispersion indication result obtained from the previous monitoring operation; the dispersion fluctuation vector includes the fluctuation amount and the fluctuation direction.

[0029] Traverse the dispersion fluctuation vector in a pre-built emulsification temperature control data space to obtain a temperature adjustment vector; the temperature adjustment vector includes the temperature adjustment amount and the temperature adjustment direction.

[0030] Perform dynamic temperature adjustment according to the temperature adjustment vector.

[0031] Further, the dispersed phase particle feature set includes particle size distribution, average particle size, and dispersion uniformity.

[0032] Further, the calculation formula for the dispersion indication result is:

[0033]

[0034] where P represents the dispersion indication result, n(r) represents the number of particles with a particle size of r in the dispersed phase particles, N represents the total number of dispersed phase particles, R i represents the diameter of the i-th dispersed phase particle, m and n respectively represent the number of rows and columns of the grid into which the image is divided; N ij represents the number of particles in the grid of the i-th row and j-th column; represents the average particle size of all dispersed phase particles; ω1, ω2, and ω3 respectively represent the weight coefficients corresponding to the particle size distribution, average particle size, and dispersion uniformity.

[0035] Further, the setting factors for the second set temperature range include: the thermal stability of the environmentally friendly emulsifier, the optimum dispersion temperature of the extreme pressure and anti-wear agent, and the solution chemical equilibrium.

[0036] Further, when adding the low-carbon preservative and the corrosion inhibitor simultaneously, the temperature is adjusted by PID control during the addition process, and after the addition is completed, the temperature is controlled to reach room temperature, including:

[0037] According to the formulation requirements of the metalworking fluid, determine the types of low-carbon preservative and corrosion inhibitor to be added, weigh the required preservative and corrosion inhibitor, and prepare the addition equipment;

[0038] According to the physical properties of the determined preservative and corrosion inhibitor, determine the temperature range required during the addition process;

[0039] Perform temperature control according to the determined temperature range required during the addition process; and add the weighed preservative and corrosion inhibitor to the solution simultaneously; during the addition process, the temperature of the solution is monitored in real time by a temperature sensor and fed back to the PID controller;

[0040] The PID controller automatically adjusts the power of the heating equipment according to the real-time temperature data fed back by the temperature sensor;

[0041] After the preservative and corrosion inhibitor are completely added and evenly dispersed, stop the heating equipment; start the cooling equipment, and gradually reduce the solution temperature to the set temperature; during the cooling process, continue to use the PID controller to ensure a stable temperature change during the cooling process.

[0042] Further, the auxiliary additives include at least one of an antioxidant, an antifoaming agent, and a rust inhibitor.

[0043] Compared with the prior art, the beneficial effects of the present invention are as follows: By combining PID control and neural network with an image monitoring system, the present invention can achieve real-time temperature feedback and adaptive adjustment, ensuring that the temperature in each stage is maintained within the optimal range required by the material, avoiding decomposition or performance attenuation caused by excessive temperature, maintaining the chemical stability of the material, thereby improving the performance and sustainability of the processing fluid;

[0044] During the implementation process, a PID controller is used to precisely adjust the temperature, and a neural network is used to predict and optimize the temperature adjustment strategy, which can avoid unnecessary energy waste. At the same time, it can continuously monitor and predict the temperature and reaction state, ensuring that the temperature fluctuations in each stage are controllable. This not only improves the stability of the production process but also reduces the need for human intervention, resulting in higher production consistency and reducing potential process risks;

[0045] Based on the difference in importance, through a neural network and an image monitoring system, the addition process of emulsifiers and extreme pressure anti-wear agents is monitored and adjusted in real time. The addition of emulsifiers requires a relatively high temperature, and the quality of the emulsification effect will directly affect the stability of the entire processing fluid. While the extreme pressure anti-wear agent can be fully mixed with the base oil to achieve the best lubrication and anti-wear effects. The image monitoring system can accurately capture various states, and the neural network can adjust the temperature control strategy according to the real-time data feedback, improving the quality of the final metal processing fluid; The heating of the base oil needs to be controlled within a certain temperature range. However, due to its fluidity and viscosity remaining stable within a relatively large temperature range, the precise control requirements for temperature in this process are relatively low. Preservatives and corrosion inhibitors are usually added at a relatively low temperature, and the temperature regulation is mainly to prevent uneven dispersion caused by too rapid cooling. Although temperature is important, the process is relatively stable. Therefore, the above temperature control is all completed by PID control, which can reduce the control difficulty. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 is a flowchart of the present invention;

[0047] Figure 2 is a flowchart of the temperature control during the addition of the environmentally friendly emulsifier. DETAILED DESCRIPTION OF THE INVENTION

[0048] The present application will be described below with reference to the drawings in the present application.

[0049] As Figure 1 shown, a method for dynamically adjusting the preparation temperature of an ester-based metal processing fluid according to the present invention. The ester-based metal processing fluid includes a low-carbon ester-based base oil, an environmentally friendly emulsifier, an extreme pressure anti-wear agent, a low-carbon preservative, a corrosion inhibitor, and an auxiliary additive. The temperature dynamic adjustment method specifically includes the following steps:

[0050] Step S100: Set the basic heating power for the low-carbon ester base oil, and heat the low-carbon ester base oil to the first set temperature range through PID control;

[0051] Step S200: Perform the addition processes of the environmental protection emulsifier and the extreme pressure and anti-wear agent respectively, and adjust the temperature based on the neural network and the image monitoring system during the addition process. After the addition is completed, control the temperature to reach the third set temperature range;

[0052] Step S300: Add the low-carbon preservative and the corrosion inhibitor simultaneously, adjust the temperature through PID control during the addition process, and control the temperature to reach room temperature after the addition is completed;

[0053] Step S400: Perform room temperature control to complete the temperature control of the addition of the auxiliary additives.

[0054] In this embodiment, by combining PID control with a neural network and an image monitoring system, real-time temperature feedback and adaptive adjustment can be achieved, ensuring that the temperature in each stage is maintained within the optimal range required by the material, avoiding decomposition or performance attenuation caused by too high temperature, maintaining the chemical stability of the material, and thus improving the performance and sustainability of the machining fluid;

[0055] During the implementation process, use the PID controller to precisely adjust the temperature, and predict and optimize the temperature adjustment strategy through the neural network, which can avoid unnecessary energy waste. At the same time, continuous monitoring and prediction of the temperature and reaction state can be achieved, ensuring that the temperature fluctuations in each stage are controllable, not only improving the stability of the production process, but also reducing the need for human intervention, making the production more consistent and reducing potential process risks;

[0056] Based on the difference in importance, through the neural network and the image monitoring system, the addition processes of the emulsifier and the extreme pressure and anti-wear agent are monitored and adjusted in real time. The addition of the emulsifier has higher temperature requirements, and the quality of the emulsification effect will directly affect the stability of the entire machining fluid. The extreme pressure and anti-wear agent can be fully mixed with the base oil to achieve the best lubrication and anti-wear effects. The image monitoring system can accurately capture various states, and the neural network can adjust the temperature control strategy according to the real-time data fed back, improving the quality of the final metal machining fluid; The heating of the base oil needs to be controlled within a certain temperature range, but since its fluidity and viscosity remain stable within a relatively large temperature range, the precise control requirements for temperature in this process are relatively low. The preservative and the corrosion inhibitor are usually added at a lower temperature, and the temperature control is mainly to prevent uneven dispersion caused by too fast cooling. Although temperature is important, the process is relatively stable. Therefore, the above temperature control is all completed by PID control, which can reduce the control difficulty.

[0057] The following describes Figure 1 the execution manners of the various steps shown.

[0058] Regarding step S100:

[0059] The purpose of step S100 is to heat the low-carbon ester base oil to a specific temperature range, focusing on the heating process of the low-carbon ester base oil, and preparing for the subsequent additive addition and mixing processes. The specific implementation is as follows:

[0060] Step S110: According to the physical properties and process requirements of the low-carbon ester base oil, determine the first set temperature range; and extract the heating time requirements corresponding to the first set temperature range from the process requirements;

[0061] Among them, regarding the physical properties, the physical properties of the low-carbon ester base oil include melting point, boiling point, viscosity, and thermal stability; the melting point determines the temperature at which the low-carbon ester base oil starts to change from solid to liquid, while the boiling point is the temperature at which it changes from liquid to gas. Viscosity is a measure of the resistance to fluid flow. For metalworking fluids, viscosity directly affects their lubricating performance. Generally, the viscosity of the low-carbon ester base oil decreases with the increase of temperature. Therefore, a temperature range needs to be determined so that the base oil has appropriate viscosity within this range to meet the processing requirements; thermal stability refers to determining the highest heating temperature that will not cause the decomposition or performance degradation of the low-carbon ester base oil;

[0062] In the process requirements, various additives will be added in the subsequent steps, such as environmentally friendly emulsifiers, extreme pressure anti-wear agents, etc. The above additives need to be fully dissolved and evenly dispersed in the base oil within a certain temperature range. The heating temperature range needs to consider the solubility of these additives; in addition, there may be chemical reactions between some additives and the base oil, and chemical reactions usually require a certain temperature to accelerate. Therefore, the heating temperature range also needs to consider the kinetic requirements of the chemical reactions involved;

[0063] Based on the above analysis, a heating temperature range that both meets the physical property requirements of the low-carbon ester base oil and conforms to the process requirements can be determined, that is, the first set temperature range; after determining the first set temperature range, it is also necessary to extract the corresponding heating time requirements from the process requirements. The determination of the heating time needs to consider factors such as the efficiency of the heating equipment, the quality of the base oil, and the heat capacity.

[0064] Step S120: Based on the first set temperature range and the heating time requirements, calculate the basic heating power; specifically, it is necessary to estimate the energy required during the heating process according to the physical characteristics of the low-carbon ester base oil and the required temperature change range. Combining the heating time requirements, the heating power required to reach the first set temperature range can be calculated. The calculation formula is:

[0065]

[0066] Where P is the heating power, m is the mass of the low-carbon ester-based base oil, c is the specific heat capacity of the low-carbon ester-based base oil, ΔT is the temperature difference between the real-time temperature of the low-carbon ester-based base oil and the minimum temperature in the first set temperature range, and t is the heating time; the basic heating power can be obtained through calculation to ensure that the heating process is both efficient and energy-saving. A reasonable heating power helps to maintain the stability and controllability of the entire preparation process, thereby improving the quality and performance of the metalworking fluid.

[0067] Step S130: Debug the proportional, integral, and derivative parameters of the PID controller. Monitor the temperature of the low-carbon ester-based base oil in real time through a temperature sensor, and feed the real-time monitored temperature back to the PID controller; debug the proportional, integral, and derivative parameters of the PID controller by using one of the empirical method, the Ziegler-Nichols method, or the auto-tuning algorithm; accurately place the temperature sensor in the low-carbon ester-based base oil to monitor its temperature change in real time, and the temperature sensor transmits the collected temperature data to the PID controller in real time;

[0068] Proportional action (P): Adjust the heating power according to the deviation between the current temperature and the set temperature;

[0069] Integral action (I): Accumulate the historical data of the temperature deviation to eliminate the steady-state error;

[0070] Derivative action (D): Predict the future temperature change trend and make adjustments in advance to reduce the overshoot;

[0071] By accurately debugging the proportional, integral, and derivative parameters of the PID controller, ensure that the temperature monitored in real time by the temperature sensor for detecting the oil product temperature can be accurately fed back to the PID controller, and through the instructions of the PID controller, achieve precise control of the temperature of the low-carbon ester-based base oil.

[0072] Step S140: Turn on the heating device and gradually heat the base oil to the first set temperature range according to the instructions of the PID controller.

[0073] Regarding step S200:

[0074] In step S200, add the environmental protection emulsifier and the extreme pressure and anti-wear agent, and use the image monitoring system and the neural network model to predict and adjust the change trend of the emulsification state and the dispersion state in real time, so as to perform dynamic temperature adjustment. The specific implementation is as follows:

[0075] Step S210: Load the neural network model into the control system and initialize the image monitoring device. Load the pre-trained neural network model into the control system. The neural network model can predict the change trends of the emulsification state and the dispersion state of the extreme pressure anti-wear agent based on the data provided by the image monitoring system. Set up and start the image monitoring device to ensure that it can capture and transmit the microscopic images of the solution after adding the emulsifier and the anti-wear agent in real time.

[0076] Step S220: Add the environmentally friendly emulsifier. During the process, the characteristic set of the dispersed phase particles after adding the environmentally friendly emulsion is detected in real time through the image monitoring system. The neural network model predicts the change trend of the emulsification state in real time according to the data fed back by the image monitoring system, and adjusts the temperature according to the change trend. More specifically, as Figure 2 shown, the temperature control method during the addition of the environmentally friendly emulsifier includes:

[0077] Step S221: Set the monitoring frequency of the image monitoring system according to the first set temperature range and the addition speed of the emulsifier. The selection of the monitoring frequency should ensure that the subtle changes during the addition of the emulsifier can be captured, and at the same time, it is not too frequent to reduce the computational burden. Assuming that the first set temperature range is 45°C to 55°C and the addition speed of the emulsifier is 100 ml per minute, image monitoring can be performed every 10 seconds.

[0078] Step S222: Start the image monitoring system while starting to add the environmentally friendly emulsifier. According to the set monitoring frequency, obtain the microscopic images of the liquid after adding the environmentally friendly emulsifier in real time through a microscope or other high-resolution imaging devices. Store the collected image data in the control system for subsequent processing and analysis.

[0079] Step S223: Perform feature recognition on the liquid microscopic images to obtain the characteristic set of the dispersed phase particles. The characteristic set of the dispersed phase particles includes particle size distribution, average particle size, and dispersion uniformity. Preprocess the collected microscopic images, such as denoising and enhancing contrast, to improve the image quality. Use image processing algorithms (such as edge detection, morphological operations, etc.) to identify the dispersed phase particles in the images. Use the OpenCV library for image processing, extract the particle size distribution and the average particle size, and calculate the dispersion uniformity.

[0080] Step S224: Organize the extracted characteristic set of the dispersed phase particles (particle size distribution, average particle size, and dispersion uniformity) into a format suitable for input into the neural network model. Input the characteristic set into the pre-trained neural network model, and the model predicts the change trend of the current emulsification state according to the input data. Use the TensorFlow or PyTorch framework to build the neural network model, input the characteristic set, and output the dispersion indication result.

[0081] Step S225: Calculate the dispersion fluctuation vector between the dispersion indication results obtained from two adjacent monitoring operations. The dispersion fluctuation vector is the dispersion indication result obtained from the latest monitoring operation minus the dispersion indication result obtained from the previous monitoring operation. The dispersion fluctuation vector includes the fluctuation amount (i.e., the absolute value of the difference) and the fluctuation direction (i.e., the positive or negative sign of the difference). Assume that the dispersion indication result of the previous monitoring is D1 and the dispersion indication result of the current monitoring is D2, then the fluctuation vector V is: V = D2 - D1;

[0082] Step S226: Pre-build a temperature control data space that contains different temperature adjustment strategies. Each strategy corresponds to a temperature adjustment vector, which includes the temperature adjustment amount and the temperature adjustment direction. Traverse the dispersion fluctuation vector in the temperature control data space to find the temperature adjustment vector that best suits the current dispersion fluctuation vector. Assume that the temperature control data space contains multiple temperature adjustment strategies, such as increasing the temperature by 1°C, decreasing the temperature by 1°C, keeping it unchanged, etc., and select the strategy that best matches the current dispersion fluctuation vector;

[0083] Step S227: According to the selected temperature adjustment vector, the PID controller sends a corresponding adjustment instruction to adjust the power of the heating or cooling equipment. Real-time monitor the temperature change of the base oil through a temperature sensor to ensure that the temperature is adjusted according to the requirements of the adjustment vector. If the temperature adjustment vector indicates an increase of 1°C, the PID controller adjusts the heating power to gradually increase the temperature by 1°C, and real-time monitor the temperature change through the temperature sensor to ensure that the temperature is stable within the new set range.

[0084] Furthermore, the calculation formula for the dispersion indication result is:

[0085]

[0086] where P represents the dispersion indication result, n(r) represents the number of particles with a dispersed phase particle size of r, N represents the total number of dispersed phase particles, R i represents the diameter of the i-th dispersed phase particle, m and n respectively represent the number of rows and columns of the grids into which the image is divided; during the image processing process, the liquid microscopic image will be divided into multiple grids of the same size to facilitate the calculation of the number of particles in each grid; N ij represents the number of particles in the grid of the i-th row and the j-th column; represents the average particle size of all dispersed phase particles. ω1, ω2, and ω3 respectively represent the weight coefficients corresponding to the particle size distribution, average particle size, and dispersion uniformity.

[0087] In step S220, the characteristics of the dispersed phase particles after adding the environmentally friendly emulsifier are detected in real time by the image monitoring system, which can quickly capture the subtle changes during the emulsification process, ensuring the controllability and stability of the emulsification process; the neural network model is used to predict the change trend of the emulsification state in real time according to the data fed back by the image monitoring system, and the temperature is adjusted according to the prediction results, improving the automation level and accuracy of the emulsification process; through the accurate identification and calculation of the characteristics of the dispersed phase particles (such as particle size distribution, average particle size, and dispersion uniformity), the emulsification effect can be evaluated more accurately, which helps to adjust the process parameters in a timely manner, optimize the emulsification process, and improve the product quality; by setting the monitoring frequency of the image monitoring system, important changes during the emulsification process can be captured, and at the same time, overly frequent data collection and calculation are avoided, thereby reducing the computational burden of the system; a temperature control data space containing different temperature adjustment strategies is pre-established, and the most suitable temperature adjustment strategy is selected according to the dispersion fluctuation vector, which can better adapt to various changes during the emulsification process, ensuring the stability and efficiency of the emulsification process; corresponding adjustment instructions are sent through the PID controller to adjust the power of the heating or cooling equipment, and the temperature change is monitored in real time through the temperature sensor to ensure that the emulsification process is carried out within the set temperature range, thereby improving the quality and stability of the product.

[0088] Step S230, after the addition of the environmentally friendly emulsifier is completed, the solution temperature is adjusted to the second set temperature range; the determination of the second set temperature range is based on the temperature conditions required after the addition of the emulsifier and the extreme pressure and anti-wear agent to ensure that the above additives can be fully mixed with the base oil and exert the best effect. The factors to be considered in determining the second set temperature range include:

[0089] a. Properties of the environmentally friendly emulsifier: Different environmentally friendly emulsifiers have different thermal stabilities and emulsification temperature ranges; therefore, when selecting the second set temperature range, the technical specifications and recommended use temperature of the emulsifier need to be referred to; the thermal stability of the emulsifier determines whether it can maintain a stable emulsification effect at high temperatures, thereby avoiding the occurrence of demulsification or stratification phenomena;

[0090] b. Requirements of the extreme pressure and anti-wear agent: The performance and dispersion effect of the extreme pressure and anti-wear agent are also affected by temperature; therefore, when determining the second set temperature range, the optimal dispersion temperature and stability of the extreme pressure and anti-wear agent need to be considered; too high or too low temperature may cause uneven dispersion of the extreme pressure and anti-wear agent in the solution, thereby affecting the performance of the processing fluid;

[0091] c. Chemical balance of the solution: During the preparation process, the chemical components in the solution will reach a certain equilibrium state; this equilibrium state is affected by temperature, so the temperature needs to be adjusted to maintain or optimize this balance; the selection of the second set temperature range should ensure that the chemical components in the solution can exist stably and exert the best synergistic effect.

[0092] Step S240: The addition of extreme pressure and anti-wear agents is to improve the extreme pressure performance and anti-wear performance of the machining fluid. Extreme pressure and anti-wear agents usually have specific chemical structures and properties, and can form a protective film during the metal processing process to reduce friction and wear between metals. When adding extreme pressure and anti-wear agents, the distribution state of the extreme pressure and anti-wear agents in the solution is detected in real time through an image monitoring system. The neural network model predicts the dispersion trend of the extreme pressure and anti-wear agents in the solution based on the data fed back by the image monitoring system, and adjusts the temperature according to the dispersion trend. The specific implementation is similar to Step S220, but this time it is for the addition process of extreme pressure and anti-wear agents. Through the collaborative work of the image monitoring system and the neural network model, the dispersion state of the extreme pressure and anti-wear agents in the solution is monitored and adjusted in real time. The core steps of Step S240 are similar to S221 to S227 in Step S220, except that the object of concern changes from the emulsifier to the extreme pressure and anti-wear agent, with the aim of ensuring that it can be evenly dispersed in the solution to achieve the best lubrication and anti-wear effects.

[0093] Step S250: After the addition of the extreme pressure and anti-wear agents is completed, the solution temperature is adjusted to the third set temperature range. First, the third set temperature range needs to be determined. At the same time, according to the physical properties of the extreme pressure and anti-wear agents (such as solubility, thermal stability, viscosity, etc.), a suitable temperature range needs to be determined. It should be noted that the extreme pressure and anti-wear agents are added at a lower temperature to prevent uneven dispersion caused by rapid cooling. Considering the dispersion and stability of the extreme pressure and anti-wear agents in the solution, as well as the temperature requirements of subsequent steps, an optimal temperature range is determined. Assuming that the optimal dispersion temperature range of the extreme pressure and anti-wear agents is 40°C to 50°C, this range can be selected as the third set temperature range.

[0094] Regarding Step S300:

[0095] Step S300 is to add low-carbon preservatives and corrosion inhibitors on the basis of having already added environmentally friendly emulsifiers and extreme pressure and anti-wear agents, and adjust the temperature through PID control to ensure that the low-carbon preservatives and corrosion inhibitor additives are evenly dispersed in the solution, and finally adjust the solution temperature to room temperature. The specific implementation is as follows:

[0096] Step S310: According to the formulation requirements of the metalworking fluid, determine the types of low-carbon preservatives and corrosion inhibitors to be added, accurately weigh the required preservatives and corrosion inhibitors, and prepare the addition equipment.

[0097] Step S320: According to the physical properties of the preservatives and corrosion inhibitors (such as solubility, thermal stability, viscosity, etc.), determine the temperature range required during the addition process. Assuming that the optimal dispersion temperature range of the preservatives and corrosion inhibitors is 30°C to 40°C, this range can be selected as the temperature setting during the addition process.

[0098] Step S330: Conduct temperature control according to the temperature range set in Step S320; simultaneously add the weighed preservative and corrosion inhibitor into the solution; during the addition process, ensure that the additives are evenly dispersed in the solution through a stirring device; monitor the temperature of the solution in real time through a temperature sensor to ensure that the temperature remains within the set range;

[0099] Step S340: The PID controller automatically adjusts the power of the heating or cooling device according to the real-time temperature data fed back by the temperature sensor to ensure that the temperature is stable within the set range; if the temperature sensor detects that the solution temperature is below 30°C, the PID controller will increase the heating power; if the temperature exceeds 40°C, the PID controller will reduce the heating power or start the cooling device;

[0100] Step S350: After the preservative and corrosion inhibitor are completely added and evenly dispersed, stop the heating device; start the cooling device to gradually reduce the solution temperature to normal temperature (room temperature, usually 20°C to 25°C); continue to use the PID controller to ensure a stable temperature change during the cooling process and avoid the solution from stratifying or the additives from failing due to a sharp drop in temperature; assuming the room temperature is 25°C, the PID controller will gradually reduce the heating power and start the cooling device according to the feedback of the temperature sensor to ensure that the solution temperature slowly drops to 25°C.

[0101] Through Step S300, it can be ensured that during the process of adding the low-carbon preservative and corrosion inhibitor, the solution temperature is precisely adjusted to the set range and finally reduced to normal temperature; this process not only improves the dispersibility and stability of the preservative and corrosion inhibitor in the solution, but also ensures that the metalworking fluid has good rust prevention and corrosion protection properties; through PID control and real-time temperature monitoring, the temperature can be precisely controlled to avoid the failure of additives or the stratification of the solution caused by temperature fluctuations, meeting the requirements of low-carbon environmental protection.

[0102] Regarding Step S400:

[0103] The goal of Step S400 is to perform normal temperature control and complete the addition of auxiliary additives on the basis of having already added the environmentally friendly emulsifier, extreme pressure anti-wear agent, low-carbon preservative and corrosion inhibitor, as follows:

[0104] Select appropriate auxiliary additives according to the formulation requirements of the metalworking fluid; these additives may include antioxidants, defoamers, rust inhibitors, etc. to further improve the performance of the working fluid;

[0105] Step S410: Select appropriate auxiliary additives. According to the formulation requirements of the metalworking fluid, select appropriate auxiliary additives; the auxiliary additives include antioxidants, defoamers, rust inhibitors, etc. to further improve the performance of the working fluid, accurately weigh the required auxiliary additives, and prepare the adding equipment;

[0106] Step S420: Determine the normal temperature range, generally between 20°C and 25°C, and ensure that the solution is within this temperature range when adding the auxiliary additive to avoid adverse effects of temperature fluctuations on the dispersibility and performance of the additive. Assuming the room temperature is 25°C, the range of 20°C to 25°C can be selected as the normal temperature control range.

[0107] Step S430: Ensure that the PID controller is in working condition and perform temperature control according to the set normal temperature range. Add the weighed auxiliary additive to the solution. During the addition process, ensure that the additive is evenly dispersed in the solution through a stirring device. Real-time monitor the temperature of the solution through a temperature sensor to ensure that the temperature remains within the normal temperature range.

[0108] Step S440: The PID controller automatically adjusts the power of the heating or cooling device according to the real-time temperature data fed back by the temperature sensor to ensure that the temperature is stable within the normal temperature range. If the temperature sensor detects that the solution temperature is below 20°C, the PID controller will increase the heating power. If the temperature exceeds 25°C, the PID controller will reduce the heating power or start the cooling device.

[0109] Step S450: After the auxiliary additive is completely added and evenly dispersed, ensure that the solution temperature is stable within the normal temperature range for a certain period of time, usually 15 to 30 minutes, to ensure that all additives are fully mixed. Assuming the normal temperature range is 20°C to 25°C, the PID controller will ensure that the temperature is stable within this range for 30 minutes.

[0110] Step S460: Verify the uniform dispersion of the auxiliary additive in the solution through sampling and testing. A microscope or other testing equipment can be used for inspection. Record the temperature change curve and the final temperature data during the addition process to ensure the traceability and quality control of the process. After sampling, use a microscope to check the dispersion of the auxiliary additive in the solution to ensure its uniform dispersion.

[0111] In step S400, by selecting and adding auxiliary additives such as antioxidants, defoamers, and rust inhibitors, the antioxidant, anti-foaming, and rust prevention properties of the machining fluid can be significantly improved, thereby extending the service life of the machining fluid, improving the processing efficiency and product quality. The normal temperature range (20°C to 25°C) is clearly specified in step S400, and precise temperature control is carried out through the PID controller, which helps to ensure that the additive can be evenly dispersed when added, avoiding the influence of temperature fluctuations on the dispersibility and performance of the additive. The use of the PID controller and temperature sensor for real-time monitoring and automatic adjustment realizes the automation and intelligence of temperature control, not only improving the production efficiency but also reducing the errors caused by human intervention, ensuring the consistency and stability of the machining fluid preparation process. Recording the temperature change curve and the final temperature data during the addition process, as well as the sampling and testing results, helps to achieve the traceability and quality control of the process.

[0112] The above are only the preferred embodiments of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the technical principle of the present invention, several improvements and modifications can be made, and these improvements and modifications should also be regarded as the protection scope of the present invention.

Claims

1. A method for dynamically adjusting the temperature of an ester-based metalworking fluid, characterized in that: The ester-based metalworking fluid includes a low-carbon ester base oil, an environmentally friendly emulsifier, an extreme pressure anti-wear agent, a low-carbon preservative, a corrosion inhibitor, and auxiliary additives. The temperature dynamic adjustment method includes: Setting a basic heating power for the low-carbon ester base oil, and heating the low-carbon ester base oil to a first set temperature range through PID control; Load the neural network model into the control system and initialize the image monitoring device; According to the first set temperature range and the emulsifier addition speed, the monitoring frequency of the image monitoring system is set; Based on the monitoring frequency, a microscopic image of the liquid after adding the environmentally friendly emulsifier is obtained in real time through an image monitoring system; Perform feature recognition on liquid microscopic images to obtain a feature set of dispersed phase particles; Inputting the dispersed phase particle feature set into a pre-built neural network model to obtain a dispersion indication result; Calculate the dispersion fluctuation vector between the dispersion indication results obtained from two adjacent monitoring operations, wherein the dispersion fluctuation vector is the dispersion indication result obtained from the latest monitoring operation minus the dispersion indication result obtained from the previous monitoring operation; the dispersion fluctuation vector includes the fluctuation amount and the fluctuation direction; Traversing the dispersed wave vector in a pre-built emulsified temperature control data space to obtain a temperature adjustment vector; the temperature adjustment vector includes a temperature adjustment amount and a temperature adjustment direction; Dynamically adjust the temperature according to the temperature adjustment vector; After the addition of the environmentally friendly emulsifier is completed, the solution temperature is adjusted to a second set temperature range; The extreme pressure anti-wear agent is added, and during the process, the distribution state of the extreme pressure anti-wear agent in the solution is detected in real time by an image monitoring system, the neural network model predicts the dispersion trend of the extreme pressure anti-wear agent in the solution according to the data fed back by the image monitoring system, and the temperature is adjusted according to the dispersion trend; After the extreme pressure anti-wear agent is added, the solution temperature is adjusted to a third set temperature range; The low-carbon preservative and corrosion inhibitor are added at the same time, and the temperature is adjusted by PID control during the addition process, and the temperature is controlled to reach room temperature after the addition is completed; Perform normal temperature control and complete the temperature control of adding auxiliary additives.

2. A method for dynamically adjusting the temperature of an ester-based metalworking fluid according to claim 1, characterized in that: The basic heating power is set for the low-carbon ester base oil, and the low-carbon ester base oil is heated to a first set temperature range through PID control, including: Determine the first set temperature range according to the physical properties and process requirements of the low-carbon ester base oil; and extract the heating time requirement corresponding to the first set temperature range from the process requirements; Calculating the basic heating power based on the first set temperature range and the heating time requirement; Debugging the proportional, integral and differential parameters of the PID controller, monitoring the temperature of the low-carbon ester base oil in real time through a temperature sensor, and feeding back the real-time monitored temperature to the PID controller; The heating device is turned on, and according to the instruction of the PID controller, the base oil is gradually heated to the first set temperature range.

3. A method for dynamically adjusting the temperature of an ester-based metalworking fluid according to claim 2, characterized in that: The proportional, integral and differential parameters of the PID controller are tuned using either the empirical method, the Ziegler-Nichols method or an automatic tuning algorithm.

4. The method for dynamically adjusting the temperature of an ester-based metalworking fluid according to claim 1, characterized in that: The dispersed phase particle feature set includes particle size distribution, average particle size and dispersion uniformity.

5. A method for dynamically adjusting the temperature of an ester-based metalworking fluid according to claim 4, characterized in that: The calculation formula of the dispersion indication result is: ； Where P represents the dispersion index result, n(r) represents the number of dispersed phase particles with a particle size of r, N represents the total number of dispersed phase particles, and R i represents the diameter of the ith dispersed phase particle, m and n represent the number of rows and columns of the grid into which the image is divided, respectively; N ij represents the number of particles in the grid of row i and column j; It represents the average particle size of all dispersed phase particles; , and They represent the weight coefficients corresponding to particle size distribution, average particle size and dispersion uniformity respectively.

6. The method for dynamically adjusting the temperature of an ester-based metalworking fluid according to claim 1, characterized in that: The setting factors of the second set temperature range include: the thermal stability of the environmentally friendly emulsifier, the optimal dispersion temperature of the extreme pressure anti-wear agent and the chemical balance of the solution.

7. A method for dynamically adjusting the temperature of an ester-based metalworking fluid according to claim 1, characterized in that: The low-carbon preservative and corrosion inhibitor are added at the same time, and the temperature is adjusted by PID control during the addition process. After the addition is completed, the temperature is controlled to reach room temperature, including: According to the formula requirements of the metalworking fluid, determine the type of low-carbon preservative and corrosion inhibitor to be added, weigh the required preservative and corrosion inhibitor, and prepare to add the equipment; Determine the temperature range required during the addition process based on the determined physical properties of the preservatives and corrosion inhibitors; The temperature is controlled according to the temperature range required during the addition process; the weighed preservative and corrosion inhibitor are added to the solution at the same time; during the addition process, the temperature of the solution is monitored in real time by a temperature sensor and fed back to the PID controller; The PID controller automatically adjusts the power of the heating equipment according to the real-time temperature data fed back by the temperature sensor; After the preservatives and corrosion inhibitors are completely added and evenly dispersed, stop the heating equipment; start the cooling equipment to gradually reduce the solution temperature to the set temperature; during the cooling process, continue to use the PID controller to ensure a smooth temperature change during the cooling process.

8. The method for dynamically adjusting the temperature of an ester-based metalworking fluid according to claim 1, characterized in that: The auxiliary additives include at least one of an antioxidant, a defoaming agent and a rust inhibitor.

Images