Long-acting stress-resistant titanium-copper foil material for VCM elastic sheet and preparation method of long-acting stress-resistant titanium-copper foil material

Abstract

The invention relates to the technical field of alloy processing, in particular to a long-acting stress-resistant titanium-copper foil material for a VCM elastic piece and a preparation method of the long-acting stress-resistant titanium-copper foil material. The preparation method comprises the following steps that firstly, raw materials including 50%-70% of titanium, 40%-28% of copper, 8%-1% of nickel, 1%-0.5% of aluminum and 1%-0.5% of phosphorus are weighed according to the mass percent; 2, the raw materials are put into a smelting furnace to be melted, and liquid melt is obtained; thirdly, the melt is poured into a casting mold for casting, and a blank is obtained; in order to solve the residual stress problem of the titanium-copper alloy foil, the thickness and temperature changes of the material after each rolling are recorded in the preparation process, the machining parameters of next rolling can be calculated, and the performance and machining efficiency of the material can be improved; and then the machining parameters of next rolling are optimized based on the historical data and the machining parameters of current rolling through the parameter prediction model, the parameter adjustment effect can be effectively improved, the stability of the rolling process and the product quality are ensured, and then the overall production efficiency is improved.

Description

Technical Field

[0001] The invention relates to the technical field of alloy processing, and in particular to a long-lasting stress-resistant titanium copper foil material for VCM shrapnel and a preparation method thereof. Background Art

[0002] VCM shrapnel is a key component used in voice coil motors. It mainly plays the role of transmitting driving force and maintaining the stability of the motor structure. Traditional VCM shrapnel materials are mainly made of copper-based alloys. With copper as the main element, other metal or non-metal elements are added to improve or adjust its performance, such as strength, conductivity, corrosion resistance, etc.

[0003] After searching, Chinese patent number CN202411408883.X discloses a high conductivity beryllium copper foil for VCM shrapnel, which includes the following components by mass percentage: Be: 0.15%-0.5%; Co: 0.35%-0.6%; Re: 0.1%-0.3%; Ni+Co>0.2%; the balance is Cu. This scheme improves the strength, hardness and conductivity of the alloy by adding appropriate amounts of beryllium, cobalt, nickel and rare earth elements to the copper alloy. The alloy has a good aging hardening effect, so it has high strength, hardness and elastic limit after heat treatment. In the preparation process of high conductivity beryllium copper foil, through a detailed preparation method, and using a high-precision rolling mill to ensure that its thickness is between 0.045mm-0.08mm, it can well meet the requirements of manufacturing VCM shrapnel. It is a new alloy material with excellent comprehensive performance.

[0004] In the above scheme, although the strength, hardness and conductivity of the alloy are improved by adding appropriate amounts of beryllium, cobalt, nickel and rare earth elements to the copper alloy. However, in the preparation process of beryllium copper foil, because the titanium copper foil is synthesized and processed by multiple metals, the complexity of the alloy system is increased. The solubility, diffusion behavior and reactivity of different metal materials in the copper matrix are different. The distribution and interaction of these elements in the alloy will affect the phase structure and grain morphology of the alloy. Therefore, in the preparation process, improper control of processing parameters will lead to insufficient grain deformation or excessive recrystallization of the titanium copper foil, thereby affecting the uniformity of the microstructure, such as different grain sizes, holes or inclusions. These defects may cause stress concentration, thereby reducing the stress resistance of the material; in addition, residual stress may be introduced into the titanium copper foil during processing. If these stresses are not properly eliminated, they may affect the long-term performance of the titanium copper foil.

[0005] Therefore, a long-lasting stress-resistant titanium copper foil material for VCM shrapnel and a preparation method thereof are proposed to solve the above-mentioned problems. Summary of the invention

[0006] Technical issues solved In view of the above-mentioned shortcomings of the prior art, the present invention provides a long-lasting stress-resistant titanium-copper foil for VCM shrapnel and a preparation method thereof, which can effectively solve the problems in the prior art that improper control of processing parameters of the titanium-copper foil will affect the uniformity of its microstructure, and residual stress will be introduced during the processing process, affecting the long-term stress resistance performance of the titanium-copper foil.

[0007] Technical Solution To achieve the above objectives, the present invention is implemented through the following technical solutions: The present invention provides a method for preparing a long-lasting stress-resistant titanium copper foil for a VCM shrapnel, comprising the following steps: Step 1: Weigh the raw materials by mass percentage, including 50%-70% titanium, 40%-28% copper, 8%-1% nickel, 1%-0.5% aluminum, and 1%-0.5% phosphorus; Step 2: Put the raw materials into a furnace for melting to obtain a liquid melt; Step 3: pouring the melt into a casting mold for casting to obtain a blank; Step 4: heat treat the blank and then cool it down; Step 5: Roll the billet again, and record the thickness and temperature changes of the billet after each rolling; Step 6: Input the thickness and temperature changes of the billet into the pre-built parameter adjustment model to obtain the processing parameters for the next rolling; Step 7: Input the processing parameters into the pre-trained prediction model to obtain the processing optimization parameters for the next rolling of the billet; the calculation formula of the parameter prediction model is: ; In the formula, To optimize the processing parameters, is the index of the processing parameters; is the number of decision trees; Indicates The predicted value of the decision tree; Step 8: Repeat steps 6 and 7 until the blank forms a titanium copper foil of target size.

[0008] Furthermore, the method of melting in the furnace in step 2 includes: Reduce the internal gas pressure of the furnace to below 0.01Pa; preheat the raw materials to 300℃ and put them into the furnace; heat the furnace from room temperature to 800℃ for 30 minutes; then increase the temperature from 800℃ to 1500℃ for 20 minutes; after reaching 1500℃ in the furnace, maintain the temperature for 10-15 minutes; start the stirring device when the furnace reaches 1450℃, set the stirring rate to 200-300RPM, and the stirring time is 30 minutes.

[0009] Furthermore, the casting method in step three includes: The pouring flow rate of the melt into the mold does not exceed 5 cm / s; the melt in the mold is stirred during pouring, the stirring method is spiral stirring, the stirring rate is set to 200-100 RPM, and the stirring time is 5 minutes; after the melt is poured, it begins to cool to form a billet.

[0010] Furthermore, the cooling method includes: When the melt is poured out of the furnace, it is cooled naturally at a cooling rate of 5°C / h for 20 hours until the surface temperature of the billet drops to 100°C. A water cooling pipe is set on the surface of the billet, the water temperature is set at 20°C-30°C, the water inlet flow rate is 1L / min, and the water cooling duration is 10 hours until the temperature of the melt drops to room temperature to form a billet.

[0011] Furthermore, the method of cooling the blank after heat treatment in step 4 includes: placing the blank into an electric furnace, setting the temperature of the electric furnace to 700°C, and maintaining this temperature for 4 hours, and then slowly cooling the blank from 700°C to room temperature at a rate of 50°C per hour.

[0012] Furthermore, the method of rolling the blank in step 5 includes: The rolling temperature of the rolling mill is set to 300℃-500℃, and the rolling speed is set to 15mm / S; the thickness reduction of the billet is controlled within 3mm during each rolling; after every 4 rollings, the billet is sent to the annealing furnace for heat treatment; the parameters of the annealing furnace heat treatment are: heating temperature is 500℃, heating rate is 5-10℃ / min; keep the billet at 500℃ for 1h, and cool the billet naturally to room temperature.

[0013] Furthermore, the construction method of the parameter adjustment model in step 6 includes: Define the variable parameters of the billet during the rolling process, including: billet thickness ; Billet temperature ; Initial thickness of blank ; Rolling speed ; Rolling force Roller gap size ; Calculate the thickness change for each rolling pass: ; In the formula, represents the thickness of the billet after the nth rolling, Indicates the billet thickness recorded after n-1 rolling passes; Adjust the next rolling temperature according to the temperature after rolling. The calculation formula is: ; In the formula, Indicates the billet temperature after the nth rolling; Indicates the billet temperature after the n+1th rolling; Indicates the temperature drop; The rolling speed is adjusted according to the thickness change and temperature change of the billet. The calculation formula is: ; In the formula, Indicates the rolling speed of the nth time; Indicates the rolling speed of the n+1th time; The rolling force is calculated according to the thickness of the billet and the rolling speed. The calculation formula is: ; In the formula, is the force required for the nth rolling, is the material constant; Adjust the roll gap size according to the thickness of the blank and the pass distribution. The calculation formula is: ; In the formula, Indicates the roll gap size of the nth rolling; Indicates the adjustment amount of the roller gap size; Indicates the size of the roller gap at the n+1th time; ; In the formula, is the adjustment factor; Represents the average strain value of the material; Indicates the maximum strain value acceptable to the material; The pass distribution is adjusted according to the rolling times and thickness changes of the billet. The calculation formula is: ; In the formula, Indicates the reduction in billet thickness during the nth rolling; Indicates the current rolling number.

[0014] Furthermore, the training method of the prediction model in step seven includes: Define the random forest model as the basic structure of the parameter prediction model, collect historical processing parameters in the rolling process to build a training set , 70% of which are training sets , 30% is the test set ; Standardize the processing parameters and extract the key features; Set the initial parameters, including: the number of decision trees and maximum depth ; Define the feature matrix and the target variable ; From the training set Randomly extract samples from the feature matrix To create multiple different decision trees; repeatedly build multiple decision trees until the stopping criteria are met, and merge all the built decision trees into a forest. The merge expression is ; In the formula, is the indicator function, which is used to count each decision tree for each possible category vote; Indicates Tree pair samples The prediction results; is a function that finds the category that maximizes the expression in parentheses ; Define the mean square error of the parameter prediction model ;In the formula For the test set The number of samples in is the actual value of the i-th sample, is the predicted value of the i-th sample; Define the absolute error of the parameter prediction model .

[0015] Furthermore, when constructing each node of the decision tree, a specific number of features are randomly selected. , evaluate the features The ability to calculate the characteristics at the optimal cutting point The purity loss of the partition is used to find the best partition point; the evaluation method is: ; In the formula, is the Gini impurity value, used to quantify the training set The impurity range is , where 0 means completely pure, and close to 1 means a high degree of impurity; Represents the total number of categories in the dataset; Indicates category In the training set The ratio is calculated as: ,in Yes Category The number of samples, Is the training set Total number of samples in represents the sum of the squared probabilities of all categories; ; In the formula, In a given feature Under the condition of The Gini impurity value of It is a feature The set of all possible values, Representation characteristics One possible value of ; Indicated in the feature The value of When the training set All samples A subset of It is a subset The number of samples; Is the training set The total number of samples; select features So that: ,in, is the minimum value of Gini impurity after partitioning; Represents from the set Select the smallest Gini impurity value.

[0016] A long-lasting stress-resistant titanium copper foil material for VCM shrapnel prepared by any of the above methods.

[0017] Beneficial Effects Compared with the prior art, the technical solution provided by the present invention has the following beneficial effects: This solution improves the long-term stress resistance of the product by adding appropriate amounts of titanium, nickel, aluminum, and phosphorus elements to the copper alloy. In order to address the residual stress problem of titanium-copper alloy foil, the thickness and temperature changes of the material after each rolling can be recorded during the preparation process to calculate the processing parameters for the next rolling, which provides a scientific basis for optimizing the rolling process and helps to improve the performance and processing efficiency of the material. The parameter prediction model is then used to optimize the processing parameters for the next rolling based on historical data and the current rolling processing parameters, which can effectively improve the effect of parameter adjustment, ensure the stability of the rolling process and product quality, and thus improve overall production efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0019] Figure 1 The figure is a schematic diagram of the process of the preparation method in Example 1 of the present invention. DETAILED DESCRIPTION

[0020] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0021] The present invention will be further described below in conjunction with the embodiments. Embodiment 1:

[0022] See attached Figure 1 A method for preparing a long-lasting stress-resistant titanium copper foil for VCM shrapnel comprises the following steps: Step 1: Weigh the raw materials by mass percentage, including 50%-70% titanium (Ti), 40%-28% copper (Cu), 8%-1% nickel (Ni), 1%-0.5% aluminum (AI), and 1%-0.5% phosphorus (P); among them, ensure that the purity of titanium reaches more than 99.5%, the purity of copper reaches more than 99.9%, and the purity of nickel, aluminum, and phosphorus is not less than 99.95%; Step 2: Put titanium, copper, nickel, aluminum and phosphorus into a melting furnace for melting to obtain a liquid melt; Step 3: pouring the melt into a casting mold for casting to obtain a blank; Step 4: heat-treat the blank and then cool it down to eliminate the grain stress of the blank; Step 5: Roll the billet again, and record the thickness and temperature changes of the billet after each rolling; Step 6: Input the thickness and temperature changes of the billet into the pre-built parameter adjustment model to obtain the processing parameters for the next rolling; Step 7: Input the processing parameters into the pre-trained prediction model to obtain the processing optimization parameters until the blank forms a titanium copper foil of target size; Step 8: Repeat steps 6 and 7 until the blank forms a titanium copper foil of target size.

[0023] Step 2 is the smelting process, which is a crucial step in the preparation of titanium-copper alloy foil. It directly determines the microstructure and properties of the alloy. In step 2, titanium, copper and alloying elements (nickel, aluminum, phosphorus) are melted in a high-temperature vacuum furnace to ensure the uniformity of the alloy composition and the overall quality. The smelting methods include: First of all, before the raw materials are put into the high-temperature vacuum furnace, it is necessary to ensure that the raw materials are dry and clean to reduce the impact of moisture and impurities. At the same time, when the raw materials are put into the high-temperature vacuum furnace, it is necessary to reduce the entry of ambient air to avoid the entry of impurities in the ambient air.

[0024] Then start the vacuum system to reduce the internal air pressure of the furnace to below 0.01Pa to prevent the infiltrated oxygen from causing metal oxidation and affecting the performance of the material.

[0025] Then start the heating system and heat the furnace to 1300℃-1500℃. Within this temperature range, the melting points of titanium and copper are always stable, which helps to ensure the full melting and combination of the components. In the process of heating up, adjust the heating rate to avoid the generation of thermal stress caused by too fast temperature change. Specifically, before the raw materials are put into the furnace, preheat them to 300℃ to remove moisture and other volatiles on the surface. The heating stage is divided into two stages: the first stage: heating the furnace from room temperature (about 20℃) to 800℃, and the second stage: heating the furnace from room temperature (about 20℃) to 800℃. The heating time is 30 minutes, and the heating rate is controlled at 25-27℃ / min to avoid thermal stress caused by rapid heating; the second stage: from 800℃ to 1500℃, the heating time is 20 minutes, and the heating rate is controlled at 30-35℃ / min to ensure that the melting temperature can be reached smoothly but still within the safe range; after reaching 1500℃ in the furnace, maintain the temperature for 10-15 minutes to ensure that all components are completely melted, which is conducive to the full mixing of alloy elements and reduces the formation of precipitates and gases.

[0026] At the same time, the temperature in the furnace reaches 1450°C, and after ensuring that all alloy elements are completely melted, the stirring device is started, the stirring rate is set to 200-300RPM, and the stirring time is 30 minutes to ensure that all elements in the melt are fully mixed without introducing too many bubbles, while eliminating possible precipitates and irregular material distribution; at the same time, the stirring method adopts axial flow stirring design to achieve uniform flow and promote thorough mixing of components in the melt.

[0027] Through the above specific processing parameter design, the heating process of titanium-copper alloy can be effectively controlled, avoiding thermal stress caused by rapid temperature changes, forming a homogenous melt, ensuring the uniform dispersion of various elements in the alloy, reducing defects in the subsequent cooling process, and laying a good foundation for subsequent casting and processing.

[0028] Step three is the casting process, which is a crucial link in the manufacturing process of titanium copper alloy foil and directly affects the microstructure and performance of the final product. The casting process includes: First, the casting mold should be made of aluminum or graphite. Both materials have excellent thermal conductivity and high temperature resistance, and can withstand the high temperature of the melt without deformation or melting. At the same time, the casting mold should be preheated to 50℃-80℃ before use to reduce the thermal shock when the melt is poured in and prevent the casting mold from breaking due to excessive temperature difference. Before pouring the melt into the casting mold, the casting area needs to be kept clean to prevent impurities and dust from entering the casting mold to reduce the formation of pores or debris. The melt is poured into the mold for cooling, and the pouring flow rate is 5 cm / s, which ensures the uniform flow and filling of the melt in the mold, reduces the generation of defects and bubbles, helps to improve the quality of the billet, protects the mold and improves the mechanical properties of the material; setting the pouring flow rate not exceeding 5 cm / s helps to ensure that the casting quality meets the expected standards while meeting production efficiency; and when the melt is poured, the melt in the mold is stirred, and the stirring method is spiral stirring, which can effectively stir the melt evenly in the mold, so that it can generate an upward flow when rotating, promote the flow and mixing of the melt, and ensure that the melt is evenly distributed in the entire mold; the stirring rate is set to 200-100 RPM, which is a relatively low speed, aiming to avoid the generation of too many bubbles and ensure the fluidity of the melt; the stirring time is 5 minutes, which ensures that the melt is fully mixed in the mold and avoids local unevenness caused by temperature changes; When the melt is completely poured into the mold, the melt begins to cool. The layered cooling adopted in this scheme can effectively control the cooling rate and temperature distribution of the blank, reduce the generation of residual stress and defects, and not only improve the overall quality of the blank, but also lay a good foundation for subsequent processing and heat treatment. Specifically: Initial air cooling: Pour the melt into a mold with a mesh structure to increase the contact area between the mold and the air, promote air circulation, and allow the billet surface to dissipate heat faster. The heat is dissipated to the surrounding environment through natural convection and radiation, and the temperature of the billet is gradually reduced. This slow cooling method effectively reduces the temperature gradient and avoids thermal stress concentration and cracks caused by rapid temperature changes. Especially for larger billets, the control of cooling speed is crucial. When the melt is poured out of the furnace, the temperature of the melt is 1500°C. At this temperature, the metal is in a liquid state and the cooling process begins. After casting, the surface temperature of the billet will drop rapidly, but the internal temperature is still high. In order to ensure that the internal temperature of the billet drops evenly and prevent stress concentration and cracks caused by excessive temperature gradients, a cooling rate of 5°C / h is selected to cool the melt. The cooling time is 20h until the surface temperature of the billet drops to 100°C. Layered water cooling: water cooling pipes are set on the surface of the billet, and water flows through these pipes to enhance the cooling effect. Water cooling can significantly speed up the cooling of the billet and avoid defects caused by uneven cooling. The water temperature is set at 20℃-30℃ to avoid overcooled water causing a sudden drop in the surface temperature of the billet, resulting in thermal stress concentration. The water inlet flow rate is 1L / min to ensure that the water flow is evenly distributed without causing excessive impact force, avoiding cracks or deformation on the billet surface. The water cooling lasts for 10 hours until the temperature of the billet drops to room temperature (about 20℃). The main purpose of this stage is to further reduce the temperature of the billet and ensure the temperature uniformity inside the billet. When the blank is cooled, at least 4 temperature sensors are set for monitoring to cover different areas of the blank, and the temperature fluctuation range should be controlled within ±5°C to ensure the quality of the blank and avoid defects caused by excessive temperature fluctuations; Finally, a dense and uniform alloy billet with a size of 300mm×300mm×100mm is obtained, reducing the overall defect rate.

[0029] Step 4 is the heat treatment process, which is an important post-processing process for castings during the casting process. Its purpose is to improve the intrinsic properties (mechanical properties and microstructure) of the blank. The heat treatment methods include: The blank is placed in an electric furnace to provide a stable heating environment for heat treatment. The temperature of the electric furnace is set to 700°C, allowing the blank to be heated at this temperature and maintained at this temperature for 4 hours. This period of time is to allow the material to be fully warmed, which helps to even out the temperature of each part of the material and ensure that the internal structure of the blank is recrystallized and changed. Then the blank is slowly cooled from 700°C to room temperature at a rate of 50°C per hour to prevent thermal stress and possible material cracking caused by excessive cooling. During the casting process, internal stress is usually generated in the billet due to temperature changes, uneven cooling rates and other reasons. Heat treatment provides a suitable environment to rearrange the atoms in the billet, eliminate the grain stress related to the cooling process, improve the uniformity of the grains, and then release these internal stresses, thereby improving the overall stability of the casting. After heat treatment, the recrystallized billet has a more uniform grain structure, thereby improving the tensile strength and fatigue strength of the material. It can also eliminate defects introduced during the casting process, such as microcracks and pores, so that the overall quality of the casting can be improved.

[0030] Step five is the rolling process, which applies pressure to make the billet thinner, improve its ductility, and make it easier to process into the desired shape and size; and through plastic deformation, the grain structure of the billet changes, which leads to an increase in dislocations inside the billet, increases the strength of the billet, and improves its hardness and wear resistance; the rolling methods include: The rolling temperature of the rolling mill is set at 300℃-500℃ to ensure the appropriate plasticity of the billet during the rolling process; the rolling speed is set at 15mm / S to ensure the appropriate strain rate and avoid damage caused by overheating of the material; the initial roller gap of the rolling mill is set to 5mm to ensure that the billet can be smoothly rolled between the rollers to achieve the required forming effect, and adjusted according to the fluidity of the billet and the thickness after rolling; each time the billet is rolled, the thickness reduction is controlled within 3mm to ensure that the thickness is gradually reduced without generating excessive stress; during the rolling process, the billet enters annealing after every 4 rollings. In the return stage, the billet is sent to the annealing furnace for heat treatment; the parameters of the heat treatment in the return stage are: the temperature of the annealing furnace is set to 500℃, which is generally considered to be the appropriate annealing temperature for titanium-copper alloys, which helps to achieve a good recrystallization effect; the heating rate is 5-10℃ / min to avoid thermal stress in the billet due to rapid temperature changes; after reaching 500℃ in the annealing furnace, the billet is kept at this temperature for 1h to ensure sufficient grain recrystallization and stress release; after the annealing heat treatment is completed, the billet is naturally cooled to room temperature, and water or forced cooling should be avoided to prevent new residual stress caused by excessive temperature difference.

[0031] Record the thickness and temperature changes of the material after each rolling, input them into the pre-built parameter adjustment model, and obtain the processing parameters for the next rolling; The construction method of the parameter adjustment model includes: defining the variable parameters of the billet during the rolling process, including: billet thickness (Unit: mm); Billet temperature (Unit: °C); Initial thickness of blank (Unit: mm); rolling speed (Unit: mm / s); rolling force (Unit: N); Roller gap size (Unit: mm); Based on the above parameters, calculate the thickness change for each rolling: In the formula, represents the thickness of the billet after the nth rolling, Indicates the billet thickness recorded after n-1 rolling is completed (i.e. the billet thickness after the previous rolling is completed); Adjust the next rolling temperature according to the temperature after rolling. The calculation formula is: ; In the formula, Indicates the billet temperature after the nth rolling; The billet temperature after the n+1th rolling is calculated based on the billet temperature after the nth rolling. After adjustment, it is the temperature set for the next rolling; It indicates the temperature drop, which is a preset value estimated according to the properties of the billet and the variable parameters in the rolling process; Is a conditional statement used to determine the current temperature Is it over 500℃? If the condition is true, the calculation of the first case will be performed (i.e. the temperature drop needs to be subtracted ), the temperature target for the next rolling will be reduced according to the current temperature value to avoid excessive thermal deformation or damage of the blank due to excessive temperature; Indicates that if the condition is not met, the billet temperature for the next rolling Maintain the current rolling billet temperature The same means that no adjustment is required within the safe temperature range. Through this formula, the target temperature of the next rolling can be reasonably adjusted according to the temperature of the material after each rolling. If the current temperature is too high, the preset temperature drop amount is subtracted. To lower the target temperature to ensure the safety and effectiveness of the rolling operation. On the contrary, when the temperature is within the safe range, there is no need to adjust the current temperature to ensure the excellent formability of the material. This process helps to optimize the rolling process and protect the material properties and processing effects; The rolling speed is adjusted according to the thickness change and temperature change of the billet. The calculation formula is: ; In the formula, Indicates the rolling speed of the nth time; Indicates the rolling speed for the n+1th time, which is based on the thickness of the billet after the current rolling. and billet temperature After adjustment, it is the speed of the next rolling; It is a conditional statement used to determine the current thickness of the blank Is it smaller than the thickness of the billet in the previous rolling? , and the current billet temperature Is it lower than 500℃? If these two conditions are met at the same time, it means that the thickness of the billet is reduced during the rolling process and the temperature is appropriate, indicating that the fluidity of the billet during the forming process is good, and the rolling speed can be appropriately increased. ; Rolling speed Adjust the formula. When the above conditions are met, the next rolling speed According to the current thickness The thickness of the previous If the ratio is adjusted Comparison If the ratio is smaller than 1, it means the rolling speed Will be reduced accordingly to control the molding process and fluidity; another case is This is the second conditional statement, which is used to determine the current billet temperature after rolling. Whether it reaches or exceeds 500℃. If the condition is met, it indicates that the billet may face the risk of deformation due to excessive temperature, so the rolling speed needs to be reduced. , reduce the rolling speed The calculation formula is Slow down the rolling process by setting the next rolling speed to 80% of the current rolling speed to avoid excessive flow or damage of the billet due to high temperature; Indicates that when the above two conditions are not met, the current blank thickness No change and the billet temperature If the temperature does not exceed 500℃, the current rolling speed is maintained. unchanged, that is ; Through this formula, the speed of the next rolling is dynamically adjusted according to the thickness and temperature after each rolling. When the billet thickness decreases and the temperature is appropriate, the rolling speed is increased proportionally to improve the billet formability. When the billet temperature is too high, the rolling speed needs to be reduced to reduce the risk of deformation. If there are no such specific conditions, the current rolling speed is kept unchanged. This adjustment mechanism provides flexibility and security for the effect of the rolling process, helping to ensure the best processing performance of the billet under different working conditions; The rolling force is calculated according to the thickness of the billet and the rolling speed. The calculation formula is: ; In the formula, The force required for the nth rolling Degree is a material constant (i.e., the strength coefficient or material constant of the billet, usually determined by experiments), which is a parameter used to describe the ability of the billet to resist deformation during rolling. The rolling force required for plastic deformation is calculated by the thickness of the billet, the rolling speed and the material constant. Increasing the thickness will increase the rolling force accordingly, because thicker billets require more force to drive their deformation. Increasing the rolling speed will also lead to the need for higher rolling forces, because fast rolling requires the billet to complete deformation in a short time, which may increase flow resistance. The selection of the material constant value depends on the material properties. The appropriate strength coefficient helps to accurately calculate the rolling force, thereby providing support and guarantee for the entire rolling process. Adjust the roll gap size according to the thickness of the blank and the pass distribution. The calculation formula is: ; In the formula, Indicates the roll gap size of the nth rolling; Indicates the adjustment amount of the roll gap size, which determines the specific change range of the roll gap size during the rolling process; Indicates the size of the roller gap for the n+1th time, which is based on the current roller gap size and the adjustment amount of the roll gap size After adjustment, the roll gap size is set for the next rolling; the adjustment amount of the roll gap size is The calculation method is as follows: First, define the initial roll gap size , that is, the initial roll gap size is set to the initial thickness of the blank Half of the original roll gap means that in theory, the initial roll gap will leave enough space to allow the plastic deformation of the billet and enable effective rolling, and ensure that the billet can maintain uniform deformation and avoid excessive compression after rolling; ; In the formula, It is the adjustment coefficient used to control the roll gap size The sensitivity of the adjustment is usually a constant obtained from previous experimental data and is used to adjust the adjustment amount of the roll gap size. size; Indicates the average strain value of the material, usually obtained through experimental monitoring equipment, reflecting the degree of deformation of the billet during the rolling process, and can help evaluate whether there is a problem of uneven deformation; Indicates the maximum acceptable strain value of the material, which is a critical value determined by the material properties and rolling process parameters. When this value is reached or exceeded, it means that the deformation of the billet may exceed the safe range, which may cause product quality problems such as material rupture or excessive flow; Is a conditional statement used to determine the current average strain value Whether it exceeds the set maximum strain value If this condition is met, it means that the blank is over-deformed and adjustment measures need to be taken to avoid potential quality problems; the adjustment formula is: , that is, by adjusting the coefficient The difference between the strain The current roll gap size , which aims to adjust the roll gap size based on the current roll gap state and strain relief ; If the condition is not met, the average strain value No need to exceed the maximum strain value , it means that the deformation of the blank is within the safe range and there is no need to make adjustments. Therefore, the adjustment amount of the roll gap size is ; Through this formula, the thickness of the billet during rolling can be Flexible adjustment of the roll gap size of the rolling mill according to changing conditions To ensure the stability of the rolling process and the quality of the products; Adjust the pass distribution according to the rolling times and thickness changes of the billet (that is, reasonably distribute the billet thickness changes during the rolling process to each rolling). The calculation formula is: ; In the formula, It indicates the reduction of billet thickness in the nth rolling, that is, the change of billet thickness from initial thickness to current thickness in the current rolling process, reflecting the influence of rolling process on billet thickness; Indicates the current rolling times; by calculating the initial thickness of the billet and current billet thickness The difference between the two is used to determine the thickness reduction of the billet during each rolling process. ; Through this formula, the thickness reduction of the billet after N rolling times is calculated The average value of the rolling thickness determines the expected thickness change in each rolling process. The deformation of the billet is monitored by dynamic feedback, which helps to optimize the automated rolling process and improve the flexibility and quality control capability of billet processing. In summary, based on the thickness and temperature changes of the billet after each rolling, the processing parameters for the next rolling can be calculated, which provides a scientific basis for optimizing the rolling process and helps to improve the performance of the material and processing efficiency.

[0032] In the rolling process, the relationship between processing parameters is often complex. The physical properties of the billet will change at different thicknesses and temperatures. These changes not only affect the rolling effect, but also affect the performance of other parameters, resulting in differences between the processing parameters calculated by the parameter adjustment model and the actual situation. By inputting the processing parameters into the pre-trained parameter prediction model, the processing optimization parameters for the next rolling of the billet are obtained. Then, according to the processing optimization parameters for the next rolling of the billet, the billet is subsequently rolled until the billet forms the required titanium copper foil. By constructing a prediction model, the parameters for the next rolling can be accurately predicted based on historical data and the current rolling processing parameters, which can effectively improve the effect of parameter adjustment, ensure the stability of the rolling process and product quality, and thus improve overall production efficiency.

[0033] The training methods of parameter prediction models include: Define the random forest model as the basic structure of the parameter prediction model, collect historical data in the rolling process (i.e., the processing parameters of multiple rollings in the past) to build a training set , 70% of which are training sets , 30% is the test set ; Process the processing parameters, handle the missing values ​​and abnormal values ​​in the processing parameters, and standardize the processing parameters to make the features of different dimensions comparable; extract the key features of the processing parameters, including: Thickness change rate ; Temperature change rate , speed change rate and the ratio of rolling force to thickness ; Create a random forest regression model instance and set the initial parameters: the number of decision trees and maximum depth ; Define the feature matrix and the target variable ; Feature matrix Represents input data, which is a data structure containing multiple key features (i.e. variables), usually represented in the form of a two-dimensional array, where each row represents a sample and each column represents a feature; target variable is the output that the model needs to predict (i.e., processing optimization parameters), usually a one-dimensional array, and the feature matrix Medium Sample Number of corresponding; The feature matrix As input features, from the training set Randomly extract samples from the feature matrix To create multiple different decision trees; when building each node of the decision tree, a specific number of features are randomly selected , these features are evaluated based on the Gini impurity , these features are evaluated based on the Gini impurity The ability to calculate the best cutting point The purity loss of the partition is used to find the best partition point; the evaluation method is: ; In the formula, is the Gini impurity value, used to quantify the training set The impurity range is , where 0 means completely pure (only one category), and close to 1 means that the categories are more evenly distributed and have higher impurity; Represents the total number of categories in the data set, that is, how many different categories there are; Indicates category In the training set The ratio is calculated as: ,in Yes Category The number of samples, Is the training set Total number of samples in Represents the sum of the squared probabilities of all categories. This calculation can reflect the concentration of the category distribution. ; In the formula, In a given feature Under the condition of The Gini impurity value reflects the Conditional training set The lower the Gini impurity, the better the sample The higher the homogeneity of the sample (i.e. The probability of belonging to the same category is higher); It is a feature The set of all possible values, Representation characteristics One possible value of ; Indicated in the feature The value of When the training set All samples A subset of It is a subset The number of samples; Is the training set The total number of samples, that is ; Indicates that the feature is obtained The value of In the case of , the proportion of samples in the entire data set; feature The total Gini impurity minus the weighted Gini impurity of this feature can be used to evaluate the effect of selecting this feature. So that: ,in, It is the minimum value of Gini impurity after partitioning, which is used to measure the value of a certain feature. The training set after partitioning The smaller the value, the purer the training set after division. sample The higher the concentration in the same category, the better the evaluation effect of the division; Represents from the set Select the smallest Gini impurity value; Repeat the above process to build multiple decision trees until the stopping criteria, such as the maximum depth, are met. , the minimum number of samples or the information gain no longer increases significantly, that is, through a certain feature The degree to which the model impurity is reduced after data partitioning; All constructed decision trees are merged into a forest to predict the processing optimization parameters; the merged expression is ; In the formula, is the number of decision trees in the random forest; is the indicator function, which is used to count each decision tree for each possible category The vote, when Tree For the input sample The prediction result is equal to the category When , the value of this function is 1, and if they are not equal, it is 0; Indicates Tree pair samples The prediction result describes the output of each decision tree in the generated random forest; is a function that finds the category that maximizes the expression in parentheses , it will return a category with the most votes among all categories. Based on the majority voting principle, this process helps to select the most reliable prediction category; the formula is calculated by counting all decision trees for samples The voting results are collected and the category with the most votes is selected. As a final prediction; Based on the above content, the calculation formula of the parameter prediction model for the processing optimization parameters is: ; In the formula, is the final average predicted value, that is, the predicted prediction parameter, is the index of the processing parameters; This is a normalization factor that is calculated by dividing the sum of the outputs of all decision trees by the number of decision trees. , thereby calculating the average value and ensuring the final prediction result It is a representative value that can reflect the overall forecast trend; Indicates The predicted value of the decision tree; Define the mean square error of the parameter prediction model ;In the formula For the test set The number of samples in is the actual value of the i-th sample, is the predicted value of the i-th sample; Define the absolute error of the parameter prediction model .

[0034] Embodiment 2: Based on Example 1, this case proposes a long-lasting stress-resistant titanium-copper foil for VCM shrapnel, which is prepared by the preparation method of a long-lasting stress-resistant titanium-copper foil for VCM shrapnel in Example 1.

[0035] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements will not cause the essence of the corresponding technical solutions to deviate from the protection scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for preparing a long-lasting stress-resistant titanium copper foil for VCM shrapnel, characterized in that: The following steps are involved: Step 1: Weigh the raw materials by mass percentage, including 50%-70% titanium, 40%-28% copper, 8%-1% nickel, 1%-0.5% aluminum, and 1%-0.5% phosphorus; Step 2: Put the raw materials into a furnace for melting to obtain a liquid melt; Step 3: pouring the melt into a casting mold for casting to obtain a blank; Step 4: heat treat the blank and then cool it down; Step 5: Roll the billet again, and record the thickness and temperature changes of the billet after each rolling; Step 6: Input the thickness and temperature changes of the billet into the pre-built parameter adjustment model to obtain the processing parameters for the next rolling; Step 7: Input the processing parameters into the pre-trained prediction model to obtain the processing optimization parameters for the next rolling of the billet; the calculation formula of the parameter prediction model is: ; In the formula, To optimize the processing parameters, is the index of the processing parameters; is the number of decision trees; Indicates The predicted value of the decision tree; Step 8: Repeat steps 6 and 7 until the blank forms a titanium copper foil of target size.

2. The method for preparing a long-lasting stress-resistant titanium copper foil for VCM shrapnel according to claim 1, characterized in that: The method of melting in the furnace in step 2 includes: Reduce the internal gas pressure of the furnace to below 0.01Pa; preheat the raw materials to 300℃ and put them into the furnace; heat the furnace from room temperature to 800℃ for 30 minutes; then increase the temperature from 800℃ to 1500℃ for 20 minutes; after reaching 1500℃ in the furnace, maintain the temperature for 10-15 minutes; start the stirring device when the furnace reaches 1450℃, set the stirring rate to 200-300RPM, and the stirring time is 30 minutes.

3. The method for preparing a long-lasting stress-resistant titanium copper foil for VCM shrapnel according to claim 1, characterized in that: The casting method in step 3 includes: The pouring flow rate of the melt into the mold does not exceed 5 cm / s; the melt in the mold is stirred during pouring, the stirring method is spiral stirring, the stirring rate is set to 200-100 RPM, and the stirring time is 5 minutes; after the melt is poured, it begins to cool to form a billet.

4. The method for preparing a long-lasting stress-resistant titanium copper foil for VCM shrapnel according to claim 3, characterized in that: The cooling method includes: When the melt is poured out of the furnace, it is cooled naturally at a cooling rate of 5°C / h for 20 hours until the surface temperature of the billet drops to 100°C. A water cooling pipe is set on the surface of the billet, the water temperature is set at 20°C-30°C, the water inlet flow rate is 1L / min, and the water cooling duration is 10 hours until the temperature of the melt drops to room temperature to form a billet.

5. The method for preparing a long-lasting stress-resistant titanium copper foil for VCM shrapnel according to claim 1, characterized in that: The method of cooling the blank after heat treatment in step 4 includes: placing the blank into an electric furnace, setting the temperature of the electric furnace to 700°C, and maintaining the temperature for 4 hours, and then slowly cooling the blank from 700°C to room temperature at a rate of 50°C per hour.

6. The method for preparing a long-lasting stress-resistant titanium copper foil for VCM shrapnel according to claim 1, characterized in that: The method of rolling the blank in step 5 includes: The rolling temperature of the rolling mill is set to 300℃-500℃, and the rolling speed is set to 15mm / S; the thickness reduction of the billet is controlled within 3mm during each rolling; after every 4 rollings, the billet is sent to the annealing furnace for heat treatment; the parameters of the annealing furnace heat treatment are: heating temperature is 500℃, heating rate is 5-10℃ / min; keep the billet at 500℃ for 1h, and cool the billet naturally to room temperature.

7. The method for preparing a long-lasting stress-resistant titanium copper foil for VCM shrapnel according to claim 1, characterized in that: The method of constructing the parameter adjustment model in step 6 includes: Define the variable parameters of the billet during the rolling process, including: billet thickness ; Billet temperature ; Initial thickness of blank ; Rolling speed ; Rolling force Roller gap size ; Calculate the thickness change for each rolling pass: ; In the formula, represents the thickness of the billet after the nth rolling, Indicates the billet thickness recorded after n-1 rolling passes; Adjust the next rolling temperature according to the temperature after rolling. The calculation formula is: ; In the formula, Indicates the billet temperature after the nth rolling; Indicates the billet temperature after the n+1th rolling; Indicates the temperature drop; The rolling speed is adjusted according to the thickness change and temperature change of the billet. The calculation formula is: ; In the formula, Indicates the rolling speed of the nth time; Indicates the rolling speed of the n+1th time; The rolling force is calculated according to the thickness of the billet and the rolling speed. The calculation formula is: ; In the formula, is the force required for the nth rolling, is the material constant; Adjust the roll gap size according to the thickness of the blank and the pass distribution. The calculation formula is: ; In the formula, Indicates the roll gap size of the nth rolling; Indicates the adjustment amount of the roller gap size; Indicates the size of the roller gap at the n+1th time; ; In the formula, is the adjustment factor; Indicates the average strain value of the material; Indicates the maximum strain value acceptable to the material; The pass distribution is adjusted according to the rolling times and thickness changes of the billet. The calculation formula is: ; In the formula, Indicates the reduction in billet thickness during the nth rolling; Indicates the current rolling number.

8. The method for preparing a long-lasting stress-resistant titanium copper foil for VCM shrapnel according to claim 7, characterized in that: The training method of the prediction model in step 7 includes: Define the random forest model as the basic structure of the parameter prediction model, collect historical processing parameters in the rolling process to build a training set , 70% of which are training sets , 30% is the test set ; Standardize the processing parameters and extract the key features; Set the initial parameters, including: the number of decision trees and maximum depth ; Define the feature matrix and the target variable ; From the training set Randomly extract samples from the feature matrix To create multiple different decision trees; repeatedly build multiple decision trees until the stopping criteria are met, and merge all the built decision trees into a forest. The merge expression is ; In the formula, is the indicator function, which is used to count each decision tree for each possible category vote; Indicates Tree pair samples The prediction results; is a function that finds the category that maximizes the expression in parentheses ; Define the mean square error of the parameter prediction model ;In the formula For the test set The number of samples in is the actual value of the i-th sample, is the predicted value of the i-th sample; Define the absolute error of the parameter prediction model .

9. The method for preparing a long-lasting stress-resistant titanium copper foil for VCM shrapnel according to claim 8, characterized in that: When constructing each node of the decision tree, a specific number of features are randomly selected , evaluate the features The ability to calculate the characteristics at the optimal cutting point The purity loss of the partition is used to find the best partition point; the evaluation method is: ; In the formula, is the Gini impurity value, used to quantify the training set The impurity range is , where 0 means completely pure, and close to 1 means a high degree of impurity; Represents the total number of categories in the dataset; Indicates category In the training set The ratio is calculated as: ,in Yes Category The number of samples, Is the training set Total number of samples in represents the sum of the squared probabilities of all categories; ; In the formula, In a given feature Under the condition of The Gini impurity value of It is a feature The set of all possible values, Representation characteristics One possible value of ; Indicated in the feature The value of When the training set All samples A subset of Is a subset The number of samples; Is the training set The total number of samples; select features So that: ,in, is the minimum value of Gini impurity after partitioning; Represents from the set Select the smallest Gini impurity value.

10. A long-lasting stress-resistant titanium copper foil for VCM shrapnel prepared according to any one of claims 1 to 9.

Images