Hot extrusion control method for stainless steel pipe machining process

Abstract

The application provides a hot extrusion control method for a stainless steel pipe machining process, relates to the technical field of metal extrusion, and comprises the following steps: continuously heating control is performed, real-time temperature monitoring is performed, and temperature monitoring data is obtained; when a preset temperature interval is met, a temperature-pressure prediction model is input to obtain prediction pressure data; if a preset pressure interval is not met, continuously heating is performed until the preset pressure interval is met, and the temperature monitoring data after heating is taken as an initial temperature control parameter; initial speed control parameters are obtained based on a pressure-speed calibration table; extrusion control is performed, and pipe product quality is recorded; optimization is performed to optimize pipe product quality as a target, and optimized control parameter combinations are obtained; and hot extrusion optimization is performed. The application solves the technical problem that the parameter control of the traditional method for hot extrusion is not accurate enough, and parameter adjustment usually depends on past experience, resulting in poor machining quality of stainless steel pipes and low production efficiency.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of metal extrusion, and particularly relates to a hot extrusion control method for a stainless steel pipe processing technology. BACKGROUND

[0002] Hot extrusion is a common metal processing technology and is widely used in the stainless steel pipe industry. In the hot extrusion process, the metal blank is heated and extruded under pressure to obtain the desired shape and size of the product. However, traditional hot extrusion processing has some technical problems that limit product quality and production efficiency. On the one hand, traditional hot extrusion processing is not accurate enough in controlling various parameters, resulting in unstable product quality. On the other hand, traditional hot extrusion processing often requires a long debugging time and manual intervention, resulting in low production efficiency and being unable to meet the needs of large-scale production. SUMMARY

[0003] The present application provides a hot extrusion control method for a stainless steel pipe processing technology, aiming to solve the technical problem of poor product quality and low production efficiency caused by the inaccurate parameter control of traditional hot extrusion and the dependence on past experience for parameter adjustment.

[0004] In view of the above problems, the present application provides a hot extrusion control method for a stainless steel pipe processing technology.

[0005] In a first aspect, a hot extrusion control method for a stainless steel pipe machining process is provided. The method is applied to a hot extrusion control device including a heating unit and an extrusion unit. The method includes: after a target metal blank is delivered to the heating unit, activating the heating unit to perform continuous temperature increase heating control on the metal blank, and activating a temperature monitoring device of the heating unit to perform real-time temperature monitoring on the heating unit to obtain temperature monitoring data; when the temperature monitoring data meets a preset temperature interval, inputting the current temperature monitoring data into a temperature-pressure prediction model to perform pressure prediction and obtain predicted pressure data; if the predicted pressure data does not meet a preset pressure interval, continuously increasing the temperature until the predicted pressure data meets the preset pressure interval; when the predicted pressure data meets the preset pressure interval, using the temperature monitoring data after heating as an initial temperature control parameter and using the current predicted pressure data as an initial pressure control parameter; based on a pressure-velocity calibration table, matching the initial pressure control parameter with an extrusion speed to obtain an initial speed control parameter; delivering the target metal blank to the extrusion unit, performing extrusion control based on the initial pressure control parameter and the initial speed control parameter, recording a pipe product quality as a pre-extrusion control result; and optimizing the initial temperature control parameter, the initial pressure control parameter, and the initial speed control parameter to obtain an optimized control parameter combination, and performing hot extrusion optimization on the target metal blank based on the optimized control parameter combination.

[0006] In a second aspect, the application discloses a hot extrusion control system for a stainless steel pipe processing technology, which is applied to a hot extrusion control device including a heating unit and an extrusion unit, and is used for the hot extrusion control method for the stainless steel pipe processing technology, and includes a temperature monitoring module, a pressure prediction module, an initial parameter acquisition module, an extrusion speed matching module, an extrusion control module and a parameter optimization module.

[0007] In a third aspect, the application discloses a computer device including a memory and a processor, wherein the memory stores a computer program, and the processor implements any step of the first aspect of the application when executing the computer program.

[0008] In a fourth aspect, the application discloses a computer readable storage medium, which stores a computer program, and the computer program implements any step of the first aspect of the application when executed by a processor.

[0009] The one or more technical solutions provided in the application have at least the following technical effects or advantages.

[0010] By monitoring the temperature data in real time and inputting it into the temperature-pressure prediction model for prediction, the heating process can be more accurately controlled by continuously heating until the predicted pressure meets the preset pressure range, which is then used as the initial pressure control parameter, ensuring the accuracy of pressure control during extrusion; by matching the speed based on the pressure-speed calibration table for the initial pressure control parameter, the coordination of extrusion speed and pressure can be ensured, thereby further improving the processing quality of the product; by optimizing the initial temperature control parameter, pressure control parameter and speed control parameter, and using the optimized parameter combination for hot extrusion optimization of the metal blank, the production efficiency can be improved under the premise of improving the product quality. In summary, the hot extrusion control method for the stainless steel pipe processing technology solves the problem of inaccurate temperature, pressure and speed control in traditional hot extrusion processing by accurately controlling parameters such as heating, pressure and speed, thereby improving the processing quality of the stainless steel pipe.

[0011] The above description is only a summary of the technical solutions of the present application. In order to more clearly understand the technical means of the present application, the following specific embodiments of the present application can be implemented in accordance with the content of the specification, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the following specific embodiments of the present application are described. BRIEF DESCRIPTION OF DRAWINGS

[0012] Figure 1 The hot extrusion control method for the stainless steel pipe processing technology provided by the embodiments of the present application is shown in the flowchart;

[0013] Figure 2 The hot extrusion control system structure diagram for the stainless steel pipe processing technology provided by the embodiments of the present application is shown in the structure diagram;

[0014] Figure 3 The internal structure diagram of the computer equipment provided by the embodiments of the present application is shown in the structure diagram.

[0015] Legend: temperature monitoring module 10, pressure prediction module 20, initial parameter acquisition module 30, extrusion speed matching module 40, extrusion control module 50, parameter optimization module 60, hot extrusion optimization module 70. DETAILED DESCRIPTION

[0016] The embodiments of the present application provide a hot extrusion control method for the stainless steel pipe processing technology, which solves the technical problem of poor processing quality and low production efficiency of the stainless steel pipe caused by the inaccurate parameter control of the traditional method for hot extrusion and the dependence on past experience for parameter adjustment.

[0017] After introducing the basic principles of the present application, various non-limiting embodiments of the present application will be described in detail below with reference to the accompanying drawings. It should be understood that the specific examples described herein are merely intended to explain the present application and are not intended to limit the present application.

[0018] As shown in Figure 1 The embodiments of the present application provide a hot extrusion control method for stainless steel pipe processing technology, which is applied to a hot extrusion control device, the hot extrusion control device comprises a heating unit and an extrusion unit, and the method comprises the following steps:

[0019] When the target metal blank is conveyed to the heating unit, the heating unit is activated to perform continuous heating control of the metal blank, and the temperature monitoring device of the heating unit is activated to perform real-time temperature monitoring of the heating unit to obtain temperature monitoring data.

[0020] The hot extrusion control method for stainless steel pipe processing technology provided by the embodiments of the present application is applied to a hot extrusion control device, the hot extrusion control device comprises a heating unit and an extrusion unit, wherein the heating unit comprises a heating element for providing heat to heat the metal blank, and a temperature monitoring device for monitoring the temperature change in the heating process in real time; the extrusion unit is used for extruding the heated metal blank to form a desired shape, such as a steel pipe, by applying pressure.

[0021] Firstly, the target metal blank is moved to the working area of the heating unit by a conveying device such as a conveyor belt or a mechanical arm. The heating element in the heating unit is started to provide heat to the metal blank, so that the metal blank is continuously heated at an appropriate rate. The temperature monitoring device of the heating unit is activated to start real-time monitoring of the temperature inside the heating unit. The temperature monitoring device can be a temperature sensor, a thermal imager, etc., which can accurately measure the temperature change in the heating unit. The temperature monitoring device continuously collects temperature data to obtain temperature monitoring data, i.e. real-time temperature information of the metal blank.

[0022] When the temperature monitoring data meets the preset temperature range, the current temperature monitoring data is input into a temperature-pressure prediction model to perform pressure prediction and obtain predicted pressure data.

[0023] The preset temperature interval is obtained by matching the stainless steel pipe sample, and the detailed matching method is described in the subsequent steps. When the temperature monitoring data reaches the preset temperature interval, it indicates that the metal blank has reached the expected heating temperature. At this time, these data are input into the temperature-pressure prediction model, which is a mathematical model that models the relationship between temperature and pressure based on theoretical calculations. The temperature-pressure prediction model uses the input temperature monitoring data to predict the pressure according to the relationship defined in the model to determine the expected pressure value at a given temperature. Through the calculation of the temperature-pressure prediction model, the predicted pressure data is obtained, which represents the expected extrusion pressure that the metal blank should withstand at the current temperature.

[0024] If the predicted pressure data does not meet the preset pressure interval, continue to heat until the predicted pressure data meets the preset pressure interval, and use the heated temperature monitoring data as the initial temperature control parameter and the current predicted pressure data as the initial pressure control parameter.

[0025] The preset pressure interval is set according to actual conditions, such as the control range of the extrusion unit and the heating range of the metal blank. After the temperature-pressure prediction model calculation, if the predicted pressure data fails to meet the pre-set pressure interval requirement, continue to heat the metal blank. During the heating process, the heating unit continuously provides heat to the metal blank, causing its temperature to rise continuously. During the continuous heating process, the predicted pressure data is continuously monitored until it reaches the preset pressure interval, at which point heating is stopped, and the temperature monitoring data at this time is used as the initial temperature control parameter, and the current predicted pressure data is used as the initial pressure control parameter.

[0026] Based on the pressure-velocity calibration table, the initial pressure control parameter is matched with the extrusion speed to obtain the initial speed control parameter.

[0027] The pressure-velocity calibration table is a pre-prepared table that records the corresponding extrusion speed at different pressures. This table is obtained through experiments or theoretical analysis and is used to guide the speed control during extrusion. According to the initial pressure control parameter, find the matching extrusion speed in the pressure-velocity calibration table to determine the initial speed control parameter, which represents the extrusion speed that should be taken under the given initial pressure condition.

[0028] The target metal blank is transferred to the extrusion unit, and based on the initial pressure control parameter and the initial speed control parameter, extrusion control is performed, and the steel pipe product quality is recorded as the preheating extrusion control result.

[0029] The target metal blank is heated by the heating unit and then delivered to the working area of the extrusion unit. According to the determined initial pressure control parameter and initial speed control parameter, the extrusion control of the metal blank is started. According to the parameter setting, the extrusion unit applies corresponding pressure and controls the extrusion speed to extrude the metal blank into the shape of a steel pipe. After the extrusion is completed, the quality of the steel pipe is recorded, including the detection of the size, shape, surface quality, etc. of the steel pipe. The obtained steel pipe product quality is the result of the preheating extrusion control.

[0030] The initial temperature control parameter, the initial pressure control parameter, and the initial speed control parameter are optimized to obtain an optimized control parameter combination, with the goal of optimizing the quality of the steel pipe product.

[0031] The goal of optimization is to improve the quality of the steel pipe product, including size accuracy, surface quality, and mechanical properties. A suitable optimization algorithm is selected to search for the optimal control parameter combination. Common optimization algorithms include genetic algorithm, particle swarm optimization, simulated annealing algorithm, etc. The quality of the steel pipe product is used as the optimization goal to establish an optimization model. The model takes the initial temperature control parameter, pressure control parameter, and speed control parameter as input and outputs quality-related evaluation indexes.

[0032] The selected optimization algorithm is used to solve the optimization model to search for the optimal control parameter combination. During the optimization process, different parameter combinations are constantly tried and evaluated for their impact on the quality of the steel pipe product. Each generated parameter combination is evaluated to calculate its impact on the quality of the steel pipe product. According to the evaluation results, it is determined which parameter combination can bring the optimal quality of the steel pipe product. After the optimization algorithm search is completed, the optimal control parameter combination is obtained, which is the optimization result of the initial temperature control parameter, pressure control parameter, and speed control parameter.

[0033] The hot extrusion optimization of the target metal blank is performed using the optimized control parameter combination.

[0034] The control parameter combination obtained by the foregoing optimization is applied to the hot extrusion control device. These optimized control parameters include optimized temperature control parameters, pressure control parameters, and speed control parameters. By using the optimized control parameter combination, the target metal blank is subjected to hot extrusion processing. During the extrusion process, the heating unit heats according to the optimized temperature control parameter, and the extrusion unit performs extrusion operation according to the optimized pressure and speed parameters to achieve the best effect of the processing process and maximize the quality of the steel pipe product.

[0035] Further, the preset temperature range is obtained by:

[0036] According to the stainless steel pipe hot working record database, a plurality of metal blank information and a plurality of hot working temperature sets of a plurality of stainless steel pipe samples are obtained;

[0037] A mapping relationship between hot working temperature and melting failure index is established based on the plurality of metal blank information;

[0038] Based on the mapping relationship between hot working temperature and melting failure index, a plurality of melting failure probability sets are obtained by analyzing the plurality of hot working temperature sets;

[0039] Based on the preset melting failure probability, the plurality of melting failure probability sets are screened, and a plurality of screened hot working temperature sets are obtained according to the screening result;

[0040] Based on the plurality of screened hot working temperature sets, a plurality of sample preset temperature intervals of the plurality of stainless steel pipe samples are established;

[0041] The target metal blank is matched with the plurality of metal blank information to obtain the preset temperature interval of the current stainless steel pipe.

[0042] A hot working record database is established to store relevant data in the hot working process of stainless steel pipes. The database includes processing parameters, process information, processing conditions and other data of different pipe samples. From the established hot working record database, the metal blank information of a plurality of stainless steel pipe samples is retrieved and extracted. The metal blank information includes the material quality, size, chemical composition, physical properties and the like of the steel material. Similarly, a plurality of hot working temperature sets of a plurality of stainless steel pipe samples are extracted from the hot working record database. The hot working temperature sets include the heating temperature in the heating process, and establish a basis for subsequent analysis.

[0043] According to the hot working requirements and process requirements, the heating temperature of each metal blank in the hot working process is determined, and a melting failure index is defined to describe the melting failure of the metal in the heating process. The melting failure index includes melting temperature, melting rate, thermal deformation rate and the like. Through statistical analysis, regression analysis and other methods, based on the collected metal blank information and the determined hot working temperature, a mapping relationship between hot working temperature and melting failure index is established. This mapping relationship is used to describe the probability of melting failure of the metal blank at a specific processing temperature.

[0044] Based on the established mapping relationship between hot working temperature and melting failure index, each hot working temperature is mapped to the corresponding melting failure index. According to the mapping relationship, the melting failure probability corresponding to each processing temperature can be calculated. The melting failure probabilities of each temperature point in each hot working temperature set obtained by analysis are summarized to obtain a plurality of melting failure probability sets. Each element in each set represents the melting failure probability under different hot working temperature conditions.

[0045] A preset melting failure probability threshold is determined, which is used to screen the hot working temperature set. The preset melting failure probability can be set according to the processing requirements, safety standards or quality requirements. Each melting failure probability set is screened to find the temperature points that meet the preset melting failure probability requirements, that is, the temperature points below the preset melting failure probability threshold are screened out according to the preset melting failure probability threshold. According to the screening result, the temperature points that meet the preset melting failure probability requirements are combined to form a new screening hot working temperature set. This screening hot working temperature set includes those processing temperature points whose predicted melting failure probability is lower than the preset threshold.

[0046] For each stainless steel pipe sample, a sample preset temperature interval is established according to its corresponding screening hot working temperature set. The sample preset temperature interval can be determined according to the lowest temperature and the highest temperature in the screening temperature set, that is, the preset temperature interval of each sample is the temperature range in its corresponding screening temperature set. The sample preset temperature interval of each stainless steel pipe sample is recorded to obtain a plurality of sample preset temperature intervals.

[0047] The metal blank information of the current stainless steel pipe is obtained, and the target metal blank information is matched with the plurality of metal blank information collected before. The matching process includes comparing the similarity and matching degree of the target metal blank with the existing information in the database. According to the matching result, the metal blank information most similar to the target metal blank is found. Based on the preset temperature interval of the selected matching metal blank, the preset temperature interval of the current stainless steel pipe is determined. This preset temperature interval can be used as a reference in the processing process to determine the heating temperature range, so as to ensure the stability of the processing quality and product performance.

[0048] Further, the temperature-pressure prediction model is constructed, including:

[0049] Obtain the temperature-rheological stress change curve when the heating unit heats the metal blank;

[0050] Obtain the rheological stress-pressure change curve when the extrusion unit extrudes the metal blank;

[0051] Correlate the temperature-rheological stress change curve and the rheological stress-pressure change curve to establish the temperature-pressure prediction model.

[0052] Using experimental or simulation methods, the metal blank is heated by the heating unit, the temperature control of the heating unit is kept stable, and the temperature is adjusted according to the preset heating curve to simulate the heating condition in the actual production process. At the same time, the flow stress data of the metal blank is measured in real time. Flow stress is the resistance of material to deformation under stress, which can be measured by tensile testing machine, pressure sensor and other equipment. The real-time measured temperature and flow stress data are recorded and analyzed. According to the change of temperature and flow stress in the heating process, the temperature-flow stress change curve is drawn with temperature as horizontal axis and flow stress as vertical axis.

[0053] Similarly, using experimental or simulation methods, the metal blank is extruded by the extrusion unit. During the extrusion process, the extrusion pressure data is measured in real time. These data can be obtained through the pressure sensor on the extruder. The real-time measured flow stress and extrusion pressure data are recorded and analyzed. According to the change of flow stress and pressure in the extrusion process, the flow stress-pressure change curve is drawn with flow stress as horizontal axis and pressure as vertical axis.

[0054] The collected temperature-flow stress change curve and flow stress-pressure change curve are preprocessed, including data cleaning, smoothing and normalization, to prepare the data for modeling. The temperature-flow stress change curve and flow stress-pressure change curve are associated, which can be done by matching the data points of the two curves to find the corresponding temperature and flow stress corresponding to the pressure data points.

[0055] According to the associated data points, a temperature-pressure prediction model can be established using regression analysis and other methods. In this model, temperature is the input variable, flow stress is the intermediate variable, and extrusion pressure is the output variable. Using existing data sets, the data set is divided into training set and test set, and the established prediction model is trained and verified. The established prediction model is evaluated to check its prediction ability and generalization ability, and the model is optimized according to the evaluation results. After the completion of model establishment and optimization, it can be used in actual production process. The model can predict the corresponding extrusion pressure according to the given temperature information to guide the production operation and optimize the production process.

[0056] Further, to optimize the quality of the finished steel pipe, the initial temperature control parameter, the initial pressure control parameter and the initial speed control parameter are optimized to obtain an optimized control parameter combination, including:

[0057] Based on the plurality of sets of melting failure probabilities, a set of melting failure probabilities of the current stainless steel pipe is obtained;

[0058] performing centralized trend analysis on the set of melting failure probabilities to obtain a representative melting failure probability;

[0059] calculating a difference between the representative melting failure probability and the preset melting failure probability to obtain a melting failure probability deviation value;

[0060] generating a target temperature control parameter with the objective of minimizing the melting failure probability deviation value;

[0061] obtaining a target pressure control parameter and a target speed control parameter based on the target temperature control parameter in combination with a temperature-pressure prediction model and a pressure-speed calibration table;

[0062] constructing an initial control parameter combination with the initial temperature control parameter, the initial pressure control parameter, and the initial speed control parameter, constructing a target control parameter combination with the target temperature control parameter, the target pressure control parameter, and the target speed control parameter, and performing control parameter optimization based on the initial control parameter combination and the target control parameter combination to obtain the optimized control parameter combination.

[0063] matching the target metal billet information with a plurality of metal billet information previously collected to find the metal billet information most similar to the target metal billet, obtaining a set of melting failure probabilities corresponding to the metal billet as the set of melting failure probabilities of the stainless steel pipe.

[0064] calculating centralized trend indicators of the set of melting failure probabilities, such as mean, median, mode, etc., which can reflect the central position of the melting failure probability, i.e., concentrated around which value, and obtaining a representative melting failure probability through calculation.

[0065] The preset melting failure probability is a probability value set according to actual conditions or historical experience, representing the normal condition of the target metal billet. The representative melting failure probability is subtracted from the preset melting failure probability to obtain a difference value between the two, i.e., the melting failure probability deviation value. This difference value can be positive or negative. A positive value indicates that the actual melting failure probability is higher than the preset value, and a negative value indicates that the actual melting failure probability is lower than the preset value.

[0066] The melting failure probability deviation value is used as an objective function to optimize the target parameter. The objective of the objective function is to make the melting failure probability deviation value as close to zero as possible, i.e., to make the actual melting failure probability consistent with the expected value. Define the spatial range of the temperature control parameter, including the value range of the temperature and the heating rate, etc. These parameters will be adjusted in the optimization process to minimize the melting failure probability deviation value. Select appropriate optimization algorithms, such as gradient descent method, genetic algorithm, simulated annealing, etc. These algorithms can search in the parameter space to find the temperature control parameter combination that minimizes the objective function.

[0067] For a given combination of temperature control parameters, calculate the corresponding melting failure probability deviation value, use the selected optimization algorithm to search iteratively in the parameter space to find the combination of temperature control parameters that minimizes the objective function until the stopping condition is reached, determine the final target temperature control parameters to achieve the minimization of the melting failure probability.

[0068] Using the determined target temperature control parameters, input into the temperature-pressure prediction model to predict the target extrusion pressure under the temperature condition, obtain the target pressure control parameter. Use the predicted target pressure value as input, look up the corresponding target speed control parameter in the pressure-velocity calibration table, obtain the target speed control parameter.

[0069] Integrate the initial temperature control parameters, the initial pressure control parameters, the initial speed control parameters to obtain the initial control parameter combination; integrate the target temperature control parameters, the target pressure control parameters, the target speed control parameters to obtain the target control parameter combination.

[0070] A key performance indicator in the production process, such as product quality, energy consumption, production efficiency, etc., is used as the objective function. Select the appropriate optimization algorithm according to the actual situation, common algorithms include gradient descent method, genetic algorithm, simulated annealing algorithm, etc. Define the search space and possible value range of the control parameters, and set the constraint conditions to ensure that the parameters change within a reasonable range. Set a stopping condition, such as reaching the maximum number of iterations, the objective function converging to a pre-set threshold, etc. When the stopping condition is met, the optimization algorithm will stop searching and return the optimal control parameter combination.

[0071] Using the selected optimization algorithm, search for the optimal control parameter combination in the defined parameter space, the algorithm adjusts the parameter values according to the changes of the objective function until the stopping condition is reached. Finally output the optimal control parameter combination, apply the optimized control parameter combination to the actual production to improve the efficiency of the production process and the quality of the products.

[0072] Further, the central tendency analysis is performed on the set of melting failure probabilities to obtain a representative melting failure probability, including:

[0073] The standard deviation of the set of melting failure probabilities is calculated to obtain a melting failure probability deviation coefficient;

[0074] When the melting failure probability deviation coefficient is greater than or equal to a pre-set deviation coefficient, the mean value of the set of melting failure probabilities is calculated to obtain a probability mean value as the representative melting failure probability;

[0075] When the melting failure probability deviation coefficient is less than the preset deviation coefficient, mode analysis is performed on the melting failure probability set to obtain a probability mode as the representative melting failure probability.

[0076] The melting failure probability deviation coefficient is a statistical quantity used to measure the dispersion degree of the melting failure probability set. Specifically, first, all probability values in the melting failure probability set are added together, and then divided by the total number of probability values to obtain the average value. Then, the deviation between each probability value and the average value is calculated. Then, the sum of the squares of these deviations is calculated, and finally, the standard deviation is obtained by dividing the total number of probability values by the square root of the total number of probability values. The calculation formula is as follows:

[0077] ;

[0078] wherein, is the standard deviation, is the i-th melting failure probability, and n represents the total number of probabilities in the melting failure probability set, is the average value of the n melting failure probabilities.

[0079] Finally, the ratio of the standard deviation to the average value is calculated to obtain the melting failure probability deviation coefficient, which is expressed in percentage. By calculating the deviation coefficient of the melting failure probability set, the dispersion degree of the probability set can be evaluated, and the stability of the melting failure probability can be understood. If the deviation coefficient is small, it indicates that the probability value is relatively stable, and vice versa.

[0080] When the melting failure probability deviation coefficient is greater than or equal to the preset deviation coefficient, it means that the dispersion degree of the melting failure probability is high, and the entire probability set cannot be directly used as the representative melting failure probability. Therefore, it is necessary to reduce the dispersion of the probability set to obtain a more stable representative melting failure probability. In this case, the average value of the melting failure probability set is calculated as the representative melting failure probability, i.e. by taking the average value to offset the fluctuations of each value in the probability set, thereby obtaining a more stable estimated value. Specifically, all probability values in the melting failure probability set are added together, and then divided by the total number of probability values to obtain the average value, which is taken as the representative melting failure probability.

[0081] When the melting failure probability deviation coefficient is less than the preset deviation coefficient, it means that the dispersion degree of the melting failure probability is relatively small, and the mode of the probability set can be used as the representative melting failure probability. The mode refers to the value with the highest frequency in a set of data. Specifically, the melting failure probability set is analyzed to determine the probability value with the highest frequency, which is the mode of the probability set. The determined mode is taken as the representative melting failure probability for subsequent analysis.

[0082] Further, based on the initial control parameter combination, the target control parameter combination, control parameter optimization is performed to obtain the optimized control parameter combination, including:

[0083] A three-dimensional optimization space is established, wherein the three-dimensional optimization space has a preset temperature interval and a preset pressure interval as constraint conditions;

[0084] In the three-dimensional optimization space, the initial control parameter combination is mapped as an optimization starting point, and the target control parameter combination is mapped as an optimization direction, wherein the mapping formula is as follows:

[0085] ;

[0086] wherein, represents the i-th optimization item of the initial control parameter combination, is the j-th optimization element of the i-th optimization item, i=1, 2, 3, j=1, 2, 3..., D, D is the number of the j-th optimization element, represents the lower limit of the j-th optimization element, represents the upper limit of the j-th optimization element, and U is a uniform distribution random function;

[0087] Control parameter mutation is performed between the optimization starting point and the optimization direction to obtain a mutated control parameter combination, wherein the mutation formula is as follows:

[0088] ;

[0089] wherein, M is the mutated control parameter combination, is the target control parameter combination;

[0090] Randomly exchange the elements in the target control parameter combination and the elements of the same optimization item in the mutated control parameter combination to obtain a first test control parameter combination;

[0091] The initial control parameter combination is replaced and updated by the first test control parameter combination, iteration optimization is performed, and the optimized control parameter combination is obtained.

[0092] According to the above steps, a preset temperature interval and a preset pressure interval are obtained, temperature control parameters, pressure control parameters, and speed control parameters are taken as three axes of a three-dimensional coordinate system, the preset temperature interval and the preset pressure interval are mapped into the three-dimensional coordinate system, wherein the extrusion speed changes with the pressure, and after mapping, a cuboid is formed, which is the three-dimensional optimization space. In this way, it can be ensured that the control parameter combination in the optimization process is within the preset temperature interval and the preset pressure interval, so as to ensure the safety and stability of the production process.

[0093] The initial control parameter combination is mapped to corresponding coordinate axes of a three-dimensional optimization space to obtain a coordinate point as an optimization starting point; the target control parameter combination is mapped to corresponding coordinate axes of the three-dimensional optimization space to obtain another coordinate point as an optimization direction, wherein the mapping formula is as follows:

[0094]

[0095] represents the i-th optimization item of the initial control parameter combination, and i ranges from 1 to D, The temperature control parameter, the pressure control parameter and the speed control parameter can be represented; represents the j-th optimization element in the i-th optimization item in the control parameter combination, wherein j ranges from 1 to D, and D is the number of the j-th optimization element, represents the lower limit of the j-th optimization element, that is, the minimum acceptable value of the control parameter, represents the upper limit of the j-th optimization element, that is, the maximum acceptable value of the control parameter, represents a value randomly generated according to a uniform distribution between the upper limit and the lower limit.

[0096] Through the formula, the initial control parameter combination can be randomly generated as the optimization starting point, and a target control parameter combination can also be determined as the optimization direction. This method can explore in multiple dimensions to find the optimal control parameter combination.

[0097] A control parameter mutation is performed between the optimization starting point and the optimization direction to obtain a mutated control parameter combination, wherein the mutation formula is as follows:

[0098]

[0099] represents the j-th optimization element in the i-th optimization item in the target control parameter combination, that is, the optimization direction, represents a random number randomly generated according to a uniform distribution in the range of [0, 1], and 3 in the formula is a coefficient for controlling the degree of mutation.

[0100] Through the mutation process, a certain randomness can be introduced in the optimization process, so as to better explore the search space and find a better control parameter combination.

[0101] ​​​​​​In the target control parameter combination and the variation control parameter combination, an element of the same optimization item is randomly selected for exchange, so that the exchange in the same optimization item is ensured, and interference between different optimization items is avoided. The selected element in the target control parameter combination is exchanged with the element of the same optimization item in the variation control parameter combination. After the exchange, the new control parameter combination obtained is the first test control parameter combination.

[0102] Through this process, a certain randomness is introduced on the basis of the target control parameter combination and the variation control parameter combination to generate the first test control parameter combination, so as to further explore the search space and find a better control parameter combination.

[0103] The first test control parameter combination and the initial control parameter combination are compared. According to the performance of the two, the first test control parameter combination is replaced with the initial control parameter combination as a new initial control parameter combination, or the initial control parameter combination is retained.

[0104] The above steps are repeated for multiple iterations. After each iteration, if a predetermined stopping condition is reached, such as reaching a maximum number of iterations, converging to a certain threshold, etc., the iteration is stopped, otherwise the next iteration is continued. Finally, the optimal control parameter combination is selected as the optimization result.

[0105] Further, the first test control parameter combination is used to replace and update the initial control parameter combination, and iterative optimization is performed to obtain the optimization control parameter combination, including:

[0106] Based on the hot extrusion simulation model, the first test control parameter combination is simulated and analog, and the simulation result is evaluated based on the hot extrusion quality evaluation index to obtain a first test parameter quality evaluation value;

[0107] Based on the hot extrusion simulation model, the initial control parameter combination is simulated and analog, and the simulation result is evaluated based on the hot extrusion quality evaluation index to obtain an initial parameter quality evaluation value;

[0108] If the first test parameter quality evaluation value is less than the initial parameter quality evaluation value, the initial control parameter combination is continued to be used as the optimization starting point;

[0109] If the first test parameter quality evaluation value is greater than or equal to the initial parameter quality evaluation value, the first test control parameter combination is used to replace the initial control parameter combination as an updated optimization starting point;

[0110] Iterative optimization is performed until a convergence condition is reached to obtain the final optimization control parameter combination.

[0111] A simulation model of the hot extrusion process is established using simulation software, which can accurately simulate the changes in key parameters such as temperature, pressure, deformation, etc. during the hot extrusion process. The first test control parameter combination is used as the input parameter of the simulation model, and the simulation model is run in the established hot extrusion simulation model to simulate the heating, extrusion and deformation of the metal blank during the hot extrusion process.

[0112] The simulation results are evaluated according to the hot extrusion quality evaluation indicators, which include indicators for steel pipe product quality, melting failure probability, mechanical properties, etc. The evaluation results of each evaluation indicator are weighted and summed to obtain the quality evaluation value of the first test parameter, which is used to measure the degree of optimization of the first test control parameter combination.

[0113] In the same way, the initial control parameter combination is used to run the simulation simulation in the established hot extrusion simulation model, and the simulation results are evaluated using the hot extrusion quality evaluation indicators to obtain the initial parameter quality evaluation value.

[0114] The first test parameter quality evaluation value is compared with the initial parameter quality evaluation value. If the first test parameter quality evaluation value is less than the initial parameter quality evaluation value, it means that the quality of the initial control parameter combination is better. In this case, the initial control parameter combination is continued to be used as the optimization starting point, and the control parameter optimization process is re-executed to try to find a better control parameter combination.

[0115] If the first test parameter quality evaluation value is greater than or equal to the initial parameter quality evaluation value, it means that the quality of the first test parameter combination is better, and the first test control parameter combination is used to replace the initial control parameter combination as the updated optimization starting point to continue to find a better control parameter combination in the next round of optimization.

[0116] The termination condition of iteration is set, for example, the maximum number of iterations is set or the threshold value of control parameter change is defined as the convergence condition. From the updated optimization starting point, the iteration process of control parameter optimization is executed. In each iteration, according to the current control parameter combination, simulation simulation is carried out, and the quality of the simulation results is evaluated. According to the evaluation results, the control parameter combination is adjusted to generate a new test parameter combination. It is judged whether the convergence condition is met. If it is met, the iteration is stopped, otherwise the next iteration is continued. When the convergence condition is met, the iteration process stops, and the control parameter combination at this time is the final optimized control parameter combination.

[0117] Through the process of iterative optimization, the control parameter combination is continuously adjusted and evaluated until the convergence condition is met, and the optimized control parameter combination can be obtained, so as to realize the optimization of the hot extrusion process and the production of the best quality.

[0118] In summary, the heat extrusion control method for stainless steel pipe processing technology provided by the embodiments of the present application has the following technical effects:

[0119] 1. By monitoring temperature data in real time and inputting it into a temperature-pressure prediction model for prediction, the heating process can be more accurately controlled. By continuously heating until the predicted pressure meets the preset pressure range, and then using it as the initial pressure control parameter, the accuracy of pressure control during extrusion can be ensured;

[0120] 2. By matching the initial pressure control parameter with the speed based on the pressure-speed calibration table, the coordination between extrusion speed and pressure can be ensured, thereby further improving the processing quality of the product;

[0121] 3. By optimizing the initial temperature control parameter, the pressure control parameter and the speed control parameter, and using the optimized parameter combination for hot extrusion optimization of the metal blank, the production efficiency can be improved on the premise of improving the product quality.

[0122] In summary, the heat extrusion control method for stainless steel pipe processing technology accurately controls parameters such as heating, pressure and speed, solves the problem of inaccurate temperature, pressure and speed control in traditional hot extrusion processing, and improves the processing quality of stainless steel pipes.

[0123] Based on the same inventive concept as the heat extrusion control method for stainless steel pipe processing technology in the foregoing embodiments, as shown in Figure 2 The present application provides a heat extrusion control system for stainless steel pipe processing technology, which is applied to a heat extrusion control device including a heating unit and an extrusion unit, and comprises:

[0124] a temperature monitoring module 10, which is used to activate the heating unit for continuous heating control of the metal blank after the target metal blank is conveyed to the heating unit, and activate the temperature monitoring device of the heating unit to monitor the temperature of the heating unit in real time to obtain temperature monitoring data;

[0125] a pressure prediction module 20, which is used to input the current temperature monitoring data into a temperature-pressure prediction model when the temperature monitoring data meets the preset temperature range, to predict the pressure and obtain predicted pressure data;

[0126] An initial parameter acquisition module 30 is configured to, if the predicted pressure data does not satisfy the preset pressure interval, continue to heat up until the predicted pressure data satisfies the preset pressure interval, and then take the temperature monitoring data after heating as an initial temperature control parameter and take the current predicted pressure data as an initial pressure control parameter.

[0127] An extrusion speed matching module 40 is configured to match the initial pressure control parameter with an extrusion speed based on a pressure-speed calibration table to obtain an initial speed control parameter.

[0128] An extrusion control module 50 is configured to deliver the target metal billet to the extrusion unit, perform extrusion control based on the initial pressure control parameter and the initial speed control parameter, and record the steel pipe product quality as a preheating extrusion control result.

[0129] A parameter optimization module 60 is configured to optimize the initial temperature control parameter, the initial pressure control parameter and the initial speed control parameter to obtain an optimized control parameter combination.

[0130] A hot extrusion optimization module 70 is configured to perform hot extrusion optimization of the target metal billet based on the optimized control parameter combination.

[0131] Further, the system further comprises a preset temperature interval acquisition module configured to perform the following operation steps:

[0132] According to a stainless steel pipe hot working record database, a plurality of metal billet information and a plurality of hot working temperature sets of a plurality of stainless steel pipe samples are obtained.

[0133] A mapping relationship between hot working temperature and melting failure index is established based on the plurality of metal billet information.

[0134] A plurality of melting failure probability sets are obtained by analyzing the plurality of hot working temperature sets based on the mapping relationship between hot working temperature and melting failure index.

[0135] Based on a preset melting failure probability, the plurality of melting failure probability sets are screened to obtain a plurality of screened hot working temperature sets according to a screening result.

[0136] Based on the plurality of screened hot working temperature sets, a plurality of sample preset temperature intervals of the plurality of stainless steel pipe samples are established.

[0137] The target metal billet is matched with the plurality of metal billet information to obtain the preset temperature interval of the current stainless steel pipe.

[0138] Further, the system further comprises a model building module, configured to perform the following operation steps:

[0139] obtain a temperature-rheological stress change curve when the heating unit heats the metal blank;

[0140] obtain a rheological stress-pressure change curve when the extrusion unit extrudes the metal blank;

[0141] correlate the temperature-rheological stress change curve and the rheological stress-pressure change curve to establish the temperature-pressure prediction model.

[0142] Further, the system further comprises an optimized control parameter combination obtaining module, configured to perform the following operation steps:

[0143] obtain a current set of stainless steel pipe melting failure probabilities based on the plurality of sets of melting failure probabilities;

[0144] perform a central tendency analysis on the set of melting failure probabilities to obtain a representative melting failure probability;

[0145] calculate a difference between the representative melting failure probability and the preset melting failure probability to obtain a melting failure probability deviation value;

[0146] generate a target temperature control parameter with the objective of minimizing the melting failure probability deviation value;

[0147] obtain a target pressure control parameter and a target speed control parameter based on the target temperature control parameter, in combination with the temperature-pressure prediction model and the pressure-speed calibration table;

[0148] construct an initial control parameter combination based on the initial temperature control parameter, the initial pressure control parameter, and the initial speed control parameter, and construct a target control parameter combination based on the target temperature control parameter, the target pressure control parameter, and the target speed control parameter, and perform control parameter optimization based on the initial control parameter combination and the target control parameter combination to obtain the optimized control parameter combination.

[0149] Further, the system further comprises a failure probability obtaining module, configured to perform the following operation steps:

[0150] perform a standard deviation calculation on the set of melting failure probabilities to obtain a melting failure probability deviation coefficient;

[0151] when the melting failure probability deviation coefficient is greater than or equal to a preset deviation coefficient, perform a mean value calculation on the set of melting failure probabilities to obtain a probability mean value as the representative melting failure probability;

[0152] When the melting failure probability deviation coefficient is less than a preset deviation coefficient, mode analysis is performed on the melting failure probability set to obtain a probability mode as the representative melting failure probability.

[0153] Further, the system further comprises an iterative optimization module to perform the following steps:

[0154] A three-dimensional optimization space is established, wherein the three-dimensional optimization space has a preset temperature interval and a preset pressure interval as constraint conditions;

[0155] In the three-dimensional optimization space, the initial control parameter combination is mapped as an optimization starting point, and the target control parameter combination is mapped as an optimization direction, wherein the mapping formula is as follows:

[0156] ;

[0157] wherein, represents the i-th optimization item of the initial control parameter combination, is the j-th optimization element of the i-th optimization item, i = 1, 2, 3, j = 1, 2, 3,..., D, D is the number of the j-th optimization element, represents the lower bound of the j-th optimization element, represents the upper bound of the j-th optimization element, and U is a uniform distribution random function;

[0158] Between the optimization starting point and the optimization direction, control parameter mutation is performed to obtain a mutated control parameter combination, wherein the mutation formula is as follows:

[0159] ;

[0160] wherein, M is the mutated control parameter combination, is the target control parameter combination;

[0161] Randomly exchange the elements in the target control parameter combination and the elements of the same optimization item in the mutated control parameter combination to obtain a first test control parameter combination;

[0162] The first test control parameter combination is used to replace and update the initial control parameter combination, iterative optimization is performed, and the optimized control parameter combination is obtained.

[0163] Further, the system further comprises an optimization module to perform the following steps:

[0164] Based on the hot extrusion simulation model, the first test control parameter combination is simulated, and the simulation result is evaluated based on the hot extrusion quality evaluation index to obtain a first test parameter quality evaluation value;

[0165] Based on the hot extrusion simulation model, the initial control parameter combination is simulated, and the simulation result is evaluated based on the hot extrusion quality evaluation index to obtain an initial parameter quality evaluation value;

[0166] If the first test parameter quality evaluation value is less than the initial parameter quality evaluation value, the initial control parameter combination is continuously used as the optimization starting point;

[0167] If the first test parameter quality evaluation value is greater than or equal to the initial parameter quality evaluation value, the first test control parameter combination is used to replace the initial control parameter combination as an updated optimization starting point.

[0168] Iterative optimization is performed until a convergence condition is reached to obtain a final optimized control parameter combination.

[0169] Through the foregoing detailed description of the hot extrusion control method for the stainless steel pipe processing technology, those skilled in the art can clearly understand the hot extrusion control system for the stainless steel pipe processing technology in the embodiment. Since the system corresponds to the method disclosed in the embodiment, the system is described relatively simply, and the relevant part is described in the method part.

[0170] In one embodiment, a computer device, which can be a server, has an internal structure diagram as shown in Figure 3 The computer device includes a processor, a memory, and a network interface connected through a system bus, wherein the processor of the computer device is configured to provide computing and control capabilities; the memory of the computer device includes a non-volatile storage medium and an internal memory, the non-volatile storage medium stores an operating system, a computer program, and a database, and the internal memory provides an environment for running the operating system and the computer program in the non-volatile storage medium; and the network interface of the computer device is configured to communicate with an external terminal through a network connection. The computer program is executed by the processor to implement the hot extrusion control method for the stainless steel pipe processing technology.

[0171] Those skilled in the art can understand that Figure 3 The structure shown in the above embodiment is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. Specifically, the computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0172] The technical features of the above embodiments can be combined in any manner. To make the description concise, not all possible combinations of the technical features in the above embodiments are described, however, as long as the combinations of the technical features do not exist contradictions, they should be considered as the scope of the present disclosure.

[0173] The foregoing description of the disclosed embodiments enables a person skilled in the art to make or use the application. Modifications of these embodiments will occur to persons of skill in the art, and, while certain embodiments according to the principles set forth herein have been shown and described, various modifications and substitutions can be made by those skilled in the art without departing from the spirit and scope of the application as set forth in the following claims. Therefore, the application is not intended to be limited to the embodiments disclosed herein, but rather is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for controlling hot extrusion for stainless steel pipe machining process, characterized by, The method is applied to a hot extrusion control device, the hot extrusion control device comprising a heating unit and an extrusion unit, and the method comprises: After a target metal blank is delivered to the heating unit, the heating unit is activated for continuous temperature-increasing heating control of the metal blank, and a temperature monitoring device of the heating unit is activated to perform real-time temperature monitoring on the heating unit to obtain temperature monitoring data; When the temperature monitoring data meets a preset temperature interval, the current temperature monitoring data is input into a temperature-pressure prediction model to perform pressure prediction and obtain predicted pressure data; The preset temperature interval is obtained by: According to a stainless steel pipe hot working record database, a plurality of metal blank information and a plurality of hot working temperature sets of a plurality of stainless steel pipe samples are obtained; A mapping relationship between hot working temperature and melting failure index is established based on the plurality of metal blank information; Based on the mapping relationship between hot working temperature and melting failure index, the plurality of hot working temperature sets are analyzed to obtain a plurality of melting failure probability sets; Based on a preset melting failure probability, the plurality of melting failure probability sets are screened, and a plurality of screened hot working temperature sets are obtained according to the screening result; Based on the plurality of screened hot working temperature sets, a plurality of sample preset temperature intervals of the plurality of stainless steel pipe samples are established; The target metal blank is matched with the plurality of metal blank information to obtain the preset temperature interval of the current stainless steel pipe; If the predicted pressure data does not meet a preset pressure interval, continuous temperature-increasing heating is performed until the predicted pressure data meets the preset pressure interval, the temperature monitoring data after heating is taken as an initial temperature control parameter, and the current predicted pressure data is taken as an initial pressure control parameter; Based on a pressure-velocity calibration table, the initial pressure control parameter is matched with an extrusion speed to obtain an initial speed control parameter; The target metal blank is delivered to the extrusion unit, and extrusion control is performed based on the initial pressure control parameter and the initial speed control parameter, and the quality of a steel pipe product is recorded as a preheating extrusion control result; The initial temperature control parameter, the initial pressure control parameter, and the initial speed control parameter are optimized to obtain an optimized control parameter combination, with the goal of optimizing the quality of the steel pipe product; The hot extrusion of the target metal blank is optimized based on the optimized control parameter combination.

2. The method of claim 1, wherein, The temperature-pressure prediction model is constructed by: A temperature-rheological stress change curve when the heating unit heats a metal blank is obtained; A rheological stress-pressure change curve when the extrusion unit extrudes a metal blank is obtained; The temperature-rheological stress change curve and the rheological stress-pressure change curve are associated to establish the temperature-pressure prediction model.

3. The method of claim 1, wherein, The initial temperature control parameter, the initial pressure control parameter, and the initial speed control parameter are optimized to obtain an optimized control parameter combination, with the goal of optimizing the quality of the steel pipe product, which comprises: Based on the plurality of melting failure probability sets, a melting failure probability set of the current stainless steel pipe is obtained; performing centralized trend analysis on the set of melting failure probabilities to obtain a representative melting failure probability; calculating a difference between the representative melting failure probability and the preset melting failure probability to obtain a melting failure probability deviation value; generating a target temperature control parameter with a target of minimizing the melting failure probability deviation value; obtaining a target pressure control parameter and a target speed control parameter based on the target temperature control parameter in combination with a temperature-pressure prediction model and a pressure-speed calibration table; constructing an initial control parameter combination with the initial temperature control parameter, the initial pressure control parameter and the initial speed control parameter, and constructing a target control parameter combination with the target temperature control parameter, the target pressure control parameter and the target speed control parameter, and performing control parameter optimization based on the initial control parameter combination and the target control parameter combination to obtain the optimized control parameter combination.

4. The method of claim 3, wherein, performing centralized trend analysis on the set of melting failure probabilities to obtain a representative melting failure probability, including: performing standard deviation calculation on the set of melting failure probabilities to obtain a melting failure probability deviation coefficient; when the melting failure probability deviation coefficient is greater than or equal to a preset deviation coefficient, performing mean value calculation on the set of melting failure probabilities to obtain a probability mean value as the representative melting failure probability; when the melting failure probability deviation coefficient is less than the preset deviation coefficient, performing mode analysis on the set of melting failure probabilities to obtain a probability mode as the representative melting failure probability.

5. The method of claim 3, wherein, performing control parameter optimization based on the initial control parameter combination and the target control parameter combination to obtain the optimized control parameter combination, including: establishing a three-dimensional optimization space, wherein the three-dimensional optimization space has a preset temperature interval and a preset pressure interval as constraint conditions; mapping the initial control parameter combination as an optimization starting point and the target control parameter combination as an optimization direction in the three-dimensional optimization space, wherein a mapping formula is as follows: ； wherein, represents the i-th optimization term of the initial control parameter combination, represents the j-th optimization element of the i-th optimization term, i = 1, 2, 3, j = 1, 2, 3..., D, D is the number of the j-th optimization element, represents the lower bound of the j-th optimization element, represents the upper bound of the j-th optimization element, U is a uniform distribution random function; performing control parameter variation between the optimization starting point and the optimization direction to obtain a variation control parameter combination, wherein a variation formula is as follows: ； wherein M is a mutation control parameter combination, P is an optimization starting point, i.e., an initial control parameter combination, 3 is a predetermined coefficient for controlling the degree of mutation, represents a random number uniformly distributed in the range of [0, 1] and randomly generated, is a target control parameter combination; randomly exchanging elements in the target control parameter combination and elements of the same optimization item in the variation control parameter combination to obtain a first test control parameter combination; replacing and updating the initial control parameter combination with the first test control parameter combination to perform iterative optimization to obtain the optimized control parameter combination.

6. The method of claim 5, wherein, replacing and updating the initial control parameter combination with the first test control parameter combination to perform iterative optimization to obtain the optimized control parameter combination, including: performing simulation modeling on the first test control parameter combination based on a hot extrusion simulation model, and evaluating the simulation modeling result based on a hot extrusion quality evaluation index to obtain a first test parameter quality evaluation value; performing simulation modeling on the initial control parameter combination based on the hot extrusion simulation model, and evaluating the simulation modeling result based on the hot extrusion quality evaluation index to obtain an initial parameter quality evaluation value; If the first test parameter quality evaluation value is less than the initial parameter quality evaluation value, the initial control parameter combination is continuously used as the optimization starting point; If the first test parameter quality evaluation value is greater than or equal to the initial parameter quality evaluation value, the first test control parameter combination is used to replace the initial control parameter combination as the updated optimization starting point; Iterative optimization is performed until a convergence condition is reached, and a final optimized control parameter combination is obtained.

7. A hot extrusion control system for a stainless steel pipe machining process, characterized by, The system is applied to a hot extrusion control device including a heating unit and an extrusion unit, and is used to implement the hot extrusion control method for the stainless steel pipe processing process according to any one of claims 1-6. The system includes: A temperature monitoring module is configured to activate the heating unit to perform continuous heating control of the metal blank after the target metal blank is delivered to the heating unit, and activate a temperature monitoring device of the heating unit to perform real-time temperature monitoring of the heating unit and obtain temperature monitoring data. A pressure prediction module is configured to input the current temperature monitoring data into a temperature-pressure prediction model when the temperature monitoring data meets a preset temperature interval, perform pressure prediction, and obtain predicted pressure data. An initial parameter acquisition module is configured to continuously heat until the predicted pressure data meets the preset pressure interval, and then use the temperature monitoring data after heating as initial temperature control parameters and use the current predicted pressure data as initial pressure control parameters. An extrusion speed matching module is configured to perform extrusion speed matching on the initial pressure control parameters based on a pressure-speed calibration table to obtain initial speed control parameters. An extrusion control module is configured to deliver the target metal blank to the extrusion unit, perform extrusion control based on the initial pressure control parameters and the initial speed control parameters, and record the quality of the steel pipe product as a preheating extrusion control result. A parameter optimization module is configured to optimize the initial temperature control parameters, the initial pressure control parameters, and the initial speed control parameters to obtain an optimized control parameter combination. A hot extrusion optimization module is configured to perform hot extrusion optimization of the target metal blank using the optimized control parameter combination.

8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that, The processor executes the computer program to implement the steps of the hot extrusion control method for the stainless steel pipe processing process according to any one of claims 1-6.

9. A computer readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the hot extrusion control method for the stainless steel pipe processing process according to any one of claims 1-6.

Images