Method and system for optimizing forging frequency of efficient radial forging machine

Abstract

The invention relates to the technical field of forging data optimization, in particular to a forging frequency optimization method and system of an efficient radial forging machine. The method comprises the steps that forging parameters in the forging process of a radial forging machine are collected, and the collected forging parameters are preprocessed; according to historical forging data and forging results of the target radial forging machine, a forging frequency optimization model is established, the preprocessed forging parameters are input, and optimization analysis is conducted on the forging parameters; according to a result obtained after optimization analysis of the frequency optimization model, forging parameter optimization is conducted, and the vibration frequency and amplitude in the forging process are adjusted so as to control the change of forging force; the system comprises a forging parameter acquisition module, a forging frequency optimization model module and a forging parameter optimization module. According to the method, the forging parameters, especially the vibration frequency and amplitude, are optimized, so that the change of the forging force is more effectively controlled, the accuracy and effectiveness of optimization analysis are ensured, and the controllability and frequency of the forging process are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of forging data optimization, and in particular to a forging frequency optimization method and system for a high-efficiency radial forging machine. Background Art

[0002] Radial forging is a rotary forging method specially used for processing solid or hollow long shaft parts. During forging, hammers (2 to 8) distributed in the circumferential direction of the bar forge the workpiece quickly and synchronously. If the workpiece has a circular cross-section, it rotates at a low speed while moving axially; if the workpiece has a non-circular cross-section, it only feeds axially without rotating. The characteristic of radial forging is that it does not require special molds and can forge precise shaft parts according to a predetermined program. The radial forging has a small compression amount each time and a high number of forging times per minute, generally 240 to 1800 times / minute, which can improve the plasticity of the metal; this method can be used for hot forging or cold forging.

[0003] Prior art 1, Chinese patent, application number: 202311852967.8 discloses a method for optimizing the forging process of a hydraulic end. According to the upper, middle and lower limits of the chemical composition range of the hydraulic end material, a temperature-density curve is established through a high-temperature volume measurement test; according to the different carbon equivalents of the chemical composition of the material, a carbon equivalent-melting point / liquidus curve and a carbon equivalent-Ac3 temperature point curve are established, and the relevant functions are fitted to determine the initial forging temperature and final forging temperature range of the hydraulic end material; at the same time, the forging process parameters such as the heating temperature, holding time, heating coefficient, deformation amount and forging ratio are optimized and controlled, so that the hydraulic end forging can be more easily deformed and its grain growth and size can be effectively controlled. Although the plasticity and forgeability of the material can be effectively improved through the optimization of the forging process of the hydraulic end, thereby ensuring the mechanical properties such as strength and toughness of the hydraulic end forging; however, it is necessary to establish multiple curves according to the chemical composition range and carbon equivalent of the hydraulic end material, which increases the complexity and cost of the process implementation.

[0004] Prior art 2, Chinese patent, application number 202410241420.2 discloses a forging process optimization system and optimization method based on digital twin, including a physical entity acquisition module and a digital twin system, the physical entity acquisition module includes a data acquisition module, and the data acquisition module is used for information data during the operation of the physical entity acquisition module. Although integrating digital twin technology into the forging process helps to form intelligent and networked production, facilitates manufacturing resource allocation and production technology sharing, facilitates offline operation training and online production guidance; improves the yield rate and reduces resource waste; however, the implementation of the digital twin system requires higher technical difficulty and increases the implementation cost of the system.

[0005] Prior art three, Chinese patent, application number 202010576109.5 discloses a non-rotating forging method for radial forging, which uses a radial forging machine to forge the blank. The radial forging machine is equipped with four symmetrically distributed hammers, two of which are oppositely arranged as one group of hammers, and the other two are oppositely arranged as two groups of hammers, including: non-rotating forging; the blank does not rotate, but is only fed in, and one group of hammers and the second group of hammers synchronously forge the blank to the set specifications; non-rotating forging is performed for several times; rotary forging; the blank is fed in while rotating forging; rounding; the final round steel is obtained after rounding. Although non-rotating forging is adopted, radial forging is achieved by controlling parameters such as the amount of reduction, the amount of feed, the forging frequency, and the forging position; however, it is difficult to accurately control the parameters.

[0006] At present, the prior art 1, prior art 2 and prior art 3 have the problems of high complexity of process implementation, high system implementation cost and great difficulty in accurately controlling parameters. Therefore, the present invention provides a forging frequency optimization method and system for an efficient radial forging machine. Summary of the invention

[0007] In order to achieve the above object, the present invention adopts the following technical scheme:

[0008] One aspect of the present invention provides a method for optimizing the forging frequency of a high-efficiency radial forging machine, comprising the following steps:

[0009] Collect forging parameters such as forging speed, pressure and heating time during the forging process of the radial forging machine, and pre-process the collected forging parameters;

[0010] According to the historical forging data and forging results of the target radial forging machine, a forging frequency optimization model is established, and the forging parameters such as forging speed, pressure and heating time after pretreatment are input to optimize the forging parameters;

[0011] According to the results of the frequency optimization model optimization analysis, the forging parameters of the radial forging machine are optimized, and the vibration frequency and amplitude during the forging process are adjusted to control the change of the forging force.

[0012] In an optional implementation, the process of collecting forging parameters such as forging speed, pressure and heating time during the forging process of the radial forging machine includes:

[0013] During the forging process of the radial forging machine, the forging speed data is collected according to the determined process parameters and equipment parameters of the radial forging machine;

[0014] Install an optical pyrometer to detect the real-time temperature of the radial forging machine and record the temperature distribution and temperature change during the forging process; and collect the heating time data during the forging process of the radial forging machine;

[0015] The collected forging parameters are preliminarily cleaned, the collected forging parameters in different units and formats are standardized, the average, maximum and minimum values ​​are extracted from the original data, and the extracted features are normalized.

[0016] In an optional implementation, the process of collecting forging speed data includes:

[0017] Determine the process parameters of the workpiece revolutions, axial feed speed and radial press-in amount that require radial forging, and set the equipment parameters of the radial forging machine according to the determined process parameters;

[0018] During the forging process, the displacement information of the radial forging machine hammer is recorded by the displacement sensor, the shape information of the forging is recorded by the visual acquisition system, and the real-time collected displacement information of the radial forging machine hammer and the shape information data of the forging are synchronously processed;

[0019] The movement speed of the hammer is calculated by analyzing the hammer displacement data; the deformation rate of the forging during the forging process is analyzed through the shape information of the forging, and the movement speed of the hammer and the deformation rate of the forging are comprehensively analyzed to obtain the forging speed data.

[0020] In an optional implementation, the process of establishing a forging frequency optimization model includes:

[0021] The historical forging data and forging results of the target radial forging machine are matched to construct a forging data set, the data in the forging data set is cleaned and fused, and the forging data set is divided into a training set and a validation set at a ratio of 8:2;

[0022] Use the grid search method to adjust the forging frequency optimization model, and select the forging frequency optimization model with the highest score for training; use the divided training set to train the forging frequency optimization model, adjust the network parameters through the back propagation algorithm, and use the early stopping strategy to avoid overfitting;

[0023] Use the divided validation set to evaluate the trained forging frequency optimization model and calculate the error index of the forging frequency optimization model; set the threshold. If it exceeds the threshold, readjust the forging frequency optimization model; if it is lower than the threshold, perform feature extraction analysis.

[0024] In an optional implementation, the process of constructing a forging data set includes:

[0025] Collect the historical forging data and forging results of the target radial forging machine, and check the missing values ​​in the data set; if missing values ​​occur, use mean filling to process them;

[0026] Draw a box plot of the forging parameters and process characteristic values ​​of the target radial forging machine; calculate the upper quartile, lower quartile and interquartile range of each parameter, and determine the upper and lower thresholds; mark the values ​​below the lower limit or above the upper limit as outliers, and analyze the outliers by replacement or deletion methods;

[0027] The extracted structural parameters and flow field characteristics are standardized; data from different sources or formats are integrated to form a unified data set.

[0028] In an optional implementation, the process of training the forging frequency optimization model using the divided training set includes:

[0029] Design the network structure of the forging frequency optimization model and select the number of hidden layers; select the activation function and loss function corresponding to the target longitudinal forging direction; input the divided training set into the forging frequency optimization model, and use the optimizer to adjust the network weights and biases of the forging frequency optimization model;

[0030] Determine the value range of the learning rate, number of hidden layers, number of nodes, and batch size hyperparameters; form a grid with all hyperparameters, and use the divided training set to train the forging frequency optimization model for each hyperparameter combination in the grid;

[0031] Use the divided validation set to verify the mean square error and accuracy of the forging frequency optimization model after each training, set the threshold, and select the forging frequency optimization model corresponding to the hyperparameter combination with the smallest error compared to the threshold as the final forging frequency optimization model.

[0032] In an optional embodiment, the process of optimizing the forging parameters of the radial forging machine includes:

[0033] According to the results of the forging frequency optimization model analysis, an orthogonal table of forging parameters is established to obtain the peak values ​​of each group of forging frequency optimization parameters;

[0034] According to the peak value data of the optimized parameters in the orthogonal table of forging parameters, each optimized parameter is divided into three levels and the level is evaluated, and the level threshold is set. If the parameter value is judged to be lower than the preset level threshold, the orthogonal table parameter peak value is used for optimization;

[0035] According to the parameter values ​​optimized by the orthogonal table of forging parameters, the servo motor of the radial forging machine is adjusted. The vibration frequency and amplitude during the forging process are adjusted by adjusting the speed of the servo motor. The changes of forging parameters are monitored, and the speed is optimized and adjusted according to the changes of forging parameters.

[0036] In an optional implementation, the process of optimizing using the orthogonal array parameter peak value includes:

[0037] Obtaining forging parameters of forging speed, pressure and heating time during the forging process of the radial forging machine after pretreatment, setting the forging parameters as design variables, and taking forging efficiency as the optimization target;

[0038] The functional relationship between forging parameters and forging efficiency is fitted by a multivariate quadratic equation; the peak value data of optimized parameters in the orthogonal table of forging parameters are graded and divided into three grades: A, B, and C;

[0039] If the target radial forging machine optimization parameter evaluation level is C, the optimal result of the forging parameter and forging efficiency fitting is used as the optimization parameter. If the target radial forging machine optimization parameter evaluation level is A or B, the optimization parameter peak data is kept unchanged and monitoring is continued.

[0040] In an optional implementation, the process of adjusting the vibration frequency and amplitude during the forging process by adjusting the rotation speed of the servo motor includes:

[0041] Set the basic parameters of the servo motor of the target forging machine, including rated voltage, current and speed, and adjust the proportional, integral and differential parameters of the speed loop to accurately control the servo motor;

[0042] Gradually increase or decrease the speed of the servo motor, monitor the changes in vibration frequency and amplitude, and monitor the changes in forging parameters, and adjust the speed according to the changes in forging parameters to make the forging parameters reach the peak value data of the orthogonal table optimization parameters;

[0043] After completing the adjustment of the servo motor of the target forging machine, the target forging machine is experimentally verified, and its control accuracy, stability and forging frequency are tested. The servo motor speed is adjusted according to the test results until the forging frequency reaches the peak value.

[0044] Another aspect of the present invention provides a forging frequency optimization system for a high-efficiency radial forging machine, comprising:

[0045] The forging parameter collection module is used to collect forging parameters such as forging speed, pressure and heating time during the forging process of the radial forging machine, and pre-process the collected forging parameters;

[0046] The forging frequency optimization model module is used to establish a forging frequency optimization model based on the historical forging data and forging results of the target radial forging machine, input the pre-processed forging parameters such as forging speed, pressure and heating time, and optimize the forging parameters;

[0047] The forging parameter optimization module is used to optimize the forging parameters of the radial forging machine according to the results of the frequency optimization model optimization analysis, and adjust the vibration frequency and amplitude during the forging process to control the change of the forging force.

[0048] The present invention can more effectively control the change of forging force by optimizing forging parameters, especially vibration frequency and amplitude, thereby improving forging quality and efficiency; ensure the accuracy and effectiveness of optimization analysis; realize intelligent analysis of forging parameters by establishing and optimizing models, and improve the controllability and frequency of the forging process; and achieve improvement of forging quality and reduction of cost by adjusting parameters. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] The accompanying drawings are used to provide further understanding of the present invention and constitute a part of the specification. They are used to explain the present invention together with the embodiments of the present invention and do not constitute a limitation of the present invention.

[0050] In the attached picture:

[0051] Figure 1 This is a flow chart of the forging frequency optimization method of the high-efficiency radial forging machine provided in Example 1 of the present invention;

[0052] Figure 2 This is a flow chart of collecting forging parameters provided in Example 2 of the present invention;

[0053] Figure 3 This is a flow chart of collecting forging speed data provided in Example 3 of the present invention;

[0054] Figure 4 This is a flow chart of establishing a forging frequency optimization model provided in Example 4 of the present invention;

[0055] Figure 5 A flowchart of constructing a forging data set provided in Example 5 of the present invention;

[0056] Figure 6 This is a flow chart of the training forging frequency optimization model provided in Example 6 of the present invention;

[0057] Figure 7 This is a flow chart for optimizing the forging parameters of a radial forging machine provided in Example 7 of the present invention;

[0058] Figure 8 This is a flow chart of optimizing the peak value of the orthogonal array parameters provided in Example 8 of the present invention;

[0059] Fig. 9 This is a flow chart of adjusting the vibration frequency and amplitude during the forging process provided in Example 9 of the present invention;

[0060] Fig.10 This is a functional module diagram of a forging frequency optimization system of a high-efficiency radial forging machine provided in Example 10 of the present invention;

[0061] Fig.11 is a block diagram of an electronic device provided in Embodiment 11 of the present invention;

[0062] Fig.12 This is a block diagram of the computer-readable storage medium provided in Example 12 of the present invention. DETAILED DESCRIPTION

[0063] The technical solutions in the embodiments of the present invention will be described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0064] In the following, the terms "first", "second", etc. are used only for convenience of description and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first", "second", etc. may explicitly or implicitly include one or more of the features. In the description of the present invention, unless otherwise specified, "plurality" means two or more.

[0065] In the present invention, unless otherwise clearly specified and limited, the term "connection" should be understood in a broad sense, for example, "connection" can be a fixed mechanical connection, or a detachable mechanical connection, or integrated; or, "connection" can be a direct connection, or an indirect connection through an intermediate medium. In addition, unless otherwise clearly specified and limited, the term "coupling" should be understood in a broad sense, for example, "coupling" can be a direct electrical connection, such as physical contact and electrical conduction between two components, and can also be understood as electrical connection between different components in a circuit structure through physical lines such as copper foil or wires on a printed circuit board (PCB) that can transmit electrical signals to transmit electrical signals; or, "coupling" can be an indirect electrical connection between two components through an intermediate medium; or, "coupling" can be an electrical connection between two components in an air-spaced / non-contact manner, for example, two components are electrically connected by capacitive coupling to transmit electrical signals.

[0066] In the embodiments of the present invention, directional terms such as "up", "down", "left" and "right" may be defined including but not limited to the orientation relative to the schematic placement of the components in the drawings. It should be understood that these directional terms may be relative concepts, which are used for relative description and clarification, and may change accordingly according to the change of the orientation of the components in the drawings.

[0067] The embodiments of the present invention can be used in the aerospace field: when manufacturing high-precision, high-strength aerospace parts, by optimizing the forging frequency, the density and mechanical properties of the material can be improved, ensuring the reliability and safety of the parts. Automobile manufacturing: when producing key components such as automobile engines and drive shafts, optimizing the forging frequency can reduce material waste and improve production efficiency while ensuring the strength and durability of the components. Energy equipment manufacturing: when manufacturing key components of large-scale energy equipment (such as gas turbines and wind turbines), by optimizing the forging frequency, the uniformity and fatigue resistance of the material can be improved, and the service life of the equipment can be extended. Mold manufacturing: in the mold production process, optimizing the forging frequency can improve the precision and durability of the mold and reduce the difficulty and cost of subsequent processing.

[0068] Embodiment 1:

[0069] like Figure 1 As shown, an embodiment of the present invention provides a forging frequency optimization method for a high-efficiency radial forging machine, comprising the following steps:

[0070] Step S100: collecting forging parameters such as forging speed, pressure and heating time during the forging process of the radial forging machine, and preprocessing the collected forging parameters;

[0071] Step S200: establishing a forging frequency optimization model based on historical forging data and forging results of the target radial forging machine, inputting pre-processed forging parameters such as forging speed, pressure and heating time, and optimizing and analyzing the forging parameters;

[0072] Step S300: According to the results of the frequency optimization model optimization analysis, the forging parameters of the radial forging machine are optimized, and the vibration frequency and amplitude during the forging process are adjusted to control the change of the forging force.

[0073] In the above embodiment, step S100 collects forging parameters such as forging speed, pressure and heating time during the forging process of the radial forging machine and performs preprocessing; by collecting key forging parameters, basic data is provided for analysis and optimization; preprocessing ensures the accuracy and consistency of the data and improves the reliability of the analysis; step S200 establishes a forging frequency optimization model based on the historical forging data and forging results of the target radial forging machine, and inputs the preprocessed forging parameters into the model for optimization analysis; the optimization model established using historical data and forging results can more accurately reflect the parameter relationship in the forging process, It provides a scientific basis for the optimization of forging parameters; step S300 optimizes the forging parameters of the radial forging machine according to the analysis results of the frequency optimization model, and adjusts the vibration frequency and amplitude during the forging process to control the change of the forging force; by optimizing the forging parameters, especially the vibration frequency and amplitude, the change of the forging force can be more effectively controlled, thereby improving the forging quality and efficiency; the accuracy and effectiveness of the optimization analysis are guaranteed; by establishing and optimizing the model, the intelligent analysis of the forging parameters is realized, and the controllability and frequency of the forging process are improved; by adjusting the parameters, the forging quality is improved and the cost is reduced.

[0074] Embodiment 2:

[0075] like Figure 2 As shown, based on Example 1, the process of collecting forging parameters in step S100 provided in this embodiment of the present invention specifically includes the following steps:

[0076] Step S101: during the forging process of the radial forging machine, collecting forging speed data according to the determined process parameters and equipment parameters of the radial forging machine;

[0077] Step S102: installing an optical pyrometer to detect the real-time temperature of the radial forging machine, and recording the temperature distribution and temperature change during the forging process; and collecting the heating time data during the forging process of the radial forging machine;

[0078] Step S103: Perform preliminary data cleaning on the collected forging parameters, standardize the collected forging parameters in different units and formats, extract the average value, maximum value and minimum value from the original data, and normalize the extracted features.

[0079] In the above embodiment, step S101 can collect forging speed data to understand the speed change in the forging process in real time, and provide basic data for process analysis and optimization; forging speed is one of the key factors affecting forging quality and efficiency; accurate speed data is helpful to evaluate the stability and controllability of the forging process, and then optimize the forging process; step S102 optical pyrometer can monitor the temperature change in the forging process in real time and record the temperature distribution; at the same time, collecting heating time data is helpful to understand the efficiency and stability of the heating process; temperature is an important factor affecting the performance of forging materials and forging results; by real-time monitoring and recording temperature data, temperature anomalies can be discovered and solved in time to ensure the smooth progress of the forging process; at the same time, the collection of heating time data is helpful to optimize the heating process, improve heating efficiency and energy utilization; step S103 data cleaning and standardization processing can eliminate outliers and noise in the original data, and improve the accuracy and reliability of the data; feature extraction and normalization are helpful to explore the potential laws and patterns of the data; through effective data preprocessing, the accuracy and efficiency of data analysis can be improved.

[0080] Embodiment 3:

[0081] like Figure 3 As shown, based on Example 2, in step S101 provided in this embodiment of the present invention, the process of collecting forging speed data specifically includes the following steps:

[0082] Step S1011: determining process parameters such as the number of revolutions of the workpiece to be radially forged, the axial feed speed, and the radial press-in amount, and setting equipment parameters of the radial forging machine according to the determined process parameters;

[0083] Step S1012: During the forging process, the displacement information of the radial forging machine hammer is recorded by the displacement sensor, the shape information of the forging is recorded by the visual acquisition system, and the real-time collected displacement information of the radial forging machine hammer and the shape information data of the forging are synchronously processed;

[0084] Step S1013: Calculate the movement speed of the hammer by analyzing the hammer displacement data; analyze the deformation rate of the forging during the forging process based on the shape information of the forging, and comprehensively analyze the movement speed of the hammer and the deformation rate of the forging to obtain the forging speed data.

[0085] In the above embodiment, step S1011 can ensure that the forging process is carried out in accordance with the predetermined process requirements, thereby achieving the expected forging effect, by accurately determining key process parameters such as the workpiece rotation speed, axial feed speed and radial pressing amount, and setting the equipment parameters of the radial forging machine according to these parameters; the stability and controllability of the forging quality are ensured, which helps to improve the forging efficiency and reduce energy consumption; step S1012 records the displacement information of the radial forging machine hammer and the shape information of the forging in real time through the displacement sensor and the visual acquisition system, and synchronously processes these two types of information, which can accurately reflect the actual situation in the forging process; the collection and synchronization of real-time data The processing step provides reliable data support for forging speed analysis; it helps to timely discover and solve problems in the forging process and ensure the smooth progress of the forging process; step S1013 calculates the movement speed of the hammer head by analyzing the unique data of the hammer head, and analyzes the deformation rate of the forging through the shape information of the forging, and comprehensively analyzes these two types of data to obtain the forging speed data, which can accurately reflect the speed changes in the forging process; the forging speed provides an important basis for the optimization of the forging process; through the analysis of the forging speed, the key factors affecting the forging quality can be found, and then the forging process can be adjusted and optimized to improve the forging quality and efficiency.

[0086] Embodiment 4:

[0087] like Figure 4 As shown, based on Example 1, the process of establishing the forging frequency optimization model in step S200 provided in the embodiment of the present invention specifically includes the following steps:

[0088] Step S201: matching the historical forging data and forging results of the target radial forging machine, constructing a forging data set, cleaning and merging the data in the forging data set, and dividing the forging data set into a training set and a validation set at a ratio of 8:2;

[0089] Step S202: Use the grid search method to adjust the forging frequency optimization model, select the forging frequency optimization model with the highest score for training; use the divided training set to train the forging frequency optimization model, adjust the network parameters through the back propagation algorithm, and use the early stopping strategy to avoid overfitting;

[0090] Among them, combining the multi-physical field coupling in the forging process (such as thermal-mechanical coupling, stress-strain relationship) and the nonlinear fitting ability of the neural network, an equation for adjusting the network parameters by the back propagation algorithm is constructed:

[0091]

[0092] Where L represents the loss function, which represents the prediction error of the forging frequency optimization model; f irepresents the output of the i-th forging frequency optimization model, that is, the optimized forging frequency; θ represents the parameters (weight and bias) of the neural network; σ i represents the material stress at the i-th forging point, indicating the dynamic response of the material during the forging process; T i represents the temperature field of the i-th forging point, indicating the thermal effect during the forging process; C represents the thermal-mechanical coupling coefficient matrix of the material, indicating the dynamic characteristics of the material under the thermal-mechanical coupling; α, β, γ represent weight coefficients, which are used to balance the influence of different physical fields on the loss function; N represents the number of discrete points in the forging process; represents the gradient of the loss function with respect to the i-th forging frequency; represents the gradient of the i-th forging frequency with respect to the neural network parameters; represents the gradient of the loss function with respect to the material stress at the i-th forging point; represents the gradient of material stress at the i-th forging point with respect to the neural network parameters; represents the gradient of the loss function with respect to the temperature of the i-th forging point; represents the gradient of the temperature of the i-th forging point with respect to the neural network parameters; Represents the gradient of the loss function with respect to the material thermal-mechanical coupling coefficient matrix; Represents the gradient of the material thermal-mechanical coupling coefficient matrix to the neural network parameters; introduces material stress and temperature field, and incorporates the thermal-mechanical coupling effect in the forging process into the model, so that the model can simultaneously optimize the forging frequency and material response; the material thermal-mechanical coupling coefficient matrix is ​​used to describe the dynamic characteristics of the material under thermal-mechanical coupling, further enhancing the physical consistency of the model; through the gradient back-propagation mechanism, the gradients of the forging frequency, material stress, temperature field and thermal-mechanical coupling coefficient matrix are combined to adjust the neural network parameters; the weight coefficient is used to balance the contribution of different physical fields to the loss function, and can be adjusted according to the specific application scenario; the formula The program introduces multi-physics field coupling (thermal-mechanical coupling) and matrix operations (thermal-mechanical coupling coefficient matrix, which enables the model to handle more complex forging processes; through the summation symbol, multiple discrete points in the forging process are considered, which enhances the global optimization ability of the model. When forging high-strength alloys, the stress-strain relationship and temperature field of the material have a significant impact on the forging results. In the multi-axis forging process, the thermal-mechanical coupling effect is more complicated. By introducing the thermal-mechanical coupling coefficient matrix, the model can more accurately describe the dynamic characteristics of the forging process; combining forging frequency optimization with multi-physics field coupling improves the physical consistency and practicality of the model;

[0093] Step S203: Use the divided validation set to evaluate the trained forging frequency optimization model, and calculate the error index of the forging frequency optimization model; set a threshold, and if it exceeds the threshold, readjust the forging frequency optimization model; if it is lower than the threshold, perform feature extraction analysis.

[0094] In the above embodiment, step S201 matches the historical forging data with the forging results, constructs a forging data set, cleans and merges the data, ensures the quality and consistency of the data, and helps to improve the accuracy of the model; divides the data set into a training set and a validation set, provides data support for model training and validation; provides a reliable data basis for model training; ensures that the model can learn effective features and information during the training process; step S202 uses a grid search method to adjust the model, finds the optimal forging frequency to optimize the model parameters, and improves the performance of the model; uses the training set to train the model, and adjusts the network parameters through the back propagation algorithm, The model can better fit the data; the early stopping strategy is adopted to avoid overfitting and ensure the generalization ability of the model; the accuracy and efficiency of the model are improved by optimizing the model parameters; overfitting is avoided, making the model more stable and reliable in practical applications; step S203 uses the validation set to evaluate the trained model and calculates the error index, providing a basis for the performance evaluation of the model; by setting the threshold, the performance of the model is judged, and corresponding adjustments or feature extraction analysis are made according to the judgment results; the performance requirements of the model in practical applications are guaranteed; through feature extraction analysis, the key factors affecting the forging results can be further understood, providing guidance for process optimization.

[0095] Embodiment 5:

[0096] like Figure 5 As shown, based on Example 4, the process of constructing a forging data set in step S201 provided in this embodiment of the present invention specifically includes the following steps:

[0097] Step S2011: collecting historical forging data and forging results of the target radial forging machine, and checking the missing values ​​in the data set; if missing values ​​occur, mean filling is used for processing;

[0098] Step S2012: draw a box plot of the forging parameters and process characteristic values ​​of the target radial forging machine; calculate the upper quartile, lower quartile and interquartile range of each parameter, and determine the upper and lower thresholds; mark the values ​​below the lower limit or above the upper limit as outliers, and analyze the outliers by methods such as replacement or deletion;

[0099] Step S2013: Standardize the extracted structural parameters and flow field characteristics; integrate data from different sources or formats to form a unified data set.

[0100] In the above embodiment, step S2011 collects historical forging data and forging results of the target radial forging machine, and checks the missing values ​​in the data set. For the missing values, mean filling is used for processing; the integrity and consistency of the data set are ensured, providing a reliable basis for data analysis; mean filling is a simple and effective missing value processing method that can maintain the overall distribution characteristics of the data; step S2012 draws a box plot to intuitively display the distribution of forging parameters and process characteristic values, calculates quartiles to determine upper and lower limit thresholds, and marks and processes outliers; through the box plot, the distribution characteristics of the data can be clearly identified, including statistics such as the median and quartiles; determine The upper and lower thresholds help to identify and process outliers and improve data quality; the processing of outliers is crucial for data analysis and model training, and can prevent the model from being interfered by extreme values; step S2013 standardizes the extracted structural parameters and flow field characteristics, integrates data from different sources or formats, and forms a unified data set; standardization can eliminate the dimensional differences between different parameters and make the data comparable; integrating data from different sources or formats helps to build a comprehensive data set, providing rich information for data analysis and model training; a unified data set is the basis for data analysis and mining, and can improve the accuracy and efficiency of analysis.

[0101] Embodiment 6:

[0102] like Figure 6 As shown, based on Example 4, the process of training the forging frequency optimization model in step S202 provided in the embodiment of the present invention specifically includes the following steps:

[0103] Step S2021: design the network structure of the forging frequency optimization model and select the number of hidden layers; select the activation function and loss function corresponding to the target longitudinal forging direction; input the divided training set into the forging frequency optimization model, and use the optimizer to adjust the network weight and bias of the forging frequency optimization model;

[0104] Step S2022: Determine the value range of hyperparameters such as learning rate, number of hidden layers, number of nodes, and number of batches; form a grid with all hyperparameters, and for each hyperparameter combination in the grid, use the divided training set to train the forging frequency optimization model;

[0105] Step S2023: Use the divided validation set to verify the mean square error, accuracy, etc. of the forging frequency optimization model after each training, set a threshold, and select the forging frequency optimization model corresponding to the hyperparameter combination with the smallest error compared to the threshold as the final forging frequency optimization model.

[0106] In the above embodiment, step S2021 can ensure that the model has sufficient complexity to capture the features in the data while avoiding overfitting or underfitting by reasonably designing the network structure; selecting the activation function and loss function corresponding to the target longitudinal forging machine can ensure that the model performs best when processing a specific type of data; the activation function affects the nonlinear expression ability of the model, while the loss function determines the goal of model optimization; by training the model with an optimizer, the network weights and biases can be continuously adjusted to make the model perform better and better on the training set; through reasonable network design, selection of activation function and loss function, and use of optimizer , a forging frequency model that performs well on the training set can be preliminarily obtained; step S2022 can narrow the search space and improve the search efficiency by determining the value range of hyperparameters such as the learning rate, the number of hidden layers, the number of nodes and the number of batches; all possible hyperparameter combinations are traversed to find the optimal hyperparameter combination; the performance of the model on the training set is further improved; step S2023 verifies the model after each training through the divided verification set to evaluate the generalization ability of the model; setting the threshold and selecting the model with the smallest error can ensure that the finally selected model performs well on the verification set, thereby having better generalization ability.

[0107] Embodiment 7:

[0108] like Figure 7 As shown, based on Example 1, the process of optimizing the forging parameters of the radial forging machine in step S300 provided in the embodiment of the present invention specifically includes the following steps:

[0109] Step S301: according to the analysis result of the forging frequency optimization model, an orthogonal table of forging parameters is established to obtain the peak value of each group of forging frequency optimization parameters;

[0110] Step S302: According to the optimization parameter peak data of the forging parameter orthogonal table, each optimization parameter is divided into three levels and the level is evaluated, and the level threshold is set. If the parameter value is judged to be lower than the preset level threshold, the orthogonal table parameter peak is used for optimization;

[0111] Step S303: According to the parameter values ​​optimized by the orthogonal table of forging parameters, the servo motor of the radial forging machine is adjusted, the vibration frequency and amplitude during the forging process are adjusted by adjusting the speed of the servo motor, and the changes of the forging parameters are monitored, and the speed is optimized and adjusted according to the changes of the forging parameters.

[0112] In the above embodiment, step S301 uses the forging frequency optimization model to conduct an in-depth analysis of the forging process to ensure the accuracy of the optimization direction; by establishing an orthogonal table of forging parameters, various parameters in the forging process can be systematically organized and managed, so that the interaction between the parameters can be clarified; the peak values ​​of each group of forging frequency optimization parameters are obtained to provide a specific reference point for parameter optimization; the optimization efficiency of the forging parameters is improved, and the time cost of blind experiments is reduced; the stability and controllability of the forging process are guaranteed through model analysis and orthogonal table design; step S302 can quantitatively evaluate the forging parameters through grade assessment and setting grade thresholds, so that the optimization of the parameters is clearer and more specific; when the parameter value is lower than the preset grade threshold, the orthogonal table parameter peak value is used in time for optimization to ensure the stability of the forging process and product quality; it realizes refined management and optimization of forging parameters and improves the quality control level of the forging process; by setting the level threshold, potential problems in the forging process can be discovered and solved in time, reducing the scrap rate and production cost; step S303 adjusts the speed of the servo motor to accurately control the vibration frequency and amplitude in the forging process, thereby realizing direct control of the forging parameters; it monitors the changes of forging parameters in real time, and optimizes and adjusts the speed according to the changes, ensuring the stability and dynamic adaptability of the forging process; it improves the automation level and intelligence of the forging process and reduces the difficulty and error of manual operation; through real-time monitoring and adjustment, it can discover and solve abnormal problems in the forging process in time, ensuring the continuity and stability of the forging process, and also improving the forging efficiency and product quality.

[0113] Embodiment 8:

[0114] like Figure 8 As shown, based on Example 7, the process of using the orthogonal array parameter peak value for optimization in step S302 provided in the embodiment of the present invention specifically includes the following steps:

[0115] Step S3021: obtaining forging parameters such as forging speed, pressure and heating time of the radial forging machine during forging after pretreatment, setting the forging parameters as design variables, and taking forging efficiency as the optimization target;

[0116] Step S3022: fitting the functional relationship between the forging parameters and the forging efficiency by a multivariate quadratic equation; grading the peak value data of the optimized parameters in the forging parameter orthogonal table and dividing them into three grades: A, B, and C;

[0117] Step S3023: If the target radial forging machine optimization parameter evaluation level is C, the optimal result of the forging parameter and forging efficiency fitting is used as the optimization parameter; if the target radial forging machine optimization parameter evaluation level is A or B, the optimization parameter peak data is kept unchanged and monitoring is continued.

[0118] In the above embodiment, step S3021 obtains the key parameters of the forging process of the radial forging machine after pretreatment, and sets these parameters as design variables, with forging efficiency as the optimization target; clarifies the direction and basis of optimization, so that parameter adjustment and optimization have clear goals and basis, which is helpful to improve forging efficiency; step S3022 fits the functional relationship between forging parameters and forging efficiency through multivariate quadratic equations, and grades the peak data of the optimized parameters, which is divided into three levels, which is helpful to quickly judge the degree of optimization of the current parameter combination; provides a scientific basis and evaluation criteria for further optimization of the parameters, helps to quickly screen out better parameter combinations, and reduces the time for blind adjustment; step S3023 adopts different processing strategies according to the evaluation level of the optimized parameters, which not only ensures the continuous optimization of the parameters, but also avoids unnecessary adjustments; improves the efficiency and accuracy of parameter optimization, avoids unnecessary waste of resources, and can timely discover the impact of parameter changes on forging efficiency, providing data support for optimization.

[0119] Embodiment 9:

[0120] like Fig. 9 As shown, based on Example 7, the process of adjusting the vibration frequency and amplitude during the forging process in step S303 provided in the embodiment of the present invention specifically includes the following steps:

[0121] Step S3031: setting basic parameters of the servo motor of the target forging machine, including rated voltage, current and speed, and adjusting the proportional, integral and differential parameters of the speed loop to precisely control the servo motor;

[0122] Step S3032: gradually increase or decrease the speed of the servo motor, monitor the changes in vibration frequency and amplitude, and monitor the changes in forging parameters, and adjust the speed according to the changes in forging parameters so that the forging parameters reach the peak value data of the orthogonal table optimization parameters;

[0123] Step S3033: After completing the adjustment of the servo motor of the target forging machine, experimental verification is performed on the target forging machine, and its control accuracy, stability and forging frequency are tested. The servo motor speed is adjusted according to the test results until the forging frequency reaches the peak value.

[0124] In the above embodiment, step S3031 ensures that the motor can operate within a safe range by setting the rated voltage, current and speed of the servo motor; adjusting the proportional, integral and differential parameters of the speed loop can achieve precise control of the servo motor and improve the response speed and stability of the motor; step S3032 gradually adjusts the speed of the servo motor to observe its influence on the vibration frequency and amplitude, so as to find the best speed range; detecting the changes in forging parameters and adjusting the speed according to these changes can ensure that the forging parameters reach the peak data of the orthogonal table optimization parameters, that is, to achieve the best forging effect; optimizing the servo motor The speed setting can reduce unnecessary vibration and energy consumption, improve forging efficiency and product quality; through real-time monitoring and adjustment, ensure that the forging process is always in the optimal state to meet production needs; step S3033 can detect key indicators such as control accuracy, stability and forging frequency of the forging machine through experimental verification; adjust the servo motor speed according to the test results, and further optimize the performance of the forging machine to achieve the best state; ensure the stability and reliability of the forging machine in actual production, improve production efficiency and product quality; through continuous adjustment and optimization, the performance of the forging machine is optimized to meet or even exceed production needs.

[0125] Embodiment 10:

[0126] like Fig.10 As shown, based on Embodiments 1 to 9, the forging frequency optimization system of a high-efficiency radial forging machine provided in the embodiment of the present invention comprises:

[0127] The forging parameter collection module 1 is used to collect forging parameters such as forging speed, pressure and heating time during the forging process of the radial forging machine, and pre-process the collected forging parameters;

[0128] The forging frequency optimization model module 2 is used to establish a forging frequency optimization model according to the historical forging data and forging results of the target radial forging machine, input the forging parameters such as the pre-processed forging speed, pressure and heating time, and optimize the forging parameters;

[0129] The forging parameter optimization module 3 is used to optimize the forging parameters of the radial forging machine according to the results of the frequency optimization model optimization analysis, and adjust the vibration frequency and amplitude during the forging process to control the change of the forging force.

[0130] In the above embodiment, the forging parameter acquisition machine module 1 acquires forging parameters such as forging speed, pressure and heating time during the forging process of the radial forging machine, and performs preprocessing; by acquiring key forging parameters, basic data is provided for analysis and optimization; preprocessing ensures the accuracy and consistency of the data and improves the reliability of the analysis; the forging frequency optimization model module 2 establishes a forging frequency optimization model based on the historical forging data and forging results of the target radial forging machine, and inputs the preprocessed forging parameters into the model for optimization analysis; the optimization model established using historical data and forging results can more accurately reflect the parameters in the forging process. The relationship provides a scientific basis for the optimization of forging parameters; the forging parameter optimization module 3 optimizes the forging parameters of the radial forging machine according to the analysis results of the frequency optimization model, and adjusts the vibration frequency and amplitude during the forging process to control the change of the forging force; by optimizing the forging parameters, especially the vibration frequency and amplitude, the change of the forging force can be more effectively controlled, thereby improving the forging quality and efficiency; ensuring the accuracy and effectiveness of the optimization analysis; by establishing and optimizing the model, the intelligent analysis of the forging parameters is realized, and the controllability and frequency of the forging process are improved; by adjusting the parameters, the forging quality is improved and the cost is reduced.

[0131] Fig.11 A block diagram of an exemplary electronic device suitable for implementing embodiments of the present invention is shown.

[0132] The electronic device may include a central processing unit / microprocessor / main control chip, etc. 4; a storage medium 5, coupled to the central processing unit / microprocessor / main control chip, etc. 4, and storing computer executable instructions therein, for performing the steps of each method of an embodiment of the present invention when executed by the processor.

[0133] The central processing unit / microprocessor / main control chip 4 may include but is not limited to, for example, one or more processors or microprocessors.

[0134] The storage medium 5 may include, but is not limited to, for example, random access memory (RAM), read-only memory (ROM), flash memory, EPROM memory, EEPROM memory, registers, computer storage media (such as hard disk, floppy disk, solid state drive, removable disk, CD-ROM, DVD-ROM, Blu-ray disc, etc.).

[0135] In addition, the electronic device may also include (but not limited to) a data bus 6, an input / output bus / external bus / device bus 7, a display 8, and input / output devices 9 (eg, keyboard, mouse, speaker, etc.).

[0136] The central processing unit / microprocessor / main control chip etc. 4 can communicate with external devices ( 8 , 9 etc.) through the I / O bus 7 via a wired or wireless network (not shown).

[0137] The storage medium 5 may also store at least one computer executable instruction for executing the various functions and / or method steps in the embodiments described in the present technology when executed by the central processing unit / microprocessor / main control chip 4.

[0138] In one embodiment, the at least one computer executable instruction may also be compiled into or constitute a software product, wherein one or more computer executable instructions are executed by a processor to perform the various functions and / or method steps in the embodiments described in the present technology.

[0139] Fig.12 A schematic diagram of a computer-readable storage medium according to an embodiment of the present invention is shown.

[0140] like Fig.12 As shown, instructions are stored on a non-transitory computer-readable storage medium 11, and the instructions are, for example, computer-readable instructions 10. When the computer-readable instructions 10 are executed by the processor, the various methods described above can be executed. Non-transitory computer-readable storage media include, but are not limited to, for example, volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and / or cache memory (cache), etc. Non-transitory non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. For example, the non-transitory computer-readable storage medium 11 can be connected to a computing device such as a computer, and then, when the computing device runs the computer-readable instructions 10 stored on the computer-readable storage medium 11, the various methods described above can be performed.

[0141] In the several embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0142] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0143] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0144] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for executing all or part of the steps of the various embodiments of the method of the present invention through a computer device (which can be a personal computer, a server, or a network device, etc.). The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (full name in English: Read-Only Memory, English abbreviation: ROM), random access memory (full name in English: Random Access Memory, English abbreviation: RAM), disk or optical disk and other media that can store program codes.

[0145] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for optimizing the forging frequency of a high-efficiency radial forging machine, characterized in that: The forging frequency optimization method of the high-efficiency radial forging machine comprises the following steps: Collect forging speed, pressure and heating time forging parameters of the radial forging machine during forging, and pre-process the collected forging parameters; According to the historical forging data and forging results of the target radial forging machine, a forging frequency optimization model is established, and the pre-processed forging speed, pressure and heating time forging parameters are input to optimize the forging parameters; According to the results of the frequency optimization model optimization analysis, the forging parameters of the radial forging machine are optimized, and the vibration frequency and amplitude during the forging process are adjusted to control the change of the forging force.

2. The forging frequency optimization method of a high-efficiency radial forging machine according to claim 1, characterized in that: The process of collecting forging parameters of forging speed, pressure and heating time during the forging process of the radial forging machine includes: During the forging process of the radial forging machine, the forging speed data is collected according to the determined process parameters and equipment parameters of the radial forging machine; Install an optical pyrometer to detect the real-time temperature of the radial forging machine and record the temperature distribution and temperature change during the forging process; and collect the heating time data during the forging process of the radial forging machine; The collected forging parameters are preliminarily cleaned, the collected forging parameters in different units and formats are standardized, the average, maximum and minimum values ​​are extracted from the original data, and the extracted features are normalized.

3. The forging frequency optimization method of a high-efficiency radial forging machine according to claim 2, characterized in that: The process of collecting forging speed data includes: Determine the process parameters of the workpiece revolutions, axial feed speed and radial press-in amount that require radial forging, and set the equipment parameters of the radial forging machine according to the determined process parameters; During the forging process, the displacement information of the radial forging machine hammer is recorded by the displacement sensor, the shape information of the forging is recorded by the visual acquisition system, and the real-time collected displacement information of the radial forging machine hammer and the shape information data of the forging are synchronously processed; The movement speed of the hammer is calculated by analyzing the hammer displacement data; the deformation rate of the forging during the forging process is analyzed through the shape information of the forging, and the movement speed of the hammer and the deformation rate of the forging are comprehensively analyzed to obtain the forging speed data.

4. The forging frequency optimization method of a high-efficiency radial forging machine according to claim 1, characterized in that: The process of establishing the forging frequency optimization model includes: The historical forging data and forging results of the target radial forging machine are matched to construct a forging data set, the data in the forging data set is cleaned and fused, and the forging data set is divided into a training set and a validation set at a ratio of 8:2; Use the grid search method to adjust the forging frequency optimization model, and select the forging frequency optimization model with the highest score for training; use the divided training set to train the forging frequency optimization model, adjust the network parameters through the back propagation algorithm, and use the early stopping strategy to avoid overfitting; Use the divided validation set to evaluate the trained forging frequency optimization model and calculate the error index of the forging frequency optimization model; set the threshold. If it exceeds the threshold, readjust the forging frequency optimization model; if it is lower than the threshold, perform feature extraction analysis.

5. The forging frequency optimization method of a high-efficiency radial forging machine as claimed in claim 4, characterized in that: The process of building a forging dataset includes: Collect the historical forging data and forging results of the target radial forging machine, and check the missing values ​​in the data set; if missing values ​​occur, use mean filling to process them; Draw a box plot of the forging parameters and process characteristic values ​​of the target radial forging machine; calculate the upper quartile, lower quartile and interquartile range of each parameter, and determine the upper and lower thresholds; mark the values ​​below the lower limit or above the upper limit as outliers, and analyze the outliers by replacement or deletion methods; The extracted structural parameters and flow field characteristics are standardized; data from different sources or formats are integrated to form a unified data set.

6. The forging frequency optimization method of a high-efficiency radial forging machine according to claim 4, characterized in that: The process of training the forging frequency optimization model using the divided training set includes: Design the network structure of the forging frequency optimization model and select the number of hidden layers; select the activation function and loss function corresponding to the target longitudinal forging direction; input the divided training set into the forging frequency optimization model, and use the optimizer to adjust the network weights and biases of the forging frequency optimization model; Determine the value range of the learning rate, number of hidden layers, number of nodes, and batch size hyperparameters; form a grid with all hyperparameters, and use the divided training set to train the forging frequency optimization model for each hyperparameter combination in the grid; Use the divided validation set to verify the mean square error and accuracy of the forging frequency optimization model after each training, set the threshold, and select the forging frequency optimization model corresponding to the hyperparameter combination with the smallest error compared to the threshold as the final forging frequency optimization model.

7. The forging frequency optimization method of a high-efficiency radial forging machine according to claim 1, characterized in that: The process of optimizing the forging parameters of the radial forging machine includes: According to the results of the forging frequency optimization model analysis, an orthogonal table of forging parameters is established to obtain the peak values ​​of each group of forging frequency optimization parameters; According to the peak value data of the optimized parameters in the orthogonal table of forging parameters, each optimized parameter is divided into three levels and the level is evaluated, and the level threshold is set. If the parameter value is judged to be lower than the preset level threshold, the orthogonal table parameter peak value is used for optimization; According to the parameter values ​​optimized by the orthogonal table of forging parameters, the servo motor of the radial forging machine is adjusted. The vibration frequency and amplitude during the forging process are adjusted by adjusting the speed of the servo motor. The changes of forging parameters are monitored, and the speed is optimized and adjusted according to the changes of forging parameters.

8. The forging frequency optimization method of a high-efficiency radial forging machine according to claim 7, characterized in that: The process of optimizing the peak value of orthogonal array parameters includes: Obtaining forging parameters of forging speed, pressure and heating time during the forging process of the radial forging machine after pretreatment, setting the forging parameters as design variables, and taking forging efficiency as the optimization target; The functional relationship between forging parameters and forging efficiency is fitted by a multivariate quadratic equation; the peak value data of optimized parameters in the orthogonal table of forging parameters are graded and divided into three grades: A, B, and C; If the target radial forging machine optimization parameter evaluation level is C, the optimal result of the forging parameter and forging efficiency fitting is used as the optimization parameter. If the target radial forging machine optimization parameter evaluation level is A or B, the optimization parameter peak data is kept unchanged and monitoring is continued.

9. The forging frequency optimization method of a high-efficiency radial forging machine according to claim 7, characterized in that: The process of adjusting the vibration frequency and amplitude during forging by adjusting the speed of the servo motor includes: Set the basic parameters of the servo motor of the target forging machine, including rated voltage, current and speed, and adjust the proportional, integral and differential parameters of the speed loop to accurately control the servo motor; Gradually increase or decrease the speed of the servo motor, monitor the changes in vibration frequency and amplitude, and monitor the changes in forging parameters, and adjust the speed according to the changes in forging parameters to make the forging parameters reach the peak value data of the orthogonal table optimization parameters; After completing the adjustment of the servo motor of the target forging machine, the target forging machine is experimentally verified, and its control accuracy, stability and forging frequency are tested. The servo motor speed is adjusted according to the test results until the forging frequency reaches the peak value.

10. A forging frequency optimization system for a high-efficiency radial forging machine, implementing the forging frequency optimization method for a high-efficiency radial forging machine as described in any one of claims 1 to 9, characterized in that: include: The forging parameter collection module is used to collect the forging speed, pressure and heating time forging parameters of the radial forging machine during the forging process, and pre-process the collected forging parameters; The forging frequency optimization model module is used to establish a forging frequency optimization model based on the historical forging data and forging results of the target radial forging machine, input the pre-processed forging speed, pressure and heating time forging parameters, and optimize the forging parameters; The forging parameter optimization module is used to optimize the forging parameters of the radial forging machine according to the results of the frequency optimization model optimization analysis, and adjust the vibration frequency and amplitude during the forging process to control the change of the forging force.

Images