Method for monitoring state of cold header for bolt machining

Abstract

The invention provides a method for monitoring the state of a cold header for bolt machining. The method comprises the steps that historical mold state parameters obtained by detecting a mold of the cold header and detected production parameters are obtained; wherein the mold state parameters comprise one or more of the abrasion degree, the deformation amount, the crack condition, the smooth degree, the hardness and fatigue damage, and the production parameters comprise one or more of the bolt model, the punching force, the feeding speed, the lubricating condition and the mold temperature; inputting the punching times and / or the production duration of the cold header after detection into a prediction model corresponding to the model and the production parameters of the die to obtain the die state parameter variable quantity of the cold header; and real-time mold state parameters of the cold header are determined based on the historical mold state parameters and the mold state parameter variable quantity. According to the invention, on-line monitoring of the state of the cold header die can be realized.

Description

Technical Field

[0001] The present invention relates to the technical field of equipment status monitoring, and particularly to a method for monitoring the status of a cold heading machine for bolt processing. Background Art

[0002] A cold heading machine is a device used for metal plastic forming. Its principle is to apply pressure to a metal blank through a die at room temperature to cause plastic deformation, thereby forming parts with the required shape and size.

[0003] Currently, the status detection of cold heading machines mainly focuses on the detection after die breakage. These detection technologies can only make simple judgments on die damage or detect the presence or absence of materials. They can only stop the machine after the die is severely damaged, and cannot perform online status monitoring of cold heading machines. It is difficult to detect the abnormal status of cold heading machines in a timely manner and make adjustments, and it is impossible to improve the service life of the die. Summary of the Invention

[0004] An embodiment of the present invention provides a method for monitoring the status of a cold heading machine for bolt processing to solve the problem of online status monitoring of cold heading machines.

[0005] In a first aspect, an embodiment of the present invention provides a method for monitoring the status of a cold heading machine for bolt processing, including: Obtaining historical die status parameters obtained by detecting the die of the cold heading machine and production parameters after detection; wherein, the die status parameters include one or more of wear degree, deformation amount, crack condition, smoothness, hardness, and fatigue damage, and the production parameters include one or more of bolt model, punching pressure, feeding speed, lubrication condition, and die temperature; Inputting the number of punching times and / or production duration of the cold heading machine after detection into a prediction model corresponding to the die model and production parameters to obtain the change amount of the die status parameters of the cold heading machine; Based on the historical die status parameters and the change amount of the die status parameters, determining the real-time die status parameters of the cold heading machine.

[0006] In a possible implementation manner, before inputting the number of punching times and / or production duration of the cold heading machine after detection into a status change prediction model corresponding to the die model and production parameters to obtain the change amount of the die status parameters of the cold heading machine, it further includes: For multiple combinations of die models and production parameters, performing punching tests on multiple cold heading machines with different numbers of punching times and production durations, and recording the change amounts of various die status parameters of each cold heading machine before and after the test; Take the number of stamping times and / or production duration of each trial of the combination of the mold of the first model and the first production parameters as input variables, and take the change amount of the mold state parameters after each trial as the label to form a training data set, and train the initial model based on the training data set to obtain a prediction model corresponding to the first model and the first production parameters; where the first model is any model and the first production parameters are any production parameters.

[0007] In a possible implementation, taking the number of stamping times and / or production duration of each trial of the combination of the mold of the first model and the first production parameters as input variables, and taking the change amount of the mold state parameters after each trial as the label to form a training data set, and training the initial model based on the training data set to obtain a prediction model corresponding to the first model and the first production parameters includes: Take the number of stamping times of each trial of the combination of the mold of the first model and the first production parameters as the input variable, and take the change amount of the mold state parameters after each trial as the label to form the first training data set; Take the production duration of each trial of the combination of the mold of the first model and the first production parameters as the input variable, and take the change amount of the mold state parameters after each trial as the label to form the second training data set; Take the number of stamping times and production duration of each trial of the combination of the mold of the first model and the first production parameters as the input variable, and take the change amount of the mold state parameters after each trial as the label to form the third training data set; Train the first initial model based on the first training data set to obtain the first candidate model corresponding to the first model and the first production parameters; Train the second initial model based on the second training data set to obtain the second candidate model corresponding to the first model and the first production parameters; Train the third initial model based on the second training data set to obtain the third candidate model corresponding to the first model and the first production parameters; Obtain the prediction model corresponding to the first model and the first production parameters based on the prediction errors of the first candidate model, the second candidate model or the third candidate model.

[0008] In a possible implementation, obtaining the prediction model corresponding to the first model and the first production parameters based on the prediction errors of the first candidate model, the second candidate model or the third candidate model includes: Take the candidate model with the smallest prediction error among the first candidate model, the second candidate model and the third candidate model as the prediction model corresponding to the first model and the first production parameters.

[0009] In a possible implementation, the first initial model is a support vector machine, the second initial model is a linear regression model, and the third initial model is a random forest model.

[0010] In a possible implementation, there are multiple groups of production parameters after detection; the number of stamping operations and / or production duration of the cold heading machine after detection are input into a prediction model corresponding to the mold type and production parameters to obtain the change amount of the mold state parameters of the cold heading machine, including: For each group of production parameters, after the cold heading machine is detected, the number of stamping operations and / or production duration corresponding to this group of production parameters are input into a prediction model corresponding to the mold type and this group of production parameters to obtain the change amount of the state parameters corresponding to this group of production parameters.

[0011] In a possible implementation, before conducting stamping tests with different numbers of stamping operations and production durations on multiple cold heading machines for multiple combinations of mold types and production parameters and recording the change amounts of various mold state parameters of each cold heading machine before and after the tests, it further includes: Conduct an interaction effect analysis on the production parameters and mold state parameters to obtain the combination of production parameter categories for predicting each combination of mold state parameter categories; wherein, each combination of mold state parameter categories has different categories of mold state parameters, and each combination of production parameter categories has different categories of production parameters.

[0012] In a second aspect, an embodiment of the present invention provides a state monitoring device for a cold heading machine used for bolt processing, including: An acquisition module, configured to acquire the historical mold state parameters obtained by detecting the mold of the cold heading machine and the production parameters after detection; wherein, the mold state parameters include one or more of wear degree, deformation amount, crack condition, smoothness, hardness, and fatigue damage, and the production parameters include one or more of bolt model, punching force, feeding speed, lubrication condition, and mold temperature; A prediction module, configured to input the number of stamping operations and / or production duration of the cold heading machine after detection into a prediction model corresponding to the mold type and production parameters to obtain the change amount of the mold state parameters of the cold heading machine; A calculation module, configured to determine the real-time mold state parameters of the cold heading machine based on the historical mold state parameters and the change amount of the mold state parameters.

[0013] In a third aspect, an embodiment of the present invention provides a terminal, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps of the method described in the first aspect or any possible implementation manner of the first aspect above.

[0014] Fourthly, an embodiment of the present invention provides a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, the steps of the method described in the first aspect above or any possible implementation manner of the first aspect are implemented.

[0015] An embodiment of the present invention provides a method for monitoring the state of a cold heading machine for bolt processing. By acquiring and using historical die state parameters and production parameters, and combining various factors such as bolt models and die models, a prediction model based on actual operation data can be established, which can realize online monitoring of the die state of the cold heading machine, timely discover and solve die problems, reduce unplanned downtime caused by die failures, and improve overall production efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the following drawings are only some embodiments of the present invention, and those of ordinary skill in the art can obtain other drawings without creative efforts based on these drawings.

[0017] Figure 1 is a flowchart of the implementation of a method for monitoring the state of a cold heading machine for bolt processing provided by an embodiment of the present invention; Figure 2 is a schematic structural diagram of a device for monitoring the state of a cold heading machine for bolt processing provided by an embodiment of the present invention; Figure 3 is a schematic diagram of a terminal provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0018] In the following description, specific details such as specific system structures and technologies are presented for the purpose of illustration rather than limitation, so as to thoroughly understand the embodiments of the present invention. However, those skilled in the art should clearly understand that the present invention can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid unnecessary details from interfering with the description of the present invention.

[0019] To make the objectives, technical solutions, and advantages of the present invention clearer, the following will be described through specific embodiments in conjunction with the drawings.

[0020] See Figure 1 , which shows a flowchart of the implementation of a method for monitoring the state of a cold heading machine for bolt processing provided by an embodiment of the present invention, and is described in detail as follows: Step 101: Obtain the historical die state parameters obtained from the inspection of the cold heading machine die and the production parameters after the inspection; among them, the die state parameters include one or more of the wear degree, deformation amount, crack condition, smoothness, hardness, and fatigue damage, and the production parameters include one or more of the bolt model, punching pressure, feeding speed, lubrication condition, and die temperature.

[0021] In this embodiment, the die state parameters are parameters describing the life and health state of the cold heading machine die. Among them, the wear degree refers to the material loss on the die surface due to long-term contact with the workpiece, and can be evaluated by measuring the change in the surface roughness of the die or directly measuring the dimensional deviation. For example, when measuring the diameter change of a key part of the die, the initial diameter is 50 mm, and it becomes 49.98 mm after being used for a period of time, then the wear amount is 0.02 mm.

[0022] The crack condition is the crack or breakage condition that may occur on the die under the action of high pressure and impact force, and non-destructive testing techniques (such as ultrasonic testing, magnetic particle inspection, etc.) are used for regular inspection. The evaluation indicators can include crack length, crack depth, and crack number.

[0023] The deformation amount is used to describe the shape change of the die due to long-term stress, and the dimensional change of the key part of the die can be detected by a precision measuring tool (such as a coordinate measuring machine). For example, the designed height of a certain plane of the die is 10 mm, and the actual measured value is 10.03 mm, then the deformation amount is 0.03 mm.

[0024] The smoothness of the die surface directly affects the quality of the workpiece, and a surface roughness meter is used for measurement. Common evaluation indicators include Ra (arithmetic mean deviation), Rz (maximum height difference), etc.

[0025] Hardness can reflect the ability of the die material to resist local plastic deformation, and a Rockwell hardness tester or a Vickers hardness tester is used for testing.

[0026] Fatigue damage is the accumulation of minute damage on the die under repeated loading, which may lead to final failure. Under laboratory conditions, the crack propagation rate can be tested by a fatigue testing machine, and the degree of fatigue damage can be evaluated accordingly.

[0027] Due to differences in geometric shape, dimensional accuracy requirements, and material properties of different types of bolt products, they have different degrees of influence on the state of the cold heading machine die during the production process. The characteristics of common types of bolts and their influence on the die are as follows: Standard hexagon head bolt: The head is a standard hexagon, the shank is threaded, the head size and thread accuracy have high requirements, usually low-carbon steel or medium-carbon steel is used, and sometimes high-strength alloy steel is also used. The forming of the hexagon head requires precise molds, so the mold surface is prone to wear due to frequent contact, especially at the hexagon die. If the punching pressure is set improperly, it may cause the mold to deform and affect the forming quality of the hexagon head. High-hardness materials may produce cracks during the forming process, especially at the mold edges and sharp corners.

[0028] Socket head cap screw: The head is an internal hexagon, the shank is threaded, the size and depth of the internal hexagon hole in the head have extremely high requirements, and high-strength alloy steel is usually used to meet the higher strength requirements. Excessive punching pressure may damage the mold or cause workpiece deformation. The forming process of the internal hexagon hole has high requirements for the rigidity of the mold, and improper pressure setting may cause the mold to deform.

[0029] Countersunk head screw: The head is a countersunk head design, usually used for flush mounting. The head thickness and flatness have extremely high requirements. Common materials include low-carbon steel, stainless steel, etc. Low-toughness materials may produce cracks during the forming process, especially at the mold edges and sharp corners.

[0030] Flange bolt: The head has a flange surface to increase the contact area. The flatness and diameter of the flange surface have extremely high requirements. Common materials include low-carbon steel, medium-carbon steel, etc.

[0031] High-strength bolt: Similar to the standard bolt, but usually has higher strength requirements. High-strength alloy steel or other special materials are usually used. High-strength materials cause greater wear to the mold during the forming process, especially the mold surface and the forming area.

[0032] Step 102, input the number of stamping times and / or production duration after the cold heading machine is detected into the prediction model corresponding to the mold model and production parameters to obtain the change amount of the mold state parameters of the cold heading machine.

[0033] In this embodiment, the cold heading machine mold usually includes several main parts such as the mold body, punch, die, and ejector device. In addition to production parameters, mold material and size are also factors affecting mold life and health status. By constructing a prediction model through the mold model and production parameters, these influencing factors can be considered together to ensure that the prediction results are more comprehensive and accurate.

[0034] During each stamping process, the die is subjected to certain stresses and frictions, which will gradually cause wear of the die. As the number of stampings increases, the degree of wear will gradually accumulate. The die material will suffer fatigue damage under repeated loading, and this damage also accumulates over time (i.e., production duration) and the number of stampings. The number of stampings and / or production duration can reflect the cumulative effect and the trend of state change of the die during the actual production process. Taking them as input variables, the prediction model can provide the trend of change of the die state, which helps to detect potential problems in advance, so as to take preventive maintenance measures and avoid production line downtime caused by sudden failures.

[0035] Step 103: Determine the real-time die state parameters of the cold heading machine based on the historical die state parameters and the change amount of the die state parameters.

[0036] In this embodiment, it is assumed that a certain factory uses a cold heading machine to manufacture standard hexagon head bolts, and state parameters such as the degree of wear, deformation amount, and crack condition of the same die under different production conditions in the past few months are collected, as well as production parameters such as the stamping force, feeding speed, lubrication condition, and die temperature corresponding thereto.

[0037] When the die is put into production again, input the current number of stampings and production duration into the prediction model, and the model outputs the predicted change amount of the die state parameters, such as the predicted wear increase of 0.01 mm.

[0038] Combining the historical die state parameters (such as the initial wear of 0.02 mm) recorded during the last inspection and the predicted change amount (0.01 mm) this time, the actual wear degree of the current die is obtained as 0.03 mm.

[0039] Through this embodiment, the health state of the die of the cold heading machine can be evaluated in real time, so that the operator can always understand the actual health condition of the die, rather than just relying on regular inspections.

[0040] By obtaining and using historical die state parameters and production parameters, and combining various factors such as bolt models and die models, the embodiment of the present invention can establish a prediction model based on actual operation data, which can realize online monitoring of the die state of the cold heading machine, timely discover and solve die problems, reduce the unplanned downtime caused by die failures, and improve the overall production efficiency.

[0041] In a possible implementation manner, before inputting the number of stampings and / or production duration of the cold heading machine after detection into the state change prediction model corresponding to the die model and production parameters to obtain the change amount of the die state parameters of the cold heading machine, it further includes: For multiple combinations of die models and production parameters, multiple cold heading machines are subjected to stamping tests with different numbers of stamping operations and production durations, and the change amounts of various die state parameters of each cold heading machine before and after the tests are recorded. Take the number of stamping operations and / or production duration of each test for the combination of the first die model and the first production parameter as input variables, and the change amount of the die state parameters after each test as labels to form a training data set, and train an initial model based on the training data set to obtain a prediction model corresponding to the first die model and the first production parameter; where the first die model is any model, and the first production parameter is any production parameter.

[0042] In this embodiment, multiple die models refer to different dies used to produce bolts (or other fasteners) of different types or specifications. Each die model may have different geometric shapes, dimensional accuracy requirements, material properties, etc.

[0043] Multiple production parameters refer to various parameters that can be adjusted during the production process, including but not limited to stamping pressure, feeding speed, lubrication conditions, die temperature, etc. Different production parameter settings will affect the product quality and the die state.

[0044] The combination of multiple die models and multiple production parameters refers to considering all possible combinations between different types of dies and various production parameter settings. For example, a die for a specific type of hexagon head bolt may be tested at different stamping pressures and feeding speeds to determine the optimal production conditions, thereby ensuring product quality and extending the die service life.

[0045] It is possible to determine the change characteristics of die state parameters (wear, deformation, crack, smoothness, hardness, and fatigue damage) of a certain die model under specific production parameters (stamping pressure, feeding speed, lubrication conditions, and die temperature) through tests, and use this as a data sample to train the model to obtain a model that can predict the change of die state parameters, so as to use the trained prediction model to monitor the change of die state parameters in real time during the subsequent production process.

[0046] Specifically, the die model and production parameters to be studied can be selected as factors (such as stamping pressure, feeding speed, lubrication conditions, die temperature), and several different level values (such as low, medium, and high levels) are set for each factor, that is, a combination of multiple die models and multiple production parameters is obtained. Then, tests are carried out under each combination of die model and production parameters and test data are collected, so as to analyze the change trend of die state parameters under each combination, and finally a comprehensive influence relationship map is obtained.

[0047] In a possible implementation, the number of stamping operations and / or production duration of each trial of the combination of the mold of the first model and the first production parameters are used as input variables, and the change amount of the mold state parameters after each trial is used as a label to form a training data set. Then, the initial model is trained based on the training data set to obtain a prediction model corresponding to the first model and the first production parameters, including: Using the number of stamping operations of each trial of the combination of the mold of the first model and the first production parameters as an input variable, and the change amount of the mold state parameters after each trial as a label, to form a first training data set; Using the production duration of each trial of the combination of the mold of the first model and the first production parameters as an input variable, and the change amount of the mold state parameters after each trial as a label, to form a second training data set; Using the number of stamping operations and production duration of each trial of the combination of the mold of the first model and the first production parameters as input variables, and the change amount of the mold state parameters after each trial as a label, to form a third training data set; Training the first initial model based on the first training data set to obtain a first candidate model corresponding to the first model and the first production parameters; Training the second initial model based on the second training data set to obtain a second candidate model corresponding to the first model and the first production parameters; Training the third initial model based on the third training data set to obtain a third candidate model corresponding to the first model and the first production parameters; Obtaining a prediction model corresponding to the first model and the first production parameters based on the prediction errors of the first candidate model, the second candidate model, or the third candidate model.

[0048] In this embodiment, the number of stamping operations, the production duration, or a combination of both are used as input variables, and the change amount of the mold state parameters is used as a label to construct different training data sets. Then, machine learning algorithms are used to train each training data set to obtain multiple candidate models, and finally the optimal model is selected from them to predict the change of the mold state parameters.

[0049] This method models for a specific mold model and production parameter combination, making the model more targeted and better able to reflect the actual situation.

[0050] In a possible implementation, obtaining a prediction model corresponding to the first model and the first production parameters based on the prediction errors of the first candidate model, the second candidate model, or the third candidate model, includes: Taking the candidate model with the smallest prediction error among the first candidate model, the second candidate model, and the third candidate model as the prediction model corresponding to the first model and the first production parameters.

[0051] In this embodiment, the performance of each candidate model can be evaluated on a test set or in an actual production environment, and metrics such as mean squared error (MSE), mean absolute error (MAE), and coefficient of determination R² are calculated to ensure that the model has good predictive ability.

[0052] In a possible implementation, the first initial model is a support vector machine, the second initial model is a linear regression model, and the third initial model is a random forest model.

[0053] In this embodiment, the random forest model can handle non - linear relationships and complex interaction effects. When the changes in die state parameters involve multiple non - linear factors and complex interactions, the random forest model can better capture these patterns. The support vector machine is good at classification and regression tasks in high - dimensional spaces, especially performing well when the feature dimension is high and the number of samples is small. The linear regression model is suitable for simple linear relationships and has strong interpretability. Combining these three models can better capture various patterns in the data.

[0054] By using different types of models, the performance of different models for a specific task when using different input parameters can be evaluated more comprehensively, so as to select the most suitable model.

[0055] In a possible implementation, the production parameters after detection are multiple groups; the number of stamping times and / or production duration of the cold - heading machine after detection are input into a prediction model corresponding to the die model and production parameters, and the change amount of the die state parameters of the cold - heading machine is obtained, including: For each group of production parameters, after the cold - heading machine is detected, the number of stamping times and / or production duration corresponding to this group of production parameters are input into a prediction model corresponding to the die model and this group of production parameters, and the change amount of the state parameters corresponding to this group of production parameters is obtained.

[0056] In this embodiment, after the cold - heading machine is detected, it may undergo production for a long time, and various production parameters may change during the production process. At this time, the time nodes when the production parameters change can be identified and divided. For example, reasonable ranges and intervals are set for each key parameter. For example, the punching pressure can be set to three levels: low (5 tons), medium (10 tons), and high (15 tons); the feeding speed can be set to three levels: slow, medium, and fast. Different values of each key parameter are combined to form multiple groups of production parameters. Then, the specific production parameters in the actual production process are matched with the previously set ranges, so as to select a suitable prediction model.

[0057] Suppose that during the monitoring period of a cold heading machine, the production parameters change once. Before the time node of the change, the production parameters used are "medium" punching pressure and "fast" feeding speed, and during this period, the number of punching operations = 1000 times, and the production duration = 5 hours. Then, the corresponding prediction model is called to obtain the predicted value of the die wear degree in the previous period (such as the predicted wear amount is 0.02 mm). After the production parameters change, the production parameters used are "low" punching pressure and "fast" feeding speed, and during this period, the number of punching operations = 600 times, and the production duration = 3 hours. The corresponding prediction model is called to obtain the predicted value of the die wear degree in the previous period (such as the predicted wear amount is 0.01 mm). Then, the two predicted values are added together to obtain a total wear amount of 0.03 mm during the overall monitoring period.

[0058] In this embodiment, training the model separately for each set of production parameters can more accurately capture the change law of the die state under this set of parameters, thereby improving the prediction accuracy.

[0059] In a possible implementation manner, before performing stamping tests with different numbers of stamping operations and production durations on multiple cold heading machines for multiple combinations of die models and production parameters and recording the change amounts of various die state parameters of each cold heading machine before and after the test, it further includes: Performing an interaction effect analysis on the production parameters and die state parameters to obtain the production parameter category combinations for predicting each combination of die state parameter categories; wherein, each combination of die state parameter categories has different categories of die state parameters, and each combination of production parameter categories has different categories of production parameters.

[0060] In this embodiment, the die state parameters refer to various indicators describing the current condition of the die, such as wear degree, deformation amount, crack condition, smoothness, hardness, and fatigue damage. The combination of die state parameter categories is used to comprehensively evaluate the overall health status of the die by considering multiple state parameters simultaneously. Since a single state parameter may not fully reflect the actual state of the die, it is necessary to consider multiple state parameters comprehensively. By comprehensively analyzing multiple die state parameters, it is possible to more accurately determine whether the die needs maintenance or replacement. For example, even if the die surface looks smooth and there are no obvious cracks, but if a significant decrease in hardness or slight deformation is detected, it indicates that the die may be approaching the limit of its service life.

[0061] The production parameters include various adjustable factors such as punching pressure, feeding speed, lubrication conditions, and die temperature. The combination of production parameter categories refers to classifying the above individual production parameters according to certain standards or ranges and forming different combination forms. For example, certain categories of die state parameters are only affected by punching pressure and feeding speed.

[0062] To determine the optimal production parameter category combination for predicting each die state parameter category combination based on the analysis results, the following steps can be adopted to implement the interaction effect analysis: Select the production parameters to be studied as factors (such as punching pressure, feeding speed, lubrication condition, die temperature), and set several different level values for each factor (such as low, medium, high levels). Use an orthogonal table (such as L9(3^4)) to design the experimental scheme to minimize the number of experiments while maximizing information acquisition.

[0063] Conduct experiments according to the designed experimental scheme, and record the die state parameter values after each experiment. First, perform single-factor analysis to separately examine the influence of each production parameter on the die state parameters and draw trend charts. Then, adopt multiple regression analysis or analysis of variance (ANOVA) to evaluate the influence of multiple production parameters acting together on the die state parameters, check the significance of the interaction terms (judged by the p-value), determine which interaction effects significantly affect the die state parameters, and thus determine the production parameter category combination for predicting each die state parameter category combination. When conducting subsequent experiments and constructing the training dataset, only the necessary die state parameter categories and production parameter category combinations can be retained to reduce the number of experiments.

[0064] It should be understood that the magnitudes of the sequence numbers of the steps in the above embodiments do not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.

[0065] The following is the device embodiment of the present invention. For the details not described in detail, reference can be made to the corresponding method embodiments above.

[0066] Figure 2 The structural schematic diagram of a cold heading machine state monitoring device for bolt processing provided by the embodiment of the present invention is shown. For the convenience of description, only the parts related to the embodiment of the present invention are shown and are described in detail as follows: As Figure 2 shown, a cold heading machine state monitoring device 2 for bolt processing includes: An acquisition module 21, configured to acquire historical die state parameters obtained by detecting the die of the cold heading machine and production parameters after detection; wherein, the die state parameters include one or more of wear degree, deformation amount, crack condition, smoothness, hardness, and fatigue damage, and the production parameters include one or more of bolt model, punching pressure, feeding speed, lubrication condition, and die temperature; A prediction module 22, configured to input the number of stamping times and / or production duration after detection of the cold heading machine into a prediction model corresponding to the die model and production parameters to obtain the change amount of the die state parameters of the cold heading machine; The calculation module 23 is configured to determine the real-time die state parameters of the cold heading machine based on the historical die state parameters and the change amount of the die state parameters.

[0067] In a possible implementation manner, the prediction module 22 is specifically configured to: Before inputting the number of stamping times and / or production duration of the cold heading machine after detection into the state change prediction model corresponding to the die model and production parameters to obtain the change amount of the die state parameters of the cold heading machine, for combinations of multiple die models and multiple production parameters, multiple stamping tests with different numbers of stamping times and production durations are performed on multiple cold heading machines, and the change amounts of various die state parameters of each cold heading machine before and after the tests are recorded; Taking the number of stamping times and / or production duration of each test of the combination of the first die model and the first production parameters as input variables, and the change amount of the die state parameters after each test as labels, a training data set is formed, and the initial model is trained based on the training data set to obtain the prediction model corresponding to the first die model and the first production parameters; wherein, the first die model is any die model, and the first production parameters are any production parameters.

[0068] In a possible implementation manner, the prediction module 22 is specifically configured to: Taking the number of stamping times of each test of the combination of the first die model and the first production parameters as input variables, and the change amount of the die state parameters after each test as labels, a first training data set is formed; Taking the production duration of each test of the combination of the first die model and the first production parameters as input variables, and the change amount of the die state parameters after each test as labels, a second training data set is formed; Taking the number of stamping times and production duration of each test of the combination of the first die model and the first production parameters as input variables, and the change amount of the die state parameters after each test as labels, a third training data set is formed; Training the first initial model based on the first training data set to obtain the first candidate model corresponding to the first die model and the first production parameters; Training the second initial model based on the second training data set to obtain the second candidate model corresponding to the first die model and the first production parameters; Training the third initial model based on the second training data set to obtain the third candidate model corresponding to the first die model and the first production parameters; Obtaining the prediction model corresponding to the first die model and the first production parameters based on the prediction errors of the first candidate model, the second candidate model or the third candidate model.

[0069] In a possible implementation manner, the prediction module 22 is specifically configured to: Select the candidate model with the smallest prediction error among the first candidate model, the second candidate model, and the third candidate model as the prediction model corresponding to the first model and the first production parameters.

[0070] In a possible implementation, the first initial model is a support vector machine, the second initial model is a linear regression model, and the third initial model is a random forest model.

[0071] In a possible implementation, there are multiple sets of production parameters after detection; the prediction module 22 is specifically configured to: For each set of production parameters, after the cold heading machine is detected, input the number of stamping times and / or production duration corresponding to this set of production parameters into the prediction model corresponding to the model of the die and this set of production parameters, and obtain the change amount of the state parameters corresponding to this set of production parameters.

[0072] In a possible implementation, the prediction module 22 is further configured to: Before conducting stamping tests with different numbers of stamping times and production durations on multiple cold heading machines for combinations of multiple die models and multiple production parameters, and recording the change amounts of various die state parameters of each cold heading machine before and after the tests, perform an interaction effect analysis on the production parameters and the die state parameters to obtain the production parameter category combinations used to predict each die state parameter category combination; where each die state parameter category combination has different categories of die state parameters, and each production parameter category combination has different categories of production parameters.

[0073] By obtaining and using historical die state parameters and production parameters, and combining various factors such as bolt models and die models, the embodiments of the present invention can establish a prediction model based on actual operation data, which can realize online monitoring of the die state of the cold heading machine, promptly discover and solve die problems, reduce the unplanned downtime caused by die failures, and improve the overall production efficiency.

[0074] Figure 3 It is a schematic diagram of the terminal provided by the embodiments of the present invention. As Figure 3 shown, the terminal 3 of this embodiment includes: a processor 30, a memory 31, and a computer program 32 stored in the memory 31 and executable on the processor 30. When the processor 30 executes the computer program 32, it implements the steps in each of the above embodiments of the method for monitoring the state of a cold heading machine for bolt processing, such as Figure 1 the steps 101 to 103 shown. Alternatively, when the processor 30 executes the computer program 32, it implements the functions of each module / unit in each of the above device embodiments, such as Figure 2 the functions of the modules / units 21 to 23 shown.

[0075] Exemplarily, the computer program 32 can be divided into one or more modules / units, and the one or more modules / units are stored in the memory 31 and executed by the processor 30 to implement the present invention. The one or more modules / units can be a series of computer program instruction segments capable of performing specific functions, and these instruction segments are used to describe the execution process of the computer program 32 in the terminal 3. For example, the computer program 32 can be divided into Figure 2 the module / units 21 to 23 shown.

[0076] The terminal 3 can be a computing device such as a desktop computer, a notebook, a palm computer, and a cloud server. The terminal 3 may include, but is not limited to, a processor 30 and a memory 31. Those skilled in the art can understand that Figure 3 merely examples of the terminal 3 do not constitute a limitation on the terminal 3, and it may include more or fewer components than shown in the figure, or combine certain components, or different components. For example, the terminal may further include input / output devices, network access devices, a bus, etc.

[0077] The so-called processor 30 may be a central processing unit (CPU), or may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0078] The memory 31 may be an internal storage unit of the terminal 3, such as the hard disk or memory of the terminal 3. The memory 31 may also be an external storage device of the terminal 3, such as a plug-in hard disk equipped on the terminal 3, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. Further, the memory 31 may also include both the internal storage unit and the external storage device of the terminal 3. The memory 31 is used to store the computer program and other programs and data required by the terminal 3. The memory 31 may also be used to temporarily store data that has been output or will be output.

[0079] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above-mentioned division of each functional unit and module is used as an example. In actual applications, the above functions can be allocated to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment can be integrated into a processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above integrated unit can be implemented in the form of hardware or in the form of a software functional unit. In addition, the specific names of each functional unit and module are only for the convenience of mutual distinction and do not limit the protection scope of this application. The specific working processes of the units and modules in the above system can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0080] In the above embodiments, the descriptions of the respective embodiments have their own emphases. For the parts not detailed or recorded in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0081] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or by a combination of computer software and electronic hardware. Whether these functions are executed in the form of hardware or software depends on the specific application and design constraints of the technical solution. Professionals can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0082] In the embodiments provided by the present invention, it should be understood that the disclosed device / terminal and method can be implemented in other ways. For example, the device / terminal embodiments described above are only illustrative. For example, the division of the above-mentioned module or unit is only a logical function division. In actual implementation, there may be other division methods. For example, 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 displayed or discussed coupling or direct coupling or communication connection between each other can be through some interfaces. The indirect coupling or communication connection of the device or unit can be in an electrical, mechanical or other form.

[0083] The unit described as a separated component may or may not be physically separated, and the component displayed as a unit may or may not be a physical unit, that is, it may be located in one place, or may be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0084] In addition, in each embodiment of the present invention, each functional unit can be integrated into a processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of a software functional unit.

[0085] If the integrated module / 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 such an understanding, to implement all or part of the processes in the above-mentioned embodiment methods of the present invention, it can also be completed by instructing relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above-mentioned various embodiments of a cold heading machine state monitoring method for bolt processing can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disc, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc. It should be noted that the content included in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electrical carrier signals and telecommunication signals.

[0086] The above-mentioned embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the various embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A method for monitoring the state of a cold heading machine for bolt processing, characterized in that: include: Acquire historical mold state parameters and production parameters after the detection obtained by detecting the mold of the cold heading machine; wherein the mold state parameters include one or more of the degree of wear, deformation, crack condition, smoothness, hardness and fatigue damage, and the production parameters include one or more of the bolt model, punching force, feed speed, lubrication condition and mold temperature; Inputting the number of punching times and / or production time of the cold heading machine after the detection into a prediction model corresponding to the model of the mold and the production parameters to obtain a change in the mold state parameter of the cold heading machine; Based on the historical mold state parameters and the mold state parameter changes, the real-time mold state parameters of the cold heading machine are determined.

2. A method for monitoring the state of a cold heading machine for bolt processing according to claim 1, characterized in that: Before inputting the number of punching times and / or production time of the cold heading machine after the detection into the state change prediction model corresponding to the model of the mold and the production parameters to obtain the change amount of the mold state parameter of the cold heading machine, the method further includes: For various types of molds and various combinations of production parameters, multiple cold heading machines were subjected to multiple stamping tests with different stamping times and production times, and the changes in various mold state parameters of each cold heading machine before and after the test were recorded; The number of stampings and / or production time of each test of the combination of a first model of a mold and a first production parameter is used as an input variable, and the change in the mold state parameter after each test is used as a label to form a training data set, and an initial model is trained based on the training data set to obtain a prediction model corresponding to the first model and the first production parameter; wherein the first model is any model, and the first production parameter is any production parameter.

3. A method for monitoring the state of a cold heading machine for bolt processing according to claim 2, characterized in that: The method uses the number of stamping times and / or production time of each test of the combination of the first model of the mold and the first production parameter as input variables, and the change amount of the mold state parameter after each test as a label to form a training data set, and trains the initial model based on the training data set to obtain a prediction model corresponding to the first model and the first production parameter, including: The number of stampings in each test of the combination of the first model of mold and the first production parameter is used as an input variable, and the change amount of the mold state parameter after each test is used as a label to form a first training data set; The production time of each test of the combination of the first model of mold and the first production parameter is used as an input variable, and the change amount of the mold state parameter after each test is used as a label to form a second training data set; The number of stampings and the production time of each test of the combination of the first model of mold and the first production parameter are used as input variables, and the change amount of the mold state parameter after each test is used as a label to form a third training data set; Training a first initial model based on the first training data set to obtain a first candidate model corresponding to the first model and the first production parameter; Training a second initial model based on the second training data set to obtain a second candidate model corresponding to the first model and the first production parameter; Training a third initial model based on the second training data set to obtain a third candidate model corresponding to the first model and the first production parameter; A prediction model corresponding to the first model and the first production parameter is obtained based on the prediction error of the first candidate model, the second candidate model or the third candidate model.

4. A method for monitoring the state of a cold heading machine for bolt processing according to claim 3, characterized in that: The obtaining the prediction model corresponding to the first model and the first production parameter based on the prediction error of the first candidate model, the second candidate model or the third candidate model includes: The candidate model with the smallest prediction error among the first candidate model, the second candidate model and the third candidate model is used as the prediction model corresponding to the first model and the first production parameter.

5. The method for monitoring the state of a cold heading machine for bolt processing according to claim 3, characterized in that: The first initial model is a support vector machine, the second initial model is a linear regression model, and the third initial model is a random forest model.

6. A method for monitoring the state of a cold heading machine for bolt processing according to claim 1, characterized in that: There are multiple groups of production parameters after the detection; the number of stamping times and / or production time of the cold heading machine after the detection is input into the prediction model corresponding to the mold model and the production parameters to obtain the change amount of the mold state parameter of the cold heading machine, including: For each set of production parameters, after the cold heading machine is tested, the number of stamping times and / or production time corresponding to the set of production parameters are input into the prediction model corresponding to the mold model and the set of production parameters to obtain the state parameter change corresponding to the set of production parameters.

7. The method for monitoring the state of a cold heading machine for bolt processing according to claim 1, characterized in that: Before performing multiple stamping tests with different stamping times and production times on multiple cold heading machines for multiple models of dies and multiple production parameter combinations, and recording the changes in various die state parameters of each cold heading machine before and after the tests, the method further includes: The interactive effect analysis of production parameters and mold state parameters is performed to obtain a production parameter category combination for predicting each mold state parameter category combination; wherein each mold state parameter category combination has different categories of mold state parameters, and each production parameter category combination has different categories of production parameters.

8. A state monitoring device for a cold heading machine for bolt processing, characterized in that: include: An acquisition module, used to acquire historical mold state parameters and production parameters after the detection of the mold of the cold heading machine; wherein the mold state parameters include one or more of the degree of wear, deformation, crack condition, smoothness, hardness and fatigue damage, and the production parameters include one or more of the bolt model, punching force, feed speed, lubrication condition and mold temperature; A prediction module, used for inputting the number of punching times and / or production time of the cold heading machine after detection into a prediction model corresponding to the model of the mold and the production parameters, to obtain a change in the mold state parameter of the cold heading machine; The calculation module is used to determine the real-time mold state parameters of the cold heading machine based on the historical mold state parameters and the change amount of the mold state parameters.

9. A terminal comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method as claimed in any one of claims 1 to 7 are implemented.

Images