Ionitriding process optimization method and device based on big data and storage medium

Abstract

The invention relates to the technical field of big data process optimization, and discloses an ion nitriding process optimization method and device based on big data and a storage medium, and the method comprises the steps: obtaining ion nitriding processing big data, and determining a workpiece feature-processing temperature mapping relation based on the ion nitriding processing big data; determining initial machining process parameters and current structural characteristics of the current to-be-machined workpiece; the multi-stage machining temperature is optimized based on the workpiece feature-machining temperature mapping relation and the current structural features, and the optimal stage heating temperature is generated; the gas introduction amount is optimized based on the optimal heating temperature stage and the processing indexes, and the optimized gas amount is generated; the heating time is optimized based on the optimal heating temperature stage and the optimized gas quantity, and the optimized heating time is generated; and generating an optimized ion nitriding process. The whole process is optimized according to different structural characteristics, meanwhile, a magnetic field control method is adopted, the ion nitriding process is deeply optimized, and the machining efficiency is improved.

Description

Technical Field

[0001] This invention relates to the field of big data process optimization technology, specifically to an optimization method, apparatus, and storage medium for ion nitriding process based on big data. Background Technology

[0002] In the field of industrial processing, there are many situations where metal surfaces need to be treated to meet practical requirements. Ion nitriding, as a common surface processing technology, strengthens the surface of metal workpieces in a specific vacuum environment by utilizing the physical phenomenon of glow discharge to meet specific needs.

[0003] In existing ion nitriding processes, technicians place the workpiece to be processed in a vacuum furnace in a vacuum environment, and then fill it with high-purity ammonia or a nitrogen-hydrogen mixture. A DC voltage of several hundred volts is applied between the workpiece (cathode) and the furnace body (anode). The electric field causes the rarefied gas in the furnace to ionize, producing a glow discharge phenomenon. Under the action of the electric field, nitrogen and hydrogen positive ions bombard the surface of the workpiece at high speed, and the surface of the workpiece is processed.

[0004] However, in practical applications, the existing process has at least the following drawbacks:

[0005] On the one hand, existing processes often use fixed parameters for processing. These fixed parameters are processing parameters obtained by technicians after conducting appropriate experiments under laboratory conditions and combining them with their personal experience. However, the shape of the workpiece may vary greatly, and fixed processing parameters cannot meet more personalized processing needs.

[0006] On the other hand, with the mature application of traditional ion nitriding processes, people have put forward higher requirements for the processing efficiency of ion nitriding processes, and existing ion nitriding processes cannot meet the actual needs. Summary of the Invention

[0007] To overcome the aforementioned technical problems in the prior art, this invention provides an optimization method, apparatus, and storage medium for ion nitriding process based on big data. By analyzing the structural characteristics of different workpieces, the overall process is optimized according to the different structural characteristics. At the same time, an innovative magnetic field control method is adopted to deeply optimize the ion nitriding process and improve processing efficiency.

[0008] To achieve the above objectives, embodiments of the present invention provide an optimization method for ion nitriding processes based on big data. The method includes: acquiring ion nitriding processing big data; determining a workpiece feature-processing temperature mapping relationship based on the ion nitriding processing big data; determining initial processing parameters and current structural features of the workpiece to be processed, wherein the initial processing parameters include multi-stage processing temperatures, gas flow rates, and heating times; optimizing the multi-stage processing temperatures based on the workpiece feature-processing temperature mapping relationship and the current structural features to generate optimal stage heating temperatures; acquiring processing indicators of the workpiece to be processed; optimizing the gas flow rate based on the optimal heating temperature stage and the processing indicators to generate optimized gas flow rates; optimizing the heating time based on the optimal heating temperature stage and the optimized gas flow rates to generate optimized heating times; and generating an optimized ion nitriding process based on the optimal stage heating temperatures, the optimized gas types, the optimized gas flow rates, and the optimized heating times.

[0009] Preferably, determining the workpiece feature-processing temperature mapping relationship based on the ion nitriding machining big data includes: extracting historical structural features of different processed workpieces from the ion nitriding machining big data, the historical structural features including aperture features, wall thickness features, sharp corner features, groove features, and surface roughness features; analyzing the ion nitriding machining big data based on the aperture features, wall thickness features, sharp corner features, groove features, and surface roughness features respectively, generating corresponding aperture local temperature rise data, wall thickness local temperature rise data, groove local temperature rise data, and surface roughness local temperature rise data; determining aperture influence factors based on the aperture local temperature rise data, wall thickness influence factors based on the wall thickness local temperature rise data, groove influence factors based on the groove local temperature rise data, and surface roughness influence factors based on the surface roughness local temperature rise data; and generating the workpiece feature-processing temperature mapping relationship based on the aperture influence factors, wall thickness influence factors, groove influence factors, and surface roughness influence factors of the ion nitriding machining big data.

[0010] Preferably, the multi-stage processing temperature includes a heating temperature and a nitriding temperature. Optimizing the multi-stage processing temperature based on the workpiece feature-processing temperature mapping relationship and current structural features to generate an optimal stage heating temperature includes: determining a rapid and uniform heating segment based on the workpiece feature-processing temperature mapping relationship; determining a non-uniform heating segment based on the workpiece feature-processing temperature mapping relationship and current structural features; determining an ion nitriding temperature segment based on the multi-stage processing temperature; and optimizing the multi-stage processing temperature based on the rapid and uniform heating segment, the non-uniform heating segment, and the ion nitriding temperature segment to generate the optimal stage heating temperature.

[0011] Preferably, the processing indicators include a nitriding brittleness indicator and a nitriding depth indicator. Optimizing the gas flow rate based on the optimal heating temperature stage and the processing indicators to generate an optimized gas flow rate includes: determining the first nitriding performance of nitrogen in the rapid uniform heating section; determining the nitrogen flow rate in the rapid uniform heating section based on the first nitriding performance, the nitriding brittleness indicator, and the nitriding depth indicator; determining the second nitriding performance of the nitrogen-ammonia mixed gas in the non-uniform heating section; determining the first mixing ratio of the nitrogen-ammonia mixed gas in the non-uniform heating section and the second mixing ratio in the ion nitriding temperature section based on the second nitriding performance; determining the first mixed gas flow rate in the non-uniform heating section based on the first mixing ratio, the nitriding brittleness indicator, and the nitriding depth indicator; determining the second mixed gas flow rate in the ion nitriding temperature section based on the second mixing ratio, the nitriding brittleness indicator, and the nitriding depth indicator; and generating the optimized gas flow rate based on the nitrogen flow rate, the first mixed gas flow rate, and the second mixed gas flow rate.

[0012] Preferably, optimizing the heating time based on the optimal heating temperature stage and the optimized gas quantity to generate an optimized heating time includes: determining a first nitriding effect and a first heating effect based on the rapid uniform heating section and the nitrogen injection rate; determining a corresponding first heating duration based on the first nitriding effect and the first heating effect; determining a second nitriding effect and a second heating effect based on the non-uniform heating section and the first mixed gas injection rate; determining a corresponding second heating duration based on the second nitriding effect and the second heating effect; determining a third nitriding effect based on the second mixed gas injection rate; determining a third heating duration for the ion nitriding temperature section based on the third nitriding effect; and generating an optimized heating time based on the first heating duration, the second heating duration, and the third heating duration.

[0013] Preferably, the method further includes: determining a first temperature distribution field of the nitrogen-ammonia mixed gas in the non-uniform heating section based on the workpiece feature-processing temperature mapping relationship, the current structural features, and the first mixed gas injection rate; determining a second temperature distribution field of the nitrogen-ammonia mixed gas in the ion nitriding temperature section based on the workpiece feature-processing temperature mapping relationship, the current structural features, and the second mixed gas injection rate; determining a first superimposed magnetic field based on the first temperature distribution field, and determining a second superimposed magnetic field based on the second temperature distribution field.

[0014] Preferably, determining the first superimposed magnetic field based on the first temperature distribution field includes: determining a first temperature difference for the current structural features based on the first temperature distribution field; determining the nitride ion distribution density based on the first temperature difference; determining a first dynamic uniform temperature field corresponding to the first temperature distribution field; determining a dynamic ion distribution density corresponding to the first dynamic uniform temperature field; determining the number of magnetic fields, the magnetic field strength, and the magnetic field direction based on the dynamic ion distribution density and the nitride ion distribution density; and constructing a first superimposed magnetic field based on the number of magnetic fields, the magnetic field strength, and the magnetic field direction.

[0015] Preferably, the method further includes: after generating the optimized heating time, determining a fourth nitriding effect and a fourth heating effect based on the first superimposed magnetic field and the first mixed gas flow rate; optimizing the second heating time based on the fourth nitriding effect and the fourth heating effect to generate a fourth heating time, wherein the fourth heating time is less than the second heating time; determining a fifth nitriding effect based on the second superimposed magnetic field and the second mixed gas flow rate; and optimizing the third heating time based on the fifth nitriding effect to generate a fifth heating time, wherein the fifth heating time is less than the third heating time.

[0016] Accordingly, the present invention also provides an optimization device for ion nitriding process based on big data. The device includes: a mapping generation unit for acquiring ion nitriding processing big data and determining a workpiece feature-processing temperature mapping relationship based on the ion nitriding processing big data; a parameter determination unit for determining the initial processing parameters and current structural features of the workpiece to be processed, wherein the initial processing parameters include multi-stage processing temperature, gas flow rate, and heating time; a first optimization unit for optimizing the multi-stage processing temperature based on the workpiece feature-processing temperature mapping relationship and the current structural features to generate an optimal stage heating temperature; a second optimization unit for acquiring the processing index of the workpiece to be processed and optimizing the gas flow rate based on the optimal heating temperature stage and the processing index to generate an optimized gas flow rate; a third optimization unit for optimizing the heating time based on the optimal heating temperature stage and the optimized gas flow rate to generate an optimized heating time; and a process generation unit for generating an optimized ion nitriding process based on the optimal stage heating temperature, the optimized gas type, the optimized gas flow rate, and the optimized heating time.

[0017] On the other hand, the present invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method provided in the embodiments of the present invention.

[0018] The present invention has at least the following technical effects through the technical solution provided by the present invention:

[0019] By analyzing the impact of different structural features of workpieces on temperature changes during processing based on a large amount of historical ion nitriding data, and optimizing each step of the process according to the analyzed workpiece feature-processing temperature mapping relationship, the processing efficiency and nitriding effect are effectively improved, thus meeting the actual interests of enterprises.

[0020] Furthermore, by innovatively employing magnetic field control, the amount of ion bombardment on different structural parts of the workpiece is controlled, thereby ensuring consistent temperature changes across different parts and improving temperature uniformity. This allows for further optimization of the ion nitriding process, increasing processing efficiency, improving product quality, and meeting the actual needs of enterprises.

[0021] Other features and advantages of the embodiments of the present invention will be described in detail in the following detailed description section. Attached Figure Description

[0022] The accompanying drawings are provided to further illustrate embodiments of the present invention and form part of the specification. They are used together with the following detailed description to explain the embodiments of the present invention, but do not constitute a limitation thereof. In the drawings:

[0023] Figure 1 This is a flowchart illustrating the specific implementation of the optimization method for ion nitriding process based on big data provided in this embodiment of the invention.

[0024] Figure 2 This is a schematic diagram of the structure of the optimized device for ion nitriding process based on big data provided in an embodiment of the present invention. Detailed Implementation

[0025] The specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are for illustration and explanation only and are not intended to limit the scope of the present invention.

[0026] In this invention, the terms "system" and "network" are used interchangeably. "Multiple" refers to two or more; therefore, in this invention, "multiple" can also be understood as "at least two." "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone. Additionally, the character " / ", unless otherwise specified, generally indicates that the preceding and following related objects have an "or" relationship. Furthermore, it should be understood that in the description of this invention, terms such as "first" and "second" are used only for descriptive purposes and should not be construed as indicating or implying relative importance or order.

[0027] The background technology of this invention will be introduced first below.

[0028] In traditional ion nitriding processes, after pretreatment and placement of the workpiece in the furnace, a vacuum is applied followed by heating, for example, using an auxiliary heater (or low-power glow discharge lamp) to raise the workpiece temperature to 300-400°C, then holding it at that temperature for 30-60 minutes before subsequent nitriding. However, with the increasing application of nitriding processes, higher demands have been placed on them. These demands include higher efficiency (faster speed) in the initial heating and nitriding stages, better nitriding results, and the ability to quickly and adaptively adopt optimal parameters based on different workpiece conditions (rather than determining an acceptable process parameter through experimentation or based on experience). Existing ion nitriding processes cannot meet these requirements.

[0029] Please see Figure 1 This invention provides an optimization method for ion nitriding processes based on big data, the method comprising:

[0030] S10) Obtain big data on ion nitriding processing, and determine the workpiece feature-processing temperature mapping relationship based on the big data on ion nitriding processing;

[0031] S20) Determine the initial processing parameters and current structural features of the workpiece to be processed. The initial processing parameters include multi-stage processing temperature, gas flow rate and heating time.

[0032] S30) Optimize the multi-stage processing temperature based on the workpiece feature-processing temperature mapping relationship and the current structural features to generate the optimal stage heating temperature;

[0033] S40) Obtain the processing parameters of the workpiece to be processed, optimize the gas flow rate based on the optimal heating temperature stage and the processing parameters, and generate the optimized gas flow rate;

[0034] S50) Optimize the heating time based on the optimal heating temperature stage and the optimized gas quantity to generate an optimized heating time;

[0035] S60) Based on the optimal stage heating temperature, the optimized gas type, the optimized gas quantity, and the optimized heating time, an optimized ion nitriding process is generated.

[0036] In one possible implementation, to optimize the entire ion nitriding process and adaptively match the shape characteristics of different workpieces to determine the optimal processing parameters, firstly, big data on ion nitriding processing is acquired, and the mapping relationship between workpiece characteristics and processing temperature is determined. For example, ion nitriding processing data of 40Cr steel workpieces (including gears, shafts, sleeves, etc.) from the past three years are collected. The data includes workpiece structural characteristics (such as gear module, tooth root radius, shaft diameter, sleeve wall thickness, etc.), processing parameters (temperature, gas volume, time), and processing results (nitriding depth, hardness, brittleness grade), etc. By performing multiple linear regression analysis on the above data, a mapping relationship model of "workpiece structural characteristics - processing temperature" is established. This mapping relationship model is mainly used to reflect the different processing temperatures used to maintain small temperature deviations in various parts of the workpiece surface (especially sharp corners, where local temperature rise is prone to occur, leading to excessive local nitriding) under different workpiece structural characteristics.

[0037] For example, in one implementation, for a certain type of gear workpiece, the workpiece is first heated to 450°C and then subjected to isothermal ion nitriding treatment to obtain the workpiece with the required parameters. Because this type of workpiece has sharp corners, direct heating will lead to excessively high local temperatures and further excessively deep nitriding in certain areas. For this type of workpiece, historical big data analysis is used to determine which parameters, based on historical process parameters, achieve the best temperature stability for heating and ion nitriding treatment, thereby generating a workpiece characteristic-processing temperature mapping relationship for all workpieces.

[0038] In the process of analyzing and constructing the mapping relationship, since the change of workpiece surface temperature is related to a variety of factors, if we only focus on the structural characteristics of the workpiece and the change of heating temperature, we may not be able to accurately characterize the influence of workpiece shape on temperature uniformity.

[0039] In this embodiment of the invention, determining the workpiece feature-processing temperature mapping relationship based on the ion nitriding machining big data includes: extracting historical structural features of different processed workpieces from the ion nitriding machining big data, the historical structural features including aperture features, wall thickness features, sharp corner features, groove features, and surface roughness features; analyzing the ion nitriding machining big data based on the aperture features, wall thickness features, sharp corner features, groove features, and surface roughness features respectively, generating corresponding aperture local temperature rise data, wall thickness local temperature rise data, groove local temperature rise data, and surface roughness local temperature rise data; determining aperture influence factors based on the aperture local temperature rise data, wall thickness influence factors based on the wall thickness local temperature rise data, groove influence factors based on the groove local temperature rise data, and surface roughness influence factors based on the surface roughness local temperature rise data; and generating a workpiece feature-processing temperature mapping relationship based on the aperture influence factors, wall thickness influence factors, groove influence factors, and surface roughness influence factors in the ion nitriding machining big data.

[0040] Specifically, when conducting big data analysis, the historical structural features of different processed workpieces are first extracted from the big data of ion nitriding processing. These historical structural features include, but are not limited to, hole diameter features, wall thickness features, sharp corner features, groove features, and surface roughness features. These features will affect the surface temperature changes of the workpiece during processing. For example, for 40Cr steel sleeves with the same wall thickness, the local temperature rise difference can reach 15-20℃ due to different hole diameters, which affects the accuracy of subsequent parameter optimization.

[0041] After determining the aforementioned historical structural characteristics, data related to each characteristic were extracted from the big data of ion nitriding processing, and data analysis was performed. For example, data analysis methods include, but are not limited to, cluster analysis, data similarity analysis, and mathematical model analysis. For example, in this embodiment of the invention, specific structural features of different workpieces are extracted from 1200 sets of 40Cr steel ion nitriding processing data: the hole diameter of sleeve-type workpieces is φ20-φ100mm (10mm interval, 9 categories in total), the wall thickness of sleeve / gear rim is 5-30mm (5mm interval, 6 categories in total), the chamfer angle of shaft-type workpieces is 30°-90° (15° interval, 4 categories in total), the width of gear tooth root groove is 0.5-2.0mm (0.3mm interval, 6 categories in total), and the surface Ra of workpieces is 0.8-6.3μm (1.5μm interval, 4 categories in total). Then, data analysis is performed separately. For example, under the same heating temperature (520℃) and gas volume (0.8m³ / h), the temperature rise change data of the inner wall of the φ20mm hole diameter sleeve is obtained, and the corresponding datasets are extracted for areas with large local temperature changes, and a local temperature rise dataset of the hole diameter is generated.

[0042] Further, based on the local temperature rise dataset corresponding to each feature, the influencing factors corresponding to each workpiece feature are determined, where the sum of the weights of the influencing factors for each workpiece is 1. For example, workpiece A has influencing factors x and y, so the sum of the weights of x and y is 1; workpiece B has influencing factors x, z, and m, so the sum of the weights of x, z, and m is 1. Then, a mathematical model is constructed based on the above influencing factors, and the workpiece feature-processing temperature mapping relationship is generated based on this mathematical model.

[0043] In this embodiment of the invention, by analyzing the data of structural features on the workpiece that affect the processing temperature based on historical processing big data, the different effects of different structural feature data on the surface temperature of the workpiece are determined, which facilitates the subsequent comprehensive control of the process method and heating conditions. The processing temperature optimized based on this mapping relationship can control the local temperature rise difference of the workpiece within ±3℃, providing a precise basis for parameter optimization.

[0044] In the actual processing, the initial processing parameters and current structural characteristics of the workpiece to be processed are first obtained. These initial processing parameters include, but are not limited to, multi-stage processing temperature, gas flow rate, and heating time. These initial processing parameters are set to meet target processing indicators, such as nitriding depth, machining brittleness, and nitriding hardness. For example, in one embodiment, the initial processing parameters are: the workpiece is preheated to 400°C in a vacuum environment, then held at that temperature for 60 minutes to eliminate residual machining stress and prevent cracking during subsequent high-temperature nitriding; then, a set amount of ammonia gas is introduced at 480°C for isothermal nitriding.

[0045] However, in practical applications, technicians have found that, on the one hand, traditional preheating methods are time-consuming, resulting in long waiting times for technicians and reducing the company's production efficiency; on the other hand, simply introducing ammonia gas can easily lead to an abnormal increase in the surface temperature of the workpiece to be processed, reducing the yield rate. For example, when processing a 40Cr steel shaft (50mm in diameter with a 30° sharp corner at the shoulder), the sharp corner of the shoulder heats up faster (20% faster than the shaft body), causing it to reach the nitriding temperature prematurely, resulting in over-nitriding (brittleness level 3), while the center of the shaft heats up slowly, resulting in insufficient nitriding depth (0.18mm).

[0046] To address the aforementioned technical problems, in this embodiment of the invention, the multi-stage processing temperature includes a heating temperature and a nitriding temperature. Optimizing the multi-stage processing temperature based on the workpiece feature-processing temperature mapping relationship and current structural features to generate an optimal stage heating temperature includes: determining a rapid and uniform heating segment based on the workpiece feature-processing temperature mapping relationship; determining a non-uniform heating segment based on the workpiece feature-processing temperature mapping relationship and current structural features; determining an ion nitriding temperature segment based on the multi-stage processing temperature; and optimizing the multi-stage processing temperature based on the rapid and uniform heating segment, the non-uniform heating segment, and the ion nitriding temperature segment to generate the optimal stage heating temperature.

[0047] In one possible implementation, during processing, the multi-stage processing temperature is first optimized based on the workpiece characteristics-processing temperature mapping relationship and structural characteristics to generate the optimal stage heating temperature. Specifically, in this embodiment of the invention, a mixed gas is used for processing. First, the mixed gas to be introduced during processing is determined. For example, the overall process is optimized into three stages: In the rapid and uniform heating stage, instead of ammonia, a chemically stable inert gas, nitrogen, is introduced. In this stage, the large number of nitrogen ions generated by nitrogen ionization are used to provide additional heating assistance without affecting the processing parameters of the workpiece, thereby improving preheating efficiency and significantly reducing the initial heating time; In the non-uniform heating stage, a mixed gas of nitrogen and ammonia is introduced for reheating to ensure temperature uniformity during heating; Finally, in the ion nitriding temperature stage, nitrogen and ammonia (but with different gas flow rates) are used for ion nitriding processing to achieve ion nitriding treatment of the workpiece.

[0048] Based on this, to balance the optimal heating rate, heating uniformity, and workpiece influence at each stage, a rapid and uniform heating range is determined according to the workpiece characteristic-processing temperature mapping relationship. For example, when a shaft workpiece has a diameter of 50mm and a 30° sharp corner on its shoulder (corresponding to a sharp corner influence factor of 0.18, with a local temperature rise 12°C higher than the baseline), the rapid and uniform heating range is determined to be 0-400°C. Within this temperature range, rapid heating allows for rapid workpiece temperature rise while maintaining a uniform overall workpiece temperature, avoiding local overheating or underheating, and minimizing the impact on parameters such as the nitriding depth, while significantly increasing the heating rate. The 400-480°C range is defined as a non-uniform heating range, and the temperature difference between the shoulder and shaft body is monitored in real-time using an in-furnace temperature sensor to address the issue of excessive heating at the sharp corner. The 480-500°C range is defined as a constant-temperature (dynamically controlled) ion nitriding temperature range, where ion nitriding is performed according to the workpiece processing specifications. By adopting the above-mentioned temperature gradation method, the optimal stage heating temperature can be generated, which can greatly optimize the ion nitriding efficiency and treatment effect for this workpiece.

[0049] In this embodiment of the invention, by using the workpiece characteristics-processing temperature mapping relationship, the processing efficiency of the ion nitriding process can be greatly improved, the processing time can be shortened, and the uniformity of the workpiece temperature distribution during processing can be effectively guaranteed (by 70%), while meeting the processing indicators and improving the business efficiency of enterprises.

[0050] After the temperature is divided into stages, the type and amount of gas introduced in each stage will affect the processing and the final processing effect. In order to accurately ensure the impact of each heating or nitriding treatment stage on the workpiece and ensure that the final processing effect meets the processing index, the optimal stage heating temperature is determined, and the gas control process is determined according to the processing index of the workpiece to be processed.

[0051] In this embodiment of the invention, the processing indicators include a nitriding brittleness indicator and a nitriding depth indicator. Optimizing the gas flow rate based on the optimal heating temperature stage and the processing indicators to generate an optimized gas flow rate includes: determining the first nitriding performance of nitrogen in the rapid uniform heating section; determining the nitrogen flow rate in the rapid uniform heating section based on the first nitriding performance, the nitriding brittleness indicator, and the nitriding depth indicator; determining the second nitriding performance of the nitrogen-ammonia mixed gas in the non-uniform heating section; determining the first mixing ratio of the nitrogen-ammonia mixed gas in the non-uniform heating section and the second mixing ratio in the ion nitriding temperature section based on the second nitriding performance; determining the first mixed gas flow rate in the non-uniform heating section based on the first mixing ratio, the nitriding brittleness indicator, and the nitriding depth indicator; determining the second mixed gas flow rate in the ion nitriding temperature section based on the second mixing ratio, the nitriding brittleness indicator, and the nitriding depth indicator; and generating the optimized gas flow rate based on the nitrogen flow rate, the first mixed gas flow rate, and the second mixed gas flow rate.

[0052] In one possible implementation, for example, the processing requirements for a 40Cr steel gear (module 2.5, tooth root groove 0.8mm) are a nitriding depth of 0.2-0.3mm and a nitriding brittleness level ≤2. Traditionally, a conventional method of continuous ammonia gas (0.8m³ / h) introduction is used. However, due to excessively high nitrogen atom concentration (high local ammonia partial pressure) at the tooth root groove, brittle cracks (level 3) appear, while the nitrogen atom concentration at the tooth tip is insufficient, resulting in a nitriding depth of only 0.17mm. Therefore, on the one hand, the optimal staged heating temperature provided in this embodiment of the invention is used for staged heating and processing; on the other hand, the type and amount of gas introduced are strictly controlled.

[0053] Specifically, the first step is to determine the initial nitriding performance of nitrogen in the rapid and uniform heating section. For example, at temperatures below 515°C, the nitriding activity of pure nitrogen is low (nitrogen atom decomposition rate is about 15%), and it can only form a thin oxide film on the workpiece surface. This can prevent excessive penetration of nitrogen atoms during subsequent nitriding. Therefore, the nitrogen flow rate in the rapid and uniform heating section can be determined. For example, by combining the nitriding brittleness index (≤2 level) and the nitriding depth index (0.2-0.3 mm), it is determined that when the flow rate is 0.6 m³ / h, the oxide film thickness on the workpiece surface is uniform (0.005-0.008 mm), and there is no risk of excessive nitriding. This flow rate is then determined as the nitrogen flow rate in the rapid and uniform heating section. Then, the second nitriding performance of the nitrogen-ammonia mixed gas in the non-uniform heating section is further determined. For example, at a temperature of 505°C, based on the influence of the nitrogen-ammonia mixed gas at different volume ratios on the workpiece surface temperature and various nitriding parameters, the optimal mixing ratio in the non-uniform heating section, such as a volume ratio of 1:2, and the optimal mixing ratio in the ion nitriding temperature section, such as a volume ratio of 1:3, can be determined.

[0054] When the volume ratio of the mixed gas is 1:2, the nitrogen atom decomposition rate is approximately 30%, falling between that of pure nitrogen (15%) and pure ammonia (45%). This allows for a slow increase in nitrogen concentration on the workpiece surface, avoiding sudden increases in local concentration. Therefore, the initial gas flow rate in the uneven heating section can be further determined. For example, with a flow rate of 1.0 m³ / h, the nitrogen concentration at the tooth root groove is 0.6% (not exceeding the critical value of 0.8% for brittleness), and the nitrogen concentration at the tooth tip is 0.4% (meeting the requirements for subsequent nitriding). This parameter is determined as the gas parameter for the uneven heating section. When the volume ratio of the mixed gas is 1:3, the nitrogen atom decomposition rate is approximately 40%. Based on the processing parameters, with a flow rate of 1.0 m³ / h, the nitriding depth at the tooth tip reaches 0.25 mm, and the nitrogen concentration at the tooth root groove is 0.7% (brittleness level 1). This flow rate is determined as the gas flow rate for the nitriding temperature section.

[0055] In this embodiment of the invention, by conducting physical analysis of various processing indicators of the ion nitriding process and combining the actual effects of different types of gases on the ion nitriding process at different temperatures, different types of gases and gas flow rates are adopted at different processing stages to increase processing efficiency and ensure processing results, thereby satisfying the actual interests of enterprises and achieving a deep optimization effect on the traditional ion nitriding process.

[0056] After optimizing parameters such as heating temperature range and gas flow in the ion nitriding process, the heating time was further optimized because the heating time also affects the reaction of ions on the workpiece surface.

[0057] In this embodiment of the invention, optimizing the heating time based on the optimal heating temperature stage and the optimized gas quantity to generate an optimized heating time includes: determining a first nitriding effect and a first heating effect based on the rapid uniform heating section and the nitrogen injection rate; determining a corresponding first heating duration based on the first nitriding effect and the first heating effect; determining a second nitriding effect and a second heating effect based on the non-uniform heating section and the first mixed gas injection rate; determining a corresponding second heating duration based on the second nitriding effect and the second heating effect; determining a third nitriding effect based on the second mixed gas injection rate; determining a third heating duration for the ion nitriding temperature section based on the third nitriding effect; and generating an optimized heating time based on the first heating duration, the second heating duration, and the third heating duration.

[0058] In one possible implementation, the first nitriding effect and the first heating effect in the rapid and uniform heating phase are first determined based on the nitrogen gas flow rate. For example, under the conditions of 510°C and 0.6 m³ / h nitrogen gas, the outer wall temperature (target 500°C) and surface nitriding condition (only thin oxide film is allowed) of the workpiece are detected every 30 minutes. After heating for 1 hour, the outer wall temperature reaches 495°C, the inner wall temperature reaches 492°C (temperature difference 3°C), and the surface oxide film thickness is 0.006 mm. At this time, the first heating time can be determined to be, for example, 1 hour, to avoid excessive heating that would lead to redundant subsequent nitriding time. Similarly, the second nitriding effect and the second heating effect in the uneven heating section are determined. For example, at 505℃, with a gas-mixture ratio of 1:2 and a flow rate of 1.0 m³ / h, the nitrogen concentration (target difference ≤ 0.1%) and temperature (target difference ≤ 2℃) of the inner and outer walls of the sleeve are measured every 15 minutes. After heating for 0.5h, the nitrogen concentration on the inner wall is 0.35% and on the outer wall is 0.38% (difference 0.03%), and the temperature on the inner wall is 503℃ and on the outer wall is 505℃ (difference 2℃). Therefore, the second heating time can be determined to be, for example, 0.5h, to ensure a uniform transition of nitrogen concentration and temperature. Furthermore, the third nitriding effect is determined based on the second mixed gas flow rate. For example, at 525°C, with a mixed gas ratio of 1:3 and a flow rate of 1.0 m³ / h, the nitriding depth in the sleeve wall thickness direction is measured every hour (target 0.2-0.3 mm). After heating for 4 hours, the depth reaches 0.28 mm. Therefore, the third heating time can be determined to be, for example, 4 hours (0.5 hours shorter than the traditional method).

[0059] In this embodiment of the invention, by determining the optimal stage heating temperature, the optimal gas introduction method, and the optimal heating time based on the actual workpiece characteristics, the traditional ion nitriding process is comprehensively optimized to achieve the best processing effect and meet the actual interests of the enterprise.

[0060] In existing ion nitriding processes, after determining the gas to be introduced and its flow rate, the corresponding gas is directly introduced into the furnace and allowed to circulate inside to achieve ion bombardment and nitriding reactions. In theory, the amount of ions passing through a unit cross-sectional area of ​​the workpiece is the same, but the outer surface contours and shapes of the workpieces are different. Therefore, the traditional method leads to uneven increases in the surface temperature of the workpiece, which causes certain problems for the traditional process.

[0061] To address the aforementioned technical problems, in this embodiment of the invention, the method further includes: determining a first temperature distribution field of the nitrogen-ammonia mixed gas in the non-uniform heating section based on the workpiece feature-processing temperature mapping relationship, the current structural features, and the first mixed gas injection rate; determining a second temperature distribution field of the nitrogen-ammonia mixed gas in the ion nitriding temperature section based on the workpiece feature-processing temperature mapping relationship, the current structural features, and the second mixed gas injection rate; determining a first superimposed magnetic field based on the first temperature distribution field; and determining a second superimposed magnetic field based on the second temperature distribution field.

[0062] In one possible implementation, the temperature distribution is first simulated using finite element analysis software (ANSYS) based on the current ion nitriding process parameters. This determines the first temperature distribution field of the workpiece in the uneven heating section and the second temperature distribution field in the ion nitriding temperature section. To achieve the same ion bombardment quantity across all shapes and structures of the workpiece, a magnetic field control method is used to bombard different quantities of ions according to the different shape characteristics of the workpiece. Specifically, a first superimposed magnetic field is determined based on the first temperature distribution field, and a second superimposed magnetic field is determined based on the second temperature distribution field. For example, for the first superimposed magnetic field, an axial magnetic field (parallel to the workpiece axis) with a magnetic field strength of 50 mT is designed, with two magnets symmetrically arranged on both sides of the gear. The magnetic field guides nitrogen ions to move towards the bottom of the groove, compensating for insufficient ion accumulation due to low temperature. For the second superimposed magnetic field, an axial magnetic field (parallel to the workpiece axis) with a magnetic field strength of 50 mT is designed, with two magnets symmetrically arranged on both sides of the gear. The magnetic field guides nitrogen ions to move towards the bottom of the groove, compensating for insufficient ion accumulation due to low temperature.

[0063] By superimposing the magnetic field, the actual ion bombardment amount of the workpiece to be processed can be precisely controlled during the ion nitriding process, thereby effectively controlling the temperature rise rate of different parts, achieving the effect that all parts are at the same temperature rise rate or maintain temperature uniformity, and at the same time precisely controlling the nitriding effect of all parts, thus improving product quality.

[0064] In this embodiment of the invention, determining the first superimposed magnetic field based on the first temperature distribution field includes: determining a first temperature difference for the current structural features based on the first temperature distribution field; determining the nitride ion distribution density based on the first temperature difference; determining a first dynamic uniform temperature field corresponding to the first temperature distribution field; determining a dynamic ion distribution density corresponding to the first dynamic uniform temperature field; determining the number of magnetic fields, the magnetic field strength, and the magnetic field direction based on the dynamic ion distribution density and the nitride ion distribution density; and constructing the first superimposed magnetic field based on the number of magnetic fields, the magnetic field strength, and the magnetic field direction.

[0065] In one possible implementation, when constructing the first superimposed magnetic field, the temperature at the bottom of the gear tooth root groove (502℃) and the tooth surface temperature (508℃) are first measured using multi-point temperature sensors (accuracy ±0.5℃) inside the furnace, based on the first temperature distribution field (non-uniform heating section). This determines the first temperature difference ΔT = 6℃. The nitride ion distribution density is then determined based on this first temperature difference. For example, using an ion concentration detector, the nitrogen ion concentration at the bottom of the groove is measured to be 1.2 × 10¹ when there is no magnetic field. 8 Units / m³, tooth surface 1.8×10¹ 8 Units / m³, density difference Δρ = 0.6 × 10¹ 8 Quantity / m³. On the other hand, based on the first temperature distribution field, the corresponding first dynamic uniform temperature field is determined, and the dynamic ion distribution density corresponding to the first dynamic uniform temperature field is further determined. For example, a target dynamic uniform temperature field is set (temperature difference between the bottom of the groove and the tooth surface ≤ 2℃). Through simulation calculation, the corresponding dynamic ion distribution density should be 1.5 × 10¹. 8 Units / m³ (Difference in density between groove and tooth surface ≤ 0.1 × 10¹) 8 (units / m³). Further, the magnetic field parameters are determined, for example, based on the density difference Δρ = 0.6 × 10¹. 8 The nitrogen ion concentration at the bottom of the trench can be increased to 1.45 × 10¹ m³ and the dynamic density target can be calculated using magnetic field-ion motion simulation software. This is achieved when there are two magnetic fields (symmetrical on both sides of the gear), a magnetic field strength of 50 mT, and the magnetic field direction is parallel to the workpiece axis. 8 The number of teeth per m³ decreased to 1.55 × 10¹. 8 Quantity / m³, density difference 0.1×10¹ 8 Finally, based on the above magnetic field parameters, the ion nitriding furnace is arranged to construct the corresponding first superimposed magnetic field.

[0066] Based on the same principle, a second superimposed magnetic field is arranged inside the ion nitriding furnace in the ion nitriding temperature range to construct the corresponding magnetic field, which will not be elaborated on here.

[0067] In this embodiment of the invention, by adopting a corresponding magnetic field superposition processing method based on the actual ion distribution in the ion nitriding furnace in the traditional ion nitriding process and the actual situation of different workpiece surface structures, the different ion bombardment amounts on different parts of the workpiece are precisely controlled, effectively achieving control of the overall temperature uniformity of the workpiece, precisely controlling the nitriding effect of each part, meeting the actual needs of enterprises, and improving product quality.

[0068] In an embodiment of the present invention, the method further includes: after generating the optimized heating time, determining a fourth nitriding effect and a fourth heating effect based on the first superimposed magnetic field and the first mixed gas flow rate; optimizing the second heating time based on the fourth nitriding effect and the fourth heating effect to generate a fourth heating time, wherein the fourth heating time is less than the second heating time; determining a fifth nitriding effect based on the second superimposed magnetic field and the second mixed gas flow rate; and optimizing the third heating time based on the fifth nitriding effect to generate a fifth heating time, wherein the fifth heating time is less than the third heating time.

[0069] In one possible implementation, by employing a non-uniform ion bombardment control method, uniform heating of each part of the workpiece is achieved. Therefore, the charge and heating temperature during glow discharge can be appropriately increased, resulting in higher processing efficiency and faster finished product yield. Specifically, after generating the optimized heating time, the fourth nitriding effect and the fourth heating effect are further determined based on the first superimposed magnetic field and the first mixed gas flow rate. For example, under the conditions of the first superimposed magnetic field (50mT, axial) and the first mixed gas flow rate (1:2 1.0m³ / h), the nitriding effect (nitrogen concentration uniformity) and the heating effect (temperature uniformity) at the end of the non-uniform heating segment (0.5h) are detected: nitrogen concentration difference 0.03% (originally 0.05%), temperature difference 2℃ (originally 3℃). Therefore, the second heating time of 0.5h is shortened to 0.4h, at which point the nitrogen concentration difference is 0.04% and the temperature difference is 2.5℃, still meeting the requirements. Based on the same principle, the heating time of the ion nitriding temperature range was also optimized to achieve higher processing efficiency while ensuring the nitriding effect.

[0070] In this embodiment of the invention, by further optimizing the ion nitriding process based on the magnetic field superposition process, higher processing efficiency is achieved, effectively improving the company's operating benefits and meeting the company's actual needs.

[0071] Please see Figure 2Based on the same inventive concept, this invention provides an optimization device for ion nitriding process based on big data. The device includes: a mapping generation unit for acquiring ion nitriding processing big data and determining a workpiece feature-processing temperature mapping relationship based on the ion nitriding processing big data; a parameter determination unit for determining the initial processing parameters and current structural features of the workpiece to be processed, the initial processing parameters including multi-stage processing temperature, gas flow rate, and heating time; a first optimization unit for optimizing the multi-stage processing temperature based on the workpiece feature-processing temperature mapping relationship and the current structural features to generate an optimal stage heating temperature; a second optimization unit for acquiring the processing index of the workpiece to be processed and optimizing the gas flow rate based on the optimal heating temperature stage and the processing index to generate an optimized gas flow rate; a third optimization unit for optimizing the heating time based on the optimal heating temperature stage and the optimized gas flow rate to generate an optimized heating time; and a process generation unit for generating an optimized ion nitriding process based on the optimal stage heating temperature, the optimized gas type, the optimized gas flow rate, and the optimized heating time.

[0072] Furthermore, embodiments of the present invention also provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the methods described in the embodiments of the present invention.

[0073] The optional embodiments of the present invention have been described in detail above with reference to the accompanying drawings. However, the embodiments of the present invention are not limited to the specific details in the above embodiments. Within the scope of the technical concept of the embodiments of the present invention, various simple modifications can be made to the technical solutions of the embodiments of the present invention, and these simple modifications all fall within the protection scope of the embodiments of the present invention.

[0074] It should also be noted that the various specific technical features described in the above embodiments can be combined in any suitable manner without contradiction. To avoid unnecessary repetition, the embodiments of the present invention will not describe the various possible combinations separately.

[0075] Those skilled in the art will understand that all or part of the steps in the methods of the above embodiments can be implemented by a program instructing related hardware. This program is stored in a storage medium and includes several instructions to cause a microcontroller, chip, or processor to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0076] Furthermore, various different implementations of the present invention can be combined arbitrarily, as long as they do not violate the spirit of the present invention, they should also be regarded as the content disclosed in the present invention.

Claims

1. A method for optimization of ion nitriding process based on big data, characterized in that, The method comprises: Obtaining ion nitriding processing big data, determining a workpiece feature-processing temperature mapping relationship based on the ion nitriding processing big data; Determine the initial processing process parameters and the current structure characteristics of the current workpiece to be processed, the initial processing process parameters include multi-stage processing temperature, gas input amount and heating time; Based on the workpiece feature-processing temperature mapping relationship and the current structure characteristics, the multi-stage processing temperature is optimized to generate the best stage heating temperature; Obtain the processing index of the workpiece to be processed, and optimize the gas input amount based on the best heating temperature stage and the processing index to generate the optimized gas amount; Based on the best heating temperature stage and the optimized gas amount, the heating time is optimized to generate the optimized heating time; Based on the best stage heating temperature, the optimized gas type, the optimized gas amount and the optimized heating time, the optimized ion nitriding process is generated.

2. The method of claim 1, wherein, The workpiece feature-processing temperature mapping relationship is determined based on the ion nitriding processing big data, which comprises: Extracting historical structure characteristics of different processing workpieces from the ion nitriding processing big data, the historical structure characteristics include aperture characteristics, wall thickness characteristics, sharp angle characteristics, groove characteristics and surface roughness characteristics; Based on the aperture characteristics, the wall thickness characteristics, the sharp angle characteristics, the groove characteristics and the surface roughness characteristics, the ion nitriding processing big data is analyzed to generate corresponding aperture local temperature rise data, wall thickness local temperature rise data, groove local temperature rise data and surface roughness local temperature rise data; Based on the aperture local temperature rise data, the aperture influence factor is determined, based on the wall thickness local temperature rise data, the wall thickness influence factor is determined, based on the groove local temperature rise data, the groove influence factor is determined, based on the surface roughness local temperature rise data, the surface roughness influence factor is determined; Based on the ion nitriding processing big data, the aperture influence factor, the wall thickness influence factor, the groove influence factor and the surface roughness influence factor, the workpiece feature-processing temperature mapping relationship is generated.

3. The method of claim 1, wherein, The multi-stage processing temperature includes heating temperature and nitriding temperature, and the multi-stage processing temperature is optimized based on the workpiece feature-processing temperature mapping relationship and the current structure characteristics to generate the best stage heating temperature, which comprises: Determine the fast and uniform temperature rise section based on the workpiece feature-processing temperature mapping relationship; Determine the non-uniform temperature rise section based on the workpiece feature-processing temperature mapping relationship and the current structure characteristics; Determine the ion nitriding temperature section based on the multi-stage processing temperature; Optimize the multi-stage processing temperature based on the fast and uniform temperature rise section, the non-uniform temperature rise section and the ion nitriding temperature section to generate the best stage heating temperature.

4. The method of claim 3, wherein, The processing index includes nitriding brittleness index and nitriding depth index, and the gas input amount is optimized based on the best heating temperature stage and the processing index to generate the optimized gas amount, which comprises: Determine the first nitriding performance of nitrogen in the fast and uniform temperature rise section; determining a nitrogen gas input amount in the fast and uniform temperature rising section based on the first nitriding performance, the nitriding brittleness index and the nitriding depth index; determining a second nitriding performance of the nitrogen-ammonia mixed gas in the uneven temperature rising section; determining a first mixed ratio of the nitrogen-ammonia mixed gas in the uneven temperature rising section and a second mixed ratio in the ion nitriding temperature section based on the second nitriding performance; determining a first mixed gas input amount in the uneven temperature rising section based on the first mixed ratio, the nitriding brittleness index and the nitriding depth index; determining a second mixed gas input amount in the ion nitriding temperature section based on the second mixed ratio, the nitriding brittleness index and the nitriding depth index; generating an optimized gas amount based on the nitrogen gas input amount, the first mixed gas input amount and the second mixed gas input amount.

5. The method of claim 4, wherein, the optimization of the heating time based on the optimal heating temperature stage and the optimized gas amount to generate an optimized heating time, comprising: determining a first nitriding effect and a first temperature rising effect based on the fast and uniform temperature rising section and the nitrogen gas input amount; determining a corresponding first heating time length based on the first nitriding effect and the first temperature rising effect; determining a second nitriding effect and a second temperature rising effect based on the uneven temperature rising section and the first mixed gas input amount; determining a corresponding second heating time length based on the second nitriding effect and the second temperature rising effect; determining a third nitriding effect based on the second mixed gas input amount; determining a third heating time length of the ion nitriding temperature section based on the third nitriding effect; generating an optimized heating time based on the first heating time length, the second heating time length and the third heating time length.

6. The method of claim 5, wherein, The method further comprises: determining a first temperature distribution field of the nitrogen-ammonia mixed gas in the uneven temperature rising section based on the workpiece feature-machining temperature mapping relationship, the current structure feature and the first mixed gas input amount; determining a second temperature distribution field of the nitrogen-ammonia mixed gas in the ion nitriding temperature section based on the workpiece feature-machining temperature mapping relationship, the current structure feature and the second mixed gas input amount; determining a first superimposed magnetic field based on the first temperature distribution field and a second superimposed magnetic field based on the second temperature distribution field.

7. The method of claim 6, wherein, The determination of the first superimposed magnetic field based on the first temperature distribution field comprises: determining a first temperature difference for the current structure feature based on the first temperature distribution field; determining a nitriding ion distribution density based on the first temperature difference; determining a first dynamic uniform temperature field corresponding to the first temperature distribution field; determining a dynamic ion distribution density corresponding to the first dynamic uniform temperature field; determining a number of magnetic fields, a magnetic field strength and a magnetic field direction based on the dynamic ion distribution density and the nitriding ion distribution density; constructing a first superimposed magnetic field based on the number of magnetic fields, the magnetic field strength and the magnetic field direction.

8. The method of claim 6, wherein, The method further comprises: after generating the optimized heating time, determining a fourth nitriding effect and a fourth temperature rising effect based on the first superimposed magnetic field and the first mixed gas input amount; The fourth heating time length is less than the second heating time length, and the fourth heating time length is generated based on the fourth nitriding effect and the fourth temperature rising effect; The fifth nitriding effect is determined based on the second superimposed magnetic field and the second mixed gas input amount; The fifth heating time length is less than the third heating time length, and the fifth heating time length is generated based on the fifth nitriding effect.

9. A device for optimizing ion-nitriding process based on big data, characterized in that, The device comprises: A mapping generation unit configured to acquire ion nitriding processing big data, and determine a workpiece feature-processing temperature mapping relationship based on the ion nitriding processing big data; A parameter determination unit configured to determine an initial processing process parameter of a current workpiece to be processed and a current structural feature, the initial processing process parameter comprising a multi-stage processing temperature, a gas input amount, and a heating time; A first optimization unit configured to optimize the multi-stage processing temperature based on the workpiece feature-processing temperature mapping relationship and the current structural feature, and generate an optimal stage heating temperature; A second optimization unit configured to acquire a processing index of the workpiece to be processed, optimize the gas input amount based on the optimal heating temperature stage and the processing index, and generate an optimized gas amount; A third optimization unit configured to optimize the heating time based on the optimal heating temperature stage and the optimized gas amount, and generate an optimized heating time; A process generation unit configured to generate an optimized ion nitriding process based on the optimal stage heating temperature, the optimized gas type, the optimized gas amount, and the optimized heating time.

10. A computer-readable storage medium having stored thereon a computer program, characterized in that, The program is executed by the processor to implement the method of any one of claims 1-8.

Images