Steel structure cooling process control device and method
Through the steel structure cooling process control device and method, the cooling process of forgings is optimized by using the graded cooling technology, the thermal stress and deformation problems in the prior art are solved, and the mechanical properties and product quality of forgings are improved.
Patent Information
- Application Number
- CN202411564251.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-05
- Publication Date
- 2024-12-06
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
Existing methods of cooling steel structures lead to thermal stress and deformation, reducing forging quality and performance.
Using steel structure cooling process control devices and methods, the information acquisition module, cooling parameter optimization analysis module, temperature scanning module, temperature distribution clustering module and cooling mapping control module can be used to realize the hierarchical cooling, optimize the cooling process of forgings, reduce thermal stress and Deformation.
It improves the accuracy of cooling control, improves the uniformity of the temperature distribution of the forging surface, reduces the negative impact of uneven temperature distribution, and improves the mechanical performance and product quality of the forging.
Smart Images

Figure CN119082440A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of steel material cooling control, and in particular to a steel structure cooling process control device and method. Background Art
[0002] The steel structure cooling process is a heat treatment technology used for steel materials and components. The metal material is heated to a certain temperature and then cooled in a controlled manner to change the microstructure and properties, increase the hardness and strength of the steel, improve toughness and wear resistance, reduce internal stress, and adjust its size and shape.
[0003] At present, due to the large size of existing forgings, conventional rapid cooling methods will cause severe thermal stress and deformation. Among them, rapid cooling will increase the temperature difference between the inside and outside of the forging, thereby generating large thermal stress, resulting in exceeding the yield limit of the material, causing cracks or deformation in the forging. Due to the inconsistent cooling speed of various parts of the forging, it will cause uneven shrinkage, resulting in dimensional deformation and shape distortion, affecting the dimensional accuracy and shape conformity of the forging, and reducing the quality of the forging.
[0004] In summary, the prior art has a technical problem that the rapid cooling method may cause severe thermal stress and deformation, resulting in reduced quality of forgings, which further affects the performance of forgings. Summary of the invention
[0005] The purpose of this application is to provide a steel structure cooling process control device and method to solve the technical problem in the prior art that the rapid cooling method will cause severe thermal stress and deformation, resulting in reduced quality of forgings and further affecting the performance of forgings.
[0006] In view of the above problems, the present application provides a steel structure cooling process control device and method.
[0007] In the first aspect, the present application also provides a steel structure cooling process control device for executing a steel structure cooling process control method, which includes: an information acquisition module for collecting forging property information, forging process parameters and expected primary cooling indicators of the target forging, and obtaining the first equipment property information of the primary cooling equipment; a primary cooling parameter optimization and analysis module for optimizing and analyzing the primary cooling parameters based on the forging property information, forging process parameters, expected primary cooling indicators and the first equipment property information, and determining the primary cooling optimization parameters; a forging temperature scanning module for performing a primary cooling operation on the target forging according to the primary cooling optimization parameters, performing a temperature scan on the target forging after the primary cooling through an infrared scanner, and generating an initial forging temperature distribution diagram; a forging temperature distribution clustering module, used to cluster and divide the initial forging temperature distribution diagram to obtain a forging temperature distribution diagram, establish a mapping association between a secondary cooling equipment array and the forging temperature distribution diagram, and obtain multiple forging area temperature distribution diagrams, wherein the forging area temperature distribution diagram and the secondary cooling equipment have a one-to-one correspondence; a secondary cooling parameter optimization analysis module, used to optimize and analyze the secondary cooling parameters based on the expected secondary cooling indicators and multiple forging area temperature distribution diagrams, using a secondary cooling twin model and a cooling evaluation function, to obtain multiple secondary cooling optimization parameters; a secondary cooling mapping control module, used to map and control the secondary cooling equipment array based on the multiple secondary cooling optimization parameters when the target forging is subjected to secondary cooling.
[0008] In a second aspect, the present application provides a steel structure cooling process control method, which is implemented by a steel structure cooling process control device, including: collecting forging attribute information, forging process parameters and expected primary cooling indicators of the target forging, and obtaining first equipment attribute information of the primary cooling equipment; based on the forging attribute information, forging process parameters, expected primary cooling indicators and first equipment attribute information, optimizing and analyzing the primary cooling parameters to determine the primary cooling optimization parameters; performing a primary cooling operation on the target forging according to the primary cooling optimization parameters, performing a temperature scan on the target forging after the primary cooling by an infrared scanner, and generating an initial forging The invention discloses a method for preparing a temperature distribution diagram of a forging part; clustering the initial forging temperature distribution diagram to obtain a forging temperature distribution diagram, establishing a mapping association between a secondary cooling device array and the forging temperature distribution diagram to obtain multiple forging area temperature distribution diagrams, wherein the forging area temperature distribution diagram and the secondary cooling device have a one-to-one correspondence; based on the expected secondary cooling index and the multiple forging area temperature distribution diagrams, the secondary cooling parameters are optimized and analyzed by using a secondary cooling twin model and a cooling evaluation function to obtain multiple secondary cooling optimization parameters; when the target forging is subjected to secondary cooling, the secondary cooling device array is mapped and controlled based on the multiple secondary cooling optimization parameters.
[0009] One or more technical solutions provided in this application have at least the following technical effects or advantages: The information acquisition module is used to collect the forging property information, forging process parameters and expected primary cooling index of the target forging, and obtain the first equipment property information of the primary cooling equipment; the primary cooling parameter optimization analysis module is used to optimize and analyze the primary cooling parameters based on the forging property information, forging process parameters, expected primary cooling index and first equipment property information, and determine the primary cooling optimization parameters; the forging temperature scanning module is used to perform a primary cooling operation on the target forging according to the primary cooling optimization parameters, and perform a temperature scan on the target forging after the primary cooling through an infrared scanner to generate an initial forging temperature distribution map; the forging temperature distribution clustering module is used to cluster the initial forging temperature distribution map to obtain the forging temperature A distribution map is constructed to establish a mapping association between the secondary cooling device array and the forging temperature distribution map, and obtain multiple forging area temperature distribution maps, wherein the forging area temperature distribution map and the secondary cooling device have a one-to-one correspondence; a secondary cooling parameter optimization analysis module is used to optimize and analyze the secondary cooling parameters based on the expected secondary cooling index and multiple forging area temperature distribution maps, and obtain multiple secondary cooling optimization parameters using the secondary cooling twin model and the cooling evaluation function; a secondary cooling mapping control module is used to map and control the secondary cooling device array based on the multiple secondary cooling optimization parameters when the target forging is subjected to secondary cooling, that is, through graded cooling, the cooling rate of the forging can be controlled, thereby reducing the occurrence of these problems. In addition, graded cooling also helps to improve the mechanical properties of the forging, such as toughness and wear resistance, while reducing deformation and residual stress after processing. Finally, the technical goal of improving the accuracy of cooling control is achieved, and the uniformity of the surface temperature distribution of the forging is improved, the negative impact caused by uneven temperature distribution is reduced, and the overall cooling effect and product quality of the forging are improved.
[0010] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented according to the contents of the specification, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are specifically cited below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS
[0011] In order to more clearly illustrate the technical solutions in the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.
[0012] Figure 1 This is a schematic diagram of the structure of a steel structure cooling process control device for this application; Figure 2 The present invention is a flow chart of a steel structure cooling process control method.
[0013] Description of reference numerals: Information collection module 11, primary cooling parameter optimization and analysis module 12, forging temperature scanning module 13, forging temperature distribution clustering module 14, secondary cooling parameter optimization and analysis module 15, secondary cooling mapping control module 16. DETAILED DESCRIPTION
[0014] This application provides a steel structure cooling process control device and method, which solves the technical problem in the prior art that the rapid cooling method will cause serious thermal stress and deformation, resulting in reduced quality of forgings and further affecting the performance of forgings. The technical goal of improving the accuracy of cooling control is achieved, and the uniformity of surface temperature distribution of forgings is improved, the negative impact caused by uneven temperature distribution is reduced, and the overall cooling effect of forgings and product quality are improved.
[0015] Below, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments of the present application. It should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application. It should also be noted that, for the convenience of description, only the parts related to the present application are shown in the accompanying drawings, rather than all of them.
[0016] For example, please refer to the attached Figure 1 The present application provides a steel structure cooling process control device, wherein the steel structure cooling process control device specifically includes: The information acquisition module 11 is used to collect the forging property information, forging process parameters and expected primary cooling index of the target forging, and obtain the first equipment property information of the primary cooling equipment. The primary cooling parameter optimization analysis module 12 is used to optimize and analyze the primary cooling parameters based on the forging property information, forging process parameters, expected primary cooling index and first equipment property information, and determine the primary cooling optimization parameters. The forging temperature scanning module 13 is used to perform a primary cooling operation on the target forging according to the primary cooling optimization parameters, perform a temperature scan on the target forging after the primary cooling by an infrared scanner, and generate an initial forging temperature distribution map. The forging temperature distribution clustering module 14 is used to cluster the initial forging temperature distribution map to obtain a forging temperature distribution map, establish a mapping association between the secondary cooling equipment array and the forging temperature distribution map, and obtain multiple forging area temperature distribution maps, wherein the forging area temperature distribution map and the secondary cooling equipment have a one-to-one correspondence. The secondary cooling parameter optimization analysis module 15 is used to optimize and analyze the secondary cooling parameters based on the expected secondary cooling index and the temperature distribution diagrams of multiple forging regions, using the secondary cooling twin model and the cooling evaluation function, to obtain multiple secondary cooling optimization parameters. The secondary cooling mapping control module 16 is used to map and control the secondary cooling device array based on the multiple secondary cooling optimization parameters when the target forging is subjected to secondary cooling.
[0017] Furthermore, the primary cooling parameter optimization analysis module 12 is also used for: Taking the first equipment attribute information as the equipment constraint, taking the forging attribute information, forging process parameters and expected primary cooling indicators as the product constraints, homologous information retrieval is performed based on the industrial Internet to obtain a sample primary cooling parameter set; clustering and dividing the sample primary cooling parameter set is performed based on the K-means algorithm, and multiple sample primary cooling parameter groups are determined, and the sample primary cooling parameter groups that do not meet the predetermined quantity threshold are eliminated, and the standard primary cooling parameter set is obtained by fusion; clustering the standard primary cooling parameter set again based on the K-means algorithm, and calculating the mean of the parameters in the optimal clustering result is set as the primary cooling optimization parameter, wherein the optimal clustering result is the clustering result with the largest number of parameters.
[0018] Furthermore, the forging temperature distribution clustering module 14 is also used for: The minimum temperature value in the initial forging temperature distribution diagram is selected as the starting point, and water is simulated to be poured into the initial forging temperature distribution diagram, and the first temperature value that the water surface does not cover is set as the first stage temperature; the temperature difference between the first stage temperature and the minimum temperature value is calculated to obtain a first temperature difference, and if the first temperature difference meets a predetermined temperature difference threshold, a first dividing line is set at the first stage temperature; if the first temperature difference does not meet the predetermined temperature difference threshold, the simulated water pouring is continued until the water surface covers the maximum temperature value in the initial forging temperature distribution diagram, and then the water pouring is stopped to obtain a plurality of dividing lines; the initial forging temperature distribution diagram is divided based on the plurality of dividing lines to obtain the forging temperature distribution diagram.
[0019] Furthermore, the secondary cooling parameter optimization analysis module 15 is also used for: Obtain the second equipment attribute information of the secondary cooling equipment, and based on the digital twin, perform simulation modeling according to the forging attribute information, the forging temperature distribution map and the second equipment attribute information to generate a secondary cooling twin model; obtain the expected secondary cooling index, wherein the expected secondary cooling index includes the expected secondary cooling temperature and the expected secondary cooling duration; randomly select the first forging area temperature distribution map from the multiple forging area temperature distribution maps, and based on the expected secondary cooling temperature, the expected secondary cooling duration and the first forging area temperature distribution map, use the secondary cooling twin model and the cooling evaluation function to optimize the secondary cooling parameters for the purpose of minimizing the overall temperature difference and equipment energy consumption, obtain the first secondary cooling optimization parameters, and add them to the multiple secondary cooling optimization parameters.
[0020] Furthermore, the secondary cooling parameter optimization analysis module 15 is also used for: Based on the temperature distribution map of the first forging area, the target forging in the secondary cooling twin model is rendered to obtain a rendered cooling twin model; the parameter rated range of the secondary cooling parameters is obtained, wherein the secondary cooling parameters include flow rate, wind speed, wind direction and temperature; based on the parameter rated range, a plurality of initial secondary cooling parameters are randomly generated, wherein the initial secondary cooling parameters satisfy a predetermined uniform constraint and a predetermined quantity constraint; the plurality of initial secondary cooling parameters and the expected secondary cooling duration are input into the rendered cooling twin model for simulated cooling to obtain a plurality of simulated temperature distribution maps; a cooling evaluation function is constructed based on the expected secondary cooling temperature, and the cooling effect of the plurality of simulated temperature distribution maps is evaluated using the cooling evaluation function to obtain a plurality of cooling fitnesses; based on the cooling evaluation function and the plurality of cooling fitnesses, the secondary cooling parameters are optimized to output the first secondary cooling optimization parameters.
[0021] Furthermore, the secondary cooling parameter optimization analysis module 15 is also used for: The expression of the cooling evaluation function is: ;in, is the cooling fitness of the i-th cooling parameter, is the overall temperature difference weight, is the equipment energy consumption weight, is the number of temperature regions in the simulated temperature distribution map, is the importance of the nth temperature zone, is the proportion of the nth temperature zone, is the simulated temperature of the nth temperature zone after cooling by the i-th cooling parameter, is the expected secondary cooling temperature, is the simulated energy consumption of the i-th cooling parameter.
[0022] Furthermore, the secondary cooling parameter optimization analysis module 15 is also used for: The initial secondary cooling parameter is set as the initial solution, and multiple initial solutions are arranged from large to small according to the cooling fitness to generate an initial solution sequence; the first Q initial solutions of the initial solution sequence are selected as the head solution, and the last M initial solutions are set as the tail solution, wherein the sum of Q and M is the number of initial solutions, and M is an integer multiple of Q; with the Q head solutions as the center, the M tail solutions are randomly clustered to obtain Q domains, wherein the number of tail solutions in each domain is the same; within the Q domains, with the head solution as the mutation direction, the tail solution is mutated once according to the predetermined mutation step length to obtain Q Update domain, wherein if the mutated tail solution does not meet the rated interval of the parameter, the mutation is not performed; the mutated tail solution is evaluated based on the cooling evaluation function, and Q update domains are identified, and if the cooling fitness of the tail solution in the update domain is greater than the cooling fitness of the head solution, the head solution is replaced by the tail solution; iterative optimization is performed until a predetermined number of optimization times is met, Q current domains are output, and the head solution in the optimal current domain is selected and set as the first secondary cooling optimization parameters, wherein the optimal current domain is the domain with the largest sum of cooling fitness among the Q current domains.
[0023] Each embodiment in this specification is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. A steel structure cooling process control method and specific examples are also applicable to a steel structure cooling process control device in this embodiment. Through the detailed description of a steel structure cooling process control method, those skilled in the art can clearly know a steel structure cooling process control device in this embodiment, so for the sake of brevity of the specification, it will not be described in detail here. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description.
[0024] Embodiment 2: Based on the steel structure cooling process control device in the above embodiment, the present application also provides a steel structure cooling process control method, please refer to the attached Figure 2 ,include: Step 1: Collect forging property information, forging process parameters and expected primary cooling indicators of the target forging, and obtain first equipment property information of the primary cooling equipment.
[0025] Specifically, in a steel structure cooling process control device, the target forging is subjected to detailed attribute information collection through the information collection module, including the material properties, size specifications, shape structure, etc. of the forging. At the same time, the information collection module records various process parameters in the forging process, such as forging temperature, forging pressure, forging speed, etc., to ensure the accuracy and controllability of the forging process. In addition, the information collection module is also responsible for collecting the expected primary cooling indicators, including the cooling speed, cooling time, temperature after cooling, etc. of the forging, including the temperature of the forging after primary cooling and other primary cooling quality indicators, to ensure that the forging meets the predetermined performance requirements during the cooling process. In order to fully grasp the cooling process, the first equipment attribute information of the primary cooling equipment is obtained through the information collection module, and the primary cooling equipment refers to air cooling or oil cooling equipment. The first equipment attribute information includes equipment type, equipment working principle, equipment operation mode, etc. By comprehensively analyzing the information, the steel structure cooling process can be effectively controlled to improve the quality and production efficiency of forgings.
[0026] Step 2: Based on the forging property information, forging process parameters, expected primary cooling indicators and first equipment property information, the primary cooling parameters are optimized and analyzed to determine the primary cooling optimization parameters.
[0027] Specifically, in the steel structure cooling process control device, the primary cooling parameter optimization analysis module is used to optimize the material, shape, size and other property information of the forgings and the process parameters such as temperature, pressure, speed and so on during the forging process, combined with the expected cooling indicators such as cooling speed, cooling time, final cooling temperature, etc., and also needs to consider the working state and performance parameters of the primary cooling equipment, such as the cooling efficiency, capacity, reliability and other information of the equipment. Through the analysis of the information by the optimization analysis module, a set of optimal primary cooling parameters can be determined, including but not limited to the flow rate, temperature, pressure and so on of the cooling medium, as well as the duration of the cooling process, to ensure that the forgings can achieve the best cooling effect during the primary cooling process, thereby ensuring the mechanical properties and dimensional accuracy of the forgings, while improving production efficiency.
[0028] Step three: performing a primary cooling operation on the target forging according to the primary cooling optimization parameters, performing a temperature scan on the target forging after the primary cooling by using an infrared scanner, and generating an initial forging temperature distribution diagram.
[0029] Specifically, the forging temperature scanning module performs a cooling operation on the target forging according to the optimal cooling parameters determined by the primary cooling parameter optimization analysis module, including the flow rate, temperature, pressure and cooling time of the cooling medium, to ensure that the forging achieves the expected cooling effect during the cooling process.
[0030] Then, after the first cooling operation is completed, the forging temperature scanning module will use an infrared scanner to perform a non-contact temperature scan on the forging surface. The infrared scanner can quickly and accurately measure the temperature distribution on the forging surface and capture the infrared radiation emitted by the forging surface.
[0031] Using the data collected by the scanner, the forging temperature scanning module will generate an initial forging temperature distribution map, which shows the temperature distribution on the forging surface, including the temperature values of various areas of the forging and possible temperature gradients, to help the operator determine whether the forging has achieved the required cooling uniformity and final temperature state.
[0032] Step 4: Cluster the initial forging temperature distribution map to obtain a forging temperature distribution map, establish a mapping association between a secondary cooling device array and the forging temperature distribution map, and obtain multiple forging area temperature distribution maps, wherein the forging area temperature distribution map and the secondary cooling device have a one-to-one correspondence.
[0033] Specifically, in the steel structure cooling process control device, the forging temperature distribution clustering module clusters the initial forging temperature distribution map, divides the forging surface into different regions, each with similar temperature characteristics, identifies patterns in the temperature data, and divides the forging surface into several temperature regions. Several temperature regions represent different parts of the forging or specific regions formed due to temperature differences generated during forging and cooling.
[0034] Next, the forging temperature distribution clustering module will establish a mapping association between the secondary cooling device array and the forging temperature distribution map. The temperature distribution map of each forging area will correspond to a specific secondary cooling device, ensuring that each area can receive targeted cooling treatment to achieve more uniform temperature control and final forging performance. Multiple forging area temperature distribution maps are obtained through mapping, each of which corresponds to one or more devices in the secondary cooling device array, ensuring that the cooling process can be customized according to the actual situation of the forging, thereby improving cooling efficiency and forging quality.
[0035] Step 5: Based on the expected secondary cooling indicators and the temperature distribution diagrams of multiple forging regions, the secondary cooling parameters are optimized and analyzed using the secondary cooling twin model and cooling evaluation function to obtain multiple secondary cooling optimization parameters.
[0036] Specifically, ensure that the expected secondary cooling indicators have been obtained, including the expected secondary cooling temperature and the expected secondary cooling time. Ensure that multiple forging area temperature distribution maps have been obtained from the forging temperature distribution clustering module. Then, use the secondary cooling twin model and the cooling evaluation function to optimize the secondary cooling parameters. The secondary cooling twin model can simulate the actual secondary cooling process, while the cooling evaluation function can evaluate the cooling effect under different secondary cooling parameters. During the optimization analysis, according to the temperature distribution maps of multiple forging areas, ensure that the cooling effect of each area can meet the expected indicators. By adjusting the secondary cooling parameters, including flow rate, wind speed, wind direction and temperature, find the best parameter combination that can make the forging reach the expected secondary cooling temperature and duration. Finally, the optimization analysis module will output multiple secondary cooling optimization parameters, which will help improve cooling efficiency, ensure forging quality, and reduce energy consumption.
[0037] Step six: When the target forging is subjected to secondary cooling, mapping control is performed on the secondary cooling device array based on the multiple secondary cooling optimization parameters.
[0038] Specifically, the secondary cooling mapping control module receives multiple secondary cooling optimization parameters output from the secondary cooling parameter optimization analysis module, including the optimal cooling parameters for different forging areas, such as flow, wind speed, wind direction and temperature. Then, the secondary cooling mapping control module maps and controls the secondary cooling device array according to the optimization parameters. Each cooling device will be assigned a specific parameter setting to ensure that each area of the forging can be properly cooled. During the secondary cooling process, the mapping control module will monitor the operating status of the cooling device and the temperature change of the forging in real time, and adjust the cooling parameters as needed to ensure the flexibility and accuracy of the cooling process. After the mapping control is completed, the secondary cooling device array will perform the cooling operation according to the set parameters. By precisely controlling the cooling conditions, it is ensured that the forging reaches the expected temperature distribution and quality standards after secondary cooling. In addition, the secondary cooling mapping control module will also record relevant data in the cooling process, such as equipment operation data, forging temperature data, etc., for subsequent analysis and further parameter optimization.
[0039] The steel structure cooling process control method is applied to a steel structure cooling process control device, achieving the technical goal of improving the accuracy of cooling control, improving the uniformity of surface temperature distribution of forgings, reducing the negative impact of uneven temperature distribution, and improving the overall cooling effect of forgings and product quality.
[0040] Furthermore, the present application also includes: Taking the first equipment attribute information as the equipment constraint, taking the forging attribute information, forging process parameters and expected primary cooling indicators as the product constraints, homologous information retrieval is performed based on the industrial Internet to obtain a sample primary cooling parameter set; clustering and dividing the sample primary cooling parameter set is performed based on the K-means algorithm, and multiple sample primary cooling parameter groups are determined, and the sample primary cooling parameter groups that do not meet the predetermined quantity threshold are eliminated, and the standard primary cooling parameter set is obtained by fusion; clustering the standard primary cooling parameter set again based on the K-means algorithm, and calculating the mean of the parameters in the optimal clustering result is set as the primary cooling optimization parameter, wherein the optimal clustering result is the clustering result with the largest number of parameters.
[0041] Specifically, equipment constraints and product constraints are defined. Equipment constraints are based on the first equipment attribute information, including equipment performance parameters, operating status and fault information, etc. Product constraints include forging attribute information, forging process parameters and expected primary cooling indicators, including material properties, size specifications, shape structure of forgings, and temperature, pressure, speed, etc. during the forging process.
[0042] Next, the industrial Internet is used to retrieve homologous information and collect historical data similar to the target forgings and equipment to form a sample primary cooling parameter set. For example, the sample primary cooling parameter set comes from the cooling process of the same model of equipment or similar forgings.
[0043] Next, the K-means algorithm is used to cluster the sample one-time cooling parameter set. The K-means algorithm is an iterative algorithm that divides data points into K clusters so that the sum of the squared distances between each data point and the assigned cluster center is minimized. Multiple sample one-time cooling parameter groups are determined through the clustering process.
[0044] Then, the sample primary cooling parameter groups that do not meet the predetermined quantity threshold are eliminated. The predetermined quantity threshold can be determined according to actual production requirements and the results of data analysis to ensure the statistical significance of the sample quantity and the accuracy of clustering.
[0045] Then, the remaining sample primary cooling parameter groups are fused to obtain the standard primary cooling parameter set, which contains the optimization parameter candidates for subsequent analysis.
[0046] Next, the K-means algorithm is used again to cluster the standard primary cooling parameter set, and the clustering result with the largest number of parameters is found as the optimal clustering result.
[0047] Then, the mean of the parameters in the optimal clustering result is calculated and set as the primary cooling optimization parameter to guide the actual primary cooling process in order to achieve the best cooling effect and forging quality.
[0048] Through the powerful analytical capabilities of historical data and the industrial Internet, combined with the intelligent clustering of the K-means algorithm, accurate primary cooling optimization parameters are provided for the steel structure cooling process, thereby improving production efficiency and product quality.
[0049] Furthermore, the present application also includes: The minimum temperature value in the initial forging temperature distribution diagram is selected as the starting point, and water is simulated to be poured into the initial forging temperature distribution diagram, and the first temperature value that the water surface does not cover is set as the first stage temperature; the temperature difference between the first stage temperature and the minimum temperature value is calculated to obtain a first temperature difference, and if the first temperature difference meets a predetermined temperature difference threshold, a first dividing line is set at the first stage temperature; if the first temperature difference does not meet the predetermined temperature difference threshold, the simulated water pouring is continued until the water surface covers the maximum temperature value in the initial forging temperature distribution diagram, and then the water pouring is stopped to obtain a plurality of dividing lines; the initial forging temperature distribution diagram is divided based on the plurality of dividing lines to obtain the forging temperature distribution diagram.
[0050] Specifically, the minimum temperature value is determined in the initial forging temperature distribution diagram and used as the starting point. The starting point will be used in the subsequent simulated water filling process.
[0051] Next, the initial forging temperature distribution diagram is simulated with water filling. The simulated water gradually covers the higher temperature area from the lowest point on the diagram until a certain temperature value is reached. When the surface of the simulated water filling exceeds the first temperature value in the initial forging temperature distribution diagram, the temperature value is set as the first stage temperature, indicating a key point in the water filling process, that is, the water covers all areas from the lowest temperature to this temperature value.
[0052] Next, the temperature difference between the first stage temperature and the minimum temperature value is calculated to obtain the first temperature difference, which represents the temperature range from the minimum temperature to the first stage temperature. If the first temperature difference meets the predetermined temperature difference threshold, it means that the temperature range is significant, and a first dividing line can be set at the first stage temperature to divide the initial forging temperature distribution map into two different areas, each with different temperature characteristics. If the first temperature difference does not meet the predetermined temperature difference threshold, it means that the temperature range is not significant enough, and it is necessary to continue to simulate water filling until the water surface submerges the maximum temperature value in the initial forging temperature distribution map.
[0053] Then, once the water surface reaches the maximum temperature value, the water filling process is stopped. During the water filling process, multiple segmentation lines are obtained, each of which represents a significant temperature change point in the temperature distribution map.
[0054] Finally, the initial forging temperature distribution map is divided based on multiple segmentation lines to obtain the forging temperature distribution map, which divides the forging surface into multiple regions. Each region has its specific temperature characteristics, which is crucial for the subsequent cooling process control and forging quality assessment.
[0055] By simulating water filling and segmentation, the complexity of temperature distribution in forgings can be effectively analyzed and understood, and accurate temperature zone division can be provided for optimization of cooling process.
[0056] Furthermore, the present application also includes: Obtain the second equipment attribute information of the secondary cooling equipment, and based on the digital twin, perform simulation modeling according to the forging attribute information, the forging temperature distribution map and the second equipment attribute information to generate a secondary cooling twin model; obtain the expected secondary cooling index, wherein the expected secondary cooling index includes the expected secondary cooling temperature and the expected secondary cooling duration; randomly select the first forging area temperature distribution map from the multiple forging area temperature distribution maps, and based on the expected secondary cooling temperature, the expected secondary cooling duration and the first forging area temperature distribution map, use the secondary cooling twin model and the cooling evaluation function to optimize the secondary cooling parameters for the purpose of minimizing the overall temperature difference and equipment energy consumption, obtain the first secondary cooling optimization parameters, and add them to the multiple secondary cooling optimization parameters.
[0057] Specifically, the second device attribute information of the secondary cooling device is obtained, including performance parameters, operating status, capacity, etc. of the device.
[0058] Next, digital twin technology is used to perform simulation modeling based on forging property information, forging temperature distribution map and secondary equipment property information. Digital twin is a virtual model that can simulate actual equipment and process to predict and optimize actual operations.
[0059] Next, the generated secondary cooling twin model will be used for subsequent cooling parameter optimization to simulate the temperature changes of the forgings and the operation of the equipment during the secondary cooling process.
[0060] Next, the expected secondary cooling index, including the expected secondary cooling temperature and the expected secondary cooling time, is obtained as the target value for optimization to guide the determination of the secondary cooling parameters. The first forging area temperature distribution map is randomly selected from the multiple forging area temperature distribution maps as the object of optimization, representing a specific part on the forging, and the temperature distribution has specific characteristics.
[0061] Then, the secondary cooling twin model and cooling evaluation function are used to optimize the secondary cooling parameters in combination with the expected secondary cooling temperature, the expected secondary cooling time and the temperature distribution diagram of the first forging area to minimize the overall temperature difference and equipment energy consumption, so as to ensure the efficiency of the cooling process and the quality of the forgings.
[0062] Through the optimization process, the optimal secondary cooling parameters of the first forging area, namely the first secondary cooling optimization parameters, can be obtained and added to a plurality of secondary cooling optimization parameter sets to guide the actual secondary cooling process.
[0063] By utilizing digital twin technology and simulation models, combined with cooling evaluation functions, the secondary cooling parameters are optimized to improve cooling efficiency, reduce energy consumption, and ensure that the forgings reach the expected temperature state.
[0064] Furthermore, the present application also includes: Based on the temperature distribution map of the first forging area, the target forging in the secondary cooling twin model is rendered to obtain a rendered cooling twin model; the parameter rated range of the secondary cooling parameters is obtained, wherein the secondary cooling parameters include flow rate, wind speed, wind direction and temperature; based on the parameter rated range, a plurality of initial secondary cooling parameters are randomly generated, wherein the initial secondary cooling parameters satisfy a predetermined uniform constraint and a predetermined quantity constraint; the plurality of initial secondary cooling parameters and the expected secondary cooling duration are input into the rendered cooling twin model for simulated cooling to obtain a plurality of simulated temperature distribution maps; a cooling evaluation function is constructed based on the expected secondary cooling temperature, and the cooling effect of the plurality of simulated temperature distribution maps is evaluated using the cooling evaluation function to obtain a plurality of cooling fitnesses; based on the cooling evaluation function and the plurality of cooling fitnesses, the secondary cooling parameters are optimized to output the first secondary cooling optimization parameters.
[0065] Specifically, based on the temperature distribution map of the first forging area, the target forging in the secondary cooling twin model is rendered to create a rendered cooling twin model that can show the temperature changes of the forging during the secondary cooling process.
[0066] Next, the parameter rating intervals of the secondary cooling parameters are obtained, including flow, wind speed, wind direction and temperature. The parameter rating intervals define the acceptable range of the parameters. Based on the parameter rating intervals, multiple initial secondary cooling parameters are randomly generated to meet the predetermined uniformity constraints and quantity constraints to ensure the diversity and rationality of the parameters.
[0067] Then, the generated multiple initial secondary cooling parameters and expected secondary cooling time are input into the rendering cooling twin model to simulate cooling, calculate the temperature distribution of the forging under different secondary cooling parameters, and generate multiple simulated temperature distribution diagrams.
[0068] Next, based on the expected secondary cooling temperature, a cooling evaluation function is constructed to evaluate the cooling effect of the simulated temperature distribution diagram and find cooling parameters that can make the forging temperature as close to the expected temperature as possible. The cooling evaluation function is used to evaluate multiple simulated temperature distribution diagrams to obtain the cooling fitness of each simulation result. Cooling fitness is an indicator that measures how close the simulation result is to the expected temperature.
[0069] Finally, based on the cooling evaluation function and cooling fitness, the secondary cooling parameters are optimized, and the secondary cooling optimization parameters of the first forging area are output for the actual secondary cooling process to achieve the best cooling effect.
[0070] Through digital twin technology and cooling evaluation function, the optimal secondary cooling parameters can be effectively found to improve cooling efficiency, ensure forging quality, and reduce energy consumption.
[0071] Furthermore, the present application also includes: The expression of the cooling evaluation function is: ;in, is the cooling fitness of the i-th cooling parameter, is the overall temperature difference weight, is the equipment energy consumption weight, is the number of temperature regions in the simulated temperature distribution map, is the importance of the nth temperature zone, is the proportion of the nth temperature zone, is the simulated temperature of the nth temperature zone after cooling by the i-th cooling parameter, is the expected secondary cooling temperature, is the simulated energy consumption of the i-th cooling parameter.
[0072] Specifically, the cooling evaluation function evaluates the cooling parameters based on factors such as the overall temperature difference and equipment energy consumption. The simulated temperature of the nth temperature zone after cooling with the i-th cooling parameter is Expected secondary cooling temperature The smaller the difference is, the more important the difference is to the nth temperature zone. , the proportion of the nth temperature zone The smaller the product of The larger the value, the better the cooling parameter, and vice versa. The smaller the cooling parameter, the better the cooling adaptability. The larger it is, the better the cooling parameters are, and vice versa.
[0073] By constructing a cooling evaluation function, the efficiency and accuracy of obtaining cooling effect evaluation results can be improved.
[0074] Furthermore, the present application also includes: The initial secondary cooling parameter is set as the initial solution, and multiple initial solutions are arranged from large to small according to the cooling fitness to generate an initial solution sequence; the first Q initial solutions of the initial solution sequence are selected as the head solution, and the last M initial solutions are set as the tail solution, wherein the sum of Q and M is the number of initial solutions, and M is an integer multiple of Q; with the Q head solutions as the center, the M tail solutions are randomly clustered to obtain Q domains, wherein the number of tail solutions in each domain is the same; within the Q domains, with the head solution as the mutation direction, the tail solution is mutated once according to the predetermined mutation step length to obtain Q Update domain, wherein if the mutated tail solution does not meet the rated interval of the parameter, the mutation is not performed; the mutated tail solution is evaluated based on the cooling evaluation function, and Q update domains are identified, and if the cooling fitness of the tail solution in the update domain is greater than the cooling fitness of the head solution, the head solution is replaced by the tail solution; iterative optimization is performed until a predetermined number of optimization times is met, Q current domains are output, and the head solution in the optimal current domain is selected and set as the first secondary cooling optimization parameters, wherein the optimal current domain is the domain with the largest sum of cooling fitness among the Q current domains.
[0075] Specifically, the initially generated secondary cooling parameters are set as the initial solution, and are arranged from large to small according to the cooling fitness to generate an initial solution sequence for the subsequent optimization process.
[0076] Then, the first Q initial solutions are selected from the initial solution sequence as the head solution, and the last M initial solutions are selected as the tail solution. The sum of Q and M is equal to the total number of initial solutions, and M is an integer multiple of Q, so as to maintain the diversity and stability of the solution in the subsequent optimization process, where Q and M are integers greater than 1.
[0077] Then, the M tail solutions are randomly clustered with the Q head solutions as the center to form Q domains. Each domain contains the same number of tail solutions, which are then used to explore the solution space during the optimization process.
[0078] Next, within the Q domains, the tail solution is mutated once with the head solution as the mutation direction according to the predetermined mutation step length. If the mutated tail solution does not meet the parameter rating interval, this mutation is not performed to ensure that the mutated solution is still within the feasible parameter range. The mutated tail solution is evaluated using a cooling evaluation function to determine the cooling fitness. Then, in the Q update domains, it is identified whether the cooling fitness of the tail solution is greater than the cooling fitness of the head solution. If it is greater than the cooling fitness of the head solution, the head solution is replaced with the tail solution to keep the solution in the domain optimal. Perform iterative optimization until the predetermined number of optimizations is reached, output Q current domains, and select the domain with the largest sum of cooling fitness as the optimal current domain.
[0079] Finally, the head solution is selected from the optimal current field as the secondary cooling optimization parameters for the first forging region, and the optimal solution obtained after multiple iterations and optimizations is used to guide the actual secondary cooling process.
[0080] Through an iterative optimization method combined with domain variation and fitness evaluation, the optimal secondary cooling parameters can be effectively found, thereby improving the cooling efficiency and forging quality while reducing energy consumption.
[0081] In summary, the steel structure cooling process control method provided in this application has the following technical effects: The information acquisition module is used to collect the forging property information, forging process parameters and expected primary cooling index of the target forging, and obtain the first equipment property information of the primary cooling equipment; the primary cooling parameter optimization analysis module is used to optimize and analyze the primary cooling parameters based on the forging property information, forging process parameters, expected primary cooling index and first equipment property information, and determine the primary cooling optimization parameters; the forging temperature scanning module is used to perform a primary cooling operation on the target forging according to the primary cooling optimization parameters, and perform a temperature scan on the target forging after the primary cooling through an infrared scanner to generate an initial forging temperature distribution map; the forging temperature distribution clustering module is used to cluster the initial forging temperature distribution map to obtain the forging temperature A distribution map is constructed to establish a mapping association between the secondary cooling device array and the forging temperature distribution map, and obtain multiple forging area temperature distribution maps, wherein the forging area temperature distribution map and the secondary cooling device have a one-to-one correspondence; a secondary cooling parameter optimization analysis module is used to optimize and analyze the secondary cooling parameters based on the expected secondary cooling index and multiple forging area temperature distribution maps, and obtain multiple secondary cooling optimization parameters using the secondary cooling twin model and the cooling evaluation function; a secondary cooling mapping control module is used to map and control the secondary cooling device array based on the multiple secondary cooling optimization parameters when the target forging is subjected to secondary cooling, that is, through graded cooling, the cooling rate of the forging can be controlled, thereby reducing the occurrence of these problems. In addition, graded cooling also helps to improve the mechanical properties of the forging, such as toughness and wear resistance, while reducing deformation and residual stress after processing. Finally, the technical goal of improving the accuracy of cooling control is achieved, and the uniformity of the surface temperature distribution of the forging is improved, the negative impact caused by uneven temperature distribution is reduced, and the overall cooling effect and product quality of the forging are improved.
[0082] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.
[0083] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application belong to the scope of the present application and its equivalent technology, the present application is also intended to include these modifications and variations.
Claims
1. A steel structure cooling process control device, It is characterized in that include: An information collection module is used to collect forging property information, forging process parameters and expected primary cooling indicators of the target forging, and obtain first equipment property information of the primary cooling equipment; A primary cooling parameter optimization analysis module, used to optimize and analyze the primary cooling parameters based on the forging property information, the forging process parameters, the expected primary cooling index and the first equipment property information, and determine the primary cooling optimization parameters; a forging temperature scanning module, used to perform a primary cooling operation on the target forging according to the primary cooling optimization parameters, and perform a temperature scan on the target forging after the primary cooling by an infrared scanner to generate an initial forging temperature distribution diagram; A forging temperature distribution clustering module is used to cluster the initial forging temperature distribution map to obtain a forging temperature distribution map, establish a mapping association between a secondary cooling device array and the forging temperature distribution map, and obtain multiple forging area temperature distribution maps, wherein the forging area temperature distribution map and the secondary cooling device have a one-to-one correspondence; The secondary cooling parameter optimization analysis module is used to optimize and analyze the secondary cooling parameters based on the expected secondary cooling index and the temperature distribution diagrams of multiple forging regions, using the secondary cooling twin model and cooling evaluation function, and obtain multiple secondary cooling optimization parameters; The secondary cooling mapping control module is used to map and control the secondary cooling device array based on the multiple secondary cooling optimization parameters when the target forging is subjected to secondary cooling.
2. According to claim 1, a steel structure cooling process control device, It is characterized in that Optimize the primary cooling parameters, including: Taking the first equipment attribute information as equipment constraints, taking the forging attribute information, forging process parameters and expected primary cooling indicators as product constraints, performing homologous information retrieval based on the industrial Internet, and obtaining a sample primary cooling parameter set; Based on the K-means algorithm, the sample primary cooling parameter set is clustered and divided, multiple sample primary cooling parameter groups are determined, and the sample primary cooling parameter groups that do not meet the predetermined number threshold are eliminated, and the standard primary cooling parameter set is obtained by fusion; The standard primary cooling parameter set is clustered again based on the K-means algorithm, and the mean of the parameters in the optimal clustering result is calculated and set as the primary cooling optimization parameter, wherein the optimal clustering result is the clustering result with the largest number of parameters.
3. According to the steel structure cooling process control device of claim 1, It is characterized in that Get the forging temperature distribution diagram, including: Selecting the minimum temperature value in the initial forging temperature distribution diagram as the starting point, simulating water filling into the initial forging temperature distribution diagram, and setting the first temperature value covered by the water surface as the first stage temperature; Calculating the temperature difference between the first stage temperature and the minimum temperature value to obtain a first temperature difference, and setting a first dividing line at the first stage temperature if the first temperature difference meets a predetermined temperature difference threshold; If the first temperature difference does not meet the predetermined temperature difference threshold, the simulated water filling is continued until the water surface exceeds the maximum temperature value in the initial forging temperature distribution diagram, and then the water filling is stopped to obtain multiple segmentation lines; The initial forging temperature distribution diagram is divided based on the multiple segmentation lines to obtain the forging temperature distribution diagram.
4. According to claim 3, a steel structure cooling process control device, It is characterized in that Optimize the secondary cooling parameters, including: Acquire the second equipment attribute information of the secondary cooling equipment, and perform simulation modeling based on the digital twin according to the forging attribute information, the forging temperature distribution diagram and the second equipment attribute information to generate a secondary cooling twin model; Obtaining an expected secondary cooling index, wherein the expected secondary cooling index includes an expected secondary cooling temperature and an expected secondary cooling time; A first forging area temperature distribution map is randomly selected from the multiple forging area temperature distribution maps, and based on the expected secondary cooling temperature, the expected secondary cooling time and the first forging area temperature distribution map, the secondary cooling twin model and the cooling evaluation function are used to optimize the secondary cooling parameters for the purpose of minimizing the overall temperature difference and equipment energy consumption, to obtain the first secondary cooling optimization parameters, and add them to the multiple secondary cooling optimization parameters.
5. A steel structure cooling process control device according to claim 4, It is characterized in that To minimize the overall temperature difference and equipment energy consumption, the secondary cooling parameters are optimized, including: Rendering the target forging in the secondary cooling twin model based on the first forging region temperature distribution map to obtain a rendered cooling twin model; Obtaining a parameter rating range of a secondary cooling parameter, wherein the secondary cooling parameter includes flow rate, wind speed, wind direction, and temperature; randomly generating a plurality of initial secondary cooling parameters based on the parameter rating interval, wherein the initial secondary cooling parameters satisfy a predetermined uniformity constraint and a predetermined quantity constraint; Inputting the multiple initial secondary cooling parameters and the expected secondary cooling duration into the rendering cooling twin model to simulate cooling, and obtaining multiple simulated temperature distribution diagrams; Constructing a cooling evaluation function based on the expected secondary cooling temperature, and evaluating the cooling effect of the multiple simulated temperature distribution diagrams using the cooling evaluation function to obtain multiple cooling fitnesses; Based on the cooling evaluation function and a plurality of cooling fitnesses, the secondary cooling parameters are optimized and the first and second cooling optimization parameters are output.
6. A steel structure cooling process control device according to claim 5, It is characterized in that Construct a cooling evaluation function, including: The expression of the cooling evaluation function is: ; in, is the cooling fitness of the i-th cooling parameter, is the overall temperature difference weight, is the equipment energy consumption weight, is the number of temperature regions in the simulated temperature distribution map, is the importance of the nth temperature zone, is the proportion of the nth temperature zone, is the simulated temperature of the nth temperature zone after cooling by the i-th cooling parameter, is the expected secondary cooling temperature, is the simulated energy consumption of the i-th cooling parameter.
7. A steel structure cooling process control device according to claim 5, It is characterized in that Based on the cooling evaluation function and multiple cooling fitnesses, optimizing the secondary cooling parameters includes: The initial secondary cooling parameters are set as the initial solution, and multiple initial solutions are arranged from large to small according to the cooling fitness to generate an initial solution sequence; The first Q initial solutions of the initial solution sequence are selected as the head solution, and the last M initial solutions are set as the tail solution, wherein the sum of Q and M is the number of initial solutions, and M is an integral multiple of Q; Taking the Q head solutions as the center, the M tail solutions are randomly clustered to obtain Q domains, where the number of tail solutions in each domain is the same; In Q domains, the head solution is used as the mutation direction, and the tail solution is mutated once according to the predetermined mutation step length to obtain Q updated domains. If the mutated tail solution does not meet the parameter rated interval, this mutation is not performed; The mutated tail solution is evaluated based on the cooling evaluation function, Q update areas are identified, and if the cooling fitness of the tail solution in the update area is greater than the cooling fitness of the head solution, the head solution is replaced by the tail solution; Iterate the optimization until the predetermined number of optimizations is met, output Q current fields, select the head solution in the optimal current field and set it as the first secondary cooling optimization parameter, wherein the optimal current field is the field with the largest sum of cooling fitness among the Q current fields.
8. A steel structure cooling process control method, It is characterized in that The steel structure cooling process control method is performed by a steel structure cooling process control device according to any one of claims 1 to 7, comprising: Collect forging property information, forging process parameters and expected primary cooling index of the target forging, and obtain first equipment property information of the primary cooling equipment; Based on the forging property information, the forging process parameters, the expected primary cooling index and the first equipment property information, optimizing and analyzing the primary cooling parameters to determine the primary cooling optimization parameters; Performing a primary cooling operation on the target forging according to the primary cooling optimization parameters, performing a temperature scan on the target forging after the primary cooling by an infrared scanner, and generating an initial forging temperature distribution diagram; Clustering the initial forging temperature distribution map to obtain a forging temperature distribution map, establishing a mapping association between a secondary cooling device array and the forging temperature distribution map to obtain a plurality of forging region temperature distribution maps, wherein the forging region temperature distribution map and the secondary cooling device have a one-to-one correspondence; Based on the expected secondary cooling index and the temperature distribution diagrams of multiple forging regions, the secondary cooling parameters are optimized and analyzed using the secondary cooling twin model and cooling evaluation function to obtain multiple secondary cooling optimization parameters. When the target forging is subjected to secondary cooling, the secondary cooling device array is mapped and controlled based on the multiple secondary cooling optimization parameters.
Citation Information
Patent Citations
Water cooling control system and method for online quenching
CN117127005A
Method and system for automatically generating production plan of heat treatment furnace
CN118333785A
Continuous annealing unit energy consumption optimization method based on digital twinning idea
CN118569062A
Process and device for cooling metals in a steel works
DE19717615A1
Optimization and control of microstructure development during hot metal working
US6233500B1
Cited By
Photovoltaic module defect diagnosis method and device using string segmentation
CN121526956A
