Metal casting cooling water control method and device, electronic equipment and storage medium

Abstract

The application provides a metal casting cooling water control method and device, electronic equipment and storage medium, and relates to the technical field of metal casting. The method comprises the following steps: acquiring real-time temperature data measured at a plurality of specified positions of a large complex structure; acquiring first target temperature data corresponding to the real-time temperature data; calculating first temperature deviation data according to the real-time temperature data and the first target temperature data; calculating cooling water flow adjustment data of a plurality of cooling circuits corresponding to the plurality of specified positions according to the first temperature deviation data; and adjusting the cooling water flow of the plurality of cooling circuits according to the cooling water flow adjustment data. The method of the application utilizes multi-point real-time temperature feedback to dynamically correct the cooling water flow, so as to cope with the influence of complex structures, sand changes and other uncertainties on the solidification process, and realize tracking and regulation of the solidification process of different regions of a complex casting.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of metal casting, in particular to a metal casting cooling water control method and device, electronic equipment and storage medium. BACKGROUND

[0002] In the sand casting production of large and complex structural parts, high-temperature liquid metal is poured into the pre-prepared sand cavity. The metal begins to solidify and form a solid casting by heat dissipation in the sand mold. Due to the significant thickness variation, internal cavities and complex geometric features of large and complex structural parts, there are great differences in heat dissipation conditions and solidification speed in different areas. During the solidification process, there is a solid-liquid phase interface, i.e. the solidification front, in the metal. The position, shape and advancing speed of the solidification front in three-dimensional space directly determine the internal organization uniformity, grain size distribution and whether micro or macro defects such as shrinkage, porosity, cracks caused by stress concentration, etc. occur in the casting. In order to regulate the solidification process of complex castings, technicians arrange cooling pipe systems outside or inside the sand mold. The system includes multiple independent cooling water circuits, each of which is responsible for cooling a specific area of the casting. By independently controlling the cooling water flow, temperature and other parameters of each cooling circuit, the heat dissipation rate of different areas of the casting can be adjusted, thereby affecting the advancement of the local solidification front.

[0003] A control method based on solidification front prediction is introduced to improve the control effect. First, a heat transfer and solidification numerical simulation model is constructed using the three-dimensional model of the casting, metal physical parameters, pouring parameters and cooling pipe layout, etc. The model can predict the three-dimensional position and shape of the solidification front at any time in the casting under given cooling conditions. Based on the predicted solidification front information, the control system calculates the required cooling water parameters for each cooling circuit. For example, if it is predicted that the solidification speed of a thick area is too slow and the solidification front position is too low, the system will calculate the cooling water flow of the cooling circuit corresponding to the area to be increased to speed up heat dissipation and promote the upward advancement of the solidification front; on the contrary, if the thin-walled area solidifies too quickly and the predicted solidification front position is too high, the cooling water flow of the cooling circuit of the area will be reduced.

[0004] However, this prediction-based control method faces challenges in practical applications. Heat transfer solidification numerical simulation models require metal physical property parameters as inputs. These metal physical property parameters can be biased due to fluctuations in alloy composition, differences between batches of materials, or differences in production environments and measurement conditions. Due to the bias in metal physical property parameters, the prediction results of the numerical simulation model for the solidification front deviate from the actual situation. The cooling pipe system contains multiple independent circuits, and the cooling water flow rate of each circuit is controlled by an electric regulating valve or a flow control valve. These actuators can have limited adjustment accuracy or response delays. After a long period of use, scale accumulation can occur inside the cooling pipe, or partial blockage of the nozzle can occur, resulting in a difference between the actual cooling water flow rate through a cooling circuit and the command value issued by the control system, and this difference can change over time. Due to the difference between the actual cooling water flow rate and the command value, the actual cooling intensity applied to the surface of the casting does not match the ideal cooling intensity required by the prediction model. Due to the double effects of inaccurate input parameters of the prediction model and execution bias of the actual cooling water flow rate, there is a cumulative error between the initial predicted solidification front position and the actual solidification front position. The structure of the casting is complex, and the solidification fronts of different regions interact with each other, and changes in the solidification state of one region can affect the heat dissipation and solidification of adjacent regions. This interaction can be difficult to fully capture in the prediction model. The permeability, thermal conductivity, and other properties of the sand mold can vary between batches or change locally due to the influence of high-temperature metal thermal radiation during pouring, which can also affect the actual heat dissipation process, but it is difficult to accurately obtain and input into the prediction model in real time. The above various uncertainties and error sources together cause the cooling water control scheme based on the initial prediction to fail to ensure that the actual solidification front of all key regions maintains the desired target position or advances along the preset path during the entire solidification process. SUMMARY

[0005] The purpose of the present application is to provide a metal casting cooling water control method, device, electronic equipment and storage medium, which uses multi-point real-time temperature feedback to dynamically correct the cooling water flow rate, to cope with the influence of complex structure, sand mold changes and other uncertainties on the solidification process, and to realize the tracking and regulation of the solidification process of different regions of complex castings.

[0006] In a first aspect, the present application provides a metal casting cooling water control method applied to sand casting of large complex structural parts, comprising the following steps:

[0007] Obtaining real-time temperature data measured at a plurality of specified positions of a large complex structural part;

[0008] Obtaining first target temperature data corresponding to the real-time temperature data;

[0009] According to the real-time temperature data and the first target temperature data, first temperature deviation data is calculated;

[0010] According to the first temperature deviation data, cooling water flow adjustment data of multiple cooling circuits corresponding to the multiple specified positions is calculated;

[0011] According to the cooling water flow adjustment data, the cooling water flow of the multiple cooling circuits is adjusted.

[0012] The metal casting cooling water control method provided by the application uses the difference between the actual temperature information from the key area of the casting and the preset target temperature to dynamically calculate and adjust the flow of each independent cooling water circuit, thereby correcting the deviation between the actual solidification process and the expected process, making the actual solidification front advance according to the preset path, and realizing the tracking and regulation of the solidification process of different regions of a complex casting.

[0013] In a second aspect, the application provides a metal casting cooling water control device applied to sand casting of large and complex structural parts, comprising:

[0014] A first acquisition module is configured to acquire real-time temperature data measured at multiple specified positions of a large and complex structural part;

[0015] A second acquisition module is configured to acquire first target temperature data corresponding to the real-time temperature data;

[0016] A first calculation module is configured to calculate first temperature deviation data according to the real-time temperature data and the first target temperature data;

[0017] A second calculation module is configured to calculate cooling water flow adjustment data of multiple cooling circuits corresponding to the multiple specified positions according to the first temperature deviation data;

[0018] An adjustment module is configured to adjust the cooling water flow of the multiple cooling circuits according to the cooling water flow adjustment data.

[0019] In a third aspect, the application provides an electronic device comprising a processor and a memory, wherein the memory stores computer readable instructions, and when the computer readable instructions are executed by the processor, the steps of the metal casting cooling water control method provided in the first aspect are executed.

[0020] In a fourth aspect, the application provides a computer readable storage medium, which stores a computer program, and when the computer program is executed by a processor, the steps of the metal casting cooling water control method provided in the first aspect are executed.

[0021] From the above, the metal casting cooling water control method provided by the application can overcome various uncertain factors such as metal physical parameter deviation, numerical simulation model simplification error, cooling water actuator adjustment deviation, cooling pipeline actual flow deviation, sand mold performance change and mutual influence of solidification processes in different regions of the casting, realize tracking and regulation of the actual solidification front position based on the solidification front prediction, significantly improve the control accuracy and robustness of the solidification process of the complex casting, effectively improve the internal organization uniformity of the casting, reduce or eliminate shrinkage holes, shrinkage, cracks and other solidification defects, and improve the casting quality and yield of the large complex structure.

[0022] Other features and advantages of the present application will be set forth in the following description, and in part will become apparent to those skilled in the art upon examination of the following or can be learned by practice of the present application. The objects and other advantages of the present application can be realized and attained by the structure particularly pointed out in the written description and the appended drawings. BRIEF DESCRIPTION OF DRAWINGS

[0023] Figure 1 A flow chart of the metal casting cooling water control method provided by the embodiment of the present application.

[0024] Figure 2 A structural schematic diagram of the metal casting cooling water control device provided by the embodiment of the present application.

[0025] Figure 3 A structural schematic diagram of the electronic device provided by the embodiment of the present application.

[0026] REFERENCE NUMERALS

[0027] 100, first acquisition module; 200, second acquisition module; 300, first calculation module; 400, second calculation module; 500, adjustment module; 13, electronic device; 1301, processor; 1302, memory; 1303, communication bus. DETAILED DESCRIPTION

[0028] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application described and shown in the drawings can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the claimed present application, but only represents selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative work belong to the scope of protection of the present application.

[0029] It should be noted that similar reference numbers and letters refer to similar items in the following drawings, and therefore, once an item is defined in one drawing, it need not be further defined and explained in subsequent drawings. Meanwhile, in the description of the present application, the terms "first", "second", and the like are only used to distinguish description, and cannot be understood as indicating or implying relative importance.

[0030] With reference to the accompanying drawings, which are incorporated herein by reference, and which illustrate embodiments of the application, in which: Figure 1 The present application provides a metal casting cooling water control method, applied to sand casting of large complex structural parts, comprising the following steps:

[0031] Obtaining real-time temperature data measured at a plurality of specified positions of the large complex structural part; the specified positions are arranged with temperature sensors;

[0032] Obtaining first target temperature data corresponding to the real-time temperature data; the first target temperature data is determined by a target temperature curve preset for the plurality of specified positions;

[0033] According to the real-time temperature data and the first target temperature data, calculating first temperature deviation data;

[0034] According to the first temperature deviation data, calculating cooling water flow adjustment data of a plurality of cooling circuits corresponding to the plurality of specified positions;

[0035] According to the cooling water flow adjustment data, adjusting the cooling water flow of the plurality of cooling circuits.

[0036] The multiple specified positions refer to pre-selected areas on the large and complex structural component that are representative of the solidification process, such as thick sections or thin-walled sections. The real-time temperature data refer to actual temperature measurements obtained during the casting solidification process through temperature sensors, such as thermocouples, arranged at the specified positions, which are used to obtain actual thermal state information of key areas of the casting. The first target temperature data refer to temperature values expected to be reached at the specified positions at the corresponding time of the real-time temperature data, which are determined by pre-setting a temperature curve changing over time for each specified position. These temperature curves can be set based on numerical simulation or process experience, which are used to provide a reference for evaluating the degree of deviation of the actual temperature. The first temperature deviation data refer to the difference between the real-time temperature data and the first target temperature data, which quantifies the deviation between the actual thermal state and the expected thermal state of the specified positions of the casting, which is used as a feedback signal to drive the subsequent cooling water flow adjustment. The cooling water flow adjustment data refer to instructions or values calculated based on the first temperature deviation data for adjusting the cooling water flow of the multiple cooling circuits, which can be calculated using algorithms such as proportional control or integral control, which are used to convert temperature deviation information into control execution instructions. Adjusting the cooling water flow of the multiple cooling circuits refers to changing the cooling water flow through each cooling circuit by controlling the corresponding actuator, such as an electric regulating valve, according to the cooling water flow adjustment data, which is used to change the heat dissipation rate of local areas of the casting and correct the actual solidification process.

[0037] The core innovation of the present application is to introduce real-time temperature feedback at specified positions of the large and complex structural component, obtain the deviation between the actual temperature and the target temperature, and dynamically calculate and adjust the cooling water flow of the multiple cooling circuits based on the deviation, thereby overcoming the uncertainty caused by relying solely on the prediction model, achieving closed-loop control of the actual solidification process, and improving the precision and adaptability of the cooling control.

[0038] Specifically, the method regulates the solidification process of large and complex structural components by establishing a control loop based on real-time feedback. During the solidification process of the casting, temperature sensors arranged at multiple designated locations continuously monitor and output real-time temperature data, which reflects the actual thermal state of the key areas of the casting. At the same time, the system obtains first target temperature data corresponding to these designated locations from the preset temperature curve at the current time, which represents the desired temperature state. Then, the real-time temperature data is compared with the first target temperature data, and first temperature deviation data is calculated, which quantifies the deviation between the actual state and the desired state. Based on this first temperature deviation data, the control algorithm calculates cooling water flow adjustment data for each cooling circuit, which indicates the amount of flow adjustment each circuit needs to make to reduce the temperature deviation. Finally, according to the calculated cooling water flow adjustment data, the control system drives the corresponding actuator to change the actual cooling water flow of each cooling circuit. By changing the flow of the cooling circuit corresponding to a specific area, the heat dissipation rate of that area can be changed, thereby affecting the advancement of the local solidification front, causing the actual temperature to approach the target temperature. This process continues, forming a dynamic feedback loop, allowing the system to respond in real time to changes in the internal thermal state of the casting and correct deviations caused by various uncertainty factors.

[0039] The working principle of the present application is to pre-set temperature sensors in the key areas of the casting / sand mold, and to monitor the actual temperature of these areas in real time. At the same time, the target temperature curve of these key areas is set as a function of time during the ideal solidification process. During the solidification process, actual temperature data is continuously collected and compared with the target temperature at the current time to calculate the temperature deviation. This temperature deviation reflects the difference between the actual solidification process and the expected process, which is caused by the accumulation of various uncertainty factors such as metal physical property parameters, model errors, actuator deviations, and sand changes. The control algorithm takes the temperature deviation as input and calculates the adjustment amount needed for the cooling water flow of the corresponding cooling circuit. For example, if the actual temperature is higher than the target temperature, it indicates that the cooling of the region is insufficient, and the system will instruct to increase the cooling water flow; if the actual temperature is lower than the target temperature, it will instruct to reduce the cooling water flow. These adjustment instructions are sent to the cooling water flow control actuator (such as an electric regulating valve) to change the actual cooling water flow through the cooling circuit in real time, thereby correcting the heat dissipation rate of the region. Through the continuous cycle of temperature monitoring, deviation calculation and flow adjustment, the system can sense and compensate for the effects of various uncertainties in real time, so that the actual temperature trajectory of the key areas is as close as possible to the target trajectory, thereby achieving dynamic tracking and regulation of the actual solidification front position and advancement speed, ensuring the internal solidification quality of the casting.

[0040] The present application can dynamically monitor the actual solidification state of key areas in the sand casting process of large and complex structural parts by introducing multi-point real-time temperature feedback and constructing a closed-loop control method. Compared with open-loop control based only on initial prediction, the present method can perceive and compensate for the deviation between the actual solidification process and the prediction caused by various uncertain factors such as deviation of metal physical property parameters, error of numerical simulation model, actual flow deviation of cooling water actuator and pipeline, change of sand performance, and mutual influence of different areas during solidification. By dynamically adjusting the cooling water flow of each independent cooling circuit according to the real-time temperature deviation, the system can effectively pull the actual temperature trajectory of the key areas back to the target trajectory reflecting the ideal solidification front advance, achieving accurate tracking and regulation of the actual solidification front position and advance speed. This significantly improves the control accuracy and robustness of the solidification process of complex castings, effectively improves the uniformity of the internal structure of the castings, reduces or eliminates shrinkage, porosity, cracks and other solidification defects, and improves the casting quality and yield of large and complex structural parts.

[0041] As a preferred embodiment, the scheme of the present application is implemented as follows: In the sand casting process of large and complex structural parts, thermocouples can be pre-embedded as temperature sensors in key areas such as thick parts or thin-walled transition zones of the casting for real-time acquisition of temperature data. These thermocouples are connected to an industrial controller through a data acquisition module. In the controller, target temperature curves set for each thermocouple position are pre-stored, which can be temperature lookup tables with time as the independent variable. The controller periodically reads the real-time temperature data of the thermocouples and obtains the corresponding target temperature data from the lookup table according to the current time. Then, the controller calculates the difference between the real-time temperature and the target temperature at each position to obtain the temperature deviation. Based on these temperature deviations, the controller runs a control algorithm to calculate the cooling water flow adjustment amount required for each cooling circuit. For example, if the actual temperature at a certain position is higher than the target temperature, the corresponding cooling circuit flow adjustment amount will indicate an increase in flow; if it is lower than the target temperature, it will indicate a decrease in flow. The calculated flow adjustment amount is sent to the electric regulating valve connected to each cooling circuit through the output module. These regulating valves change the valve opening according to the received signal to control the cooling water flow through each cooling circuit. The whole process is executed in a set cycle to achieve dynamic regulation of the casting solidification process.

[0042] Through the above scheme, the real-time temperature feedback mechanism is introduced, the actual heat state of the key area of the casting is directly monitored, and the closed-loop adjustment of the cooling water flow is carried out based on the deviation between the actual state and the target state. This feedback-based control method can compensate for the deviation of the solidification process caused by various uncertain factors such as metal physical property parameter deviation, cooling system execution error, sand performance change, and mutual influence between regions. Compared with the scheme that purely relies on the prediction model, the method can reflect and respond to the dynamic changes in the actual solidification process, improving the accuracy and adaptability of the cooling control. By regulating the heat dissipation rate of different regions, the position and advancing speed of the solidification front can be controlled, which helps to obtain a uniform structure of the casting.

[0043] In some embodiments, according to the first temperature deviation data, the step of calculating the cooling water flow adjustment data of the plurality of cooling circuits corresponding to the plurality of specified positions comprises:

[0044] According to the first temperature deviation data, the deviation degree of the solidification state of different regions in the large and complex structural part and the spatial deviation distribution characteristics are determined;

[0045] According to the deviation degree of the solidification state and the spatial deviation distribution characteristics, based on the cooling influence characteristics of the plurality of cooling circuits on different regions in the large and complex structural part, the cooling water flow adjustment data of the plurality of cooling circuits is calculated; the cooling influence characteristics describe the influence degree and range of the unit flow change of each cooling circuit on the temperature or solidification state of different regions in the large and complex structural part.

[0046] The deviation degree of the solidification state refers to the difference between the actual solidification state (such as solid phase rate, temperature, solidification speed, etc.) of different regions inside the large and complex structural part and the preset target solidification state, which can be quantified by temperature deviation, solid phase rate deviation, solidification speed deviation, etc. The spatial deviation distribution characteristics refer to the distribution of the above-mentioned deviation degree of the solidification state in the three-dimensional space of the large and complex structural part, including the position, shape, size of the deviation region and the relative relationship between different deviation regions, which can be described by spatial interpolation, region division, feature extraction, etc. The cooling influence characteristics refer to the influence degree and range of the cooling water flow change of each cooling circuit of the large and complex structural part on the temperature or solidification state of different regions inside the casting, which can be represented by influence matrix, transfer function, response surface, etc. Model, reflecting the adjustment ability and action range of the cooling circuit.

[0047] The present scheme is a refinement and improvement of the step of calculating cooling water flow adjustment data based on first temperature deviation data, aiming to solve the technical problem of how to comprehensively utilize temperature deviation data from multiple locations, consider the mutual influence of solidification in different regions and the difference in the influence of different cooling circuits on different regions, and calculate adjustment data that can coordinate the action of multiple cooling circuits and optimize the overall solidification process in the context of sand casting of large complex structural parts. First, according to the first temperature deviation data, the solidification state deviation degree and spatial deviation distribution characteristics of different regions in the large complex structural part are determined. The role of this step is not only to simply obtain the temperature deviation of the specified location, but also to further analyze and infer the deviation degree of the actual solidification state of different regions in the casting from the target state based on these deviation information, as well as the distribution of this deviation in the entire casting space. By transforming local temperature deviation information into an understanding of the overall solidification state and its spatial distribution, the actual situation of uneven solidification inside the casting can be more comprehensively and accurately grasped, and the regions that need to be focused on and adjusted and the severity of the problem can be identified, providing more instructive information for subsequent precise adjustment. Second, according to the solidification state deviation degree and spatial deviation distribution characteristics, based on the cooling influence characteristics of multiple cooling circuits on different regions in the large complex structural part, the cooling water flow adjustment data of multiple cooling circuits is calculated. After the deviation of the solidification state inside the casting and the spatial distribution are determined, this step utilizes the actual cooling influence characteristics of each cooling circuit on different regions of the casting to calculate the specific flow adjustment amount. Cooling influence characteristics describe the influence degree and range of unit flow change of each cooling circuit on the temperature or solidification state of different regions in the large complex structural part, which reflects the actual adjustment capacity and range of the cooling system. By combining the solidification state deviation information (degree and distribution) that needs to be corrected and the actual influence ability of the cooling circuit, the flow adjustment amount that each cooling circuit needs to make can be calculated, so that the adjustment measures can be targeted to the regions with solidification problems, and the actual effects and mutual influence of different circuits are considered, so that the uneven solidification can be corrected more effectively, and the precise control of the solidification process of the casting is realized. Through the above steps, the present scheme can transform scattered temperature deviation information into a comprehensive understanding of the overall solidification state of the casting, and combine the actual influence ability of the cooling system to calculate consistent cooling water flow adjustment data, thereby overcoming the limitations of simple adjustment based on local temperature deviation, and realizing fine and integrated control of the solidification process of large complex structural parts.

[0048] In one embodiment, determining the solidification state deviation and spatial deviation distribution of different regions in the large complex structural part according to the first temperature deviation data can be specifically implemented in the following manner: first, an inference model of the internal temperature field is constructed using the geometric model of the large complex structural part, the thermal physical parameters of the material, and the thermal physical parameters of the sand mold, etc. The model can be a numerical simulation model based on finite element or finite difference method, or a prediction model based on machine learning. Then, the first temperature deviation data measured at the specified location is input, and the temperature deviation data at other locations in the large complex structural part without temperature sensors is inferred based on the inference model. Then, the temperature deviation field at any location inside the large complex structural part can be calculated by integrating the first temperature deviation data at the specified location and the inferred temperature deviation data at other locations. Based on the temperature deviation field and combined with the solidification characteristics of the material (for example, the relationship between solid fraction and temperature), the solid fraction deviation or solidification speed deviation of different regions can be further calculated, thereby determining the solidification state deviation. At the same time, by analyzing the spatial distribution of the temperature deviation field or the solidification state deviation field, the regions with large deviation, the gradient direction of the deviation, and the spatial relationship between different deviation regions are identified, thereby determining the spatial deviation distribution. In the same embodiment, based on the cooling influence characteristics of multiple cooling circuits on different regions in the large complex structural part according to the solidification state deviation and the spatial deviation distribution, the cooling water flow adjustment data of the multiple cooling circuits can be calculated in the following manner: first, the cooling influence characteristic model describing the influence of unit flow change of each cooling circuit on the temperature or solidification state of different regions of the casting is obtained or established. The model can be a linear or nonlinear mapping relationship, such as an influence matrix, where the matrix elements represent the influence coefficient of unit flow change of a certain cooling circuit on the temperature or solid fraction of a certain region. Then, the determined solidification state deviation and spatial deviation distribution are input, and combined with the cooling influence characteristic model, an optimization problem or control algorithm is constructed. The optimization problem can be to minimize the overall solidification state deviation or maximize the solidification uniformity as the objective, with the cooling circuit flow adjustment range as the constraint, to solve the optimal flow adjustment amount of each cooling circuit. The control algorithm can be a model-based predictive control algorithm or a multivariable PID control algorithm, which uses the solidification state deviation information and the cooling influence characteristic model to calculate the flow adjustment data of each cooling circuit in real time that can effectively reduce the deviation. For example, if there is a large solidification lag (high solidification state deviation) in a certain region, and the region is mainly affected by one or a few cooling circuits (judged according to the spatial deviation distribution and the cooling influence characteristics), the flow adjustment amount of these cooling circuits is calculated to be increased, while considering the influence of other circuits on the region and adjacent regions, to coordinate the actions of each circuit and avoid excessive cooling or cause new unevenness.

[0049] By the technical solution, the solidification state deviation of different regions in the large complex structural member and the spatial distribution thereof can be comprehensively considered, and the actual cooling influence ability of the multiple cooling circuits on different regions is combined to calculate the coordinated and consistent cooling water flow adjustment data. This makes the cooling control no longer rely on the local temperature feedback, but is based on the more comprehensive cognition of the overall solidification process of the casting and the accurate grasp of the adjustment ability of the cooling system. Therefore, the scheme can more effectively correct the uneven solidification, avoid local overcooling or undercooling, reduce the generation of casting defects such as shrinkage holes and shrinkage porosities, and thus improve the casting quality and yield of the large complex structural member.

[0050] In some embodiments, the step of determining the solidification state deviation degree and the spatial deviation distribution characteristics of different regions in the large complex structural member according to the first temperature deviation data comprises:

[0051] obtaining specific parameter information; the specific parameter information comprises geometric information of the large complex structural member, thermal physical parameters of the large complex structural member, and thermal physical parameters of the sand mold;

[0052] determining an inference mechanism of the internal temperature field of the large complex structural member based on the specific parameter information;

[0053] inferred second temperature deviation data of other positions except the specified positions in the large complex structural member according to the first temperature deviation data and the inference mechanism; the other positions are not arranged with temperature sensors;

[0054] determining the solidification state deviation degree and the spatial deviation distribution characteristics of different regions in the large complex structural member according to the first temperature deviation data and the second temperature deviation data.

[0055] Specifically, first, specific parameter information is needed, which is the basis for understanding and predicting the internal temperature field changes of large complex structural parts during sand casting. The specific parameter information can include the geometric information of the large complex structural part, such as its three-dimensional shape, size, internal structure, etc.; the thermal physical parameters of the large complex structural part, such as the thermal conductivity, specific heat capacity, density, and phase change latent heat of the casting material at different temperatures; and the thermal physical parameters of the sand mold, such as the thermal conductivity, specific heat capacity, and density of the sand mold. These parameters provide the necessary physical constraints and inputs for subsequent temperature field modeling or inference mechanisms. Based on these specific parameter information, the inference mechanism of the internal temperature field in the large complex structural part can be determined. The inference mechanism is a method or model that can estimate or predict the internal temperature distribution or deviation of the entire structure based on known temperature information. The inference mechanism can be built based on physical principles, such as solving heat transfer equations through numerical simulation methods (such as finite element method, finite difference method), or based on data-driven methods, such as learning the temperature distribution rules in historical data through machine learning models. The role of the inference mechanism is to extend the limited local temperature information to the entire structure region.

[0056] The present application aims to solve the technical problem that in the sand casting of large complex structural parts, the sensor arrangement position is discrete and the number is limited, and the solidification state information of all areas cannot be directly obtained, by introducing a physical parameter-based inference mechanism, so as to accurately infer the solidification state deviation degree and spatial distribution characteristics of the overall area of the large complex structural part according to limited discrete temperature deviation data. Specifically, first, specific parameter information is obtained, including the geometric information of the large complex structural part, the thermal physical parameters of the large complex structural part and the thermal physical parameters of the sand mold. These parameters are the basis for constructing a model or mechanism for understanding and predicting the temperature field changes inside the casting, providing necessary physical constraints and inputs for subsequent inference. Based on the specific parameter information, the inference mechanism of the internal temperature field in the large complex structural part is determined. This inference mechanism utilizes the physical characteristics of the casting and the sand mold, and can estimate or predict the temperature distribution or deviation inside the entire structure according to the known local temperature information. According to the first temperature deviation data and the inference mechanism, the second temperature deviation data of other positions in the large complex structural part except the specified positions is inferred. By inputting the actual temperature deviation of the specified position into the inference mechanism as a known condition, the temperature deviation of the area not covered by the sensor can be estimated, so as to extend the temperature deviation information from the limited specified position to the entire structure. According to the first temperature deviation data and the second temperature deviation data, the solidification state deviation degree and the spatial distribution characteristics of the deviation in different areas of the large complex structural part are determined. Combining the measured temperature deviation of the specified position and the inferred temperature deviation of other positions, more comprehensive temperature deviation distribution information of the entire large complex structural part can be obtained. Based on this more comprehensive temperature deviation distribution, the deviation degree of the actual temperature of different areas relative to the target temperature can be more accurately judged, and then the deviation degree of the solidification state of these areas relative to the target state and the spatial distribution characteristics of these deviations in the entire structure can be inferred, providing more accurate basis for subsequent cooling water flow adjustment. Compared with the scheme of relying only on the temperature deviation of the specified position for evaluation, the present scheme obtains more comprehensive temperature information through the inference mechanism, significantly improves the accuracy and coverage of the overall solidification state evaluation of the large complex structural part, so that the subsequent cooling control can more accurately act on the areas that need to be adjusted, thereby more effectively regulating the overall solidification process and reducing the occurrence of casting defects.

[0057] As a specific implementation, the inference mechanism of the internal temperature field can be a transient heat transfer numerical model based on finite element method. In this case, obtaining the specific parameter information can include: obtaining the geometric information of the large complex structural part by reading its CAD model file; obtaining the thermal conductivity, specific heat capacity, density and solidification phase change related physical parameters (such as solidification temperature interval, phase change latent heat) of the casting material (for example, a certain specific brand of alloy) at different temperatures by consulting the material manual or conducting experimental measurement; obtaining the thermal physical parameters such as thermal conductivity, specific heat capacity and density of the sand mold by consulting the technical specification book of the sand mold material or conducting experiments. Based on these parameters, a three-dimensional finite element grid model of the large complex structural part and its surrounding sand mold can be constructed, and mathematical equations describing the transient heat transfer of the casting process can be established. When inferring the second temperature deviation data according to the first temperature deviation data and the inference mechanism, the real-time temperature data (or the deviation from the target temperature) of the specified position can be used as the boundary condition or internal constraint of the finite element model. For example, if the measured temperature of a certain specified position is too high, an additional heat flow can be applied to the corresponding position in the model or the local heat transfer coefficient can be adjusted, so that the calculation result of the model is consistent with the measured temperature. Then, run the finite element simulation to calculate the temperature distribution of other positions in the model that are not arranged with sensors. Comparing these calculated temperatures with the target temperature at the corresponding time, the second temperature deviation data can be obtained. Finally, when determining the deviation degree of the solidification state and the spatial distribution characteristics of the deviation according to the first temperature deviation data and the second temperature deviation data, the measured first temperature deviation data and the inferred second temperature deviation data can be integrated to form a temperature deviation field covering the entire large complex structural part. Combined with the solidification temperature interval and other physical parameters of the casting material, the deviation of the actual temperature of different regions from the solidification temperature interval can be determined according to the temperature deviation field, for example, which regions have not started to solidify due to too high temperature, which regions are experiencing solidification, and which regions have completely solidified and have low temperature. At the same time, the distribution of these different solidification state regions in the three-dimensional space of the large complex structural part can be visualized.

[0058] By acquiring specific physical parameters of the large complex structural part and the sand mold, and determining the inference mechanism of the internal temperature field based on these parameters, the scheme can use limited real-time temperature deviation data at specified positions to infer temperature deviation data at positions without sensors. Combining the measured temperature deviation at specified positions with the inferred temperature deviation at other positions can obtain more comprehensive and detailed temperature deviation distribution information covering the entire large complex structural part. Based on this more comprehensive temperature deviation distribution, the degree of deviation of the solidification state of different regions in the large complex structural part and the distribution characteristics of these deviations in space can be more accurately judged. This overcomes the limitations of relying only on discrete sensor data for evaluation, improves the accuracy and completeness of the perception of the overall solidification process state of the large complex structural part, and provides a more reliable and comprehensive basis for subsequent cooling water flow adjustment, which helps to achieve fine regulation of the solidification process of the large complex structural part, thereby improving the quality of the casting and reducing defects.

[0059] In some embodiments, the step of inferring the second temperature deviation data at positions other than the specified positions in the large complex structural part according to the first temperature deviation data and the inference mechanism includes:

[0060] Acquiring physical parameters related to the solidification phase change process of the material of the large complex structural part;

[0061] According to the first temperature deviation data and the inference mechanism, the second temperature deviation data is inferred;

[0062] According to the second temperature deviation data and the physical parameters related to the solidification phase change process, identify the regions in the large complex structural part that are experiencing or will experience the solidification phase change as target regions;

[0063] For the target region, based on the physical parameters related to the solidification phase change process, the corresponding second temperature deviation data is corrected, and the corrected second temperature deviation data is taken as the final second temperature deviation data of the target region.

[0064] The physical parameters related to the solidification phase change process refer to parameters that describe the thermodynamic and thermophysical properties of the material during the transition from liquid to solid state, such as the solidification temperature range of the material, latent heat, the relationship between specific heat capacity and temperature, the relationship between thermal conductivity and temperature, and density, etc. These parameters are key information for understanding and simulating the energy release and transfer in the material solidification process. The inference mechanism refers to an algorithm or model that uses limited known data to predict unknown data based on known physical laws or data models. In the context of casting, this mechanism can be a numerical simulation model based on heat transfer principles, or a prediction model trained through machine learning methods, with the goal of predicting temperature deviations at other locations based on temperature deviation data at specified locations. Identifying areas in large complex structural parts that are undergoing or will undergo solidification phase change refers to determining which areas inside the casting have temperatures at or near the material's solidification temperature range based on the inferred temperature information and the material's phase change characteristics, thereby determining which areas are likely to be undergoing or will undergo phase change. Correcting the corresponding second temperature deviation data refers to adjusting the preliminary inferred temperature deviation data using the physical parameters related to the solidification phase change for the identified phase change areas to more accurately reflect the actual temperature state of these areas during the phase change process.

[0065] The technical problem to be solved by the scheme is that in the sand casting of large complex structural parts, the metal solidification phase change process is accompanied by latent heat release, which affects the local temperature field change, and the temperature deviation of the unmeasured area based on the inference mechanism may have errors in the phase change area, thereby improving the accuracy of the inference result, especially the accuracy of the solidification front position and state judgment. The scheme realizes accurate inference of temperature deviation data in unmeasured areas through a series of steps. First, the physical parameters related to the solidification phase change process of the large complex structural part material are obtained. These parameters, such as latent heat, phase change temperature interval, specific heat change with temperature, etc., are key information for describing the thermal behavior of the material during the solidification process. These parameters are obtained in order to accurately identify the phase change area and correct the inferred data in the subsequent steps. Then, according to the first temperature deviation data measured at the specified position and the preset inference mechanism, the second temperature deviation data of other positions in the large complex structural part except the specified position is inferred. This step follows the basic inference idea and obtains the preliminary temperature deviation distribution of the entire casting. Then, using the second temperature deviation data inferred preliminarily and the previously obtained physical parameters related to the solidification phase change process, the areas in the large complex structural part that are currently experiencing or will experience solidification phase change are identified, and these areas are determined as target areas. This is because the phase change area is the core of the solidification process, and its temperature state has the greatest impact on the final casting quality, and it is also the area where temperature inference is most prone to error. By combining the inferred temperature and the phase change characteristics of the material, these key areas can be accurately circled. Finally, for the identified target areas, based on the physical parameters related to the solidification phase change process, the second temperature deviation data inferred preliminarily is corrected, and the corrected data is taken as the final second temperature deviation data of the target area. This correction step is the core contribution of the scheme. Since the thermal behavior of the phase change area is significantly affected by factors such as latent heat release, a simple inference mechanism may not be able to accurately simulate it. By using the phase change physical parameters to correct the inference data of these areas, such as considering the influence of latent heat on the temperature change rate, the accuracy of the inferred temperature deviation in these key areas can be significantly improved, and the solidification state can be more accurately reflected, thereby providing more accurate input for subsequent solidification state deviation degree judgment and cooling water flow adjustment. By further correcting the key areas based on the preliminary inference and combining the solidification phase change physical characteristics of the material, the scheme can more accurately capture the temperature field change near the solidification front, overcome the limitations of relying only on the general inference mechanism, and make the grasp of the overall temperature deviation distribution of the casting more fine and reliable.

[0066] In one embodiment, the second temperature deviation data of other positions in the large complex structural component except the specified position can be inferred according to the first temperature deviation data and the inference mechanism in the following manner. First, the physical parameters related to the solidification phase change process of the material of the large complex structural component are obtained, for example, the standard physical parameter manual of the alloy material can be consulted, or the solidification temperature interval, latent heat and other parameters of the material can be measured by experimental means such as differential scanning calorimetry (DSC). Then, according to the first temperature deviation data measured at the specified position and the preset inference mechanism, for example, the inference mechanism can be a transient heat transfer model based on the finite element method, the measured temperature deviation is used as the boundary condition or model calibration input, and the model is run to calculate the preliminary second temperature deviation data of other positions in the large complex structural component. Then, according to the preliminary inferred second temperature deviation data and the previously obtained physical parameters related to the solidification phase change process, the regions that are experiencing or will experience the solidification phase change are identified. For example, according to the preliminary inferred temperature value, it can be judged which regions have temperatures within the solidification temperature interval of the material, or by analyzing the rate of change of the inferred temperature with time, regions with a significantly slowed temperature change rate can be identified, which are likely to be releasing latent heat and in the phase change process. These identified regions are determined as target regions. Finally, for these target regions, the preliminary inferred second temperature deviation data is corrected based on the physical parameters related to the solidification phase change process. For example, if the preliminary inferred temperature is within the phase change interval but the temperature change rate is too fast, the temperature deviation value of this region can be adjusted according to the latent heat and specific heat capacity information of the material, so that it is more consistent with the temperature change rule in the actual phase change process, thereby obtaining the corrected second temperature deviation data as the final temperature deviation inference result of these target regions.

[0067] Through the above technical solution, the second temperature deviation data of other positions in the large complex structural component except the specified position can be inferred according to the first temperature deviation data and the inference mechanism, and targeted correction can be made for the solidification phase change region. This solves the problem that the release of latent heat affects the accuracy of local temperature field inference during metal solidification. By obtaining the physical parameters related to the solidification phase change and using these parameters to identify the phase change region and correct the inferred data, the accuracy of temperature deviation inference in the key phase change region is improved. This makes the grasp of the overall temperature field of the casting more accurate, especially the judgment of the position and state of the solidification front more reliable, providing more accurate basic data for subsequent solidification state judgment and cooling water flow adjustment based on temperature deviation, thereby helping to achieve more refined solidification process control.

[0068] In some embodiments, the step of identifying the regions in the large complex structural component that are experiencing the solidification phase change as target regions according to the second temperature deviation data and the physical parameters related to the solidification phase change process comprises:

[0069] determining an inferred actual temperature of other positions according to the second temperature deviation data and the second target temperature data corresponding to the time point of the second temperature deviation data;

[0070] identifying a phase change region in which the inferred actual temperature is within a phase change temperature interval according to the inferred actual temperature and physical parameters related to the solidification phase change process;

[0071] obtaining the inferred actual temperature of the phase change region at continuous time points and constructing a temperature sequence;

[0072] calculating a change rate of the inferred actual temperature of the phase change region with time according to the temperature sequence;

[0073] determining a phase change region undergoing the solidification phase change as a target region according to the inferred actual temperature of the phase change region, the change rate of the inferred actual temperature with time, and the physical parameters related to the solidification phase change process.

[0074] The second temperature deviation data refers to an estimated value of the difference between the temperature and the target temperature of other positions in the large complex structural part obtained through an inference mechanism, except for the specified positions. The second target temperature data refers to an expected temperature value preset or calculated for other positions in the large complex structural part, except for the specified positions, at the time corresponding to the second temperature deviation data. The inferred actual temperature of other positions refers to an estimated value of the actual temperature of positions in the large complex structural part where no temperature sensor is arranged, which is calculated according to the inferred temperature deviation and the target temperature. The physical parameters related to the solidification phase change process refer to parameters describing the thermal physical behavior of a specific metal material in the solidification process, such as the characteristics of the phase change temperature interval, latent heat size, specific heat capacity, thermal conductivity coefficient, etc. of the material varying with temperature. The phase change temperature interval refers to the temperature range from the start of solidification of the liquid state of the metal material to the end of complete solidification. The phase change region refers to a region preliminarily judged to be within the phase change temperature interval according to the inferred actual temperature. The temperature sequence refers to a collection of inferred actual temperature values of a specific region at continuous time points. The change rate of the inferred actual temperature with time refers to the speed of the change of the inferred actual temperature value with time in the temperature sequence, which can be represented by the derivative or difference of the temperature with respect to time.

[0075] The method provided by the application realizes accurate identification of the region in the large and complex structure that is experiencing solidification phase change by combining static temperature information and dynamic temperature change information. First, the inferred actual temperature of the position where no sensor is arranged is calculated according to the inferred temperature deviation and the target temperature, which provides basic data for subsequent judgment. Then, based on the inferred actual temperature and the physical parameters of the solidification phase change of the material, the region whose temperature is in the phase change temperature interval is preliminarily screened out, and these regions are potential phase change regions. In order to more accurately judge whether these regions are “experiencing” phase change, the method further obtains the inferred actual temperature of these regions at continuous time points to form a temperature sequence. In the metal solidification process, the release of latent heat will cause the temperature drop rate to slow down significantly, and even a temperature platform will appear, which is an important feature of the region that is experiencing phase change. By calculating the change rate of the temperature sequence with time, this dynamic feature can be captured. Finally, by comprehensively considering the current inferred actual temperature of the region (whether it is still in the phase change interval), the change rate of the inferred actual temperature of the region with time (whether it shows the temperature change trend characteristic of phase change) and the physical parameters related to the solidification phase change process (which provide the basis for judgment), it can be more accurately determined which regions are currently undergoing solid-liquid phase change, and these regions are determined as the target regions that need to be focused on and the temperature deviation needs to be corrected. This judgment method combining static temperature and dynamic rate can effectively distinguish the regions before, during and after phase change, and overcome the limitations of relying only on temperature threshold judgment. The region identified as being in the process of phase change is the target region, and the inferred temperature deviation corresponding to the target region will be corrected. The corrected deviation data will be used to determine the degree and spatial distribution characteristics of the solidification state deviation, and then affect the calculation and adjustment of the cooling water flow. By focusing on the key phase change regions of the cooling control and correcting the deviation based on more accurate temperature information, the local solidification process can be more effectively regulated and controlled, and the solidification front can be guided to advance along the expected path, thereby improving the solidification quality of the entire casting.

[0076] The identification method of the present application will be further described below in combination with a specific embodiment. It is assumed that at a certain time, the second temperature deviation data of the positions in the large and complex structural member where no sensors are arranged and the second target temperature data corresponding to the time have been obtained. First, for each grid point in the structural member, the inferred actual temperature of the grid point is calculated according to its second temperature deviation data and second target temperature data. Then, the solidification phase change temperature interval of the metal material is determined by referring to the physical parameter manual of the metal material. All grid points whose inferred actual temperatures fall within the phase change temperature interval are identified by traversing all grid points, and these grid points constitute the preliminary phase change region. Next, for each grid point in the preliminary phase change region, the inferred actual temperature values of the grid point at a plurality of consecutive time steps in the past are obtained to construct a temperature sequence of the grid point. According to the temperature sequence, the change rate of the inferred actual temperature of the grid point at the current time with respect to time is calculated, for example, the finite difference method can be used to calculate the temperature difference between the current time and the previous time divided by the time step. Finally, for each grid point in the phase change region, whether its current inferred actual temperature is still within the phase change temperature interval, whether the change rate of its inferred actual temperature with respect to time is less than a certain threshold value (indicating that the temperature drop slows down or a platform appears), and whether the grid point is experiencing solidification phase change are determined in combination with the physical parameters such as the latent heat release characteristics of the material. The set of all grid points determined to be experiencing solidification phase change is the target region.

[0077] By the above method, the present application can more accurately identify the region in the large and complex structural member that is experiencing solidification phase change, overcoming the technical problem that it is difficult to accurately identify the regions in different phase change stages based on only the temperature threshold value. This accurate identification improves the accuracy of the judgment of the actual solidification front position, provides a more reliable basis for subsequent targeted correction of the inferred temperature deviation and adjustment of the cooling water flow rate, and helps to achieve fine control of the solidification process of the large and complex structural member.

[0078] In some embodiments, according to the solidification state deviation degree and the spatial deviation distribution characteristics, based on the cooling influence characteristics of the plurality of cooling circuits on different regions of the large and complex structural member, the step of calculating the cooling water flow rate adjustment data of the plurality of cooling circuits comprises:

[0079] obtaining the initial cooling influence characteristics of the plurality of cooling circuits on different regions of the large and complex structural member;

[0080] selecting one or more of the plurality of cooling circuits according to a preset disturbance strategy and applying a preset cooling water flow rate disturbance; the disturbance strategy contains disturbance parameters, and the disturbance parameters include the set of cooling circuits to which the disturbance is applied, the disturbance amplitude of each cooling circuit, and the duration of the disturbance;

[0081] Monitoring the real-time temperature response variation of multiple specified locations of the large complex structure after applying the cooling water flow disturbance;

[0082] According to the applied cooling water flow disturbance and the monitored real-time temperature response variation, evaluating and updating the cooling influence characteristics of the selected cooling circuits on different regions of the large complex structure;

[0083] According to the solidification state deviation degree, spatial deviation distribution characteristics, and updated cooling influence characteristics, calculating the cooling water flow adjustment data of multiple cooling circuits.

[0084] The initial cooling influence characteristics refer to the preliminary or estimated description of the influence degree and range of multiple cooling circuits on the temperature or solidification state of different regions of the large complex structure at the beginning of the solidification process or at a certain time, which can be obtained by numerical simulation results, historical data analysis, or preliminary experimental calibration. The preset disturbance strategy refers to the planned scheme for applying changes to the cooling water flow in order to stimulate system response and identify or update the cooling influence characteristics, which can take the form of step disturbance, pulse disturbance, pseudo-random binary sequence disturbance, or sinusoidal disturbance. The disturbance parameters refer to the set values used to implement the disturbance strategy, which can include the number or set of cooling circuits to be disturbed, the flow variation amplitude of each disturbed cooling circuit, and the time length of the disturbance. The real-time temperature response variation refers to the actual variation of the temperature at multiple specified locations of the large complex structure over time during or after the application of the cooling water flow disturbance, which can be obtained by continuous or periodic measurement through temperature sensors arranged at the specified locations. Evaluating and updating the cooling influence characteristics of the selected cooling circuits on different regions of the large complex structure refers to the process of correcting or optimizing the mathematical model or parameters describing the influence of the cooling circuits according to the applied cooling water flow disturbance and the monitored real-time temperature response variation, using system identification or parameter estimation methods, which can be implemented using algorithms such as least squares, recursive least squares, Kalman filtering, or neural networks.

[0085] The working principle of the present scheme is that a preliminary model of the cooling circuit influence, i.e. the initial cooling influence characteristic, is first obtained as the basis for subsequent dynamic adjustment. Then, by deliberately applying preset flow disturbances to one or more cooling circuits, the temperature response inside the large and complex structural part is actively excited. At the same time of applying the disturbances, the system monitors the temperature changes at designated locations of the large and complex structural part in real time, capturing the actual dynamic feedback of the system to these disturbances. Then, by taking the applied flow disturbances as input signals and the monitored real-time temperature response changes as output signals, the relationship between the input and output is analyzed using system identification techniques, so as to evaluate and correct the initial cooling influence characteristic model, making it more accurately reflect the actual influence of the cooling circuit on different regions of the casting at the current time. Since the cooling influence characteristic is dynamically updated based on actual measurement data, it can effectively overcome the uncertainties caused by changes in material parameters, actuator errors, changes in sand mold state, and mutual influences between regions. Finally, the solidification state deviation degree and spatial deviation distribution characteristics determined according to the temperature deviation data are combined with the more accurate cooling influence characteristic obtained through actual disturbance and monitoring update, to calculate the cooling water flow adjustment data that needs to be applied to multiple cooling circuits. This calculation based on the dynamically updated influence characteristic enables the adjustment data to more accurately guide the adjustment of the cooling water flow, thereby more effectively correcting the deviation of the solidification state. By integrating the step of dynamically updating the cooling influence characteristic into the control process based on the solidification state deviation, the present scheme can continuously adapt to various dynamic changes in the casting process, ensuring the effectiveness and robustness of the control strategy.

[0086] In one embodiment, the initial cooling influence characteristics of multiple cooling circuits on different regions of the large complex structure can be obtained by heat transfer numerical simulation of the large complex structure and its cooling pipe system to obtain the temperature field distribution and solidification process under standard cooling conditions, and based on this, a preliminary influence coefficient matrix of unit flow change of each cooling circuit on the temperature or solidification rate of the key region is calculated. According to the preset disturbance strategy, a certain cooling circuit currently in operation can be selected, and a step change in cooling water flow is applied for a period of time, for example, the flow is increased by a predetermined percentage based on the current set value. After applying the cooling water flow disturbance, real-time temperature data can be collected by multiple thermocouple sensors arranged near the key regions of the large complex structure at a high sampling frequency. According to the applied cooling water flow disturbance and the monitored real-time temperature response change, a recursive least squares algorithm can be used to estimate the dynamic model parameters of the cooling circuit affecting the monitoring points by taking the flow disturbance sequence and the temperature response sequence as input, thereby updating the cooling influence characteristics description of the cooling circuit. According to the determined solidification state deviation, the spatial deviation distribution characteristics, and the updated cooling influence characteristics, a model-based controller, such as a model predictive controller, can be used to minimize the solidification state deviation information as the control target and the updated cooling influence characteristics as the system model to calculate the cooling water flow adjustment data of multiple cooling circuits that can minimize the solidification state deviation.

[0087] The present scheme dynamically obtains and updates the cooling influence characteristics of the cooling circuit on different regions of the large complex structure during solidification, overcoming the problem of model mismatch caused by actual process dynamics when control is based on static or offline models. This makes the cooling water flow adjustment data calculated based on the solidification state deviation and the spatial deviation distribution characteristics more accurately reflect the actual required adjustment amount, thereby improving the accuracy of the cooling control and the adaptability to process uncertainties. By more accurately regulating the solidification process of the large complex structure, the advancement of the solidification front can be effectively controlled, and the occurrence of casting defects such as shrinkage and porosity can be reduced or avoided.

[0088] Please refer to Figure 2 , Figure 2 is a metal casting cooling water control device in some embodiments of the present application, applied to sand casting of large complex structures, which is integrated in the form of a computer program in a rear-end control device, comprising:

[0089] The first acquisition module 100 is configured to acquire real-time temperature data measured at a plurality of specified positions of the large complex structure.

[0090] The second acquisition module 200 is configured to acquire first target temperature data corresponding to the real-time temperature data.

[0091] The first calculation module 300 is configured to calculate first temperature deviation data according to the real-time temperature data and the first target temperature data.

[0092] The second calculation module 400 is configured to calculate cooling water flow adjustment data of a plurality of cooling circuits corresponding to a plurality of specified positions according to the first temperature deviation data.

[0093] The adjustment module 500 is configured to adjust the cooling water flow of the plurality of cooling circuits according to the cooling water flow adjustment data.

[0094] Please refer to Figure 3 , Figure 3 A structure schematic diagram of an electronic device provided by the embodiment of the present application is provided, and the present application provides an electronic device 13, which comprises a processor 1301 and a memory 1302. The processor 1301 and the memory 1302 are interconnected and communicate with each other through a communication bus 1303 and / or other forms of connection mechanism (not marked). The memory 1302 stores computer readable instructions executable by the processor 1301. When the electronic device is running, the processor 1301 executes the computer readable instructions to execute the metal casting cooling water control method in any optional implementation manner of the above-mentioned embodiments to realize the following functions: obtaining real-time temperature data measured at a plurality of specified positions of a large and complex structural part; obtaining first target temperature data corresponding to the real-time temperature data; calculating first temperature deviation data according to the real-time temperature data and the first target temperature data; calculating cooling water flow adjustment data of a plurality of cooling circuits corresponding to a plurality of specified positions according to the first temperature deviation data; and adjusting the cooling water flow of the plurality of cooling circuits according to the cooling water flow adjustment data.

[0095] The embodiment of the present application provides a computer readable storage medium, which stores a computer program. When the computer program is executed by a processor, the metal casting cooling water control method in any optional implementation manner of the above-mentioned embodiments is executed to realize the following functions: obtaining real-time temperature data measured at a plurality of specified positions of a large and complex structural part; obtaining first target temperature data corresponding to the real-time temperature data; calculating first temperature deviation data according to the real-time temperature data and the first target temperature data; calculating cooling water flow adjustment data of a plurality of cooling circuits corresponding to a plurality of specified positions according to the first temperature deviation data; and adjusting the cooling water flow of the plurality of cooling circuits according to the cooling water flow adjustment data.

[0096] The computer readable storage medium can be realized by any type of volatile or nonvolatile storage devices or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0097] In the embodiments of the present application, it should be understood that the disclosed device and method can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of the units is merely a logical function division. In actual implementation, another division manner can be used. For example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some communication interfaces, devices or units, and can be electrical, mechanical or other forms.

[0098] In addition, the units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed on a plurality of network units. According to actual needs, some or all of the units can be selected to achieve the purpose of the embodiments.

[0099] Furthermore, the functional modules in each embodiment of the present application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0100] In this paper, the relationship terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between the entities or operations.

[0101] The above merely illustrates the embodiments of the present application but should not be taken as limitations to the protection scope of the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A metal casting cooling water control method applied to sand casting of a large and complex structure, characterized by, The method comprises the following steps: obtaining real-time temperature data measured at multiple specified positions of a large complex structure; obtaining first target temperature data corresponding to the real-time temperature data; calculating first temperature deviation data according to the real-time temperature data and the first target temperature data; calculating cooling water flow adjustment data of multiple cooling circuits corresponding to the multiple specified positions according to the first temperature deviation data; adjusting the cooling water flow of the multiple cooling circuits according to the cooling water flow adjustment data; The step of calculating the cooling water flow adjustment data of the multiple cooling circuits corresponding to the multiple specified positions according to the first temperature deviation data comprises: determining the solidification state deviation degree and spatial deviation distribution characteristics of different regions in the large complex structure according to the first temperature deviation data; calculating the cooling water flow adjustment data of the multiple cooling circuits based on the cooling influence characteristics of the multiple cooling circuits on different regions in the large complex structure according to the solidification state deviation degree and the spatial deviation distribution characteristics; The step of determining the solidification state deviation degree and spatial deviation distribution characteristics of different regions in the large complex structure according to the first temperature deviation data comprises: obtaining specific parameter information; the specific parameter information includes geometric information of the large complex structure, thermal physical parameters of the large complex structure, and thermal physical parameters of the sand mold; determining an inference mechanism of the internal temperature field in the large complex structure based on the specific parameter information; inferred second temperature deviation data of other positions except the specified positions in the large complex structure according to the first temperature deviation data and the inference mechanism; determining the solidification state deviation degree and spatial deviation distribution characteristics of different regions in the large complex structure according to the first temperature deviation data and the second temperature deviation data; The step of inferring the second temperature deviation data of other positions except the specified positions in the large complex structure according to the first temperature deviation data and the inference mechanism comprises: obtaining physical parameters related to the solidification phase change process of the material of the large complex structure; inferred second temperature deviation data according to the first temperature deviation data and the inference mechanism; identifying regions in the large complex structure that are experiencing or will experience solidification phase change as target regions according to the second temperature deviation data and the physical parameters related to the solidification phase change process; for the target regions, correcting the corresponding second temperature deviation data based on the physical parameters related to the solidification phase change process, and taking the corrected second temperature deviation data as the final second temperature deviation data of the target regions; The step of identifying regions in the large complex structure that are experiencing solidification phase change as target regions according to the second temperature deviation data and the physical parameters related to the solidification phase change process comprises: determining the inferred actual temperature of other positions according to the second temperature deviation data and the second target temperature data corresponding to the moment of the second temperature deviation data; identifying a phase change region in which the inferred actual temperature is in the phase change temperature interval according to the inferred actual temperature and the physical parameters related to the solidification phase change process; obtaining the inferred actual temperature of the phase change region at consecutive time points and constructing a temperature sequence; calculating the change rate of the inferred actual temperature of the phase change region with time according to the temperature sequence; According to the inferred actual temperature of the phase change region, the rate of change of the inferred actual temperature over time, and the physical parameters related to the solidification phase change process, the phase change region that is undergoing a solidification phase change is determined and targeted as a target region.

2. The metal casting cooling water control method according to claim 1, characterized by, According to the degree of deviation of the solidification state and the spatial deviation distribution characteristics, the cooling influence characteristics of the multiple cooling circuits on different regions of the large complex structure are calculated, and the cooling water flow adjustment data of the multiple cooling circuits are calculated. Obtain the initial cooling influence characteristics of the multiple cooling circuits on different regions of the large complex structure; According to the preset disturbance strategy, one or more of the multiple cooling circuits are selected and a preset cooling water flow disturbance is applied; Monitor the real-time temperature response changes of the multiple specified positions of the large complex structure after the cooling water flow disturbance is applied; According to the applied cooling water flow disturbance and the monitored real-time temperature response changes, the cooling influence characteristics of the selected cooling circuits on different regions of the large complex structure are evaluated and updated; According to the degree of deviation of the solidification state, the spatial deviation distribution characteristics, and the updated cooling influence characteristics, the cooling water flow adjustment data of the multiple cooling circuits are calculated.

3. The metal casting cooling water control method according to claim 2, characterized by, The disturbance strategy includes disturbance parameters, including the set of cooling circuits to which the disturbance is applied, the disturbance amplitude of each cooling circuit, and the duration of the disturbance.

4. A metal casting cooling water control device using the metal casting cooling water control method according to any one of claims 1 to 3, applied to sand casting of a large and complex structure, characterized by It includes: The first acquisition module is configured to acquire real-time temperature data measured at the multiple specified positions of the large complex structure; The second acquisition module is configured to acquire first target temperature data corresponding to the real-time temperature data; The first calculation module is configured to calculate first temperature deviation data according to the real-time temperature data and the first target temperature data; The second calculation module is configured to calculate cooling water flow adjustment data of the multiple cooling circuits corresponding to the multiple specified positions according to the first temperature deviation data; The adjustment module is configured to adjust the cooling water flow of the multiple cooling circuits according to the cooling water flow adjustment data.

5. An electronic device, comprising: It includes a processor and a memory, and the memory stores computer readable instructions, when the computer readable instructions are executed by the processor, the steps in the metal casting cooling water control method of any one of claims 1-3 are run.

6. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to run the steps in the metal casting cooling water control method of any one of claims 1-3.

Images