Search

CN-121979151-A - Vacuum brazing temperature field real-time prediction and control method based on digital twin

CN121979151ACN 121979151 ACN121979151 ACN 121979151ACN-121979151-A

Abstract

The invention discloses a digital twin-based vacuum brazing temperature field real-time prediction and control method, which particularly relates to the technical field of program control and is used for solving the problem of unnecessary shutdown caused by forced triggering of production interruption of a safety protection unit in the existing vacuum brazing control system under extreme working conditions; according to the method, the temperature field data and the pressure data in the furnace are acquired in real time, the extreme working condition approaching the safety threshold is dynamically identified, a weighted graph model is constructed based on the high temperature region to analyze the heat influence relation, the minimum intervention region is precisely positioned, a flexible regulation and control strategy is generated, the digital twin model is utilized to simulate the strategy execution effect in the virtual space, the safety recovery condition is intelligently evaluated through analyzing the graph signal frequency domain energy change, and finally a programmed decision is realized to execute flexible regulation and control or trigger production interruption, so that the control precision and the operation continuity are improved.

Inventors

  • CHEN JIMING

Assignees

  • 深圳市晟达真空钎焊技术有限公司

Dates

Publication Date
20260505
Application Date
20260205

Claims (10)

  1. 1. The digital twinning-based vacuum brazing temperature field real-time prediction and control method is characterized by comprising the following steps of: S1, acquiring real-time temperature field data and furnace pressure data of a vacuum brazing furnace; s2, judging whether an extreme working condition approaching a safety threshold occurs or not based on real-time temperature field data and furnace pressure data; S3, when the extreme working condition is judged to occur, constructing a weighted graph model which takes a high-temperature area as a node and takes a heat influence relation among the nodes as a weight based on real-time temperature field data; S4, based on a weighted graph model, identifying a node set which plays a key role in maintaining an abnormal temperature field structure by analyzing the topological importance of the nodes in the graph, and determining a physical area corresponding to the node set as a minimum intervention area; s5, analyzing the graph signal frequency domain energy change caused by the flexible regulation strategy to the minimum intervention area on the weighted graph model through the digital twin model; S6, judging whether the flexible regulation and control strategy meets the safety recovery condition based on the frequency domain energy change, if so, executing the flexible regulation and control strategy, and if not, triggering the production interruption of the safety protection unit.
  2. 2. The method for predicting and controlling the temperature field of the vacuum brazing based on the digital twin according to claim 1, wherein the step of obtaining the real-time temperature field data and the pressure data of the vacuum brazing furnace comprises the following steps: Based on a plurality of temperature acquisition areas divided by the internal space of the vacuum brazing furnace, acquiring temperature values from each temperature acquisition area in real time to form temperature field data; Acquiring the furnace pressure data comprises acquiring pressure values from pressure monitoring points of the vacuum brazing furnace in real time.
  3. 3. The method for predicting and controlling a vacuum brazing temperature field in real time based on digital twinning according to claim 1, wherein determining whether an extreme condition approaching a safety threshold occurs based on real-time temperature field data and furnace pressure data comprises: identifying whether a high temperature region exceeding a temperature threshold exists in the real-time temperature field data; monitoring whether the pressure data in the furnace exceeds a pressure threshold; and when the existence of the high-temperature area is detected at the same time and the pressure data in the furnace exceeds the pressure threshold value, judging that the extreme working condition approaching the safety threshold value occurs.
  4. 4. The method for predicting and controlling a vacuum brazing temperature field in real time based on digital twin according to claim 1, wherein when it is determined that an extreme condition occurs, constructing a weighted graph model based on real-time temperature field data, wherein the weighted graph model is based on a high temperature region as a node and a thermal influence relationship between nodes as a weight, comprises: When the extreme working condition is judged to occur, a temperature acquisition area with the temperature value exceeding a high-temperature threshold value is extracted from the real-time temperature field data to serve as a node; calculating a thermal influence relation weight based on the spatial distance and the temperature gradient between the nodes; The space distance is determined by the geometrical center distance of the temperature acquisition area corresponding to the nodes, and the temperature gradient is determined by the temperature change rate among the nodes; And constructing a weighted graph model by using all the nodes and the calculated heat influence relation weights.
  5. 5. The method for predicting and controlling the temperature field of the vacuum brazing based on the digital twin system according to claim 4 is characterized in that a weighted graph model is constructed by utilizing all nodes and the calculated heat influence relation weight, wherein the weighted graph model comprises the steps of taking a node set as the top point of the graph, and establishing edges among the nodes according to the heat influence relation weight so as to form a weighted graph structure, wherein the nodes correspond to high-temperature areas, and the edge weight represents the strength of the heat influence relation among the nodes.
  6. 6. The method for predicting and controlling the vacuum brazing temperature field in real time based on digital twin according to claim 1 is characterized in that a node set which plays a key role in maintaining an abnormal temperature field structure is identified by analyzing the topological importance of the nodes in the graph based on a weighted graph model, and a physical area corresponding to the node set is determined as a minimum intervention area: Calculating a topological importance index of each node in the weighted graph model, wherein the topological importance index is obtained by weighted combination of node degree centrality and feature vector centrality; Selecting nodes with topology importance indexes exceeding a preset importance threshold to form a key node set; mapping the key node set back to the physical space of the vacuum brazing furnace, and determining the corresponding temperature acquisition area as the minimum intervention area; Based on the thermal load distribution characteristics and thermal influence relation weights of the minimum intervention region, a flexible regulation strategy comprising a power regulation amplitude and an action time sequence is generated.
  7. 7. The method for predicting and controlling the temperature field of the vacuum brazing based on the digital twin system according to claim 6, wherein mapping the set of key nodes back to the physical space of the vacuum brazing furnace and determining the corresponding temperature acquisition area as the minimum intervention area comprises positioning the temperature acquisition area in the physical space through node identification according to the corresponding relation between the key nodes and the temperature acquisition area and defining the set of the temperature acquisition area as the minimum intervention area.
  8. 8. The method for predicting and controlling the temperature field of the vacuum brazing based on the digital twin according to claim 1, wherein analyzing the graph signal frequency domain energy change caused by the flexible regulation strategy to the minimum intervention region on the weighted graph model through the digital twin model comprises the following steps: defining the temperature field distribution difference of the minimum intervention area and adjacent nodes thereof before and after the flexible regulation strategy is applied as a graph signal; carrying out graph Fourier transform on the graph signals based on the Laplace matrix of the weighted graph model to obtain corresponding frequency spectrum distribution; extracting high-frequency components from the spectrum distribution and calculating energy values thereof; And comparing the energy values of the high-frequency components before and after the flexible regulation strategy is applied to obtain the attenuation rate of the high-frequency energy as the frequency domain energy change of the image signal.
  9. 9. The method for predicting and controlling the temperature field of the vacuum brazing based on the digital twin system according to claim 8 is characterized in that the step of performing graph Fourier transform on graph signals based on a Laplacian matrix of a weighted graph model to obtain corresponding frequency spectrum distribution comprises the steps of calculating the Laplacian matrix of the weighted graph model and then applying graph Fourier transform on the graph signals to obtain the frequency spectrum distribution, wherein the graph signals represent temperature field distribution differences, and the frequency spectrum distribution comprises frequency domain component information.
  10. 10. The method for predicting and controlling the temperature field of the digital twin-based vacuum brazing according to claim 1, wherein the method for predicting and controlling the temperature field of the digital twin-based vacuum brazing is characterized by judging whether the flexible regulation and control strategy meets the safety recovery condition based on the frequency domain energy change, executing the flexible regulation and control strategy if the flexible regulation and control strategy meets the safety recovery condition, and triggering the production interruption of the safety protection unit if the flexible regulation and control strategy does not meet the safety recovery condition, and comprises the following steps: comparing the high-frequency energy attenuation rate with a preset safety recovery threshold value; When the attenuation rate of the high-frequency energy is larger than or equal to the safety recovery threshold value, judging that the flexible regulation strategy meets the safety recovery condition and executing a corresponding strategy; When the high-frequency energy attenuation rate is smaller than the safety restoration threshold value, the safety restoration condition is judged not to be met and the production interruption of the safety protection unit is triggered.

Description

Vacuum brazing temperature field real-time prediction and control method based on digital twin Technical Field The invention relates to the technical field of program control, in particular to a digital twinning-based real-time prediction and control method for a vacuum brazing temperature field. Background Vacuum brazing is a core process for manufacturing high-end equipment key components such as an aerospace engine, a precise instrument and the like, the process quality directly determines the service performance and reliability of a component, and the uniformity and stability of a temperature field are primary factors influencing the brazing quality; in the prior art, a digital twin system and a bottom execution mechanism, such as a heater and a vacuum system, are integrated to form a complete program control system practice, and the system executes a preset temperature control program according to prediction data output by a digital twin model. However, when the integrated control system faces extreme working conditions of pressure sudden rise in a furnace, over-limit of temperature of a region and the like approaching a safety threshold, the internal operation logic of the integrated control system is contradicted, in order to ensure absolute safety, a safety protection unit independently arranged in the system can follow the inherent design of the integrated control system and forcedly trigger production interruption, but the formalized protection mechanism fails to consider flexible regulation and control judgment which can be possibly made by a digital twin system based on the global perception and prediction capability of the digital twin system or can avoid shutdown, and the decision conflict between the safety logic and the control intelligence leads to unnecessary interruption of the production process due to recoverable transient disturbance, thus not only causing product rejection and energy waste, but also restricting the full play of continuous and stable operation efficiency of the intelligent manufacturing system. Disclosure of Invention Aiming at the technical problems existing in the prior art, the invention provides a digital twin-based vacuum brazing temperature field real-time prediction and control method. The technical scheme for solving the technical problems is as follows: The digital twinning-based vacuum brazing temperature field real-time prediction and control method comprises the following steps: S1, acquiring real-time temperature field data and furnace pressure data of a vacuum brazing furnace; s2, judging whether an extreme working condition approaching a safety threshold occurs or not based on real-time temperature field data and furnace pressure data; S3, when the extreme working condition is judged to occur, constructing a weighted graph model which takes a high-temperature area as a node and takes a heat influence relation among the nodes as a weight based on real-time temperature field data; S4, based on a weighted graph model, identifying a node set which plays a key role in maintaining an abnormal temperature field structure by analyzing the topological importance of the nodes in the graph, and determining a physical area corresponding to the node set as a minimum intervention area; s5, analyzing the graph signal frequency domain energy change caused by the flexible regulation strategy to the minimum intervention area on the weighted graph model through the digital twin model; S6, judging whether the flexible regulation and control strategy meets the safety recovery condition based on the frequency domain energy change, if so, executing the flexible regulation and control strategy, and if not, triggering the production interruption of the safety protection unit. Further, acquiring real-time temperature field data and furnace pressure data of the vacuum brazing furnace, including: Based on a plurality of temperature acquisition areas divided by the internal space of the vacuum brazing furnace, acquiring temperature values from each temperature acquisition area in real time to form temperature field data; Acquiring the furnace pressure data comprises acquiring pressure values from pressure monitoring points of the vacuum brazing furnace in real time. Further, based on the real-time temperature field data and the furnace pressure data, judging whether an extreme working condition approaching a safety threshold occurs or not, including: identifying whether a high temperature region exceeding a temperature threshold exists in the real-time temperature field data; monitoring whether the pressure data in the furnace exceeds a pressure threshold; and when the existence of the high-temperature area is detected at the same time and the pressure data in the furnace exceeds the pressure threshold value, judging that the extreme working condition approaching the safety threshold value occurs. Further, when it is determined that an extreme working condition occurs, constructing