CN-122021265-A - Real-time early warning method for light alloy casting cracks based on big data

CN122021265ACN 122021265 ACN122021265 ACN 122021265ACN-122021265-A

Abstract

The invention belongs to the technical field of light alloy casting, and discloses a light alloy casting crack real-time early warning method based on big data, which comprises the steps of collecting key parameters of the whole process of preheating, casting and cooling of a die in real time, including die cavity temperature, molten metal flow rate and die cavity stress change data, carrying out data preprocessing and feature extraction, the invention realizes the full-flow and multi-parameter real-time monitoring and early warning of casting cracks, and effectively improves the production quality and efficiency.

Inventors

Lan qiao
DOU YONG
MA ZHUANG
ZHANG WENHUA
ZHANG JIELIN

Assignees

凤阳爱尔思轻合金精密成型有限公司

Dates

Publication Date: 20260512
Application Date: 20260109

Claims (8)

1. The real-time early warning method for the light alloy casting cracks based on the big data is characterized by comprising the following steps: Step S1, acquiring key parameters in a casting process in real time, wherein the casting process comprises a mould preheating process, a casting process and a cooling process; Step S2, preprocessing the multi-source data acquired in the step S1, including data cleaning and data standardization, for removing abnormal data and converting different types of data into the same standard; step S3, extracting features of the processed data, and respectively extracting key early warning indexes for early warning cracks in a mould preheating process, a casting process and a cooling process; And S4, carrying out crack real-time early warning on the preheating process, the casting process and the cooling process of the die respectively based on the key early warning indexes extracted in the step S3.
2. The real-time early warning method for the light alloy casting crack based on the big data according to claim 1, wherein the working process of the step S1 comprises the following steps: In the mould preheating process, a pouring preparation stage is carried out, the mould is required to be preheated, and temperature data of each area in the mould cavity are monitored in real time; in the casting process, the method is divided into three stages of slow, fast and slow according to a casting principle, and the flow velocity data of molten metal in the three stages are respectively monitored; and in the cooling process, monitoring stress change data of a stress concentration part of the mold cavity wall in real time.
3. The real-time early warning method for the light alloy casting crack based on the big data according to claim 2, wherein the working process of the step S3 comprises the following steps: in the mould preheating process, obtaining initial temperature and final temperature of each region in a set time period, and constructing a mould preheating process early warning index mathematical model, wherein the expression is as follows: ; In the formula, And Respectively expressed in a set time period The initial temperature and the final temperature of the x-th region of the inner mold, Indicating the average rate of temperature change for each region of the mold, Indicating the average final temperature of the various regions of the mold, And Respectively, the weight coefficients are represented by the weight coefficients, The early warning index is used for the preheating process of the die.
4. The real-time early warning method for the casting cracks of the light alloy based on the big data according to claim 3, wherein the working process of the step S3 further comprises: In the casting process, obtaining time-dependent change data of the metal liquid flow rate in the current time period, and constructing a casting process early warning index mathematical model, wherein the expression is as follows: ; In the formula, For the current casting phase, i belongs to n, - Time consuming for the ith casting stage, For real-time data of the flow rate of the metal liquid in the ith casting stage with time, The flow rate of the metal liquid in the ith casting stage set for the system is time-varying standard data, For the weight coefficients corresponding to the different phases, The early warning index is used for the casting process.
5. The real-time early warning method for the light alloy casting crack based on the big data according to claim 4, wherein the working process of the step S3 further comprises: In the cooling process, stress change data of each stress concentration part of the mold cavity wall in the current time period are obtained, and a cooling process early warning index mathematical model is constructed, wherein the expression is as follows: ; In the formula, For the number of stress concentration sites, j belongs to m, For the maximum stress that occurs during the cooling process, In order to cast the tensile strength of the metal, For the rate of change of temperature in the jth zone, A j-th zone temperature change standard rate set for the system, For the weight coefficient corresponding to the jth region, The early warning index is used for the cooling process.
6. The real-time early warning method for the light alloy casting crack based on the big data according to claim 3, wherein the working process of the step S4 comprises the following steps: Respectively pre-warning indexes of the preheating process of the die Early warning index in casting process And a cooling process early warning index And comparing the detected light alloy with a threshold value set by a system, if any early warning index is larger than or equal to the corresponding threshold value, indicating that the current casting process possibly causes cracking of the light alloy, and immediately sending out early warning.
7. The real-time early warning method for the light alloy casting cracks based on the big data according to claim 6, wherein the early warning comprises an acousto-optic early warning and a message early warning, the acousto-optic alarm device is arranged in a monitoring room of a casting shop, the early warning is sent to a manager through acousto-optic light, and the message early warning is sent to the manager through a notification message.
8. The real-time early warning method for the casting cracks of the light alloy based on big data according to any one of claims 1 to 7, wherein the method further comprises a model updating step of periodically collecting new casting data, and retraining and optimizing a threshold value set by a system to adapt to the change of the casting process of the light alloy and the attenuation of the equipment performance.

Description

Real-time early warning method for light alloy casting cracks based on big data Technical Field The invention belongs to the technical field of light alloy casting, and particularly relates to a light alloy casting crack real-time early warning method based on big data. Background Light alloys (such as aluminum alloys, magnesium alloys, titanium alloys and the like) are widely applied to the fields of aerospace, automobile manufacturing, rail transit and the like due to the excellent performances of low density, high strength, corrosion resistance and the like. In the casting process of the light alloy, the casting is easy to generate crack defects due to complex casting technology and changeable working conditions (such as temperature gradient, uneven stress distribution, difference of cooling speed and the like). The existing light alloy casting crack real-time early warning method has the problems that 1, cracks are mainly found through nondestructive detection after casting is finished, early warning and intervention cannot be carried out in the production process, and waste of materials and working hours is caused, 2, the cracks are caused by multi-stage factors such as preheating, casting and cooling, and the specific links and root causes of the cracks are caused by difficulty in accurate positioning in the traditional method. Therefore, the invention provides a real-time early warning method for light alloy casting cracks based on big data. Disclosure of Invention The invention aims to provide a light alloy casting crack real-time early warning method based on big data, which solves the technical problems. The aim of the invention can be achieved by the following technical scheme: a real-time early warning method for light alloy casting cracks based on big data comprises the following steps: Step S1, acquiring key parameters in a casting process in real time, wherein the casting process comprises a mould preheating process, a casting process and a cooling process; Step S2, preprocessing the multi-source data acquired in the step S1, including data cleaning and data standardization, for removing abnormal data and converting different types of data into the same standard; step S3, extracting features of the processed data, and respectively extracting key early warning indexes for early warning cracks in a mould preheating process, a casting process and a cooling process; step S4, carrying out crack real-time early warning on the preheating process, the casting process and the cooling process of the die respectively based on the key early warning indexes extracted in the step S3 As a further description of the technical solution of the present invention, the working process of step S1 includes: In the mould preheating process, a pouring preparation stage is carried out, the mould is required to be preheated, and temperature data of each area in the mould cavity are monitored in real time; in the casting process, the method is divided into three stages of slow, fast and slow according to a casting principle, and the flow velocity data of molten metal in the three stages are respectively monitored; and in the cooling process, monitoring stress change data of a stress concentration part of the mold cavity wall in real time. As a further description of the technical solution of the present invention, the working process of step S3 includes: in the mould preheating process, obtaining initial temperature and final temperature of each region in a set time period, and constructing a mould preheating process early warning index mathematical model, wherein the expression is as follows: ; In the formula, AndRespectively expressed in a set time periodThe initial temperature and the final temperature of the x-th region of the inner mold,Indicating the average rate of temperature change for each region of the mold,Indicating the average final temperature of the various regions of the mold,AndRespectively, the weight coefficients are represented by the weight coefficients,The early warning index is used for the preheating process of the die. As a further description of the technical solution of the present invention, the working process of step S3 further includes: In the casting process, obtaining time-dependent change data of the metal liquid flow rate in the current time period, and constructing a casting process early warning index mathematical model, wherein the expression is as follows: ; In the formula, For the current casting phase, i belongs to n,-Time consuming for the ith casting stage,For real-time data of the flow rate of the metal liquid in the ith casting stage with time,The flow rate of the metal liquid in the ith casting stage set for the system is time-varying standard data,For the weight coefficients corresponding to the different phases,The early warning index is used for the casting process. As a further description of the technical solution of the present invention, the working process of step S