Shrinkage during solidification of complex structure castings based on convolutional neural network deformation prediction research

Dong, Yiwei; Guo, Xiang; Ye, Qianwen; Yan, Weiguo

doi:10.1007/s00170-021-08137-5

Cited by 9 publications

(4 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Sata [18] proposed a prediction penalty index (ppi) and compared it to the relative predictive capability of neural and multivariate regression models, and found that multiple regression was better at predictions. The CNN (convolutional neural networks) model used by Dong [19] can accurately predict the shrinkage deformation and trend of complex castings during precision casting. Yu [20] proposed a data-driven framework, which improved the yield of castings by 14.91% by optimizing the process parameters.…”

Section: Introductionmentioning

confidence: 99%

Data–Physics Fusion-Driven Defect Predictions for Titanium Alloy Casing Using Neural Network

Yu,

Ji,

Sun

et al. 2024

Materials

View full text Add to dashboard Cite

The quality of Ti alloy casing is crucial for the safe and stable operation of aero engines. However, the fluctuation of key process parameters during the investment casting process of titanium alloy casings has a significant influence on the volume and number of porosity defects, and this influence cannot be effectively suppressed at present. Therefore, this paper proposes a strategy to control the influence of process parameters on shrinkage volume and number. This study constructed multiple regression prediction models and neural network prediction models of porosity volume and number for a ZTC4 casing by simulating the gravity investment casting process. The results show that the multiple regression prediction model and neural network prediction model of shrinkage cavity total volume have an accuracy of over 99%. The accuracy of the neural network prediction model is higher than that of the multiple regression model, and the neural network model realizes the accurate prediction of shrinkage defect volume and defect number through pouring temperature, pouring time, and mold shell temperature. The sensitivity degree of casing defects to key process parameters, from high to low, is as follows: pouring temperature, pouring time, and mold temperature. Further optimizing the key process parameter window reduces the influence of process parameter fluctuation on the volume and number of porosity defects in casing castings. This study provides a reference for actual production control process parameters to reduce shrinkage cavity and loose defects.

show abstract

Section: Introductionmentioning

confidence: 99%

Data–Physics Fusion-Driven Defect Predictions for Titanium Alloy Casing Using Neural Network

Yu,

Ji,

Sun

et al. 2024

Materials

View full text Add to dashboard Cite

show abstract

“…9 Although the geometrical information of the blade castings can be acquired from the design specifications, the produced cast dimensions are smaller than those of the die cavity because of wax shrinkage and alloy directional solidification(DS). 10 The characteristics of turbine blades manufactured with DS (i.e. hollow, thin-walled, and complex) make controlling dimensional accuracy difficult.…”

Section: Introductionmentioning

confidence: 99%

Modeling and experimental study on deformation prediction of thin-walled turbine blades during investment casting process

Zhou

Wang

Cui

et al. 2023

Proceedings of the Institution of Mechanical Engineers, Part B:

View full text Add to dashboard Cite

Due to variable cross-sections and a thin-walled structure, gas turbine blades have stringent dimensional, and geometrical tolerance requirements. Single-crystal hollow blades are manufactured using the following investment casting processes: ceramic core preparation, wax injection, ceramic coating, wax removal, metal casting, and finishing. The main causes of the final casting deformation are wax pattern deformation, core deflection, and metal solidification warpage. This paper proposes a numerical simulation method to predict the deformation of the wax pattern, core deflection, and the directional solidification (DS) process of large single-crystal blades. Additionally, it investigates the displacement field and the influence of casting process parameters on dimensional accuracy. Three groups of DS process parameters were selected for experiments, and the deformation prediction was in agreement with the experimental results. The selected blade section deformation is the smallest when the pouring temperature is 1530°C and the withdrawal rate is 5 mm/min. The proposed finite element model is efficient to predict the deformation in all the investment casting processes, providing geometric guidance for the control of the dimensional accuracy of the turbine blade.

show abstract

“…The average deviations were 5.8% and 2.4%, respectively, which improved the accuracy compared to existing studies. After that, the authors [19] further predicted the shrinkage of complex castings during IC based on convolutional neural networks (CNNs) and obtained a higher precision. In contrast to the previous unpredictability, the introduction of neural networks has made it possible to clarify the coupling relationship between geometry and the shrinkage of turbine blades.…”

Section: Introductionmentioning

confidence: 99%

“…Thus, it is insufficient to characterize the overall dimensional change in turbine blades to adopt a specific cross-section or average dimensional shrinkage as a response. When studying the shrinkage of turbine blades, researchers have typically identified blade curvature, non-linear thickness [10], 2D discrete point deviation, and shrinkage [18,19] as response metrics. In this paper, while referring to the above classical response metrics, new response metrics are proposed to better characterize the shrinkage of turbine blades.…”

Section: Introductionmentioning

confidence: 99%

Experimental Study and GRNN Modeling of Shrinkage Characteristics for Wax Patterns of Gas Turbine Blades Considering the Influence of Complex Structures

et al. 2023

View full text Add to dashboard Cite

With the continuous increase in power demand in aerospace, shipping, electricity, and other industries, a series of manufacturing requirements such as high precision, complex structure, and thin wall have been put forward for gas turbines. Gas turbine blades are the key parts of the gas turbine. Their manufacturing accuracy directly affects the fuel economy of the gas turbine. Thus, how to improve the manufacturing accuracy of gas turbine blades has always been a hot research topic. In this study, we perform a quantitative study on the correlation between process parameters and the overall wax pattern shrinkage of gas turbine blades in the wax injection process. A prediction model based on a generalized regression neural network (GRNN) is developed with the newly defined cross-sectional features consisting of area, area ratio, and some discrete point deviations. In the qualitative analysis of the cross-sectional features, it is concluded that the highest accuracy of the wax pattern is obtained for the fourth group of experiments, which corresponds to a holding pressure of 18 bars, a holding time of 180 s, and an injection temperature of 62 °C. The prediction model is trained and tested based on small experimental data, resulting in an average RE of 1.5% for the area, an average RE of 0.58% for the area ratio, and a maximum MSE of less than 0.06 mm2 for discrete point deviations. Experiments show that the GRNN prediction model constructed in this study is relatively accurate, which means that the shrinkage of the remaining major investment casting procedures can also be modeled and controlled separately to obtain turbine blades with higher accuracy.

show abstract

Shrinkage during solidification of complex structure castings based on convolutional neural network deformation prediction research

Cited by 9 publications

References 19 publications

Data–Physics Fusion-Driven Defect Predictions for Titanium Alloy Casing Using Neural Network

Data–Physics Fusion-Driven Defect Predictions for Titanium Alloy Casing Using Neural Network

Modeling and experimental study on deformation prediction of thin-walled turbine blades during investment casting process

Experimental Study and GRNN Modeling of Shrinkage Characteristics for Wax Patterns of Gas Turbine Blades Considering the Influence of Complex Structures

Contact Info

Product

Resources

About