Prediction and reconstruction of edge shape in adaptive machining of precision forged blade

Feng, Yazhou; Ren, Junxue; Liang, Yongshou

doi:10.1007/s00170-018-1771-x

Cited by 10 publications

(3 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Zhao et al [17] improved the accuracy of reconstruction by inserting knots. Feng et al [2] predicted the desired spline curves considering the deformation and thickness of the blank material while preserving the design intent. Yu et al [18] established the relationship between measured points and the velocity field of the blade's section.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

LETR: An End-to-End Detector of Reconstruction Area in Blades Adaptive Machining with Transformer

et al. 2022

Self Cite

View full text Add to dashboard Cite

In the leading/trailing edge’s adaptive machining of the near-net-shaped blade, a small portion of the theoretical part, called the reconstruction area, is retained for securing aerodynamic performance by manual work. The next work is to recognize the reconstruction area of the reconstructed leading/trailing edge’s image. To accelerate this process, an anchor-free neural network model based on Transformer was proposed, named Leading/trailing Edge Transformer (LETR). LETR extracts image features from an aspect of mixed frequency and channel domain. We also integrated LETR with the newest meta-Acon activation function. We tested our model on the self-made dataset LDEG2021 on a single GPU and got an mAP of 91.9%, which surpassed our baseline model, Deformable DETR, by 1.1%. Furthermore, we modified LETR’s convolution layer and named the new model after Ghost Leading/trailing Edge Transformer (GLETR) as a lightweight model for real-time detection. It is proved that GLETR has fewer weight parameters and converges faster than LETR with an acceptable decrease in mAP (0.1%) by test results. The proposed models provide the basis for subsequent parameter extraction work in the reconstruction area.

show abstract

Section: Related Workmentioning

confidence: 99%

“…Hence, we need to reconstruct the theoret-ical leading/trailing edge. In this case, adaptive machining [2] is imported to the machining process of near-netshaped blades. Adaptive machining technology aims to modify manufacturing data on the basis of changed conditions.…”

Section: Introductionmentioning

confidence: 99%

LETR: An End-to-End Detector of Reconstruction Area in Blades Adaptive Machining with Transformer

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…Um et al [13] applied a STEP-based numerical control (STEP0NC)-based process planning method in additive manufacturing for automating the derivation of the repair section. Feng et al [14] proposed a method to predict and reconstruct an expected profile of the edge shape in adaptive machining. Zheng et al [15] developed a hybrid method to repair damaged parts by using additive manufacturing techniques, which integrates coordinate measuring machine data collection, defective model regeneration, and decision marking for process selection for the repair.…”

Section: Additive Manufacturing Repairmentioning

confidence: 99%

A Fast Hole-Filling Method for Triangular Mesh in Additive Repair

et al. 2020

View full text Add to dashboard Cite

In the triangular meshes obtained in additive repair, it is a challenge to find one single hole-filling method to close all holes and make the filling patches assort with surrounding meshes well with low time complexity, which is mainly caused by the shape complexity and size difference of the various holes, especially in the fields of intelligent manufacturing, 3D measurement, and reverse engineering. Therefore, it is reasonable to adopt different algorithms to fill different types of holes. In this research, a fast hole-filling method for triangular mesh is proposed based on the hole size. First, a group of basic concepts is defined to make them uniform throughout the whole text, followed by the descriptions of hole detection and boundary cleaning. Second, three different algorithms are developed to fill the small-sized, middle-sized, and large-sized holes classified by hole size respectively, which can fill all the detected holes in a fast and proper manner. Finally, two experiments are carried out to verify the efficiency, robustness, and ability to recover the shape of our method. Compared to two state-of-the-art hole-filling methods in the first experiment, the quantitative evaluation results demonstrate that our proposed method is much faster than them with the ability to guarantee the regularity of most filling triangles. The second experiment proves that our method can produce satisfactory filling results by making the filling patches be compatible with surrounding meshes well.

show abstract

Analysis of machining deformation for adaptive CNC machining technology of near-net-shaped jet engine blade

Wang

Peng

et al. 2019

Int J Adv Manuf Technol

View full text Add to dashboard Cite

Prediction and reconstruction of edge shape in adaptive machining of precision forged blade

Cited by 10 publications

References 22 publications

LETR: An End-to-End Detector of Reconstruction Area in Blades Adaptive Machining with Transformer

LETR: An End-to-End Detector of Reconstruction Area in Blades Adaptive Machining with Transformer

A Fast Hole-Filling Method for Triangular Mesh in Additive Repair

Analysis of machining deformation for adaptive CNC machining technology of near-net-shaped jet engine blade

Contact Info

Product

Resources

About