4.5 Article

Image Morphology-Based Path Generation for High-Speed Pocketing

Publisher

ASME
DOI: 10.1115/1.4046349

Keywords

pocket milling; contour-parallel tool path; process constraint; morphological operation; CAD/CAM/CAE; machining processes

Funding

  1. National Natural Science Foundation of China [51805260]
  2. China Aerospace Science and Technology Corporation [U1537209]
  3. National Natural Science Foundation of China

Ask authors/readers for more resources

Pocket milling has long been a popular means for machining pocket features in structural parts and skins in the aviation industry. Recent advanced milling technologies pose new challenges for pocket milling path which existing contour-parallel path generation schemes cannot overcome. For high-speed machining, pocket milling path is desired to be smooth and with no tool retractions during the process, while the path stepover should be kept within a prescribed range to achieve relatively constant cutting load. These geometric constraints are also vital in the application of aircraft skin mirror milling in order to guarantee a correct and consistent thickness signal reception for real-time adjustment of the process. Traditional path optimization based on local modification can only meet a few of these constraints while others are being violated. Therefore, we propose a novel contour-parallel path generation scheme that respects all these process constraints by utilizing the idea of image morphology. The two-step scheme first generates an initial path by propagating from the rectified medial curve of the pocket shape. The initial path is then treated as a binary image being iteratively deformed and projected back into the pocket region via quadratic optimization. Experimental results show that our developed scheme can generate a smooth, tool retraction free and stepover-guaranteed path for various shapes of pocket.

Authors

I am an author on this paper
Click your name to claim this paper and add it to your profile.

Reviews

Primary Rating

4.5
Not enough ratings

Secondary Ratings

Novelty
-
Significance
-
Scientific rigor
-
Rate this paper

Recommended

Article Materials Science, Composites

Microwave heating and curing of metal-like CFRP laminates through ultrathin and flexible resonance structures

Jing Zhou, Yingguang Li, Zexin Zhu, Eyan Xu, Shengping Li, Shaochun Sui

Summary: For the first time, a method has been proposed to make highly reflective CFRP laminates perfectly absorptive by introducing ultra-thin and flexible metallic resonance structures, leading to rapid energy-efficient heating. Experimental results show that the cured CFRP laminates using this method exhibit comparable or even higher mechanical properties than autoclave processed counterparts.

COMPOSITES SCIENCE AND TECHNOLOGY (2022)

Article Automation & Control Systems

A Meta-Invariant Feature Space Method for Accurate Tool Wear Prediction Under Cross Conditions

Changqing Liu, Yingguang Li, Jingjing Li, Jiaqi Hua

Summary: This article proposes a meta-invariant feature space (MIFS) learning method for accurate tool wear prediction under cross conditions with large variations, by learning the nature law of data under different conditions through meta-learning.

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS (2022)

Article Engineering, Manufacturing

A seven-question based critical thinking framework for cultivating innovation talents in engineering research and its implementation perspectives

Yingguang Li, Changqing Liu, Ke Xu, Xiaozhong Hao, Shaochun Sui

Summary: The ability of research innovation is crucial in the rapidly changing era. This paper introduces a critical thinking framework based on seven questions, which helps engineering students to cultivate innovative thinking and develop their own ideas.

PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART B-JOURNAL OF ENGINEERING MANUFACTURE (2022)

Article Computer Science, Artificial Intelligence

Federated learning-based collaborative manufacturing for complex parts

Tianchi Deng, Yingguang Li, Xu Liu, Lihui Wang

Summary: This research aims to achieve manufacturing data sharing based on federated learning, utilizing scattered data for machine learning while protecting data privacy. An enterprise-oriented framework is proposed to find FL participants with similar data resources, and an FL model is developed for machining parameter planning in aircraft structural parts.

JOURNAL OF INTELLIGENT MANUFACTURING (2023)

Article Materials Science, Composites

Development of Wireless Self-heating Tooling for Polymer Composites Using Microwave Technology

Wenzheng Xue, Yingguang Li, Jing Zhou, Tao Yang, Xiaozhong Hao, Youyi Wen

Summary: This paper presents the development of a wireless self-heating tooling with good durability and low thermal mass using microwave technology. By employing electromagnetic resonators, efficient and rapid microwave heating of the metallic panel was achieved. Experimental results showed that the composite laminates cured by the self-heating tooling exhibited comparable quality and performance, while reducing energy consumption by 81.5%.

APPLIED COMPOSITE MATERIALS (2023)

Article Chemistry, Physical

Microwave heating of carbon materials for on-demand thermal patterning via tunable electromagnetic resonators

Di Li, Jing Zhou, Yingguang Li, Wenzheng Xue, Zexin Zhu, Youyi Wen

Summary: Recently, the interest in thermal manipulation in carbon materials using microwave heating has increased. Microwave heating has advantages such as non-contact heating, fast temperature response, and low energy consumption. However, the lack of effective control methods on electromagnetic properties has made it challenging to achieve real-time thermal manipulation. In this study, we propose a solution by using tunable electromagnetic resonators, allowing pixel-controlled microwave heating in carbon materials. The experimental results show that the microwave absorbance and heating rate can be tuned, suggesting potential applications in customized materials processing, thermal display, deicing, and defrosting.

CARBON (2023)

Article Engineering, Industrial

A step-wise numerical thermal control method for advanced composite curing process using digital image based programming

Yingguang Li, Ke Xu, Shixin Wang, James Gao, Paul Maropoulos

Summary: This paper introduces a new thermal control method using digital image based programming to accurately control temperature distribution in advanced heat treatment processes. The method efficiently estimates required heat sources and controls temperature distribution in a step-wise numerical manner. Simulation and real heating tests validate the method for microwave curing of composites, showing excellent temperature uniformity and consistency compared to existing technologies.

CIRP ANNALS-MANUFACTURING TECHNOLOGY (2023)

Article Computer Science, Interdisciplinary Applications

Sparse identification for ball-screw drives considering position-dependent dynamics and nonlinear friction

Xu Liu, Yingguang Li, Yinghao Cheng, Yu Cai

Summary: Establishing accurate dynamic models for ball-screw drives is crucial for improving motion control precision. However, due to nonlinear factors such as position-dependent dynamics and friction disturbance, accurately modeling these drives is challenging. To overcome this, a sparse identification method is proposed, representing the drives as discrete-time linear parameter-varying systems and using dictionary function libraries. By constructing the system model and implementing stepwise sparse regression, an accurate and linearizable dynamic model can be identified.

ROBOTICS AND COMPUTER-INTEGRATED MANUFACTURING (2023)

Article Computer Science, Interdisciplinary Applications

Multiple source partial knowledge transfer for manufacturing system modelling

Xu Liu, Yingguang Li, Lu Chen, Gengxiang Chen, Boya Zhao

Summary: This paper proposes a method called Multiple Source Partial Knowledge Transfer (MSPKT) to address the global shift and local discrepancy problems in multi-source learning. It introduces the TSK fuzzy system as the basic learner to represent partial knowledge effectively. A transferability measurement of partial knowledge is designed to support transfer learning with multiple source domains. The effectiveness of the proposed method is validated using a synthetic dataset and two manufacturing system datasets.

ROBOTICS AND COMPUTER-INTEGRATED MANUFACTURING (2023)

Article Mechanics

A novel physics-informed neural operator for thermochemical curing analysis of carbon-fibre-reinforced thermosetting composites

Qinglu Meng, Yingguang Li, Xu Liu, Gengxiang Chen, Xiaozhong Hao

Summary: This paper proposes a novel physics informed neural operator (PINO) framework that can solve parametric coupled PDEs unsupervised and accelerate the training process significantly by enforcing global constraints on the field outputs. Experiments demonstrate the notable superiority of the proposed method under both deterministic and parametric settings.

COMPOSITE STRUCTURES (2023)

Article Computer Science, Artificial Intelligence

Physics-guided high-value data sampling method for predicting milling stability with limited experimental data

Lu Chen, Yingguang Li, Gengxiang Chen, Xu Liu, Changqing Liu

Summary: This paper proposes a Physics-Guided High-Value (PGHV) data sampling method to reduce the required experiments for data-driven stability prediction. The optimal experimental parameter set is determined by maximizing the dataset value, and the experimental labelled dataset is constructed by performing cutting experiments under the sampled experimental parameters. The stability prediction model can then be obtained by the data-driven modelling method with the experimental labelled dataset. Experimental verification shows that the proposed method can reduce the number of experiments by more than 60% compared to the existing sampling methods.

JOURNAL OF INTELLIGENT MANUFACTURING (2023)

Article Engineering, Industrial

Thermally controlled shape programming via image-based optimization towards distortion-reduced composite curing

Ke Xu, Yingguang Li, Guanguan Cao, Shuting Liu

Summary: This paper proposes an image-based optimization scheme to control the temperature field in thermosetting composite curing process. A grayscale image is generated to encode a nominal temperature field, and an adaptive thresholding algorithm is developed to regularize the temperature field, reducing cure-induced distortion. Experimental results show a noticeable reduction in distortion distribution, with a decrease of 25-50% in average distortion using the optimized temperature field.

JOURNAL OF MANUFACTURING SYSTEMS (2023)

Article Engineering, Industrial

Physics-guided neural operator for data-driven composites manufacturing process modelling

Gengxiang Chen, Yingguang Li, Xu Liu, Charyar Mehdi-Souzani, Qinglu Meng, Jing Zhou, Xiaozhong Hao

Summary: This paper proposes a physics-guided neural operator to directly predict the high-dimensional temperature history from the given cure cycle. By integrating domain knowledge into a time-resolution independent parameterised neural network, the mapping between cure cycles to temperature histories can be learned using a limited number of labelled data. Detailed experiments show that the proposed model can accurately predict the temperature histories and provide better process optimisation results.

JOURNAL OF MANUFACTURING SYSTEMS (2023)

Article Engineering, Manufacturing

Non-contact and full-field online monitoring of curing temperature during the in-situ heating process based on deep learning

Qiang-Qiang Liu, Shu-Ting Liu, Ying-Guang Li, Xu Liu, Xiao-Zhong Hao

Summary: This paper proposes a non-contact, full-field monitoring method based on deep learning to predict the internal temperature field of composite parts in real time. It achieves high accuracy and feasibility.

ADVANCES IN MANUFACTURING (2023)

Article Computer Science, Artificial Intelligence

Physics-Informed Neural Networks With Weighted Losses by Uncertainty Evaluation for Accurate and Stable Prediction of Manufacturing Systems

Jiaqi Hua, Yingguang Li, Changqing Liu, Peng Wan, Xu Liu

Summary: This article proposes a kind of PINN with weighted losses (PNNN-WLs) by uncertainty evaluation for accurate and stable prediction of manufacturing systems. The proposed approach improves the prediction accuracy and stability over existing methods by quantifying the variance of prediction errors and establishing an improved PINN framework.

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2023)

No Data Available