Internships

ASM Pacific is a world-leader in the field of semiconductor equipment. At ASM ALSI in Beuningen, the Netherlands, we develop an advanced multi-beam laser dicing tool, but we also have a technology development team (ASM Center of Competency) that supports the global ASM company with high-tech innovations in various domains, like artificial intelligence, advanced motion control, industrial vision, machine learning and data science. In both the laser dicing business unit and the Center of competency ASM Pacific Technology provides challenging internship positions for university level students. Both short-term (3 months) as well as full-lengths (9 months) MSc internships are supported. We currently have several master students working on their internships in the fields of advanced motion control and artificial intelligence and are always looking for new projects + students.

ASM offers:

  • A dynamic high-tech industrial environment in which you learn to apply academic knowledge to real-life problems
  • Exposure to the larger ASM organization (>16000 person), opportunities to interact/present to colleagues in Hong Kong and Singapore.
  • Solid supervision by senior professionals that have a strong academic and industrial background
  • A market-conform internship compensation and travel expense compensation
  • Contribute to state-of-the art industrial developments

Master Thesis Projects:

Benchmarking Software for Machine Health Management

The ASM Centre of Competency, located in the Netherlands, is responsible for identifying new high-tech innovation opportunities for the full global ASM Pacific Technology product portfolio [1]. The equipment portfolio of ASM Pacific Technology covers the complete back-end section of the semiconductor equipment market, and offers comprehensive assembly and advanced packaging solutions for its customers in the fields of optoelectronics, electronics, solar energy, automotive and other segments.

Challenges

The semiconductor industry is one of the most technology-evolving and capital-intensive market sectors [2-5]. To strengthen a competitive position in the semiconductor industry, the key challenges a manufacturing plant has to face are the increase of production throughput and yield. Monitoring health conditions of the semiconductor machines is therefore necessary to secure the required product quality. Furthermore, effective prediction of the failures of the semicon equipment is a way to decrease a machine downtime, improve productivity, and reduce production costs and repairing time.

The semiconductor manufacturing equipment is equipped with different sensors for real-time machine control and equipment condition monitoring. Data from these sensors can be used to detect deviations of the machine performance from the nominal one, in order to avoid degradations in the product quality and losses in the production yield. The same data is useful in the process of discovering when the equipment needs a maintenance to avoid machine failures and unscheduled breaks in the production.

To achieve automated machine condition monitoring and predictive maintenance functionalities, we need to address the following challenges [2-7]:

  • make appropriate selection of sensors for machine condition monitoring and choose optimal locations where these sensors have to be installed,
  • develop algorithms for machine health management, starting from extraction of machine health condition indicators (CI’s) out of the sensor signals, up to design of predictive methods for forecasting equipment behaviour and health diagnostics,
  • optimally schedule maintenance operations according to the equipment conditions.

Company ASM Pacific Technology is developing proprietary software for machine health management, which is customized for applications and deployment on own semicon machines. The question how well this software performs in comparison with commercial off-the-shelf software packages for condition monitoring, health diagnostics and predictive maintenance. Therefore, it is instructive to benchmark the proprietary software of ASM Pacific Technology with commercial software tools in terms of available functionalities, calculation efficiency, user friendliness, level of automation, reliability and accuracy of forecasting machine behaviour, etc.

Internship Assignment

In this project, we will benchmark the proprietary software of ASM Pacific Technology with at least one commercial software package for machine health management. An interesting off-the-shelf candidate is the LabVIEW Analytics and Machine Learning Toolkit [8]. If time would allow, we may also include the Predictive Maintenance Toolbox of Matlab [9] in benchmarking.

The Center of Competency has a large collection of data measured on many ASMPT machines operating in the field. These data involve standard readings from motion and current sensors. The idea is to process these data using the company proprietary software and commercial tools, such as to benchmark functionalities, performance and autonomy of the company software with respect to the off-the-shelf solutions. Furthermore, the Center of Competency has several models of a wirebonder machine that can be used for simulation of machine behaviours that might not be captured in the available measurements. If needed, synthetic data could be generated in simulations to make more complete evaluation of the software capabilities.

The investigation objectives are:

  • literature study on methods for machine condition monitoring, health diagnostics and predictive maintenance,
  • learn how to perform machine health management using the proprietary software of ASM Pacific Technology and LabVIEW Analytics and Machine Learning Toolkit,
  • process available machine data using the proprietary and commercial software packages and critically evaluate advantages and limitations of these software tools,
  • if needed, generate synthetic data by simulation of machine behaviours that are not captured in the existing measurements but could be used for evaluation of some specific software functionalities,
  • eventually, include Predictive Maintenance Toolbox of Matlab in the benchmarking,
  • identify pro’s and con’s of the proprietary software for machine health management and give recommendations for its eventual improvements.

The results of this project will be disseminated via the internship report and presentations at the knowledge institution and Center of Competency. The generated knowledge can become a valuable academic know-how and drive technological advantages against other producers of the semiconductor equipment.

To apply for this internship please contact gknippels@alsi.asmpt.com , 024 678 2873

References

  • ASM Center of Competency, https://alsi.asmpt.com
  • Munirathinam and B. Ramadoss, “Predictive Models for Equipment Fault Detection in the Semiconductor Manufacturing Process,” IACSIT International Journal of Engineering and Technology, Vol. 8, No. 4, pp. 273-285, 2016.
  • Liu, Predictive modeling for intelligent maintenance in complex semiconductor manufacturing processes, PhD thesis, The University of Michigan, 2008.
  • Iskandar, J. Moyne, K. Subrahmanyam, P. Hawkins, and M. Armacos: “Predictive Maintenance in semiconductor manufacturing,” 26th Annual SEMI Advanced Semiconductor Manufacturing Conference, Saratoga Springs, NY, USA, 2015.
  • Scheibelhofer, D. Gleispach, G. Hayderer, and E. Stadlober: “A Methodology for Predictive Maintenance in Semiconductor Manufacturing,” Austrian Journal of Statistics, Vol. 41, No. 3, pp. 161–173, 2012.
  • Khanore, Predictive Maintenance Algorithms Development for a Wire Bonder, DCT internship report, 2019.
  • van Bussel: Obtaining Machine Health Condition Indicators Using Wavelet Transforms, DCT internship report, 2019.
  • LabVIEW Analytics and Machine Learning Toolkit,
    http://www.ni.com/pdf/manuals/377061a.html
  • Predictive Maintenance Toolbox of Matlab, https://nl.mathworks.com/products/predictive-maintenance.html

Internship: Generative models for understanding micro-scale devices from minimum-labeled data

Imaging and computer vision play a key role in micro-scale manufacturing processes.

 

They enable both online assembly processes and subsequent defect inspection steps, not to mention their important role in various factory automation and related robotics tasks. Recent progresses in deep learning allow for more reliable visual recognition capabilities. State of the art object detection and segmentation methods are being employed at ASM for various assembly and packaging workflows. Nonetheless, supervised deep learning, based mostly on convolutional neural networks, is proving data and labor intensive for many real-world applications. In a semiconductor manufacturing environment, for example, the configuration of assembled devices can frequently change, and the need for relabeling new datasets on the factory floor can be a bottleneck in a practical deployment scenario. While techniques such as transfer learning are alleviating such bottlenecks, developing a capacity for generalization in machine learning workflows will be greatly beneficial in advanced manufacturing. ASM Pacific Technology is currently exploring data augmentation and generalization techniques based on realistic simulations. To complement this effort, we aim at using Generative models, such as those based on GANs, for enabling prediction from limited labeled data. Such models are showing promise in various applications and would potentially enable the synthesis of large-scale datasets and a better prediction quality in various applications. The goal of this Thesis internship is to explore the use of Generative models for improving the visual recognition of semiconductor device components and for enhancing the reasoning performance of defect detection modules. During his work, the intern will undertake the following tasks:

  • Literature search on the state of the art (deep) generative models and their application to realistic image synthesis and data augmentation (focusing mainly on GANs.)
  • Make a choice of a limited number of models for experimentation and further development.
  • Understand the inclusion of various physical constraints in the Generative models.
  • Train the models on ASM device images and demonstrate the image synthesis results.
  • Analyze the generalization capabilities of the investigated models on object detection and semantic segmentation tasks, working with the ASM center of competency staff.
  • Summarize the results and analysis in a final and mid-term reports.

To apply for this internship please contact gknippels@alsi.asmpt.com , 024 678 2873

References:

[1] Goodfellow, Ian, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. “Generative adversarial nets.” In Advances in neural information processing systems, pp. 2672-2680. 2014.

[2] Radford, Alec, Luke Metz, and Soumith Chintala. “Unsupervised representation learning with deep convolutional generative adversarial networks.” arXiv preprint arXiv:1511.06434 (2015).

[3] Karras, Tero, et al. “Progressive growing of GANs for improved quality, stability, and variation.” arXiv preprint arXiv:1710.10196 (2017).

[4] Brock, Andrew, Jeff Donahue, and Karen Simonyan. “Large Scale GAN Training for High Fidelity Natural Image Synthesis.” arXiv preprint arXiv:1809.11096 (2018).

Internship: Micro-device 3D structure inference using deep learning

In advanced micro-scale manufacturing, such as in the semiconductor assembly and packaging field, machine vision plays a key role in inspection and process control.

The use of 3D micro-scale imaging is increasingly popular for several critical tasks. Cost, throughput, and space limitations can however restrict the integration of complex 3D capture devices for certain applications. An attractive option is to use the already available optics and 2D sensors and reconstruct 3D information computationally. Conventionally, in such approach one would need to acquire multiple 2D images, from different viewpoints, to obtain a good reconstruction. Other techniques can be used as well, including depth recovery from focus stacks. These methods are, however, considered too slow for online semiconductor manufacturing applications. More recently, the task of reconstructing 3D from single images regained attention due to the possibilities offered by deep convolutional networks. A CNN model can be trained on pairs of 2D and 3D images, learning the geometric structure of the objects of interest. This can potentially turn ordinary industrial vision cameras into 3D acquisition devices. The goal of this Master thesis project is to:

  • Perform a literature search on the latest deep-learning based 3D reconstruction techniques, with a focus on monocular methods.
  • Select two or three methods for evaluation and further development.
  • Acquire 2D/3D training pairs using available ASM equipment (confocal microscopes, stereo cameras, and regular 2D cameras.) The imagery will be acquired on ASM application-related devices.
  • Train suitable 3D reconstruction models, using internal and external datasets, and employing transfer learning when relevant.
  • Explore the incorporation of prior knowledge about device geometry and materials in the reconstruction process.
  • Compile the results and analysis in a final and mid-term reports.

The intern will be supported and advised in his various tasks by ASM Pacific Technology staff, interacting with the local team in the Netherlands, as well as with the Asia-based groups.

To apply for this internship please contact gknippels@alsi.asmpt.com , 024 678 2873

References:

[1] Eigen, David, Christian Puhrsch, and Rob Fergus. “Depth map prediction from a single image using a multi-scale deep network.” In Advances in neural information processing systems, pp. 2366-2374. 2014.

[2] Garg, Ravi, Vijay Kumar BG, Gustavo Carneiro, and Ian Reid. “Unsupervised cnn for single view depth estimation: Geometry to the rescue.” In European Conference on Computer Vision, pp. 740-756. Springer, Cham, 2016.

[3] Rezende, Danilo Jimenez, SM Ali Eslami, Shakir Mohamed, Peter Battaglia, Max Jaderberg, and Nicolas Heess. “Unsupervised learning of 3d structure from images.” In Advances in Neural Information Processing Systems, pp. 4996-5004. 2016.

[4] Fan, Haoqiang, Hao Su, and Leonidas J. Guibas. “A Point Set Generation Network for 3D Object Reconstruction from a Single Image.” CVPR. Vol. 2. No. 4. 2017.

[5] Wu, Jiajun, Chengkai Zhang, Tianfan Xue, Bill Freeman, and Josh Tenenbaum. “Learning a probabilistic latent space of object shapes via 3d generative-adversarial modeling.” In Advances in Neural Information Processing Systems, pp. 82-90. 2016.

[6] Zhou, Tinghui, Matthew Brown, Noah Snavely, and David G. Lowe. “Unsupervised learning of depth and ego-motion from video.” In CVPR, vol. 2, no. 6, p. 7. 2017.