Tuesday, August 30, 2022

Postdoctoral Fellowships for Sustainability Solutions at USC

 


The Postdoctoral Fellowships for Sustainability Solutions program aims to accelerate sustainability research; train future leaders in academia, government and non-governmental organizations, and industry; and support discovery, evaluation, and implementation of innovative solutions to sustainability problems.  


This postdoctoral fellowship seeks to advance the capacities of early-career scholars and researchers to conduct interdisciplinary research on sustainability problems. An interdisciplinary and diverse cohort of fellows will address challenges in one or more of the following areas: 

  • human health and well-being; 
  • infrastructure and the built environment;
  • natural environment and ecosystem services; 
  • communications, policy, and institutions; 
  • risk analysis and economic impacts.  

How to apply

Candidates must have earned a doctoral degree (e.g., Ph.D., Sc.D., M.D., J.D.) within the previous five yearsin a relevant field of study prior to the start of the appointment.  

 

Applications will be submitted online. Candidates should submit the following materials to the on-line application:

 

      Cover letter (1 page)

      Curriculum Vitae

      Research proposal (up to 2 pages)

      Names, contact information, and a joint statement of endorsement from two (2) USC faculty mentors with primary appointments in two different USC schools. The letter should provide a brief statement regarding their plan to provide career support and mentorship for the duration of the appointment. Examples of mentorship activities include, but are not limited to:

§  Conduct yearly reviews of the postdoc's IDP

§  Attend planned events for the program

§  Assist in preparing the research design and executing the research activities.

§  Arrange forums for the presentation, dissemination, and/or critique of the applicant’s research.

§  Identify potential publication sources and assisting in the preparation and submission of articles and manuscripts.

§  Connect the postdoc to other relevant investigators at USC and at other institutions.

§  Identify external funding sources and assisting in the preparation of grant proposals.

      Statement that highlights contributions to diversity, equity, and inclusion (up to 1 page)

      Names and e-mail addresses of two (2) references for letters of recommendation 

 

Applications will be evaluated starting at the beginning of November 2022. For full consideration of your application, please submit your material no later than 11/15/2022.

 

To find more information on the application process and to apply, click here

Monday, August 15, 2022

Data Analytics Workshop for Advanced Manufacturing was organized at USC on August 14, 2022

The invited speakers include

  • Prof. Hao Yan, Arizona State University
  • Prof. Andi Wang, Arizona State University
  • Prof. Cesar Ruiz,  University of Oklahoma
  • Prof. Yuanxiang Wang, Tongji University 
PhD students from USC Huang Lab, Weizhi Lin, Chris Henson, and Gabriel Gu presented their dissertation research on machine learning for Additive Manufacturing. Undergraduate researchers Yilin and Chengxi shared their summer research work. 

The workshop ended with a great dinner at Savoca at LA Live!

Sunday, August 14, 2022

An Impulse Response Formulation for Small-Sample Learning and Control of Additive Manufacturing Quality

This work establishes an impulse response formulation of layer-wise AM processes to relate design inputs with the deformed final products. To enable prescriptive learning from a small sample of printed parts with different 3D shapes, we develop a fabrication-aware input-output representation, where each product is constructed by a large amount of basic shape primitives. The impulse response model depicts how the 2D shape primitives (circular sectors, line segments, and corner segments) in each layer are stacked up to become final 3D shape primitives. A geometric quality of a new design can therefore be predicted through the construction of learned shape primitives. Essentially, the small-sample learning of printed products is transformed into a large-sample learning of printed shape primitives under the impulse response formulation of AM. This fabrication-aware formulation builds the foundation for applying well-established control theory to the intelligent quality control in AM. It not only provides theoretical underpinning and justification of our previous work, but also enable new opportunities in ML4AM. As an example, it leads to transfer function characterization of AM processes to uncover process insights. It also provides block-diagram representation of AM processes to design and optimize the control of AM quality.

https://doi.org/10.1080/24725854.2022.2113186


Sunday, June 5, 2022

Share two new journal papers: one extending the fabrication-aware convolution learning framework to a broader class of 3D geometries for 3D printing accuracy control, and the other providing accuracy control for Wire and Arc Additive Manufacturing.

Share two new journal papers: one extending the fabrication-aware convolution learning framework to a broader class of 3D geometries for 3D printing accuracy control, and the other providing accuracy control for Wire and Arc Additive Manufacturing:

  • Yuanxiang Wang*, Cesar Ruiz*, and Q. Huang, 2022, “Learning and Predicting Shape Deviations of Smooth and Non-Smooth 3D Geometries through Mathematical Decomposition of Additive Manufacturing, ” IEEE Transactions on Automation Science and Engineering, DOI: 10.1109/TASE.2022.3174228, in press.

  • Cesar Ruiz*, Davoud Jafari, Vignesh V. Subramanian, Tom H.J. Vaneker, Wei Ya, and Qiang Huang, 2022, “Prediction and Control of Product Shape Quality in Wire and Arc Additive Manufacturing Using Generalized Additive Models,” ASME Transactions, Journal of Manufacturing Science and Engineering, DOI: 10.1115/1.4054721, in press.

Tuesday, October 5, 2021

IISE Transactions: Special Issue Call-for-papers - AI and Machine Learning for Manufacturing

 

Special Issue: AI and Machine Learning for Manufacturing

IISE Transactions: Focused Issue on Design and Manufacturing 

As a trend of future manufacturing, consumer demand increasingly shifts to personalization, customization, and consumer-maker co-creation. Intertwined with these changing demands , rapid technology advances in new manufacturing technologies, Internet of Things (IoT), robotics, AI and machine learning methods, have significantly expanded, and are continually expanding manufacturing capability, utility, and accessibility. Manufacturing processes and systems have become more connected, intelligent, agile, and collaborative. The special editor team senses that we are right now at a critical juncture of the manufacturing revolution. IISE Transactions Design and Manufacturing Focused Issue is hereby organizing a special issue to capture this moment and capitalize this opportunity. This special issue has two primary objectives: (a) showcase how the AI and machine learning methods have reshaped the landscape of manufacturing in its research and practice; and (b) bring a community of researchers in multiple disciplines to establish new theories, methodologies, and tools to enable smart and intelligent manufacturing by taking full advantage of the recent AI and machine learning innovations.

The topics include, but will not be limited to the following:


·       AI methodologies for manufacturing

·       Cybersecurity for manufacturing

·       Digital twins for manufacturing

·       Fabrication-aware machine learning

·       Human-robot collaborative manufacturing

·       Intelligent manufacturing machines or processes (e.g., smart 3D printers)

·       Intelligent manufacturing systems

·       Intelligent maintenance for manufacturing

·       Machine learning enabled in-process quality improvements methods

·       Machine learning enabled design optimization 

·       Machine learning-based collaborative manufacturing

·       Manufacturing-as-a-Service (MaaS)

·       New anomaly detection algorithms with limited supervision.

·       New advances in cyber-physical manufacturing systems and Industry 4.0

·       Novel manufacturing such as space manufacturing

·       Physical model-guided machine learning for manufacturing

·       Smart monitoring and control of manufacturing

·       Smart sensing and IoT for manufacturing

Papers must be submitted through http://mc.manuscriptcentral.com/iietransactions and prepared according to the journal’s Instructions for authors. Select “Special Issue” for the question “Please select the Focus Issue to which the paper is most related” at Step 1 in the submission process, and select the specific special issue at Step 6. We highly encourage authors to submit abstracts to the lead editor (qiang.huang@usc.edu) in order for the editorial team to provide feedback on the submission and to facilitate a timely review of the full paper.

Important Dates

·       (Encouraged) Abstract Submission: 3/31/2022

·       Manuscript submission: 6/30/2022

·       Completion of 1st round review: 9/30/2022

·       Completion of 2nd round review: 1/31/2023

·       Final manuscript submission: 3/1/2023

·       Tentative publication date: 7/2023


Guest Editors   

Qiang Huang, Professor
University of Southern California
 
Bianca Maria Colosimo, Professor
Politecnico di Milano

John Hart, Professor
Massachusetts Institute of Technology

Conrad Tucker, Professor
Carnegie Mellon University

Lihui Wang, Professor
KTH Royal Institute of Technology

Focus Issue Editor   
Zhenyu (James) Kong, Professor
Virginia Polytechnic Institute and State University


_________________________________________________
Qiang Huang, Ph.D.
Professor
Epstein Department of Industrial and Systems Engineering
Mork Family Department of Chemical Engineering & Materials Science
University of Southern California 
3715 McClintock Ave, GER 216C
Los Angeles, CA 90089-0193
Phone: 213-740-2433(O)



Tuesday, September 7, 2021

Fabrication-aware Machine Learning of Heterogeneous Shape Quality Data Wins 2021 IEEE-CASE Best Conference Paper Award

Ph.D. candidate Yuanxiang Wang and post-doctoral scholar Cesar Ruiz at the USC Daniel J. Epstein Department of Industrial and Systems Engineering received the Best Conference Paper Award in 2021 IEEE 17th International Conference on Automation Science and Engineering (CASE). The presentation video can be found at https://case2021.sciencesconf.org/resource/page/id/37.

Extended Fabrication-Aware Convolution Learning Framework for Predicting 3D Shape Deformation in Additive Manufacturing

 Yuanxiang Wang, Cesar Ruiz, Qiang Huang*

Engineering processes such as 3D printing generate complex shape data in the form of 3D point clouds. Qualification and verification of 3D shapes involves modeling and learning of heterogeneous shape deviation data that are affected by both product geometries and process physics. This study develops an engineering-informed, small-sample machine learning methodology to learn and predict deviations of smooth and non-smooth 3D shapes in a unified modeling framework. The generation of a non-smooth 3D shape is mathematically decomposed into the smooth base shape formation and shape difference realization. Both process physics and shape geometries are captured in the learning framework. It provides a new data analytical tool for shape engineering in additive manufacturing and beyond. 

Tuesday, November 17, 2020

Post-doc position at University of Alberta

 


 Postdoctoral Position In Topology Optimization And Finite Element Modeling 

The Position 

The Additive Design and Manufacturing Systems Laboratories has recently commissioned a laser powder bed fusion metal additive manufacturing system and a wire-arc additive manufacturing system. The laboratory has experienced significant growth and is looking to hire a post-doctoral researcher who will support the topology optimization, structure design and finite element modeling for metal additive manufacturing processes. 

This position will be open to candidates possesing an undergraduate degree in Mechanical Engineering, Civil Engineering, or a relevant discipline, and a PhD in topology optimization, design for additive manufacturing, or finite element modeling for structures under dynamic forces (PhD obtained after 01-December-2016). Applicants who have applied before to ADAMS lab may also apply provided their PhD completion date is after December 01, 2016. The initial term of the contract will be one year with a possibility of extension dependant on continuation of contract and availability of funding. 

Candidate profile and requirements 

The candidate must necessarily possess expertise and experience in the following research areas: 

1. Application of topology optimization for design and modeling of mechanical structures using techniques such as unit cell-based design, level sets, meta materials, and generative design for structural design of mechanical components under given mechanical and manufacturing design specification. 

2. Expertise in solid modeling, mesh generation, and linear and non-linear finite element analysis with applications to areas such as vibration and impact, contact, fatigue, and wear of mechanical systems and machines under varying test conditions. Experience and expertise in at least one of the main FEA software's such as ABQUS or ANSYS is required. 

3. Experience of material characterisation including mechanical testing such as tensile, flexural, and compression testing, and digital image correlation. 


In addition to above necessary requirements, candidates with experience in the following areas will be given priority: 

  1. a. Experience of working with metal additive manufacturing systems. 
  2. b. Experience of microstructure and material characterisation such as microscopy, XRD, EDX, and EBSD. 
  3. c. Experience of working with polymer additive manufacturing systems. 


The successful candidate will be required to work independently and must demonstrate excellent verbal and written English communication skills evident through high-quality journal publications in the research area. It is expected that the successful candidate will be able to start the position at the latest by January 02, 2021. The candidate should possess or be eligible to apply for a valid drivers license and will be expected to travel within the city and Alberta as per the project requirements (and following COVID-19 mandated restrictions). The candidate should also be willing and eligible to travel to other provinces, or internationally as per the project needs, but following COVID-19 mandated restrictions noted by the University of Alberta, and the Governments of Alberta and Canada. 

The Project 

The candidate's primary responsibility will be to analyze and redesign components of machinery equipment used in the energy, mining, space, and automotive industries using topology optimization techniques and metal additive manufacturing technology to improve functional performance, reliability, and quality of the systems. 

The scope of the project includes the following tasks for the design and manufacturing of components: 

  • • Applying topology optimization and assembly consolidation concepts to reimagine existing conventionally manufactured components and assemblies for novel designs suitable for AM processes. 
  • • Validation of the designs using an appropriate finite element analysis. 
  • • Experimental characterization and validation of materials and printed components with a focus on wear resistant materials through laser powder bed fusion, wire arc additive manufacturing, or plasma transfer arc additive manufacturing. 


Application Procedure 

The application may be submitted through an online submission process by accessing the link given below: 

https://forms.gle/X1X6rm2Ju7SEpadD7 

The candidates will be asked to fill an online form and upload a single PDF file which includes: 

  1. i- A cover letter that high lights your suitability for the position 
  2. ii- A detailed curriculum vitae highlighting areas of research, a list of publications, awards and honours, and a list of three professional references. 
  3. iii- A minimum of 2 samples of the candidate's most significant scholarly work pertaining to the research areas defined in the candidate profile. Additional documents may be requested upon submission of the aforementioned documents. 


Please note that only the complete applications, including the documents i-iii from the candidates graduating with Ph.D. after December 01, 2016, will be considered. The review of applications will begin immediately, and applications will be accepted until the position has been filled. 

Interested candidates should use ADAMS771611PDF as the job competition number in the online form. 

We thank all applicants for their interest; however, only those short listed for an interview will be contacted. 

The University of Alberta is committed to an equitable, diverse, and inclusive workforce. We welcome applications from all qualified persons. We encourage women; First Nations, Métis and Inuit; members of visible minority groups; persons with disabilities; persons of any sexual orientation or gender identity and expression; and all those who may contribute to the further diversification of ideas and the University to apply. 

Saturday, June 20, 2020

Smart 3D Printing Quality Control Service Portal: PrintFixer 1.0


We at the University of Southern California  have been developing a smart 3D printing service portal to control dimensional quality and shape distortion of 3D printed products. The service portal is at PrinFixer 1.0

Selected users can be provided free dimensional quality control service. Join us to build a quality control service platform for 3D printing user community!

Contact: Prof. Q. Huang (qiang.huang@usc.edu)

Friday, June 12, 2020

Special Issue on Machine Learning in Dimensional Metrology: Call for Papers

https://www.journals.elsevier.com/precision-engineering/call-for-papers/special-issue-on-machine-learning-in-dimensional-metrology

Precision engineering has been, and continues to be, one of the disciplines needed to enable future technological progress, especially in the area of manufacturing. Demands for increasing precision have also evolved in almost all other industrial sectors; ranging from planes, trains and automobiles, to printers (printing electronics and optical surfaces), scientific and analytical instruments (microscopes and telescopes to particle accelerators), medical and surgical tools, and traditional and renewable power generation. At the root of all of these technologies are increasingly advanced machines and controls, and in manufacturing, advanced products. Metrology plays a key role in precision engineering, allowing the degree of precision and accuracy to be quantified and used in later processes. Modern digital manufacturing (a.k.a. Industry 4.0) requires the creation, manipulation and sharing of large amounts of data. But, the adoption of digital technology in manufacturing processes is currently hindered by lack of efficiency and confidence in data that is captured within those processes. Confidence in data is the key enabler for adoption of the Industry 4.0 methodologies. Through traceability, metrology is one of the pillars for demonstrating confidence in data, without which, industry suffers from unnecessary waste, inefficient processes and increased costs for quality. A significant issue with the adoption of digital manufacturing is the vast amount of data that can be produced with new measurement technologies. But, this data-rich issue can be an opportunity if advanced data handling, analysis and learning methods can be developed and employed. These issues are ideal for machine learning (ML), which is only now being utilised for measurement applications, to enhance the capability and performance of instruments, e.g. understand surface orientations, automatically segment 3D point clouds, infer surface information from missing data using a priori information and automatically segment objects, especially for machine vision applications.
Many of the speed and data challenges that plague metrology for digital manufacturing could be overcome by combining ML approaches with precision engineering/metrology. The special issue will investigate where machine learning can be applied in the following areas:
  • Coordinate metrology
  • ML in optical metrology
  • ML for quality control and in-process metrology
  • ML for surface metrology
  • ML for X-ray computed tomography
  • ML for critical dimension and overlay
  • Sampling and interpolation in surface measurement
  • Ultra-fast surface defect and feature recognition
  • Uncertainty methods with ML measurement models
  • Monte Carlo simulation using ML methods
Guest Editors:
Prof. Richard Leach
University of Nottingham
richard.leach@nottingham.ac.uk
Dr. Samanta Piano
University of Nottingham
Samanta.piano@nottingham.ac.uk
Dr. Benjamin Haefner
Karlsruhe Institute of Technology
benjamin.haefner@kit.edu
Prof. Robert Schmitt
RWTH Aachen and Fraunhofer IPT
r.schmitt@wzl.rwth-aachen.de
Prof . Bianca Colosimo
Polytechnico Milano
biancamaria.colosimo@polimi.it
Submission Deadline: February 2021
Acceptance Deadline: April 2021
Please submit your paper here - https://www.evise.com/profile/#/PRE/login

Friday, June 5, 2020

USC Post-doc Position on Data Science for Engineering Applications (Position filled)

Posting Date: June 5, 2020
Application Deadline: Open until filled


Prof. Huang's Lab, in the Epstein Department of Industrial and Engineering at the University of Southern California (HuangLab.usc.edu), seeks applicants for a postdoctoral scholar working in Data Science for Engineering Applications. Project goals focus on, but not limited to, developing AI and Machine Learning algorithms for non-intrusive inspection and maintenance systems with imaging data.  The duration of the initial appointment will be for one year. The position is can be renewable based on research productivity, performance and funding. Performance review is conducted every six months.

USC provides outstanding benefits for post-doc scholars. Policy regarding minimum salary and benefit can be found at https://policy.usc.edu/postdoctoral-scholars/.


Duties & Responsibilities:
The postdoctoral scholar will be expected to take a leading role in developing machine learning algorithms and defect detection methods for non-intrusive inspection and maintenance systems. Other than top-notch publications, the postdoctoral scholar is expected to prepare project reports, supervise and collaborate with junior PhD students, and attend conferences to present his/her research work. 

Stating date: September 16, 2020

Contact: Prof. Huang (Email: qiang.huang@usc.edu)

Note: This announcement might be updated with more details.