Jigar Patel

Jigar Patel

Trying to make sense of metal 3D printing using data

Sitemap

A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.

Pages

Posts

Belief test January 2023: What if I am wrong about……planning?

7 minute read

Published:

I spent a lot of time in 2022 looking at the world and feeling down about how polarizing everything and everyone seem. I took a class that had interesting content around that. The content modules, called ‘perspectives’ talked about rational and irrational thoughts (The elephant and the rider metaphor), confirmation bias and moral foundation theory. It made reflect about how I too have some strong opinions and having them questioned makes my palms sweat and I feel a rush of blood.

portfolio

Using Data Science to Analyze the printability of novel copper powder

I’m currently working on building a dataset of novel copper print data to predict factors that play a crucial role in its printability. Copper alloys are some of the most challenging materials to print using Laser Powder Bed Fusion, owing to their high reflectivity. I’m attempting collect sensor and machine settings data and build tree based classifiers that can help identify successful print zones

publications

Prediction of Material Removal Rate in Die-Sinking Electrical Discharge Machining

Published in Procedia Manufacturing, 2016

This paper presents a semi-empirical model which shows the relationship between material removal rate in die-sinking Electrical Discharge Machining and peak current and on-time. Peak current and on-time are considered as two critical factors that affect the material removal rate.

Recommended citation: Prediction of material removal rate in die-sinking electrical discharge machining NSLB Izwan, Z Feng, JB Patel, WN Hung - Procedia Manufacturing, 2016 http://jigarp12892.github.io/files/paper2.pdf

Quality Enhancement with Ultrasonic Wave and Pulsed Current in Electrochemical Machining

Published in Procedia Manufacturing, 2017

This paper explores a novel experimental set-up that combines pulsed electrochemical machining with ultrasonic vibrations directly applied to electrolyte

Recommended citation: Quality enhancement with ultrasonic wave and pulsed current in electrochemical machining JB Patel, Z Feng, PP Villanueva, WNP Hung - Procedia Manufacturing, 2017 http://jigarp12892.github.io/files/paper1.pdf

Towards generalizable machine learning prediction of downskin surface roughness in laser powder bed fusion

Published in Advances in Industrial and Manufacturing Engineering, 2017

This paper combines the challenge of poor understanding of L-PBF surface roughness and lack-of-generalizability of ML models that are often trained for such predictive capability.

Recommended citation: Patel, Vlasea, and Patel, “Towards Generalizable Machine Learning Prediction of Downskin Surface Roughness in Laser Powder Bed Fusion.” https://www.sciencedirect.com/science/article/pii/S2666912925000078

talks

“Correlative Analytics of Downskin Surface Roughness Outcomes Using Systematic Data Science Workflows

Published:

Laser Powder Bed Fusion (LBPF) is a widely adopted AM technology owing to the demonstrated benefits in design freedom and part consolidation for complex components. However, due to the complex and multiscale process physics that governs the process, ensuring consistent quality is an ongoing challenge. Data science is a promising tool to better understand the interaction between the LPBF process physics and the uncertainty in laser-material interaction phenomena. In this study we attempt to correlate downskin surface roughness outcomes to parameterized and simulated process inputs. The study specifically focusses on data collected from 4405 and maraging steel specimens built with different overhang angles. The data from multiple builds was consolidated and subjected to a systematic and data-centric analytics workflow. In our study, the dataset quality guides the process of developing descriptive, diagnostic and predictive insights. We share these insights, along with broader implications of using data-centric workflows.

Data-Centric Machine Learning for Surface Roughness in Laser Powder Bed Fusion

Published:

Understanding and tailoring surface roughness on Laser Powder Bed Fusion (L-PBF) components is an ongoing challenge in key aerospace and medical applications. Large experiments or computationally intense simulations to understand the phenomena are often needed. However, machine learning (ML) is an alternative approach that can accelerate and enhance experimental and simulation-based efforts. Effective ML models rely on large, informative and diverse training data to predict across different domains. There is a scarcity in the development and availability of such datasets. This study proposes and executes a database approach to build a large training dataset that predicts surface roughness and generate synthetic surfaces on ideal CAD profiles. A modular and extensible relational data model was developed and implemented to ingest data from a wide range of builds and specimens. The database currently spans data from over 25 different builds and surface roughness data from over 1000 specimens. An ML workflow was developed using the database wherein models are trained with the goal of generalizability in predicting surface roughness for unseen processing conditions. The preliminary results show significant potential for achieving robust prediction of surface roughness (reasonable prediction error on challenging test sets of different domains.). This work aims to address two challenges affecting L-PBF reliability: (i) A stronger understanding of L-PBF surface roughness and (ii) improved generalizability and usability of ML models training for L-BPF applications.

teaching

MMET 181-Manufacturing and Assembly Processes

Workshop, Texas A&M University, Engineering Technology and Industrial Distribution, 2015

I taught in-person manufacturing labs and graded reports and tests for more than 200 students across 4 semesters. Labs skills included basic welding, machining, casting, metrology and CNC machining.