MeetupIn person

Predictive Maintenance at the Synchrotron (and another mystery talk)

SEP15
18:00

About this event

The MLAI Meetup is a community for AI researchers and professionals which hosts monthly talks on exciting research. Our format is:

6:00 - 6:20: Socializing
6:20 - 6:40: Announcements and AI news
6:40 - 7:40: Talk(s) and Q&A
7:40 - 8:00 Networking
8:00: Head to the nearest pub for dinner

Joanna Wieclaw: "From Fixed Thresholds to Learned Boundaries: Predictive Maintenance at the Australian Synchrotron"

Talk Description: Last year I showed you how the Australian Synchrotron works. This year I'd like your help keeping it working.

Much of my job in Controls involves troubleshooting equipment after something has already gone wrong. I'd rather catch the warning signs first.

I'm developing a proposal for a phased predictive-maintenance system using data we already collect through EPICS (Experimental Physics and Industrial Control System). The proposed first phase is deliberately simple: choose one system, set fixed upper and lower thresholds, and alert on breaches. In parallel, I'd like to explore what can be learned from our historical data using offline ML models, with signals such as encoder drift, motor current and vacuum levels among the first targets.

Later phases could augment those thresholds with learned boundaries and look for patterns across equipment rather than within a single system.

I'd like to hear how you would approach it: what methods are worth trying early, how you would validate models when labelled failures are scarce, and what I should be implementing now to make the data useful as the system develops.

Speaker Bio: Joanna Wieclaw is a Senior Controls Technician at the Australian Synchrotron (ANSTO). With a mechatronics background and extensive experience in system integration and live fault-finding, she spends much of her time diagnosing complex equipment under pressure.

More upcoming events in Docklands

AUG
05

From Search to AI: Building Smarter Applications with Elastic & GenAI

Docklands, VIC, Docklands, Australia
In person
  • This meetup explores how teams use search, retrieval, and generative AI to build intelligent applications powered by real-world data.
  • It is designed for developers, engineers, and builders working with large language models, retrieval-augmented generation, and vector search.
  • Attendees will learn practical approaches for creating scalable AI systems and connecting data to smarter user experiences.
AI & Machine LearningNetworkingTalks & PanelsOperators
16:00 · Free · MeetupDetails →
AUG
08

Designare’s Coffee Meet Up

Milkbar, Docklands, Australia
In person
  • This event brings together Melbourne's creative community to share design ideas, exchange feedback, and build connections in an informal coffee setting.
  • Attendees can present work, discuss challenges, and explore opportunities in design through peer collaboration.
  • It is suited for creative professionals seeking to engage with peers and foster creativity outside typical meeting rooms.
Networking
11:00 · aud 5 · CompetitionDetails →
AUG
13

KSUG.AI x The Real-Time Platform for AI Conference Melbourne - 13 Aug 2026

Events Centre at Collins Square Level 5, Docklands, Australia · KSUG.AI Australia
In person
  • This conference focuses on AI and real-time platforms, bringing together professionals and enthusiasts in Melbourne.
  • Attendees can expect to explore innovations in AI technology and network with peers in the industry.
  • The event is suitable for those interested in AI development and applications.
AI & Machine LearningTalks & Panels
08:00 · ConferenceDetails →
AUG
18

When Maps Aren’t Enough: Using Spatial AI to Measure the Green We See

912 Collins St, Docklands, Australia · Machine Learning & AI Meetup
In person

The MLAI Meetup is a community for AI researchers and professionals which hosts monthly talks on exciting research. Our format is: 6:00 - 6:20: Socializing 6:20 - 6:40: Announcements and AI news 6:40 - 7:40: Talk(s) and Q&A 7:40 - 8:00 Networking 8:00: Head to the nearest pub for dinner Shinjita Das: When Maps Aren’t Enough: Using Spatial AI to Measure the Green We See Talk description: A tree can cool a street, appear clearly on a map – and still be completely invisible from someone’s window. That gap between what exists in a city and what people actually see and experience has shaped much of my research journey. When I first started working with geospatial science, I was fascinated by the idea that spatial data could reveal patterns in cities that are difficult to notice on the ground. During my Master’s research, I used deep learning to detect individual urban trees and examined their contributions to urban cooling. That was my first real encounter with machine learning, and it changed the way I thought about maps: they were no longer just tools for showing where things are, but platforms for asking what else we could learn from the environment. That curiosity led me further into GeoAI. If machine learning could help identify trees and quantify their environmental role, could similar computational approaches help us understand how people actually experience greenery? This question followed me into my PhD, where my toolkit expanded from 2D GIS and spatial statistics to 3D city modelling, computer vision and emerging GeoAI approaches. At the same time, the research question became more human. Instead of simply asking “Where is the green?”, I began asking, “Who can actually see it and how does the view impact mental health?” In this talk, I’ll trace that journey through examples from my research: from detecting trees and measuring their cooling effects to reconstructing urban environments in 3D and modelling greenery from the perspective of apartment resid

18:00 · MeetupDetails →
Share this event