Please rotate your phone horizontally or reopen this page on a larger viewport to view case study content.

BHP

Optimus-AI

A web app for BHP's port operators to monitor iron ore throughput, identify equipment bottlenecks, and optimise equipment routing.
product design
machine learning
data viz
web
my role
Lead Designer,
UX/ UI, prototyping
tools
Sketch, InVision, Zeplin
team
2 designers, 4 data scientists, 5 full-stack engineers
Date
Sep – Nov 18
backgroundresearchPrototypingsolutionimpact
background

AI–powered logistics for the world's largest mining company

BHP is one of the largest and most successful natural resources companies in the world. It mines, refines, and ships a vast array of natural resources across the world and is responsible for over 30% of global iron ore production. My team's focus was to find value creation opportunities for BHP by applying our advanced analytics expertise.
metrics overview, trigger schedule optimiser (click to view)
problem statement

How can we use advanced analytics to improve throughput at the port?

The Port had throughput issues – malfunctioning conveyor belts, worn-out car dumpers, and suboptimal equipment schedules – that prevented them from reaching their throughput targets. Most of the port's operations were monitored manually and decisions for equipment schedules were made on the fly. This behaviour resulted in inaccurate assessments and wasted man hours.

Throughput: the amount of material or items passing through a system or process.
our machine learning model ran on trillions of possible routes to ship
a bird's eye view of Port Hedland

Using the largest iron ore port as a template

Port Hedland, located in Western Australia, proved to be BHP's most promising prospect for a digital transformation. Our reasoning was that if we could succeed at the largest and most complex iron ore port, then our insights could be scaled down to ports around the world.
two general material flows for iron ore to from train cars to ship

Porsche's Formula-E Debut

In 2019, Porsche's legendary Le Mans racing team announced they were joining Formula-E for the 2020 season. Over four months of working closely with our client, McKinsey / QuantumBlack designed a bespoke, web-based tool that allowed the racing team to predict competitor outcomes, manage their car’s energy, and play out “what if?” forecasting scenarios. We called this tool Prometheus AI, which ultimately allowed Porsche to make better in-race strategic decisions.

To date, the Porsche team has seen great success by leveraging Prometheus AI during their fall training and their debut race, finishing second place in Al Diriyah and they have sought out my team’s services to continue building out the tool for the 2021 season.
understanding the logistics

I spoke to industry experts to gain an understanding of the iron ore supply chain

after mined, iron ore is transported hundreds of miles, by train, to the nearest port
port operators work remotely in 12-hour shifts, often hundreds of miles away from the port
port operators track live performance metrics and need to react quickly to equipment breakdowns
Sketching UI

UI Explorations

prototyping

Validating design from the other side of the planet.

I was based in London, my team was based in Perth and Sydney, and our clients were based in Port Hedland. I leveraged remote collaboration tools and McKinsey's extensive network of knowledge experts to validate my early concepts and user flows.

user testing

Testing lo-fi prototypes with port operators

Our client was based in Perth, Western Australia so going testing my concepts in person was infeasible in the limited time we had. I used cognitive walkthroughs of key user flows to elicit feedback and validate my designs. During testing I realised that my flows made sense, but that our data visualisations, for product material movements, needed to somehow incorporate metadata for product type.

final designs

Crafting a custom colour palette and a forward–looking UI

I defined a custom UI colour palette based on colours observed at Port Hedland and in the BHP branding – rust oranges, sky blues, and warm blacks. I used the different shades of the warm blacks as the UI base and bright oranges and blues accents for CTAs and visualisations.

colour palette & typography (click to expand)
final UI mocks (click to expand)
metrics overview, trigger schedule optimiser (click to expand)
product switching, schedule optimiser (click to expand)
IMPACT

Winning a 7-figure contract with BHP for a digital transformation

I pitched my team's design proposal to c-suite executives at BHP ultimately influencing them to invest in digital infrastructure that could solve their logistics challenges. As a result, McKinsey won a multi-million dollar contract with BHP that 13 other companies were also vying for.

reflection

Final Thoughts

[]

Want to see more work?