Model Behavior: Driving Greater Fuel Economy for Industrial Engines

Welcome to the sixth installment of Model Behavior. This ongoing series provides an inside look at Uptake’s industrial data scientists and the challenging work they do on behalf of our customers. Why is this topic so important? Because tough problems don’t solve themselves. See how model Uptakers build and deploy Uptake’s models — and how both of those elements must work together in harmony to create a world that always works.

It takes a lot to run an industrial enterprise. A lot of skill and know-how. A lot of time and resources. The stakes are high, attention to detail matters and risk isn’t taken lightly.

More and more, today’s industrial companies face the daunting task of doing more with less. In order to compete in tough markets, they must continue to invest in innovation while lowering their operations and maintenance (O&M) costs.

It’s a constant balancing act.

At Uptake, we believe that data breeds superheroes. When data is used to its full potential, it empowers people to be superhuman. They can know all the facts, ask the right questions, make decisions with total clarity and see around corners. Businesses gain the benefit of being able to run more efficiently and predictably than ever before.

Now Here’s the Catch

Uptake industrial data scientist Max Li is an expert at efficiency. As a member of our Fuel Engine Team, Max spends his time studying the fuel usage patterns of our customers’ most critical assets — such as trucks, locomotives and construction equipment — to help ensure those machines run as efficiently as possible.

Why is efficiency the name of the game? Because in heavy industrial sectors around the world, fuel is one of the largest operating costs for today’s businesses. Perhaps the truest example of this is in the trucking industry, where vehicles rely on fuel to get from point A to point B safely and on time.

One of Uptake’s customers owns and operates a large fleet of trucks. On one of those trucks, our model recently identified a mechanical failure with its Diesel Particulate Filter (DPF) — a key component that removes soot from the exhaust gas of the vehicle’s diesel engine.

Trucks are susceptible to DPF failures because, like any filter, they’re prone to clogging over time. If the vehicle cannot pass exhaust fully through its system, then in essence it cannot breathe. As a result, other components and systems of the truck are increasingly likely to malfunction, and the engine will start to deliberately constrain its power.

To catch this behavior, our model analyzes data from multiple sensors on the truck to understand the vital operating factors that impact fuel usage — including acceleration, speed and temperature.

Once our model was deployed and live on the asset, it quickly identified that our customer’s truck had been burning up to 20% more fuel than normal over the past four months. To put that cost into perspective: The cost of the excess fuel consumed for all of the trips taken by that one truck during that time amounted to approximately $5,000; that cost more than doubled the cost of the original repair of $2,000 had the issue been known about and addressed at the onset.

By alerting our customer to the problem and equipping its maintenance team with this actionable insight, technicians were able to prioritize the truck for repair, fix the DPF before other problems resulted, and get the truck out of the shop and back onto the road with optimal fuel economy.

Ask Me About My Failures

In this video, Max explains the catch in his own words:

Want to meet more of Uptake’s industrial data scientists? Check out our past episodes to see how they’re using their skills to:

Power a brighter future for society.

Keep manufacturing lines up and running.

Make sure trucking fleets stay on the road and deliver on time.

Help locomotives run better for more reliable rail transport.

Keep wind turbines turning to produce more renewable energy.

New to Our Model Behavior Series?

Here are some helpful definitions to know:

A machine learning model is a codified structure and digital representation of an industrial asset that physically exists in the real world. It organizes the data generated by the asset and standardizes relationships within that data — and, importantly, how all of that data relates to the physical properties of the actual asset. A model targets a specific component of a specific asset, growing increasingly accurate over time with each new data point.

At Uptake, our machine learning models are the output of our AI engines, which are tools that automate the development and deployment of our models. Our engines use valuable insights gained from different industrial use cases to come up with approaches that solve common sets of problems.

A failure happens when an asset or one of its components shuts down unexpectedly in its operating environment, causing problems like unplanned downtime, lost production, service disruptions, unsafe working conditions and more. Failures are what models try to predict and prevent from happening.

A catch is when one of our models — running in a live production environment for our customers — generates an alert that correctly warns of a failure or performance issue that’s bound to happen. Or, in other words: A catch means our model did what it set out to do.

Think you have what it takes to become an industrial data scientist at Uptake? Visit our Careers Page to view our open positions.

Check out the seventh installment of Model Behavior here.