We use cookies essential for this site to function well. Please click “Accept” to help us improve its usefulness with additional cookies. Learn about our use of cookies, and collaboration with select social media and trusted analytics partners here

Maximizing energy output using renewables equipment
Optimizing vessels' engines for greener maritime
Enabling remote diagnostics using data from wearables
Life Sciences
Utilizing AI across the medical treatment value chain

ChordX: Predictive maintenance for vessels

Speak with an AI/ML expert in your industry
Contact us
View our cases to discover what we have reaserched
ChordX: Predictive maintenance for vessels - 2

About customer

CHORD X was founded in 2019 and is based in Singapore. Chord X is a maritime data analytics company that focuses on the energy management of large maritime assets. The key to our solution is delivering predictive maintenance and insights to optimise the performance and energy consumption of fleets.

The Challenge

Chord X is on a journey to transform how shipping companies work with asset data onboard their vessels. Moving away from reactive responses to incidents or issues, Chord X uses machine learning techniques based on vast data sets from vessels to provide actionable insights, and move from reactive to predictive maintenance, and avoid breakdowns before they happen. Along with that spirit, Chord X wants to use independent variables identified through these techniques and apply them to emissions control levers, allowing ship owners, operators, and charterers to identify practices that will manage emissions down, in line with the industry goals

The Solution

Chord X, in collaboration with technology and solutions consulting firm Neurons lab, set up alternative models and algorithms to identify anomalies across different vessel types, and identified an ensemble of solutions to surface insights that allow early alerts and notifications to prevent failure modes.

In this collaboration with Neurons Lab, new models and algorithms were created that helped to reveal inefficiencies in the engine combustion process and generated new valuable insights into the possible root causes. These improvements also can be applied to reduce fuel consumption and emissions.

The Result


  • Rule-based and statistical models for root cause analysis of the fault analysis
  • Visualisations of the engine combustion process for insights generation


  • More advanced physics-derived feature sets for pressure curves analysis
  • Physics-aware deep learning models for more accurate fault detection