Algorithm ahoy!

The shipping industry is under mounting regulatory pressure. For example, stringent environmental rules mandate continuous monitoring and documentation of vessel emissions. In this context, ships running on heavy fuel oil may be fitted with scrubbers to reduce the sulfur content of their exhaust gases. The efficiency of the scrubbers is then analyzed using continuous emissions monitoring systems (CEMS). These systems – such as the MARSIC analyzers from Endress+Hauser – work by measuring concentrations of the relevant pollutants in the engine exhaust gases before and after scrubbing. In short, the measurement values not only document the emissions released into the environment but also monitor the process efficiency of the scrubbers and catalytic converters themselves.

Should these monitoring systems go down, ship operators risk noncompliance because they can no longer prove adherence to the mandated limits. They may even face sanctions. In many cases, they simply don’t have the specialist personnel needed to undertake CEMS repairs at sea. But now this problem can be solved with a digital twin – in the event of sensor downtime, smart algorithms extrapolate the missing emissions and compliance status data from the available vessel and scrubber operating data. For this purpose, machine learning models analyze historical data to create a digital twin of the vessel’s on-board measurement system.