Guest Feature: Driving Operational Change with Data-Driven Analytics

Real-time reporting and data analysis are key tools to understanding and improving complex operating environments of today’s companies where the overall effects of any individual action can be very difficult to identify without a proper tool set at hand.

Identifying and continuously improving best practices are also best served by the same process which then allows shipowners and operators to see what’s happening underneath all the noise — to find what otherwise would be lost in the variance of the data.

In order to make operational improvements driven by data analysis and reporting, a systematic approach is needed that covers key areas which must be studied, analyzed, changed and constantly monitored in order to meet the desired outcome; efficient, cost-effective operations.

In the continuation of the article, Henrik Lano, Director of Analytics at Eniram, Finnish provider of energy management technology and data analytic services, elaborates on cost reduction and performance improvement.

The 5 steps of this systematic approach are to:

• Identify improvement areas: digging deep into the details to find the issue
• Understand the current situation: learning how operations/processes are created and linked
• Plan improvement actions: charting a course for reaching a desired target state
• Implement change: working the plan for continuous improvement practices
• Follow up and maintain change: ensuring the change benefits continue to materialize

When analysing a fleet’s performance in general or a focused area of operations, bringing the lowest performers to at least the level of average performers is often both the fastest and most effective action.

EXAMPLE 1: FLEET SPEED PROFILE PERFORMANCE

The following example is a study carried out by Eniram on two vessels. Each dot on the graph represents one leg that has been operated by the vessel and how much extra energy was used because of the speed profile and engine combinations. Both vessels operated on comparable schedules under similar conditions.

Problem identified: By using specific data-gathering processes via Eniram Platform on both vessels, it was determined that Vessel A had a tendency to sprint in the beginning of the leg, then loiter at the end, which naturally leads to lower overall speed profile performance.

Result: By identifying the vessel differences, it was possible to reduce the total fuel consumption of Vessel A by approximately 1% of the total fuel consumption. The visibility of the effects of the speed profile enabled the shipping company to take improvement actions on vessels where it was most needed.

Observation/recommendation: Further analysis can be used to find the real causes behind those differences. Planning improvement action, executing on that action and consistently following up is the only way to ensure a successful outcome.

EXAMPLE 2: BUNKERING MANAGEMENT CASE STUDY

In this example it was found that whether some of the vessels in their fleet were holding too much Heavy Fuel Oil (HFO) on board.

Problem identified: Again using the Eniram Platform, several analyses were performed on tank levels on these ships and found that despite consistent bunkering patterns in the same port and no major bunker price differences, many vessels were indeed holding an overage of HFO.

Result: The extra 1,000 tons of HFO on each vessel was eliminated; the difference of over 1000 tons of HFO onboard between the minimum levels means increased draft, and that there is an extra half a million USD tied in working capital on the vessel, which costs in total circa $100k each year per vessel depending on the type of vessels and company’s internal cost of capital.

Observation/recommendation: Simply by using in-depth reporting analysis, and performing follow-ups on tank levels through a regular report that aggregates data on the amount of fuel onboard, the company could easily track fuel levels. As a result, the levels of HFO were reduced closer to the company’s policy; showcasing how bringing this high-level of sophisticated data analytics can help to improve overall operations when these problems become visible.

EXAMPLE 3: ACTIVE ROUTE MANAGEMENT

Routing is a very traditional problem and also very complex with many factors affecting it such as weather, shallows, distance to the shore, currents and ECA zones.

When analyzing routing, quite often the most effective way to improve this within the fleet is to compare where the vessels are having the most problems and then create best practices for those legs which seem to be problematic.

In this case, the difference between the best and worst routes is over 12% of the total fuel consumption (a rare case). According to Eniram’s analytics studies, the overall average potential improvement of actively managing routes of a fleet is typically around 3% of the total fuel consumption.

Every operational issue is different and every company has different operating parameters.

However, according to Eniram, data analytics and reporting is an inexpensive way to find and realize quick wins in operational efficiency.

Source: Eniram