Dynamic fuel reconciliation & delivery variance modelling

Location: Carrum Downs, VIC

Duration: 4-5 months

Keywords: Data science analysis, programming, modelling, charting, presenting

Project Background

Environmental Monitoring Solutions Pty. Ltd. has been specialising in Wetstock Management (SIR Leak Detection and Real-time Fuel Data analytics) and Forecourt Automation (Automatic Tank Gauging, Submersible Turbine Pumps) for the past 25 years. 100% Australian owned and operated, the company focuses on a team-based approach to its commercial products and delivery to leverage its technology and service expertise in petroleum storage systems solutions.

Over this time, EMS has developed our own intellectual property to deliver high value, certified Greenscan SIR Leak Detection services, complemented by Fuelsuite our remote monitoring and 24/7 support service that keeps our clients sites operational around the clock, whilst reducing environmental exposure and lowering maintenance budgets.

Wetstock management and specifically leak detection at fuel storage facilities is critical for protection of the environment, reducing occupational health and safety risk to site employees and the general public, and for maintaining effective business management processes for the owner.

Monitoring fuel losses at service stations is influenced by many external factors, which can be difficult to predict. The diverse and often unstable weather conditions across Australia, the differences in fuel composition from the various suppliers, the inaccuracies in measurement equipment on site and a lack of information such as tank diameter, in-tank temperature etc. can often make identifying and quantifying losses very difficult.

With a plan to go global, EMS would like to collaborate with a PhD student with expertise and an interest in mathematics/statistics/physics to develop a hose meter to tank mapping algorithm to correlate metered sales to a hose in the correct tank and product to establish the relationship of meters to tanks. This is called meter-to-tank map.

This then establishes the correct basis for dynamic fuel reconciliation where every hose meter transaction is tested against in-tank level/volume/temp movement.

Research to be Conducted

The objectives EMS would like to achieve through the internship are as follows;

  1. Develop a meter-to-tank mapping algorithm that supports up to 64 fueling positions with up to five meters per fueling position.
  2. Develop a variance algorithm to compare tanker dispatch tickets [ticketed delivery] to in-tank detected delivery to accurately assess and report on variance.
  3. Big Data modelling concepts. With access to voluminous data, there is an opportunity to ‘explore’ the data to look for and unlock interesting patterns and correlations for the purpose of leading conceptual product development.

The project will have access to 18+ months’ worth of data from service stations across all temperature regions/zones within Australia. This data will include a mixture of basic daily data measured manually using a dipstick and highly granular data measured every 30 minutes via an Automatic Tank Gauge (includes in-tank fuel temperature readings).

Skills Required

  • Experience in data science analysis
  • Programming skills
  • Experience in modelling, charting
  • Able to present finding to various stakeholders
  • Able to work within a multidisciplinary team

Expected Outcomes

The expected outcomes of the project include a feasibility report detailing;

  1. The models to be used to achieve the three objectives with supporting proofs
  2. A recommendation on whether each model should be integrated into existing IP or be developed separately as a stand-alone application
  3. Guidelines on how to best interpret/use the results from the three models

Additional Details

The intern will receive $3,000 per month of the internship, usually in the form of stipend payments.

It is expected that the intern will primarily undertake this research project during regular business hours, spending at least 80% of their time on-site with the industry partner. The intern will be expected to maintain contact with their academic mentor throughout the internship either through face-to-face or phone meetings as appropriate.

The intern and their academic mentor will have the opportunity to negotiate the project’s scope, milestones and timeline during the project planning stage.

To participate in the AMSI Intern program, all applicants must satisfy the following criteria:

  • Be a PhD student currently enrolled at an Australian university
  • PhD candidature must be confirmed.
  • Applicants must have the written approval of their Principal Supervisor to undertake the internship. This approval must be submitted at the time of application via the standard form available on the AMSI Intern website during the application process.
  • Internships are also subject to any requirements stipulated by the student’s and the academic mentor’s university.
Applications Close

23 October 2017

INT – 0346