Marker.io integration Marker.io integration END

Increasing fuel efficiency for a global mining company

A global mining company wanted to optimize operational costs by reducing fuel consumption for each vehicle across its fleet.

Challenge

In the current climate of low commodity prices, many mining companies are under increasing pressure to reduce operating costs. This is also exacerbated by growing fuel costs - some of which contribute to ~30% of total operating costs.

The most obvious way to cut costs on fuel is to look for price reductions, but with the competitive nature of supplying to mines there is very little margin left to “squeeze” out of the suppliers.

A global mining company wanted to reduce operating costs, and identified fuel consumption as the primary driver. It wanted to reduce fuel consumption for each vehicle across its fleet. Past analytics attempts made by the client to improve fuel consumption were siloed, and did not lead to actions.

Forward-thinking decision makers were urgently looking for tangible quantified insights that could directly translate into operational improvement.

SparkBeyond Discovery's Root Cause Analysis technology helps identify the root causes in operational fluctuations - the hidden drivers of breakdowns and slowdowns - providing the ability to react in real time: not only to the symptoms, but to the underlying issues.

Approach

The company used SparkBeyond Discovery to integrate “never-before connected data sets” such as tire pressure, refueling data, fuel & oil quality, road quality and gradient to deliver insights on how to increase efficiency. 

By combining these diverse internal datasets (IoT data, fleet management system, maintenance logs) and external datasets (Wikipedia, weather), the platform created a ‘digital twin’ of each vehicle in the fleet. 

The platform evaluated millions of hypotheses on real-time data, surfacing significant drivers of fluctuations in reliability metrics. This uncovered 300 predictors of fuel consumption, and was used to drive behavioural change management at the site. 

Result

Within one hour of runtime, multiple actionable opportunities were generated, including: 

• Interventions and planning 
• Visualization of fuel consumption under recommended speed and payload utilization  
• The positive impact of certain maintenance activities on fuel efficiency and consumption 

Using AI-powered root-cause analysis, the company reduced fuel consumption by 10% in the first 4 months.

Fuel contributes to 30% of overall operating costs of the site. This 10% reduction translates into a 3% reduction in variable costs, giving the client a competitive advantage.

What's more, fuel consumption dropped by ~20K liters per day, thus having a positive impact on the environment

Features

No items found.
No items found.

It was easier in this project since we used this outpout

Business Insights

Apply key dataset transformations through no/low-code workflows to clean, prep, and scope your datasets as needed for analysis

Predictive Models

Apply key dataset transformations through no/low-code workflows to clean, prep, and scope your datasets as needed for analysis

Micro-Segments

Apply key dataset transformations through no/low-code workflows to clean, prep, and scope your datasets as needed for analysis

Features For
External Models

Apply key dataset transformations through no/low-code workflows to clean, prep, and scope your datasets as needed for analysis

Business Automation
Rules

Apply key dataset transformations through no/low-code workflows to clean, prep, and scope your datasets as needed for analysis

Root-Cause
Analysis

Apply key dataset transformations through no/low-code workflows to clean, prep, and scope your datasets as needed for analysis

Join our event about this topic today.

Learn all about the SparkBeyond mission and product vision.

RVSP
Arrow