Senex’s success with Machine Learning and predictive maintenance

Betfair Logo

Senex is an established and growing Australian natural gas producer, providing gas for industries that support local communities, manufacturing, jobs and a cleaner energy future. Senex’s primary focus is on developing further opportunities to expand production, earnings and cash flow while balancing commitments around safety, environment, community and sustainability.

Betfair Main Image

At a Glance

Like many organisations in the mining and energy sector, Senex has many data assets scattered across many sites and servers.

A strategic review provided requirements for a new data & analytics operating model, leveraging the cloud to bring data together and scale data capabilities without traditional constraints.

Servian with Google Cloud responded to and won a tender to help Senex build out their platform.

The Challenge

The first delivery phase of this program of work established the Google Cloud environment for Senex and focused on some key, prioritised use cases.

The most promising use case focused on moving a torque spike model, which helps predict failures and faults, which has the potential for a significant impact on both the business and Senex’s bottom line.

A Torque spike is a strong predictor of pump failure. A torque spike means the pump is suddenly working harder, which could be because of solids contaminating the outputs or some other cause. The pumps are costly to run and replace, taking a forego of sales whilst the wells are offline.

The Solution

Servian, working in conjunction with Senex resources and supported by Google Cloud, rapidly took an existing model and re-deployed it to Google Cloud, with some refactoring to help it leverage cloud capabilities.

The new Google Cloud data platform hosts a Torque Spike ML model that uses key SCADA measures (from sensors at the wells) to identify wells at risk of torque spikes. A data pipeline ingests live data from SCADA Historian application data into Google BigQuery tables – which then is the source for the Tensorflow Machine Learning model to predict torque events for each window of 15-minute data. A front end application (hosted in a VM on Google Cloud) visualises the raw data. It predicts torque events in several ways, allowing engineers to quickly identify torque events and diagnose underlying causes associated with a particular torque event.

The Benefits

Scalable, Secure, Serverless

Increased loading and prevention of maintenance costs

Servian ‘s GCP data platform has made it possible to run all wells every 15 minutes, which was not feasible previously. Reducing expensive pump failure and maintenance spend. 

Metadata Driven ETL

Optimised to reduce future torque spikes

Servian provided Senex with a Pipeline approach that allows adjustments in usage and/or maintenance to avoid torque spikes. Meaning the will be fewer pump failures during busy times. 

The Result

This enablement is a significant improvement compared to the previous torque model implementation. Running the model on Google Cloud has enabled the model to run across all of Senex’s wells. 

Previously the model could only work for a small number of wells and could not cope with live SCADA data. More importantly, the resolution of the torque spike ML model improves from 60 minutes to 15 minutes when the model is running on Google Cloud. This solution is crucial for Senex to promptly identify and respond to torque spike events to minimise any impact on their production line. 

Learn more about what Servian can do for you

Get in contact with our team to explore new opportunities

Why Servian

We drive a competitive advantage for our customers by enabling them to become truly data driven. We help organisations design and implement robust enterprise data management strategies and data platforms that ensure the security, accuracy, and reliability of their data. Our services in data and analytics span across advisory, consulting and managed services.

Book a free consultation to learn more