In its 2015 report Unlocking the potential of the Internet of Things the McKinsey Global Institute estimated there could be more than $US360 billion ($A470.76 billion) a year in benefits could be delivered across all industries in improved equipment maintenance alone.

"Using sensors to monitor the health of machinery in use, companies can shift to a condition-based maintenance model - maintaining equipment when there is an actual need rather than relying on a regular maintenance schedule or repairing equipment only when it breaks down," McKinsey said.

Woodside has been an industry leader in this area, extending its relationship with Accenture last September using predictive analytics for maintenance and process control in production operations across its LNG assets, starting with Pluto.

Prime example

Woodside chief technology officer Shaun Gregory told the Amazon Web Services Summit in Sydney in April that when it started up the $10 billion Pluto LNG plant in 2012 it was equipped with some 200,000 sensors that monitored operations including temperature and pressure.

Then, in 2014, Woodside undertook a project to assess the potential of harnessing information from a subset of those sensors to improve the Pluto's operation, using cloud-based services to crunch the data.

The subject of the project was the plant's acid gas removal unit, which would periodically experience foaming, which Gregory said was akin to pouring beer too quickly into a glass.

He said foaming was capable of shutting down the plant for weeks or months at a time and was tough to detect as the AGRU is enclosed.

Working with data scientists, information from 10,000 of Pluto's sensors and 30 years of operating experience, Woodside developed a model that that would not only detect forming but could produce a two-hour, 72-hour and up to a one-week forecast of when foaming might occur.

The project took just six weeks.

"This had a dramatic impact on the culture of our organisation, because we were used to technology evolving in many, many years," Gregory said.

"Now it was evolving in weeks."

Last month senior Woodside employees were consulted by Perth-based "start-up studio" Atomic Sky on business modelling, rapid prototyping and design thinking techniques at an "ideation" session with Cisco and Curtin University staff to come up with ideas to implement at the "Internet of Everything" centre.

Lack of faith

Despite these benefits, IFS global director for oil and gas Knut Moystad said there was still a level of scepticism in the value of predictive maintenance, rooted in the lack of proper metrics to measure it.

While Woodside has shown leadership in this area, Moystad told Energy News that IFS focused more on the oil and gas service industry, and has an early adopter program in place at the offshore drilling, FPSO, seismic and offshore support vehicle industries.

"In these industries, predictive maintenance is still in early days and we assist clients in determining the right strategies to capture value from this area," Moystad said.

He said that three of what he believes to be the top five barriers to maximising the benefits were beatable.

Of these he believes technology (such as the cost of installing radio-frequency ID tags), interoperability and intellectual property barriers "can be solved when you put your mind to it".

Security and compliance and organisation of talent, including the available resource pool, onsite staff and the planning/engineering department of any given organisation are more difficult obstacles.

Yet even then, "with the right attention", Moystad is confident regulators and classification societies will listen and develop along with the companies seeking the benefits.

He said the organisation and talent element could be the trickiest to overcome because changing the framework and work practices for such a critical domain as maintenance may be tougher to drive from the bottom up.

"A strong leadership is therefore needed to drive changes and motivate the company in a new direction," he said.

"So, even if the value of predictive maintenance in some instances is still regarded with disbelief and the barriers preventing change seem high, we do seem to be at the point where we should start to act."