Clemens Weis and Christoph Schmierer discuss predictive maintenance and new manufacturing business models

When machines fail unexpectedly, British businesses foot a bill running to a staggering £180bn a year. This can vary from a few thousand pounds in the fast-moving consumer goods industry up to millions of pounds in the automotive sector.

In the hope to reduce the impact of unexpected stoppages, we turn to big data; nobody really understood how radically it would change the way we produce things. However, using big data to predict when, where, and even how a tool may malfunction can make a major impact to a business’s bottom line – that’s why predictive maintenance is the next big thing.

For manufacturing, we need data to help us predict when a machine or tool needs extra attention before it stops performing as expected. It allows operators to plan maintenance during scheduled downtime, before a real problem occurs. This lowers the costs of maintenance but also increases the overall equipment effectiveness. In addition to increasing efficiency, big data has the ability to re-write business models when it’s used to its full potential. It’s enabling a paradigm shift in the way we manufacture in a variety of industries.

Saving costs in production
The combination of historical and real-time big data feeds into predictive analytics and results in forecasting models that are able to predict when a machine will likely fail, or when it no longer produces the optimum quality output. By calculating a machine or tool’s useful life, companies are able to better plan their maintenance budgets and production schedules in advance. It is hugely beneficial to them to be able to predict and prevent machine failure to minimise unplanned downtime.

On top of preventing loss of production capacity, companies can also mitigate costs of faulty produced items.

The use of predictive maintenance allows businesses to save money in two important ways:

    1. Industrie Reply estimates that shifting the focus from fixed service intervals to service times based on predictive maintenance can reduce maintenance costs by between ten to 40 per cent. Furthermore, it’s estimated that prouctivity improves by between 45 to 55 per cent using predictive maintenance programmes. Finally, it is estimated to improve precision of maintenance procedures by up to 85 per cent.
    2. It foresees potential downtime and avoids unexpected machine outages, which allows maintenance work to take place ahead of time. With reduced unplanned machine outages, the overall equipment effectiveness is increased by between 30 to 50 per cent.

Even though cost saving initiatives are always appealing, achieving these results have actually been costly in the past – making the necessary investment in digital analytics tools in particular. However, over the last years, operating costs have reduced drastically. The majority of manufacturing machines today are already equipped with the required sensors to perform predictive maintenance tasks. We no longer need to retrofit sensors, which is very costly. Moreover, the costs of data storage and data processing has drastically reduced over the years. Easy-to-use forecasting models are now readily available to businesses, meaning they no longer have to rely on highly trained, and expensive, service technicians with specialist statistical knowledge.

Costs of development have also dropped significantly in the last few years. Consultants can now make use of pre-trained machine learning models, based on many years‘ experience with similar or identical machines, such as drives, pumps and components.

In addition, predictive maintenance models can now be operational much faster than before, allowing businesses to achieve a faster return on investment.

Improved services
On top of the previously mentioned benefits, predictive maintenance can have more positive effects on businesses. By offering predictive maintenance as part of the digitial services portfolio, mechanical engineers can decrease machine outages, while simultaneously optimising the required maintenance work.

Improving the service offering has a range of other noticeable benefits; given that the interaction increases, customer loyalty is likely to improve. The interaction opportunities between mechanical engineers and customers is even expected to drastically increase, specifically in the durable capital goods industry.

Predictive maintenance also allows engineers to provide a better quality of service – resource planning is enhanced and maintenance dates determined and agreed upon well ahead of time. This will also allows for stock levels to significantly decrease as parts are only ordered when they are needed. This frees up storage space for other, potentially revenue generating, items.

Shifting service models
Predictive maintenance is a driving force for new service models such as ‘Power by the Hour’, where businesses can, for example, predict the provision of tools per hour and the output quantity of different machines per hour. Customers can avoid high investment costs as this allows them to only pay for the services they need and use. On the other hand, suppliers of machinery experience fewer unexpected machine outage times while at the same time minimising negative effects to their income streams. Additionally, it allows after-sales teams to provide extra services to clients by including predictive-maintenance-as-a-service (PMaaS) for machines to their portfolio.

In short, companies with predictive maintenance are able to be far more proactive and react to not only their own needs, but also the needs of their clients. Maintenance is less costly and results in less downtime. This all contributes to improved client relationships as direct contact is more frequent and services will be more tailor-made and timely.

Big data brings new capabilities and opportunities. The future looks bright as we move into a new era of productivity for manufacturers and improved relationship-building between manufacturers, their suppliers and their customers.

Clemens Weis & Christoph Schmierer
Clemens Weis is Partner, Industrie Reply, and Christoph Schmierer is Manager, Industrie Reply. Industrie Reply, a Reply Group company, orchestrates innovation for industrial customers. It brings significant experience in leading edge technologies, which enable companies to transition from a traditional company to an Industrie 4.0 company.