Unlocking savings and efficiencies in automotive manufacturing

When changes have threatened the automotive industry, it has always been able to innovate and respond. Now, car manufacturers are experiencing another seismic shift, with changing driver habits and growing pressure from consumers, governments, and other stakeholders to provide greener, more efficient, and more sustainable vehicles and ownership models.
These changes are driving a new era of automotive innovation, transforming the vehicles themselves, as well as the engineers, facilities, assets, and manufacturing processes that produce them.

One of the biggest challenges within the automotive sector is to drive ever-greater production efficiencies. Currently, the cost of downtime in the automotive industry exceeds $3.5m per hour. This reality is forcing operations and maintenance teams to ensure production equipment is as efficient and reliable as possible.

The nature of automotive manufacturing environments is becoming increasingly interconnected. Components and vehicles flow through the factory in an increasingly coordinated manner. This places more significant pressure on production managers and their engineering colleagues to minimize machine failures. When one production asset is offline, the impact is felt throughout the factory and directly impacts the bottom line.

Engineers and maintenance staff must view their production environments as vast, synchronized organisms of moving parts and components. Minimizing costly downtime and maximizing the efficiency of automotive production requires a real-time, factory-wide view of machine conditioning. It is no longer acceptable to focus merely on critical points of failure.

More frequent, manual checks of plant machinery have the potential to reduce the likelihood of failure. But this approach is also an expensive, inefficient means of solving the problem. The move to smart factories and predictive maintenance provides a solution to both problems. Offering the opportunity to unlock savings and improve operational efficiencies by ensuring that machinery is kept in good working order, without unnecessary and wasteful over-maintenance driven only through a planned maintenance approach. Predictive maintenance has existed for some time now as another way to increase planned maintenance efficiencies.

Traditionally expert data analysts will take manual readings relating to condition monitoring such as torque, rotational speed, and vibration from assets, and compare these findings with bespoke models for each monitored machine to identify known signs that indicate deteriorating condition.

While proven to be effective, only the most critical assets could be monitored this way due to the high cost of the workforce and the manually intensive nature of building failure models, taking readings, and comparing findings.

Senseye has advanced this practice forward rapidly with Senseye PdM, a specialized software powered by AI and machine learning that makes it possible to deliver predictive maintenance at scale.
Senseye PdM analyses data collected from industrial assets to identify and inform users ahead of the time when a piece of equipment is likely to fail. It is already being used to monitor thousands of assets in real-time across the globe.

Senseye PdM uses a series of standard algorithms that allow the immediate analysis of data from any instrumented machine, comparing data gathered against known faults from each asset and others like them. Crucially, these algorithms teach themselves to be more effective over time as they learn more about each machine's unique quirks and characteristics.

Senseye’s product capabilities allow automotive manufacturers to monitor all of their production assets. Maximizing the efficiency of plant and maintenance operations, and minimizes the chances of costly machine downtime.

Senseye helps clients achieve substantial savings by applying its technology to large-scale automotive production environments. We see levels of unplanned downtime halve once clients introduce Senseye PdM, maintenance costs fall by 40 percent, which translates into multi-millions savings, and productivity levels improve to the extent that individual sites are making 5,000 more cars per year than they were before.

The scalable nature of Senseye’s product means it can be applied to any asset range to reduce the strain for internal or outsourced maintenance teams. The savings achieved typically pay for the cost of introducing and using Senseye PdM within the first three months of deployment.

The pressure on automotive manufacturers is already changing the industry for the better, with ever cleaner and more efficient vehicles rolling off the production line daily. Senseye’s technology, as part of the broader smart factory movement, is playing a crucial role in transforming the productivity and sustainability of those production lines, as well as the people responsible for keeping them rolling.

Nissan Case Study CTA_1