Simon Jesenko , Senseye's CFO, looks at how an effective maintenance programme can hold the key to cash conservation for manufacturers.
With margins squeezed tighter than ever before, and the need to meet ever-changing customer demands, manufacturers the world over are finding themselves under pressure to cut costs and conserve cash, particularly in light of the uncertainty that the global pandemic has brought. Many will be looking to minimize capital expenditure, and are therefore looking to extend the lifespan of existing assets.
With this in mind, one area that’s vital for ensuring efficiencies, both in terms of cost and performance, is equipment maintenance, with even just an hour of downtime potentially costing manufacturers up to $3.5 million in lost production. Add to this that more and more manufacturers are now subject to penalties from customers if they don’t deliver on time and in full, and it’s abundantly clear that equipment must be working at optimum levels of efficiency at all times.
But striking the right balance between necessary maintenance and excessive maintenance is easier said than done. Efforts to be ultra-efficient when it comes to comprehensive maintenance programmes can be undermined by under-utilized maintenance teams, excess downtime, and unnecessary stock and inventory, all of which rack up unnecessary costs. In light of this, more businesses are attempting to implement Predictive Maintenance (PdM) as a strategy, an approach that is proving so successful that the global PdM market is set to grow to $6.3 billion by 2022.
Predictive Maintenance enables a move away from corrective and interval-based maintenance, by capturing and analyzing the huge amounts of data that manufacturing equipment generates to build up an accurate picture of the performance and condition of assets. It’s possible to identify looming faults and take the necessary action before it impacts on production, highlighting any inefficiencies and pinpointing where maintenance needs to be carried out. This allows maintenance activities to be performed at optimal times, minimizing downtime and causing minimal disruption to operations, boosting uptime, increasing customer satisfaction and maximizing the longevity of your assets, all of which have a dramatic effect on keeping costs to a minimum.
But, while the potential cost savings are well documented, one of the things that often stands in the way of implementing PdM is existing infrastructure. This is particularly true for those manufacturers who have invested heavily in traditional Enterprise Asset Management (EAM) or maintenance systems and are loath to abandon these investments altogether.
Utilize your assets
However, solutions such as Senseye PdM, adapt and enhance existing maintenance arrangements, leveraging prior investments to provide a robust PdM function while underpinning valuable cost savings. This means you can utilize incumbent systems, as well as analyzing data that’s already been collected and making use of maintenance teams already in place, to hit the ground-running with a maintenance programme that doesn’t involve long lead times and a disappointing ROI that can be years in the making.
The speed of achieving ROI is enhanced too, with solutions deployed in the cloud quickening the pace of implementation massively, not to mention the cost savings that come from not having to invest in additional hardware. Such is the speed and ease of deployment that such solutions such as Senseye PdM are able to provide detailed asset performance information within 14 days, ready to underpin an effective, efficient and optimal PdM programme and speeding up that vital ROI even more.
With the right solution in place, manufacturers can scale and focus their maintenance activities often without the need for additional resources. It’s no longer the case of having to start from scratch when it comes to PdM. With the ability to make use of valuable information, assets and people the cornerstone of the most effective preventative maintenance strategies. The targeted application of AI and machine learning derives optimum levels of value from a manufacturer’s existing assets, focusing on those which need the most attention in line with the strategic priorities of the business. For manufacturers in particular, this serves to transform the core function of maintenance from an often expensive cost center into a valuable method of cash conservation.