As industry buzzwords, “Big Data” is one of those phrases that has become seemingly ubiquitous. Everyone wants to be using big data to better their operation. The maintenance department is no exception to this trend.
Accordingly, maintenance teams are beginning to embrace the use of big data and analytics to improve performance. In emphasizing the use of “big data”, maintenance can establish predictive maintenance programs, which reduce downtime and save on maintenance costs. They can also extend the life of their equipment, reduce unnecessary preventive maintenance tasks, and optimize their spare part inventory.
Let’s explore how this looks like in practice.
Predictive Maintenance
A natural extension of big data in maintenance is a predictive maintenance. By using machine data along with other area data, the operation can truly understand the health and performance of its machines. This is done by installing sensors and utilizing the data to model the equipment performance. Once a model is established, the operation can use real-time data to predict when the machine will see a breakdown.
Obviously, this information is very valuable. With the ability to perceive a future event, the manufacturing line can appropriately plan a response. No more scrambling by the maintenance, operations, and supply chain teams – saving tons of time and hassle for all parties.
A key to an effective predictive maintenance strategy is the use of a CMMS for planning and tracking of maintenance events. And with software tools, the data from the assets can be fed directly into the CMMS or used to automate work orders.
A predictive maintenance program not only saves money, it reduces risk and, in some cases, even can save lives by avoiding catastrophic failures of critical equipment.
Longer Life of Assets
Replacing before breakdown is not the only outcome of data analytics. Advanced data can be used to better understand how to extend the life of the current asset in service. What are the common failure modes, and how can they be mitigated? This information can be very valuable.
For example, Valmet is using big data to prolong roll life in paper manufacturing operations. In doing so they have extended roll life by 20%. This not only saves money in replacement cost, but it reduces downtime because there is less changeover time.
PM Optimization
As data is gathered on the equipment health, a better understanding is gained on the activities needed to keep them running efficiently. With this information, the maintenance team can start to optimize its preventive maintenance activities.
Many in manufacturing have seen the rush to add PM activities as a precaution against breakdowns. As more and more PMs are added, the maintenance technicians eventually become overburdened with too many unnecessary jobs. This type of inclination wastes manpower on frivolous activity, wasting company money in the process.
Since predictive maintenance programs rely on real time conditions of the equipment, these PMs can be cut down tremendously. The maintenance staff can focus on addressing the most important needs. They can also work on root cause analysis and thus increase reliability of the equipment.
Spare Parts
Spare part inventories are often managed by use date. If a factory hasn’t used a spare part in a long period of time, they question whether they should continue to stock it. This line of thinking misses many subtleties, such as the lead time of the spare part from the manufacturer, the criticality of the asset, the cost of the part, and so on.
When using bug data analytics in maintenance, the parts stocker can use data to weigh all these factors. It is no longer a process of eliminating inventory by date, which may miss critical information and harm the business.
Some maintenance departments have even begun 3D printing of parts onsite. This allows for additional flexibility in maintaining inventory. Often the cost for printing a part is much lower than traditional manufacturing methods (in one case, from $3000 to $3). So not only does the part have a smaller lead time, it is also cheaper.
Conclusion
The role of big data is growing in maintenance, and this trend is improving the way that the maintenance team works. The movement toward data analytics is increasing the effectiveness of the maintenance department, and in turn improving the uptime of operation.
Using big data can lead to longer equipment life, reduction of unnecessary PMs, and a decrease in spare part inventories. All these benefits lead to a happier, more productive workforce, driving even more value out of the programs.