An occasional series of vendor perspectives on the world of connected business – because it’s all about making new connections and starting new conversations.
Despite huge advances, the Industrial Internet of Things (IIoT) is still in its adolescence. Between advanced analytics, big data, edge computing, and the cloud, we have a good idea of what the factory of the future will look like, and how far manufacturers need to go to complete their transformational journey to Industry 4.0.
Yet one place where all of these advances are coming together to reduce costs and increase efficiency is predictive maintenance. Machines on the factory shop floor can now monitor and evaluate their own performance – and even order their own replacement parts when necessary.
By implementing predictive maintenance, manufacturers can improve safety, reduce downtime, and extend equipment life.
The case for evolving maintenance
Manufacturers have a huge incentive to improve the efficiency and effectiveness of equipment maintenance. Poor maintenance can reduce a plant’s productivity by 5-20 percent, while unplanned downtime costs US manufacturers an estimated $50 billion each year.
Fewer interruptions in production also mean more reliable product delivery, helping to keep customers loyal. This higher customer retention can then lead to increase revenue.
Previously, manufacturers used preventive maintenance or servicing equipment based on expected wear and tear to prevent breakdowns. Predictive maintenance is significantly more efficient than preventive maintenance, because corrective action is much more closely linked to the actual condition of the machinery.
The goal is not to replace a part too early, when it’s still in good condition, but instead only to service equipment when it’s really necessary. It’s like bringing your car in for service based on fluid levels or belt thickness, rather than mileage.
By minimising both unnecessary maintenance and downtime, there is huge potential for cost savings. Predictive maintenance costs manufacturers an average of $9 per hour, while preventive maintenance costs $13 (44 percent more).
Data-fuelled predictive maintenance
Advanced techniques, including infrared thermal imaging, vibration analysis, and oil analysis, and can be used to predict failures. As a rule of thumb, 70 percent of machine-specific malfunctions can be predicted by using sensors to monitor and collect machine data, and then using analytics to determine when equipment failures might occur.
When administrative procedures related to ordering and installing new parts are triggered automatically, cost savings can also be experienced in the back office.
For example, a machine could sense that a drill bit is wearing out and automatically order a new one, alert the technical service department to send a field service representative, and forward the purchase request for a new part to the ERP system. By automating manual, error-prone, labour-intensive administrative functions in this way, manufacturers can ensure greater efficiency.
However, connecting the shop floor with the back office isn’t always easy. The machines used in existing business processes will likely generate data, but the challenge is in accessing and evaluating this information. Data streams from production plants need to be integrated into company applications.
Machines, devices, sensors, and people need to connect and communicate with one another seamlessly. There also often needs to be a virtual copy of physical operations (a digital twin) in order to make sense of all the data and conceptualise the information.
Technologies such as artificial intelligence also may need to be deployed to support decision making and problem solving, making cyber systems as autonomous as possible.
There are also specific hurdles that need to be overcome. Manufacturers’ proprietary information will likely need to be kept private, using data filtering, with additional security measures to protect financial and customer data from hackers.
Most importantly, any data management platform needs scalability to collect, filter, process, and share huge volumes of data with a very high level of performance and reliability.
The factory of the future
When machine data can be used to perform predictive maintenance with a high level of precision, manufacturers can focus on differentiating products using digital capabilities like self-awareness of technical health.
A manufacturer’s value can be measured not only by the quality of its shop floor processes, but also by how it protects its assets. This can be achieved by using predictive maintenance to extend equipment life and improve the efficiency of maintenance procedures.
Predictive maintenance is an essential part of the factory of the future. Manufacturers who automate not only manufacturing processes, but also equipment maintenance, can benefit from a whole new level of production efficiency.
Internet of Business says: This opinion piece has been provided by Magic Software, and not by our independent editorial team.
First published in Internet of Business
Learn more about Magic xpi Integration Platform