Embracing IIoT’s potential for maintenance
Companies can and should embrace and apply critical aspects of IIoT, including machine learning, analytics, and mobility.
The Industrial Internet of Things (IIoT) and the concept of IIoT for Maintenance are popular buzzwords in the maintenance world today. But what do they mean, and how can these concepts benefit maintenance professionals attempting to meet production demands, increase productivity and boost the bottom line?
The IIoT story has evolved far beyond what it was when it was first introduced to me 15 years ago. In the early days, there was reluctance from upper management to embrace IIoT. Today, leveraging cloud technology is becoming a requirement. Cloud-based systems and IIoT enable companies to buy the best-of-breed solutions without turning the information technology department upside down. Companies today can embrace and apply critical aspects of IIoT, including machine learning, analytics, and mobility.
Machine learning is a type of artificial intelligence that provides computers with the ability to learn patterns and trends without specific programming. Machine learning focuses on the development of programs that change when exposed to new data. For maintenance professionals, these programs can mean changes in preventive (PM) or predictive (PdM) maintenance schedules based on equipment condition.
It is not critical how information is imported into a system such as a computerized maintenance management system (CMMS). My experiences with the evolution of CMMS and mobility have shown that even with manual methods, machine learning can result in establishing procedures to address planning pitfalls, better inventory control, stronger PM practices and maintenance discipline.
Information on all assets, labor, and work management is readily available with the ability to connect CMMS and tools. More specifically, through advanced analytics, maintenance professionals can interpret data from multiple sources (including structured and unstructured data) into a wide variety of operational and asset management systems. This analysis provides a deep and wide perspective, exposing conditions not normally evaluated.
An example would be to understand the environmental status of an asset when it begins to fail, and then when it does fail. This deeper and wider view may shed light on contributing factors not previously considered. With this data, it is easier to make predictions on what may happen. Companies are analyzing the performance of equipment yesterday and today to predict what will happen tomorrow. With the power of IIoT analytics:
- Manufacturers can prevent vehicle breakdowns and notify drivers, or predict outages in the assembly line process
- Oil and gas companies can develop optimized maintenance schedules for critical assets
- Facilities can predict outages in power generation equipment.
In today’s industrial world, smartphones and laptops are more prevalent than desktops. Mobility is tied to most things in our world, and can help provide a cost-effective method to leverage IIoT. The power of mobile technology can turn machine learning and analytics into action by feeding the data directly from a piece of equipment to a handheld device.
Smartphones and tablets help make a wealth of data available, including asset history for critical equipment to influence future decisions.
By correlating historical trends and current conditions as they occur, companies can detect faults and increase equipment uptime. Standard operating procedures for equipment repair can also be accessed on a smartphone, reducing the rate of failure due to manual error.
For maintenance professionals, this means that where your company is today might not be so far away from where you can be tomorrow. The tools for getting started integrating IIoT are available today.
Kevin Clark is director of global service and alliances for Fluke Corp.
See additional stories from the Plant Engineering May 2017 cover story below.