As businesses increasingly turn to big data and automation to streamline their operations, companies are now competing on what were once considered “minor” details—auxiliary business processes like inventory control, maintenance management, and people management.
So what if your competitor achieves 15% less downtime than your organization? Well, not only are they saving hundreds of thousands of dollars in maintenance costs each year, but they’re producing more of your product and most likely worming their way into your market share. Remember: if you’re not keeping up, you’re falling behind.
Even if New Year’s resolutions went out of vogue during the pandemic, 2022’s arrival is still a welcome opportunity to reassess what you’ve been doing and prepare for the year ahead. Here’s what you need to know about the latest, most exciting trends in maintenance management to keep your business on the cutting edge.
1. Sensor technology will give everyone superpowers
IoT sensors have changed the game, enabling maintenance teams to remotely monitor machinery. By automating the process of collecting maintenance data, such as mean time between failures (MTBF) and asset life cycle, facilities can establish preventive maintenance and predictive maintenance programs that grow more accurate over time as the system accumulates more data. While many forms of industrial sensing exist— including pressure, position, temperature, and speed—vibration sensing is still the most common.
Vibration analysis is used in rotating machinery to detect loose or worn bearings, equipment misalignment, or low fluid levels, all of which manifest as changes in vibration (normal vibration occurs at frequencies between 6-10 kHz). Using sensors to anticipate machine failure can save companies millions of dollars. Parts that cost a few dollars can cost manufacturers many times that in repairs and lost revenue when they fail.
In 2020, Forrester predicted that companies that already used sensors on 25% of their machinery would increase their use by four-fold through 2023.
2. Decentralized repair teams? Yes, please!
With sensing technology at their fingertips, companies are reconsidering whether to keep an onsite maintenance staff for each facility. Open networks of repair logs and real-time machine data enable managers to keep tabs on productivity in real-time, which enables them to quickly deploy remote maintenance teams to different facilities in the event of an emergency.
Some organizations are experimenting with decentralized maintenance management— that is, turning maintenance management into a shared responsibility among all personnel rather than the sole purview of the maintenance technicians. Instilling a culture of autonomous maintenance means involves charging machine operators with minor maintenance tasks such as cleaning equipment and checking the oil. This is done by empowering workers to take ownership over their workstations and the equipment they use.
Decentralized maintenance is ideal for large organizations that operate multiple facilities. Dispersing authority throughout the organization shortens the approval process and enables maintenance teams to execute faster.
3. You'll get a lot of s**t about downtime and inventory management if you don't do it right
With the mainstreaming of CMMS and other maintenance management software solutions, extensive unscheduled downtime and poor inventory control are no longer acceptable. A new report from Industrial IT predicts that the global CMMS software market will reach $1913.1 million by 2028, growing at a CAGR of 10% over the analysis period. Now that facilities can easily track parts inventory and availability using software, more manufacturers will focus on mitigating inefficiency in their current storeroom.
Companies know that reducing unplanned downtime yields major cost savings—thereby creating a competitive advantage. Estimates show that downtime costs industrial manufacturers $50 billion a year. Between 2015 and 2019, oil and gas companies involved in exploration and production spent an average of $80 billion a year on maintenance. With increased competition, businesses need to become more agile. Aside from technology use, practices like autonomous maintenance (training machine operators to perform minor maintenance tasks) will be key to reducing unscheduled downtime.
4. AR and VR are making a (real) impact
It’s no longer just hype. Augmented reality (AR) has real capabilities as both a training and productivity tool for maintenance management. AR enhances the user’s environment by superimposing a layer of virtual information over their field of view. VR, on the other hand, places the viewer in a fully immersive virtual environment. This technology enables maintenance workers to practice complex or infrequent jobs in a safe environment. Maintenance managers can also use AR to provide remote training for technicians. While VR is still useful for training purposes, unlike AR it cannot be used to perform maintenance tasks in real-time.
Picture this: while repairing a hydraulic pump on an assembly line, the technician can see step-by-step instructions on how to perform the repair virtually overlaid on a smartphone or while wearing AR glasses. Used in conjunction with IoT machine sensors, the AR platform can provide real-time information on pump pressure, temperatures, and other critical data.
A recent report from the Industrial Data Corporation (IDC) predicts that by 2023, the commercial use cases of AR/VR that are forecast to receive the two largest investments are training ($8.5 billion) and industrial maintenance ($4.3 billion).
5. AI is taking over the world! (Kind of, not really)
AI-powered CMMS solutions can automate repetitive jobs and maintenance planning. It can identify maintenance requirements, prioritize and adjust schedules to ensure the right person is assigned to the right task. A study by Manufacturing Business Technology stated that predictive maintenance using AI can save companies over $630 billion in costs over the next 15 years. Why? Because the default M.O. doesn’t work. A Boeing study suggests that 85% of equipment fails unexpectedly despite calendar-based maintenance.
AI uses data to do continuous monitoring, which involves both the failure system and the anomaly system. The failure system reads data patterns that indicate and predict operation failure so that the system learns the symptoms and indications of failure over time. On the other hand, an anomaly system reads data as deviations from the normal routine operations. Unlike failure systems, it picks up variations from normal patterns. Combined, this data gives us a fairly accurate readout on operational processes.