By: Abhishek Jadhav, Industrial IOT Business Development Manager; Sensata Technologies
Unplanned downtime represents one of the major challenges facing factory and building operators worldwide.
Industry data shows that the average number of downtimes per year for a factory is 144, and the average annual cost of unplanned standstills for a factory is $2.3 million. In some industries — such as automotive — those costs are even higher, with losses of tens of thousands of dollars per minute of unplanned downtime.
There are other challenges, too: 32% of billion-dollar manufacturers estimate that they will lose over $100 million as the Baby Boomer generation retires over the next five years. Almost 25% of the U.S. manufacturing workforce is over the age of 55, and by 2030, there could be up to 2.1 million unfilled jobs in the sector due to a growing skills gap. A full 74% of firms predict a shortfall of qualified skilled trade workers, according to a survey from the Associated General Contractors of America.
On several fronts, plant managers are being asked to do more with less — making the ongoing maintenance of their equipment assets a constant challenge.
Legacy Maintenance Approaches Create Stubborn, Inefficient Processes
There are four core maintenance strategies generally practiced. The first one is called Reactive Maintenance, also known as "Fix it when it fails" or "Run to failure." The overall maintenance cost for this strategy is very high, and the cost of production downtime is high because you run the assets to failure. For that reason, you always must keep spares, which increases both your inventory costs and labor costs to repair the equipment after a catastrophic failure. The main advantage of reactive maintenance is that it reduces the cost of performing unnecessary condition-based or usage-based maintenance, but the disadvantage is that the asset will eventually fail. Therefore, this strategy is most effective with non-critical machines that are inexpensive and quick to repair.
The second maintenance strategy is Preventative Maintenance, also known as "Fix it before it is due to fail" or "Interval-based monitoring." This approach is often seen as most valuable for assets with age-related failure modes (and where no cost-effective condition-based ways can be implemented). The disadvantage is that it is often implemented on assets without age-related failure modes, increasing downtime and costly routine maintenance expenses on those assets. Every unnecessary maintenance action performed on a machine is also an opportunity for new issues to be introduced.
The third type of maintenance strategy is Proactive Maintenance, or "Maintain it, so it keeps running." The idea here is to do everything possible to reduce the likelihood of failure, including operating the equipment properly and conducting proactive maintenance tasks such as cleaning and proper lubrication.
The advantage is that it eliminates many of the root causes of equipment failure, and you extend the life of the equipment. The disadvantage is that it takes the support of management to be given the time to perform these tasks instead of just performing reactive tasks.
The last maintenance strategy is Predictive Maintenance, also known as condition-based monitoring of assets. It can also be described by the old adage, "If it ain't broke, don't fix it." Predictive Maintenance involves testing the condition of the equipment to determine if a failure will occur in the foreseeable future so that the components in question can be repaired or replaced at the most convenient time. While monitoring the machines alone does not stop the components from failing, plant managers can extend the life of the asset at a minimum cost by replacing the failing component just before it is due to fail.
The advantage of predictive maintenance is reduced downtime, repair costs, secondary damage and spare inventory costs over time; it is most valuable for situations where there are critical assets that have a high cost of downtime, assets that have a history of failures, or hard-to-reach assets where regular checks may be difficult or dangerous.
This is where connected sensors and the Industrial Internet of Things (IIoT) come into play.
Connected Devices and IoT Gaining Momentum
Predictive maintenance and the Industrial Internet of Things are concepts that have been building in the industry for years but have finally reached a point of maturity where solutions are becoming more and more accessible.
Looking at the industry holistically, the predictive maintenance market stood at $5.6 billion at the end of 2020, representing a 17% jump year-over-year.
While impressive, it represents just the starting point. Survey data found that less than 40% of companies have invested in predictive maintenance, but within the next three years, more than 75% expect to have projects in motion.
Even at companies where smart sensors and other IIoT strategies are in place, the cost structures associated with those platforms mean that only 15% of assets are currently monitored by connected devices. In an integrated building or factory setting, a production line is only as resilient as its least reliable asset.
As solutions become more affordable and return-on-investment evaluations shift, growth in IIoT is expected to scale rapidly. From 2021 to 2026, the industry will nearly double its acceleration, with a forecasted compound annual growth rate of 31% through 2026.
As the share of assets being monitored by smart sensors in real-time is set to grow, plant managers can use that data to rethink how those assets are maintained on an ongoing basis.
Connected Assets Drive Condition-Based and Predictive Maintenance Approaches
The growth of IIoT-based solutions is unleashing a paradigm shift in machine health monitoring — allowing companies to gently shift away from manual walkarounds and legacy PM schedules and toward condition-based and predictive asset monitoring approaches.
Condition-based systems are built around a sensor (such as a vibration, pressure or temperature sensor) connected to a monitoring platform via either a wired or wireless connection.
Based on the machinery and processes in place, an alarm or alert value is set, which would represent an error state or potential machine health issue. If the alarm is triggered, technicians are alerted, and the team works to identify the issue and replace the machine or part.
One straightforward example may be the concept of using temperature sensors to monitor high-resistance joints in a motor, where loose or corroded electrical connections can generate current arcing, a rise in temperature and a potential fire. When the temperature reading reaches a critical value — signifying an issue where motors may be nearing a failure point — the maintenance team is alerted and can schedule corrective action appropriately.
Predictive maintenance takes the principles of condition-based maintenance and pushes them further — using machine learning/artificial intelligence to identify issues earlier, proposing what maintenance steps may be helpful in rectifying them and creating a better overall picture of machine health.
Rather than waiting for issues to reach a critical alert value, the system looks for anomalies in various sensing modalities and uses those values in combination with machine learning/AI algorithms to predict upcoming machine failures and identify the root causes of potential issues. This kind of automated fault characterization can also reduce the need for companies to have a vibration analysis expert on hand.
This dynamic is often represented using the P-F (Potential Failure-Functional Failure) curve, where the system can interpret different sensor readings and make judgments about the remaining useful life of the asset.
Vibration monitoring specifically can create a strong return-on-investment for a wide variety of assets, as its principles can be widely applied to motors, pumps and other rotary equipment assets. Over 50% of motor failures are due to premature bearing failures. In addition, many of the rotating machine faults that can be diagnosed with vibration condition monitoring, such as unbalance, misalignment and mechanical looseness, directly impact the motor’s bearings.
Vibration analysis also ties in directly to the ISO 20816 standard (which replaced the previously existing 10816 standard), which establishes how companies should evaluate machine vibration magnitude and shifts to help ensure reliable operation of the equipment.
In most cases, vibration begins far earlier on the P-F curve than audible noise or temperature variations that can be detected during a standard operator walkaround.
By using vibration analysis in combination with other sensor types, operators can identify potential machine health issues earlier in the process and approach corrective action on those assets with a long-term view. Repairs do not need to take place immediately but can be scheduled for the optimal time within the expected useful life of the asset.
This type of predictive insight also creates additional benefits from a supply chain and balance sheet perspective, as plant managers can optimize their near-term and medium-term parts requirements and may be able to keep fewer parts on hand on a regular basis.
How Plant Managers can Avoid Pitfalls in Machine Health Monitoring Programs
The first step in establishing a predictive maintenance or machine health monitoring program is to establish an internal pilot strategy to identify the best assets for this type of platform.
Factors may include:
- Assets with a high risk and/or history of failure — Some assets tend to fail more than others.
- Impact of potential downtime — Downtime with some assets is more damaging than others and often goes beyond the loss of production. When looking at the standard flow of work, understand whether an asset failure could lead to delivery failures, fines, or strain on other production lines.
- Potential duration of downtime —What is the lead time for replacement parts on each asset, and how long does a repair take?
Once a company’s machine assets are viewed through those lenses, the highest-risk assets should rise to the top.
In choosing a platform or IIoT system, there are a variety of factors to consider:
- Ease of installation and scalability — Sensors should be easy to install and configure to minimize any downtime with system startup. And with the advancement of wireless technology, the infrastructure required for them should be appropriate and limited.
- Relevant and accurate sensing modalities —It is important for plant managers and integrators to understand what sensors will deliver the correct data about the health of an asset. Is it a temperature sensor, vibration sensor or both?
- Intuitive data analysis tools — Systems should be designed to be managed by most members of the maintenance team and not be so complicated as to require the hire of outside experts. While it is helpful to monitor the RMS vibration readings on their own, AI or machine-learning algorithms may catch an anomaly that even experts may overlook.
- Costs/Return on Investment (ROI) — Machine health monitoring systems should offer a compelling ROI in months, driven by a reduction in unnecessary maintenance actions, unplanned downtime and walkaround costs.
Digital Transformation for Smart Factories and Buildings
As these connected solutions continue to transform maintenance approaches, plant managers and other corporate leaders will need to remain flexible as the idea of smart buildings and factories continues to mature.
Solutions likely to deliver the best near-term gains will likely be iterative solutions that can be retrofit onto existing motors and other assets, with true “connected” options from many OEMs still in various aspects of the product development phase.
But as each asset comes online, the maintenance processes around it will shift from reactive break-fix solutions toward predictive, smart approaches that prioritize the right actions at the right time. That will allow maintenance personnel to put down their clipboards and focus on performing the tasks that improve machine health, reduce downtime and drive down costs across the organization.
By: Abhishek Jadhav, Industrial IOT Business Development Manager; Sensata Technologies
