tablet held by a person

For years, manufacturing companies relied on time-based equipment maintenance, where the machine's age decided maintenance requirements. Older machines had more frequent maintenance cycles.

However, a recent study by ARC found globally that only 18 percent of equipment failed due to age while 82 percent of equipment failures are random. This indicates the ineffectiveness of time-based maintenance and affirms the need to dynamically predict machine failures to lower maintenance costs. That's where the Internet of Things (IoT) predictive maintenance (PdM) comes in.

Instead of relying on how old the machine is, PdM uses dynamic equipment condition monitoring data from IoT sensors to model baseline performance characteristics. Statistical analytics and machine learning use this data to predict potential faults to intervene promptly.

The World Economic Forum (WEF) study shows that PdM helps manufacturing companies reduce maintenance costs by 30 percent and plant downtime by 70 percent. IoT system design plays a crucial role in fully exploiting PdM's benefits that go beyond maintenance cost reduction.

PdM Resolves the Key Challenges of Industry 4.0 Use Cases

In the manufacturing lifecycle, the maintenance cost of industrial equipment approaches 60-70 percent of the overall cost of production. Traditional approaches to equipment maintenance in the industrial sector can be classified into two main types: corrective, where repair follows malfunction, often leading to costly plant shutdown, and preventive, where maintenance is scheduled based on time and not on the equipment's functional condition.

The inadequacy of these techniques is a leading cause of unplanned downtime, estimated at $50 billion per year for global producers while reducing the plant's total productive ability by up to 20 percent. These approaches are not sustainable as more manufacturers embrace Industry 4.0.

Industry 4.0 use cases require maintenance techniques that go beyond simply preventing individual asset downtime. Ubiquitous connectivity and sensorization of smart factories have made Industrial IoT (IIoT)-based PdM a reality, which, according to a study, increases uptime by 10 to 20 percent while reducing maintenance costs by 5 to 10 percent and maintenance planning time by 20 to 50 percent.

Industry 4.0 use cases are already benefiting from IIoT-based PdM. The Volvo Group, for example, reduced diagnostic times of their fleet by up to 70 percent and repair times by 20 percent by accurately predicting defects in gearing and motor equipment.

Again, in milling industries, collecting and analyzing data from ultrasonic and vibration sensors attached to the spindles enabled milling companies to minimize costly spindle repair costs by predicting cracking and spalling of the rotating equipment. Maastricht Mill applied IIoT PdM to expect damage to bearings and gears by collecting data from their press rolls equipped with temperature and vibration sensors.

In mining and oil and gas companies, inspection and diagnostics of production equipment have the added challenge of personnel working in hazardous environments. Chevron addressed this with IIoT PdM. The company installed sensors across its pipelines to measure pH, gaseous and aqueous CO2/H2S content and the pipeline's internal diameter and thickness. Leveraging a cloud-based IIoT PdM solution, Chevron analyzed sensor data to reliably predict corrosion and pipeline damages that reduced the risks of unplanned shutdowns and personnel hazards

Essential Components of IIoT PdM

IIoT PdM is a series of processes, such as condition-based monitoring (CbM), machine learning and analytics to predict potential machine failures reliably.

CbM involves measuring the current health of machines or assets by collecting sensor data. The collected data is processed and fed into machine learning (ML) algorithms. ML algorithms can reveal hidden correlations in data sets to detect abnormal patterns in data.

These data patterns are then reflected in predictive models. These models are trained and used to identify potential anomalies and failures, which facilitate engineers to predict and ultimately prevent failures.

Using IIoT PdM, engineers can compute the Remaining Useful Life (RUL) of the equipment as the basis to dynamically schedule maintenance and repair only when required.

System Design Considerations for Optimal PdM Outcomes

An optimal PdM implementation efficiently utilizes the right mix of techniques and sensors. Sensor design and the selection of sensors are critically important to ensure faults are detected and predicted with a high degree of confidence.

Since PdM applications involve a complex mix of rotating machines (motors, gears, pumps and turbines) and nonrotating machines (valves, circuit breakers and cables), it is an imperative that the critical faults are understood well along with using sensors that are most suitable for detecting them. For example, vibration analysis is a common PdM technique that relies on vibration sensors like accelerometers.

Low cost, small size, suitable bandwidth and low noise are some of the design considerations for efficiently sensing machine faults such as bearing condition, gear meshing, pump cavitation, misalignment and imbalance. These failures are more common in rugged and often hazardous industrial environments.

System designers should also consider sourcing sensors and other components from trusted vendors to safeguard against counterfeits.


Sravani Bhattacharjee has worked as a tech leader at Cisco, Honeywell and other companies where she delivered many successful innovations to the market. As the principal of Irecamedia, she collaborates with Industrial IoT innovators to create compelling vision, strategy and content that drives awareness and business decisions.


Follow TTI, Inc. on LinkedIn for more news and market insights.

Statements of fact and opinions expressed in posts by contributors are the responsibility of the authors alone and do not imply an opinion of the officers or the representatives of TTI, Inc. or the TTI Family of Specialists.


Sravani Bhattacharjee

Sravani Bhattacharjee

Sravani Bhattacharjee is a technology marketing leader and an industry-recognized content strategist and writer for disruptive technologies such as the Internet of Things (IoT), Cybersecurity and AI. She is author of "Practical Industrial IoT Security" — the first comprehensive book on IIoT security, which has been widely adopted across the industry and the academia.

Sravani has worked as a tech leader at Cisco, Honeywell and other companies where she delivered many successful innovations to the market. As the principal of Irecamedia, she currently collaborates with Industrial IoT innovators to create compelling vision, strategy, and content that drives awareness and business decisions.

View other posts from Sravani Bhattacharjee. View other posts from Sravani Bhattacharjee.

News & Information

Lead Time Trends
Current average manufacturer lead times for parts you depend on

Supply Chain News
Coverage of global conditions impacting manufacturers

Raw Materials Prices
Trends in feedstock metals, oil and other key materials

Podcasts

Listen to our new podcast, TTI Distribution Download! TTI Specialists, supplier partners and more share their expertise and insight on the electronics industry. 

Apple | Spotify | YouTube | Google

Filter Articles By Category

View All Connector Articles


Select Contributor to view their article(s)

View All Passive Articles


Select Contributor to view their article(s)

View All Supply Chain Articles


Select Contributor to view their article(s)

Stay Updated

Subscribe to our newsletters, promotions, and product updates.

Material Costs

Search MarketEYE