Bluetooth IoT predictive maintenance: Bluetooth IoT gateways, sensors, and data

By Brad Canham

The following describes the rapid growth of the industrial IoT predictive maintenance market, the emergence of enterprise Bluetooth IoT, and the competitive advantages of long-range Bluetooth edge gateways within the IoT predictive maintenance market for Industry 4.0 manufacturers, and IoT system integrators.

IoT Predictive Maintenance: Challenges and Opportunities

Few movies capture the dynamics and complex relationship between the forces of condition monitoring, production, and “system failure” than the 2016 disaster film “Deepwater Horizon.”

Moreover, driven by a large market opportunity as well as “fragmentation in the IoT ecosystem” industrial IoT manufacturers are increasingly turning to Internet of Things (IoT) system integrators (SIs) to navigate those forces and assemble the components of an IoT derived predictive maintenance system. In turn, competitive forces and technological advances have pushed IoT system integrators to move beyond traditional condition monitoring and move to data-rich IoT predictive maintenance systems.

IoT predictive maintenance is viewed as strategic Industry 4.0 business function, according to a McKinsey report. due to reported reductions in downtime of up to 50%, and reductions in maintenance costs of 10-40%. Manufacturers are expected to see an increase in profitability and reduced capital investments costs estimated at 3-5%, resulting in a “potential economic impact of nearly $630 billion/year in 2025,”.

In short, the incentives for Industry 4.0 manufacturers, as well as IoT system integrators implementing IoT predictive maintenance systems, are massive. For an example of a Bluetooth IoT predictive maintenance in an industrial IoT setting see the Cassia use case, “Monitoring IIoT: How long-range Bluetooth keeps the machines running.”

IoT Predictive Maintenance: A dynamic $11B annual market

Moreover, multiple estimates of the IoT predictive maintenance market place it’s expected compound annual growth rate (CAGR) between 29-to-39%. This CAGR, defined as “annual PdM technology-spend,” is expected to ramp from ~$1.4 billion in 2016, to $3 billion in 2018, to $8-11 billion in 2022 in a neck-straining growth curve.

“The (predictive maintenance) market is also projected to witness growth in the system integration and consulting services segment…” according to a Market and Markets, March 2017 report on predictive maintenance, with the largest market in the United States and the fastest growing market in the APAC region.

IoT Predictive Maintenance: Why the fast growth, why now?

Previously, the complexity and volume of inter-related production systems constrained such services to “condition-based monitoring” (CbM) and hot spot testing. In general, CbM systems were limited to “preventative” monitoring based on feedback capabilities, but lacked “predictive” capabilities associated with big data capabilities.

For example, even with multiple layers of condition monitoring, feedback, and testing, the Deepwater Horizon disaster had at least eight major system failures, all inter-related, in complex ways. Monitoring those complex interrelationships in a timely manner requires the power of big data to correlate the monitored data with possible outcomes.

This “next step,” beyond condition monitoring, IoT predictive maintenance and monitoring, required the new technical capabilities of an IoT ecosystem combining low-cost sensors, connectivity, open standards, and data analysis in the cloud, as well as “the edge.”

Moreover, the market itself is shaping the technologies used, such as the case with Bluetooth predictive maintenance. As the PdM market matures, competition has put downward pressure on the costs of PdM systems. Also, increasingly PdM system integrators are responding to increased competition by building “value-add” capabilities, such as those provided by edge computing, into deployments. In that regard, advances in multi-connected and long-range BLE have positioned Bluetooth IoT predictive maintenance systems as an option that checks all the boxes of an open standard, low cost, connectivity, technology which delivers IIoT data at the edge and to the cloud.

In turn, system integrators delivering the new IoT predictive maintenance options, like Bluetooth, are driving much of the IoT predictive maintenance CAGR. The IoT system integrators are especially good at helping Industry 4.0 manufacturers to focus on their core “production” competencies, pushing IT to the “cloud” and serving as a

IoT System Integrator with industry-specific predictive maintenance knowledge

Today, forward-looking system integrators with specialized industry knowledge are taking the lead with IoT predictive maintenance systems. IoT system integrators can do so, because these they possess the repeated insider experience required to accurately map industry-specific engineering requirements and system interdependencies to all layers in the IoT predictive maintenance stack.

For example, a system integrators holistic knowledge of the client company infrastructure, such as data gathered from newer machines versus older machines, provides for insights into which machines and how specific machines should be monitored.

Moreover, niche market system integrators understand the primary driver for IoT predictive maintenance varies considerably based on the specific industry. Some industries are focused on cost containment, others risk mitigation, and others safety concerns. For example, in the oil and gas industry, ROI is “not always the primary objective,” but rather “risk mitigation” noted Azima DLI, Burt Hurlock, CEO in a 2016 Control Engineering magazine article on predictive maintenance and risk mitigation.

Also, IoT system integrators have access to the newest IoT predictive maintenance components, such as the newest sensors (vibration, pressure, etc…) and connectivity options including long-range Bluetooth edge gateways. System integrators with specific industry expertise understand which Bluetooth sensor is a better fit for their industry. For example, an IoT SI may use a vibration sensor which is calibrated to a specific range of vibrations for small machine health versus a vibration sensor more application to an oil refinery pump or pipeline.

Moreover, because simple “efficiency model” problems are showing quick ROI in IIoT, Industry 4.0 has embraced the gains of business intelligence (BI) systems and big data faster than most other IoT verticals. As a result, successful IoT predictive maintenance use cases are more common, resulting in a virtuous circle of projects and funding for IoT predictive maintenance system integrators. Increasingly, predictive maintenance system integrators are able to offer “future proof” IoT predictive maintenance systems with capabilities such as Bluetooth IoT “edge” or “fog” predictive maintenance capabilities.