The many facets of PdM: Analyst examines how technologies are helping users improve PdM models
The medley of predictive maintenance (PdM) strategies for improving machine health is growing larger and more powerful, whether using classic portable tools for non-critical asset inspection rounds and on-site problem verification and troubleshooting, or advanced technologies such as the IIoT, cloud, and AI and ML algorithms.
Leaders and analysts who go on record by documenting improvements gained from predictive maintenance initiatives provide a window into the immense potential of today’s enabling technologies. This article features a leading industry analyst offering her thoughts on how PdM will evolve over the next several years.
The other case studies include:
- Oil and gas supermajor uses AI predictive analytics
- Midstream energy company uses IIoT strategy with integrated CMMS
- Consumer products manufacturer uses AI and ML models
- Self-driving truck company uses CMMS, BI tooling, and mobile app
- Tire manufacturer uses 24/7 wireless vibration monitoring system
- Thermal battery manufacturer uses Generative AI-driven data operations platform
- Mining company uses industrial edge data platform and SCADA system
Maintenance and reliability professionals have long relied on condition monitoring to detect early signs of asset degradation and prevent unexpected failures of critical equipment. Tried and true methods such as vibration and temperature monitoring, oil analysis, infrared thermography, and ultrasound inspection enable predictive maintenance during scheduled outages to avoid unplanned downtime.
But the early applications typically involved time-consuming inspection rounds and data gathering, often in spreadsheets, for manual analysis. Fortunately, vast technological improvements are helping to eliminate the data silos, integrate and automate data collection and analysis, and better predict and prevent failures.
Inderpreet Shoker, director of research at ARC Advisory Group, notes the industrial world has made tremendous improvements when it comes to maintenance strategies. “The next big change in asset management is brought by technologies like artificial intelligence (AI), analytics, and machine learning (ML). These technologies are helping us improve PdM models,” she explains.
PdM approaches employ near real-time equipment and process data analysis to predict failure. Applying continuously improving technology to PdM enables a higher degree of confidence and low false positives.
“The next level that progressive end-users are looking to achieve is prescriptive maintenance, whereby leveraging AI and ML technology, users get recommended steps to better maintain assets. As the industry is facing a shortage of skilled workers, these technologies will be instrumental in addressing the skills gap,” adds Shoker.
In fact, the most impactful technologies in the next five years, according to the ARC Digital Transformation, Sustainability and Technology Survey conducted by ARC Advisory Group in Q4 2023, include AI with a significant lead and industrial analytics, cloud, and industrial internet of things (IIoT) technologies also prominent. Each of these is already playing a role in improving PdM and prescriptive maintenance approaches.
Notably, reliability and asset management applications are not the only beneficiaries. There are smart solutions detecting patterns and predicting issues in product engineering, production planning, process automation, quality control, energy conservation, supply chain optimization, safety and security management, workforce development, and more. But what’s unique about improving predictive and prescriptive maintenance is that it also bolsters these other business areas.
