Manufacturers know well the challenges that come when skilled workers retire. And in the current economic landscape, losing talent is one of the major hurdles that modern plants must overcome.
A recent report from Deloitte and the Manufacturing Institute indicates that manufacturers may need up to 3.8 million new workers by 2033 , with nearly half of these positions potentially going unfilled if current labor gaps persist. This is largely due to experienced workers retiring and fewer skilled laborers entering the field. Currently, the average age of highly skilled workers is 56, with nearly a quarter of this workforce set to retire in the next decade.
As a result, companies are losing the qualified analysts and technicians needed to maintain and optimize their assets.
This pain point is all too familiar. But where there are challenges, there are also opportunities. In this article, we’ll explore how technologies equipped with artificial intelligence (AI) are stepping in to revolutionize asset management, turning workforce woes into wins for efficiency and growth.
From Manual to Modern: The Transformation of Asset Management
To put the current resource constraint — and solutions — in perspective, it’s important to look at how asset management has evolved and contributed to this challenge.
Asset management has come a long way from its early days of manual checks and reactive maintenance. Initially, the focus was on robust, manually operated machinery that required regular, hands-on attention. Maintenance teams relied heavily on routine inspections and manual data collection to identify issues and perform necessary repairs. This could take an extremely long time — sometimes weeks or even months to go through all the data and write out reports.
As the industry progressed, the types of machinery used in plants changed. Companies shifted from a few robust, heavy-duty machines to more precision-based, complex machinery. Machines transitioned from simple on/off modes to more sophisticated on-demand operations with varying cycles and variable speeds, making analysis more challenging.
Furthermore, plants used to have redundant assets or backups, ensuring that there was always a machine available if one went down. Nowadays, lean operations mean fewer backups, meaning every machine is critical. Plus, the traditional method of scheduling dedicated maintenance shifts where operations would pause for maintenance is becoming less common as more plants operate 24/7. Such a shift has caused demand for continuous monitoring and maintenance.
In summary, these changes mean that:
- The number of assets monitored has increased. Monitoring doesn’t just focus on critical machines, but the entire plant.
- Assets are now monitored around the clock. We’ve moved from annual to quarterly, monthly, and now daily data collection.
- Analysts must face vastly increased data loads from constantly running machines. They also have to manage increased data complexity due to more frequent and varied data types (vibration analysis, process data, oil analysis).
To put it simply, modern plants have more machines, more data, but less analyst capacity. 54% of companies say that they can’t achieve their digital transformation because they have this skill shortage.
Addressing the Resource Deficit
Given the increased complexity and volume of data, coupled with a shrinking pool of skilled analysts, it’s essential for plants to rethink their approach to asset management. Today, there’s a three-pronged approach that organizations can take to overcome modern challenges. This involves incorporating wireless and AI-powered technologies that can drastically aid in the shift to a more connected, seamlessly managed plant.
Here are the three steps plants can take to shift their asset management strategies:
1. Capture Data Effectively with Advanced Wireless Sensors
Compared to historical vibration analysis methods that required trained personnel to walk around and manually collect data, today’s methods are much less time-consuming and more efficient. Using wireless sensors, companies can automate the data collection process to generate high-quality, actionable insights.
Connected sensors eliminate the need for manual intervention in data collection. Azima’s wireless vibration sensors for instance are mesh network devices that are simple to install and easy to use. No configuration or extensive training is necessary for use. You simply turn on the sensor and forget about it.
2. Improve Data Analysis with AI and Machine Learning
The next challenge is making sense of the vast amounts of data collected from your wireless sensors, given the shrinking pool of skilled analysts. Remember, more machines and more data do not necessarily mean better analysis. There’s no point if all your sensors simply ‘red light’ issues that then require an analyst to arrive on-site to examine them further.
So, how do you analyze the data collected without an analyst on call 24×7? Leveraging AI and machine learning is the way.
- Advanced vibration analytics and AI-powered recommendations: By using advanced AI and machine learning programs, companies can fill the gap left by the shortage of skilled analysts and technicians. These tools can swiftly process and interpret large datasets, identifying patterns and anomalies that would be impossible for human analysts to detect promptly.
Azima’s AI-powered diagnostic engine, for example, is trained on 30 years of data, drawing from 100 trillion data points across 50 machinery component types. This extensive knowledge base allows the system to diagnose problems with incredible accuracy. It also recommends precise corrective actions needed to keep assets running smoothly.
Furthermore, as AI systems continuously learn and improve over time, they become even more effective at identifying issues and optimizing maintenance schedules, turning a data deluge into a strategic advantage. - Clear, actionable insights and repair recommendations: Importantly, because the data is processed through Azima’s cloud-based automation system, the result is consistent and reliable regardless of the data source. This means that plant managers do not have to worry about interpreting different severity levels from various systems. The output of this diagnostic engine is a prioritized, actionable repair recommendation, showing exactly what teams need to do to improve machine health.
- Effective asset prioritization: By turning vast amounts of data into clear and prioritized actions, AI systems allow for a more strategic approach to maintenance. Typically, about 15% of machines in a plant are in a fault state, meaning 85% are healthy. In order to come up with a maintenance plan, manual analysts would need to review all the data, including data from healthy machines, which is not efficient. AI systems automate this process by confirming healthy machines and prioritizing those with faults.
This prioritization allows plant managers to focus on the most critical issues first. For example, in a plant with 100 machines, 15 are likely to have faults, and the system will identify the most critical issues first. In turn, technicians can address the most severe problems promptly. By providing a clear, prioritized list of actions, the AI system allows technicians to focus on the most critical tasks, optimizing their workflow and improving overall plant reliability.
3. Deliver Insights Across the Organization
The final step is to transform the analyzed data into clear, actionable insights that facilitate decision-making across all levels of the organization. This means presenting the information in a way that is understandable and useful for both technical staff and business leaders.
Azima’s advanced diagnostic systems will turn technical knowledge from machine assets into detailed yet user-friendly reports for business leaders. Knowing how many machines are healthy provides critical insights into risk management. Identifying the worst offenders in the plant helps direct efforts to where they are most needed. Highlighting machines that lack sufficient data uncovers potential blind spots. Compliance metrics indicate which machines meet regulatory standards and which do not. Proactive Response gives plant managers and other higher level stakeholders information on whether they are acting quick enough on required repair actions. And Key Saves helps leaders better understand the ROI of their reliability solution.
These insights allow technical staff to focus on critical issues, and business leaders to make informed strategic decisions about where to allocate resources. This comprehensive approach ensures that all stakeholders, from analysts to executives, have the information they need to maintain efficient and reliable operations.
And this solution can be applied not just in one facility but across multiple plants. Enterprises often have identical machines across various locations. Leveraging the knowledge gained from one plant, decision-makers can quickly deploy models to others, drastically reducing the time to establish a healthy baseline. By scaling this solution across multiple facilities, the same high standards of asset management are maintained, regardless of location — effectively addressing the resource deficit.
The Future of Asset Management
Imagine a plant where every machine operates at peak performance, not because of constant human oversight, but because of smart, self-improving systems. It’s a future where resource constraints become a footnote rather than a headline, and where the integration of AI and machine learning turns potential crises into opportunities for growth. In this landscape, the role of human expertise evolves, with analysts still valued for their expertise, but employed more strategically and more efficiently.
The path to resilience and progress in manufacturing lies in the seamless blend of human ingenuity and technological advancement. It’s not about replacing the workforce but amplifying its capabilities, ensuring that every machine, and every decision, is as precise and effective as possible. This is the future of manufacturing — intelligent, adaptable, and remarkably efficient.
This article is based on the session ‘Maintaining Reliable Assets in a Resource-Constrained Economy,’ presented by Michael De Maria, Director of Product Management at Azima DLI, at Xcelerate ‘24.