Mitigating Downtime Costs in Manufacturing

First, as in most other industries, manufacturing assets, whether they are machines or furnaces, wear down over time and naturally stop functioning. Another challenge occurs when components and parts produced do not meet quality specifications. In such instances, production stops until workers can identify and fix the problem, taking hours or even days. Such downtime can be expensive. According to Aberdeen Research, companies across all industries bleed a little over a quarter-million dollars for every hour of downtime.

Manufacturing is tackling the problem of downtime with data-driven digital transformation, known as smart manufacturing or Industry 4.0-and utilizing rugged mobile devices is vital in diagnosing problems and executing corrective actions on the plant floor.

Costs of Downtime and Other Industry Challenges

Traditional manufacturing has worked with advanced technologies and automation. However, physical assets on the plant floor remain a closed black box too often. As only qualified and experienced technicians can diagnose and troubleshoot problems. Given that downtime is expensive, organizations in the manufacturing industry have traditionally solved the challenge in a few ways.

• Replace parts or assets according to a fixed schedule, whether they need it or not
• 
  
• Allowing machines to "run to fail" and keeping spare parts on hand in-house to shorten the time it takes to fix broken machines
• 
  
• Dispatch workers on operator rounds to record the "vital signs" on devices so they can stay on top of any changes
• 
  
• Rely on experienced workers or specialists to "hear" when a machine sounds different
• 
  
• Lean on camera inspection systems to diagnose when production does not meet specifications

These solutions are the best that manufacturers have worked with, but they do not significantly impact or solve the problem. At best, they are fair stopgap measures. For one thing, replacing parts according to a fixed schedule is expensive. A one-size-fits-all program does not work, and even a custom plan does not fully solve the challenge. Throwing away parts before you have extracted their total value is a waste of resources. When companies try hard to meet environmental, sustainability, and governance guidelines, this method becomes a problem.

The run-to-fail approach depends on in-house inventories of spare parts, which presents another problem. Too much capital gets tied up in inventory-related capital expenditures for features that shop floors may or may not need in any month or year. It is an inefficient way of doing business.

Leaning on operator expertise to listen to machines and diagnose problems is not a data-based approach to the problem. The expertise leaves the building when the technician retires or is not at work. Dispatching workers to conduct daily readings of machine parameters is a waste of human resources, especially when talent is hard to find. Workers do not want to work dull and tedious jobs either.

Camera inspection systems can detect production defects. However, the process often comes much later in the manufacturing pipeline to be of much use. These systems might also miss minor and difficult-to-identify flaws.

As a result, downtime has remained an ongoing challenge despite automation and efficiencies in other aspects of manufacturing-until Industry 4.0.

AI-driven Manufacturing Cuts Downtime Costs

One of the promises of Industry 4.0 is that it can decrease manufacturing downtime costs by enabling machines and production assets to "talk." If a machine could tell workers it is not feeling well before it breaks down, the worker could intervene and deliver the right medicine in time before the device causes much more severe damage.

Manufacturing needs to integrate operational technology (OT) such as physical assets with enterprise software-driven information technology (IT) systems. Applying technological advancements of rugged computing solutions to physical assets will help manufacturers get ahead of the black box.

But how do users get machines to talk? Industry 4.0 relies on the Industrial Internet of Things (IIoT) for this magic. IIoT captures various kinds of data from devices through embedded sensors. Temperature and vibration profiles are typical datasets gathered. The data finds its way into machine learning (a subset of artificial intelligence) algorithms. By studying large amounts of historical data, the algorithms detect patterns. They are also trained on which patterns are expected-and which ones are not. So, when data streams from manufacturing equipment flow into these programs, the algorithm studies the design and compares it against normal behavior. When it detects abnormalities, it can take whatever corrective action-alert a worker through text, for example-it is programmed to do. These principles apply equally to machine maintenance and parts inspection.

These corrective actions roll into place days and even weeks before machines fail. The cost of downtime decreases significantly because manufacturers keep machines running unless it signals there's a problem.

The advantages of such an AI-driven Industry 4.0 approach to manufacturing include:

• An ability to deliver predictive instead of reactive maintenance. Manufacturers need no longer tie up capital expenditures in replacement parts or attend to problems only when systems break down. Using this low-touch approach, they can also squeeze the most life out of assets used in the manufacturing process.
• 
  
• Save operating costs on parts and experts. In addition to saving money on parts, manufacturers also need not hire experts at the last minute to help bring systems back in production.
• 
  
• Leaning on machine learning algorithms to do the hard work of predictive maintenance keeps proprietary information in-house. Know-how need not leave when experts retire or are out sick. Centralizing information that everyone can access also empowers recruits to the team. Manufacturers can design workflows to ramp up training and learn to recognize problems faster.
• 
  
• Enable small-batch specialty manufacturing. Understanding how and when machines can be used also helps manufacturers fine-tune the process with better outcomes. A data-driven approach can enable manufacturers to accept smaller specialty orders and make the most of every production line.

How Rugged Mobile Solutions Help

Rugged mobile solutions help manufacturers embrace the advantages of Industry 4.0 in cutting downtime costs.

Using rugged mobile devices, a worker can securely access information on the plant floor and see the complete picture. Depending on what the alert says, they can take action for repair or order parts as needed. Since OT integrates with IT, plant managers can supervise operations remotely. All authorized personnel have access to the same information through approved rugged mobile devices, so there is a decreased chance of miscommunication.

Rugged portable devices can withstand the harsh environments of manufacturing facilities. And since they are portable, these devices significantly improve worker productivity by going to where the work is instead of the other way around. Mobile devices should also be able to accommodate any new or future technologies coming down the pike. IT administrators can configure these devices to enable specific functions securely. For these reasons, rugged mobile devices are needed on the production floor in manufacturing. They are an integral part of Industry 4.0 and key to decreasing downtime costs.

The steep costs of downtime have plagued the manufacturing industry for a long time. Integration of OT and IT utilizing rugged mobile devices will likely yield insights into real-time production floor machinery health leading to decreased downtime. Rugged mobile devices continue to be a vital solution in accessing these insights in real-time and on the production floor when they are most needed.

Learn more about Getac Rugged Mobile Solutions for the manufacturing industry.

Public link

Please use the above public link if you want to share this noodl on another website.