Featured Product
This Week in Quality Digest Live
Lean Features
Jake Mazulewicz
Three tips from high-reliability organizations
Gleb Tsipursky
Here’s the true path to junior staff success
Tina Behers
First, leaders must overcome their fear of failure
Emily Newton
Understand your Wi-Fi environment
Megan Wallin-Kerth
Watch and learn

More Features

Lean News
Introducing solutions to improve production performance
Helping organizations improve quality and performance
Quality doesn’t have to sacrifice efficiency
Weighing supply and customer satisfaction
Specifically designed for defense and aerospace CNC machining and manufacturing
From excess inventory and nonvalue work to $2 million in cost savings
Tactics aim to improve job quality and retain a high-performing workforce
Sept. 28–29, 2022, at the MassMutual Center in Springfield, MA
Enables system-level modeling with 2D and 3D visualization, reducing engineering effort, risk, and cost

More News

Emily Newton


AI and Other Technologies Improve Industrial Equipment Testing

With Industry 4.0 technology, businesses can enable new equipment testing, monitoring, and maintenance techniques

Published: Thursday, July 22, 2021 - 12:03

Effective equipment testing is essential for manufacturers of industrial equipment and end-users. Without testing, defects and damage can shorten the life span of equipment, cause unplanned downtime, and reduce the quality of finished goods.

This is especially true for businesses in sectors like food and beverage manufacturing, where equipment being in good condition is necessary to maintain safety and quality standards.

New industry 4.0 technology is transforming how businesses approach industrial equipment testing. Techniques enabled by innovations like AI and IoT devices can help companies automate testing processes and gather additional information on equipment performance.

IIoT enables new types of data collection

In some cases, new industrial IoT (IIoT) devices may make it practical to collect real-time operational data on parameters that were difficult or impractical to track automatically in the past.

For example, in most industrial settings, motors are necessary to drive equipment like mixers, conveyor belts, and packaging equipment. Without regular maintenance and testing, wear and tear can easily cause engines to fail due to lubrication fluid contamination, winding faults, ground faults, and faulty connections.

Certain industrial settings, like food processing plants, present additional challenges. Safety standards mean motor housing may require regular washdowns, and food waste or other site contaminants could degrade or adulterate the grease used to lubricate an electric motor.

Analysis of an electric motor ensures that the proper amount of grease is delivered at the correct interval and that there is a continuous supply of uncontaminated lubricant available.

It is possible to continuously monitor a device’s lubrication in the same way that condition-monitoring tools can gather information on vibration, temperature, and ultrasonic sound. Oil and grease analysis sensors can regularly draw fluid samples from in-service machinery, providing frequent updates on the current state of lubrication.

Historically, however, businesses have avoided oil analysis sensors in favor of manual tests due to the high cost and limited applicability of existing sensors. Oil analysis was instead accomplished by collecting and testing fluid samples from machines at regular intervals. The data this approach yields are discrete, may require downtime, and will not be able to detect problems that emerge between tests.

As industrial IoT technology has evolved, manufacturers have created a growing range of oil analysis sensors that are cheaper and more practical than previous options.

These new sensors can often be incorporated into existing operational monitoring systems. Once embedded in a machine, they can provide additional information to manufacturers on machine health more frequently than manual testing, typically without requiring more downtime or new data analysis platforms.

Testing equipment during manufacturing with industry 4.0 technology

New technology can also help improve testing industrial equipment during the manufacturing process.

For example, manufacturers of electric motors perform several standard tests to check the integrity of a new engine. They typically evaluate static and dynamic operational parameters, including insulation, electrical current leakage, back electromagnetic field and noise, vibration, and harshness.

Effective testing is essential, but not all methods can detect 100 percent of motor issues. Some latent defects will not appear in standard tests required by testing regulations. They can pass through the manufacturing process undetected and may cause problems for end-users almost immediately.

Certain novel testing systems help solve this problem, enabling measurement techniques like partial discharge that can uncover these latent issues.

Industry 4.0 technology can also fully automate steps in the testing process that previously required human labor. Businesses can use machine vision for AI to automate visual quality assurance. An AI algorithm trained on visual data of defective products can scan for obvious defects and construction errors. The system can flag those defective parts, ensuring they’re removed from the production line as soon as possible.

Automating machine analysis with AI

Industry 4.0 technology also makes it possible to automate the analysis of information from tests and IoT sensors. A predictive maintenance approach, enabled by AI and big data analysis, allows businesses to build on preventive maintenance with analysis of the real-time information gathered by networked sensors.

With the predictive maintenance approach, manufacturers create a network of condition-monitoring sensors that can provide a real-time picture of machine health. These sensors typically track performance information like vibration, machine timing, temperature, lubrication, and ultrasonic sound.

Information is continuously sent to both the site maintenance team and the cloud, where it is processed by an algorithm trained on machine performance data from other industrial sites.

Once IoT sensors have been active for long enough to establish a baseline of machine performance for a particular site, the predictive maintenance algorithm can detect abnormalities. It can alert maintenance staff when a machine begins to behave unusually. The maintenance team can then quickly inspect the device, allowing them to catch potential issues or damaged components.

Some predictive maintenance systems may also identify specific issues, allowing technicians to pinpoint damaged or nonfunctional machine parts more quickly. This approach has been found to significantly reduce maintenance costs and machine downtime compared to preventive maintenance.

The advantages can become even more significant for businesses upgrading from a reactive or purely corrective maintenance strategy. The average adopter of predictive maintenance sees a tenfold return on their investment, according to data from the U.S. Department of Energy. The average adopter will also reduce maintenance costs by 25 to 30 percent and breakdowns by 70 to 75 percent.

In some cases, embedded sensors can also act as decision-makers. A system may be able to automatically shut down a machine or make adjustments to operating parameters to prevent damage when it is detected. This further reduces the risk of unplanned downtime and unnecessary equipment wear and tear.

How industry 4.0 technology is simplifying equipment testing

With the right Industry 4.0 technology, business owners can enable a wide range of new equipment testing, monitoring, and maintenance techniques.

Tests that were difficult to automate in the past—like lubrication fluid testing—are often much easier to automate with the right IoT sensor. They can also streamline equipment monitoring and provide information that manual tests and inspections may not provide.

AI and big data analytics make it possible to turn these additional data into a real-time warning system that provides a business’s maintenance team with advance notice on potential machine failure.


About The Author

Emily Newton’s picture

Emily Newton

Emily Newton is the editor-in-chief of Revolutionized, an online magazine exploring the innovations disrupting the scientific and industrial sectors.