Analytics and cognitive are improving asset reliability

Share this post:

In the previous blog we focused on capabilities and benefits available to manufacturing organizations via the combination of the IoT and analytic technologies – each fundamental components of cognitive manufacturing. Intelligent, instrumented, connected equipment now enables lines of business closely associated with manufacturing processes to gain a far more detailed and accurate understanding of equipment usage and performance, and as a result improve reliability of critical production assets.

Cognitive can improve reliability for manufacturers

Applying analytics to historical and real-time operational data obtained from the shop floor via sensors, devices, wireless networking and the latest IoT technologies enables creation of a predictive model that can provide advanced notice of pending equipment failure. Once the predictive model has been created and applied cognitive capabilities can continuously refine the predictive model, learning from any changes in operational data, such as equipment performance when configured to manufacture a new component or the addition of new sensors to obtain additional operational data. In either instance, cognitive uses new data to refine the model. Continually improving accuracy of the predictive model further decreases the likelihood of equipment failure and concomitantly increases reliability.

Cognitive also plays another role in improving reliability – through analysis of maintenance records, i.e., the unstructured information that contains a wealth of repair information, practices, procedures, and expertise not found in technical documents and whose volume makes it impractical for any human to review and analyze. Cognitive brings additional perspective regarding maintenance practices and procedures to enhance reliability. For example: which components are most prone to failure, what conditions or circumstances such as operator errors (not captured via the IoT) lead to failure, are certain maintenance procedures more effective than others?

The combination of analytics and cognitive applied to relevant sources of operational and maintenance information helps organizations gain a far more detailed and accurate understanding of equipment performance and current maintenance practices. This information can improve reliability of manufacturing equipment in the following ways:

  • Adopt a predictive maintenance strategy to proactively address pending equipment failure or degradation and avoid catastrophic failure
  • Identify the most likely reason for pending failure and prescribe appropriate procedures to take based upon this information to reduce mean time to repair.
  • Prioritize and optimize maintenance schedules and resources with the goal of conducting maintenance procedures only when necessary, thereby reducing unplanned downtime and overall maintenance costs.

Equipment manufacturers also benefit from instrumented, connected, IoT-enable equipment by gaining a level of operational and performance understanding never before possible. In turn, this information advises multiple lines of business regarding improved functionality and reliability of the equipment they design, manufacture and support. Here we assume the customer is willing to share data with the manufacturer or the manufacturer offers equipment monitoring and analysis as a service.

Accurate and detailed understanding of equipment performance benefits product designers, suppliers, field service and warranty management in the following ways. Designers gain insight into how equipment is performing, what situations lead to degradation or failure, which components are likely to fail, or unusual usage circumstances, and use this information to improve equipment design to deliver greater reliability.

Upon discovery of parts or components that are sources of failure, suppliers can be notified with the goal of rectifying the problem through better component design or implementing a higher quality manufacturing process.

Field service receives advanced notification of pending failure, predicted time to failure, identification of the most likely reasons for failure, and recommendations regarding appropriate actions to accelerate time to repair.

Warranty management gains a better understanding of equipment usage, analysis of repair or replacement trends and the ability to develop or refine cost-effective warranty programs that meet the needs of various market segments.

The combination of IoT, analytics and cognitive facilitates a virtuous cycle of continuous equipment and process improvement with the goal of achieving greater reliability. Detailed, real-time understanding of equipment usage and performance leads to design enhancements and maintenance strategies that improve reliability. In turn, greater equipment reliability enhances all aspects of the manufacturing process.

A critical factor in reliability is the overall quality of design as well as materials, parts and components that compromise the equipment. In the next blog we’ll discuss how IoT, analytics and cognitive facilitate improvement in quality of equipment design, functionality and manufacturing processes.

More Manufacturing stories
By Lauren Longhi on November 9, 2018

The top 5 takeaways from the Industrial IoT World conference

From October 29-30, companies from across industries gathered in Atlanta, GA for the Industrial IoT World conference to accelerate their projects “from inspiration to implementation.” As a leader in the IIoT space, IBM was invited to share its expertise. I joined IBM five months ago, and was excited to see our capabilities in person. Here […]

Continue reading

By Ashok Kumar on October 8, 2018

Are MES systems dead? How IoT and AI are transforming the shop floor

Manufacturing is changing due to advancements in the Internet of Things (IoT) and Artificial Intelligence (AI). With  consumer demand for customization driving new requirements for speed and agility, many manufacturers are struggling to keep up. On top of this, more competition and increased demand is putting higher pressure on manufacturers to increase overall plant performance.  […]

Continue reading

By Chris O'Connor on October 2, 2018

Do you have the needed data around yield, throughput, and quality to make sound operational decisions?

Here is a bold idea – your machines, your connected systems, your factories all diagnosing themselves and predicting needs before they affect production. What do you think when you read that? Are you thinking early and accurate identification of defects, improved production, optimized throughput, less waste and no product recalls? You should. Because that is what […]

Continue reading