Put the AI ​​in maintenance

please send your inquiries to us

Contact Us


  Bringing the KI into Maintenance

By Sean Robinson, Service Manager, Novotek UK & Ireland

Over the past five years, the industrial sector has begun to recognize the value of digitization, and has more in the acquisition invested. Thus, a cultural shift from reactive asset maintenance to proactive maintenance that anticipates problems has been accomplished. This article explains how asset managers can make proactive machine learning maintenance even more effective.

In 2006, British mathematician Clive Humby claimed that "data is the new oil". Whether you are a food manufacturer or a car manufacturer, data from production processes are the foundation for greater efficiency, effectiveness and overall performance.

If you are familiar with the Industrial Internet of Things (IIoT), you will know this The most important sales arguments in the concept include the insights into the performance of the system and the effectiveness of the processes, which in turn brings benefits for the company.

This has changed the maintenance culture in facilities that have introduced the IIoT technology. Rather than responding to a break or performing scheduled maintenance based on the expected life of the equipment, engineers can make informed decisions about when to maintain systems based on device health.

Minimizing unplanned downtime has obvious benefits, but reducing planned downtime adds significant value to increased overall throughput for no new capital expenditures. However, achieving this is a challenge due to the amount of data and subsequent analysis required to safely change maintenance schedules.

This is an opportunity for machine learning in industrial maintenance. With machine learning, algorithms can be trained to identify correlation factors in data to indicate not only a problem but also the cause. It sounds simple in principle, but the number of possible things to consider can be too high for a human to work effectively.

More Products  Rising energy costs call for drive systems

There may be dozens of sensors or other health signals in a single machine. To get a clear picture of all the things that affect reliability, this data should be evaluated along with things like maintenance logs and a history of the machines. Even environmental conditions and crew data can reveal what problems can arise.

The only effective way to navigate the multitude of variables is an IoT machine learning platform, such as GE Digital's Predix platform and Asset Performance Management (APM) suite. When an IoT-enabled computer is connected to the platform, machine learning algorithms can be analyzed with the combination of standard measurements and advanced analysis of the APM. This allows maintenance personnel not only to know when to service a machine, but also why.

For example, a semiconductor manufacturer could reject 10 percent of its power due to manufacturing errors. Although all machines can be IoT-connected, there is too much data that an engineer can reasonably analyze. For example, with IoT Analytics Machine Learning algorithms, the APM may detect that a machine has increased vibration levels that damage the semiconductors.

The algorithms can evaluate this against historical data to detect patterns of how often this happens. Identify the preceding performance labels and, if integrated into a management system, send alerts to the technicians as the machine needs servicing. This allows the machine to be serviced only when its conditions indicate and switches from a preventive to a condition-based predictive maintenance.

In fact, machine learning allows maintenance data analysis to become a more automated process. In fact, there are certain industrial applications where the algorithms could reconfigure a machine directly with the right settings. And as machine algorithms learn, this will be an increasingly practical way to improve efficiency.

More Products  NEMA: China tariffs will penalize American manufacturers

Whether you believe that data is the new oil or not, it is undeniable that it is a valuable resource that promotes overall operational improvement for plant managers and maintenance engineers. The key is to use industrial analytics intelligently and effectively to extract oil in industrial maintenance.

Please send us your request with full details via the following link to supply your equipment in the fields of power, instrumentation and industrial computers. We will try to respond to you as soon as possible.

Click to Send inquiry to Ocean Part

Leave a Reply