The way to minimize downtime is obvious: prevent the failures that cause disruptions. What is not so obvious and has in fact been very challenging is how to accomplish this.

Historically, the way to prevent failures was to follow the advice of the device’s manufacturer and employ their time or usage-based preventative maintenance schedule (e.g., change assembly line motor oil every three months or every 500 hours of use).  However, this approach must also take into account the environment that the device, or machine, has been deployed in.

And of course, the manufacturer’s recommendations are based on historical information and statistics, so while they will minimize failures across a very large number of motors, they may not at all be accurate predicting the failure of your specific unit. Your environment will affect the actual outcome and in fact, due to variations in manufacturing, the core physical attributes of your device may also impact performance over time.

Following standard manufacturer recommendations, therefore, will often result in either maintenance actions (ie, replacing your oil) too soon and thereby wasting money and time, or worse, resulting in maintenance actions too late, and potentially leading to costly damage.   

LLumin’s approach to preventing failure and minimizing downtime is Proactive Maintenance, which is a combination of preventative and predictive maintenance.  Proactive Maintenance, as implemented in LLumin’s Operations software, supports time, usage, and condition based maintenance approaches, all of which can be deployed simultaneously.

 READYAsset, for example, integrates with the machine or industrial asset control system and then monitors each machine’s specific conditions or state in real-time. When it detects conditions that could cause a potential failure, its expert system, AI-based rules utility automatically trigger the best preventative, pro-active  response. Going back to the motor example, this would be like READYAsset recommending an oil change when an oil transparency sensor in the motor reported particles in the oil even though its not been three months since the last oil change.

By triggering corrective action based on the real-time conditions of specific machines rather than on statistical average data (e.g., manufacturer’s historical usage info), READYAsset reduces downtime and saves money by taking the best corrective action at the best time, neither too soon nor too late.