The internet of things (IoT) is increasingly applied in cleanroom industry to help support the asset health status. Leveraging IoT and complementary technologies such as Industry 4.0 requires the application of skills and expertise in-house. Our reliability engineers have a vital role here. ABN Cleanroom Technology partners up strategically with IoT service provider SmartLog.com to set up, access and analyze data from sensors and devices and convert them into actionable insights with our CleanConnect platform. We use this intelligence for condition monitoring, risk management and reliability improvement initiatives.
Predictive technology sensors are strategically located on critical HVAC assets and communicate via the cloud (or on premise). The cloud provides a secure infrastructure for streaming, analyzing and storing data for more in-depth advanced analytics later. These systems can gather information and statistics of the data which can be used for process and reliability optimization. The condition of the equipment is continuously monitored and readings are compared with defined parameters. This enables the tracking of patterns, or combinations of patterns, that might indicate equipment failure.
Our reliability engineer has the ability to build different failure models to generate P-F curves for predicting corrective actions. Our knowledge of the reasons for failure or failure mechanisms, identifying the combination of key parameter values indicating failure, and using statistical data analytics & mathematics to build the model is of great importance. These failure models serve as P-F intervals. We use machine learning in those cases where we cannot define a failure model for our equipment using advanced data analytics. Machine learning is an integral part of how data is processed, allowing algorithms to detect impending failures.
This feedback passes through the reliability engineer for validation and follow-up action. It essentially enables online condition monitoring of cleanroom equipment, allowing us to predict failures and plan and perform necessary repairs prior to a functional failure.
We have used the following predictive technology sensors in our CleanConnect platform:
- Existing DCS and PLC data to reduce unplanned downtime and to schedule maintenance
- Vibration sensors to monitor the vibration of HVAC equipment and report their health status
- Temperature sensors to monitor temperature fluctuations
- Oil level sensors to measure the variation in oil level (cooling equipment for compressors)
- Acoustic sensors to detect changes in ultrasonic sound
- Engine voltage and current sensors to monitor degradation and imbalance.
In order to put the above maintenance strategy into practice, it is essential that CMMS platforms (Ultimo, Maximo, SAP) allow secure and reliable data transfers via Application User Interfaces (API).