Every day, vast amounts of data are generated across different sectors, containing valuable information that could aid businesses in their operational and strategical decision-making. In order to unlock and extract the value that lies within data, advanced modelling techniques such as machine learning models have become increasingly important, where information such as the condition of instruments, fault detection and diagnosis, and a forecast of future performance based on historical trends, can be obtained. Flowmeters, such as ultrasonic flowmeters (USMs), are capable of outputting digital data sets with the potential to be used for diagnostic purposes to indicate device performance and installation conditions. To maintain their accuracy and reliability, flowmeters are typically calibrated and maintained under fixed time-intervals, for example once every year; this is known as time-based monitoring. However, this type of calibration procedure is a crude method, neglecting many important factors, such as frequency of usage and operational conditions, that can directly impact the health of flowmeters and instrumentation.
展开▼
