Deep Surrogate of Modular Multi Pump using Active Learning
This work addresses data scarcity in sensor-limited pump design for the energy industry, though it appears incremental as it applies existing active learning techniques to a specific domain.
The researchers tackled the problem of estimating the feasible operating point of a Modular Multi Pump with limited sensor data by developing an active learning framework, which successfully reduced the dataset needed for accurate surge distance estimation in real-world energy applications.
Due to the high cost and reliability of sensors, the designers of a pump reduce the needed number of sensors for the estimation of the feasible operating point as much as possible. The major challenge to obtain a good estimation is the low amount of data available. Using this amount of data, the performance of the estimation method is not enough to satisfy the client requests. To solve this problem of scarcity of data, getting high quality data is important to obtain a good estimation. Based on these considerations, we develop an active learning framework for estimating the operating point of a Modular Multi Pump used in energy field. In particular we focus on the estimation of the surge distance. We apply Active learning to estimate the surge distance with minimal dataset. Results report that active learning is a valuable technique also for real application.