Mass Flow Measurement of Pneumatically Conveyed Solids Through Multi-Modal Sensing and Machine Learning

Electrostatic sensors – Their principles and applications

“…To measure the mass flowrate of particles in a pneumatic conveying pipe, Abbas et al [155] proposed a multi-modal sensing platform along with machine learning models. The sensing platform consists of an array of electrostatic sensors and temperature, humidity and differential-pressure There is a clear trend that soft computing algorithms are being combined with electrostatic sensors and sensor arrays to tackle some measurement challenges or enhance the performance of existing measurement or monitoring systems.…”

Mass Flow Rate Measurement of Pneumatically Conveyed Solids Through Multimodal Sensing and Data-Driven Modeling

“…For the purpose of exploring the potential and applicability of data driven models for mass flow rate measurement of solids under different air velocities, all the other physical parameters such as pipe orientation and environmental conditions are kept constant. However, the data driven models can also be generalized for different pipe orientations and environmental conditions, provided they are trained with the data under the correct wide range of pipe orientations, ambient temperatures and relative humidity under which the sensors are to be installed for practical applications [16,22].…”

“…There has been an earlier attempt to deploy data driven models to achieve the gas-solid flow measurement by establishing a relationship between characteristics of the sensors and the flow parameters. The authors of this paper proposed an initial method for mass flow rate measurement of solids through multi-modal sensing and the data driven models [16]. For a constant particle velocity 22.1 m/s, the support vector machine (SVM) model has given the best performance with a relative error within ±10%.…”