University of Twente Student Theses
Applying Artificial Intelligence on an Integrated Pressure and Mass Flow Sensor
Groen, R.R.A. (2020) Applying Artificial Intelligence on an Integrated Pressure and Mass Flow Sensor.
|
PDF
1MB |
| Abstract: | The integrated mass flow and pressure sensor consist of four read-out structures, two capacitive sensors for the displacement of the tube and two resistive pressure sensors to attain the pressure drop across the tube. The sensor’s purpose is to measure the mass flow in the tube and the pressure drop across the tube. However, to attain these quantities, information is lost which is related to the physical quantities of the fluid. For example, the actuation frequency is filtered but is related to the density of the fluid. This research uses machine learning algorithms to learn classification models for the fluids based on the lost information. This is the first research into combining artificial intelligence into the field of the mass flow sensor. The first step is classifying fluids using the data. However, integrating parameter and composition estimations could be included in future research. The integration holds vast potential such as creating applications for the medical and industrial market. Applications include oil quality estimations and drug administration. Integrating artificial intelligence could potentially enhance these applications and lead to novel applications. The training data consisted out of the non-filtered data attained from the sensor using six fluids, eight mass flows and three pre-pressures. Three machine learning algorithms are tested with the best performance achieved by k nearest neighbour and decision tree algorithms which were able to classify fluids with an accuracy of 95% and 92% respectively. However, this accuracy is only achieved for discrete mass flows, therefore further research is needed to achieve classification for continuous mass flows. |
| Item Type: | Essay (Bachelor) |
| Faculty: | EEMCS: Electrical Engineering, Mathematics and Computer Science |
| Subject: | 53 electrotechnology |
| Programme: | Electrical Engineering BSc (56953) |
| Link to this item: | https://purl.utwente.nl/essays/82326 |
| Export this item as: | BibTeX EndNote HTML Citation Reference Manager |
Show download statistics for this publication
Show download statistics for this publicationRepository Staff Only: item control page