Flow regime identification of particles conveying in pneumatic pipeline using electric charge tomography and neural network techniques

• Main Author: Ahmed Sabit, Hakilo
• Format: Thesis
• Language: English
• Published: 2006
• Subjects: TK Electrical engineering. Electronics Nuclear engineering
• Online Access: http://eprints.utm.my/id/eprint/5146/1/HakiloAhmedSabitMFKE2006.pdf; http://eprints.utm.my/id/eprint/5146/
• Institution: Universiti Teknologi Malaysia

Solid particles flow in a pipeline is a common means of transportation in industries. Pharmaceutical industries, food stuff manufacturing industries, cement and chemical industries are some of the industries to exploit this transportation technique. For such industries, monitoring and controlling materials flow through the pipeline is essential to ensure plant efficiency and safety of the system. The pipeline transportation used in this research makes use of electrodynamic sensors which are charge to voltage converters. The process flow data is captured fitting an array of 16 such sensors around the circumference of the pipe to capture the inherent charge on the flowing solid materials. A high speed data acquisition card DAS1800HC is used to interface the sensors to a personal computer which processes the data using linear back projection algorithm (LBPA) and filtered back projection algorithm (FBPA). Data captured for this purpose is in the range of mass flow rates 26 g/s to 204 g/s. A Visual C++ programming language is used to develop an application program to compute the image reconstruction algorithms and display the tomograms which represent the concentration profiles at a measurement crosssection of the pipe. A neural network based flow regime identifier program is developed in Matlab environment. Baffles of different shapes are inserted to artificially create expected flow regimes and data captured in this way are used in training and evaluating the network’s performance. This research has produced filtered back concentration profiles of each flow regimes owing to the technique of neural network method of flow regime identification.