Remote Industrial Process Monitoring and Control of Industrial Process Using Artificial Neural Networks

Author: Dimoji David Onyemaechi
Department: Electronic and Computer Engineering
Affiliation: Nnamdi Azikiwe University

This Dissertation is on the design of remote monitoring and control of industrial processes using artificial neural network. This is in order to address the need for close monitoring and control of critical processes in oil and gas industries. The critical parameters monitored here are temperature, pressure, liquid level and flow rate. If any of these parameters is above the set threshold, the adverse effect could lead to complete plant shut down, which is highly undesirable shell petrol Development Company (SPDC) was used as a case study. Several industrial visits were made to shell flow station at Oyigbo and Nembe and the processes and devices involved in the production of oil and gas from the well head to LNG terminal at bonny, were closely observed. Useful data were also gathered through interviewers with instrument and production engineers. These facilitated the design of a microcontroller based remote industrial process monitoring and control system using artificial neural networks (ANN). The system consists of nine subsystems each with an embedded processor interfaced to a central pc. Since this is sequential logic design, the algorithmic state machine (ASM) chart approach was used in the design. The pc serves as SMS gateway and also hosts a database to store various diagnostic information for management decision support. A Nokia N90 series GSM modem was also interfaced to the PC to facilitate interaction with system/maintenance engineers anywhere they maybe, anytime it becomes necessary. Assembly language, c language and visual basic were used at different stages to program the system. Functional simulation of the system was done using Proteus and the data obtained from the simulation was further analyzed using mat lab. The use of intelligent automation eliminated completely the frequent plant shut down due to faults, experienced in the old system. The performance evaluation and the curve generated with mat lab shows that using ANN controllers gives a better performance than on/off controllers. The system availability was improved from 70% in the old system to 90% in the new.

For full copy of this document please visit the digital library help desk.

Tags: , , , , , ,

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s


%d bloggers like this: