Intelligence-Based Supervisory Control for Optimal Operation of a DCS-Controlled Grinding System

The application of automation and supervisory control and data acquisition (SCADA) systems to municipal water and wastewater treatment plants is rapidly increasing. However, the application of these systems is less frequent in the research and development phases of emerging treatment technologies used in these industries. This study involved the implementation of automation and a SCADA system to the submerged membrane adsorption hybrid system for use in a semi-pilot scale research project. An incremental approach was used in the development of the automation and SCADA systems, leading to the development of two new control systems. The first system developed involved closed loop control of the backwash initiation, based upon a pressure increase, leading to productivity improvements as the backwash is only activated when required, not at a fixed time. This system resulted in a 40% reduction in the number of backwashes required and also enabled optimised operations under unsteady concentrations of wastewater. The second system developed involved closed loop control of the backwash duration, whereby the backwash was terminated when the pressure reached a steady state. This system resulted in a reduction of the duration of the backwash of up to 25% and enabled optimised operations as the foulant build-up within the reactor increased.

Download Full-text

WATER DEMAND PREDICTION USING ARTIFICIAL NEURAL NETWORK FOR SUPERVISORY CONTROL

Nigerian Journal of Technology ◽

10.4314/njt.v36i1.19 ◽

2016 ◽

Vol 36 (1) ◽

pp. 148-154

Author(s):

BI Gwaivangmin ◽

JD Jiya

Keyword(s):

Neural Network ◽

Supervisory Control ◽

Water Demand ◽

Water Distribution ◽

Distribution Network ◽

Water Distribution Network ◽

Optimal Operation ◽

Demand Prediction ◽

The Neural Network ◽

Water Demand Prediction

With increase in population growth, industrial development and economic activities over the years, water demand could not be met in a water distribution network. Thus, water demand forecasting becomes necessary at the demand nodes. This paper presents Hourly water demand prediction at the demand nodes of a water distribution network using NeuNet Pro 2.3 neural network software and the monitoring and control of water distribution using supervisory control. The case study is the Laminga Water Treatment Plant and its water distribution network, Jos. The proposed model will be developed based on historic records of water demand in the 15 selected demand nodes for 60 days, 24 hours run. The data set is categorized into two set, one for training the neural network and the other for testing, with a learning rate of 50 and hidden nodes of 10 of the neural network model. The prediction results revealed a satisfactory performance of the neural network prediction of the water demand. The predictions are then used for supervisory control to remotely control and monitor the hydraulic parameters of the water demand nodes. The practical application in the plant will cut down the cost of water production and even to a large extend provide optimal operation of the distribution networks solving the perennial problem of water scarcity in Jos. http://dx.doi.org/10.4314/njt.v36i1.19

Download Full-text