The summer season can be utilized by the pursue of research on the following few ideas. The ideas are developed based on the type of audience that means whether B.Tech. or M.Tech, Students or Teachers, etc. students will enjoy doing these topics to complete their PG or UG requirement.
Title: Short Term Rainfall forecasting by ANN-MCDM Approach
Pre-requisite :
Various data of climatic parameters, land use pattern of the region, cloud type and density for 1 to 5 days before the day of forecast.
Justification of the Study :
Rainfall can impact the output of many industrial and agricultural processes. Even the energy output from the power sector is affected by the climatic parameter. Short term rainfall forecasting is an important concept as it can help the planners of this industry to adjust their input so that the required output will remain unaffected.
Brief Methodology :
A widescale expert and local survey followed by a literature review have to be conducted to identify the parameters which mostly impact the rainfall probability. After the most critical parameters are determined, MCDM methods like Analytical Hierarchy Process or Fuzzy Decision Making can be applied to determine the relative weightage of the importance of the selected parameters. A weight function can be then developed to estimate the probability of rainfall in the next day or day after tomorrow or within the next five days.
Title: Development of a Spatial Predictive Model for Estimation of Flow Rate in Pen-stock Networks
Prerequisite :
Artificial Neural Network and model development, concepts on open channel flow, GIS and Remote Sensing
Justification
The penstock is the vital part of a hydropower plant which ensures that the conversion of energy from potential to kinetic takes place and utilized to produce electricity. A flow prediction within the penstock can ensure the prevention of hammering and other hazards related to open channel flow.
Brief Methodology
A neural network model can be developed to predict the flow rate at different points of the pen-stock network in a hydro-power plant. The value of the parameters in the earlier junction can be used to predict the value of the same parameters in the present junction. A digitized map of the pen-stock network can be developed where each junction and pen-stock length between the junctions are digitized and the data of the vital parameters are stored in the attribute table linked to the shapefiles. The collected data stored and continuously updated in the attribute table can be used to train a model by the neural network methodology for prediction. Such models can be used to know the status of the pen-stocks at different points.
Title: Development of indicator-based real-time Flow Monitoring System within the primary watersheds by the application of Geographical Information Systems(GIS) and Cognitive tools
Prerequisite :
Knowledge of GIS and RS, Working knowledge about the ANN, PNN, etc.
Justification
The vast and complex network topology of watersheds in India often incorporate errors in reports due to which erroneous predictions are common. That is why a more accurate model is required to be developed.If a GIS framework is developed then the model can be encoded and the images produced from the GIS can be used for further actions.
Brief Methodology
The GIS-based condition monitoring systems can be developed to monitor the vital parameters of primary watersheds which are used to carry water from the source to the sink. The plant efficiency is often compromised due to the reduction of the conveyance efficiency of the pen-stock network. The reason for this decrease can be attributed to the diminution in the depth to width ratio or increase in roughness coefficient due to sedimentation or increase in infiltration due to erosion of the channel bed.
Thanking you,