MODELING THE EFFECT OF TEMPERATURE ON ENVIRONMENTALLY SAFE OIL BASED DRILLING MUD USING ARTIFICIAL NEURAL NETWORK ALGORITHM

Due to increase in environmental legislation against the deposition of oil based mud on the environment, drilling companies have come up with an optimum drilling mud such as plant oil based mud with little or no aromatic content, which its waste is biodegradable. Optimum mud carry out the same function as diesel oil based drilling fluid and equally meets up with the HSE (Health, safety and environment) standard. It is expedient to determine the down hole mud properties such density in the laboratory or use of available correlation but most time; the range of data is not either reliable or unavailable. In this study, artificial neural network (ANN) was used to address the unreliable laboratory data and unavailable correlation for environmentally friendly oil based drilling mud such as jatropha and canola oil. The new artificial neural network model was developed for predicting the down hole mud density of diesel, jatropha and canola oil based drilling mud using 30 data sets. 60% of the data were used for training the network, 20% for testing, and another 20% for validation. The test results revealed that the back propagation neural network model (BPNN) showed perfect agreement with the experimental results in term of average absolute relative error returned.