Water quality management is an important issue in modern times. Determination of status of water quality is highly indeterminate. The purpose of this study is to bring about an association between the parameters in order to assess water quality. The term quality ascribed to water is itself fuzzy as it is only a relative term. However, in a more general characterization, it can be said that increase in total hardness (TH) is due to increase in calcium and magnesium. But, it is impossible to develop a precise mathematical model that can predict crisp numerical values of calcium or magnesium that correspond to crisp values of hardness. Similar argument holds good for total dissolved solids (TDS). TDS consists of inorganic salts such as carbonates, bicarbonates, chlorides, sulphates, phosphates of calcium, magnesium, potassium, iron, etc… and small amount of organic matter and dissolved gases. The determination of water quality due to contamination is highly unpredictable in crisp numerical terms. It may be necessary, with the help of previous experience, to generate additional linguistic expressions for the definition of related water quality parameters. The potential of fuzzy logic in developing qualitative model for characterization by approximate reasoning really lies here. Fuzzy set theory provides a powerful tool for modelling uncertainty associated with vagueness and imprecision. The present study deals with fifteen parametric variables that include Sodium, Potassium, Iron, Calcium, Magnesium, Bicarbonate, Carbonate, Chloride, Fluoride, Nitrates, Sulphates, Total Dissolved Solids, Conductivity, Hardness, pH. The experimental data is modeled in seven distinct steps. In the first five steps, one antecedent and one consequent models are developed. In the last two steps, two antecedents and one consequent models are developed. In total, seven fuzzy inference systems are built. An attempt has also been made to establish sensitivity of parameters. Results indicate that, TDS and total hardness turns to be very significant parameters to determine water quality. It is concluded that, the fuzzy inference system provides a prudent way to capture uncertainty in relationships among parameters that control the water quality.