Intelligence test case based-approach for crude oil prediction system

Abstract

The intelligent system has the ability to predict the future depending on dataset and rules relations. Petroleum prediction using computational intelligence techniques aims at enhancing the petroleum industry. Using test cases processes, we are able to discover information, more effective for different classes of and prove strictness prediction results. In the case of crude oil prediction, the prediction results are going to be so conservative that it is often felt useless for decision-making, using test cases and clustering functions of the predicted results and empirical values prove to have more precision and efficiency. In this paper, the computational intelligence technique (Fuzzy), test case and clustering functions are used to achieve overlap Strictness Crude Oil Prediction System (SCOPS). The dataset sources are extracted from distinct oilfields sources. The proposed prediction intelligent system manipulates petroleum vagueness data, retesting predicted results and reduces system failures to achieve idealistic results.