In order to identify oil pipeline work conditions accurately and quickly, fuzzy C-means algorithm method is applied to this paper. For obtaining clustering standard, sixteen groups of raw data, which include each work condition, are selected from massive pressure data collected in the field. Analyzed data for convenience, each group of raw data is normalized with mean zero and high-frequency noise is eliminated from pressure signal by wavelet transform. The analyzed results on time-domain prove that statistical indexes can clearly and responsively describe pressure variation caused by changed work condition. The paper extracts time-domain statistical indexes from de-noised pressure data as characteristic indexes for fuzzy clustering. Comprehensively considered efficiency and accuracy of fuzzy C-means algorithm, six time-domain parameters are regarded as the characteristic indexes. The clustering centers, which are found by fuzzy C-means algorithm with sixteen groups of samples' eigenvectors, are regarded as the standard of pattern recognition for work conditions. It is identified by calculating Euclidean norm between awaiting identification operation status and clustering center. Application results verify that field operation status of oil pipeline is recognized effectively and accurately. The accuracy rate of recognition is by 95%. Especially pipeline leakage is identified accurately.