Abstract: Detecting a pipeline’s abnormal status, which is typically a blockage and leakage accident, is important for the continuity and safety of mine backfill. The pipeline system for gravity-transport high-density backfill (GHB) is complex. Specifically designed, efficient, and accurate abnormal pipeline detection methods for GHB are rare. This work presents a long short-term memory-based deep learning (LSTM-DL) model for GHB pipeline blockage and leakage diagnosis. First, an industrial pipeline monitoring system was introduced using pressure and flow sensors. Second, blockage and leakage field experiments were designed to solve the problem of negative sample deficiency. The pipeline’s statistical characteristics with different working statuses were analyzed to show their complexity. Third, the architecture of the LSTM-DL model was elaborated on and evaluated. Finally, the LSTM-DL model was compared with state-of-the-art (SOTA) learning algorithms. The results show that the backfilling cycle comprises multiple working phases and is intermittent. Although pressure and flow signals fluctuate stably in a normal cycle, their values are diverse in different cycles. Plugging causes a sudden change in interval signal features; leakage results in long variation duration and a wide fluctuation range. Among the SOTA models, the LSTM-DL model has the highest detection accuracy of 98.31% for all states and the lowest misjudgment or false positive rate of 3.21% for blockage and leakage states. The proposed model can accurately recognize various pipeline statuses of complex GHB systems.