Pipeline safety early warning (PSEW) systems based on distributed optical fiber sensors are used to recognize and locate third-party events that may damage long-distance energy transportation pipelines and are essential to ensure pipeline safety and energy supply. However, the deployment of PSEW systems in real sites is hindered by the high experimental cost of collecting large real-site data sets for model building and the small percentage of labeled data (typically less than 0.5%). Besides, the optical fiber sensors are sensitive to hardware and the environment, ensuring challenges to directly migrate the old PSEW system for a new deployment. In this study, a novel semi-supervised learning model is proposed to monitor the safety of pipelines in real-time. Concretely, the sparse stacked autoencoder trained with unlabeled data is used to extract more robust features, and the fully-connected network trained with a small amount of labeled data is used for location and identification. Encouraging empirical results on the real-world long-distance energy pipelines of the PipeChina confirm that our method achieves better recognition and localization performance in comparison to the baseline with less labeled data. Further, the model size and recognition latency are reduced by 18.9× and 7.9× of the baseline, respectively. Also, the decoded features have better visualization than the input. This work reduces the cost of PSEW system deployments, improves its performance and portability, and will contribute to the widespread use of PSEW systems in the industry.

Previously, we have shown that ASK1-interacting protein 1 (AIP1, also known as DAB2IP), a novel member of the Ras-GAP (Ras-GTPase-activating protein) protein family, opens its conformation in response to tumor necrosis factor (TNF), allowing it to form a complex with TRAF2-ASK1 that leads to activation of ASK1-JNK/p38 signaling in endothelial cells (EC). In the present study, we show that a TNF-inducible 14-3-3-binding site on AIP1 is critical for the opening of its conformation and for the AIP1-mediated TNF signaling. Ser-604, located in the C-terminal domain of AIP1, was identified as a 14-3-3-binding site. TNF treatment of EC induces phosphorylation of AIP1 at Ser-604 as detected by a phospho-specific antibody, with a similar kinetics to ASK1-JNK/p38 activation. 14-3-3 associates with an open, active state of AIP1 assessed by an in vitro pulldown assay. Mutation of AIP1 at Ser-604 (AIP1-S604A) blocks TNF-induced complex formation of AIP1 with 14-3-3. TNF treatment normally induces association of AIP1 with TRAF2-ASK1. The interactions with TRAF2 and ASK1 do not occur with AIP1-S604A, suggesting that phosphorylation at this site not only creates a 14-3-3-binding site but also opens up AIP1, allowing binding to TRAF2 and ASK1. Overexpression of AIP1-S604A blocks TNF-induced ASK1-JNK activation. We further show that RIP1 (the Ser/Thr protein kinase receptor-interacting protein) associates with the GAP domain of AIP1 and mediates TNF-induced AIP1 phosphorylation at Ser-604 and JNK/p38 activation as demonstrated by both overexpression and small interfering RNA knockdown of RIP1 in EC. Furthermore, RIP1 synergizes with AIP1 (but not AIP1-S604A) in inducing both JNK/p38 activation and EC apoptosis. Our results demonstrate that RIP1-mediated AIP1 phosphorylation at the 14-3-3-binding site Ser-604 is essential for TNF-induced TRAF2-RIP1-AIP1-ASK1 complex formation and for the activation of ASK1-JNK/p38 apoptotic signaling.