Accurate Pipeline Blockage Detection with Low-Cost Multi-modal Sensing

Industrial sensing applications place a premium on cost-effectiveness and accuracy. Traditional approaches often use expensive, invasive sensors from concern that inexpensive, non-invasive sensors will incur many false positives. High sensor cost leaves many lower value sites with sparse automation and no sensing. In this paper, we show how a combination of different types of sensors can provide reliable detection of industrial events while avoid false positives. Our use of multiple, low-cost sensors can enable greater levels of automation for these applications. We explore this problem by studying a specific application: blockages in oil flow lines common in cold weather. We sense changes in fluid flow from pipe skin temperature, and combine readings with acoustic data to avoid false positives and be robust to environmental changes. We demonstrate that our approach is effective with field experiments, and explore a broader range of problems in laboratory experiments. Our general approach applies to the classes of problems where false positives from one sensing modality can be resolved by multi-modal sensing.