Assessment of pipeline stability in the Gulf of Mexico during hurricanes using dynamic analysis

Pipelines are the critical link between major offshore oil and gas developments and the mainland. Any inadequate on-bottom stability design could result in disruption and failure, having a devastating impact on the economy and environment. Predicting the stability behavior of offshore pipelines in hurricanes is therefore vital to the assessment of both new design and existing assets. The Gulf of Mexico has a very dense network of pipeline systems constructed on the seabed. During the last two decades, the Gulf of Mexico has experienced a series of strong hurricanes, which have destroyed, disrupted and destabilized many pipelines. This paper first reviews some of these engineering cases. Following that, three case studies are retrospectively simulated using an in-house developed program. The study utilizes the offshore pipeline and hurricane details to conduct a Dynamic Lateral Stability analysis, with the results providing evidence as to the accuracy of the modeling techniques developed.

DyPipe: A Holistic Approach to Accelerating Dynamic Neural Networks with Dynamic Pipelining

Dynamic neural network(NN)techniques are increasingly important because they facilitate deep learning techniques with more complex network architectures.However,existing studies,which predominantly optimize the static computational graphs by static scheduling methods,usually focus on optimizing static neural networks in deep neural network(DNN)accelerators.We analyze the execution process of dynamic neural networks and observe that dynamic features introduce challenges for efficient scheduling and pipelining in existing DNN accelerators.We propose DyPipe,a holistic approach to optimizing dynamic neural network inferences in enhanced DNN accelerators.DyPipe achieves significant performance improvements for dynamic neural networks while it introduces negligible overhead for static neural networks.Our evaluation demonstrates that DyPipe achieves 1.7x speedup on dynamic neural networks and maintains more than 96%performance for static neural networks.

Real-time implementation of Kalman filter for unsteady flow measurement in a pipe

A Kalman filter which estimates unsteady laminar flow in a pipe is implemented on a real-time computing system. The plant model is the optimised finite element model of pipeline dynamics considering unsteady laminar friction. A steady-state Kalman filter is built based on the model of pipeline dynamics. Pressure signals at both ends of a target section of a pipe are input to the model of pipeline dynamics, and as an output of the model an estimated pressure signal at a mid-point of the pipe is obtained. Difference between measured and estimated pressure signals at the mid-point is fed back to the model of pipeline dynamics to modify state variables of the model. According to the Kalman filter principle, the state variables of the model are adjusted so that they converge to real values. It is demonstrated that real-time implementation of the Kalman filter is possible with the sampling time of 0.1 ms.