Digital twin-driven fault diagnosis method for composite faults by combining virtual and real data

Abstract

The subsea production system is essential for the subsea production of oil and gas. Real-time monitoring can ensure safe production. The subsea production control system is the core of the subsea production system and the top priority to be monitored. Troubleshooting the subsea production system involves lifting the component to the platform to repair it. And then send it back subsea. There is no doubt that it is expensive. In this case, some faults will not be handled temporarily if they do not affect the system operation seriously. This leads to multiple faults existing simultaneously, resulting in mixed signals. That makes it difficult to distinguish the state of the subsea production system. Thus, a fault diagnosis method for composite faults is needed. A digital twin-driven fault diagnosis method for composite faults is proposed by combining virtual and real data. Bernoulli Equation combines loss, control, and state parameters to build a digital twin model. A cross-validation enhanced fault diagnosis method is applied to single faults. A Bayesian network-based fault diagnosis model combining virtual and real data is built for composite faults. Field data from an offshore platform in the South Sea of China is used to demonstrate the effect of the proposed method. The results indicate that the method is extremely effective for composite faults of the subsea production control system.