Heat exchangers play an important role in offshore oil and gas production and offshore low-temperature waste heat power generation. Heat exchanger health management mainly relies on performance parameter monitoring; however, accurate fault mode identification remains a challenge and the diagnostic results are difficult to interpret. This paper proposed an interpretable intelligent diagnosis method for heat exchangers based on Shapley Additive exPlanation and eXtreme Gradient Boosting. Firstly, secondary parameters characterizing the health state of heat exchangers are constructed based on online monitored data such as pressure and temperature. Then, the multi-dimensional feature vector is constructed by integrating the online monitored data and secondary parameters. The XGBoost fault diagnosis model for leakage and scaling faults is established with the multi-dimensional feature vector as the input. To improve the model performance on diagnosis, a grid search optimization algorithm is adopted. After the fault diagnosis of a heat exchanger is completed, the SHAP method is introduced to analyze the contribution of features by quantifying their influence on the fault diagnosis results. Finally, the effectiveness of the proposed method is verified by the heat exchanger fault simulation experiment. The proposed method achieved a diagnosis accuracy of 99.79%, which has better performance than the traditional fault diagnosis method.

The degradation of a machine is nonlinear, which brings challenges to its performance assessment during condition monitoring, especially when there is a run-in period. Technically, the quantification of mechanical degradation is to define a distance metric from a health baseline. This paper develops an integrated condition monitoring scheme, where the degradation evaluation and fault diagnosis are combined by using one technical framework. Specifically, an optimum healthy state (OHS) is determined based on the clustering center of the self-organizing map (SOM) neural network instead of the commonly used initial working state. Then, the distance metric deviating from the OHS is defined as a health index, where the perceptual vibration hashing is improved to make it more sensitive to degradation. Visualized fault diagnosis is carried out by the SOM when the health index exceeds the preset threshold. Two cases with experiments are conducted to demonstrate the accuracy and robustness of the proposed method.