In Nuclear Power Plants (NPPs), online condition monitoring and the fault detection of structures, systems and components (SSCs) can aid in guaranteeing safe operation. The use of data-driven methods for these tasks is limited by the requirement of physically consistent outcomes, particularly in safety-critical systems. Considering the importance of regulating valves (e.g., safety relief valves and main steam isolation valves), this work proposes a multistage Physics-Informed Neural Network (PINN) for fault detection in such components. Two stages of the PINN are built by developing the process model of the regulating valve, which integrates the basic valve sizing equation into the loss function to jointly train the two stages of the PINN. In the 1st stage, a shallow Neural Network (NN) with only one hidden layer is developed to estimate the equivalent flow coefficient (a key performance indicator of regulating valves) using the displacement of the valve as input. In the 2nd stage, a Deep Neural Network (DNN) is developed to estimate the flow rate expected in normal conditions using inputs such as the estimated flow coefficient from the 1st stage, the differential pressure, and the fluid temperature. Then, the residual, i.e., the difference between the estimated and measured flow rates, is fed into a Deep Support Vector Data Description (DeepSVDD) to detect the occurrence of faults. Moreover, the deviation between the estimated flow coefficients of normal and faulty conditions is used to interpret the consistency of the detection result with physics. The proposed method is, first, applied to a simulation case implemented to emulate the operating characteristics of regulating the valves of NPPs and then validated on a real-world case study based on the DAMADICS benchmark. Compared to state-of-the-art fault detection methods, the obtained results from the proposed method show effective fault detection performance and reasonable flow coefficient estimation, thus guaranteeing the physical consistency of the detection results.

The aero-engine is the heart of an aircraft; its performance deteriorates rapidly due to the high temperature and high-pressure environment during flights. It is necessary to predict the remaining useful life (RUL) to improve the reliability of aero-engines and provide security for reliable flights. In previous flights, the sensors collected a lot of performance parameter data and formed a database regarding the aero-engine degradation process. These performance parameters cannot reflect the degradation process directly. In this paper, fuzzy clustering is applied to divide the degradation stages of the aero-engine, construct the health indicator, and describe the degradation process. Time-series decomposition modeling is applied to predict the degradation process of the health indicator. Based on the idea of similarity comparison, the RUL is predicted by comparing the similarity of time series through example learning. The method is verified and analyzed on the dataset published by National Aeronautics and Space Administration (NASA), and the mean square error (MSE) is 528. The result is better than the comparative method.

Electromechanical actuators (EMAs) have shown a high efficiency in flight surface control with the development of more electric aircraft. In order to identify the abnormalities and potential failures of EMA, a methodology for fault diagnosis is developed. A simulating model of EMA is first built to perform different working states. Based on the modeling of EMA, the corresponding faults are then simulated to re-generate the fault data. Afterwards, a gated recurrent unit (GRU) and co-attention-based fault diagnosis approach is proposed to classify the working states of EMA. Experiments are conducted and a satisfying classification accuracy on simulated data is obtained. Furthermore, fault diagnosis on an actual working system is performed. The experimental results demonstrate that the proposed method has a high efficiency.

Bearings, as integral parts and components in machinery and equipment, play a critical role in system performance. In this paper, the theoretical models of basic axial load rating, basic radial load rating, and friction torque for the planetary thread roller bearing (PTRB) were derived. Then, a detailed comparison was made between the performance indexes of a PTRB prototype and common high-quality bearing products to demonstrate the advantages of PTRB in volume, bearing capacity, and use method. Next, the effects of different structural parameters on the performance indexes of PTRB were analyzed. On this basis, a multi-objective optimization design was carried out on PTRB under axial load and radial load separately with basic load rating and friction torque as optimization objects to obtain PTRB with superior comprehensive performance. Designers could, in consideration of their specific needs and optimized design results, select the structural parameters of PTRB. Furthermore, a dedicated performance test system was researched and developed, which verified the good static bearing capacity and impact resistance of the PTRB prototype. Within the range of dynamic load rating, the test data were slightly larger than the simulation data for the friction torque, manifesting a relatively high degree of precision of the theoretical model.

Prognosis is a key technology to improve reliability, safety and maintainability of products, a lot of researchers have been devoted to this technology. But to improve the predict accuracy of remaining life of products has been difficult. To predict the lifetime specification of pneumatic cylinders with high reliability and long lifetime and small specimen, this paper put forward the prognosis algorithm based on the path classification and estimation (PACE) model. PACE model is based entirely on failure data instead of failure threshold. Pneumatic cylinders normally characterize with failure mechanism wear and tear. Since the minimum working pressure increases with the number of working cycles, the minimum working pressure is chosen as degradation signal. PACE model is fundamentally composed of two operations: path classification and remaining useful life (RUL) estimation. Path classification is to classify a current degradation path as belonging to one or more of previously collected exemplary degradation paths. RUL estimation is to use the resulting memberships to estimate the remaining useful life. In order for verification and validation of PACE prognostic method, six pneumatic cylinders are tested. The test data is analyzed by PACE prognostics. It is found that the PACE based prognosis method has higher prediction accuracy and smaller variance and PACE model is significantly outperform population based prognostics especially for small specimen condition. PACE model based method solved the problem of prediction accuracy for small specimen pneumatic cylinders’ prognosis.