The health status of rotating machinery equipment in nuclear power plants is of paramount importance for ensuring the overall normal operation of the power plant system. In particular, significant failures in large rotating machinery equipment, such as main pumps, pose critical safety hazards to the system. Therefore, this paper takes pump equipment as a representative of rotating machinery in nuclear power plants and proposes a fault diagnosis method based on a multi-scale convolutional self-attention network for three types of faults: outer ring fracture, inner ring fracture, and rolling element pitting corrosion. Within the multi-scale convolutional self-attention network, a multi-scale hybrid feature complementarity mechanism is introduced. This mechanism leverages an adaptive encoder to capture deep feature information from the acoustic signals of rolling bearings and constructs a hybrid-scale feature set based on deep features and original signal characteristics in the time–frequency domain. This approach enriches the fault information present in the feature set and establishes a nonlinear mapping relationship between fault features and rolling bearing faults. The results demonstrate that, without significantly increasing model complexity or the volume of feature data, this method achieves a substantial increase in fault diagnosis accuracy, exceeding 99.5% under both vibration signal and acoustic signal conditions.

A fault diagnosis method using bond graphs in an expert system is proposed for a reactor coolant system. Firstly, the time causality graph and the variable relationship graph are derived from the bond graph. Secondly, the fault signature matrix is obtained by combining the change relationship of fault parameters. Finally, the fault signature matrix is used as the rule of the inference engine design in the expert system for fault diagnosis. In this paper, the key equipment of the reactor coolant system is used to verify the fault diagnosis method of the bond graph expert system, and the path reasoning relationship between alarms is obtained, which can accurately obtain the deep knowledge required by the operators. A new idea for fault diagnosis in a nuclear power plant’s expert system is provided by this method.

Addressing the impact of axial forces and two-phase cross-flow on U-shaped heat transfer tube vibration, this study employs a CFD/CSD-coupled model with a nonlinear energy sink. Simulations of a 9×11 square tube bundle reveal that vibration amplitude increases linearly at low velocities due to decreasing bend stiffness. Additionally, increasing the void fraction at a constant mass flow rate exacerbates the vibration response. These findings provide critical data for assessing the operational life of steam generator U-shaped heat transfer tube.

Natural circulation systems (NCS) are prone to instabilities, they are more unstable compared to forced circulation systems as a result of the low driving head and nonlinearity of the system. Flashing instability is prominent in these systems at low pressure due to the presence of a long nonheated riser to enhance the driving force. RELAP5 code has been identified as one of the Best Estimate (BE) codes used in the analysis of the systems. The studies by different authors showed that the effects of system parameters on instability generally have gained the attention of researchers in recent years. However, these studies have not discussed how these parameters prevent or enhance the commencement of flashing instability. This we sought to achieve in this work, by zeroing in on the inception of flashing instability, by comparing what happened at different heat fluxes. The objective of this work is to investigate the effects of system parameters on the inception of flashing instability in a natural circulation system using the RELAP5 code. With the increase in inlet subcooling and height of the riser, flashing moved to the outlet of the riser, stabilizing the system. However, an opposite effect was observed with an increase in the inlet resistance.

Reliable arc-length regulation is essential in narrow-gap pulsed tungsten inert gas (TIG) welding because restricted groove clearance makes small torch-height errors capable of destabilizing the arc and reducing process repeatability. However, pulse switching, wire–pool interaction, and acquisition noise generate voltage transients that conventional arc-voltage control (AVC) may misinterpret as geometric deviations, whereas strong filtering delays genuine drift correction. This study proposes a reconstruction–decision–adaptation architecture. An experimentally calibrated actuator–arc model supports adaptive Kalman filter (AKF)-based feedback reconstruction; an amplitude–duration–area criterion fixed from open-loop statistics rejects brief disturbances; and only identified effective errors drive online fuzzy-PID gain adaptation. Using fixed decision thresholds, NSGA-II jointly tunes estimator and controller parameters based on voltage RMSE and cumulative actuator travel. Across 20 simulation seeds, the tuned configuration reduced voltage RMSE and ramp-disturbance error by 15.8% and 51.0%, respectively, while travel decreased by 1.9%. Physical welding tests demonstrated improved voltage regulation while maintaining actuator activity: the 13.0 V comparison reduced RMSE by 19.7% and adjustment events by 8.3%, while six additional records at three prescribed voltages showed consistent mean voltage regulation within the tested conditions.