In this study, we investigated the performance and reliability of commercial corrosion sensors for monitoring the integrity of piping systems in various fluid environments as an alternative to ultrasonic transducers. To this end, we investigated pipes’ wall-thinning using commercial electrical resistance (ER), linear polarization resistance (LPR), and ultrasonic transducer (UT) sensors under various operating environments. A pilot-scale closed-loop test bed was built to simulate a real pipeline flow situation, from which the sensor data were collected and analyzed. Experimental results indicate that, in the case of the LPR sensor, it is challenging to accurately measure the corrosion rate when a specific measure exceeds the threshold in a severe corrosion environment. In contrast, the ER sensor could measure metal loss under all conditions and reflect the corresponding characteristics. The metal loss (about 0.25 mm) of the real pipe after the experiment was confirmed to be equal to the metal loss (0.254 mm) measured by the sensor. Furthermore, the regression analysis revealed a high correlation between the results obtained from the ER and UT sensors. Thus, evaluating the remaining thickness of the piping system using the commercial ER sensor is deemed to be effective and reliable.

Vibration-based diagnosis of propulsion-shaft misalignment supports condition monitoring in electric ships, but reported accuracies are often inflated by overlapping-window leakage and by untested cross-recording, cross-session, and cross-speed generalization. We evaluated leakage-free, deployment-oriented protocols (chronological, leave-one-recording-out (LORO), leave-one-session-out, and leave-one-speed-out) on a 50 kW electric-propulsion land-based test system with six accelerometer channels under 0, 2, and 4 mm offset misalignments, comparing feature-engineered gradient-boosting models, raw-signal deep models, and nominal-speed order-normalized features. Under LORO evaluation, a raw-signal one-dimensional convolutional neural network (1D-CNN) achieved 0.93–1.00 accuracy and outperformed LightGBM in all 15 folds. Under leave-one-speed-out testing, MiniRocket retained 0.775 accuracy, whereas InceptionTime dropped to 0.468. Fixed-Hz features outperformed nominal-speed order-normalized features by 0.079 (p = 0.022), and single-window 1D-CNN inference required 0.50 ms on a CPU. Recording-level and cross-session evaluation are therefore essential for reliable misalignment diagnosis, and raw-signal models provide the strongest deployable performance on the present test rig.