This study introduces a deep learning engine designed for the non-destructive automatic detection of defects within weld beads. A 1D waveform ultrasound signal was collected using an A-scan pulser receiver to gather defect signals from inside the weld bead. We established 5,108 training datasets and 500 test datasets for five pass/fail labels in this study. We developed a multi-branch deep fusion network (MBDFN) model that independently trains 1D-CNN for local pattern learning within a sequence and 2D-CNN for spatial feature extraction and then combines them in an ensemble method, achieving a classification accuracy of 92.2%. The resulting deep learning engine has potential applications in automatic welding robots or welding inspection systems, allowing for rapid determination of internal defects without compromising the integrity of the finished product.

Optical receiver modules play an important role in receiving signals from the Fiber Bragg Grating (FBG) sensors used for monitoring in civil structures, power facilities, and other sensing applications. When multiple sensors are used, more photo diodes receive optical signals; thin-film beam splitters with polarization characteristics are therefore used to reduce the size of the optical receiver module. Using a reflective semiconductor optical amplifier (R-SOA) with polarization characteristics in a sensing system with an FBG sensor, a structure that is less sensitive to polarization was developed by packaging a quad optical receiver module. A stabilization of ±14.67% was achieved using the dual optical receiver module in polarization and of ±11.20% with the quad optical receiver module in polarization.

In this paper, we present a sensing device with the optical temperature sensors-based quad receiver (Quad-RX) module and a security module. In addition, in order to prevent cyberattacks on critical national infrastructures and key facilities, we implemented symmetric-key and secure hash algorithm-based hardware security modules in the key elements of the sensing device. A preliminary test was conducted prior to a field trial to verify the performance of the developed sensing device. The accuracy and stability of the sensing device were then verified for 1 month in a field test at facilities for energy storage systems and photovoltaic converters in sewage treatment plants.