A seismic data acquisition system based on wireless network transmission is designed to improve the low-frequency response and low sensitivity of the existing acquisition system. The system comprises of a piezoelectric transducer, a high-resolution data acquisition system, and a wireless communication module. A seismic piezoelectric transducer based on a piezoelectric simply supported beam using PMN-PT is proposed. High sensitivity is obtained by using a new piezoelectric material PMN-PT, and a simply supported beam matching with the PMN-PT wafer is designed, which can provide a good low-frequency response. The data acquisition system includes an electronic circuit for charge conversion, filtering, and amplification, an FPGA, and a 24-bit analog-to-digital converter (ADC). The wireless communication was based on the ZigBee modules and the WiFi modules. The experimental results show that the application of the piezoelectric simply supported beam based on PMN-PT can effectively improve the sensitivity of the piezoelectric accelerometer by more than 190%, compared with the traditional PZT material. At low frequencies, the fidelity of the PMN-PT piezoelectric simply supported beam is better than that of a traditional central compressed model, which is an effective expansion of the bandwidth to the low-frequency region. The charge conversion, filtering, amplification, and digitization of the output signal of the piezoelectric transducer are processed and, finally, are wirelessly transmitted to the monitoring centre, achieving the design of a seismic data acquisition system based on wireless transmission.

No abstract

After the production of printed circuit boards (PCB), PCB manufacturers need to remove defected boards by conducting rigorous testing, while manual inspection is time-consuming and laborious. Many PCB factories employ automatic optical inspection (AOI), but this pixel-based comparison method has a high false alarm rate, thus requiring intensive human inspection to determine whether alarms raised from it resemble true or pseudo defects. In this paper, we propose a new cost-sensitive deep learning model: cost-sensitive siamese network (CSS-Net) based on siamese network, transfer learning and threshold moving methods to distinguish between true and pseudo PCB defects as a cost-sensitive classification problem. We use optimization algorithms such as NSGA-II to determine the optimal cost-sensitive threshold. Results show that our model improves true defects prediction accuracy to 97.60%, and it maintains relatively high pseudo defect prediction accuracy, 61.24% in real-production scenario. Furthermore, our model also outperforms its state-of-the-art competitor models in other comprehensive cost-sensitive metrics, with an average of 33.32% shorter training time.

No abstract

No abstract