6 March 2025 in IEEE Transactions on Instrumentation and Measurement
Traditional torque measurement has greatly depended on the contact between sensors and the rotating shaft. However, the high-speed rotation of the shaft leads to significant sensor wear, compromising the stability of the measurement system. Additionally, the newly collected test data tend to be high in latency and noise, which introduces accuracy challenges for artificial intelligence algorithms in torque measurement. This paper presents the measurement method, hardware platform design, data calibration and software optimization of a torque and rotational speed measurement system, which uses a non-invasive method and accurately estimate torque and rotational speed under both low and high-speed operating conditions by analyzing the mechanical phase difference between two pulse signals. The pulse signals are precisely captured by Hall sensors and an FPGA microcontroller circuit, while signal delay and noise are optimized through a CNN-LSTM artificial intelligence algorithm and system calibration programming. To verify the correctness of the proposed method, a test platform equipped with Hall sensors and servo motor and 200N·m standard torsion device for measuring the torque and rotational speed under torque force generation device's control was implemented. The effectiveness of the proposed method is demonstrated by achieving a measurement error rate within 1%, with the rotational speed error reduced from 3.15% to 0.86% and the torque error decreased to 0.96%.
10 September 2025 in IEEE Transactions on Power Electronics
Early diagnosis of photovoltaic module faults is crucial to reducing maintenance costs. The I–V curve can be intuitively used for diagnosis, but traditionally, only certain feature points on the curve are extracted, neglecting the entire curve’s deformation characteristics. This article analyzes the I–V curves deformation characteristics based on three-diode model, and presents a novel diagnosis method utilizing I–V curve and computer vision. The voltage, current, and power corresponding to each point on the I–V curve is mapped to the three channels in RGB format to form a color image. In this way, the complete deformation features of the I–V curve can be captured and converted into color features on the image. The improved multiaxis vision transformer (I-MaxViT) is proposed for fault diagnosis on the color image by introducing the scaled cosine attention mechanism and log-spaced continuous position deviation into MaxViT block, which reduces the model’s computational complexity. Experimental results demonstrate that the proposed innovative diagnostic method achieves the highest diagnostic accuracy, reaching 94%, when compared to the other six diagnostic algorithms, and shows better universality.