Feng Bu

Fatigue failure is a common mode of failure in ferromagnetic materials, yet traditional electromagnetic detection techniques and assessment models struggle to accurately estimate fatigue levels. To address this, a reliability method for evaluating the fatigue degree of ferromagnetic materials is proposed in this paper, integrating multi-electromagnetic features with a multi-model stacking ensemble learning approach. Four types of electromagnetic parameters, namely magnetic Barkhausen noise, incremental permeability, tangential magnetic field, and hysteresis loops, are collected as feature parameters. Subsequently, a stacking ensemble learning framework is constructed. Least squares support vector machine models serve as base learners with a multivariate linear regression model serving as the meta-learner. Experimental results on Q345 steel samples demonstrate that the proposed method achieves an average error rate of 7.3% in fatigue degree assessment, enabling early fatigue detection and lifespan prediction for materials.

Fatigue failure is a common mode of failure in ferromagnetic materials. Nondestructive electromagnetic testing technology can detect microstructural changes in ferromagnetic materials, but it is challenging to accurately estimate fatigue levels using a single parameter. To address this, a method for evaluating the fatigue degree of ferromagnetic materials is proposed, combining multi-parameter electromagnetic measurements with neural networks. First, a multi-electromagnetic testing system is established to collect four types of electromagnetic parameters, which include magnetic Barkhausen noise, incremental permeability, tangential magnetic field and hysteresis loop. Then, correlation analysis and principal component analysis are performed to reduce the dimensionality of the multi-parameter data, constructing an effective feature parameter set. Finally, an improved neural network model is used to predict fatigue levels. Experimental results on Q345 steel samples demonstrate that this method can accurately assess the fatigue degree of ferromagnetic materials, achieving an accuracy of 91%, enabling early fatigue detection and life prediction for materials.

Processing errors can result in an asymmetric stiffness distribution within a microelectromechanical system (MEMS) disk resonator gyroscope (DRG) and thereby cause a mode mismatch and reduce the mechanical sensitivity and closed-loop scale factor stability. This paper proposes an automatic mode-matching method that utilizes mode reversal to obtain the true resonant frequency of the operating state of a gyroscope for high-precision matching. This method constructs a gyroscope control system that contains a drive closed loop, sense force-to-rebalance (FTR) closed loop, and quadrature error correction closed loop. After the gyroscope was powered on and started up, the x- and y-axes were quickly switched to obtain the resonant frequencies of the two axes through a phase-locked loop (PLL), and the x-axis tuning voltage was automatically adjusted to match the two-axis frequency. The experimental results show that the method takes only 5 s to execute, the frequency matching accuracy reaches 0.01 Hz, the matching state can be maintained in the temperature range of −20 to 60 °C, and the fluctuation of the frequency split does not exceed 0.005 Hz.

The micro disk resonator gyroscope is a micro-mechanical device with potential for navigation-grade applications, where the performance is significantly influenced by the quality factor, which is determined by various energy dissipation mechanisms within the micro resonant structure. To enhance the quality factor, these gyroscopes are typically enclosed in high-vacuum packaging. This paper investigates a wafer-level high-vacuum-packaged (<0.1 Pa) cobweb-like disk resonator gyroscope, presenting a systematic and comprehensive theoretical analysis of the energy dissipation mechanisms, including air damping, thermoelastic damping, anchor loss, and other factors. Air damping is analyzed using both a continuous fluid model and an energy transfer model. The analysis results are validated through quality factor testing on batch samples and temperature characteristic testing on individual samples. The theoretical results obtained using the energy transfer model closely match the experimental measurements, with a maximum error in the temperature coefficient of less than 2%. The findings indicate that air damping and thermoelastic damping are the predominant energy dissipation mechanisms in the cobweb-like disk resonant gyroscope under high-vacuum conditions. Consequently, optimizing the resonator to minimize thermoelastic and air damping is crucial for designing high-performance gyroscopes.

Lying state detection is a typical psychological calculation problem with significant spatiotemporal dynamic changes. However, most existing detection methods have not fully considered the dynamic changes in psychological states, and the distribution information of time series in multimodal spaces has not effectively utilized. The current detection systems lack adaptive fusion methods for multimodal features and it is difficult to extract their spatiotemporal dependencies. Therefore, a novel speech lie detection model was proposed that combines a Convolutional Neural Network (CNN) with a Bidirectional Long Short-Term Memory (BiLSTM) neural network and multimodal feature fusion of Spatiotemporal Attention Mechanism (SAM). CNN has the ability to extract local spatial features, while BiLSTM can handle long sequences and long-term dependencies in bidirectional information flows, and the contextual information in sequences can be captured. The proposed model combined the short-term stationary characteristics in time and the diversity of semantic environments in space, and introduced SAM to fuse multimodal features of temporal and spatial dependencies as feature vectors for the detection model of lying psychological states. The simulation experiment results on the Open-source Real Life Trial lie database show that the average lie detection rate reaches 88.09%. In general, the proposed speech lie detection model has a significant detection accuracy improvement compared to the existing lie detection models.

Micro‐electro‐mechanical system gyroscope detection output is susceptible to drift due to ambient temperature variations. Furthermore, the drive‐mode vibration amplitude is affected by the signal pickup circuit and structural parameters, which significantly influence the temperature drift of the bias and scale factor (SF). This study proposes a vibration amplitude control method based on harmonic amplitude sideband‐ratio (SBR), namely SBR‐AGC, which characterizes the vibration amplitude using the harmonic amplitude ratio of the vibrational electrical signal. The constancy of vibration amplitude is maintained via closed‐loop control to suppress bias and SF temperature drift. The experimental results on cobweb‐like disk resonator gyroscope reveal that the temperature coefficient of bias in the SBR‐AGC mode lies within −20 to 60°C and decreases by 36%, and the temperature coefficient of the SF lies within −10 to 50°C and decreases by 49.7%. Therefore, the environmental adaptability of the gyroscope is effectively improved.

In the domain of lie detection, a common challenge arises from the dissimilar distributions of training and testing datasets. This causes a model mismatch, leading to a performance decline of the pretrained deep learning model. To solve this problem, we propose a lie detection technique based on a domain adversarial neural network employing a dual‐mode state feature. First, a deep learning neural network was used as a feature extractor to isolate speech and facial expression features exhibited by the liars. The data distributions of the source and target domain signals must be aligned. Second, a domain‐antagonistic transfer‐learning mechanism is introduced to build a neural network. The objective is to facilitate feature migration from the training to the testing domain, that is, the migration of lie‐related features from the source to the target domain. This method results in improved lie detection accuracy. Simulations conducted on two professional lying databases with different distributions show the superiority of the detection rate of the proposed method compared to an unimodal feature detection algorithm. The maximum improvement in detection rate was 23.3% compared to the traditional neural network‐based detection method. Therefore, the proposed method can learn features unrelated to domain categories, effectively mitigating the problem posed by different distributions in the training and testing of lying data.

Lie detection technology in speech is a process of lying psychological state recognition according speech signal analysis. Normally, the emotion of tension if felt when people lie. As a result, this tension leads to some subtle changes of the sound channel structure; for example, the semantic characteristics, prosodic characteristics, resonance peak, and the psychoacoustics parameters all can be different from before. In this paper, the development situation of current lie detection technology is presented. Several public speech databases for lie detection are also introduced. Then, the research situation of feature expression, selection, and extraction for lie detection is described. In addition, the research progress of lie detection algorithm is highlighted. Finally, the future direction and the existing problems of lie detection technology in speech are summarized.

The quadrature coupling error is an important factor that affects the detection output of microelectromechanical system (MEMS) gyroscopes. In this study, two quadrature error control methods, quadrature force-to-rebalance control (Mode I) and quadrature stiffness control (Mode II) were analyzed. We obtained the main factors affecting the zero-rate output (ZRO) under force-to-rebalance (FTR) closed-loop detection. The analysis results showed that the circuit phase delay in Mode I caused the quadrature channel to leak into the in-phase channel. However, in Mode II, the quadrature coupling stiffness was corrected in real time, which effectively improved the stability of the ZRO. The changes in the vibration displacement and Q-factor were the main factors for the ZRO drift in Mode II. Therefore, we propose an online compensation method for ZRO drift based on multiparameter fusion. The experimental results on a cobweb-like disk resonator gyroscope (CDRG) with a 340 k Q-factor showed that the bias instability (BI) of Mode II was significantly better than that of Mode I. After online compensation, the BI reached 0.23°/h, and the bias repeatability reached 3.15°/h at room temperature.

The force-to-rebalance (FTR) closed-loop detection method is commonly used to expand the bandwidth (BW) for micro-electro-mechanical system (MEMS) gyroscopes with low-frequency split and high-quality factors. However, the relationship between the BW and output noise is often incompatible; thus, reducing the detection accuracy of the gyroscope. This paper presents an analysis of the BW and noise spectra under modulation-demodulation FTR gyroscopes. The expressions for the BW and the noise-equivalent rate (NER) spectrum are derived to explore the effects of the loop gain on the BW and NER. It is demonstrated that the gain of the amplifier circuit is maximally transferred to the vibration displacement signal conversion part, which can reduce the output noise without affecting the BW. The simulation and experimental results on the Cobweb-like disk resonator gyroscope show that the derived expressions of BW and NER are correct, and the noise optimization method is effective, which provides an idea for the realization of a high-precision MEMS gyroscope.