Query:
学者姓名:梁伟
Refining:
Year
Type
Indexed by
Source
Complex
Co-
Language
Clean All
Abstract :
The input-output relationship of inductive displacement sensors is typically nonlinear, which demands numerous computational resources for precise calculation. Therefore, the traditional analytical methods for the inductive displacement sensors cannot meet the real-time high-precision measurement requirements. In response to the aforementioned issues, this paper proposes an optimized Long Short-Term Memory (LSTM) neural networks based on one-dimensional convolutional neural networks (1DCNN) to modeling the input-output relationship of the inductive displacement sensor. First, the measurement principle of the inductive displacement sensors was analyzed, and the analytical model of the sensor output was derived. And the influences of the key parameters of sensors on the relationship between the induced voltage and the displacement were studied. Then, the 1DCNN-LSTM-AT network for modelling the input-output relationship of the inductive displacement sensor was studied. The spatial features of historical induced electromotive force (EMF) data generated by the induction coil were initially extracted using the 1DCNN network. And these spatial features were then utilized as input to the LSTM neural network to capture the temporal features of the historical induced EMF data. Subsequently, the spatiotemporal features of the induced EMF data were fed into the regression prediction layer to compute the displacement measurement results corresponding to the current input. Moreover, the attention mechanism was used for the 1DCNN-LSTM model to enhance the prediction accuracy and stability of the model. Finally, the experimental results demonstrate that the proposed 1DCNN-LSTM-AT model achieves an average absolute percentage error (MAPE) of 3.1%, significantly outperforming traditional models such as LSTM (29.3%), CNN (4.7%), and ANN (4.3%). This paper provides a new method for modelling the nonlinear relationships of the inductive displacement sensor, and presents a fresh perspective for research in the data processing of nonlinear sensors.
Keyword :
1DCNN 1DCNN attention mechanism attention mechanism inductive displacement sensor inductive displacement sensor LSTM LSTM nonlinear mapping nonlinear mapping
Cite:
Copy from the list or Export to your reference management。
GB/T 7714 | Li, Jinlin , Yang, Xinyue , Zhong, Shuncong et al. Modeling of an inductive displacement sensor based on 1DCNN-LSTM-AT [J]. | MEASUREMENT SCIENCE AND TECHNOLOGY , 2025 , 36 (1) . |
MLA | Li, Jinlin et al. "Modeling of an inductive displacement sensor based on 1DCNN-LSTM-AT" . | MEASUREMENT SCIENCE AND TECHNOLOGY 36 . 1 (2025) . |
APA | Li, Jinlin , Yang, Xinyue , Zhong, Shuncong , Liang, Wei , Guo, Qiaoying . Modeling of an inductive displacement sensor based on 1DCNN-LSTM-AT . | MEASUREMENT SCIENCE AND TECHNOLOGY , 2025 , 36 (1) . |
Export to | NoteExpress RIS BibTex |
Version :
Abstract :
Accurate rotational speed measurement is a prerequisite for realizing the condition monitoring and fault diagnosis of rotating equipment. This study proposes a novel rotational speed measurement method based on optical coherent displacement measurement. An optical coherence system is used to measure the relative depth of the shaft surface with uniformly etched micro-indentations on the circumferential surface. Fast Fourier transform (FFT) and the Hanning window energy centrobaric method (HnWECM) are used to process the collected photoelectric signals to obtain depth information and thereby realize the measurement of surface microindentations. During the operation, the rotational speed of the shaft is obtained by calculating the ratio of the angular difference between the relative depth of the rectangular pulses of the surface and the time interval. The experimental validation of the response is performed. The experimental results show that in the range of 0 rpm to 60 rpm, the indication error is <1 %, the nonlinearity error is <0.3584 %, and the repeatability error is <0.28 %. In the range of 0 rpm to 600 rpm, the rotational speed measurement method performed well with an indication error of <0.5 %, a maximum nonlinear error of 0.22 %, and a repeatability error of no >0.28 %. Compared with the results reported in existing literature, the proposed method offers advantages in terms of accuracy, linearity, and repeatability.
Keyword :
FFT FFT Hanning window Hanning window Micro-indentation Micro-indentation Optical measurement Optical measurement Rotational speed measurement Rotational speed measurement
Cite:
Copy from the list or Export to your reference management。
GB/T 7714 | Liang, Wei , Hong, Xiaodong , Huang, Dichang et al. Novel rotational speed measuring method based on micro-indentation-shaft detected by optical coherent system [J]. | OPTICS AND LASERS IN ENGINEERING , 2025 , 184 . |
MLA | Liang, Wei et al. "Novel rotational speed measuring method based on micro-indentation-shaft detected by optical coherent system" . | OPTICS AND LASERS IN ENGINEERING 184 (2025) . |
APA | Liang, Wei , Hong, Xiaodong , Huang, Dichang , Chen, Linnan , Zhong, Jianfeng , Zhang, Qiukun et al. Novel rotational speed measuring method based on micro-indentation-shaft detected by optical coherent system . | OPTICS AND LASERS IN ENGINEERING , 2025 , 184 . |
Export to | NoteExpress RIS BibTex |
Version :
Abstract :
This study investigated the static coupling characteristics of a column-type six-component force/moment transducer. An output model of the transducer was developed and validated through finite element method (FEM) simulations. Length-to-diameter ratio (RLD), deflection angles of strain gauge, and multi-component loads were analysed in relation to transducer coupling. Six transducers with different RLDs and strain gauge deflection angles were tested under single and multi-component loads. It was found that the coupling of Fz under Fx or Fy was pronounced when RLD was small. The coupling of Fz under Fx increased from less than 5 % to 34 % when RLD decreased from 3.5 to 2.0. However, couplings of other components under Fz were not sensitive to RLD. The strain gauge deflection angles had the largest effect on the coupling of the Fz component, its coupling increased from 2.5 % to over 17.5% under Mx as the deflection angle increased from 0 degrees to 6 degrees. However, couplings of other components caused by Fz were not sensitive to strain gauge deflection angle. The couplings under multicomponent loads were found to approximate the superposition of those under single-component loads, with deviations within 2 %, indicating good linearity and easy decoupling of the transducer.
Keyword :
Column-type Column-type Coupling characteristics Coupling characteristics Force measurement Force measurement Six-component Six-component
Cite:
Copy from the list or Export to your reference management。
GB/T 7714 | Liang, Wei , Xu, Zhenting , Xie, Zhijie et al. Coupling characteristic of column-type six-component force/ moment transducers [J]. | MEASUREMENT , 2025 , 242 . |
MLA | Liang, Wei et al. "Coupling characteristic of column-type six-component force/ moment transducers" . | MEASUREMENT 242 (2025) . |
APA | Liang, Wei , Xu, Zhenting , Xie, Zhijie , Hong, Xiaodong , Zhong, Jianfeng , Zhong, Shuncong et al. Coupling characteristic of column-type six-component force/ moment transducers . | MEASUREMENT , 2025 , 242 . |
Export to | NoteExpress RIS BibTex |
Version :
Abstract :
The outstanding performance of current machine-learning fault diagnosis methods is mainly attributed to the availability of a large amount of labeled training data. However, in practical dynamic weighing systems, the high costs and variability of operating conditions limit the availability of reliable training data, hampering engineering fault diagnoses in dynamic weighing systems. To address this issue, this study proposes a novel cross-sensor fault diagnosis method based on multi-feature fusion using a transfer component analysis (TCA)-weighted k-nearest-neighbor (WKNN) network. Using this method, time- and frequency-domain features are extracted from a laboratory-simulated set of fault data with small batches of real operational data. Source and target domain features are fused, and TCA is applied to map the source and target domain samples to a latent space using kernel functions to reduce the distribution differences among the samples. Finally, the WKNN is employed as a metric learner to enhance small-sample data matching and classification to improve diagnostic accuracy. The results show that with three samples per support set, the proposed method achieves a diagnostic accuracy of 93.33%. Compared with other approaches, the proposed method exhibits stronger generalizability for diagnostic knowledge transference from sensor to dynamic weighing failure data, effectively improving precision in on-site small-sample environments and reducing sample imbalances.
Keyword :
cross-sensor cross-sensor dynamic weighing system dynamic weighing system fault diagnosis fault diagnosis multi-feature fusion multi-feature fusion transfer component analysis transfer component analysis weighted k-nearest neighbor algorithm weighted k-nearest neighbor algorithm
Cite:
Copy from the list or Export to your reference management。
GB/T 7714 | Liang, Wei , Chen, Zhixiong , Zhong, Jianhua et al. Multi-feature fusion-based TCA-WKNN cross-sensor fault diagnosis method for dynamic weighing [J]. | MEASUREMENT SCIENCE AND TECHNOLOGY , 2024 , 35 (1) . |
MLA | Liang, Wei et al. "Multi-feature fusion-based TCA-WKNN cross-sensor fault diagnosis method for dynamic weighing" . | MEASUREMENT SCIENCE AND TECHNOLOGY 35 . 1 (2024) . |
APA | Liang, Wei , Chen, Zhixiong , Zhong, Jianhua , Liao, Huazhong , Zhong, Shuncong . Multi-feature fusion-based TCA-WKNN cross-sensor fault diagnosis method for dynamic weighing . | MEASUREMENT SCIENCE AND TECHNOLOGY , 2024 , 35 (1) . |
Export to | NoteExpress RIS BibTex |
Version :
Abstract :
Space deployable structures are able to be deployed from a folded state to a predetermined or desired configuration. They are superior in terms of spatial packaging ratio, controllability, and structural complexity, in order to solve the space limitations for aerospace vehicles. Therefore, they have been applied in structural designs and concepts for various aerospace missions, including space support booms, space deployable antennas, solar panels, as well as flexible solar sails. Recent development of advanced manufacturing technologies and applications of novel smart materials and structures, brings new degree of design freedom to space deployable mechanics, inspiring novel space deployable mechanisms, especially for smart driving and control strategies. Here, we present a review on development of mechanics and smart driving of space deployable structures. Advantages and limitations for various deployable mechanisms are also presented to reveal further insights. The trends and future deployable mechanics are directed by further advancements in terms of modularisation, intelligences, and deployment precision. Multi-disciplinary cross-integrations are leading the way for future breakthroughs in novel deployable mechanics and intelligent driving control for space explorations.
Keyword :
Deployable Deployable Driving Driving Mechanics Mechanics Smart Smart Structure Structure
Cite:
Copy from the list or Export to your reference management。
GB/T 7714 | Wang, Bing , Zhu, Juncheng , Zhong, Shuncong et al. Space deployable mechanics: A review of structures and smart driving [J]. | MATERIALS & DESIGN , 2024 , 237 . |
MLA | Wang, Bing et al. "Space deployable mechanics: A review of structures and smart driving" . | MATERIALS & DESIGN 237 (2024) . |
APA | Wang, Bing , Zhu, Juncheng , Zhong, Shuncong , Liang, Wei , Guan, Chenglong . Space deployable mechanics: A review of structures and smart driving . | MATERIALS & DESIGN , 2024 , 237 . |
Export to | NoteExpress RIS BibTex |
Version :
Abstract :
In response to the high-precision and multi-dimensional force measurement requirements in the fields of biology and medicine, this paper proposes a novel three-dimensional microforce measurement method based on the broadband optical coherence. A novel, compact, and low-coupling elastic element was designed, with a maximum outer diameter of 26 mm and a capacity of 50 g in the X-, Y-, and Z-directions, respectively. The functional relationship between the displacements of the three detecting points on the elastic element and the applied external force was derived based on the elastic mechanics theory. And it was also verified by the finite element method. A self-built optics system was set up to sense the displacements of the three points on the elastic element. The experiments results showed that the resolution in the X-, Y-, and Z-directions was 0.10 mN, 0.11 mN and 0.13 mN, respectively. In the measuring range of (10-50) g, the maximum coupling rate was 4.55 %, and the maximum linear error was 4.70 %. The maximum repeatability error was only 0.615 %. The method and sensor were verified with good characteristics of high resolution, low coupling rate, high linearity and high accuracy, comparing to other reported researches. The multi-dimensional force measuring method could be used in the fields of biology and medicine.
Keyword :
Force measurement Force measurement Micro force Micro force Optical coherence Optical coherence Three-dimensional Three-dimensional
Cite:
Copy from the list or Export to your reference management。
GB/T 7714 | Liang, Wei , Li, Xingqiang , Zhong, Shuncong et al. Three-dimensional micro-force measurement method based on broadband optical coherence [J]. | MEASUREMENT , 2024 , 234 . |
MLA | Liang, Wei et al. "Three-dimensional micro-force measurement method based on broadband optical coherence" . | MEASUREMENT 234 (2024) . |
APA | Liang, Wei , Li, Xingqiang , Zhong, Shuncong , Zhang, Qiukun , Lin, Jiewen . Three-dimensional micro-force measurement method based on broadband optical coherence . | MEASUREMENT , 2024 , 234 . |
Export to | NoteExpress RIS BibTex |
Version :
Abstract :
为保证多维力传感器测量准确度,必须对该传感器进行静态标定,因此研究多维力传感器静态标定装置具有重要意义.首先,从多维力传感器静态标定需求出发,按工作原理将目前国内外主流使用的多维力传感器静态标定装置划分为静重式和叠加式这两类.然后,介绍了砝码式、杠杆式、自动式这三种静重式多维力传感器静态标定装置和液压式、龙门式、试验机式、移动平台式、电机式这五种叠加式多维力传感器静态标定装置的工作原理,对各种装置的国内外研究现状和存在不足分别进行了评述,并分析对比了各种装置的关键技术特点及优缺点.最后,从通用性、重复性、多维力模拟能力、成本效益等方面对多维力传感器静态标定装置进行了展望,指出了装置的设计和实施面临的挑战.该研究为后续多维力传感器静态标定装置的研创提供了参考.
Keyword :
串接 串接 叠加式 叠加式 多维力传感器 多维力传感器 静态标定装置 静态标定装置 静重式 静重式
Cite:
Copy from the list or Export to your reference management。
GB/T 7714 | 梁伟 , 谢智杰 , 黎兴强 et al. 多维力传感器静态标定装置的研究进展 [J]. | 自动化仪表 , 2024 , 45 (9) : 1-13 . |
MLA | 梁伟 et al. "多维力传感器静态标定装置的研究进展" . | 自动化仪表 45 . 9 (2024) : 1-13 . |
APA | 梁伟 , 谢智杰 , 黎兴强 , 张秋坤 , 徐震廷 , 顾立勋 et al. 多维力传感器静态标定装置的研究进展 . | 自动化仪表 , 2024 , 45 (9) , 1-13 . |
Export to | NoteExpress RIS BibTex |
Version :
Abstract :
针对医学领域科学研究、临床疾病的诊断与手术等对微小力值测量的迫切需求,对医学领域微小力值传感测量研究方向、进展及其应用情况进行了综述.首先,从医学领域微小力值测量的需求出发,分析了测量的特点与要求,介绍了电容式、电阻应变式和压电式等传统电学式微小力传感测量技术的国内外研究成果,分析了电学式测量方法的技术特点与不足;然后,系统地介绍了目前微小力值测量中广泛采用的光学式一维及多维传感测量技术,对基于光学相干层析成像(OCT)、法布里-珀罗干涉仪(FPI)、光纤布拉格光栅(FBG)、强度调制型光纤传感等的光学式微小力值传感测量原理、方法、技术特点进行了分析;最后,对国内外最新研究成果、发展水平及在医学领域的应用情况进行了分类整理和归纳评述,对不同测量原理与方法的技术特性、优缺点、适用测量范围与应用场景进行了系统性的对比分析.研究结果表明:当前医学领域微小力值传感测量存在的主要问题包括微小力值无法溯源、高精度宽量程测量需求无法满足,并且在多种参数的并行监测和同步测量、复合传感测量、集成光路式传感技术等方面有待进一步研究和探索.该综述可为后续医学领域微小力值传感测量研究方向与思路提供参考.
Keyword :
光学式力传感测量 光学式力传感测量 光学相干层析成像 光学相干层析成像 光纤布拉格光栅 光纤布拉格光栅 力传感器 力传感器 力的测量仪表 力的测量仪表 多维力传感测量 多维力传感测量 微小力值 微小力值 法布里-珀罗干涉仪 法布里-珀罗干涉仪
Cite:
Copy from the list or Export to your reference management。
GB/T 7714 | 梁伟 , 黎兴强 , 陈志雄 et al. 医学领域微小力值传感测量技术的研究进展 [J]. | 机电工程 , 2024 , 41 (11) : 2068-2086 . |
MLA | 梁伟 et al. "医学领域微小力值传感测量技术的研究进展" . | 机电工程 41 . 11 (2024) : 2068-2086 . |
APA | 梁伟 , 黎兴强 , 陈志雄 , 陈林楠 , 杨晓翔 . 医学领域微小力值传感测量技术的研究进展 . | 机电工程 , 2024 , 41 (11) , 2068-2086 . |
Export to | NoteExpress RIS BibTex |
Version :
Abstract :
在轴重式动态汽车衡的服役状态下,由于受到重型货车频繁的加卸载循环冲击,会导致其内部螺栓发生松弛脱落,针对这一问题,提出了一种基于莱维飞行改进粒子群算法优化的广义回归神经网络(LPSO-GRNN)的轴重式动态汽车衡螺栓松紧状态预测模型,并结合振动信号特征提取,将该模型应用于汽车衡螺栓松紧状态的预测。首先,研究并提取了螺栓不同松紧状态下输出振动信号的波形指标、峰值指标、脉冲指标、峭度指标等信号特征,并将其作为模型的共同输入特征向量;然后,采用莱维飞行提高了粒子群优化算法的寻优能力,通过产生随机步长,提高了算法的全局寻优能力,避免算法陷入局部最优值;利用改进的算法对广义回归神经网络(GRNN)的光滑因子进行了优化,得到了全局最优的光滑因子;最后,通过设计实验,分别使用广义回归神经网络(GRNN)、粒子群算法优化广义回归神经网络(PSO-GRNN)和LPSO-GRNN,以此来对螺栓松紧状态进行了预测,并将预测结果与实际情况进行了对比分析。实验结果表明:基于LPSO-GRNN建立的螺栓松紧状态预测模型,其预测准确率可达到95%。研究结果表明:该螺栓松紧状态预测模型可以有效提高汽车衡螺栓松紧预测的准确率,同时有效解决粒子群算法容易陷入局部最优收敛的问题。
Keyword :
LPSO-GRNN预测模型 LPSO-GRNN预测模型 广义回归神经网络 广义回归神经网络 振动信号特征提取 振动信号特征提取 粒子群算法优化 粒子群算法优化 莱维飞行 莱维飞行 螺栓紧固 螺栓紧固 轴重式动态汽车衡 轴重式动态汽车衡
Cite:
Copy from the list or Export to your reference management。
GB/T 7714 | 梁伟 , 陈志雄 , 欧阳忠杰 et al. 基于LPSO-GRNN模型的螺栓松紧状态预测研究 [J]. | 机电工程 , 2023 , 40 (11) : 1814-1822 . |
MLA | 梁伟 et al. "基于LPSO-GRNN模型的螺栓松紧状态预测研究" . | 机电工程 40 . 11 (2023) : 1814-1822 . |
APA | 梁伟 , 陈志雄 , 欧阳忠杰 , 龚晟炜 , 钟建华 , 钟舜聪 et al. 基于LPSO-GRNN模型的螺栓松紧状态预测研究 . | 机电工程 , 2023 , 40 (11) , 1814-1822 . |
Export to | NoteExpress RIS BibTex |
Version :
Abstract :
Dynamic characteristics play a crucial role in evaluating the performance of weight sensors and are essential for achieving fast and accurate weight measurements. This study focuses on a weight sensor based on optical coherence displacement. Using finite element analysis, the sensor was numerically simulated. Frequency domain and time domain dynamic response characteristics were explored through harmonic response analysis and transient dynamic analysis. The superior dynamic performance and reduced conditioning time of the non-contact optical coherence-based displacement weight sensor were confirmed via a negative step response experiment that compared the proposed sensing method to strain sensing. Moreover, dynamic performance metrics for the optical coherence displacement-type weight sensor were determined. Ultimately, the sensor's dynamic performance was enhanced using the pole-zero placement method, decreasing the overshoot to 4.72% and reducing the response time to 0.0132 s. These enhancements broaden the sensor's operational bandwidth and amplify its dynamic response capabilities.
Keyword :
displacement type displacement type dynamic characteristics dynamic characteristics optical coherence optical coherence weight sensor weight sensor
Cite:
Copy from the list or Export to your reference management。
GB/T 7714 | Lai, Zhengchuang , Ouyang, Zhongjie , Zhong, Shuncong et al. Dynamic Characterization of Optical Coherence-Based Displacement-Type Weight Sensor [J]. | SENSORS , 2023 , 23 (21) . |
MLA | Lai, Zhengchuang et al. "Dynamic Characterization of Optical Coherence-Based Displacement-Type Weight Sensor" . | SENSORS 23 . 21 (2023) . |
APA | Lai, Zhengchuang , Ouyang, Zhongjie , Zhong, Shuncong , Liang, Wei , Yang, Xiaoxiang , Lin, Jiewen et al. Dynamic Characterization of Optical Coherence-Based Displacement-Type Weight Sensor . | SENSORS , 2023 , 23 (21) . |
Export to | NoteExpress RIS BibTex |
Version :
Export
Results: |
Selected to |
Format: |