Search Results (28)

In recent years, deep learning-based end-to-end Text-To-Speech (TTS) models have made significant progress in enhancing speech naturalness and fluency. However, existing Variational Inference Text-to-Speech (VITS) models still face challenges such as insufficient pitch modeling, inadequate contextual dependency capture, and low inference efficiency in the decoder. To address these issues, this paper proposes an improved TTS framework named Q-VITS. Q-VITS incorporates Rotary Position Embedding (RoPE) into the text encoder to enhance long-sequence modeling, adopts a frame-level prior modeling strategy to optimize one-to-many mappings, and designs a style extractor based on a diffusion model for controllable style rendering. Additionally, the proposed decoder ConfoGAN integrates explicit F0 modeling, Pseudo-Quadrature Mirror Filter (PQMF) multi-band synthesis and Conformer structure. The experimental results demonstrate that Q-VITS outperforms the VITS in terms of speech quality, pitch accuracy, and inference efficiency in both subjective Mean Opinion Score (MOS) and objective Mel-Cepstral Distortion (MCD) and Root Mean Square Error (RMSE) evaluations on a single-speaker dataset, achieving performance close to ground-truth audio. These improvements provide an effective solution for efficient and controllable speech synthesis. Full article

The paper presents results of experimental research on tyre–road contact stress distributions, measured indoors for a motorsport slick tyre. The triaxial contact stress distributions have been measured using the complex transducer containing a transversal array of 30 sensing pins covering the entire contact patch width. Wheel displacement in the longitudinal direction was measured using a rotary encoder. The parameters allocated for the experimental programme have included different values of tyre inflation pressure, vertical load, camber angle and toe angle. All measurements were performed at low longitudinal speed in free-rolling conditions. The influence of tyre functional parameters on the contact patch shape and size has been discussed. The stress distributions on each orthogonal direction are presented in multiple formats, such as 2D graphs in which the curves show the stresses measured by each sensing element versus contact length; surfaces with stress values plotted as vertical coordinates versus contact patch length and width; and colour maps for stress distributions and orientations of shear stress vectors. The effects of different parameter types and values on stress distributions have been emphasised and analysed. Furthermore, the magnitude and position of local extreme values for each stress distribution have been investigated with respect to the above-mentioned tyre functional parameters. Full article

The stability of gearbox bearings is crucial to the operational efficiency and safety of industrial equipment, as their faults can lead to downtime, economic losses, and safety risks. Traditional models face difficulties in handling complex industrial time-series data due to insufficient feature extraction capabilities and poor training stability. Although transformers show advantages in fault diagnosis, their ability to model local dependencies is limited. To improve feature extraction from time-series data and enhance model robustness, this paper proposes an innovative method based on the ViT. Time-series data were converted into two-dimensional images using polar coordinate transformation and Gramian matrices to enhance classification stability. A lightweight front-end encoder and depthwise feature extractor, combined with multi-scale depthwise separable convolution modules, were designed to enhance fine-grained features, while two-dimensional rotary position encoding preserved temporal information and captured temporal dependencies. The constructed RoPE-DWTrans model implemented a unified feature extraction process, significantly improving cross-dataset adaptability and model performance. Experimental results demonstrated that the RoPE-DWTrans model achieved excellent classification performance on the combined MCC5 and HUST gearbox datasets. In the fault category diagnosis task, classification accuracy reached 0.953, with precision at 0.959, recall at 0.973, and an F1 score of 0.961; in the fault category and severity diagnosis task, classification accuracy reached 0.923, with precision at 0.932, recall at 0.928, and an F1 score of 0.928. Compared with existing methods, the proposed model showed significant advantages in robustness and generalization ability, validating its effectiveness and application potential in industrial fault diagnosis. Full article

Addressing the significant challenge of speech enhancement in ultra-low-Signal-to-Noise-Ratio (SNR) scenarios for Unmanned Aerial Vehicle (UAV) voice communication, particularly under edge deployment constraints, this study proposes the Edge-Deployed Band-Split Rotary Position Encoding Transformer (Edge-BS-RoFormer), a novel, lightweight band-split rotary position encoding transformer. While existing deep learning methods face limitations in dynamic UAV noise suppression under such constraints, including insufficient harmonic modeling and high computational complexity, the proposed Edge-BS-RoFormer distinctively synergizes a band-split strategy for fine-grained spectral processing, a dual-dimension Rotary Position Encoding ($\mathrm{RoPE}$) mechanism for superior joint time–frequency modeling, and $\mathrm{FlashAttention}$ to optimize computational efficiency, pivotal for its lightweight nature and robust ultra-low-SNR performance. Experiments on our self-constructed DroneNoise-LibriMix (DN-LM) dataset demonstrate Edge-BS-RoFormer’s superiority. Under a −15 dB SNR, it achieves Scale-Invariant Signal-to-Distortion Ratio (SI-SDR) improvements of 2.2 dB over Deep Complex U-Net (DCUNet), 25.0 dB over the Dual-Path Transformer Network (DPTNet), and 2.3 dB over HTDemucs. Correspondingly, the Perceptual Evaluation of Speech Quality (PESQ) is enhanced by 0.11, 0.18, and 0.15, respectively. Crucially, its efficacy for edge deployment is substantiated by a minimal model storage of 8.534 MB, 11.617 GFLOPs (an 89.6% reduction vs. DCUNet), a runtime memory footprint of under 500MB, a Real-Time Factor (RTF) of 0.325 (latency: 330.830 ms), and a power consumption of 6.536 W on an NVIDIA Jetson AGX Xavier, fulfilling real-time processing demands. This study delivers a validated lightweight solution, exemplified by its minimal computational overhead and real-time edge inference capability, for effective speech enhancement in complex UAV acoustic scenarios, including dynamic noise conditions. Furthermore, the open-sourced dataset and model contribute to advancing research and establishing standardized evaluation frameworks in this domain. Full article

Named Entity Recognition (NER) is a fundamental task in Natural Language Processing (NLP) that supports applications such as information retrieval, sentiment analysis, and text summarization. While substantial progress has been made in NER for widely studied languages like English, Arabic presents unique challenges due to its morphological richness, orthographic ambiguity, and the frequent occurrence of nested and overlapping entities. This paper introduces a novel Arabic NER framework that addresses these complexities through architectural innovations. The proposed model incorporates a Hybrid Feature Fusion Layer, which integrates external lexical features using a cross-attention mechanism and a Gated Lexical Unit (GLU) to filter noise, while a Compound Span Representation Layer employs Rotary Positional Encoding (RoPE) and Bidirectional GRUs to enhance the detection of complex entity structures. Additionally, an Enhanced Multi-Label Classification Layer improves the disambiguation of overlapping spans and assigns multiple entity types where applicable. The model is evaluated on three benchmark datasets—ANERcorp, ACE 2005, and a custom biomedical dataset—achieving an F1-score of 93.0% on ANERcorp and 89.6% on ACE 2005, significantly outperforming state-of-the-art methods. A case study further highlights the model’s real-world applicability in handling compound and nested entities with high confidence. By establishing a new benchmark for Arabic NER, this work provides a robust foundation for advancing NLP research in morphologically rich languages. Full article

With the rapid increase in the number of Earth Observation Satellites (EOSs), research on autonomous mission scheduling has become increasingly critical for optimizing satellite sensor operations. While most existing studies focus on static environments or initial planning states, few address the challenge of dynamic request replanning for real-time sensor management. In this paper, we tackle the problem of multi-satellite rapid mission replanning under dynamic batch-arrival observation requests. The objective is to maximize overall observation revenue while minimizing disruptions to the original scheme. We propose a framework that integrates stochastic master-satellite mission allocation with single-satellite replanning, supported by reactive scheduling policies trained via deep reinforcement learning. Our approach leverages mission sequence modeling with attention mechanisms and time-attitude-aware rotary positional encoding to guide replanning. Additionally, scalable embeddings are employed to handle varying volumes of dynamic requests. The mission allocation phase efficiently generates assignment solutions using a pointer network, while the replanning phase introduces a hybrid action space for direct task insertion. Both phases are formulated as Markov Decision Processes (MDPs) and optimized using the PPO algorithm. Extensive simulations demonstrate that our method significantly outperforms state-of-the-art approaches, achieving a 15.27% higher request insertion revenue rate and a 3.05% improvement in overall mission revenue rate, while maintaining a 1.17% lower modification rate and achieving faster computational speeds. This demonstrates the effectiveness of our approach in real-world satellite sensor applications. Full article

To address the issue of efficiently reusing the massive amount of unstructured knowledge generated during the handling of track circuit equipment faults and to automate the construction of knowledge graphs in the railway maintenance domain, it is crucial to leverage knowledge extraction techniques to efficiently extract relational triplets from fault maintenance text data. Given the current lag in joint extraction technology within the railway domain and the inefficiency in resource utilization, this paper proposes a joint extraction model for track circuit entities and relations, integrating Global Pointer and tensor learning. Taking into account the associative characteristics of semantic relations, the nesting of domain-specific terms in the railway sector, and semantic diversity, this research views the relation extraction task as a tensor learning process and the entity recognition task as a span-based Global Pointer search process. First, a multi-layer dilate gated convolutional neural network with residual connections is used to extract key features and fuse the weighted information from the 12 different semantic layers of the RoBERTa-wwm-ext model, fully exploiting the performance of each encoding layer. Next, the Tucker decomposition method is utilized to capture the semantic correlations between relations, and an Efficient Global Pointer is employed to globally predict the start and end positions of subject and object entities, incorporating relative position information through rotary position embedding (RoPE). Finally, comparative experiments with existing mainstream joint extraction models were conducted, and the proposed model’s excellent performance was validated on the English public datasets NYT and WebNLG, the Chinese public dataset DuIE, and a private track circuit dataset. The F1 scores on the NYT, WebNLG, and DuIE public datasets reached 92.1%, 92.7%, and 78.2%, respectively. Full article

Advanced microfabrication technologies have revolutionized the field of reflective encoders by integrating all necessary optical components and electronics into a miniature single-chip solution. Contemporary semiconductor sensors could operate at wide tolerance ranges that make them ideal for integration into compact and lightweight modular encoder kit systems. However, in order to achieve the high accuracy of the operating encoder, precise mechanical installation is still needed. To overcome this issue and exploit the full potential of modern sensors, the self-calibratable absolute modular rotary encoder is developed. The equal division average (EDA) method by combining the angular position readings from multiple optical sensors is used to simplify the installation process and ensure the high accuracy of the system. The produced prototype encoder is experimentally tested vs. the reference encoder and the measurement deviations of using different numbers and arrangements of optical sensors are determined. The obtained results show encoder ability to handle the mounting errors and minimize the initial system deviation by more than 90%. Full article

We present a method for improving the amplitude and angular error of inductive position sensors, by advancing the design of receiver coil systems with multiple windings on two layers of a printed circuit board. Multiple phase-shifted windings are connected in series, resulting in an increased amplitude of the induced voltage while decreasing the angular error of the sensor. The amplitude increase for a specific number of windings can be predicted in closed form. Windings are placed electrically in series by means of a differential connection structure, without adversely affecting the signal quality while requiring a minimal amount of space in the layout. Further, we introduce a receiver coil centerline function which specifically enables dense, space-constrained designs. It allows for maximization of the number of possible coil windings while minimizing the impact on angular error. This compromise can be fine-tuned freely with a shape parameter. The application to a typical rotary encoder design for motor control applications with five periods is presented as an example and analyzed in detail by 3D finite-element simulation of 18 different variants, varying both the number of windings and the type of centerline functions. The best peak-to-peak angular error achieved in the examples is smaller than 0.1° electrically (0.02° mechanically, periodicity 5) under nominal tolerance conditions, in addition to an amplitude increase of more than 170% compared to a conventional design which exhibits more than twice the angular error. Amplitude gains of more than 270% are achieved at the expense of increased angular error. Full article

Advancements in machining technology demand higher speeds and precision, necessitating improved control systems in equipment like CNC machine tools. Due to lead errors, structural vibrations, and thermal deformation, commercial CNC controllers commonly use rotary encoders in the motor side to close the position loop, aiming to prevent insufficient stability and premature wear and damage of components. This paper introduces a multivariable iterative learning control (MILC) method tailored for flexible feed drive systems, focusing on enhancing dynamic positioning accuracy. The MILC employs error data from both the motor and table sides, enhancing precision by injecting compensation commands into both the reference trajectory and control command through a norm-optimization process. This method effectively mitigates conflicts between feedback control (FBC) and traditional iterative learning control (ILC) in flexible structures, achieving smaller tracking errors in the table side. The performance and efficacy of the MILC system are experimentally validated on an industrial biaxial CNC machine tool, demonstrating its potential for precision control in modern machining equipment. Full article

In the realm of large language models (LLMs), extending the context window for long text processing is crucial for enhancing performance. This paper introduces SBA-RoPE (Segmented Base Adjustment for Rotary Position Embeddings), a novel approach designed to efficiently extend the context window by segmentally adjusting the base of rotary position embeddings (RoPE). Unlike existing methods, such as Position Interpolation (PI), NTK, and YaRN, SBA-RoPE modifies the base of RoPE across different dimensions, optimizing the encoding of positional information for extended sequences. Through experiments on the Pythia model, we demonstrate the effectiveness of SBA-RoPE in extending context windows, particularly for texts exceeding the original training lengths. We fine-tuned the Pythia-2.8B model on the PG-19 dataset and conducted passkey retrieval and perplexity (PPL) experiments on the Proof-pile dataset to evaluate model performance. Results show that SBA-RoPE maintains or improves model performance when extending the context window, especially on longer text sequences. Compared to other methods, SBA-RoPE exhibits superior or comparable performance across various lengths and tasks, highlighting its potential as an effective technique for context window extension in LLMs. Full article

Bubble growth processes are highly influenced by the elongational viscosity of the blowing agent-loaded polymer melt. Therefore, the elongational viscosity is an important parameter for the development of new polymers for foaming applications, as well as for the prediction of bubble growth processes. Thus, knowledge of the initial expansion and deformation behavior in dependency on the polymer, the blowing agent concentration, and the process conditions is necessary. This study presents a novel method for the in-line observation and analysis of the initial expansion and deformation behavior within the bead foam extrusion process. For this purpose, nitrogen as the blowing agent was injected into the polymer melt (PS and PLA) during the extrusion process. The in-line observation system consists of a borescope equipped with a camera, which was integrated into the water box of an underwater pelletizer. The camera is controlled by a developed trigger by means of angular step signal analysis of a rotary encoder on the cutter shaft of the underwater pelletizer. Thus, images can be taken at any time during the foaming process depending on the cutter position to the die outlet. It is shown that the developed method provides reliable results and that the differences of the initial expansion and deformation behavior during bubble growth can be analyzed in-line in dependency on real foaming process conditions and the type of polymer used. Full article

(1) Background: Technically, a simple, inexpensive, and non-invasive method of ascertaining volume changes in thoracic and abdominal cavities are required to expedite the development and validation of pulmonary mechanics models. Clinically, this measure enables the real-time monitoring of muscular recruitment patterns and breathing effort. Thus, it has the potential, for example, to help differentiate between respiratory disease and dysfunctional breathing, which otherwise can present with similar symptoms such as breath rate. Current automatic methods of measuring chest expansion are invasive, intrusive, and/or difficult to conduct in conjunction with pulmonary function testing (spontaneous breathing pressure and flow measurements). (2) Methods: A tape measure and rotary encoder band system developed by the authors was used to directly measure changes in thoracic and abdominal circumferences without the calibration required for analogous strain-gauge-based or image processing solutions. (3) Results: Using scaling factors from the literature allowed for the conversion of thoracic and abdominal motion to lung volume, combining motion measurements correlated to flow-based measured tidal volume (normalised by subject weight) with R² = 0.79 in data from 29 healthy adult subjects during panting, normal, and deep breathing at 0 cmH₂O (ZEEP), 4 cmH₂O, and 8 cmH₂O PEEP (positive end-expiratory pressure). However, the correlation for individual subjects is substantially higher, indicating size and other physiological differences should be accounted for in scaling. The pattern of abdominal and chest expansion was captured, allowing for the analysis of muscular recruitment patterns over different breathing modes and the differentiation of active and passive modes. (4) Conclusions: The method and measuring device(s) enable the validation of patient-specific lung mechanics models and accurately elucidate diaphragmatic-driven volume changes due to intercostal/chest-wall muscular recruitment and elastic recoil. Full article

Despite an emerging interest in soft and rigid pneumatic lightweight robots, the pneumatic rotary actuators available to date either are unsuitable for servo pneumatic applications or provide a limited angular range. This study describes the functional principle, design, and manufacturing of a servo pneumatic rotary actuator that is suitable for continuous rotary motion and positioning. It contains nine radially arranged linear bellows actuators with rollers that push forward a cam profile. Proportional valves and a rotary encoder are used to control the bellows pressures in relation to the rotation angle. Introducing freely programmable servo pneumatic commutation increases versatility and allows the number of mechanical components to be reduced in comparison to state-of-the-art designs. The actuator presented is designed to be manufacturable using a combination of standard components, selective laser sintering, elastomer molding with novel multi-part cores and basic tools. Having a diameter of 110 mm and a width of 41 mm, our prototype weighs less than 500 g, produces a torque of 0.53 Nm at 1 bar pressure and a static positioning accuracy of 0.31° with no limit of angular motion. By providing a description of design, basic kinematic equations, manufacturing techniques, and a proof of concept, we enable the reader to envision and explore future applications. Full article

In this paper, a new solution for an electro-hydraulic servo drive is proposed, which consists of two electro-hydraulic servo drives: one with a hydraulic cylinder and one with a hydraulic rotary motor. In the proposed drive, the linear actuator is attached to a horizontal base and the hydraulic motor is mounted on the actuator piston rod. Thus, the output signal of the drive is the lifting and lowering of the element suspended on the rope. The paper describes the structure, kinematics, dynamics, and control of a novel electro-hydraulic servo drive. A servo valve and a proportional valve are used to control the flow of the hydraulic cylinder and the hydraulic motor. Special attention is paid to the construction of two actuators in one drive unit. The controller is based on the PLC controller. The measuring system uses laser displacement sensors and an encoder. The results of laboratory investigations are discussed in the paper. The proposed drive contains all of the characteristics of a mechatronic device. The main contribution of this study is the proposal of the controller architecture and the algorithm to control the speed and position when lifting or lowering loads. Full article