Generator Speed Research Articles

LFC-UNet: learned lossless medical image fast compression with U-Net.

In the field of medicine, the rapid advancement of medical technology has significantly increased the speed of medical image generation, compelling us to seek efficient methods for image compression. Neural networks, owing to their outstanding image estimation capabilities, have provided new avenues for lossless compression. In recent years, learning-based lossless image compression methods, combining neural network predictions with residuals, have achieved performance comparable to traditional non-learning algorithms. However, existing methods have not taken into account that residuals often concentrate excessively, hindering the neural network's ability to learn accurate residual probability estimation. To address this issue, this study employs a weighted cross-entropy method to handle the imbalance in residual categories. In terms of network architecture, we introduce skip connections from U-Net to better capture image features, thereby obtaining accurate probability estimates. Furthermore, our framework boasts excellent encoding speed, as the model is able to acquire all residuals and residual probabilities in a single inference pass. The experimental results demonstrate that the proposed method achieves state-of-the-art performance on medical datasets while also offering the fastest processing speed. As illustrated by an instance using head CT data, our approach achieves a compression efficiency of 2.30 bits per pixel, with a processing time of only 0.320 seconds per image.

AN INVESTIGATION OF THE EFFECTS OF WIND VELOCITY ON THE PERFORMANCE OF TURBINES AND GENERATORS

Variations in wind speed at 4,6 and 8 m altitudes were analyzed using a 24-hour dataset. The greatest recorded wind velocity was 3.3 m/s at a height of 8 meters, and the lowest was around 2.4 m/s at a height of 4 meters. The investigation also identified discrepancies in velocity between the generator and turbine while they were operating with and without a load. The turbine's speed increased when there was no weight present. The peak wind velocity reached 3.9 meters per second, accompanied by a similar variation of 5.4 rotations per minute. The average discrepancy in rotational velocity between the turbine and generator during periods of low wind was 3.74 RPM. This discovery establishes a fundamental basis for comprehending the movement of wind and enabling future in-depth explorations in the field of atmospheric sciences. The generator's performance is assessed by the measurement of current and voltage, which serves to highlight its versatility and effectiveness. The correlation between wind velocity and generator rotational speed is crucial for energy conversion, since the turbine's velocity needs to be adjusted to match the heightened load, affecting the generator's speed.

DBVS-APF-RRT*: A global path planning algorithm with ultra-high speed generation of initial paths and high optimal path quality

During the last decade, RRT* algorithm has been widely concerned by researchers because of its asymptotic optimality. However, the slow convergence rate of the RRT* algorithm leads to poor quality of the optimal paths at small number of iterations. Meanwhile, searching the initial path slowly limits its application scenarios. To overcome these problems, a directionally biased variable step APF-RRT* (DBVS-APF-RRT*) algorithm is proposed in this paper. Firstly, a novel directionally biased variable step sampling strategy is used in RRT* algorithm to quickly generate the initial path. Then, global random sampling and key region sampling strategies are added to improve global search ability and optimal path quality. At the same time, an artificial potential field (APF) method is introduced to improve the ability of obstacle avoidance. In addition, we propose a pruning strategy based on triangular inequality with direct connection of goal points to reduce the number of redundant nodes and shorten the path length. Finally, DBVS-APF-RRT* algorithm is compared with RRT*, Bias-RRT*, Informed-RRT* and Bias-P-RRT* algorithms to verify its superiority of optimal path quality, stability of the algorithm and its rapidity of finding the initial path.

High order sliding mode observer-based fault-tolerant control scheme for DFIG in wind energy applications with model predictive controller

This research presents a novel fault-tolerant predictive power control method for a Doubly-fed induction generator (DFIG) used in wind turbine control systems. Due to the proposed control mechanism, the system can continue to function effectively despite open-circuit or short-circuit faults in the insulated-gate bipolar transistors (IGBTs) of the MPC controller. Depending on the type of problem and its location, the tolerant IGBT overcomes power oscillations and limits the power converter's potential switching states. By monitoring the optimal generator speed, wind turbine control systems strive to maximize power output. For wind turbines operating in the partial-load area, a fault-tolerant model predictive control strategy is recommended in order to achieve control goals despite disturbances, uncertainties, sensor, and actuator difficulties. A high order sliding mode observer (HOSMO) is used to evaluate both the actual states and sensor-faults at the same time. A high order sliding mode (HOSM) control strategy based on the MPC controller is used to regulate the speed of wind turbines in order to harness the wind's maximum power.

Prefrontal cortex activation while walking did not change but gait speed improved after a randomized physical therapy intervention

BackgroundHigher prefrontal cortex (PFC) activation while walking may indicate reduced gait automaticity.AimWe examine whether PFC activation during walking improves after training in older adults at risk for mobility disability.MethodsForty-two adults aged ≥ 65 participated in a randomized clinical trial (NCT026637780) of a 12-week timing and coordination physical therapy intervention to improve walking (n = 20 intervention, n = 22 active control). PFC activation was measured by functional near-infrared spectroscopy (fNIRS) during four walking tasks over 15 m, each repeated 4 times: even surface walking, uneven surface walking, even dual-task, uneven dual-task; dual-task was reciting every other letter of the alphabet while walking. Gait speed and rate of correct letter generation were recorded. Linear mixed models tested between arm differences in change of fNIRS, gait speed, and letter generation from baseline to follow-up (12-week, 24-week, and 36-week).ResultsIntervention arms were similar in mean age (74.3 vs. 77.0) and baseline gait speed (0.96 vs. 0.93 m/s). Of 24 comparisons of between arm differences in the fNIRS signals, only two were significant which were not supported by differences at other follow-up times or on other tasks. Gait speed, particularly during dual-task conditions, and correct letter generation did improve post-intervention but improvements did not differ by arm.Discussion and ConclusionsAfter training, PFC activation during walking generally did not improve and did not differ by intervention arm. Improvements in gait speed without increased PFC activation may point toward more efficient neural control of walking.

Research and application of a Model selection forecasting system for wind speed and theoretical power generation in wind farms based on classification and wind conversion

This study focuses on ensuring the stable operation of the power grid by accurately forecasting the theoretical power generation capacity of wind turbine units, especially in scenarios integrating significant amounts of renewable energy into the grid. The forecasting process involves two key steps: initially forecasting wind speeds and then estimating theoretical power generation using wind turbine power conversion curves. This article proposes a wind speed forecasting system based on deep learning, integrating multiple hybrid models and employing deep learning algorithms to select the optimal wind speed hybrid forecasting model, optimized by the multi-objective mayfly optimization algorithm. Additionally, a wind energy conversion simulation system for wind turbines has been developed, precisely simulating the physical process of converting wind energy into electrical energy. This system, in conjunction with wind speed forecasting, estimates the theoretical power generation of wind farms. The results of this research hold significant practical implications for enhancing the operational efficiency of wind power, strengthening the grid's supply-demand balance, and increasing the economic and environmental value of wind power projects.

Application of machine learning algorithms to character interaction in single-player role-playing games

Character interaction in single-player role-playing games refers to the role interactions between the player character and the non-player characters (NPCs) in the game including dialogue, social interaction, cooperation, and competition, which are designed and implemented to achieve certain game goals and effects. This paper summarizes and compares machine learning algorithms applied to game development using a paper review and theoretical analysis, aiming to provide new solutions for optimizing and improving algorithms commonly used in game design. The ADEM algorithm can automate the evaluation of semantic relevance and logical coherence of character dialogues, but it is more costly in the pre-training phase and more difficult to perform domain adaptation for specific game content. The BERT algorithm can improve the speed of character dialogue generation through the training of unlabeled text, and then improve the flexibility of the dialogue through a small amount of labeled text for domain adaptation and fine-tuning, but it lacks in the generation of smooth and complex text and other aspects. The GAN algorithm can learn from a single or a small number of action sequences to achieve the transformation and mixing of character actions, thus generating multiple action gestures. However, its training process may suffer from problems such as pattern collapse leading to degradation in the quality of the generation, and it is also difficult to set a uniform objective criterion to determine the loss function.

Wind Power Determination for Maximum Power Point Tracking in Lab-scale Multi-MW Wind Energy Systems

The low voltage ride through (LVRT) grid code requirements are pushing the new era of multi MW wind energy conversion systems (WECS) to full power topologies. Lab scale emulation of such multi MW systems usually substitutes the wind energy conversion by a torque producing emulator (e.g. DC machine). Nevertheless, the complete study of the wind energy system is more insightful and allows a better analysis of the WECS. This work focuses on the design of the blades and the wind power calculation for lab scale emulation of multi MW wind energy systems. Theoretical analysis for the design of the lab scale system is presented and experimental results show the wind power characteristic curves for maximum power point tracking of variable speed generators.

A Novel Approach to Using Dual-Field Excited Synchronous Generators as Wind Power Generators

Integrating wind power generators, whose frequency varies in a wide range due to varying wind speeds, into a grid is a formidable problem. At present, the use of permanent magnet synchronous generators (PMSG) and doubly fed induction generators (DFIG) as wind generators with suitable control is the best possible solution. However, a dual-field excited synchronous generator (DESG), which has two windings on the rotor, can also be used for the same purpose with appropriate control. A new control strategy, which essentially employs the d-axis and q-axis components of the alternator terminal voltage, is suggested here. This strategy essentially results in exciting the two field windings with a slip frequency. This eventually holds the stator frequency constant, irrespective of the rotor speed of the wind generator. The difference between the required frequency and the natural frequency, analogous to the rotor speed of the wind power generator, is the slip frequency. The ring modulator automatically adjusts the slip frequency depending on the actual speed of the generator’s rotor. This paper uses the ANSYS MAXWELL 2022 R1 software to design a DESG and uses a ring modulator as the control function generator for feedback with ANSYS TWIN BUILDER 2022 R1. Simulations are carried out using transient–transient co-simulation by combining both of these software tools for cases of both a constant-speed input and of a variable-speed input to the rotor of the machine. Moreover, a mathematical model of the DESG as a wind generator with the proposed controlled strategy is used to perform the stability analysis of a nine-bus three-machine system, and the results are compared with those of conventional wind generators.

Wind generation and power system interaction analysis using probabilistic techniques

. Energy power from renewable sources, especially wind turbine generators, are being considered as an important generation alternative in the electrical power systems around the world due to their non contaminant nature and low environmental effects. In particular, the power supplied by wind generators is widely random following the random nature of weather conditions; therefore a probabilistic approach during planning seems much more appropriate than the deterministic approach actually used in the electrical utilities. This paper presents a methodology that allows the application of probabilistic analysis, thru the use of programming tools, in the load flow planning studies. The methodology described provides the opportunity to obtain the steady state response in systems where wind power exists using a wind power generation model (WPGM) and an iterative routine to the load flow analysis considering each value of generation of the wind sources. A wind power generation model (WPGM) was developed using a random wind speed generator. The random wind speed generator describes the Weibull distribution of wind measurements, and then using Montecarlo simulation techniques, a program in Visual Basic executes the automatic evaluation of random samples of speed of wind considering the characteristic power curve of a wind turbine, obtaining a widely database of wind generation conditions. As a result of the investigation, a computational tool was developed in order to use it, in combination with the PSS/E load flow analysis software, for steady state power system analysis. The methodology was used as an assessment tool to identify the effects of wind turbines generation into the substation voltages and power flow profiles in the power network, for a wind farm project intended to be installed in Margarita Island. The analysis aimed to identify the transmission adjustments, reinforcements and expansions needed to guarantee the wind farm project integration successful into the power system.

Intelligent path planning by an improved RRT algorithm with dual grid map

This research addresses the limitations of existing autonomous vehicle path planning algorithms, notably their slow processing speeds and suboptimal route efficiency. We introduce an innovative path planning algorithm that synergizes the A* algorithm with the Rapidly-exploring Random Tree (RRT) approach. This hybrid model significantly enhances route timeliness and reliability, particularly in obstacle avoidance scenarios for driverless vehicles. Our methodology employs a 'two-level map' approach, where a lower-resolution grid map is derived from a high-resolution map. Utilizing the A* algorithm on this framework, we ascertain a preliminary 'coarse path' for the navigation target. The RRT algorithm, modified to reduce the traditional redundancy associated with random uniform sampling, is then applied for probabilistic sampling within this defined area. ovel aspect of our approach is the simultaneous generation of two trees, originating from both the start and end points, guided by a target-biased strategy and dual-direction theory. This method probabilistically expands towards the node of the opposite tree, thereby enhancing both the generation speed and trajectory viability. Further refinements are made through a pruning process, optimizing the path, and employing Bezier curves for smoothing, ensuring compliance with the dynamic constraints of Ackerman chassis vehicles. Comparative analysis in complex environments demonstrates the superiority of our proposed algorithm. It outperforms traditional methods with a 400 % increase in planning speed relative to the RRT-Connect algorithm, and a 30 % reduction in average path length. Additionally, the mean curvature of routes generated by our algorithm is 19 % lower than traditional routes, underscoring significant advancements in both the timeliness and viability of the planned routes.

Research on a Mongolian Text to Speech Model Based on Ghost and ILPCnet

The core challenge of speech synthesis technology is how to convert text information into an audible audio form to meet the needs of users. In recent years, the quality of speech synthesis based on end-to-end speech synthesis models has been significantly improved. However, due to the characteristics of the Mongolian language and the lack of an audio corpus, the Mongolian speech synthesis model has achieved few results, and there are still some problems with the performance and synthesis quality. First, the phoneme information of Mongolian was further improved and a Bang-based pre-training model was constructed to reduce the error rate of Mongolian phonetic synthesized words. Second, a Mongolian speech synthesis model based on Ghost and ILPCnet was proposed, named the Ghost-ILPCnet model, which was improved based on the Para-WaveNet acoustic model, replacing ordinary convolution blocks with stacked Ghost modules to generate Mongolian acoustic features in parallel and improve the speed of speech generation. At the same time, the improved vocoder ILPCnet had a high synthesis quality and low complexity compared to other vocoders. Finally, a large number of data experiments were conducted on the proposed model to verify its effectiveness. The experimental results show that the Ghost-ILPCnet model has a simple structure, fewer model generation parameters, fewer hardware requirements, and can be trained in parallel. The average subjective opinion score of its synthesized speech reached 4.48 and the real-time rate reached 0.0041. It ensures the naturalness and clarity of synthesized speech, speeds up the synthesis speed, and effectively improves the performance of the Mongolian speech synthesis model.

IPC‐based robust disturbance accommodating control for load mitigation and speed regulation of wind turbines

SummaryOver the past few decades, global demand for renewable energy has been rising steadily. To meet this demand, there has been an exponential growth in size of wind turbines (WTs) to capture more energy from wind. Consequent increase in weight and flexibility of WT components has led to increased structural loading, affecting reliability of these wind energy conversion systems. Spatio‐temporal variation of rotor effective wind field acts as a disturbance to a WT system, hence, necessitating controllers that can cancel this disturbance. Additionally, assumptions made in extracting linear models for controller design lead to modeling errors resulting from changing operating conditions. Previous attempts have proposed robust controllers incorporating wind disturbance models. However, these controllers have been evaluated on smaller WTs, which experience lower structural loading than larger ones. Additionally, a majority these controllers are based on collective pitch control (CPC), hence do not address loading in the blades. To address these challenges, this contribution proposes an independent pitch‐based robust disturbance accommodating controller (IPC‐RDAC) for reducing structural loads and regulating generator speed in utility‐scale WTs. The proposed controller is designed using ‐synthesis approach and is evaluated on the 5 MW National Renewable Energy Laboratory (NREL) reference WT. Its performance is evaluated against a gain‐scheduled proportional integral (GSPI)‐based reference open‐source controller (ROSCO) and a CPC‐based RDAC (CPC‐RDAC) controller, developed previously by the authors. Simulation results for various wind conditions show that the proposed controller offers improved performance in blade and tower load mitigation, as well a generator speed regulation.

Synthetical reasoning for hybrid tabular-textual question answering over multitasking model

Hybrid tabular-textual question answering (QA) is a crucial task in natural language processing that involves reasoning and locating answers from various information sources, primarily through numerical reasoning and span extraction. Cur-rent techniques in numerical reasoning often rely on autoregressive models to decode program sequences. However, these methods suffer from exposure bias and error propagation, which can significantly decrease the accuracy of program generation as the decoding process unfolds. To address these challenges, this paper proposes a novel multitasking hybrid tabular-textual question answering (MHTTQA) framework. Instead of generating operators and operands step by step, this framework can independently generate entire program tuples in parallel. This innovative approach solves the problem of error propagation and greatly improves the speed of program generation. The effectiveness of the method is demonstrated through experiments using the ConvFinQA and MultiHiertt datasets. Our proposed model outperforms the strong FinQANet baselines by 7% and 7.2% Exe/Prog Acc and the MT2Net baselines by 20.9% and 9.4% EM/F1. In addition, the program generation rate of our method far exceeds that of the baseline method. Additionally, our non-autoregressive program generation method exhibits greater resilience to an increasing number of numerical reasoning steps, further highlighting the advantages of our proposed framework in the field of hybrid tabular-textual QA.

Deep learning-based synthetic dose-weighted LET map generation for intensity modulated proton therapy

The advantage of proton therapy as compared to photon therapy stems from the Bragg peak effect, which allows protons to deposit most of their energy directly at the tumor while sparing healthy tissue. However, even with such benefits, proton therapy does present certain challenges. The biological effectiveness differences between protons and photons are not fully incorporated into clinical treatment planning processes. In current clinical practice, the relative biological effectiveness (RBE) between protons and photons is set as constant 1.1. Numerous studies have suggested that the RBE of protons can exhibit significant variability. Given these findings, there is a substantial interest in refining proton therapy treatment planning to better account for the variable RBE. Dose-average linear energy transfer (LETd) is a key physical parameter for evaluating the RBE of proton therapy and aids in optimizing proton treatment plans. Calculating precise LETd distributions necessitates the use of intricate physical models and the execution of specialized Monte-Carlo simulation software, which is a computationally intensive and time-consuming progress. In response to these challenges, we propose a deep learning based framework designed to predict the LETd distribution map using the dose distribution map. This approach aims to simplify the process and increase the speed of LETd map generation in clinical settings. The proposed CycleGAN model has demonstrated superior performance over other GAN-based models. The mean absolute error (MAE), peak signal-to-noise ratio and normalized cross correlation of the LETd maps generated by the proposed method are 0.096 ± 0.019 keV μm−1, 24.203 ± 2.683 dB, and 0.997 ± 0.002, respectively. The MAE of the proposed method in the clinical target volume, bladder, and rectum are 0.193 ± 0.103, 0.277 ± 0.112, and 0.211 ± 0.086 keV μm−1, respectively. The proposed framework has demonstrated the feasibility of generating synthetic LETd maps from dose maps and has the potential to improve proton therapy planning by providing accurate LETd information.

Adaptation of Dual Contouring and Marching Cubes Algorithms for 3D Reconstruction of the Human Lumbar Spine

The article deals with the problem of three-dimensional reconstruction of the human lumbar spine using the Marching Cubes and Dual Contouring surface triangulation algorithms for subsequent planning of a surgical intervention based on the analysis of digital computed tomography images. 3D reconstructions of the human lumbar spine are presented, as well as the results of a comparative analysis of the developed methods according to the following criteria: mesh generation speed; the number of generated cells; the absence of conflict situations (intersections of the surface). The optimal algorithm for solving the problem is determined on the basis of a comparative analysis.

An efficient power control strategy for active mitigation of blade in‐plane fatigue loading in PMSG‐based wind turbines

AbstractThis paper assesses the dynamic performance of permanent magnet synchronous generator‐based wind turbine (WT) regarding the blade in‐plane fatigue loads once the WT is controlled in power control mode. Blade in‐plane oscillations, associated with the poorly blade in‐plane modes, can be excited by turbulent winds or grid disturbances that may lead to damage of the blades and reduce the drive‐train reliability. To overcome this drawback, at first, a model with three degrees of freedom is extracted for the drive‐train system, and then, an active mitigation approach is proposed to mitigate the blade in‐plane oscillations. The proposed method can effectively suppress the blade in‐plane vibrations by adding a supplementary term into the power control loop that is proportional to the speed difference between the blade and generator. The speed difference between the blade and generator is obtained by estimation of the blade‐hub and hub‐generator shaft torsional torques. Next, the performance of the proposed active mitigation approach is examined by the modal and frequency response analyses and time‐domain simulations. Finally, it is shown that the proposed approach has superior performance over the conventional approaches based on the simplified drive‐train model and crossing the measured generator speed through a band‐pass filter.

Quantifying the impact of sensor precision on power output of a wind turbine: A sensitivity analysis via Monte Carlo simulation study

Wind turbines (WTs) are complex systems with multiple interacting components, posing challenges in identifying factors affecting power output (PO). Sensors play an important role; however, sensor precision can result in measured values differing from actual values. Analyzing the impact of sensor precision on PO is essential. In this study, we employ sensitivity analysis (SA) via Monte Carlo (MC) simulation, offering a novel approach to quantify the influence of sensor precision on the PO of a 4.8 MW WT. We focus on evaluations under 5–20 m/s wind profiles, representing partial and full load regions that portray normal operation. Based on mean squared error (MSE) and parameter sensitivity (PS) index analyses, findings show the generator speed sensor’s precision significantly impacts PO. Therefore, designers should prioritize high-impact sensors like the generator speed, while sensorless strategies may be considered as alternatives to low-impact sensors like the blade pitch angle sensor, where appropriate.

Modeling the dependency relationship between wind speed and wind power generation: An application of copula theory

The concern with global warming and pollution has increased interest in the development of renewable energy sources, which are less aggressive to the environment. Wind energy can provide adequate solutions to the above-mentioned problems. The use of this energy eliminates unwanted waste that is harmful to health and the environment from other energy sources such as coal and nuclear power plants. This work aims to analyse the dependence relationship between wind speed and wind energy production, a rather complex relationship, so this study seeks to understand the stochastic nature of both phenomena. As a methodological tool the copula theory was used. A copula function is used as a general method, which consists of formulating multivariate distributions so that different dependency structures can be represented. That is, the study is based on the analysis and modelling of the dependence between wind speed data and electrical energy generation, for an hourly database of a wind farm in the state of Bahia, collected in the entire year of 2017. Thus, this paper proposes a study aiming the search for the copula function referring to the data in the period mentioned.

Research on Operation and Maintenance Strategy of New Energy Photovoltaic Power Generation System Considering Extreme Weather Conditions

Abstract This paper employs the gray correlation analysis method to compute the correlation between irradiance, ambient temperature, wind speed, and photovoltaic power generation efficiency. This method relies on screened data for data normalization, and after processing, it determines the degree of similarity between the factors. We propose a dynamic combined maintenance strategy for PV power generation systems that considers reliability, overhaul resources, and overhaul time constraints. We propose a two-layer optimization strategy based on extreme weather factors and failure-related characteristics, and we use empirical analysis to investigate the maintenance strategy’s effectiveness. The analysis reveals a positive correlation between irradiance and PV power generation efficiency, with a multiplicative increase in the range of 1-3. In the correlation analysis of ambient temperature and wind speed variables, the power generation curve is not consistent with its trend, which is related to the influence of extreme temperature and extreme wind speed, and the meteorological factors affecting the PV power generation efficiency change at different moments of the day, where the correlation coefficient at 6:45 is 0.912. When the failure correlation strength increases to a value of 0.1, the number of repairs rises to 8. When the weather accessibility ratio is 0.2, the reduction in system availability is up to 62%. The two-layer optimization strategy, which considers extreme weather factors and failure-related characteristics, is both economical and universal.