Online identification of postcontingency transient stability is essential in power system control, as it facilitates the grid operator to decide and coordinate system failure correction control ...actions. Utilizing machine learning methods with synchrophasor measurements for transient stability assessment has received much attention recently with the gradual deployment of wide-area protection and control systems. In this paper, we develop a transient stability assessment system based on the long short-term memory network. By proposing a temporal self-adaptive scheme, our proposed system aims to balance the trade-off between assessment accuracy and response time, both of which may be crucial in real-world scenarios. Compared with previous work, the most significant enhancement is that our system learns from the temporal data dependencies of the input data, which contributes to better assessment accuracy. In addition, the model structure of our system is relatively less complex, speeding up the model training process. Case studies on three power systems demonstrate the efficacy of the proposed transient stability as sessment system.
This paper demonstrates that multilingual denoising pre-training produces significant performance gains across a wide variety of machine translation (MT) tasks. We present
—a sequence-to-sequence ...denoising auto-encoder pre-trained on large-scale monolingual corpora in many languages using the BART objective (Lewis et al.,
). mBART is the first method for pre-training a complete sequence-to-sequence model by denoising full texts in multiple languages, whereas previous approaches have focused only on the encoder, decoder, or reconstructing parts of the text. Pre-training a complete model allows it to be directly fine-tuned for supervised (both sentence-level and document-level) and unsupervised machine translation, with no task- specific modifications. We demonstrate that adding mBART initialization produces performance gains in all but the highest-resource settings, including up to 12 BLEU points for low resource MT and over 5 BLEU points for many document-level and unsupervised models. We also show that it enables transfer to language pairs with no bi-text or that were not in the pre-training corpus, and present extensive analysis of which factors contribute the most to effective pre-training.
► The performance of two controlled-release N fertilizers (BBF and PCU) under two water regimes: CF and AWD in comparison with urea were evaluated. ► AWD performed comparably to or better than the ...CF. ► BBF performed comparably with urea, while PCU significantly improved agronomic performance compared with BBF and urea. ► There was lack of interactions between water regime and N-source on yield and NUE, but it did exist on WUE. ► The AWD and PCU combination was recommended for the late-season rice.
Alternate wetting and drying (AWD) irrigation has been widely adopted to replace continuous flooding (CF) irrigation for saving water and increasing water productivity in irrigated rice systems. There is limited information on the performance of controlled-release nitrogen fertilizer (CRNF) under AWD conditions. The objectives of this study were to investigate the effects of four N managements (control, N0; conventional urea at 240kgNha−1, UREA; controlled-release bulk blending fertilizer at 240kgNha−1, BBF; polymer-coated urea at 240kgNha−1, PCU) under CF and AWD water regime on dry matter accumulation (DMA), grain yield, water and N use efficiencies (WUE/NUE) in late-season rice. Compared with CF, AWD significantly reduced the number of irrigation (5 in 2010 and 3 in 2011) and the amount of irrigation water (41.9% in 2010 and 28.0% in 2011). Thus, field water level was shallowed and rainwater storage capacity and usage were improved, leading to reduced surface runoff. AWD performed comparably to or better than CF on plant biomass (root, shoot, panicle, shoot, and whole rice), yield, WUE and NUE, while N fertilization significantly enhanced those parameters. BBF performed comparably with urea on DMA, yield, WUE and NUE, while PCU significantly improved those traits compared with BBF and urea. The interactions of W×N on DMA, grain yield, total N uptake, and NUE were not significant, while those on WUE were significant. The combined AWD and PCU treatment enhanced root and panicle dry matter accumulation and partitioning, effective panicles per m2, spikelets per m2, grain filling and harvest index. As a result, it increased grain yield and subsequently increased WUE and NUE with reduced water input by AWD and enhanced N utilization by PCU. Our results suggested that the new water and N management combination can be an effective means to save water, promote rice production, and improve WUE and NUE for late-season rice.
This paper introduces an automatic dosing system used in the reclaimed water reuse equipment for river water treatment. The automatic dosing system can replace the manual regulation mode. In view of ...the shortcomings of manual dosing in the sewage treatment system, through the study of sewage inlet and outlet flow, online water quality index and other factors. Fully combine feedforward control, feedback control, correction of dosing ratio and other control methods, and use PLC communication and control model to reasonably transform the dosing system, so as to achieve the purpose of intelligent sewage treatment.
Conventional neural autoregressive decoding commonly assumes a fixed left-to-right generation order, which may be sub-optimal. In this work, we propose a novel decoding algorithm— InDIGO—which ...supports flexible sequence generation in arbitrary orders through insertion operations. We extend Transformer, a state-of-the-art sequence generation model, to efficiently implement the proposed approach, enabling it to be trained with either a pre-defined generation order or adaptive orders obtained from beam-search. Experiments on four real-world tasks, including word order recovery, machine translation, image caption, and code generation, demonstrate that our algorithm can generate sequences following arbitrary orders, while achieving competitive or even better performance compared with the conventional left-to-right generation. The generated sequences show that InDIGO adopts adaptive generation orders based on input information.
Online vehicle routing is an important task of the modern transportation service provider. Contributed by the ever-increasing real-time demand on the transportation system, especially small-parcel ...last-mile delivery requests, vehicle route generation is becoming more computationally complex than before. The existing routing algorithms are mostly based on mathematical programming, which requires huge computation time in city-size transportation networks. To develop routes with minimal time, in this paper, we propose a novel deep reinforcement learning-based neural combinatorial optimization strategy. Specifically, we transform the online routing problem to a vehicle tour generation problem, and propose a structural graph embedded pointer network to develop these tours iteratively. Furthermore, since constructing supervised training data for the neural network is impractical due to the high computation complexity, we propose a deep reinforcement learning mechanism with an unsupervised auxiliary network to train the model parameters. A multisampling scheme is also devised to further improve the system performance. Since the parameter training process is offline, the proposed strategy can achieve a superior online route generation speed. To assess the proposed strategy, we conduct comprehensive case studies with a real-world transportation network. The simulation results show that the proposed strategy can significantly outperform conventional strategies with limited computation time in both static and dynamic logistic systems. In addition, the influence of control parameters on the system performance is investigated.
Real-time traffic speed estimation is an essential component of intelligent transportation system (ITS) technologies. It is the foundation of modern transportation control and management ...applications. However, the existing traffic speed acquisition systems can only provide real-time speed measurements of a small number of roads with stationary speed sensors and crowdsourcing vehicles. How to utilize this information to provide traffic speed maps for transportation networks is becoming a key problem in ITSs. In this paper, we present a novel deep-learning model called graph convolutional generative autoencoder to fully address the real-time traffic speed estimation problem. The proposed model incorporates the recent development in deep-learning techniques to extract the spatial correlation of the transportation network from the input incomplete historical data. To evaluate the proposed speed estimation technique, we conduct comprehensive case studies on a real-world transportation network and vehicular traces. The simulation results demonstrate that the proposed technique can notably outperform existing traffic speed estimation and deep-learning techniques. In addition, the impact of dataset properties and control parameters is investigated.
This paper presents a simple yet practical network architecture, ProLiF (Progressively-connected Light Field network), for the efficient differentiable view synthesis of complex forward-facing scenes ...in both the training and inference stages. The progress of view synthesis has advanced significantly due to the recent Neural Radiance Fields (NeRF). However, when training a NeRF, hundreds of network evaluations are required to synthesize a single pixel color, which is highly consuming of device memory and time. This issue prevents the differentiable rendering of a large patch of pixels in the training stage for semantic-level supervision, which is critical for many practical applications such as robust scene fitting, style transferring, and adversarial training. On the contrary, our proposed simple architecture ProLiF, encodes a two-plane light field, which allows rendering a large batch of rays in one training step for image- or patch-level losses. To keep the multi-view 3D consistency of the neural light field, we propose a progressive training strategy with novel regularization losses. We demonstrate that ProLiF has good compatibility with LPIPS loss to achieve robustness to varying light conditions, and NNFM loss as well as CLIP loss to edit the rendering style of the scene.
Display omitted
•Introduction of ProLiF, a simple and efficient network architecture for differentiable view synthesis.•Development of a progressive training strategy with novel regularization losses to ensure multi-view 3D consistency.•Demonstration of ProLiF’s compatibility with various loss functions for enhanced robustness and style editing capabilities.