1,322 research outputs found
Thermo-economic assessment of flexible nuclear power plants in future low-carbon electricity systems: Role of thermal energy storage
No full textThe increasing penetration of intermittent renewable power will require additional flexibility from conventional plants, in order to follow the fluctuating renewable output while guaranteeing security of energy supply. In this context, coupling nuclear reactors with thermal energy storage could ensure a more continuous and efficient operation of nuclear power plants, while at other times allowing their operation to become more flexible and cost-effective. This study proposes options for upgrading a 1610-MWel nuclear power plant with the addition of a thermal energy storage system and secondary power generators. The total whole-system benefits of operating the proposed configuration are quantified for several scenarios in the context of the UK’s national electricity system using a whole-system model that minimises the total system costs. The proposed configuration allows the plant to generate up to 2130 MWel during peak load, representing an increase of 32% in nominal rated power. This 520 MWel of additional power is generated by secondary steam Rankine cycle systems (i.e., with optimised cycle thermal efficiencies of 24% and 30%) and by utilising thermal energy storage tanks with a total heat storage capacity of 1950 MWhth. Replacing conventional with flexible nuclear power plants is found to generate whole-system cost savings between £24.3m/yr and £88.9m/yr, with the highest benefit achieved when stored heat is fully discharged in 0.5 h. At an estimated cost of added flexibility of £42.7m/yr, the proposed flexibility upgrades to such nuclear power plants appears to be economically justified with net system benefits ranging from £4.0m/yr to £31.6m/yr for the examined low-carbon scenarios, provided that the number of flexible nuclear plants in the system is small. This suggests that the value of this technology is system dependent, and that system characteristics should be adequately considered when evaluating the benefits of different flexible nuclear plant configurations and choosing the most cost-effective designs and operational characteristics
feiyuno1987/MPS-Training-Image-Selection-based-on-CNN v1.1.0
No full textTraing image Selection with CNN (基于CNN选择合适的MPS训练图像)
This procedure can achieve TI selected precision test, the output file is output.log. By default, there are 4 examples of data. If you need to do custom testing, please modify the example section of the code in the TI_Selection.cs file.
Author : Siyu YU([email protected]) Date : 2021.1In this new version, all of the code for the project has been converted to.NET Cor
Strategic Positioning Under Agricultural Structural Change: A Critique of Long Jump Co-operative Ventures
No full textIndustrial Organization, Agribusiness,
STRATEGIC POSITIONING UNDER AGRICULTURAL STRUCTURAL CHANGE: A CRITIQUE OF LONG JUMP CO-OPERATIVE VENTURES
No full textStructural change in US agriculture has disrupted the traditional organization of the supply chain. Not only does the scale increase of firms common during the industrial period (1970-1995) continue, but also with the rise of a knowledge-based economy, new organizational forms and supply chain linkages are proliferating. Examples are the radical transformation of the relationship between input suppliers and producers in the biotech arena, the dominance of the swine industry by the integrated model, the rise of marketing and production contracting, and the arrival of multi-member closed producer organizations such as the new generation cooperatives and limited liability companies. The focus of this research is these new integrated producer organizations. Much of the activity and subsequent analysis of new producer organizations has focused on value-added opportunities through integration (i.e., Merrett et al, 1999). There are numerous examples from pasta plants and egg breaking, to cattle feeding, hog slaughter, and alcohol production. These value-added opportunities we define as long jump ventures. That is, they lie outside the core competencies of the principles in the firm, the producers. Strategic management theory (Prahalad, 1986,1990,1993; Quinn, 1977,1990; Mintzberg, 1987,1994,1996,1998,2000) suggests that there may be other opportunities available to producer organizations that better leverage their core competencies, short jump ventures. Short jump ventures are value-creating opportunities that involve a minimum R&D, less capital, less risk, and less direct specialized knowledge. While the economy at large is producing vast quantifies of long jump innovations in the fields of biotechnology and information, there is another revolution occurring in business involving short jump innovation in the area of service. This new field, known as; one-to-one marketing (Pepper, 1993, 1999), relationship management (Hansen, 1983), relationship marketing (Curry, 2000), and strategic partnering (Rackam, 1996), focuses on the supplier-client interface. Value is created by significant coordination between supplier and client. The boundary between firms is blurred, knowledge is actively shared, and partners are dedicated to mutual profitability. By understanding the needs of the client, the supplying firm is able to adapt its products and more importantly services. This creates a unique and more valuable business for the supplier insulating it from competitive forces and allowing greater value capture. This not only creates greater supply chain efficiency, but intra-firm and inter-firm product innovation result as well. The objective of this paper is to study strategic options for production agriculture dealing with the failure of the commodity business model. From this analysis of strategic positioning the paper introduces relationship management as a viable strategic alternative for commodity producers. Finally, a case study of the Wairarapa Lamb Cooperative, a New Zealand based firm doing business in the United States, is introduced. The case serves not only as an example of relationship management in agriculture but also demonstrates how producers can work within their own core competencies, leverage knowledge assets, and avoid highly specific fixed assets. The methodology will be: 1) Review the literature as to the types of activities in which integrated producer organizations are engaged. 2) Present a theoretical model of strategy analyzing short jump versus long jump ventures. 3) Introduce Relationship Management. 4) Employ a case study example of the theory in practice. This paper theoretically analyzes producers' vertical integration through "brick and mortar" investments, such as hog slaughter and ethanol production. A theoretical model using strategic management theory and a case study are used to critique the long jump strategy and suggest relationship management as a more viable alternative.Agribusiness,
Improving Monocular SLAM: using Depth Estimating CNN
No full textTo bring down the number of traffic accidents and increase people’s mobility companies, such as Robot Engineering Systems (RES) try to put automated vehicles on the road. RES is developing the WEpod, a shuttle capable of autonomously navigating through mixed traffic. This research has been done in cooperation with RES to improve the localization capabilities of the WEpod. The WEpod currently localizes using its GPS and lidar sensors. These have proven to be not accurate and reliable enough to safely navigate through traffic. Therefore, other methods of localization and mapping have been investigated. The primary method investigated in this research is monocular Simultaneous Localization and Mapping (SLAM). Based on literature and practical studies, ORB-SLAM has been chosen as the implementation of SLAM. Unfortunately, ORB-SLAM is unable to initialize the setup when applied on WEpod images. Literature has shown that this problem can be solved by adding depth information to the inputs of ORB-SLAM. Obtaining depth information for the WEpod images is not an arbitrary task. The sensors on the WEpod are not capable of creating the required dense depth-maps. A Convolutional Neural Network (CNN) could be used to create the depth-maps. This research investigates whether adding a depth-estimating CNN solves this initialization problem and increases the tracking accuracy of monocular ORB-SLAM. A well performing CNN is chosen and combined with ORB-SLAM. Images pass through the depth estimating CNN to obtain depth-maps. These depth-maps together with the original images are used in ORB-SLAM, keeping the whole setup monocular. ORB-SLAM with the CNN is first tested on the Kitti dataset. The Kitti dataset is used since monocular ORB- SLAM initializes on Kitti images and ground-truth depth-maps can be obtained for Kitti images. Monocular ORB-SLAM’s tracking accuracy has been compared to ORB-SLAM with ground-truth depth-maps and to ORB-SLAM with estimated depth-maps. This comparison shows that adding estimated depth-maps in- creases the tracking accuracy of ORB-SLAM, but not as much as the ground-truth depth images. The same setup is tested on WEpod images. The CNN is fine-tuned on 7481 Kitti images as well as on 642 WEpod images. The performance on WEpod images of both CNN versions are compared, and used in combination with ORB-SLAM. The CNN fine-tuned on the WEpod images does not perform well, missing details in the estimated depth-maps. However, this is enough to solve the initialization problem of ORB-SLAM. The combination of ORB-SLAM and the Kitti fine-tuned CNN has a better tracking accuracy than ORB-SLAM with the WEpod fine-tuned CNN. It has been shown that the initialization problem on WEpod images is solved as well as the tracking accuracy is increased. These results show that the initialization problem of monocular ORB-SLAM on WEpod images is solved by adding the CNN. This makes it applicable to improve the current localization methods on the WEpod. Using only this setup for localization on the WEpod is not possible yet, more research is necessary. Adding this setup to the current localization methods of the WEpod could increase the localization of the WEpod. This would make it safer for the WEpod to navigate through traffic. This research sets the next step into creating a fully autonomous vehicle which reduces traffic accidents and increases the mobility of people
BackboneAnalysis: Structured Insights into Compute Platforms from CNN Inference Latency
No full textCustomization of a convolutional neural network (CNN) to a specific compute platform involves finding an optimal pareto state between computational complexity of the CNN and resulting throughput in operations per second on the compute platform. However, existing inference performance benchmarks compare complete backbones that entail many differences between their CNN configurations, which do not provide insights in how fine-grade layer design choices affect this balance.We present BackboneAnalysis, a methodology for extracting structured insights into the trade-off for a chosen target compute platform. Within a one-factor-at-a-time analysis setup, CNN architectures are systematically varied and evaluated based on throughput and latency measurements irrespective of model accuracy. Thereby, we investigate the configuration factors input shape, batch size, kernel size and convolutional layer type.In our experiments, we deploy BackboneAnalysis on a Xavier iGPU and a Coral Edge TPU accelerator. The analysis reveals that the general assumption from optimal Roofline performance that higher operation density in CNNs leads to higher throughput does not always hold. These results highlight the importance for a neural network architect to be aware of platform-specific latency and throughput behavior in order to derive sensible configuration decisions for a custom CNN
Building segmentation from airborne vhr images using mask r-cnn
No full textUp-to-date 3D building models are important for many applications. Airborne very high resolution (VHR) images often acquired annually give an opportunity to create an up-to-date 3D model. Building segmentation is often the first and utmost step. Convolutional neural networks (CNNs) draw lots of attention in interpreting VHR images as they can learn very effective features for very complex scenes. This paper employs Mask R-CNN to address two problems in building segmentation: detecting different scales of building and segmenting buildings to have accurately segmented edges. Mask R-CNN starts from feature pyramid network (FPN) to create different scales of semantically rich features. FPN is integrated with region proposal network (RPN) to generate objects with various scales with the corresponding optimal scale of features. The features with high and low levels of information are further used for better object classification of small objects and for mask prediction of edges. The method is tested on ISPRS benchmark dataset by comparing results with the fully convolutional networks (FCN), which merge high and low level features by a skip-layer to create a single feature for semantic segmentation. The results show that Mask R-CNN outperforms FCN with around 15% in detecting objects, especially in detecting small objects. Moreover, Mask R-CNN has much better results in edge region than FCN. The results also show that choosing the range of anchor scales in Mask R-CNN is a critical factor in segmenting different scale of objects. This paper provides an insight into how a good anchor scale for different dataset should be chosen.Optical and Laser Remote Sensin
Frequency learning for structured CNN filters with Gaussian fractional derivatives
No full textA structured CNN filter basis allows incorporating priors about natural image statistics and thus require less training examples to learn, saving valuable annotation time. Here, we build on the Gaussian derivative CNN filter basis that learn both the orientation and scale of the filters. However, this Gaussian filter basis definition depends on a predetermined derivative order, which typically results in fixed frequency responses for the basis functions whereas the optimal frequency of the filters should depend on the data and the downstream learning task. We show that by learning the order of the basis we can accurately learn the frequency of the filters, and hence adapt to the optimal frequencies for the underlying task. We investigate the well-founded mathematical formulation of fractional derivatives to adapt the filter frequencies during training. Our formulation leads to parameter savings and data efficiency when compared to the standard CNNs and the Gaussian derivative CNN filter networks that we build on.Computer Science | Data Science and Technolog
FPQNet: Fully Pipelined and Quantized CNN for Ultra-Low Latency Image Classification on FPGAs Using OpenCAPI
No full textConvolutional neural networks (CNNs) are to be effective in many application domains, especially in the computer vision area. In order to achieve lower latency CNN processing, and reduce power consumption, developers are experimenting with using FPGAs to accelerate CNN processing in several applications. Current FPGA CNN accelerators usually use the same acceleration approaches as GPUs, where operations from different network layers are mapped to the same hardware units working in a multiplexed manner. This will result in high flexibility in implementing different types of CNNs; however, this will degrade the latency that accelerators can achieve. Alternatively, we can reduce the latency of the accelerator by pipelining the processing of consecutive layers, at the expense of more FPGA resources. The continued increase in hardware resources available in FPGAs makes such implementations feasible for latency-critical application domains. In this paper, we present FPQNet, a fully pipelined and quantized CNN FPGA implementation that is channel-parallel, layer-pipelined, and network-parallel, to decrease latency and increase throughput, combined with quantization methods to optimize hardware utilization. In addition, we optimize this hardware architecture for the HDMI timing standard to avoid extra hardware utilization. This makes it possible for the accelerator to handle video datasets. We present prototypes of the FPQNet CNN network implementations on an Alpha Data 9H7 FPGA, connected with an OpenCAPI interface, to demonstrate architecture capabilities. Results show that with a 250 MHz clock frequency, an optimized LeNet-5 design is able to achieve latencies as low as 9.32 µs with an accuracy of 98.8% on the MNIST dataset, making it feasible for utilization in high frame rate video processing applications. With 10 hardware kernels working concurrently, the throughput is as high as 1108 GOPs. The methods in this paper are suitable for many other CNNs. Our analysis shows that the latency of AlexNet, ZFNet, OverFeat-Fast, and OverFeat-Accurate can be as low as 69.27, 66.95, 182.98, and 132.6 µs, using the architecture introduced in this paper, respectively.Computer Engineerin
CNN Based Road User Detection Using the 3D Radar Cube
No full textThis letter presents a novel radar based, single-frame, multi-class detection method for moving road users ( pedestrian, cyclist, car ), which utilizes low-level radar cube data. The method provides class information both on the radar target- and object-level. Radar targets are classified individually after extending the target features with a cropped block of the 3D radar cube around their positions, thereby capturing the motion of moving parts in the local velocity distribution. A Convolutional Neural Network (CNN) is proposed for this classification step. Afterwards, object proposals are generated with a clustering step, which not only considers the radar targets’ positions and velocities, but their calculated class scores as well. In experiments on a real-life dataset we demonstrate that our method outperforms the state-of-the-art methods both target- and object-wise by reaching an average of 0.70 (baseline: 0.68) target-wise and 0.56 (baseline: 0.48) object-wise F1 score. Furthermore, we examine the importance of the used features in an ablation study.Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.Intelligent Vehicle
- …
