YOLSO: You Only Look Small Object

Small object detection is challenging and far from satisfactory. Most general object detectors suffer from two critical issues with small objects: (1) Feature extractor based on classification network cannot express the characteristics of small objects reasonably due to insufficient appearance information of targets and a large amount of background interference around them. (2) The detector requires a much higher location accuracy for small objects than for general objects. This paper proposes an effective and efficient small object detector YOLSO to address the above problems. For feature representation, we analyze the drawbacks in previous backbones and present a Half-Space Shortcut(HSSC) module to build a background-aware backbone. Furthermore, a coarse-to-fine Feature Pyramid Enhancement(FPE) module is introduced for layer-wise aggregation at a granular level to enhance the semantic discriminability. For loss function, we propose an exponential L1 loss to promote the convergence of regression, and a focal IOU loss to focus on prime samples with high classification confidence and high IOU. Both of them significantly improves the location accuracy of small objects. The proposed YOLSO sets state-of-the-art results on two typical small object datasets, MOCOD and VeDAI, at a speed of over 200 FPS. In the meantime, it also outperforms the baseline YOLOv3 by a wide margin on the common COCO dataset.     

喷油方式对斜齿轮齿面温度的影响

为探讨喷油方式对齿面温度的影响，以斜齿轮为研究对象，通过CFD仿真和试验研究不同喷油方式对斜齿轮齿面温度的影响。针对斜齿轮喷油润滑过程的特点，分析其齿面摩擦生热量，简化轮齿喷油润滑计算模型，并基于CFX进行齿面对流换热仿真研究，得到了不同喷油方式下的齿面温度；基于功率开放式斜齿轮试验平台，对不同喷油方式下的齿面温度进行了试验测量，与仿真计算结果进行对比分析。结果表明：在高速重载斜齿轮传动系统中，啮出侧喷油润滑的方式比啮入侧喷油润滑方式的冷却降温效果要好。     

A novel fast distance relay for series compensated transmission lines

This paper presents a fast distance relay for series compensated transmission lines based on the R–L differential-equation algorithm using the theory of equal transfer process of transmission lines. The measuring distances based on the proposed algorithm can fast approach the actual value of fault distance when a fault occurs in front of the series capacitor. When a fault occurs behind of the series capacitor, the fault loop, including the series capacitor, does not match the R–L transmission line model, so the measuring distances fluctuate severely. Based on this, the relative position of the fault with respect to the series capacitor can be judged effectively according to the fluctuation range of the measuring distances, and the accurate fault location can be obtained fast. A variety of PSCAD/EMTDC simulation tests show that the new relay has fast operating speed and high accuracy when applied to the long series compensated transmission lines.     

使用FPGA与SDRAM实现液晶显示控制模块的浅析

针对液晶显示控制板上存储器(SRAM)存储量小和频率低的情况,提出了基于DDR sdram作为显示存储器的LCD显示控制器的设计。使用了灵活性与可靠性高的现场可编程门阵列(FPGA)来实现各模块的逻辑功能,分析了实现LCD显示屏控制模块的方案。     

Combined hardware–software multi-parallel prefiltering on the Convey HC-1 for fast homology detection

Protein databases used in research are huge and still grow at a fast pace. Many comparisons need to be done when searching similar (homologous) sequences for a given query sequence in these databases. Comparing a query sequence against all sequences of a huge database using the well-known Smith–Waterman algorithm is very time-consuming. Hidden Markov Models pose an opportunity for reducing the number of entries of a database and also enable to find distantly homologous sequences. Fewer entries are achieved by clustering similar sequences in a Hidden Markov Model. Such an approach is used by the bioinformatics tool HHblits. To further reduce the runtime, HHblits uses two-level prefiltering to reduce the number of time-consuming Viterbi comparisons. Still, prefiltering is very time-consuming. Highly parallel architectures and huge bandwidth are required for processing and transferring the massive amounts of data. In this article, we present an approach exploiting the reconfigurable, hybrid computer architecture Convey HC-1 for migrating the most time-consuming part. The Convey HC-1 with four FPGAs and high memory bandwidth of up to 76.8 GB/s serves as the platform of choice. Other bioinformatics applications have already been successfully supported by the HC-1. Limited by FPGA size only, we present a design that calculates four first-level prefiltering scores per FPGA concurrently, i.e. 16 calculations in total. This score calculation for the query profile against database sequences is done by a modified Smith–Waterman scheme that is internally parallelized 128 times in contrast to the original Streaming ‘Single Instruction Multiple Data (SIMD)’ Extensions (SSE)-supported implementation where only 16-fold parallelism can be exploited and where memory bandwidth poses the limiting factor. Preloading the query profile, we are able to transform the memory-bound implementation to a compute- and resource-bound FPGA design. We tightly integrated the FPGA-based coprocessor into the hybrid computing system by employing task-parallelism for the two-level prefiltering. Despite much lower clock rates, the FPGAs outperform SSE-based execution for the calculation of the prefiltering scores by a factor of 7.9.     

搅拌式风力致热装置启动性能研究

搭建搅拌式风力致热试验台,以自制的2种致热器为研究对象,使其分别在3个不同平均角加速度24.92、14.66、8.04 rad/s2下启动。通过动态扭矩测试仪和数据采集仪测试记录致热器启动阶段的相关数据。结果表明:致热器启动时所需扭矩与角加速度的一次方、转速、叶片半径的二次方成正比,同时得出这些因素之间的关系式;满负荷时,启动扭矩会出现一个峰值,且角加速度越大峰值越大,自然风必须提供峰值以上的扭矩,否则装置无法启动。     

Fault handling in large water networks with online dictionary learning

Fault detection and isolation in water distribution networks is an active topic due to the nonlinearities of flow propagation and recent increases in data availability due to sensor deployment. Here, we propose an efficient two-step data driven alternative: first, we perform sensor placement taking the network topology into account; second, we use incoming sensor data to build a network model through online dictionary learning. Online learning is fast and allows tackling large networks as it processes small batches of signals at a time. This brings the benefit of continuous integration of new data into the existing network model, either in the beginning for training or in production when new data samples are gathered. The proposed algorithms show good performance in our simulations on both small and large-scale networks.     

Distributed wireless power transfer in sensor networks with multiple Mobile Chargers

We investigate the problem of efficient wireless power transfer in wireless sensor networks. In our approach, special mobile entities (called the Mobile Chargers) traverse the network and wirelessly replenish the energy of sensor nodes. In contrast to most current approaches, we envision methods that are distributed and use limited network information. We propose four new protocols for efficient charging, addressing key issues which we identify, most notably (i) what are good coordination procedures for the Mobile Chargers and (ii) what are good trajectories for the Mobile Chargers. Two of our protocols (DC, DCLK) perform distributed, limited network knowledge coordination and charging, while two others (CC, CCGK) perform centralized, global network knowledge coordination and charging. As detailed simulations demonstrate, one of our distributed protocols outperforms a known state of the art method, while its performance gets quite close to the performance of the powerful centralized global knowledge method.     

A simulation study of reduction kinetics for sponge iron production in a rotary hearth furnace

ABSTRACT

A mathematical model has been developed by coupling genetic algorithm (GA) with heat and material balance equations to estimate rate parameters and solid-phase evolution related to the reduction of iron ore-coal composite pellets in a multi-layer bed Rotary hearth Furnace (RHF). The present process involves treating iron ore-coal composite pellets in a crucible over the hearth in RHF. The various solid phases evolved at the end of the process are estimated experimentally, and are used in conjunction with the model to estimate rate parameters. The predicted apparent activation energy for the wustite reduction step is found to be lower than those of the reduction of higher oxides. The thermal efficiency is found to decrease significantly with an increase in the carbon content of the pellet. Thermal efficiency was also found to increase mildly up to three layers. Multilayer bed remains as a potential design parameter to increase thermal efficiency.