Shenyang Institute of Automation,Chinese Academy Of Sciences
Not a member yet
23582 research outputs found
Sort by
Adaptive Learning Attention Network for Underwater Image Enhancement
No full textUnderwater images suffer from color casts and low illumination due to the scattering and absorption of light as it propagates in water. These problems can interfere with underwater vision tasks, such as recognition and detection. We propose an adaptive learning attention network for underwater image enhancement based on supervised learning, named LANet, to solve these degradation issues. First, a multiscale fusion module is proposed to combine different spatial information. Second, we design a novel parallel attention module (PAM) to focus on the illuminated features and more significant color information coupled with the pixel and channel attention. Then, an adaptive learning module (ALM) can retain the shallow information and adaptively learn important feature information. Further, we utilize a multinomial loss function that is formed by mean absolute error and perceptual loss. Finally, we introduce an asynchronous training mode to promote the network's performance of multinomial loss function. Qualitative analysis and quantitative evaluations show the excellent performance of our method on different underwater datasets. The code is available at: https:// github.com/LiuShiBen/LANet
Design of Online Optimizing Strategy of Ore Grinding Process Setpoint
No full text针对基于传统模型的方法难以在线优化磨矿过程回路设定值的问题,提出了基于案例推理与强化学习的运行指标优化方法,建立基于自回归神经网络的Q函数模型,并应用案例推理更新模型连接权值,实现了磨矿过程关键参数的实时优化。</p
A multiplicative maximin-based evaluation approach for evolutionary many-objective optimization
No full textThis paper presents a new fitness evaluation approach based on aggregated pairwise comparisons (APC), i.e., a multiplicative maximin fitness ranking indicator with norm-p (M2F-p), for solving multi/many-objective problems. The M2F-p uses an adjustable aggregation of pairwise comparisons induced by p to alleviate the incomparability of solutions in terms of Pareto dominance when the number of objectives increases. We analyze the search ability of M2F-p under different p values. It is shown that the p values can control the shape of contour lines (i.e., a set of equal M2F-p values), which can affect the convergence and uniformity of solutions. Then, we illustrate that the M2F-p offers a set of promising properties that can enhance the discriminability of solutions. Further, we develop an efficient algorithm based on M2F-p by using an adaptive p-selection strategy and a diversity-maintenance mechanism. We conduct experiments on a suit of test problems with up to 10 objectives. The experimental results validate the effectiveness of the proposed algorithm on both multi-objective problems and many-objective problems.</p
Simulation Research of Full-Ocean-Depth Manned Submersible Based on Experimental Data
No full textThe motion simulation of manned submersible plays an important role in the whole submersible development. During the actual operation of manned submersible, it is affected by the factors such as deep ocean current, model uncertainty and unmodeled dynamics, which make the traditional simulation results differ greatly from the actual results. Taking 'Fen Douzhe' manned submersible as the research object, the kinematic and dynamic models were established, and the system disturbance was estimated by using long and short term memory neural network, and the model was verified by simulation calculation with the experimental data of 'Fen Douzhe'. The effectiveness of the simulation method is verified by comparing the simulation results with the actual experimental data
Infrared small target detection based on multiscale local contrast learning networks
No full textRecently, model-driven deep networks have achieved excellent detection performance on infrared small targets in cluttered environments. However, its detection performance is sensitive to the hyperparameters in the embedded model-driven module. Therefore, we propose a novel multiscale local contrast learning network (MLCL-Net), which is an end-to-end fully convolutional infrared small target detection network. By constructing a local contrast learning (LCL) structure, it can learn to generate local contrast feature maps during training. Considering the difference in target size, we further build a multiscale local contrast learning (MLCL) module based on LCL. By extracting and fusing local contrast information of different scales from feature maps of the same level, the feature information of targets is fully excavated. At the same time, due to the small size of the target, a slight pixel shift will cause a severe loss of accuracy. We propose a bilinear feature pyramid network (BFPN) based on the feature pyramid network (FPN). Compared to state-of-the-art methods, the proposed MLCLNet achieves superior performance with an intersection-over-union (IoU) of 0.772 and normalized IoU (nIoU) of 0.755 on the public SIRST dataset
一种铋-无定型钨酸铋光催化剂及其制备方法与应用
No full text本发明公开了一种铋‑无定型钨酸铋光催化剂及其制备方法与应用，属于光催化剂技术领域。本发明的一种铋‑无定型钨酸铋光催化剂的制备方法，包括以下步骤：(1)将含有钨酸根的乙二醇溶液滴入含有铋离子的乙二醇溶液中并搅拌均匀，得混合溶液；(2)向混合溶液中加入有机还原剂搅拌均匀后进行保温反应，反应结束后，冷却、洗涤、烘干，得铋‑无定型钨酸铋光催化剂；本发明提供的制备方法采用一步溶剂热法即可合成铋‑无定型钨酸铋光催化剂，合成步骤少，操作简单，能够用于大量生产，且合成得到的铋‑无定型钨酸铋光催化剂具有优异的ppb级NO去除活性，其中，光催化下10分钟时的去除率可达86％
一种机匣流道焊缝机器人自动磨削的装备及方法
No full text本发明公开了一种机匣流道焊缝机器人自动磨削的装备及方法，属于工业机器人自动加工技术领域。该装备包括机器人、工具模块、机匣工件、装夹工具、角度调节装置和工作台。加工方法主要包括：基于最小二乘法的重力补偿标定方法、机匣工件零点自动校正方法、基于位置阻抗控制方式的柔顺磨削过程、机匣自动倾斜角度设定和调整方法、磨削质量检测系统。本发明的装备和方法可以实现机匣流道焊缝的机器人自动加工去除，相比于人工加工，本发明提出的装备和方法降低人工劳动强度和加工成本，提高加工型面质量稳定性和一致性，提高了加工效率，保证了加工质量和系统的正常运行，较好地解决了机匣流道焊缝的自动化加工问题
一种驻车执行器生产线的末端检测系统
No full text本发明涉及驻车执行器生产领域，具体地说是一种驻车执行器生产线的末端检测系统，包括综合检测机构、紧急释放拉绳位移检测机构、拉索位移检测机构和壳体定位工装，执行器设于壳体定位工装上，壳体定位工装、紧急释放拉绳位移检测机构、拉索位移检测机构呈一线设置，综合检测机构设于壳体定位工装上方；综合检测机构包括可移动的伺服电机，且伺服电机的输出端设有可升降的旋转头以及多个检测元件，紧急释放拉绳位移检测机构包括复位气缸、位移传感器和可移动的紧急释放拉绳固定板，拉索位移检测机构包括拉索固定组件、拉力传感器和拉索位移传感器。本发明可以对生产线上装配完成的驻车执行器进行多个指标检测，并通过信息系统记录产品
一种基于角接触球轴承装配线的凸出量测量装置
No full text本发明属于轴承性能检测设备领域，具体地说是一种基于角接触球轴承装配线的凸出量测量装置，包括底板、气浮转台部件、支撑立座、升降部件、移动座及用于测量凸出量的测量部件。本发明通过采用气浮转台旋转带动待测轴承一起匀速旋转，可降低驱动部件对测量结果的影响，从而使测量数据更真实可靠，可以最大限度地排除回转驱动所带来的测量干扰；通过伺服电机和直线模组驱动，可精确控制移动座上下移动，导轨滑块结合直线模组保证了垂直方向Z向运动直线度高，使检测位置的重复性更好；通过测量部件的整体设置，测量部件与待测轴承接触冲击力小，传感器的使用寿命增长，振动小，因此也减少了因为振动引起的检测误差
AUV用360度回转合成推进机构
No full text本发明涉及一种AUV用360度回转合成推进机构，其中艏部回转段包括艏部安装筒、艏部浮力段和艏部推进器，艏部安装筒内部设有回转驱动组件，艏部浮力段与艏部安装筒前端转动连接并通过所述回转驱动组件驱动转动，艏部浮力段内部两侧均设有艏部推进器，且两侧艏部推进器轴向相同并垂直于AUV轴向，艉部回转段包括艉部安装筒、艉部浮力段和艉部推进器，艉部安装筒内设有艉部回转电机，艉部浮力段与艉部安装筒后端转动连接并通过艉部回转电机驱动转动，艉部浮力段两侧均设有艉部推进器，且艉部推进器轴向与AUV轴向呈夹角α设置。本发明可以通过空间运动直驱的方式对AUV进行运动控制，整个操控过程响应速度高，控制系统模型较为精简