Shenyang Institute of Automation,Chinese Academy Of Sciences
Not a member yet
23582 research outputs found
Sort by
Laser induced breakdown spectroscopy online monitoring of laser cleaning quality on carbon fiber reinforced plastic
No full textCarbon fiber reinforced polymer (CFRP) has attracted extensive attention in the industrial field due to its advantages of light weight and high hardness. The use of laser to clean the epoxy resin film on the surface of the carbon fiber is beneficial to improve the bonding performance. Combined with laser-induced breakdown spectroscopy (LIBS) technology, an on-line monitoring system for laser cleaning is designed to monitor the quality of laser cleaning in real time. The laser used in the experiment is a fiber laser widely used in laser cleaning, which has high cleaning efficiency, flexible use, and can be processed in a multi-dimensional space. The system is coupled with the scanning galvanometer which can be cleaned dynamically in all directions. The function of fast, real-time and high-resolution on-line monitoring of cleaning quality is realized. In this paper, prior information such as element composition and LIBS spectrum of epoxy resin and substrate carbon fiber in CFRP materials were obtained, and the differences were compared and analyzed. The results shown that the LIBS technology was feasible to monitor the cleaning quality. Subsequently, the experiment tested the influence of the laser process parameters on the LIBS characteristic spectrum, and it was confirmed that the average spectral intensity value at the wavelength (588.819 nm) was positively correlated with the average laser power. After that, according to the measured LIBS characteristic strength value, three evaluation grades of cleaning quality were effectively delineated. The piecewise linear fitting method was used to solve the value range of LIBS mapped by different grades, and the key data such as the optimal cleaning parameter threshold were calculated. Finally, scanning electron microscope (SEM) was used to observe the morphological characteristics of samples after laser cleaning under different grades, confirming that the LIBS characteristic line could effectively characterize the quality of laser cleaning
Routing failure prediction and repairing for AUV-assisted underwater acoustic sensor networks in uncertain ocean environments
No full textUnderwater acoustic sensor networks (UASNs) provide temporary links, which is of great significance when it comes to dealing with abnormal situations or emergencies in Internet of underwater things (IoUT). However, UASNs are susceptible to changes and uncertainties in network topology, channel conditions, etc., which can easily lead to frequent link interruptions. In this paper, we introduce a link failure prediction mechanism and an autonomous underwater vehicle (AUV)-assisted routing holes repairing mechanism for routing design of UASNs in uncertain ocean environments, to save system energy consumption and improve network connectivity. The proposed link failure prediction mechanism takes into account residual energy of sensor nodes, node drifting information, and uncertain ocean ambient noise. When the energy of multiple sensor nodes is exhausted, the particle swarm optimization algorithm (PSO) is adopted to calculate the optimal repair location, and an AUV is used for fixed point repairing. The proposed method can effectively reduce the energy consumption of sensor nodes, increase the packet delivery ratio, and extend the life of entire network of UASNs.</p
AMF-Net: An adaptive multisequence fusing neural network for multi-modality brain tumor diagnosis
No full textTo precisely diagnose the brain tumor types and grades, magnetic resonance imaging (MRI), which is a kind of multisequence imaging technology, is usually applied. However, with the limitations of databases, most current computer-aided brain tumor diagnosis methods employ only a single MRI sequence, and the generalizability of these methods is not ideal. To improve the brain tumor diagnosis performance, an adaptive multisequence fusing neural network (AMF-Net), which can merge the characteristics of different MRI sequences with adaptive weights, is proposed. Inspired by the approximate horizontal symmetry of brains and manual diagnosis process, normalized horizontal differential images are adopted as the spatial attention mechanism, and dense skip connections from T2-weighted (T2-W) sequences are implemented to emphasize the importance of the T2-W sequences. Moreover, to adaptively combine different MRI sequences, an innovative self-learning mechanism, namely adaptive sequence fusion (ASF) module, is proposed. The experimental results show that the average accuracies of the AMF-Net on two databases reach 98.1% and 92.1%, respectively, and the application of the proposed spatial attention mechanism and the ASF module can improve the average accuracy on two databases by 1.7%/1.7% and 1.3%/2.1%, respectively, which indicates that the proposed spatial attention mechanism and the ASF module can improve the performance for brain tumor diagnosis tasks.</p
Reducing self-absorption effect by double-pulse combination in laser-induced breakdown spectroscopy
No full textThe method of double-pulse laser-induced breakdown spectroscopy is usually employed to enhance the spectral signal intensity. However, in this study, double-pulse laser-induced breakdown spectroscopy is adopted to investigate the effect of the self-absorption reduction of the spectrum. This research explored that the influence of the change of the gas environment generated by the first laser beam on the self-absorption effect of the plasma spectrum by the second laser beam. Especially despite the different combinations of laser energy, for the three elements of Cu, Mn and Ni, the weakest spectral self-absorption effect can be obtained when the double-pulse delays are around 80 μs, 100 μs, and 110 μs, respectively. In addition, this paper also found that when the energy of the first laser beam is unchanged, the spectral self-absorption effect has a strong correlation with the double-pulse delay, and has a weak correlation with the change of the second laser energy.</p
FluidFM for single-cell biophysics
No full textFluidic force microscopy (FluidFM), which combines atomic force microscopy (AFM) with microchanneled cantilevers connected to a pressure controller, is a technique allowing the realization of force-sensitive nanopipette under aqueous conditions. FluidFM has unique advantages in simultaneous three-dimensional manipulations and mechanical measurements of biological specimens at the micro-/nanoscale. Over the past decade, FluidFM has shown its potential in biophysical assays particularly in the investigations at single-cell level, offering novel possibilities for discovering the underlying mechanisms guiding life activities. Here, we review the utilization of FluidFM to address biomechanical and biophysical issues in the life sciences. Firstly, the fundamentals of FluidFM are represented. Subsequently, the applications of FluidFM for biophysics at single-cell level are surveyed from several facets, including single-cell manipulations, single-cell force spectroscopy, and single-cell electrophysiology. Finally, the challenges and perspectives for future progressions are provided.</p
Underwater glider observation of the oxygen minimum zone in the northern South China Sea
No full text最小含氧带(OxygenMinimumZone,OMZ)是指海洋中层水体处存在的稳定的溶解氧(DissolvedOxygen,DO)极小值层, OMZ的分布与变化对南海生态系统和生地化循环具有重要意义。本文利用2019年7-9月“海翼”号水下滑翔机(Sea-wing Glider)在南海北部陆坡区的组网观测数据,对南海北部陆坡区OMZ的空间分布特征进行了分析。结果显示,在垂向上,研究区域内DO极小值层出现在深度约700~900 m处,其含量约为80~100μmol·L~(-1),在700~900 m深度范围内, DO含量变化不大,形成了厚度约为200 m的OMZ。在水平方向上, OMZ自陆坡西南部起向东北方向延伸,厚度由西南至东北逐渐变薄,整体呈楔形分布,并在靠近吕宋海峡处逐渐消失。此外,研究还选取了两台水下滑翔机7-8月连续两周内的观测数据,经计算显示,OMZ区域内的DO含量在跨陆坡方向上的平均变化速率为增加0.023μmol·L~(~(-1))day~(~(-1)),在沿陆坡方向上为减少0.034μmol·L~(-1)day~(-1)。沿吕宋海峡入侵南海的高氧水能够解释OMZ东北部DO含量局部升高的现象, OMZ的分布特征和形成原因与海水的平流运动、水团分布以及水体层化等物理过程,和生物呼吸、有机物分解以及还原性物质的氧化等多种影响因素有关。</p
A novel transfer learning model for traditional herbal medicine prescription generation from unstructured resources and knowledge
No full textTraditional Chinese medicine (TCM) is an essential part of the world's traditional medicine. However, there are still many issues in the promotion and development of TCM, such as a lot of unique TCM treatments are taught only between the master and an apprentice in practice, it takes dozens of years for a TCM practitioner to master them and the complicated TCM treatment principles. Intelligent TCM models, as a promising method, can overcome these issues. The performance of previously proposed AI models for intelligent TCM is restricted since they rely on clinical medical records, which are limited, hard to collect, and unavailable for intelligent TCM researchers. In this work, we propose a two-stage transfer learning model to generate TCM prescriptions from a few medical records and TCM documentary resources, called TCMBERT for short. First, the TCMBERT is trained on TCM books. Then, it is fine-tuned on a limited number of medical records to generate TCM prescriptions. The experimental results show that the proposed model outperforms the state-of-the-art methods in all comparison baselines on the TCM prescription generation task. The TCMBERT and the training process can be used in TCM tasks and other medical tasks for dealing with textual resources.</p
Context-aware scheduling and control architecture for cyber-physical production systems
No full textCyber-physical production systems provide a flexible and open mechanism for manufacturing process scheduling and control, and they also offer an opportunity to further improve the performance of systems by the joint optimization of scheduling and control (JSC). With given optimization objectives, the solution of JSC not only provides the schedule plan but also provides the optimal control parameters. However, due to the dynamic nature of the production system, it is not possible to consider all potential situations to make an ideal solution for the JSC at the beginning. Therefore, this paper formulates the problem of dynamic JSC and proposes an architecture for context-aware production scheduling and control systems, which utilizes ontology and reasoning technologies from knowledge engineering to enhance the adaptabilities of production systems. To illustrate the feasibility of the proposed architecture, we take an international competition platform as a case study and compare the performance with the champion team's system. The result shows that our system performs better than does the system of the champion team, and it also proves the feasibility of the proposed architecture
A transfer weighted extreme learning machine for imbalanced classification
No full textPrevious class imbalance learning methods are mostly grounded on the assumption that all training data have been labeled, however, is impractical in many real-world applications. The limited amount of labeled instances may produce a classifier with poor generalization. To address the issue, a transfer weighted extreme learning machine (TWELM) classifier is proposed, with the purpose of extracting knowledge from other domains to improve the classification performance of a classifier in a limited labeled target domain. To be specific, a well-tuned weighted extreme learning machine classifier is first learned from source data that has been completely labeled. Subsequently, another extreme learning machine classifier is obtained from the limited labeled target domain data to preserve the target domain structural knowledge and the decision boundary information. Finally, the target classifier is optimized by minimizing the outputs of the two classifiers on unlabeled target data. Experimental results on real-world data sets show that TWELM outperforms existing algorithms on classification accuracy and computation cost.</p
An efficient approach of centroid alignment for spaceflight vehicles considering parameter uncertainties
No full textThis paper deals with centroid alignment for the spaceflight vehicles that work on orbit under microgravity environment, due to the unavailability of centroid measurement on ground, which is based on the principle of mass-radius products in different configurations of static equilibrium. A physical prototype of articulated mechanism for centroid alignment, consisting of three sets of linear modules with moving mass mounted, was developed and experimentally validated. The variational method was adopted to derive the error model for accuracy and sensitivity analysis of the developed articulated mechanism with the consideration of parameter uncertainties, from which it is found that the centroid position of the whole system is much more sensitive to the angular parameter variations than the linear ones. With the developed error model, an iterative approach of centroid alignment to ensure the centroid offset to meet the requirement is proposed, regardless of whether the parameter variations can be ignored, and numerous simulations verify the efficiency of the proposed approach