A novel robot co-worker system for paint factories without the need of existing robotic infrastructure

This paper presents a human–robot co-working system to be applied to industrial tasks such as the production line of a paint factory. The aim is to optimize the picking task with respect to manual operation in a paint factory. The use of an agile autonomous robot co-worker reduces the time in the picking process of materials, and the reduction of the exposure time to raw materials of the worker improves the human safety. Moreover, the process supervision is also improved thanks to a better traceability of the whole process. The whole system consists of a manufacturing process management system, an autonomous navigation system, and a people detection and tracking system. The localization module does not require the installation of reflectors or visual markers for robot operation, significantly simplifying the system deployment in a factory. The robot is able to respond to changing environmental conditions such as people, moving forklifts or unmapped static obstacles like pallets or boxes. The system is not tied to specific manufacturing orders. It is fully integrated with the manufacturing process management system and it can process all possible orders as long as their components are placed into the warehouse. Real experiments to validate the system have been performed in a paint factory by a real holonomic platform and a worker. The results are promising from the evaluation of performance indicators such as exposure time of the worker to raw materials, automation of the process, robust and safe navigation, and the assessment of the end-user.     

Oxidation mechanisms in bulk Ti2AlC: Influence of the grain size

In this work, oxidation mechanisms were studied in fine-grained (FG) and coarse-grained (CG) Ti₂AlC bulk samples. Results showed that the oxidation kinetics are controlled by the grain size of Ti₂AlC. Bigger are the grains, faster is the oxidation. A dense and protective Al₂O₃ layer forms at the surface of FG-Ti₂AlC samples while for the CG-Ti₂AlC samples, a thick TiO₂ layer forms on top of a discontinuous Al₂O₃. CG-Ti₂AlC was observed to simultaneously transform into Ti₃AlC₂ and TiC instead of being directly transformed into TiC. This transformation result in the following crystallographically sandwich-like structure: (0001) Ti₂AlC // (0001) Ti₃AlC₂ // (111) TiC. The volume shrinkage associated to this transformation produces elongated holes that are partially filled by α-Al₂O₃. The stress caused by the volume shrinkage generates cracks at the surface, which makes the oxygen inwards diffusion easier and thus worsens the oxidation resistance the CG-Ti₂AlC bulk.     

Deep learning techniques for tumor segmentation: a review

Recently, deep learning, especially convolutional neural networks, has achieved the remarkable results in natural image classification and segmentation. At the same time, in the field of medical image segmentation, researchers use deep learning techniques for tasks such as tumor segmentation, cell segmentation, and organ segmentation. Automatic tumor segmentation plays an important role in radiotherapy and clinical practice and is the basis for the implementation of follow-up treatment programs. This paper reviews the tumor segmentation methods based on deep learning in recent years. We first introduce the common medical image types and the evaluation criteria of segmentation results in tumor segmentation. Then, we review the tumor segmentation methods based on deep learning from technique view and tumor view, respectively. The technique view reviews the researches from the architecture of the deep learning and the tumor view reviews from the type of tumors.

     

Gas temperatures in heavy goods vehicle fires in tunnels

Large-scale fire tests were carried out with heavy goods vehicle (HGV) cargos in the Runehamar tunnel in Norway. The tunnel is a decommissioned, two-way-asphalted road tunnel that is 1600 m long, 6 m high and 9 m wide, with a slope varying between 0.5% uphill and 1% downhill. In total four tests were performed with fire in an HGV set-up and a longitudinal ventilation flow of approximately 3 m/s. In three tests, mixtures of different cellulose and plastic materials were used; in the fourth test a commodity consisting of furniture and fixtures was used. In all tests the mass ratio was approximately 82% cellulose and 18% plastic. A polyester tarpaulin covered the cargo.One purpose of the large-scale tests was to obtain new relevant gas temperature-time data from large-scale HGV fires in tunnels. There is presently a lack of such information for road tunnels. The maximum heat release rates produced by the four different fire loads varied between 66 and 202 MW resulting in maximum gas temperatures at the ceiling ranging between 1281 and 1365 °C. A comparison with literature values shows that the gas temperatures obtained here are uniformly higher than those obtained in other similar large-scale test series conducted using solid materials. A mathematical correlation of a temperature–time curve is given and this is the best representation of the measured temperature and a combination of frequently used temperature curves for tunnels (the HC curve and the RWS curve).     

高性能整数倍稀疏网络行为识别研究

目的 行为识别在人体交互、行为分析和监控等实际场景中具有广泛的应用。大部分基于骨架的行为识别方法利用空间和时间两个维度的信息才能获得好的效果。GCN (graph convolutional network)能够将空间和时间信息有效地结合起来,然而基于GCN的方法具有较高的计算复杂度,结合注意力模块和多流融合策略使整个训练过程具有更低的效率。目前大多数研究都专注于算法的性能,如何在保证精度的基础上减少算法的计算量是行为识别需要解决的关键性问题。对此,本文在轻量级Shift-GCN (shift graph convolutional network)的基础上,提出了整数倍稀疏网络IntSparse-GCN (integer sparse graph convolutional network)。方法 首先提出奇数列向上移动,偶数列向下移动,并将移出部分用0替代新的稀疏移位操作,并在此基础上,提出将网络每层的输入输出设置成关节点的整数倍,即整数倍稀疏网络IntSparse-GCN。然后对Shift-GCN中的mask掩膜函数进行研究分析,通过自动化遍历方式得到精度最高的优化参数。结果 消融实验表明,每次算法改进都能提高算法整体性能。在NTU RGB+D数据集的子集X-sub和X-view上,4流IntSparse-GCN+M-Sparse的Top-1精度分别为90.72%和96.57%。在Northwestern-UCLA数据集上,4流IntSparse-GCN+M-Sparse的Top-1精度达到96.77%,较原模型提高2.17%。相比代表性的其他算法,在不同数据集及4个流上的准确率均有提升,尤其在Northwestern-UCLA数据集上提升非常明显。结论 本文针对shift稀疏特征提出整数倍IntSparse-GCN网络,对Shift-GCN中的mask掩膜函数进行研究分析,并设计自动化遍历方式得到精度最高的优化参数,不但提高了精度,也为进一步的剪枝及量化提供了依据。     

Smooth feedrate planning for continuous short line tool path with contour error constraint

In the machining program for free form surfaces, the tool path is usually represented as continuous short lines. For the computer numerical control, the feedrate profile for short line tool path should be smooth and optimized in order to achieve high machining quality and high speed. In high speed machining, the feedrate profile also has a strong influence on contour accuracy. This paper presents a new real-time smooth feedrate planning algorithm for short line tool path, in which the contour error constraint is included. To realize contour error control, the feedrate is adaptively adjusted based on the curvature radius of the tool path, which is directly estimated from the short lines. The 7-phase jerk-limited look-ahead planning is employed to generate a smooth feedrate profile. The target feedrate filter (TFF) and planning units merging techniques are developed to improve the smoothness of the feedrate profile and reduce the overhead on look-ahead. The advantage of the proposed algorithm is that it is not only convenient to achieve the balance among accuracy, smoothness and productivity by adjusting parameters, but also efficient in design, which makes it possible to be implemented on low cost hardware platforms. Experiment results demonstrate the feasibility of the proposed algorithm on smooth feedrate planning and contour error control for continuous short line tool path.     

Extraction and analysis of multiple time window features associated with muscle fatigue conditions using sEMG signals

In this work, an attempt has been made to differentiate surface electromyography (sEMG) signals under muscle fatigue and non-fatigue conditions with multiple time window (MTW) features. sEMG signals are recorded from biceps brachii muscles of 50 volunteers. Eleven MTW features are extracted from the acquired signals using four window functions, namely rectangular windows, Hamming windows, trapezoidal windows, and Slepian windows. Prominent features are selected using genetic algorithm and information gain based ranking. Four different classification algorithms, namely naïve Bayes, support vector machines, k-nearest neighbour, and linear discriminant analysis, are used for the study. Classifier performances with the MTW features are compared with the currently used time- and frequency-domain features. The results show a reduction in mean and median frequencies of the signals under fatigue. Mean and variance of the features differ by an order of magnitude between the two cases considered. The number of features is reduced by 45% with the genetic algorithm and 36% with information gain based ranking. The k-nearest neighbour algorithm is found to be the most accurate in classifying the features, with a maximum accuracy of 93% with the features selected using information gain ranking.     

Dynamic threshold for imbalance assessment on load balancing for multicore systems

The introduction of multicore microprocessors has enabled smaller organizations to invest in high performance shared memory parallel systems. These systems ship with standard operating systems using preset thresholds for task imbalance assessment to activate load balancing. Unfortunately, this will unnecessarily trigger task migrations when the number of tasks is a few multiples of the number of processing cores. We illustrate this unnecessary task migration behavior through simulation and introduce a dynamic threshold for task imbalance assessment that is dependent on the number of tasks and the number of processing cores. This is as a replacement for the static threshold that is used by standard operating systems. With the dynamic threshold method, we are able to illustrate a performance gain of up to 17% on a synthetic benchmark and up to 25% gain using the Integer Sort Benchmark from the National Aeronautics and Space Administration (NASA) Advanced Supercomputing Parallel Benchmark Suite.     

Task offloading in cloud-edge collaboration-based cyber physical machine tool

The Cyber-Physical Machine Tool (CPMT) is a promising solution for the next generation of machine tool digitalization and servitization due to its excellent interconnection, intelligence, adaptability, and autonomy. The rapid development of next-generation information technologies, such as the Internet of Things (IoT) and artificial intelligence (AI), provided richer services for CPMT but also led to problems of idle on-site computing resources, and excessive pressure on the cloud, slow service response and poor privacy. To solve the above problems, this paper proposes a cloud-edge collaboration-based CPMT architecture, which makes full use of the computing resources of existing devices in the industrial sites, offloads digital twin (DT) modeling and data processing from the cloud to the edge, and provides microservice interfaces for users at the edge. Given the limited computing resources available in the field and the demand for latency-sensitive applications, task offloading methods aimed at response speed and load balancing are proposed, respectively. Finally, a case of machine tool Prognostics and Health Management (PHM) service is presented, in which the proposed method is used to perform tool wear monitoring, prediction, and health management.