Dynamic plugging regulating strategy of pipeline robot based on reinforcement learning

Pipeline isolation plugging robot (PIPR) is an important tool in pipeline maintenance operation. During the plugging process, the violent vibration will occur by the flow field, which can cause serious damage to the pipeline and PIPR. In this paper, we propose a dynamic regulating strategy to reduce the plugging-induced vibration by regulating the spoiler angle and plugging velocity. Firstly, the dynamic plugging simulation and experiment are performed to study the flow field changes during dynamic plugging. And the pressure difference is proposed to evaluate the degree of flow field vibration. Secondly, the mathematical models of pressure difference with plugging states and spoiler angles are established based on the extreme learning machine (ELM) optimized by improved sparrow search algorithm (ISSA). Finally, a modified Q-learning algorithm based on simulated annealing is applied to determine the optimal strategy for the spoiler angle and plugging velocity in real time. The results show that the proposed method can reduce the plugging-induced vibration by 19.9% and 32.7% on average, compared with single-regulating methods. This study can effectively ensure the stability of the plugging process.

The Effectiveness of Self-regulated Learning Strategies on Chinese College Students' English Learning

The purpose of this paper is to argue the effectiveness of self-regulated learning in English education in Chinese college classroom instruction. A study is given to show whether the introduction of self-regulated learning can help improve Chinese college students' English learning, and help them perform better in the National English test-CET-4 (College English Test Level-4,).

Advanced Policy Learning Near-Optimal Regulation

Designing advanced design techniques for feedback stabilization and optimization of complex systems is important to the modern control field. In this paper, a near-optimal regulation method for general nonaffine dynamics is developed with the help of policy learning. For addressing the nonaffine nonlinearity, a pre-compensator is constructed, so that the augmented system can be formulated as affine-like form. Different cost functions are defined for original and transformed controlled plants and then their relationship is analyzed in detail. Additionally, an adaptive critic algorithm involving stability guarantee is employed to solve the augmented optimal control problem. At last, several case studies are conducted for verifying the stability, robustness, and optimality of a torsional pendulum plant with suitable cost.

Research on College Studentst'Autonomous EFL Learning Affer Course Exemption

By analyzing the English learning logs of 12 students in a provincial university in south-west China after they had been exempted from taking college English courses,this study investigated college students’autonomous EFL(English as a foreign language)learning after course exemption,including the use of mediational means in EFL learning,EFL learning hours,and other factors affecting EFL learning,in the hope of giving new perspectives on college ELF curriculum design,teaching,and education management.

Multi-Agent Hierarchical Graph Attention Reinforcement Learning for Grid-Aware Energy Management

The increasing adoption of renewable energy has posed challenges for voltage regulation in power distribution networks.Gridaware energy management,which includes the control of smart inverters and energy management systems,is a trending way to mitigate this problem.However,existing multi-agent reinforcement learning methods for grid-aware energy management have not sufficiently considered the importance of agent cooperation and the unique characteristics of the grid,which leads to limited performance.In this study,we propose a new approach named multi-agent hierarchical graph attention reinforcement learning framework(MAHGA)to stabilize the voltage.Specifically,under the paradigm of centralized training and decentralized execution,we model the power distribution network as a novel hierarchical graph containing the agent-level topology and the bus-level topology.Then a hierarchical graph attention model is devised to capture the complex correlation between agents.Moreover,we incorporate graph contrastive learning as an auxiliary task in the reinforcement learning process to improve representation learning from graphs.Experiments on several real-world scenarios reveal that our approach achieves the best performance and can reduce the number of voltage violations remarkably.

Adaptive Optimal Output Regulation of Interconnected Singularly Perturbed Systems With Application to Power Systems

This article studies the adaptive optimal output regulation problem for a class of interconnected singularly perturbed systems(SPSs) with unknown dynamics based on reinforcement learning(RL).Taking into account the slow and fast characteristics among system states,the interconnected SPS is decomposed into the slow time-scale dynamics and the fast timescale dynamics through singular perturbation theory.For the fast time-scale dynamics with interconnections,we devise a decentralized optimal control strategy by selecting appropriate weight matrices in the cost function.For the slow time-scale dynamics with unknown system parameters,an off-policy RL algorithm with convergence guarantee is given to learn the optimal control strategy in terms of measurement data.By combining the slow and fast controllers,we establish the composite decentralized adaptive optimal output regulator,and rigorously analyze the stability and optimality of the closed-loop system.The proposed decomposition design not only bypasses the numerical stiffness but also alleviates the high-dimensionality.The efficacy of the proposed methodology is validated by a load-frequency control application of a two-area power system.

Exploration and Practice of “Construction Engineering Regulations” Course Reform

Based on the analysis of the existing teaching situation of the“Construction Engineering Regulations”course,this paper divides the course content into three parts according to the course characteristics and content,and explores three corresponding teaching modes.The proportion of student-led relationships in the three teaching modes is 80%,60%,and 90%,respectively,realizing a teaching mechanism centered on students and stimulating students’interest in independent learning.Teaching methods such as problem-oriented learning,group discussion,student reporting,MOOC(massive open online course),case analysis,etc.,have been used to establish a variety of comprehensive examination mechanisms such as quiz games,follow-up tests,and work displays.Practice has shown that after adopting these three teaching modes,classroom teaching efficiency has significantly improved,and students’abilities in exploration,expression,innovation,and team cooperation have also been enhanced.

基于M-learning的高职生自主学习平台构建与推广——高职院校图书馆在微时代的服务创新

基于M-learning的高职生自主学习平台构建与推广是高职院校图书馆在微时代为适应高职教育国际化、信息化发展趋势而推出的创新服务举措。平台的构建应在成熟的E-learning自主学习平台(如moo-dle、blackboard或者其他的专业平台)的基础上融入移动信息技术,使之能兼容E-learning自主学习平台上的资源,同时支持安卓等系统的使用以及多样化的应用软件(APP)进入,从而使平台实用、易用。平台的推广则应注重与课堂教学的有机融合并用多种形式进行立体宣传。.

Effects of Batroxobin on Spatial Learning and Memory Disorder of Rats with Temporal Ischemia and the Expression of HSP32 and HSP70

The effect of Batroxobin on spatial memory disorder of left temporal ischemic rats and the expression of HSP32 and HSP70 were investigated with Morri`s water maze and immunohistochemistry methods. The results showed that the mean reaction time and distance of temporal ischemic rats in searching a goal were significantly longer than those of the sham-operated rats and at the same time HSP32 and HSP70 expression of left temporal ischemic region in rats was significantly increased as compared with the sham-operated rats. However, the mean reaction time and distance of the Batroxobin-treated rats were shorter and they used normal strategies more often and earlier than those of ischemic rats. The number of HSP32 and HSP70 immune reactive cells of Batroxobin-treated rats was also less than that of the ischemic group. In conclusion, Batroxobin can improve spatial memory disorder of temporal ischemic rats; and the down-regulation of the expression of HSP32 and HSP70 is probably related to the attenuation of ischemic injury.

Research Needs and Applications of Machine Learning｡ｪPredicting Logistics Stress by Machine Learning

Machine learning is the use of computers to learn the intrinsic laws and information contained in data through algorithms to gain new experience and knowledge,in order to improve the intelligence of computers,so that they can make decisions similar to those made by humans when faced with problems.With the development of various industries,the amount of data has increased and the efficiency of data processing and analysis has become more demanding,a series of machine learning algorithms have emerged.Machine learning algorithms are essentially steps and processes that apply a large number of statistical principles to solve optimisation problems.Appropriate machine learning algorithms can be used to solve practical problems more efficiently for a wide range of model requirements.This paper presents the interim state of a dynamic disruption management software solution for logistics,using machine learning methods to study the extent to which stress is predicted based on physiological and subjective parameters,to prevent physical and mental stress on workers in the logistics industry,to maintain their health,to make them more optimistic and better able to adapt to their work,and to facilitate more accurate deployment of human resources by companies according to the real-time requirements of the logistics industry.

The Relationship of Effortful Control to Academic Achievement via Children’s Learning-Related Behaviors

Effortful control (EC) is a temperamental self-regulatory capacity, defined as the efficiency of executive attention [1], which is related to individual differences in self-regulation. Although effortful control covers some dispositional self-regulatory abilities important to cope with social demands of successful adaptation to school, such as attention regulation, individual differences in EC have recently been associated with school functioning through academic achievement including the efficient use of learning-related behaviors, which have been found to be a necessary precursor of learning and they refer to a set of children’s behaviors that involve organizational skills and appropriate habits of study. Therefore, the aim of this study is to review the literature on EC’s relationship to academic achievement via learning-related behaviors, which reflect the use of metacognitive control processes in kindergarten and elementary school students. The findings indicate that EC affects academic achievement through the facilitation of the efficient use of metacognitive control processes.

N6-甲基腺苷相关调节因子与骨关节炎:生物信息学和实验验证分析

背景:越来越多证据表明N6-甲基腺苷(N6-methyladenosine,m6A)调节因子与骨关节炎密切相关,被认为是防治骨关节炎新方向,但具体作用机制不明。目的:通过对骨关节炎基因芯片数据集进行生物信息学分析,探讨m6A对骨关节炎的作用,解析骨关节炎发病机制。方法:首先利用R软件提取GEO数据库中GSE1919数据集中骨关节炎相关m6A调节因子及其表达量,进而对提取结果行基因差异分析及GO、KEGG富集分析;接着对PPI网络拓扑学分析结果和机器学习结果取交集得到m6A关键调节因子,并通过体外细胞实验验证。结果与结论:①提取得到16个骨关节炎相关m6A调节因子表达量,通过差异分析获得ZC3H13、YTHDC1、YTHDF3、HNRNPC等11个m6A差异调节因子;②GO富集分析显示,骨关节炎相关m6A差异调节因子在生物过程中主要于mRNA转运、RNA分解代谢、胰岛素样生长因子受体信号通路调控等发挥作用;③KEGG富集分析显示,差异调节因子主要参与p53、白细胞介素17和AMPK信号通路;④综合PPI网络拓扑学分析和机器学习结果获得m6A关键调节因子——YTHDC1;⑤体外细胞实验结果表明,m6A关键调节因子——YTHDC1在对照组与骨关节炎组中表达存在显著差异(P<0.05);⑥结果显示,YTHDC1与骨关节炎发生发展密切相关,有望成为m6A治疗骨关节炎的分子靶点。

可视化反馈促进自我调节学习的实验研究

建设终身学习型社会要求学习者具备更高的自我调节学习能力。这就要求教育不仅要教会学生知识,更要教会学生学习。然而,当前关于促进基础教育中学习者自我调节学习的研究较少,并且缺乏可以应用于线下课堂的实用工具,导致测评数据无法被深入解读。立足于基础教育课堂教学,设计开发促进学习者自我调节学习的可视化反馈工具,深入分析测评数据,挖掘其中蕴藏的有效信息。该工具提供包括自我认识、学习动机、学习策略三个维度的可视化反馈报告,将知识掌握情况、错题归因、试题定位等信息呈现给学习者,助力其自我调节学习的发生。为检验该工具的效果,在两个班级开展对比实验,对两组学生的自我调节学习能力和学习成绩进行差异性检验。独立样本T检验结果显示,实验班和对照班在自我调节学习能力和学习成绩之间均存在显著性差异,并且均呈现出0.4左右的效应量。证明该工具提供的可视化反馈报告能够有效促进学习者的自我调节学习,同时能够促进学业表现。

混合式教学下高等数学课程思政建设的优化路径

课程思政理念融入大学数学教育,对培养合格的社会主义接班人起到重要作用。基于大学边界理论的视角,在CSCL为基础的协助学习环境中优化高等数学课程与思政课程之间的边界。在具体的课堂教学情境中,将知识学习、价值凸显与能力培养进行有机结合。在大学数学类课堂教学中强调辨析社会系统中的数学、复杂性问题解决、工程伦理以及数学价值观的塑造。

基于深度学习的学生学习行为规制路径研究

由于自身和外部环境因素的影响,在线上线下混合式教学中,学生会出现一些问题学习行为,而问题学习行为必将弱化学习效果,无法实现深度学习。通过线上线下混合式教学中的学生学习行为,总结教学过程中普遍存在的三个问题:学习目标价值偏离,线上即时引导面临挑战;线下教学模式依赖固化,线上即时指导存在障碍;评价未适用混合式教学,评价结果效用缺位。在此基础上,以规制学生学习行为为目标,提出价值引导、任务驱动及立体评价三个机制。在三个规制机制的指导下,把课程的教学设计作为一种学术研究,在《隧道工程》教学中针对性地创设不同的规制措施,并观测学生的反馈效果。再通过发放问卷调查课程教学的效用,结果表明,该教学设计可以有效增强学生知识习得和优化学习行为,有效促进深度学习的实现。

基于卷积神经网络与可视图像的类滑动放电模式识别

为了提高机器学习算法对类滑动放电模式识别的准确率,提出了一种基于卷积神经网络(convolutional neuralnetworks,CNN)与可视图像识别电晕放电、弥散放电和类滑动放电等模式的方法。通过选取气体体积流量0~16 L/min、电极间隙2~10 mm、脉冲频率0.5~3 kHz等不同条件下的类滑动放电图像构建图像库,搭建CNN模型并优化影响CNN识别性能的超参数,包括网络层数、全连接层(full connected layer,FC)神经元数、卷积核尺寸以及激活函数类型,最后比较了CNN与决策树(decision tree,DT)算法和随机森林(random decision forests,RF)算法的识别效果。结果表明,CNN识别准确率为100%,高于传统机器学习方法。此外,本文还给出了放电模式及条件参数,通过基于反向传播神经网络(back propagation neural networks,BPNN)的聚类分析算法识别弥散放电和类滑动放电,并且准确率为100%。