A hybrid multiple feature construction approach for classification using Genetic Programming

The purpose of feature construction is to create new higher-level features from original ones. Genetic Programming (GP) was usually employed to perform feature construction tasks due to its flexible representation. Filter-based approach and wrapper-based approach are two commonly used feature construction approaches according to their different evaluation functions. In this paper, we propose a hybrid feature construction approach using genetic programming (Hybrid-GPFC) that combines filter’s fitness function and wrapper’s fitness function, and propose a multiple feature construction method that stores top excellent individuals during a single GP run. Experiments on ten datasets show that our proposed multiple feature construction method (Fcm) can achieve better (or equivalent) classification performance than the single feature construction method (Fcs), and our Hybrid-GPFC can obtain better classification performance than filter-based feature construction approaches (Filter-GPFC) and wrapper-based feature construction approaches (Wrapper-GPFC) in most cases. Further investigations on combinations of constructed features and original features show that constructed features augmented with original features do not improve the classification performance comparing with constructed features only. The comparisons with three state-of-art methods show that in majority of cases, our proposed hybrid multiple feature construction approach can achieve better classification performance.     

Integration of imitation learning using GAIL and reinforcement learning using task-achievement rewards via probabilistic graphical model

The integration of reinforcement learning (RL) and imitation learning (IL) is an important problem that has long been studied in the field of intelligent robotics. RL optimizes policies to maximize the cumulative reward, whereas IL attempts to extract general knowledge about the trajectories demonstrated by experts, i.e, demonstrators. Because each has its own drawbacks, many methods combining them and compensating for each set of drawbacks have been explored thus far. However, many of these methods are heuristic and do not have a solid theoretical basis. This paper presents a new theory for integrating RL and IL by extending the probabilistic graphical model (PGM) framework for RL, control as inference. We develop a new PGM for RL with multiple types of rewards, called probabilistic graphical model for Markov decision processes with multiple optimality emissions (pMDP-MO). Furthermore, we demonstrate that the integrated learning method of RL and IL can be formulated as a probabilistic inference of policies on pMDP-MO by considering the discriminator in generative adversarial imitation learning (GAIL) as an additional optimality emission. We adapt the GAIL and task-achievement reward to our proposed framework, achieving significantly better performance than policies trained with baseline methods.     

结合优化支持向量机与K-means++的工控系统入侵检测方法

针对工业控制系统传统单一检测算法模型对不同攻击类型检测率和检测速度不佳的问题，提出一种优化支持向量机和K-means++算法结合的入侵检测模型。首先利用主成分分析法（PCA）对原始数据集进行预处理，消除其相关性；其次在粒子群优化（PSO）算法的基础上加入自适应变异过程避免在训练的过程中陷入局部最优解；然后利用自适应变异粒子群优化（AMPSO）算法优化支持向量机的核函数和惩罚参数；最后利用密度中心法改进K-means算法与优化后的支持向量机组合成入侵检测模型，从而实现工业控制系统的异常检测。实验结果表明，所提方法在检测速度和对各类攻击的检测率上得到明显提升。     

Usability of a cloud-based collaborative learning framework to improve learners’ experience

Computer-Supported Collaborative Learning (CSCL) is concerned with how Information and Communication Technology (ICT) might facilitate learning in groups which can be co-located or distributed over a network of computers such as Internet. CSCL supports effective learning by means of communication of ideas and information among learners, collaborative access of essential documents, and feedback from instructors and peers on learning activities. As the cloud technologies are increasingly becoming popular and collaborative learning is evolving, new directions for development of collaborative learning tools deployed on cloud are proposed. Development of such learning tools requires access to substantial data stored in the cloud. Ensuring efficient access to such data is hindered by the high latencies of wide-area networks underlying the cloud infrastructures. To improve learners’ experience by accelerating data access, important files can be replicated so a group of learners can access data from nearby locations. Since a cloud environment is highly dynamic, resource availability, network latency, and learner requests may change. In this paper, we present the advantages of collaborative learning and focus on the importance of data replication in the design of such a dynamic cloud-based system that a collaborative learning portal uses. To this end, we introduce a highly distributed replication technique that determines optimal data locations to improve access performance by minimizing replication overhead (access and update). The problem is formulated using dynamic programming. Experimental results demonstrate the usefulness of the proposed collaborative learning system used by institutions in geographically distributed locations.     

An energy-saving nonlinear position control strategy for electro-hydraulic servo systems

The electro-hydraulic servo system (EHSS) demonstrates numerous advantages in size and performance compared to other actuation methods. Oftentimes, its utilization in industrial and machinery settings is limited by its inferior efficiency. In this paper, a nonlinear backstepping control algorithm with an energy-saving approach is proposed for position control in the EHSS. To achieve improved efficiency, two control valves including a proportional directional valve (PDV) and a proportional relief valve (PRV) are used to achieve the control objectives. To design the control algorithm, the state space model equations of the system are transformed to their normal form and the control law through the PDV is designed using a backstepping approach for position tracking. Then, another nonlinear set of laws is derived to achieve energy-saving through the PRV input. This control design method, based on the normal form representation, imposes internal dynamics on the closed-loop system. The stability of the internal dynamics is analyzed in special cases of operation. Experimental results verify that both tracking and energy-saving objectives are satisfied for the closed-loop system.     

Maneuverability modeling and trajectory tracking for fish robot

This study develops a 6-DOF mathematical model for a robotic fish that considers surge, sway, heave, roll, pitch, and yaw. The model considers the conditions of a fish swimming in ocean current perturbations similar to the ocean current perturbations of the slender-body autonomous underwater vehicles. For swimming and turning behaviors, a nonlinear, dynamic, carangiform locomotion model is derived by using a planar four-link model. A 2-DOF barycenter mechanism is proposed to provide body stabilization and to serve as an actuating device for active control design. A barycenter control scheme is developed to change the center of gravity of the robot fish body by moving balancing masses along two axes. The projected torque on x and y axes propel pitch and roll angles to the desired settings. A Stabilizing controller, fish-tail mechanism, rigid body dynamics, and kinematics are incorporated to enable the fish robot to move in three dimensional space. Simulation results have demonstrated maneuverability and control system performance of the developed controller which is proposed to conduct path tracking of the robot fish as it swims under current perturbations.     

基于Matlab的制芯机器人夹持器稳定性研究与分析

由于铸造厂制芯机器人的工作环境恶劣,机器人抓取砂芯的稳定性较差,时常出现掉砂芯、夹伤砂芯的问题。针对上述问题建立以夹持器、气压、机械振动的系统数学模型,采用高阶系统极点在[s]平面的分布法来判定该系统的稳定性。在确保高阶系统极点值不变的情况下,通过改变系统的零点值来观察零点值对系统稳定性、振荡衰减时间的影响。用Matlab的pzmap和impulse函数分别对系统的零点、极点分布和零点值的不同对系统响应进行仿真,运用仿真结果与现场试验进行优化参数,结果表明采用一种刚度与柔度各为1/2的夹持器对制芯机器人的稳定性具有较好优化效果。     

Improved synergetic excitation control for transient stability enhancement and voltage regulation of power systems

This paper proposes decentralized improved synergetic excitation controllers (ISEC) for synchronous generators to enhance transient stability and obtain satisfactory voltage regulation performance of power systems. Each generator is considered as a subsystem, for which an ISEC is designed. According to the control objectives, a manifold, which is a linear combination of the deviation of generator terminal voltage, rotor speed and active power, is chosen for the design of ISEC. Compared with the conventional synergetic excitation controller (CSEC), a parameter adaptation scheme is proposed for updating the controller parameter online in order to improve the transient stability and voltage regulation performance simultaneously under various operating conditions. Case studies are undertaken on a single-machine infinite-bus power system and a two-area four-machine power system, respectively. Simulation results show the ISEC can provide better damping and voltage regulation performance, compared with the CSEC without parameter adaptation scheme and the conventional power system stabilizer.     

生姜主要病虫害及其防治技术分析

生姜的根状茎为使用部分,其中包含姜油酮、姜油醇、姜油酚、蛋白质、粗脂肪、糖,并且钙、铁的含量也较为丰富,是人们日常生活当中不可或缺的调味品,还能够加工成为姜片、糖姜片和盐姜片等诸多食品,其在医药方面的应用也较为广泛,备受人们的推崇与喜爱。我国在生姜栽培方面的历史较为悠久,技术也较为成熟,每年生姜出口贸易都能为我国带来非常可观的经济效益。     

轨道式垃圾回收机器人设计与分析

针对高速公路高峰期拥挤产生的垃圾等问题,设计一种轨道式垃圾回收机器人,由光伏发电装置、机器人壳体、末端手爪、关节臂以及控制系统等组成,主体结构采用双臂三关节结构,采用西门子PLC控制系统,通过控制关节臂的旋转以及偏转、末端手爪的旋转及开合等动作来实现工作的目的。结合外场作业的特殊性,采用光伏能源装置,对其结构及控制系统进行设计,通过对机器人进行三维建模、运动和控制仿真分析,验证系统的可行性及有效性。