【当期目录】IEEE/CAA JAS 第8卷 第6期

主题：

机器学习、最优控制、神经网络、模糊滑模控制、进化计算...

作者：

欧洲科学院院士Qing-Long Han教授，IEEE Intelligent Transportation Systems Magazine主编Ljubo Vlacic教授，IEEE Fellow Teng Joon (T. J.) Lim教授、Hak-Keung Lam教授、Okan K. Ersoy教授...

机构：

英国King’s College London，美国Purdue University，澳大利亚Swinburne University of Technology、University of Sydney、Murdoch University，东北大学、东南大学、哈尔滨工业大学...

Eman Mousavinejad, Xiaohua Ge, Qing-Long Han, Teng Joon Lim and Ljubo Vlacic, "An Ellipsoidal Set-Membership Approach to Distributed Joint State and Sensor Fault Estimation of Autonomous Ground Vehicles," IEEE/CAA J. Autom. Sinica, vol. 8, no. 6, pp. 1107-1118, June 2021. 

doi: 10.1109/JAS.2021.1004015

An augmented descriptor vehicle model is first established, where the unknown sensor fault is modeled as an auxiliary state of the system model.

A new distributed ellipsoidal set-membership estimation approach is developed so as to construct an optimized bounding ellipsoidal set which guarantees to contain the vehicle’s true state and the sensor fault at each time step despite the existence of UBB disturbance and measurement noises.

A convex optimization algorithm is put forward such that the gain matrix of each distributed estimator can be recursively obtained.

Jiaxin Zhang, Kewen Li and Yongming Li, "Output-Feedback Based Simplified Optimized Backstepping Control for Strict-Feedback Systems with Input and State Constraints," IEEE/CAA J. Autom. Sinica, vol. 8, no. 6, pp. 1119-1132, June 2021. 

doi: 10.1109/JAS.2021.1004018

An adaptive NN optimal control scheme is developed for nonlinear systems with input saturation.

The Barrier type of optimal cost functions are constructed to solve the optimal control problem for nonlinear system.

By using the actor-critic architecture with tan-type BLF, the optimal controllers are designed by the backstepping recursive design.

Qingling Wang and Changyin Sun, "Distributed Asymptotic Consensus in Directed Networks of Nonaffine Systems With Nonvanishing Disturbance," IEEE/CAA J. Autom. Sinica, vol. 8, no. 6, pp. 1133-1140, June 2021. 

doi: 10.1109/JAS.2021.1004021 

This is the first work to consider the leaderless consensus problem of high-order nonaffine agents with uncertain dynamics, nonvanishing disturbance, and unknown control directions, in contrast to existing results for consensus of nonaffine agents.

A new DRISE design combined with the Nussbaum-type function is first proposed to guarantee not only the desired asymptotic consensus, but also the uniform boundedness of all closed-loop variables.

Different from existing results on consensus of agents with nonvanishing disturbance, in this work the integral operation in the proposed control algorithm is adopted to incorporate in a continuous manner and ensure less chattering behavior.

Zhixiong Zhong, Xingyi Wang and Hak-Keung Lam, "Finite-Time Fuzzy Sliding Mode Control for Nonlinear Descriptor Systems," IEEE/CAA J. Autom. Sinica, vol. 8, no. 6, pp. 1141-1152, June 2021. 

doi: 10.1109/JAS.2021.1004024

By using a descriptor redundancy approach, the fuzzy representation in the derivative matrix of system is reformulated into the linear one.

For a specified time interval, partition with transient dynamics of sliding mode control into two subintervals: Reaching phase and sliding motion phase.

Based on the Lyapunov function in the descriptor system domain, the design of FSMC Law is derived in terms of LMIs.

Jie Zhang, Yang Lu, Ke Shi and Chong Xu, "Empirical Research on the Application of a Structure-Based Software Reliability Model," IEEE/CAA J. Autom. Sinica, vol. 8, no. 6, pp. 1153-1162, June 2021.

doi: 10.1109/JAS.2020.1003309

Reveals the relationship between software code metrics and software reliability from an empirical perspective, which makes it possible to introduce reliability engineering to ensure software quality at the early stage of software development without having to rely on the final test reports.

The strategy of classification, screening and aggregation of measurement data is proposed in order to calculate the module reliability value accordingly. 

A framework for empirical research is presented.

Qinqin Fan and Okan K. Ersoy, "Zoning Search With Adaptive Resource Allocating Method for Balanced and Imbalanced Multimodal Multi-Objective Optimization," IEEE/CAA J. Autom. Sinica, vol. 8, no. 6, pp. 1163-1176, June 2021.

doi: 10.1109/JAS.2021.1004027

The ZS-SRA can allocate different computational resources among all subspaces.

The ZS-SRA can assist “regular” MMOEA in finding more equivalent solutions on imbalanced MMOPs.

The ZS-SRA outperforms “special” and “regular” MMOEAs on imbalanced and balanced MMOPs.

A. A. M. Muzahid, Wanggen Wan, Ferdous Sohel, Lianyao Wu and Li Hou, "CurveNet: Curvature-Based Multitask Learning Deep Networks for 3D Object Recognition," IEEE/CAA J. Autom. Sinica, vol. 8, no. 6, pp. 1177-1187, June 2021. 

doi: 10.1109/JAS.2020.1003324

CurveNet is a novel volumetric CNN 3D for object classification.

It takes curvature points features as input；It applies network parameter sharing and shows soft sharing achives the best results.

It achieves state-of-the-art voxels representation results.

Chuan Sun, Hongpeng Yin, Yanxia Li and Yi Chai, "A Novel Rolling Bearing Vibration Impulsive Signals Detection Approach Based on Dictionary Learning," IEEE/CAA J. Autom. Sinica, vol. 8, no. 6, pp. 1188-1198, June 2021. 

doi: 10.1109/JAS.2020.1003438

A novel data-driven detection approach based on dictionary learning is proposed to detect rolling bearing vibration impulsive signal under background noise and nonstationary conditions.

An AR algorithm based linear prediction is used to estimate frequencies and phases of harmonics, which can efficiently separate harmonic components.

An improved MED model is used to weaken Gaussian noise without destroying the inner structure of impulsive signals, which improves the quality of the training dataset to build an appropriate dictionary.

Ziyan Zhao, Shixin Liu, MengChu Zhou and Abdullah Abusorrah, "Dual-Objective Mixed Integer Linear Program and Memetic Algorithm for an Industrial Group Scheduling Problem," IEEE/CAA J. Autom. Sinica, vol. 8, no. 6, pp. 1199-1209, June 2021. 

doi: 10.1109/JAS.2020.1003539

This work tackles a new bi-objective group scheduling problem arising from a real-world steel production system.

It optimizes two objectives, i.e., minimizing the number of late jobs and minimizing total setup time.

It considers the constraints of release time, due time, and sequence-dependent setup time.

Guojun Wang, Jian Wu, Rui He and Bin Tian, "Speed and Accuracy Tradeoff for LiDAR Data Based Road Boundary Detection," IEEE/CAA J. Autom. Sinica, vol. 8, no. 6, pp. 1210-1220, June 2021. 

doi: 10.1109/JAS.2020.1003414

Presents a road-segmentation-line-based classification method for classifying feature points. The road segmentation line is determined by a beam band model and an improved peak-finding algorithm. The method can classify left and right feature points accurately on curved roads up to 70 meters away.

Proposes a distance filter and random sample consensus filter for candidate point extraction and seed point extraction. The candidate points and seed points would be used for the subsequent feature points filtering based on an iterative Gaussian process.

Proposes an iterative Gaussian Process Regression (GPR) based feature points filtering method. The GPR algorithm can be applied to various road shapes without assuming that road boundaries are parametric models. At this same time, the algorithm can effectively remove false points caused by obstacle occlusions.

网站：

http://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=6570654

www.ieee-jas.net

微信：JAS自动化学报英文版

Blog: http://blog.sciencenet.cn/?3291369

Twitter: IEEE/CAA JAS

Facebook: Ieee/Caa Jas

投稿：https://mc03.manuscriptcentral.com/ieee-jas

Email: jas@ia.ac.cn

Tel: 010-82544459