Classification and regression models of audio and vibration signals for machine state monitoring in precision machining systems

We present a data-driven method for monitoring machine status in manufacturing processes. Audio and vibration data from precision machining are used for inference in two operating scenarios: (a) variable machine health states (anomaly detection); and (b) settings of machine operation (state estimation). Audio and vibration signals are first processed through Fast Fourier Transform and Principal Component Analysis to extract transformed and informative features. These features are then used in the training of classification and regression models for machine state monitoring. Specifically, three classifiers (K-nearest neighbors, convolutional neural networks and support vector machines) and two regressors (support vector regression and neural network regression) were explored, in terms of their accuracy in machine state prediction. It is shown that the audio and vibration signals are sufficiently rich in information about the machine that 100% state classification accuracy could be accomplished. Data fusion was also explored, showing overall superior accuracy of data-driven regression models.     

基于决策树技术的日前市场清算电价预测

以澳大利亚昆士兰州电力市场为背景,采用决策树技术,建立了提前日的电力市场清算电价预测模型。详细介绍了决策树技术的原理及其在电价预测中的实现方法,考虑了非电价因素对电价预测的影响。实际结果表明该方法具有良好的预测效果和直观性。     

Intelligent tool wear monitoring based on parallel residual and stacked bidirectional long short-term memory network

Effective tool wear monitoring (TWM) is essential for accurately assessing the degree of tool wear and for timely preventive maintenance. Existing data-driven monitoring methods mainly rely on complex feature engineering, which reduces the monitoring efficiency. This paper proposes a novel TWM model based on a parallel residual and stacked bidirectional long short-term memory (PRes–SBiLSTM) network. First, a parallel residual network (PResNet) is used to extract the multi-scale local features of sensor signals adaptively. Subsequently, a stacked bidirectional long short-term memory (SBiLSTM) network is used to obtain the time-series features related to the tool wear characteristics. Finally, the predicted tool wear value is outputted through a fully connected network. A smoothing correction method is applied to improve the prediction accuracy. The proposed model is experimentally verified to have a high prediction accuracy without sacrificing its generalization ability. A TWM system framework based on the PRes–SBiLSTM network is proposed, which has a certain reference value for TWM in actual industrial environments.     

Stability of a class of switched stochastic nonlinear systems under asynchronous switching

The stability of a class of switched stochastic nonlinear retarded systems with asynchronous switching controller is investigated. By constructing a virtual switching signal and using the average dwell time approach incorporated with Razumikhin-type theorem, the sufficient criteria for pth moment exponential stability and global asymptotic stability in probability are given. It is shown that the stability of the asynchronous stochastic systems can be guaranteed provided that the average dwell time is sufficiently large and the mismatched time between the controller and the systems is sufficiently small. This result is then applied to a class of switched stochastic nonlinear delay systems where the controller is designed with both state and switching delays. A numerical example illustrates the effectiveness of the obtained results.     

基于状态聚类的多站点CSPS系统的协同控制方法

单站点传送带给料加工站（Conveyor-serviced production station,CSPS）系统中,可运用强化学习对状态——行动空间进行有效探索,以搜索近似最优的前视距离控制策略.但是多站点CSPS系统的协同控制问题中,系统状态空间的大小会随着站点个数的增加和缓存库容量的增加而成指数形式（或几何级数）增长,从而导致维数灾,影响学习算法的收敛速度和优化效果.为此,本文在站点局域信息交互机制的基础上引入状态聚类的方法,以减小每个站点学习空间的大小和复杂性.首先,将多个站点看作相对独立的学习主体,且各自仅考虑邻近下游站点的缓存库的状态并纳入其性能值学习过程;其次,将原状态空间划分成多个不相交的子集,每个子集用一个抽象状态表示,然后,建立基于状态聚类的多站点反馈式Q学习算法.通过该方法,可在抽象状态空间上对各站点的前视距离策略进行优化学习,以寻求整个系统的生产率最大.仿真实验结果说明,与一般的多站点反馈式Q学习方法相比,基于状态聚类的多站点反馈式Q学习方法不仅具有收敛速度快的优点,而且还在一定程度上提高了系统生产率.     

A multi-document summarization system based on statistics and linguistic treatment

The massive quantity of data available today in the Internet has reached such a huge volume that it has become humanly unfeasible to efficiently sieve useful information from it. One solution to this problem is offered by using text summarization techniques. Text summarization, the process of automatically creating a shorter version of one or more text documents, is an important way of finding relevant information in large text libraries or in the Internet. This paper presents a multi-document summarization system that concisely extracts the main aspects of a set of documents, trying to avoid the typical problems of this type of summarization: information redundancy and diversity. Such a purpose is achieved through a new sentence clustering algorithm based on a graph model that makes use of statistic similarities and linguistic treatment. The DUC 2002 dataset was used to assess the performance of the proposed system, surpassing DUC competitors by a 50% margin of f-measure, in the best case.     

A new approach of audio emotion recognition

A new architecture of intelligent audio emotion recognition is proposed in this paper. It fully utilizes both prosodic and spectral features in its design. It has two main paths in parallel and can recognize 6 emotions. Path 1 is designed based on intensive analysis of different prosodic features. Significant prosodic features are identified to differentiate emotions. Path 2 is designed based on research analysis on spectral features. Extraction of Mel-Frequency Cepstral Coefficient (MFCC) feature is then followed by Bi-directional Principle Component Analysis (BDPCA), Linear Discriminant Analysis (LDA) and Radial Basis Function (RBF) neural classification. This path has 3 parallel BDPCA + LDA + RBF sub-paths structure and each handles two emotions. Fusion modules are also proposed for weights assignment and decision making. The performance of the proposed architecture is evaluated on eNTERFACE’05 and RML databases. Simulation results and comparison have revealed good performance of the proposed recognizer.     

Research on the measure method of complaint theme influence on online social network

Consumer complaints on online social network quickly become online groups complaints through many people’s aggregation and looking on, interaction and word-of-mouth communication. Therefore, assessing and managing online complain influence has become a new problem for enterprise to listen to and manage online group complaints. This paper analyzed the complaint information feature of consumer group on online social network, from three-dimensional perspective of complaint text’s quality, transmission timeliness and user interaction degree. We built the influence measure model of online complaint theme based on entropy weight model by monitoring and analyzing real-time the static and dynamic properties of complaint information, explored the measure method of complaint theme influence, employed empirical method to verify the validity and provided scientific decision-making tools and methods for enterprise listening to and managing online group complains.     

Finite‐time formation control of multiple nonholonomic mobile robots

This paper considers finite‐time formation control problem for a group of nonholonomic mobile robots. The desired formation trajectory is represented by a virtual dynamic leader whose states are available to only a subset of the followers and the followers have only local interaction. First of all, a continuous distributed finite‐time observer is proposed for each follower to estimate the leader's states in a finite time. Then, a continuous distributed cooperative finite‐time tracking control law is designed for each mobile robot. Rigorous proof shows that the group of mobile robots converge to the desired geometric formation pattern in finite time. At the same time, all the robots can track the desired formation trajectory in finite time. Simulation example illustrates the effectiveness of our method. Copyright © 2012 John Wiley & Sons, Ltd.     

双馈风机附加频率控制对系统调频动态的影响

针对双馈风机附加频率控制对系统调频动态特性产生的影响,通过建立双馈风机多物理控制环节耦合特性数学模型、互联电力系统考虑风机接入的负荷-频率控制动态特性数学模型,以风机采用惯性支撑与下垂控制结合的附加频率控制为研究对象,利用小干扰稳定分析研究了风机参与系统调频的动态特性,以及各控制环节的运动模态耦合特性。分析结果表明,双馈风机附加频率控制对系统调频动态的小干扰稳定性不会产生明显影响,但惯量支撑控制使系统的调频动态增加一种模态,并使负荷-频率控制的调频动态环节与风机的多物理控制环节在部分振荡和非振荡模态上发生耦合作用。进一步利用阻尼比和振荡频率研究了附加频率控制参数对振荡模态动态特性的影响,并通过时域仿真验证了理论分析的合理性。