漂浮基空间机器人的基于模糊神经网络的自适应补偿控制

针对自由漂浮状态的空间机器人模型不确定性及其动力传动机构的摩擦死区非线性,将一种自适应模糊小脑模型关联控制( FCMAC)补偿策略用于轨迹跟踪及补偿问题.利用模糊神经网络并引入GL矩阵及其乘法算子“.”分别对执行机构中的摩擦死区及系统模型不确定部分进行自适应补偿,其补偿误差及外界扰动通过滑模控制器来消除.基于Lyapunov理论证明了闭环系统跟踪误差的有界性.仿真表明控制器可以达到较高精度,且能满足实时性要求.     

基于模糊神经网络的高校科技成果转化评价研究

针对高校科技成果转化具有一定模糊性的特点,利用模糊神经网络具有模糊化和良好泛化(预测)能力,在给出高校科技成果转化评价指标的基础上,建立了高校科技成果转化评价的模糊神经网络模型.实例验证了该模型具有较好的学习能力,可以较好地对高校科技成果转化进行评价.     

Nonlinear process monitoring based on generic reconstruction-based auto-associative neural network

A significant concern with statistical fault diagnosis is the large number of false alarms caused by the smearing effect. Although the reconstruction-based approach effectively solves this problem, most of them only focus on linear rather than nonlinear systems. In the present work, a generic reconstruction-based auto-associative neural network (GRBAANN) is proposed that uses the reconstruction-based approach to isolate simple and complex faults for nonlinear systems. Nevertheless, in GRBAANN, it is challenging to acquire a trivial solution for the reconstruction-based index, which is equivalent to a complex vector fixed-point problem. In this regard, the Steffensen method is employed to deal with this problem with an accelerated iterative process, which is appropriate for both single and multiple variable faults. The variable selection procedure is time-consuming but imperative for reconstruction-based approaches, with no exception to the proposed method. In order to ensure the real-time diagnosis for large-scale systems, the Sequential floating forward selection method with memory is proposed to minimize the computation time of the variable selection procedure. The effectiveness of the proposed GRBAANN scheme is illustrated through a validation example and an industrial example. Comparisons with the state-of-art methods are also presented.     

基于神经网络识别的复杂工艺参数柔性优化

为提高复杂工艺环境下生产合格率,动态的柔性优化工艺参数组合,以现场生产数据为学习样本和控制对象,基于可适应BP神经网络建立识别生产变化的工艺参数柔性优化模型。在此基础上,通过引入惩罚机制改进粒子群算法在神经网络输入端迭代求解最优参数组合。为了验证模型的有效性,验证实例由3条轻化工艺路线生产数据构成,结果表明模型预测误差绝对值在3%以内,优化得到的参数组合提高合格率到85%以上,有效的提高生产效果和生产柔性。     

Modeling and simulation of shear resistance of R/C beams using artificial neural network

Artificial neural network (ANN) has been used in several engineering application areas including civil engineering. The use of ANN to predict the behavior of reinforced concrete (R/C) members, using the vast amount of experimental data as a test-bed for learning and verification of results, proved to be a viable method for carrying out parametric studies. This paper presents application of ANN for predicting the shear resistance of rectangular R/C beams. Six parameters that influence the shear resistance of beams, mainly shear-span-to-depth ratio, concrete strength, longitudinal reinforcement, shear reinforcement, beam depth and beam width, are used as input for the ANN. A back propagation neural network (BPNN) with different activation functions is used and their results are compared. The sigmoid function with variable threshold is adopted due to its accuracy of prediction. The ANN prediction and the measured experimental values are compared with the shear strength predictions of ACI318-02 and BS8110 codes. A sensitivity study of the parameters that affect shear strength of R/C beams is carried out and the underlying complex nonlinear relationships among these parameters were investigated. Shear response curves and surfaces based on these parameters were generated. It is concluded that ANN can predict, to a great degree of accuracy, the shear resistance of rectangular R/C beams and it is a viable tool for carrying out parametric study of shear behavior of R/C beams.     

Modeling and simulation of low-cycle fatigue life of steel reinforcing bars using artificial neural network

This study presents a model for predicting the low-cycle fatigue life of steel reinforcing bars using Artificial Neural Network (ANN). A Radial Basis Function (RBF) artificial neural network topology with two additional hidden layers and four neurons (processing elements) in each of these layers is used. The input parameters for the network are the maximum tensile strain (ε_s,max) and the strain ratio (R) and the output of the ANN is the number of cycles to fatigue failure (N_f). Low-cycle fatigue tests were conducted by the authors in a previous study for different types of steel reinforcing bars subjected to different strain amplitudes and at different strain ratios. The data resulted from these tests were used to train and test the ANN. It is observed that the ANN prediction of low-cycle fatigue life of steel reinforcing bars is within ±2 cycles of the experimental results for the majority of the test data. A parametric study had been carried out to investigate the effect of maximum strain and strain ratio on the fatigue life of steel reinforcing bars. It is concluded that both the strain ratio and the maximum strain have significant effect on the low-cycle fatigue life of such bars, especially at low values of maximum strain and their effect should be considered in both analysis and design. Other observations and conclusions were also drawn.     

Fixed-time synchronization of memristor-based fuzzy cellular neural network with time-varying delay

This paper mainly investigates the fixed-time synchronization of memristor-based fuzzy cellular neural network (MFCNN) with time-varying delay. By utilizing differential inclusion, set-valued map theory, the definitions of finite-time and fixed-time stability, we convert the fixed-time synchronization control of the drive-response MFCNN into the equivalent fixed-time stability problem of the error system between the drive-response systems. Some novel sufficient conditions are derived to guarantee the fixed-time synchronization of the drive-response MFCNN based on a simple Lyapunov function and a nonlinear feedback controller. Meanwhile, the settling time can be estimated by simple calculations. Furthermore, these fixed-time synchronization criteria here are easy to validate and extend to the MFCNN without time-varying delay and general memristor-based neural networks. Finally, three numerical examples are given to illustrate the correctness of the main results.     

Adaptive control of PLL using neural network

This paper proposes a method for increasing capture range of a phase-locked loop (PLL). The behavior of PLL in the initial condition is nonlinear. This nonlinearity phenomenon is caused by phase detector (PD). A method using neural network as controller in PLL is proposed for overcoming this problem. In the proposed method, the reference frequency and frequency of VCO converted to voltage by FTV. Frequency tracking is achieved by neural network. The circuit has been fabricated in a standard 0.13 μm CMOS process. Simulation results show a tracking range of 110 MHz, and a capture range of 90 MHz while operating from a 2 V supply with maximum 2.18 mW power consumption.     

Modeling user preferences using neural networks and tensor factorization model

With the expansion of information on the web, recommendation systems have become one of the most powerful resources to ease the task of users. Traditional recommendation systems (RS) suggest items based only on feedback submitted by users in form of ratings. These RS are not competent to deal with definite user preferences due to emerging and situation dependent user-generated content on social media, these situations are known as contextual dimensions. Though the relationship between contextual dimensions and user’s preferences has been demonstrated in various studies, only a few studies have explored about prioritization of varying contextual dimensions. The usage of all contextual dimensions unnecessary raises the computational complexity and negatively influences the recommendation results. Thus, the initial impetus has been made to construct a neural network in order to determine the pertinent contextual dimensions. The experiments are conducted on real-world movies data-LDOS CoMoDa dataset. The results of neural networks demonstrate that contextual dimensions have a significant effect on users’ preferences which in turn exerts an intense impact on the satisfaction level of users. Finally, tensor factorization model is employed to evaluate and validate accuracy by including neural network’s identified pertinent dimensions which are modeled as tensors. The result shows improvement in recommendation accuracy by a wider margin due to the inclusion of the pertinent dimensions in comparison to irrelevant dimensions. The theoretical and managerial implications are discussed.     

Accelerating a recurrent neural network to finite-time convergence using a new design formula and its application to time-varying matrix square root

In this paper, a new design formula is presented to accelerate the convergence speed of a recurrent neural network, and applied to time-varying matrix square root finding in real time. Then, according to such a new design formula, a finite-time Zhang neural network (FTZNN) is proposed and investigated for finding time-varying matrix square root. In comparison with the original Zhang neural network (ZNN) model, the FTZNN model makes a breakthrough in the convergence performance (i.e., from infinite time to finite time). In addition, theoretical analyses of the design formula and the FTZNN model are provided in details. Comparative results further verify the superiority of the proposed FTZNN model to the original ZNN model for finding time-varying matrix square root.     

Modeling switched circuits based on wavelet decomposition and neural networks

In this paper, switched circuits are modeled based on wavelet decomposition and neural network. Also describes the usage of wavelet decomposition and neural network for modeling and simulation of nonlinear systems. The switched circuits are piecewise-linear circuits. At each position of switch the circuit is linear but when considered all switching positions of the circuit it becomes nonlinear. An important problem which arises in modeling switched circuit is high structural complexity. In this study, wavelet decomposition is used for feature extracting from input signals and neural network is used as an intelligent modeling tool. Two performance measures root-mean-square (RMS) and the coefficient of multiple determinations (R²) are given to compare the predicted and computed values for model validation. The evaluated R² value is 0.9985 and RMS value is 0.0099. All simulations showed that the proposed method is more effective and can be used for analyzing and modeling switched circuits. When we consider obtained performance, we can easily say that the proposed method can be used efficiently for modeling any other nonlinear dynamical systems.     

DSP-based synchronous control of dual linear motors via Sugeno type fuzzy neural network compensator

A digital signal processor (DSP)-based complementary sliding mode control (CSMC) with Sugeno type fuzzy neural network (SFNN) compensator is proposed in this study for the synchronous control of a dual linear motors servo system installed in a gantry position stage. The dual linear motors servo system comprises two parallel permanent magnet linear synchronous motors (PMLSMs). The dynamics of the single-axis motion system with a lumped uncertainty which contains parameter variations, external disturbances and nonlinear friction force is briefly introduced first. Then, a CSMC is designed to guarantee the precision position tracking requirement in single-axis control for the dual linear motors. Moreover, to enhance the robustness to uncertainties and to eliminate the synchronous error of dual linear motors, the CSMC with a SFNN compensator is proposed where the SFNN compensator is designed mainly to compensate the synchronous error. Furthermore, to increase the control performance of the proposed intelligent control approach, a 32-bit floating-point DSP, TMS320VC33, is adopted for the implementation of the proposed CSMC and SFNN. In addition, some experimental results are illustrated to show the validity of the proposed control approach.     

Towards a real-time processing framework based on improved distributed recurrent neural network variants with fastText for social big data analytics

Big data generated by social media stands for a valuable source of information, which offers an excellent opportunity to mine valuable insights. Particularly, User-generated contents such as reviews, recommendations, and users’ behavior data are useful for supporting several marketing activities of many companies. Knowing what users are saying about the products they bought or the services they used through reviews in social media represents a key factor for making decisions. Sentiment analysis is one of the fundamental tasks in Natural Language Processing. Although deep learning for sentiment analysis has achieved great success and allowed several firms to analyze and extract relevant information from their textual data, but as the volume of data grows, a model that runs in a traditional environment cannot be effective, which implies the importance of efficient distributed deep learning models for social Big Data analytics. Besides, it is known that social media analysis is a complex process, which involves a set of complex tasks. Therefore, it is important to address the challenges and issues of social big data analytics and enhance the performance of deep learning techniques in terms of classification accuracy to obtain better decisions.In this paper, we propose an approach for sentiment analysis, which is devoted to adopting fastText with Recurrent neural network variants to represent textual data efficiently. Then, it employs the new representations to perform the classification task. Its main objective is to enhance the performance of well-known Recurrent Neural Network (RNN) variants in terms of classification accuracy and handle large scale data. In addition, we propose a distributed intelligent system for real-time social big data analytics. It is designed to ingest, store, process, index, and visualize the huge amount of information in real-time. The proposed system adopts distributed machine learning with our proposed method for enhancing decision-making processes. Extensive experiments conducted on two benchmark data sets demonstrate that our proposal for sentiment analysis outperforms well-known distributed recurrent neural network variants (i.e., Long Short-Term Memory (LSTM), Bidirectional Long Short-Term Memory (BiLSTM), and Gated Recurrent Unit (GRU)). Specifically, we tested the efficiency of our approach using the three different deep learning models. The results show that our proposed approach is able to enhance the performance of the three models. The current work can provide several benefits for researchers and practitioners who want to collect, handle, analyze and visualize several sources of information in real-time. Also, it can contribute to a better understanding of public opinion and user behaviors using our proposed system with the improved variants of the most powerful distributed deep learning and machine learning algorithms. Furthermore, it is able to increase the classification accuracy of several existing works based on RNN models for sentiment analysis.     

技术创新网络知识增长过程建模与仿真研究

基于国内外现有研究成果,针对网络密度对技术创新网络知识增长的影响机理,从知识扩散与知识创新两个方面进行了理论分析,提出了网络密度与技术创新网络知识增长呈倒U型关系的研究假设。应用基于多主体(Agent)的建模方法建立一个基于多Agent的技术创新网络知识增长过程模型,采用NetLogo仿真平台进行仿真,对研究假设进行检验。研究结果表明:网络密度具有双面性,太高或太低都不利于技术创新网络的知识增长;网络密度过高往往先抑制技术创新网络知识扩散,随后进一步提高再是阻碍知识创新。     

Optimization of fuzzy model using genetic algorithm for process control application

A technique for the modeling of nonlinear control processes using fuzzy modeling approach based on the Takagi-Sugeno fuzzy model with a combination of genetic algorithm and recursive least square is proposed. This paper discusses the identification of the parameters at the antecedent and consequent parts of the fuzzy model. For the antecedent fuzzy parameters, genetic algorithm is used to tune them while at the consequent part, recursive least squares approach is used to identify the system parameters. This approach is applied to a process control rig with three subsystems: a heating element, a heat exchanger and a compartment tank. Experimental results show that the proposed approach provides better modeling when compared with Takagi Sugeno fuzzy modeling technique and the linear modeling approach.     

基于SOM神经网络的负荷特性分类

负荷模型对电力系统仿真结果有重要影响,由于负荷特性的辨识是负荷建模的主要方面之一,故提高负荷模型的准确度就需要对负荷特性分类进行研究。文章在详细分析SOM自组织映射神经网络结构的基础上,采用了基于SOM神经网络的负荷分类方法,以负荷模型参数作为负荷动态特性分类特征向量,应用SOM神经网络对负荷特性进行分类,并对分类结果进行测试,结果表明该方法可有效地对负荷样本进行分类。     

基于人工神经网络的汉字识别方法研究

电子计算机广泛应用于信息处理中,有极强的算术和逻辑运算能力,有极高的运算速度、精确度和可靠度。但是,它的形象思维能力与人相距甚远。如果计算机具备了模式识别能力,人们就可以使用机器来执行感知任务。文章运用了人工神经网络,模式识别的方法及原理,以Matlab软件作为平台来探讨应用神经网络对汉字进行识别。并通过对汉字样本图象采集输入,汉字图象二值化,行字切分,十进制存储等预处理,分别在有、无干扰的情况下对汉字进行识别,从而评价其性能的优劣。     

基于BP神经网络的经理管理防御程度测评模型

提出一种基于主成分分析的BP神经网络模型,用于对经理人员的管理防御程度进行综合测评.首先采用主成分分析方法对10个影响因素进行降维处理,在此基础上构建管理防御程度的BP神经网络测评模型.实际测评结果显示,该模型不仅可以有效测评经理人员的管理防御程度,并且可以减少原始指标间的信息冗余从而减少了神经网络的训练和测试时间,此外还具有较高的合理性和适用性.