无缝钢管张减过程平均壁厚控制迭代自学习方法

迭代学习控制针对具有重复运行性质的系统 ,利用系统实际输出与期望输出的偏差信号 ,产生新的控制信号 ,使得系统跟踪调节性能得以提高。根据张减过程轧制前后钢管壁厚的实测数据和钢管的特征数据 ,采用迭代自学习控制算法 ,提出了无缝钢管张减过程的平均壁厚控制的迭代自学习控制。该控制技术在轧制过程中在线自适应调整各轧制机架的稳态转速分布 ,补偿由物理参数的时变不确定性和建模误差造成的轧辊转速分布参数误差。

汽车起步离合器半接合点自学习方法研究

在离合器控制过程中,离合器半接合点位置是一个非常重要的控制参数,对离合器过程控制的性能有着重要的影响;因此,对这个位置的自学习算法具有重大的工程实践意义。对离合器半接合点的识别是通过离合器本身特性及其接合过程特征实现的,因此算法需要使整车运行到能体现离合器半接合点特征的工况,然后根据该工况下的信号特征识别出半接合点位置。

客车轻便换挡系统自学习方法的研究

介绍了客车轻便换挡(Electronic Pneumatics Shift,简称EPS)系统的基本原理,并针对轻便换挡系统的适应性问题,提出了一种寻求最佳换挡力的在线、实时自学习方法。

基于SVM算法的工业防火墙规则自学习方法

针对工控网络的攻击不断增多,工业防火墙在网络防火墙基础上增加工业协议过滤模块,在应用层深度解析工业协议内部,添加基于白名单策略的过滤规则表,只允许合法数据通过,从而提高工控网络安全。提出一种自生成过滤规则的方法,利用SVM算法对提取的工控网络数据特征学习生成识别模型,通过优化训练样本与模型参数提高模型识别性能,然后识别出正常数据自动添加进过滤规则表。实验结果表明,该方法生成过滤规则准确率高,提高了工业防火墙整体性能。

商用车AMT车重快速自学习方法

整车载荷是重型商用车换挡规律非常重要的控制输入量,可以根据动态载荷对挡位进行差值修正。文章以一款全自动变速器(AMT)车型为研究对象,通过起步过程的动力学分析,提出了一种在起步过程中进行车辆质量自学习的方法。试验表明,此方法可以快速估算车辆质量,精度满足换挡规律的要求,解决了车辆空载新的驾驶循环前几次换挡驾驶性差的问题,满足驾驶员需求。

一种基于改进AGNES算法的POS机位置自学习方法

由于POS机刷卡量持续增长,寻找一种能减少银行卡盗刷现象的有效手段迫在眉睫。提出一种基于改进的AGNES算法的POS机位置自学习方法,并利用运营商移动网络现有位置服务,可向银行信用卡中心提供实时的持卡入手机位置和刷卡位置的一致性查询服务,模拟验证实验结果表明,该方法对于判断POS刷卡是否正常具有一定参考作用。

基于半监督学习的命名实体识别的方法

命名实体识别是信息抽取中基础且关键的一项子任务。本文根据不同领域文本的特性,设置了通用的特征模板,利用半监督学习的方法,对新闻文本和桥梁文本分别进行了命名实体识别。实验表明,仅使用少量标注的语料也可以达到较好的识别效果。

基于置信规则库的防空目标意图识别方法

为解决防空反导体系对于目标意图识别中多源信息处理的问题,提出了一种新的防空目标识别方法——置信规则库(Belief Rules Base)识别模型,该方法是基于BRB专家知识系统的自学习方法,可以有效处理多源不确定性信息。同时,为了提高其识别效率,建立了一种与之相匹配的参数优化模型,并选择差分进化算法作为BRB识别模型的优化引擎。此外,在BRB识别模型中,专家意见也被引用到模型的初始化和推理过程中。最后采用一个实例对BRB识别模型的准确度进行验证。研究表明:该方法具有较强的实用性,可为防空反导体系的目标意图识别提供有力支撑。

自学习模糊控制器在锅炉水位控制中的应用

本文针对船用锅炉水位控制问题，提出一种学习模糊控制器，介绍了自学习方法及变量的归一模糊化，针对某船主锅炉进行了仿真研究，并给出了仿真结果。

L型电控发动机过程控制模型分析与研究

世界能源环境状况的变化使汽车制造企业面临更大的压力和挑战,作为尾气排放的直接及唯一来源,汽车发动机的电子控制也面临着更高、更严格的技术要求。现以L型电控燃油喷射发动机为例,提出了一种首先利用数学运算方法建立起发动机运行过程中燃油喷射量基本模型,并利用ECU在控制过程中对该模型中系数进行调整与转换、存储与调用,从而实现发动机工作过程中实时调整喷油量的自学习方法。最终,结合原有发动机的空燃比闭环控制,能够进一步提高燃油喷射量的控制精度,大大减少尾气的排放。

测量系统小波与神经网络联合去噪研究

本文将神经网络的非线性阈值单元和训练方法引入小波去噪中 ,提出了一种具有阈值自学习能力的小波与神经网络联合去噪方法。这一方法的去噪阈值能够根据训练信号进行学习 ,有利于针对实际系统寻找较优的去噪阈值 ,适用于对确定系统的测量信号进行去噪。文中给出了相应的训练算法并对该方法的有效性进行了检验。

An Intelligent Neural Networks System for Adaptive Learning and Prediction of a Bioreactor Benchmark Process

The adaptive learning and prediction of a highly nonlinear and time-varying bioreactor benchmark process is studied using Neur-On-Line, a graphical tool kit for developing and deploying neural networks in the G2 real time intelligent environment,and a new modified Broyden, Fletcher, Goldfarb, and Shanno （BFGS） quasi-Newton algorithm. The modified BFGS algorithm for the adaptive learning of back propagation （BP） neural networks is developed and embedded into NeurOn-Line by introducing a new search method of learning rate to the full memory BFGS algorithm. Simulation results show that the adaptive learning and prediction neural network system can quicklv track the time-varving and nonlinear behavior of the bioreactor.

Promoting language Learners＇ Autonomy in Cooperative Learning

Learner Autonomy （LA） is the desirable goal of the education. To date, many Learner Autonomy training programs have been carried out in foreign language teaching. Cooperative Learning （CL） is a language teaching and learning strategy which gets learners actively and cooperatively involved in learning a foreign language in groups. Both of them have been respectively advocated from pedagogical point of view and from the perspective of philosophy. However, being autonomous does not necessarily mean learning alone. Language learners should learn cooperatively and autonomously. It is the author＇s contention that CL is a good method to promote LA. CL has positive effects on both students＇ readiness and their ability to be more autonomous. CL enhances self-esteem and self-confidence, increases high motivation, encourages learners＇ responsibility for learning, enhances self-management skills, increases support for language learners to move from interdependence to independence. The paper stresses in the end that promoting LA is the teacher＇s long-term pedagogic goal.

Learner autonomy of English majors in out-of-class English reading program

Learner autonomy plays a vital role in effective out-of-class English reading. The purpose of the research is to find ways of improving leamer autonomy of English majors in out-of-class reading program based on the problem found from the data of a survey among tertiary students in a university in China. Learning portfolio and cooperative reading within the framework of reactive autonomy were introduced by the author as two tentative solutions of promoting learner autonomy in out-of-class English reading program.

The Model of Speaking in Teaching Indonesian to Foreign Speakers Based on Self-Regulated Learning and Anxiety Reduction Approaches

Model for spoken is expected to overcome difficulties in teaching and learning Indonesian language for foreign speakers. Language anxiety is the anxiety that arises when a person learns foreign language. Foreign Language Anxiety （anxiety to learn a foreign language） is of concern or negative emotional reactions that arise when studying or using foreign language. Self-regulated learning is an active and constructive process undertaken by learners in setting goals for their learning and trying to monitor, regulate, and control of cognition, motivation, and behavior, then everything is directed and driven by purpose and adapted to the context and environment. The research method used is an R and D （research and development） method with a sample of foreign speakers of Chinese. Variables that receive interference are the ability to speak in Indonesian, while the variables used to interfere with the self-regulated learning and language anxiety as a variable controller. Intrapersonal factors become barriers that cause stuttering speech limited due to the mastering subject content. On the basis of that, this speaking model applies the principle of self-regulated learning in the learning process, using a communicative and contextual approach. This model intended for foreign speakers who learn Indonesian language outside of Indonesia, so to bring the atmosphere mandated in sociolinguistic built through media and relevant teaching methods.

An Empirical Study on the 1 ＋ 1 Model in College English Listening and Speaking Class

Improving college students＇ listening and speaking ability is a very important part of college English teaching Based on the foreign and domestic studies on how to improve students＇ listening and speaking ability, this paper explores the 1 ＋ 1 model in listening and speaking class, which is to divide the listening and speaking class into two parts--small speaking class combined with students＇ online autonomous learning. Through one-year experiment and study on two classes, although there is no significant difference between the performances of these classes, this study has shed some light on how to vary the teaching methods, how to improve the class efficiency, students＇ autonomy in leaming, and how to build new assessment system. Further studies could be made later based on this

Fast Learning in Spiking Neural Networks by Learning Rate Adaptation

For accelerating the supervised learning by the SpikeProp algorithm with the temporal coding paradigm in spiking neural networks (SNNs), three learning rate adaptation methods (heuristic rule, delta-delta rule, and delta-bar-delta rule), which are used to speed up training in artificial neural networks, are used to develop the training algorithms for feedforward SNN. The performance of these algorithms is investigated by four experiments: classical XOR (exclusive or) problem, Iris dataset, fault diagnosis in the Tennessee Eastman process, and Poisson trains of discrete spikes. The results demonstrate that all the three learning rate adaptation methods are able to speed up convergence of SNN compared with the original SpikeProp algorithm. Furthermore, if the adaptive learning rate is used in combination with the momentum term, the two modifications will balance each other in a beneficial way to accomplish rapid and steady convergence. In the three learning rate adaptation methods, delta-bar-delta rule performs the best. The delta-bar-delta method with momentum has the fastest convergence rate, the greatest stability of training process, and the maximum accuracy of network learning. The proposed algorithms in this paper are simple and efficient, and consequently valuable for practical applications of SNN.

分层模糊控制器的解析表达式及自适应控制方法

为解决模糊多变量控制中的“维数灾”问题 ,提出了一种 4输入 1输出的分层模糊控制器 ,推导了它的解析表达式。依据分层模糊控制器的解析表达式 ,提出了其设计参数的模型参考自学习方法 ,其中参考模型选取典型二阶系统 ,用梯度法设计自学习律 ,在线学习分层模糊控制器的可调参数 ,以达到最优值。为检验所提出控制策略的有效性 ,将其应用到板球系统的轨迹跟踪问题 ,并进行了仿真实验。仿真实验结果表明 ,这种分层模糊控制器的可调参数少 ,学习算法收敛快 ,控制效果好 ,具有较强的实用性。

Teaching Innovation Exploration basic theory of art and technology professionals

According to features of current undergraduate curriculum design in the teaching of art and science, and combing exploration and the problems that exist during the process of teaching of basic theory of art and science, this paper taking design courses of interactive introduction for example, it tries to innovate classroom teaching methods of exhibition of art and technology, interactive art and technology are principle theoretical classes of their major. Making good use of initiative of self- learning is the core element to help students in subjects learning, we constantly improve and perfect teaching concepts and classroom teaching mode to create the space for students to learn and explore actively, make personalized study according to their own characteristics, we make students experience the interest of freedom, autonomy, inquiry learning, enjoy the delight of appearance of personality and vitality of the burst of life vigor. Combining personal teaching experience, we should explore the way to led art students to learn with initiative in principle theoretical classes of their major.