脉冲GTAW熔池动态过程模糊神经网络建模与控制

展示了模糊推理与神经网络结合在脉冲GTAW熔池动态过程智能控制中的应用研究 结果.建立了脉冲GTAW平板对接动态过程特征:正反面熔池的最大宽度、长度与面积等参数 的神经网络模型,基于实验数据采用模糊辨识方法提取焊接过程的模糊控制规则,进而设计了 具有自学习适应能力的模糊神经网络控制器.建立了脉冲GTAW熔池动态过程智能控制系统, 焊接实验验证了所设计的模糊神经网络控制器具有智能控制效果.     

一种用模糊—神经技术建造专家系统的方法

本文提出了一种用模糊－神经技术建造专家系统的方法。从领域专家处获取的知识是以模糊规则和隶属函数的形式表示的。根据本文提出的方法，首先将模糊规则和隶属函数用神经网络表示出来（导入）；生成的神经网络用于实现模糊推理，然后利用修改的反传算法训练神经网络，从而提高系统的精度，修改隶属函数，求精模糊规则；最后从神经网络中提取隶属函数和模糊规则（导入），帮助解释神经网络的内部表示和操作，利用本文所提出的方法建     

一种新的模糊规则提取方法

提出了一种新的模糊规则提取方法,该方法先采用基于山峰函数的减法聚类法自适应地确定初始的聚类中心,然后由此构造动态自组织神经网络进行学习,在学习的过程中可根据情况适当地合并或分裂神经元,并重构神经网络继续学习,最后按聚类中心确定模糊子集数目和隶属函数并形成模糊规则集.实验结果表明,通过网络结构和神经元的动态自适应变化能够获取样本集中的模糊信息,形成直观的模糊规则.     

一种用模糊－神经技术建造专家系统的方法

本文提出了一种用模糊－神经技术建造专家系统的方法（ＦＮＴ方法）。从领域专家处获取的知识是以模糊规则和隶属函数的形式表示的。根据本文提出的方法，首先将模糊规则和隶属函数用神经网络表示出来（导入）；生成的神经网络用于实现模糊推理，然后利用修改的反传算法训练神经网络，从而提高系统的精度，修改隶属函数，求精模糊规则；最后从神经网络中提取隶属函数和模糊规则（导出），帮助解释神经网络的内部表示和操作。利用本文所提出的方法建造的系统可实现快速的无匹配模糊推理，并具有较强的学习能力。     

机器人神经模糊控制

本文首先讨论了机器人动力学的特殊性，提出了一种基于神经网络的模糊控制方法。该方法借助于一类新型的神经网络结构，实现了模糊规则的自动更新和隶属函数的自调整。该算法被用于机器人动态控制，取得了满意的仿真结果。     

一种基于动态聚类的模糊分类规则的生成方法

介绍了一种基于动态聚类的模糊分类规则的生成方法，这种方法能决定规则数目，隶属函数的位置及形状．首先，介绍了基于超圆雏体隶属函数的模糊分类规则的基本形式；然后，介绍动态聚类算法，该算法能将每一类训练模式动态的分为成簇，对于每簇，则建立一个模糊规则；通过调整隶属函数的斜度，来提高对训练模式分类识别率，达到对模糊分类规则进行优化调整的目的；用两个典型的数据集评测了这篇文章研究的方法，这种方法构成的分类系统在识别率与多层神经网络分类器相当，但训练时间远少于多层神经网络分类器的训练时间．     

神经模糊控制在船舶自动舵中的应用

针对常规模糊自动舵由于受船舶控制过程的非线性、时变性以及风浪干扰等因素影响,模糊控制规则和隶属函数需要校正,利用神经网络的自学习能力,用神经网络去实现模糊控制,设计自动舵神经模糊控制器,采用BP算法和最小二乘算法的混合学习算法实现对模糊规则和隶属函数的参数训练,提高控制器的自适应能力。仿真实验表明所设计的控制器有效可行,适应船舶在风浪干扰环境下的控制性能要求。     

神经模糊控制在船舶自动舵中的应用

针对常规模糊自动舵由于受船舶控制过程的非线性、时变性以及风浪干扰等因素影响,模糊控制规则和隶属函数需要校正,利用神经网络的自学习能力,用神经网络去实现模糊控制,设计自动舵神经模糊控制器,采用BP算法和最小二乘算法的混合学习算法实现对模糊规则和隶属函数的参数训练,提高控制器的自适应能力.仿真实验表明所设计的控制器有效可行.适应船舶在风浪干扰环境下的控制性能要求.     

智能系统中获取模糊规则的神经网络方法

智能系统中一类重要的定性知识要用模糊集理论中的模糊语言进行描述。本文在研究模糊定性知识形式描述和自组织竞争神经网络特性的基础上，提出了一种从一组具有数值特性的训练样本集中获取隶属函数和模糊规则的神经网络模型和方法。通过对Ｉｒｉｓ数据集的应用实验表明了该方法能对这一类数据进行有效的描述。     

基于模块化模糊子系统的分层模糊神经网络

提出一种基于模块化模糊子系统的分层模糊神经网络,该分层模糊神经网络基于高斯隶属函数,且功能上等价于一个TSK模糊系统,这种分层神经网络在保留了传统模糊神经网络很多优点的同时有效地抑制了“维数灾”问题,而且在模糊子系统中模糊规则的激活强度有所提高,仿真试验结果表明。该方法能获得更为简洁有效的模糊规则集。     

Neural-network-based self-organized fuzzy logic control for arc welding

Fuzzy logic control (FLC) is becoming an attractive technique to control processes in welding mainly due to its ability to solve problems in the absence of an accurate mathematical model. In this paper, a novel technique, that combines both FLC and neural network (NN) techniques is presented to control the gas tungsten arc welding (GTAW) process. This technique overcomes limitations such as the dependency on the experts for fuzzy rule generation and non-adaptive fuzzy set. The adaptation of membership function as well as the self-organizing of fuzzy rule are realized by the self-learning and competitiveness of the NN. This approach facilitates the automatic determination of the fuzzy rule and in-process adaptation of membership function for an advanced welding process control. This overcomes the limitations of a fixed membership function, which cannot guarantee the required performance in a highly time-variable environment such as an arc-welding process. The proposed technique has been verified to be highly effective in an arc-welding process in which the welds bead width is regulated. Computer simulations confirm that the characteristics of the system have improved notably when compared with the currently available methods.     

SVM-based fuzzy rules acquisition system for pulsed GTAW process

This paper proposes a support vector machine-based fuzzy rules acquisition system (SVM-FRAS) for modeling of the gas tungsten arc welding (GTAW) process. The character of SVM in extracting support vector provides a mechanism to extract fuzzy IF–THEN rules from the training data set. We construct the fuzzy inference system using fuzzy basis function. The gradient technique is used to tune the fuzzy rules and the inference system. Theoretical analysis and comparative tests are performed comparing with other fuzzy systems. Modeling is one of the key techniques in the automatic control of the arc welding process, and is still a very difficult problem. Comprehensibility is one of the required characteristics in modeling for the complex GTAW process. We use the proposed SVM-FRAS to obtain the rule-based model of the aluminum alloy pulse GTAW process. Experimental results show the SVM-FRAS model possesses good generalization capability as well as high comprehensibility.     

Closed-Loop Control of Robotic Arc Welding System with Full-penetration Monitoring

The real-time detection of the state of the gap and weld penetration control are two fundamental issues in robotic arc welding. However, traditional robotic arc welding lacks external information feedback and the function of real-time adjusting. The objective of this research is to adopt new sensing techniques and artificial intelligence to ensure the stability of the welding process through controlling penetration depth and weld pool geometry. A novel arc welding robot system including function modules (visual modules, data acquisition modules) and corresponding software system was developed. Thus, the autonomy and intelligence of the arc welding robot system is realized. Aimed at solving welding penetration depth, a neural network (NN) model is developed to calculate the full penetration state, which is specified by the back-side bead width (Wb), from the top-side vision sensing technique. And then, a versatile algorithm developed to provide robust real-time processing of images for use with a vision-based computer control system is discussed. To this end, the peak current self adaptive regulating controller with weld gap compensation was designed in the robotic arc welding control system. Using this closed-loop control experiments have been conducted to verify the effectiveness of the proposed control system for the robotic arc welding process. The results show that the standard error of the Wb is 0.124 regardless of the variations in the state of the gap.     

AGFS: Adaptive Genetic Fuzzy System for medical data classification

A Genetic Fuzzy System (GFS) is basically a fuzzy system augmented by a learning process based on a genetic algorithm (GA). Fuzzy systems have demonstrated their ability to solve different kinds of problems in various application domains. Currently, there is an increasing interest to augment fuzzy systems with learning and adaptation capabilities. Two of the most successful approaches to hybridize fuzzy systems with learning and adaptation methods have been made in the realm of soft computing. The GA can be merged with Fuzzy system for different purposes like rule selection, membership function optimization, rule generation, co-efficient optimization, for data classification. Here we propose an Adaptive Genetic Fuzzy System (AGFS) for optimizing rules and membership functions for medical data classification process. The primary intension of the research is 1) Generating rules from data as well as for the optimized rules selection, adapting of genetic algorithm is done and to explain the exploration problem in genetic algorithm, introduction of new operator, called systematic addition is done, 2) Proposing a simple technique for scheming of membership function and Discretization, and 3) Designing a fitness function by allowing the frequency of occurrence of the rules in the training data. Finally, to establish the efficiency of the proposed classifier the presentation of the anticipated genetic-fuzzy classifier is evaluated with quantitative, qualitative and comparative analysis. From the outcome, AGFS obtained better accuracy when compared to the existing systems.     

Robotic Welding Systems with Vision-Sensing and Self-learning Neuron Control of Arc Welding Dynamic Process

This paper addresses the vision sensing and neuron control techniques for real-time sensing and control of weld pool dynamics during robotic arc welding. Current teaching playback welding robots are not provided with this real-time function for sensing and control of the welding process. In our research, using composite filtering technology, a computer vision sensing system was established and clear weld pool images were captured during robotic-pulsed Gas Tungsten Arc Welding (GTAW). A corresponding image processing algorithm has been developed to pick up characteristic parameters of the weld pool in real-time. Furthermore, an ANN model of the weld pool dynamic process of robotic-pulsed GTAW was developed. Based on neuron self-learning PSD controller design, the real-time control of weld pool dynamics during the pulsed GTAW process has been realized in robotic systems.     

Influential rule search scheme (IRSS) - a new fuzzy pattern classifier

Automatic generation of fuzzy rule base and membership functions from an input-output data set, for reliable construction of an adaptive fuzzy inference system, has become an important area of research interest. We propose a new robust, fast acting adaptive fuzzy pattern classification scheme, named influential rule search scheme (IRSS). In IRSS, rules which are most influential in contributing to the error produced by the adaptive fuzzy system are identified at the end of each epoch and subsequently modified for satisfactory performance. This fuzzy rule base adjustment scheme is accompanied by an output membership function adaptation scheme for fine tuning the fuzzy system architecture. This iterative method has shown a relatively high speed of convergence. Performance of the proposed IRSS is compared with other existing pattern classification schemes by implementing it for Fisher's iris data problem and Wisconsin breast cancer data problems.     

Research on the Real-time Tracking Information of Three-dimension Welding Seam in Robotic GTAW Process Based on Composite Sensor Technology

Aiming at the shortcomings of teaching-playback robot that can??t track the three-dimensional welding seam in real time during GTAW process, this paper designed a set of composite sensor system for tracking the three-dimensional welding seam based on visual sensor and arc sensor technology, which can effectively acquire three-dimensional welding seam information, such as clear images of seam and pool and stable arc voltage signals. The characteristic values of weld image and arc voltage signals were accurately extracted by using proper processing algorithm, and the experiments have been done to verify the precision of processing algorithms. The results demonstrate that the error is very small, which is accurate enough to meet the requirements of the subsequent real-time tracking and controlling during the welding robot GTAW process.     

Intelligent modelling and optimization of the gas tungsten arc welding process

This paper describes an application of neural networks and simulated annealing (SA) algorithm to model and optimize the gas tungsten arc welding (GTAW) process. The relationships between welding process parameters and weld pool features are established based on neural networks. In this study, the counter-propagation network (CPN) is selected to model the GTAW process due to the CPN equipped with good learning ability. An SA optimization algorithm is then applied to the CPN for searching for the welding process parameters with optimal weld pool features. Experimental results have shown that GTAW performance can be enhanced by using this approach.     

Generalised influential rule search scheme for fuzzy function approximation

The present paper is a humble attempt to develop a fuzzy function approximator which can completely self-generate its fuzzy rule base and input-output membership functions from an input-output data set. The fuzzy system can be further adapted to modify its rule base and output membership functions to provide satisfactory performance. This proposed scheme, called generalised influential rule search scheme, has been successfully implemented to develop pure fuzzy function approximators as well as fuzzy logic controllers. The satisfactory performance of the proposed scheme is amply demonstrated by implementing it to develop different major components in a process control loop. The versatility of the algorithm is further proved by implementing it for a benchmark nonlinear function approximation problem.