A fuzzy neural network with fuzzy impact grades

Fuzzy rule derivation is often difficult and time-consuming, and requires expert knowledge. This creates a common bottleneck in fuzzy system design. In order to solve this problem, many fuzzy systems that automatically generate fuzzy rules from numerical data have been proposed. In this paper, we propose a fuzzy neural network based on mutual subsethood (MSBFNN) and its fuzzy rule identification algorithms. In our approach, fuzzy rules are described by different fuzzy sets. For each fuzzy set representing a fuzzy rule, the universe of discourse is defined as the summation of weighted membership grades of input linguistic terms that associate with the given fuzzy rule. In this manner, MSBFNN fully considers the contribution of input variables to the joint firing strength of fuzzy rules. Afterwards, the proposed fuzzy neural network quantifies the impacts of fuzzy rules on the consequent parts by fuzzy connections based on mutual subsethood. Furthermore, to enhance the knowledge representation and interpretation of the rules, a linear transformation from consequent parts to output is incorporated into MSBFNN so that higher accuracy can be achieved. In the parameter identification phase, the backpropagation algorithm is employed, and proper linear transformation is also determined dynamically. To demonstrate the capability of the MSBFNN, simulations in different areas including classification, regression and time series prediction are conducted. The proposed MSBFNN shows encouraging performance when benchmarked against other models.     

Application of an adaptive neural fuzzy inference system to thermal comfort and group technology problems

The Adaptive Neural Fuzzy Inference System (ANFIS) is used to design two vague systems, namely thermal comfort and group technologies in production and operations management. Results show that both systems can be modeled successfully by the combined use of a fuzzy approach and neural network learning.     

基于ISSA-LSTM的热舒适短期预测模型

为解决在测试日内的短期预测过程中,农村城镇人体热舒适中建筑惰性及人员等随机因素使人体感受变化的样本对预测结果影响大而导致预测精准度低的问题,提出基于改进麻雀搜索算法（Improvement Sparrow Search Algorithm, ISSA）优化长短期记忆神经网络（Long Short-Term Memory Neural Network, LSTM）的方法建立新型户用空调热舒适短期预测模型。首先,对测试日气象数据进行动态性分析,对数据进行有效性验证并构建多种热舒适预测模型;随后选用新型户用热舒适短期预测模型（ISSA-LSTM）对热舒适进行预测。结果表明,模型的最高预测均方误差（Mean Squared Error,MSE）比麻雀搜索算法（Sparrow Search Algorithm,SSA）和蜣螂优化算法（Dung beetle optimizer,DBO）优化LSTM分别提高了0.02296和0.10827,采用ISSA-LSTM方法后改善了短期热舒适预测的精度问题,并提高了分体式空调通过热舒适来控制温度的性能。     

基于模糊神经网络的通用模型自适应控制

自适应控制是一种提高系统鲁棒性的有效方法。模糊神经网络具有了模糊逻辑和神经网络两者的优点,结合模糊神经网络（Fuzzy Neural Network—FNN）自适应控制策略和通用模型控制（Common Model Control—CMC）方法,以此来实现被控对象的逆控制,提出了基于模糊神经网络的通用模型自适应控制（FNNC—CMAC）。此控制方法参考轨迹是一条典型二阶曲线,仿真结果验证了鲁棒性,与基于模糊神经网络的通用模型控制及基于模糊逻辑的通用模型自适应控制相比,其控制性能更好。     

基于改进的粒子群算法优化反向传播神经网络的热舒适度预测模型

针对热舒适度预测是一个复杂的非线性过程,不便于空调的实时控制应用的问题,提出一种基于改进的粒子群优化(PSO)算法优化反向传播(BP)神经网络的热舒适度预测模型。这一预测模型通过采用PSO算法优化BP神经网络的初始权值和阈值,改善了传统BP算法收敛速度慢及对网络初始值敏感的问题。同时,针对标准PSO算法易出现早熟收敛、局部寻优能力弱等缺点,提出了相应改进策略,进一步提高了PSO优化BP神经网络的能力。实验结果表明：与传统BP模型和标准PSO-BP模型相比,基于改进的PSO-BP算法的热舒适度预测模型具有更高的预测精度和更快的收敛速度。     

A quasi-physical model for predicting the thermal insulation and moisture vapour resistance of clothing

Based on the improved understanding of the effects of wind and walking motion on the thermal insulation and moisture vapour resistance of clothing induced by air ventilation in the clothing system, a new model has been derived based on fundamental mechanisms of heat and mass transfer, which include conduction, diffusion, radiation and natural convection, wind penetration and air ventilation. The model predicts thermal insulation of clothing under body movement and windy conditions from the thermal insulation of clothing measured when the person is standing in the still air. The effects of clothing characteristics such as fabric air permeability, garment style, garment fitting and construction have been considered in the model through the key prediction parameters. With the new model, an improved prediction accuracy is achieved with a percentage of fit being as high as 0.96.     

Applying fuzzy neural network to estimate software development effort

The ability to accurately and consistently estimate software development efforts is required by the project managers in planning and conducting software development activities. Since software effort drivers are vague and uncertain, software effort estimates, especially in the early stages of the development life cycle, are prone to a certain degree of estimation errors. A software effort estimation model which adopts a fuzzy inference method provides a solution to fit the uncertain and vague properties of software effort drivers. The present paper proposes a fuzzy neural network (FNN) approach for embedding artificial neural network into fuzzy inference processes in order to derive the software effort estimates. Artificial neural network is utilized to determine the significant fuzzy rules in fuzzy inference processes. We demonstrated our approach by using the 63 historical project data in the well-known COCOMO model. Empirical results showed that applying FNN for software effort estimates resulted in slightly smaller mean magnitude of relative error (MMRE) and probability of a project having a relative error of less than or equal to 0.25 (Pred(0.25)) as compared with the results obtained by just using artificial neural network and the original model. The proposed model can also provide objective fuzzy effort estimation rule sets by adopting the learning mechanism of the artificial neural network.     

A CAD system for multi-style thermal functional design of clothing

Designing clothing with good thermal functional performance is very demanding and time-consuming if we follow traditional design methods. An innovative method consisting of a CAD system, allowing the designer to perform multi-style clothing thermal functional design on a customized virtual human body, is presented in this paper. The new functionalities of the virtual system provide the abilities to perform intelligent design of different clothing styles and materials for different body parts according to individual design requirements, namely design of various categories of clothing, such as hat, coat, trousers, gloves and shoes in the same design scheme. The designed clothing can be worn on a virtual human body and set in various wearing scenarios. The thermal behaviors in the human body-clothing-environment are simulated to predict the thermal performance of clothing and thermal response of the human body at multi-parts. 2D/3D visualization and animation of the simulation results are presented to help the designers to preview and determine whether the thermal performance of clothing is satisfactory and then obtain feedback to improve their designs iteratively.     

A polynomial fuzzy neural network for modeling and control

This paper introduces a novel neurofuzzy system based on polynomial fuzzy neural network (PFNN) architecture. A PFNN consists of a set of if-then rules with appropriate membership functions (MFs) whose parameters are optimized via a hybrid genetic algorithm. A polynomial neural network is employed in the defuzzification scheme to improve output performance and to select appropriate rules. A performance criterion for model selection is defined to overcome the overfitting problem in the modeling procedure. For a performance assessment of the PFNN inference system, two well-known problems are employed for a comparison with other methods. The results of these comparisons show that the PFNN inference system out-performs the other methods and exhibits robustness characteristics. This work was presented in part at the Fourth International Symposium on Artificial Life and Robotics, Oita, Japan, January 19–22, 1999     

A multi-disciplinary strategy for computer-aided clothing thermal engineering design

The designers and manufactures in apparel industry have urgent needs in designing clothing with superior thermal functions with user-friendly and cost-effective design tools. This paper presents a multi-disciplinary strategy for computer-aided clothing thermal engineering design. It provides a systematical approach to integrate multi-disciplinary knowledge and transfer it into engineering-oriented design tools, thus the designers and manufacturers can easily carry out 1D, 2D and even 3D clothing thermal engineering designs according to the practical design requirements with a short design cycle and low design cost. The research work of this strategy begins from the investigation of the role of the thermal functions of clothing in the thermal comfort of human body. Then the framework is proposed to integrate the multi-disciplinary knowledge and illustrate the process to achieve the thermal engineering design of clothing. The important issues in the realization of computational simulation are addressed, including multi-scale model integration, data availability of characteristic parameters and hierarchical computational scheme. To issue easy-to-use design tools, the thermal functional design of clothing is quantified with important influence parameters, and the user-friendly wizard is designed for the CAD system development. Finally, the design applications of this strategy are discussed in terms of 1D, 2D and 3D thermal engineering designs with versatile CAD systems.     

An improved fuzzy neural network based on T–S model

An improved fuzzy neural network based on Takagi–Sugeno (T–S) model is proposed in this paper. According to characteristics of samples spatial distribution the number of linguistic values of every input and the means and deviations of corresponding membership functions are determined. So the reasonable fuzzy space partition is got. Further a subtractive clustering algorithm is used to derive cluster centers from samples. With the parameters of linguistic values the cluster centers are fuzzified to get a more concise rule set with importance for every rule. Thus redundant rules in the fuzzy space are deleted. Then antecedent parts of all rules determine how a fuzzification layer and an inference layer connect. Next, weights of the defuzzification layer are initialized by a least square algorithm. After the network is built, a hybrid method combining a gradient descent algorithm and a least square algorithm is applied to tune the parameters in it. Simultaneous, an adaptive learning rate which is identified from input-state stability theory is adopted to insure stability of the network. The improved T–S fuzzy neural network (ITSFNN) has a compact structure, high training speed, good simulation precision, and generalization ability. To evaluate the performance of the ITSFNN, we experiment with two nonlinear examples. A comparative analysis reveals the proposed T–S fuzzy neural network exhibits a higher accuracy and better generalization ability than ordinary T–S fuzzy neural network. Finally, it is applied to predict markup percent of the construction bidding system and has a better prediction capability in comparison to some previous models.     

Linguistic time series forecasting using fuzzy recurrent neural network

It is known that one of the most spread forecasting methods is the time series analysis. A weakness of traditional crisp time series forecasting methods is that they process only measurement based numerical information and cannot deal with the perception-based historical data represented by linguistic values. Application of a new class of time series, a fuzzy time series whose values are linguistic values, can overcome the mentioned weakness of traditional forecasting methods. In this paper we propose a fuzzy recurrent neural network (FRNN) based time series forecasting method for solving forecasting problems in which the data can be presented as perceptions and described by fuzzy numbers. The FRNN allows effectively handle fuzzy time series to apply human expertise throughout the forecasting procedure and demonstrates more adequate forecasting results. Recurrent links in FRNN also allow for simplification of the overall network structure (size) and forecasting procedure. Genetic algorithm-based procedure is used for training the FRNN. The effectiveness of the proposed fuzzy time series forecasting method is tested on the benchmark examples.     

基于模糊聚类的模糊神经网络控制

对于复杂的非线性离散系统,提出将模糊聚类算法同神经网络相结合,使用衡量聚类有效性的S函数确定模糊规则数目,进而确定模糊神经网络的结构;控制器的设计应用LMI方法。以典型的非线性系统二级倒立摆为例,在Matlab中进行仿真实验,结果表明,基于聚类算法的神经网络控制能够在较大范围的初始状态下使系统获得稳定。     

神经网络在PMV指标控制中的应用研究

人们对室内热舒适度的关注涉及到与其有关的6个输入因素及PMV控制输出.神经网络具有很强的适应性和在线自学习能力,可以逼近任意非线性映射.用神经网络来训练,可得到空调控制系统的输入输出模型,实现空调的智能控制.     

正则模糊神经网络是模糊值函数的泛逼近器

通过分析多元模糊值Bernstein多项式的近似特性，证明了4层前向正则模糊神经网络（FNN）的逼近性能，该类网络构成了模糊值函数的一类泛逼近器，即在欧氏空间的任何紧集上，任意连续模糊值函数能被这类FNN逼近到任意精度，最后通过实例给出了实现这种近似的具体步骤。     

一种多电机同步传动模糊神经网络控制器的设计

设计了具有知识表达和自学习能力的模糊神经网络同步控制器．建立了模糊控制规则,进而提出了多电机同步控制的模糊神经网络学习算法．对四轴同步控制系统进行仿真实验．结果表明模糊神经网络同步控制器能有效实现多电机同步控制,收敛速度较快．鲁棒性较好。     

基于直觉模糊ART神经网络的群事件检测方法

描述了态势评估系统中的目标编群问题、目标群处理流程和群事件的检测。结合直觉模糊贴近度理论,构造了直觉模糊ART神经网络。设计了网络的运行机制和网络权值向量的学习机制。给出了一个具体实例,检验了直觉模糊ART神经网络的目标编群效果,为群事件检测提供了一条有效途径。     

HPSO-based fuzzy neural network control for AUV

A fuzzy neural network controller for underwater vehicles has many parameters difficult to tune manually. To reduce the numerous work and subjective uncertainties in manual adjustments, a hybrid particle swarm optimization （HPSO） algorithm based on immune theory and nonlinear decreasing inertia weight （NDIW） strategy is proposed. Owing to the restraint factor and NDIW strategy, an HPSO algorithm can effectively prevent premature convergence and keep balance between global and local searching abilities. Meanwhile, the algorithm maintains the ability of handling multimodal and multidimensional problems. The HPSO algorithm has the fastest convergence velocity and finds the best solutions compared to GA, IGA, and basic PSO algorithm in simulation experiments. Experimental results on the AUV simulation platform show that HPSO-based controllers perform well and have strong abilities against current disturbance. It can thus be concluded that the proposed algorithm is feasible for application to AUVs.