Artificial neural network application for modeling the rail rolling process

Rail rolling process is one of the most complicated hot rolling processes. Evaluating the effects of parametric values on this complex process is only possible through modeling. In this study, the production parameters of different types of rails in the rail rolling processes were modeled with an artificial neural network (ANN), and it was aimed to obtain optimum parameter values for a different type of rail. For this purpose, the data from the Rail and Profile Rolling Mill in Kardemir Iron & Steel Works Co. (Karabük, Turkey) were used. BD1, BD2, and Tandem are three main parts of the rolling mill, and in order to obtain the force values of the 49 kg/m rail in each pass for the BD1 and BD2 sections, the force and torque values for the Tandem section, parameter values of 60, 54, 46, and 33 kg/m type rails were used. Comparing the results obtained from the ANN model and the actual field data demonstrated that force and torque values were obtained with acceptable error rates. The results of the present study demonstrated that ANN is an effective and reliable method to acquire data required for producing a new rail, and concerning the rail production process, it provides a productive way for accurate and fast decision making.     

Time series forecasting by neural networks: A knee point-based multiobjective evolutionary algorithm approach

In this paper, we investigate the problem of time series forecasting using single hidden layer feedforward neural networks (SLFNs), which is optimized via multiobjective evolutionary algorithms. By utilizing the adaptive differential evolution (JADE) and the knee point strategy, a nondominated sorting adaptive differential evolution (NSJADE) and its improved version knee point-based NSJADE (KP-NSJADE) are developed for optimizing SLFNs. JADE aiming at refining the search area is introduced in nondominated sorting genetic algorithm II (NSGA-II). The presented NSJADE shows superiority on multimodal problems when compared with NSGA-II. Then NSJADE is applied to train SLFNs for time series forecasting. It is revealed that individuals with better forecasting performance in the whole population gather around the knee point. Therefore, KP-NSJADE is proposed to explore the neighborhood of the knee point in the objective space. And the simulation results of eight popular time series databases illustrate the effectiveness of our proposed algorithm in comparison with several popular algorithms.     

Use of ANP weighted crisp and fuzzy QFD for product development

Quality Function Deployment (QFD) is a popular planning method often used to transform customer demands/requirements into the technical characteristics of a new or improved product or service. In order to better capture (and represent) the multifarious relationships between customer requirements and technical characteristics, and the relative weights among customer requirements, in this study a hybrid analytic network process (ANP)-weighted fuzzy methodology is proposed. The goal is to synthesize renowned capabilities of ANP and fuzzy logic to better rank technical characteristics of a product (or a service) while implementing QFD. To demonstrate the viability of the proposed methodology a real-world scenario, where a new equipment to squeeze the polyethylene pipes to stop the gas flow without damaging the pipes, is developed. The ranking of technical characteristics of the product is calculated using both crisp and fuzzy weights for illustration and comparison purposes.     

A hybrid intelligent system for medical data classification

In this paper, a hybrid intelligent system that consists of the Fuzzy Min–Max neural network, the Classification and Regression Tree, and the Random Forest model is proposed, and its efficacy as a decision support tool for medical data classification is examined. The hybrid intelligent system aims to exploit the advantages of the constituent models and, at the same time, alleviate their limitations. It is able to learn incrementally from data samples (owing to Fuzzy Min–Max neural network), explain its predicted outputs (owing to the Classification and Regression Tree), and achieve high classification performances (owing to Random Forest). To evaluate the effectiveness of the hybrid intelligent system, three benchmark medical data sets, viz., Breast Cancer Wisconsin, Pima Indians Diabetes, and Liver Disorders from the UCI Repository of Machine Learning, are used for evaluation. A number of useful performance metrics in medical applications which include accuracy, sensitivity, specificity, as well as the area under the Receiver Operating Characteristic curve are computed. The results are analyzed and compared with those from other methods published in the literature. The experimental outcomes positively demonstrate that the hybrid intelligent system is effective in undertaking medical data classification tasks. More importantly, the hybrid intelligent system not only is able to produce good results but also to elucidate its knowledge base with a decision tree. As a result, domain users (i.e., medical practitioners) are able to comprehend the prediction given by the hybrid intelligent system; hence accepting its role as a useful medical decision support tool.     

神经网络在炸药晶体密度预测中的应用

运用密度泛函理论,在DFT-B3LYP/6-31G·的水平上对16种炸药分子进行全分子优化,并进行频率振动分析,分析了求得各个炸药分子量化结构参数,结果表明,平均极化率、平均四极矩和偶极矩与炸药密度有较好的相关性.结合人工神经网络算法,用以上3种参数作为描述符,构建炸药密度的网络预测模型.预测结果表明,预测值与文献值的最大相对误差为6.6%,最小相对误差为0.47%,说明神经网络可以用来预测炸药密度.     

Mn对含炭耐火材料抗渣侵蚀性的影响

以烧结板状刚玉、锆莫来石、天然鳞片状石墨为主原料 ,酚醛树脂为结合剂 ,Al、Si、B4C、Mn粉为添加剂 ,经 1 4 50℃埋炭烧成后 ,制成铝炭和铝锆炭系列试样 ,并对各试样的抗渣侵蚀性能进行了对比研究。结果表明 :在铝锆炭材料中 ,当Mn与Al、Si复合加入且Mn与C的质量比为 1∶4时 ,试样的抗侵蚀性和渗透性均较好 ;在铝炭材料中 ,当Mn与Al、Si、B4C复合加入且Mn与C的质量比为 1∶4时 ,试样的抗渗透性较好     

无线传感网络中拥塞控制与路由的跨层设计:分布式牛顿法

无线传感网络应用广泛, 其性能与路由选择和拥塞控制密切相关. 致力于拥塞控制与多径路由的跨层优化, 以实现在链路容量受限和节点能量受限情况下的无线传感网络效用最大化. 针对对偶次梯度算法具有收敛速度慢与信息交互量大等缺陷, 设计了具有二阶收敛性能的分布式牛顿算法来实现网络效用最大化. 通过矩阵分裂技术, 实现了只需单跳信息交互的牛顿对偶方向的分布式求解方法. 仿真结果表明, 分布式牛顿算法的收敛性能显著优于对偶次梯度算法.     

带观测滞后和不确定噪声方差的多智能体传感网络鲁棒序贯协方差交叉融合Kalman滤波

针对带观测滞后和不确定噪声方差的分簇多智能体传感网络系统,研究鲁棒序贯协方差交叉融合Kalman滤波器的设计问题.应用最邻近法则,传感网络被分成簇.应用极大极小鲁棒估计原理,基于带噪声方差最差保守上界的最差保守传感网络系统,提出了两级序贯协方差交叉(SCI)融合鲁棒稳态Kalman滤波器,可减小通信和计算负担并节省能量,且保证实际滤波误差方差有一个最小保守上界.一种Lyapunov方程方法被提出用于证明局部和融合滤波器的鲁棒性.提出了鲁棒精度的概念且证明了局部和融合鲁棒Kalman滤波器的鲁棒精度关系.证明全局SCI融合器的鲁棒精度高于每簇SCI融合器的精度且两者的鲁棒精度都高于每个局部鲁棒滤波器的精度.一个跟踪系统的仿真例子证明了鲁棒性和鲁棒精度关系.     

A hybrid hub-and-spoke postal logistics network with realistic restrictions: A case study of Korea Post

Postal logistics has a complex transportation network for efficient mail delivery. Therefore, a postal logistics network consists of various functional sites with a hybrid hub-and-spoke structure. More specifically, there are multiple Delivery & Pickup Stations (D&PSs), multiple Mail Processing Centers (MPCs), and one Exchange Center (EC). In this paper, we develop two mathematical models with realistic restrictions for Korea Post for the current postal logistics network by simultaneously considering locations and allocations. We propose an Integer Linear Programming (ILP) model for transportation network organization and vehicle operation and a Mixed Integer Linear Programming (MILP) model that considers potential ECs for decision making while simultaneously regarding the EC location, transportation network organization, and vehicle operation. We use modified real data from Korea Post. Additionally, we consider several scenarios for supporting EC decision makers. The proposed models and scenarios are very useful in decision making for postal logistics network designers and operators.     

An effective node-selection scheme for the energy efficiency of solar-powered WSNs in a stream environment

Previous research on scheduling and solar power issues of wireless sensor networks (WSNs) assumes that the sensors are deployed in a general environment. While monitoring the stream environment, sensors are attached to the stream side to collect the sensed data and transmit the data back to the sink. The stream environment can be scaled in several similar environments. This type of geographic limitation not only exists in a stream environment but also on streets, roads, and trails. This study presents an effective node-selection scheme to enhance the efficiency of saving power and coverage of solar-powered WSNs in a stream environment. Analysis of the sensor deployment in the stream environment permits sensors to be classified into different segments, and then allows the selection of active nodes for building inter-stream connections, inter-segment connections, and intra-segment connections. Based on these connections, the number of active nodes and transmitted packets is minimized. Simulation results show that this scheme can significantly increase the energy efficiency and maintain the monitoring area in solar-powered WSNs.