Identification of variegated coloring in skin tumors: neuralnetwork vs. rule-based induction methods

The use of neural networks for automatic identification of variegated coloring, which is believed to be one of the most predictive features for malignant melanoma, is described. The Nestor development system (NDS) was chosen for neural network implementation. At the heart of NDS is a three-layer neural network called a restricted Coulomb energy (RCE) network. The learning scheme and the database for detection of variegated coloring are discussed. Results are reported     

人工智能在电力市场竞价策略中的应用

在电力市场环境下,发电厂商可通过策略性的竞价取得最大利润.介绍了人工神经网络在电力市场市场清算价预测上的应用,以及用模糊聚类(FCM)和人工神经网络(ANN)构造发电厂商最优报价策略的方法.指出人工智能在电力市场竞价策略这一课题领域的应用前景.     

Applications of artificial intelligence in power systems

Application of Artificial Intelligence technologies (mainly in the form of Expert Systems) to power systems has been an active area of research for about a decade and significant successes have been achieved. This paper lists the literature related to artificial intelligence applications to power systems and notes the artificial intelligence technologies that are becoming important in conjunction with expert systems.     

A combinatorial artificial intelligence real-time solution to the unit commitment problem incorporating V2G

Plug-in hybrid electric vehicles (PHEVs) have been the center of attention in recent years as they can be utilized to set up a bidirectional connection to a power grid for ancillary services procurement. By incorporating Vehicle to Grid (V2G), this paper proposes a real-time solution to a non-convex constrained unit commitment (UC) optimization problem considering V2G parking lots as dispersed generation units. V2G parking lots can be considered as virtual power plants that my decrease dependency to small expensive units in a UC problem. In this paper, firstly a probabilistic attendance model of PHEVs in a parking lot is investigated, while expected number of PHEVs as well as the equivalent generation capacity of the parking lot is obtained using a radial basis neural network. Secondly, a particular UC problem considering V2G parking lot is solved using GA-ANN as a hybrid heuristic method. A real-time estimation of PHEVs number in the V2G parking lot and real-time solution to UC–V2G problem associated with load variation makes this work distinguished, while the proposed method is applied to a standard IEEE 10-unit test system with promising results.     

钻井事故人工智能实时监控系统

钻井事故实时监控系统是利用故障与征兆之间的关系对地下钻井复杂系统的运行状态进行实时监测、诊断和控制。简要地介绍了钻井事故监控系统软件开发的思路和关键部分的知识组织开发。     

High voltage transmission lines studies with the use of artificial intelligence

The paper presents an alternative approach for the studies of high voltage transmission lines based on artificial intelligence and more specifically artificial neural networks (ANNs). In contrast to the existing conventional–analytical techniques and simulations which are using in the calculations empirical and/or approximating equations, this approach is based only on actual field data and actual measurements. The proposed approach is applied on high voltage transmission lines in order to calculate the lightning outages, on grounding systems in order to assess the grounding resistance and on high voltage transmission lines’ polluted insulators in order to estimate the critical flashover voltage. The obtained results are very close to the actual ones for all three case studies, something which clearly implies that the ANN approach is well working and has an acceptable accuracy, constituting an additional tool of electric engineers.     

Four methods for short-term load forecasting using the benefits of artificial intelligence

Four methods are developed for short-term load forecasting and are tested with the actual data from the Turkish Electrical Authority. The method giving the most successful forecasts is a hybrid neural network model which combines off-line and on-line learning and performs real-time forecasts 24-hours in advance. Loads from all day types are predicted with 1.7273% average error for working days, 1.7506% for Saturdays and 2.0605% for Sundays.     

人工智能在电气自动化控制方面的实践运用分析

随着人工智能的发展,第四次工业革命应时而来。从历代工业革命的发展来看,每次工业革命都昭示着整个时代的全面变革与进步,更为人类社会经济发展与人类文明建设进程带来巨大的机遇和挑战。电气系统的自动化控制技术显然是第四次工业革命所带来的时代硕果,更是人工智能应用的典型领域之一。本文从电气自动化控制方面分析了人工智能的实践和应用,以期为人工智能在我国电气自动化控制方面的应用带来一定的推动和指导作用。     

人工智能背景下测量仪器技术发展探讨

电子测量技术作为装备发展、科技创新的基础性和引领性技术,其发展水平对提升国家科技水平、增强国防科技力量有着重大影响。在数字化、智能化、网络化高新技术快速发展背景下,测试需求和测试任务不断演化,对测试指标和测试功能提出更高要求,传统测试技术急需与先进技术融合创新发展,打破原有技术瓶颈,为国家战略科技力量贡献积极作用。该文在概述测量仪器发展现状和驱动因素基础上,讨论了人工智能技术对于测量仪器具有较大价值的特性,对人工智能技术为测量仪器赋能的几种方式进行了分析。展望了人工智能技术与测量仪器相结合的趋势,探讨了人工智能背景下测量仪器研发和规划方向。为人工智能高速发展背景下,如何实现测试仪器智能化,如何实现我国高端仪器仪表自主创新、自立自强发展提供参考。     

Increase in the efficiency of the speed controller of an induction machine drive by means of artificial intelligence

This paper describes the application of artificial intelligence to the synthesis of an efficient speed controller for an indirect field-oriented induction machine drive. In this case, two methods of artificial intelligence are proposed to reproduce the characteristics of a fuzzy controller with the maximum number of fuzzy sets. The first method is the adaptive network-based fuzzy inference system (ANFIS) structure by Sugeno and the second is the artificial neural network (ANN) structure. The resulting characteristics of each controller are presented.     

Diagnostics of the information subsystem of an automatic process control system using artificial intelligence technologies

A method for diagnosing partial failures of the measuring-and-information channels of an automatic process control system is considered on the basis of modern artificial intelligence technologies. The algorithm proposed for correcting the results of measurements is based on the information redundancy of a technological process. The possibility of using neural network technologies, evolution optimization algorithms, and fuzzy logic elements is investigated.     

改进的人工鱼群算法在水质参数识别中的应用

水质参数是建立河流水质数学模型、预报河流水质状态变化的基本数据.因此,准确估计模型参数具有重要意义.通过构造目标函数使模拟结果与已知值之间误差达到最小,从而将此参数估计问题转化为一个参数优化问题进行求解.结合水质模型参数优化的特点,将具有收敛速度快、全局优化能力强的新型智能算法-改进的人工鱼群算法应用于该优化问题求解.通过进行多组参数组合实验,结果表明:当参数变化范围较小时,改进的人工鱼群算法在求解上述问题上具有较好的适用性和有效性,可以获得较为精确的结果;但随着参数变化范围的不断扩大,该算法的搜索效率和精度有所下降.关于算法参数的设置,如何解决算法受参数变化范围的影响问题都是需要进一步研究的问题.     

Engineering in genomics: the emerging in-silico scientist; how text-based bioinformatics is bridging biology and artificial intelligence

Current work in text-based bioinformatics has both immediate and future applications. It has been said that AI has not lived up to its promise, in part because AI is most successful at performing tasks that humans perform poorly and least successful at tasks where humans excel. That is, they excel at tasks such as classification and recognition, but have not been successful in employing methods of logic and reason-the traits we most closely associate with human intelligence. Perhaps AI needs to meet the grand challenges of biomedicine before it can be truly appreciated.     

一种文化鱼群算法及其在电机参数辨识中的应用

针对基本鱼群算法盲目搜索的问题,提出一种新的基于知识的带变异算子的人工鱼群算法。利用文化算法的框架,将鱼群算法嵌入到种群空间当中,构造适用于文化鱼群算法的新的影响函数。同时应用信念空间中的规范知识和情境知识通过影响函数指导人工鱼群算法中的进化步长和方向。通过高维多峰函数检验新算法的性能,最后将新算法应用于一台内置有执行器的鼠笼电机系统的参数辨识问题,得到了参数化的执行器-转子模型。仿真结果表明新算法与基本鱼群算法相比性能显著提高,并且能够有效地解决工程优化问题。     

人工智能与模糊控制在电力系统继电保护应用的研究现状及前景

对人工智能及模糊控制在电力系统继电保护中应用的国内外研究现状进行了综述,指出了需要进一步研究的方向和主要内容.     

人工智能与模糊控制在电力系统继电保护应用的研究现状及前景

对人工智能及模糊控制在电力系统继电保护中应用的国内外研究现状进行了综述 ,指出了需要进一步研究的方向和主要内容     

泛在电力物联网背景下人工智能在变电班组安全管理中的应用与探索

随着我国电力建设和电力市场竞争机制的引入,人工智能在电力系统中的应用前景将更加广阔。分析了适于人工智能应用的电力系统安全管理问题,概括介绍了其中几种应用广泛的人工智能技术,最后指出人工智能在电力系统中的应用发展趋势和应用前景。班组是企业的最小单元,加强班组安全管理是企业安全生产的重要保障。以变电班组为例,通过分析当前班组安全管理中的主要问题,探索人工智能在提升变电班组安全管理水平的应用,从而为泛在电力物联网建设提供安全生产的务实基础。     

单片机在液压泵特性测试中应用

文中给出由８０３１单片机构成的专用液压泵测试系统,它按原机械工业部液压泵测试Ｂ级标准设计,可对液压泵进行多种特性测试,测试过程由微机控制,避免了人工测试的繁复操作和运算,从而提高了测试数据的置信度。     

型材在成套开关设备柜架单元上的应用

从成套开关设备柜架单元的演变过程说明了用型材组装成套开关设备柜架的优点,分析了常用型材的主要机械性能,介绍了不同的型材在组成柜架时的特点。