公开(公告)号：US06604029B2

公开(公告)日：2003-08-05

申请号：US09851289

申请日：2001-05-08

申请人： Dennis J. Cronin ,  Roger D. Foster

发明人： Dennis J. Cronin ,  Roger D. Foster

IPC分类号： G06F1518

CPC分类号： G05B13/027 ,  B64D43/02 ,  G01P13/025

摘要： An air data sensing probe such as a multi-function probe includes a barrel having multiple pressure sensing ports for sensing multiple pressures. Instrumentation coupled to the pressure sensing ports provides electrical signals indicative of the pressures. An inertial navigation system input of the probe receives electrical signals indicative of inertial navigation data for the aircraft. A neural network of the probe receives as inputs the electrical signals indicative of the multiple pressures and the electrical signals indicative of the inertial navigation data. The neural network is trained or configured to provide as an output, electrical signals indicative of an air data parameter.

摘要翻译： 诸如多功能探头的空气数据感测探头包括具有用于感测多个压力的多个压力感测端口的筒体。 耦合到压力感测端口的仪器提供指示压力的电信号。 探测器的惯性导航系统输入接收指示飞机的惯性导航数据的电信号。 探头的神经网络接收表示多个压力的电信号和指示惯性导航数据的电信号作为输入。 神经网络被训练或配置为提供指示空气数据参数的电信号作为输出。

公开(公告)号：US06601052B1

公开(公告)日：2003-07-29

申请号：US09598006

申请日：2000-06-19

申请人： Soo Young Lee ,  Ki Young Park

发明人： Soo Young Lee ,  Ki Young Park

IPC分类号： G06F1518

CPC分类号： G06K9/6256 ,  G06N3/0454

摘要： The present invention discloses an implementation of the selective attention mechanism occurring in the human brain using a conventional neural network, multi-layer perceptron and the error back-propagation method as a conventional learning method, and an application of the selective attention mechanism to perception of patterns such as voices or characters. In contrast to the conventional multi-layer perceptron and error back-propagation method in which the weighted value of the network is changed based on a given input signal, the selective attention algorithm of the present invention involves learning a present input pattern to minimize the error of the output layer with the weighted value set to a fixed value, so that the network can receive only a desired input signal to simulate the selective attention mechanism in the aspect of the biology. The present invention also used the selective attention algorithm to define the degree of attention to a plurality of candidate classes as a new criterion for perception, thus providing high perception performance relative to the conventional recognition system for a single candidate class.

摘要翻译： 本发明公开了使用常规神经网络，多层感知器和误差反向传播方法作为常规学习方法在人脑中发生的选择性注意机制的实现，以及选择性注意机制对感知的应用 模式，如声音或人物。 与其中基于给定输入信号改变网络的加权值的常规多层感知器和误差反向传播方法相反，本发明的选择性关注算法涉及学习当前输入模式以最小化误差 的输出层，其加权值设置为固定值，使得网络可以仅接收期望的输入信号来模拟生物学方面的选择性注意机制。 本发明还使用选择性关注算法来将多个候选类的注意度定义为感知的新标准，从而相对于单个候选类的常规识别系统提供高感知性能。

公开(公告)号：US06601050B1

公开(公告)日：2003-07-29

申请号：US09625572

申请日：2000-07-25

申请人： Wasyl Malyj

发明人： Wasyl Malyj

IPC分类号： G06F1518

CPC分类号： G06K9/6232 ,  G06F19/22 ,  G06T9/008 ,  Y10S707/99933

摘要： Electronic data is classified using adaptive focused replicator networks (AFRNs). AFRNs are sets of array elements, each array element being trainable in order to replicate a predetermined sub-group of data. Unknown data is inputted into each and every array element in an AFRN array and then replicated by each element array. A comparison is made for each array element to determine the accuracy of each replication. If only one array element successfully replicates the unknown data, then the unknown data is classified in accordance with the corresponding predetermined sub-group of data.

摘要翻译： 使用自适应聚焦复制器网络（AFRN）对电子数据进行分类。 AFRN是阵列元素的集合，每个阵列元素是可训练的，以便复制预定的数据组。 未知数据被输入到AFRN阵列中的每个数组元素中，然后由每个元素数组复制。 对每个数组元素进行比较，以确定每个复制的准确性。 如果只有一个数组元素成功地复制未知数据，则根据对应的预定的数据组分类未知数据。

公开(公告)号：US06598036B1

公开(公告)日：2003-07-22

申请号：US09542376

申请日：2000-04-04

申请人： Nanxin Wang ,  Beverly Joyce Becker ,  Gregory Allen Kaepp ,  Fang Liu ,  Zhengyu Lei ,  Yan Xue

发明人： Nanxin Wang ,  Beverly Joyce Becker ,  Gregory Allen Kaepp ,  Fang Liu ,  Zhengyu Lei ,  Yan Xue

IPC分类号： G06F1518

CPC分类号： G06F17/50 ,  G06F2217/04

摘要： A method is disclosed for determining the correctness of proposed values or data for engineering parameters. The method incorporates the use of a server side computer and a client side computer connected to each other via an electronic network. The method includes the steps of obtaining a knowledge base of data. The knowledge base is stored on the server side computer. Proposed values or data are generated at the client side computer using an applet. The proposed data is then transmitted over the network from the client side computer to the server side network. The proposed data is then compared against the knowledge base of data using a servlet designed to invoke and utilize computers other than the server side computer that may have rules or facts necessary to test the proposed data. The results are prepared and then transmitted from the server side computer to the client side computer. The client side computer does not require a proprietary application to be resident therein. It merely requires a web browser to access and utilize all of the information resident in the knowledge base stored in the server side computer.

摘要翻译： 公开了一种用于确定工程参数的建议值或数据的正确性的方法。 该方法包括使用通过电子网络彼此连接的服务器侧计算机和客户端计算机。 该方法包括获得数据知识库的步骤。 知识库存储在服务器端计算机上。 建议的值或数据在客户端计算机上使用小程序生成。 所提出的数据然后通过网络从客户端计算机传输到服务器侧网络。 然后将所提出的数据与数据的知识库进行比较，该servlet被设计成调用并利用服务器端计算机以外的可能具有测试建议数据所必需的规则或事实的计算机。 准备结果，然后从服务器端计算机发送到客户端计算机。 客户端计算机不需要驻留在其中的专有申请。 它只需要一个网络浏览器来访问和利用驻留在服务器端计算机中存储的知识库中的所有信息。

公开(公告)号：US06587846B1

公开(公告)日：2003-07-01

申请号：US09640896

申请日：2000-08-18

申请人： John E. LaMuth

发明人： John E. LaMuth

IPC分类号： G06F1518

CPC分类号： G06N3/004

摘要： A new model of motivational behavior, described as a ten-level metaperspectival hierarchy of ethical terms, serves as the foundation for an ethical simulation of artificial intelligence. This AI system is organized as a tandem, nested expert system, composed of a primary affective language analyzer, overseen by a master control unit-expert system (coordinating the motivational interchanges over real time). The systematic organization of the ethical hierarchy allows for extreme efficiency in the programming of the respective knowledge bases, employing the principles of inheritance for modeling the more abstract levels of the hierarchy: allowing a precise determination of the motivational level at issue during a given verbal interchange (defined as the passive-monitoring mode). An optional active monitoring mode permits the posing of simple yes-or-no questions, allowing for clarification of ambiguous language input. This basic motivational determination, in turn, serves as the basis for the synthesis of a response repertoire tailored to the computer, simulating a sense of motivation in a given verbal interaction (defined as the true AI simulation mode). The AI mode operates in concert with the passive monitoring mode, and in potential alternation with the active monitoring mode.

摘要翻译： 动机行为的新模式，被描述为伦理术语的十层次观察层次，是人工智能伦理模拟的基础。 这个AI系统是一个串联的嵌套专家系统，由主要情感语言分析器组成，由主控单元 - 专家系统监督（实时协调激励交互）。 道德层次的系统组织允许在相应的知识库的编程中具有极高的效率，采用继承原则来建模层次结构的更抽象层次：允许在给定的语言交换期间精确地确定所讨论的动机水平 （定义为被动监控模式）。 可选的主动监控模式允许构成简单的“是”或“否”问题，从而可以澄清歧义语言输入。 这种基本的动机决定反过来又是合成针对计算机的响应曲目的基础，在给定的语言交互（定义为真实的AI模拟模式）中模拟动机感。 AI模式与被动监控模式一致，并与主动监控模式进行潜在交替。

公开(公告)号：US06574613B1

公开(公告)日：2003-06-03

申请号：US09403878

申请日：2000-03-02

申请人： Jorge Moreno-Barragan

发明人： Jorge Moreno-Barragan

IPC分类号： G06F1518

CPC分类号： G01N33/0034 ,  G05B19/406 ,  Y10S706/905 ,  Y10S706/913

摘要： A system and a method for diagnosis of engine conditions are proposed. In particular, the system and the method are directed to an extraction of features from different information sources and to their processing. These features, together with a series connection of two neural networks, form the crux of the system and method, so that a dependable diagnosis of engine conditions, particularly an error recognition is possible. As a result thereof, maintenance corresponding to the current engine condition is enabled.

摘要翻译： 提出了一种用于诊断发动机条件的系统和方法。 特别地，系统和方法旨在从不同信息源及其处理中提取特征。 这些特征与两个神经网络的串联连接形成了系统和方法的关键，从而可以对引擎状况进行可靠的诊断，特别是错误识别。 结果，能够进行与当前发动机状态对应的维护。

公开(公告)号：US06567795B2

公开(公告)日：2003-05-20

申请号：US09726516

申请日：2000-12-01

申请人： Ali T. Alouani ,  Peter S. Chang

发明人： Ali T. Alouani ,  Peter S. Chang

IPC分类号： G06F1518

CPC分类号： G05B13/027 ,  G06N3/0436 ,  Y10S706/902 ,  Y10S706/907

摘要： Power industry boiler tube failures are a major cause of utility forced outages in the United States, with approximately 41,000 tube failures occurring every year at a cost of $5 billion a year. Accordingly, early tube leak detection and isolation is highly desirable. Early detection allows scheduling of a repair rather than suffering a forced outage, and significantly increases the chance of preventing damage to adjacent tubes. The instant detection scheme starts with identification of boiler tube leak process variables which are divided into universal sensitive variables, local leak sensitive variables, group leak sensitive variables, and subgroup leak sensitive variables, and which may be automatically be obtained using a data driven approach and a leak sensitivity function. One embodiment uses artificial neural networks (ANN) to learn the map between appropriate leak sensitive variables and the leak behavior. The second design philosophy integrates ANNs with approximate reasoning using fuzzy logic and fuzzy sets. In the second design, ANNs are used for learning, while approximate reasoning and inference engines are used for decision making. Advantages include use of already monitored process variables, no additional hardware and/or maintenance requirements, systematic processing does not require an expert system and/or a skilled operator, and the systems are portable and can be easily tailored for use on a variety of different boilers.

摘要翻译： 电力行业锅炉管故障是美国实行有效停电的主要原因，每年出现约41,000个管道故障，每年耗资50亿美元。 因此，早期的管泄漏检测和隔离是非常需要的。 早期检测允许安排修理而不是遭受强制中断，并显着增加防止相邻管损坏的机会。 即时检测方案开始于锅炉管泄漏过程变量的识别，分为通用敏感变量，局部泄漏敏感变量，组泄漏敏感变量和子组泄漏敏感变量，并且可以使用数据驱动方法自动获得， 泄漏灵敏度功能。 一个实施例使用人工神经网络（ANN）来学习适当的泄漏敏感变量与泄漏行为之间的映射。 第二种设计理念将ANN与使用模糊逻辑和模糊集的近似推理相结合。 在第二种设计中，ANN用于学习，而近似推理和推理引擎则用于决策。 优点包括使用已经监控的过程变量，无需额外的硬件和/或维护要求，系统处理不需要专家系统和/或技术熟练的操作员，并且系统是便携式的，并且可以容易地定制以用于各种不同的 锅炉

公开(公告)号：US06560584B1

公开(公告)日：2003-05-06

申请号：US09452825

申请日：1999-12-01

申请人： Nader Afshar ,  Gopal Chaudhuri ,  Kuolung Hu

发明人： Nader Afshar ,  Gopal Chaudhuri ,  Kuolung Hu

IPC分类号： G06F1518

CPC分类号： H04L41/142 ,  H04L41/147

摘要： A method and apparatus for prediction of system reliability is disclosed. The method comprises the steps of: (a) identifying the minimal path set of components which must function for the system to function; (b) constructing a minimal path set matrix by representing the minimal path sets as binary numbers in the matrix; (c) constructing a design matrix from OR operations on sets of columns of the minimal path set matrix whose results are appended to the original minimal path set matrix; (d) constructing a vector of ones having signs related to the position in the vector; and (e) calculating the system reliability from the design matrix, vector of ones and the reliabilities of each of the components of the system. The method of the present invention also determines the structure function of the system from the design matrix, vector of ones, and the states of the components of the system. The apparatus for performing the method of the present invention comprises a programmable processor. The present invention is capable of accurately predicting system reliability of complex systems composed of many components and is easy to implement and to use.

摘要翻译： 公开了一种用于预测系统可靠性的方法和装置。 该方法包括以下步骤：（a）识别必须对系统起作用的部件的最小路径集合; （b）通过将最小路径集合表示为矩阵中的二进制数来构造最小路径集矩阵; （c）从最小路径集矩阵的列集合的OR运算构建设计矩阵，其结果附加到原始最小路径集矩阵; （d）构建具有与向量中的位置有关的符号的向量; 和（e）从设计矩阵，向量和系统的每个组件的可靠性计算系统可靠性。 本发明的方法还根据设计矩阵，向量，系统的各个部件的状态来确定系统的结构功能。 用于执行本发明的方法的装置包括可编程处理器。 本发明能够准确地预测由许多部件组成的复杂系统的系统可靠性，并且易于实现和使用。

公开(公告)号：US06542880B2

公开(公告)日：2003-04-01

申请号：US09218945

申请日：1998-12-22

申请人： Eren Tolga Rosenfeld ,  Ekpedeme Mfon Bassey ,  Beth Elyse Zadik ,  Martha Torrey O'Connor ,  Alexander Han Leung Poon ,  Eric Jeffrey Lannert ,  Tracey Andrea Solomon ,  Jonathan Christian Conant ,  Alexander Zorba ,  Carl Michael Puccio ,  Timothy John Gobran ,  James Andrew Gilchrist ,  Mark Stewart Nichols ,  Brandon Denning Fleisher ,  Craig William Friedman ,  Adebisi Detoro Lipede ,  Matthew Allen Bailey

发明人： Eren Tolga Rosenfeld ,  Ekpedeme Mfon Bassey ,  Beth Elyse Zadik ,  Martha Torrey O'Connor ,  Alexander Han Leung Poon ,  Eric Jeffrey Lannert ,  Tracey Andrea Solomon ,  Jonathan Christian Conant ,  Alexander Zorba ,  Carl Michael Puccio ,  Timothy John Gobran ,  James Andrew Gilchrist ,  Mark Stewart Nichols ,  Brandon Denning Fleisher ,  Craig William Friedman ,  Adebisi Detoro Lipede ,  Matthew Allen Bailey

IPC分类号： G06F1518

CPC分类号： G09B7/04 ,  Y10S706/927

摘要： A system is disclosed that provides a goal based learning system utilizing a rule based expert training system to provide a cognitive educational experience. The system provides the user with a simulated environment that presents a business opportunity to understand and solve optimally. Mistakes are noted and remedial educational material presented dynamically to build the necessary skills that a user requires for success in the business endeavor. The system utilizes an artificial intelligence engine driving individualized and dynamic feedback with synchronized video and graphics used to simulate real-world environment and interactions. Multiple “correct” answers are integrated into the learning system to allow individualized learning experiences in which navigation through the system is at a pace controlled by the learner. A robust business model provides support for realistic activities and allows a user to experience real world consequences for their actions and decisions and entails realtime decision-making and synthesis of the educational material. The system is architected around a table of components to manage and control the system.

摘要翻译： 公开了一种系统，其提供基于目标的学习系统，其利用基于规则的专家训练系统来提供认知教育经验。 该系统为用户提供了一个模拟环境，为您提供了理解和最佳解决方案的商机。 注意到错误，并动态呈现补救性教材，以建立用户在业务活动中获得成功所需的必要技能。 该系统利用人造智能引擎，驱动具有同步视频和图形的个性化和动态反馈，用于模拟现实环境和交互。 将多个“正确”答案整合到学习系统中，以允许个人化的学习体验，其中通过系统的导航处于学习者控制的步伐。 强大的商业模式提供对现实活动的支持，并允许用户体验现实世界对他们的行为和决策的后果，并需要实时决策和综合教材。 系统围绕一个组件表进行架构，以管理和控制系统。

公开(公告)号：US06535866B1

公开(公告)日：2003-03-18

申请号：US09468068

申请日：1999-12-20

申请人： Akihito Iwadate

发明人： Akihito Iwadate

IPC分类号： G06F1518

CPC分类号： G06Q10/107 ,  G06Q10/087 ,  Y10S707/99933

摘要： A method and device for automatically informing an end user of a message resulting from regular analysis of data on a database. A storage 3 stores result transmission requirements 4 which is prepared for determining whether the message resulting from regular analysis of the data by a database system 1 should be transmitted to an end user 2 or not. A result fetch section 5 fetches analysis results from the database system 1. A mail host 6 transmits an e-mail addressed to the end user 2 when a fetched analysis result satisfies the result transmission requirements 4 in order to inform the end user 2 of the requirement satisfaction. The transmitted e-mail is stored in a mail server 7 via a network 8. The end user 2 obtains the e-mails addressed to him/her from the mail server 7 by operating a mail client 9. The end user 2 notices that the analysis result which satisfies the result transmission requirements 4 has been issued by the database system 1. The notice is helpful for solving problems regarding to business affairs to which the end user 2 relates.

摘要翻译： 一种用于通过对数据库上的数据的定期分析而自动通知终端用户的消息的方法和装置。 存储器3存储结果传输要求4，其准备用于确定由数据库系统1对数据的定期分析产生的消息是否应被发送到终端用户2。 结果提取部分5从数据库系统1获取分析结果。当获取的分析结果满足结果传输要求4时，邮件主机6发送寻址到最终用户2的电子邮件，以便向终端用户2通知 要求满意。 所发送的电子邮件通过网络8存储在邮件服务器7中。最终用户2通过操作邮件客户端9从邮件服务器7获得他/她的电子邮件。最终用户2注意到 满足结果传输要求4的分析结果已由数据库系统1发布。该通知有助于解决与终端用户2所关联的商业事务有关的问题。