Artificial Neural Network Method Based on Expert Knowledge and Its Application to Quantitative Identification of Potential Seismic Sources

In this paper,an approach is developed to optimize the quality of the training samples in the conventional Artificial Neural Network(ANN)by incorporating expert knowledge in the means of constructing expert-rule samples from rules in an expert system,and through training by using these samples,an ANN based on expert-knowledge is further developed.The method is introduced into the field of quantitative identification of potential seismic sources on the basis of the rules in an expert system.Then it is applied to the quantitative identification of the potential seismic sources in Beijing and its adjacent area.The result indicates that the expert rule based on ANN method can well incorporate and represent the expert knowledge in the rules in an expert system,and the quality of the samples and the efficiency of training and the accuracy of the result are optimized.     

Intelligence-Aided Seismic Zonation System IASHES

In this paper,the structure of the intelligence-aided seismic zonation system IASHES and its validation are briefly introduced.Emphasis is placed on the two rank scheme of potential seismic source areas; an expert subsystem for estimating the seismicity trends of rank A source areas; an expert subsystem for delineation of rank B source areas; an expert subsystem for judgment of upper limit of magnitude of rank B source areas,and an improved procedure for determination of weighting factors of rank B source areas,which is specially suitable to ES(Expert systems).     

Seismological Research on the Mining Tremors

A sophisticated seismological method has been introduced to the study of mining tremors by the Institute of Geophysics,SSB in cooperation with the Beijing Mining Bureau of NCC.Achievements have been obtained in the following areas:modification of the seismic monitoring system,compilation of a software package for analysis of mining tremors,research on the mechanical model for mining tremors,classification of mining tremors and development of an expert system of tremor prediction.     

Wing walls for enhancing the seismic performance of reinforced concrete frame structures

A building retrofitted with wing walls in the bottom story, which was damaged during the 2008 M8.0 Wenchuan earthquake in China, is introduced and a corresponding 1/4 scale wing wall-frame model was subjected to shake table motions to study the seismic behavior of this retrofitted structural system. The results show that wing walls can effectively protect columns from damage by moving areas that bear reciprocating tension and compression to the sections of the wing walls, thus achieving an extra measure of seismic fortification. A ‘strong column-weak beam' mechanism was realized, the flexural rigidity of the vertical member was strengthened, and a more uniform distribution of deformation among all the stories was measured. In addition, the joint between the wing walls and the beams suffered severe damage during the tests, due to an area of local stress concentration. A longer area of intensive stirrup is suggested in the end of the beams.     

Predictability performance enhancement for suspended sediment in rivers:Inspection of newly developed hybrid adaptive neuro-fuzzy system model

Reliable modeling of river sediments transport is important as it is a defining factor of the economic viability of dams, the durability of hydroelectric-equipment, river susceptibility to pollution, suitability for navigation, and potential for aesthetics and fish habitat. The capability of a new machine learning model, fuzzy c-means based neuro-fuzzy system calibrated using the hybrid particle swarm optimization-gravitational search algorithm（ANFIS-FCM-PSOGSA） in improving the estimation accur...     

The formation evaluation tool and its application in offshore China

The Formation Evaluation Tool （FET） introduced in the paper represents a new generation of formation evaluation systems developed and manufactured by China Oilfield Services Limited （COSL）, CNOOC, using a FET technology transfer from Crocker Research, Australia. The system has been applied successfully in the Bohai Sea and South China Sea. For instance, a multilayered oil and water system has been confirmed with the aid of accurate formation pressure tests, even in very thin beds and edge water reservoirs, overcoming the difficulty of determining this kind of oil-water and gas-water contacts. Moreover, the FET pumping and real-time fluid monitoring function allows acquiring a true sample of formation fluid unpolluted by drilling mud which plays an important role in determining the fluid properties of the target stratum and analyzing the fluid component. The principles and purpose of the Formation Evaluation Tool （FET） will be briefly introduced and successful examples of the application of the technology will be described in detail in this paper.     

H_∞ drift control of time-delayed seismic structures

In this paper,an optimal H∞ control algorithm was applied to the design of an active tendon system installed at the first story of a multi-story building to reduce its interstory drift due to earthquake excitations.To achieve optimal control performance and to guarantee the stability of the control system,an optimum strategy to select control parameters γ and α was developed.Analytical expressions of the upper and the lower bounds of γ and α were obtained for a single degree-of-freedom system with state fee...     

Remote sensing data classification using tolerant rough set and neural networks

Professor Pawlak introduced rough set theory, which is a method to represent, learn and induce in-complete data and uncertainty knowledge, in 1982[1]. Compared with traditional set theory, the strict axiom condition is broadened in rough set theory, which in-cluded vagueness concept and extended logic of set theory. It has been used successfully to deal with vagueness and uncertainty fields, for example machine learning, knowledge acquirement, decision analysis, pattern recognition and data mi…     

Sorption of Eu~(3+) onto nano-size silica-water interfaces

A large amount of nuclear wastes has been pro-duced due to nuclear weapon development and nuclear electricity generation. One possible resolution for the disposal of the nuclear wastes is to seal them in an underground repository, which requires detailed knowledge on the mobility, chemical behavior and immobilization of radionuclides in underground water. In addition, toxic heavy metals are extensively present in ground and underground water, how to immobilize and remedy these toxic heavy meta…     

Design and development of safety evaluation system of buildings on a seismic field based on the network platform

This paper describes a set of on-site earthquake safety evaluation systems for buildings, which were developed based on a network platform. The system embedded into the quantitative research results which were completed in accordance with the provisions from Post-earthquake Field Works, Part 2: Safety Assessment of Buildings, GB18208.2-2001, and was further developed into an easy-to-use software platform. The system is aimed at allowing engineering professionals, civil engineeing technicists or earthquake-affected victims on site to assess damaged buildings through a network after earthquakes. The authors studied the function structure, process design of the safety evaluation module, and hierarchical analysis algorithm module of the system in depth, and developed the general architecture design, development technology and database design of the system. Technologies such as hierarchical architecture design and Java EE were used in the system development, and My SQL5 was adopted in the database development. The result is a complete evaluation process of information collection, safety evaluation, and output of damage and safety degrees, as well as query and statistical analysis of identified buildings. The system can play a positive role in sharing expert post-earthquake experience and promoting safety evaluation of buildings on a seismic field.     

地震预报专家系统ESEP 3.0

近期研制成功的地震预报专家系统ESEP 3．0将模糊系统、神经网络与专家系统技术相结合，引入了驾驭式的推理机制，除具有第一代专家系统的符号推理与解释功能、以及第二代专家系统的学习功能外，还具有较强的人机交互能力，是一个全新的专家系统。ESEP 3．0由知识编辑、机器学习、驾驭式模糊推理机和解释等4个子系统组成，本文介绍了系统的组成和概况。     

地震预报专家系统ESEP 3.0中的知识表示方法

知识表示是专家系统建造中的一个关键环节，知识表示方法的好坏直接关系到系统的智能水平和解决问题的能力。在地震预报专家系统ESEP3．0中有多种知识表示方法，本文介绍了该系统的结构知识、地震学和前兆预报知识、机器学习知识、综合预报知识、确定异常证据可信度知识以及支持知识等多种知识表示方法，提出了确定异常证据可信度模型。这些知识表示方法可以很好地表示各类地震预报知识。     

Knowledge Representation Methods in Expert System for Earthquake Prediction ESEP 3.0

INTRODUCTIONKnowledgerepresentationandknowledgeacquisitionarekeyissuesinbuildinganexpertsystem .Theyarecloselyrelatedtothedomainproblem solvinglevelandcompetenceoftheexpertsystem .Intheknowledgeacquisitionprocess,thedomainexpertwillfirstofferandorganizepr…     

径向基函数(RBF)神经网络及其应用

介绍了径向基函数(RBF)神经网络的原理、 学习算法及其在地震预报专家系统ESEP 3.0中的应用。 实际应用结果表明, 该神经网络可以很好地克服BP神经网络学习过程的收敛过分依赖于初值和可能出现局部收敛的缺陷, 具有较快的运算速度、 较强的非线性映射能力和较好的预报效能。     

ESEP3.0专家系统在新疆年度地震形势预测中的应用检验

使用2000—2003年度新疆地震局震情研究报告中的资料建立异常证据文件,应用ESEP3．0专家系统进行了推理预测,将其中的1年以内的预测意见与这4年新疆“震情研究报告”的预测意见及实际发生的地震情况进行了对比,并按中国地震局制定的“地震预报评分办法”进行了评分,最后认为：ESEP3．0专家系统目前可以用于新疆的年度地震趋势和地震危险区预测。     

The expert system for earthquake prediction (I)—the overall design and main structure

The Expert System For Earthquake Prediction (ESEP) is summarized in this paper. ESEP embraces three subsystems: long-middle term prediction system, annual prediction system and middle-short term prediction system. Each of the subsystems is composed of seven modules: the controlling module, the data base module, the expert knowledge base module, the method base module, the fact preparation module, the reasoning and decision-making module and the plotting and displaying module. The reasoning model ESEP/R and the knowledge expression model ESEP/K are set up in the ESEP, and new evidence combinations, CON (confine), W (weigh), and SYN (synthesize), have been proposed. The distinctive features of the ESEP are: (1) systemized; (2) several experts’ knowledge can be synthesized; (3) a large amount of data and experts’ experience is embraced; (4) four reasoning models and the synthetic decision-making technic are adopted; (5) several software environments are used; (6) modularization; and (7) possessing the friendly user interfaces. The Chinese version of this paper appeared in the Chinese edition ofActa Seismologica Sinica,14, 1–8, 1992.     

基于模糊神经网络和符号的地震预报专家系统NGESEP

本文介绍了专家系统的发展、神经网络、模糊系统与专家系统相结合的优点以及新一代地震报专家系统的构成等。该系统除具有传统专家系统的特点外，还因使用模糊联想记忆神经网络模型而具有良好的学习功能。文中也对ＦＡＭ神经网络模型及其应用作了介绍。     

高层钢筋混凝土结构抗震选型的模糊专家系统

本文在专家调查和文献资料收集事理的基础上，建立了高层钢筋混凝土结构抗震选型的影响因素。因素关系及其模糊量化的知识表示方法；针对结构选型因素的层次性，提出了层因素逐级综合的模糊推理方法；在开发工具Ｃ－ＡＤＶＩＳＯＲ上具体建造了此类结构抗震选型的专家系统。     

Expert system for earthquake prediction（ESEP）（2）－Knowledge representation and evidence combination

Ｅｘｐｅｒｔｓｙｓｔｅｍｆｏｒｅａｒｔｈｑｕａｋｅｐｒｅｄｉｃｔｉｏｎ（ＥＳＥＰ）（２）－ＫｎｏｗｌｅｄｇｅｒｅｐｒｅｓｅｎｔａｔｉｏｎａｎｄｅｖｉｄｅｎｃｅｃｏｍｂｉｎａｔｉｏｎＨｏｎｇ－ＳｈｕｎＦＡＮ（范洪顺）ａｎｄＢｉ－ＱｕａｎＷＡＮＧ（王碧泉...     

震后趋势决策支持系统PTDSS

介绍了作者研制的“震后趋势决策支持系统PTDSS”的构成及预报效果,该系统使用模糊联想记忆FAM（Fuzzy Associative Menory)模型将神经网络与模糊系统结合起来,使之具有第2代专家系统的学习功能,系统知识库中除存有专家多年来总结的有关地震现场预报的知识外,还通过系统学习得到了一批十分有意义的,目前专家尚未总结的知识,震例检验的结果该系统有较好的预报效果。