Using the algebraic sum method in medical expert systems

In the development of a medical expert system, the choice of algorithms is an important consideration. According to 1979 statistics, some 60% of medical expert systems were based on the Bayes method, 30% were based on a linear discriminant function, matching handle and criterion tree, and 10% were based on other algorithms. Overall diagnostic accuracy rates were generally about 90%. Although the Bayes method has been used very widely, it has some limitations. Its two assumptions are difficult to satisfy in computer-assisted diagnostic systems, and it does not do well in solving the contradiction between the low frequency of a disease manifestation and the high specificity of the manifestation. A weighted summation method can better solve this problem, since the diagnostic value can be adjusted according to the real importance of each item of diagnostic information. The weighted summation method has been widely used in the development of many medical expert systems, such as the earliest expert system of traditional Chinese medicine: “The Computer Program for the Diagnosis and Treatment of Liver Disease Based on the Principle of Dialectical Treatment”. It is concluded that the algebraic sum method is an efficient, simple, and convenient mathematical model for the development of medical expert systems     

Consistent knowledge discovery in medical diagnosis

Discusses eliminating contradictions among rules in computer-aided systems, experts rules, and databases. The study has demonstrated how consistent data mining in medical diagnosis can create a set of logical diagnostic rules for computer-aided diagnostic systems. Consistency avoids contradiction among rules generated using data mining software, rules used by an experienced radiologist, and a database of pathologically confirmed cases. The authors identified major problems: to find contradiction between diagnostic rules and to eliminate contradiction. They applied two complimentary intelligent technologies for extraction of rules and recognition of their contradictions. The first technique is based on discovering statistically significant logical diagnostic rules. The second technique is based on the restoration of a monotone Boolean function to generate a minimal dynamic sequence of questions to a medical expert. The results of this mutual verification of expert and data-driven rules demonstrate feasibility of the approach for designing consistent computer-aided diagnostic systems     

粗糙集理论在电力系统中的应用

粗糙集理论是一种较新的软计算方法,可以有效地分析和处理不完备信息。近几年来,该理论日益受到国际学术界的重视,已在模式识别、预测建模、医疗诊断、决策分析等许多领域得到成功的应用。粗糙集理论在电力系统中的研究起步较晚,目前尚鲜见实际应用的报道。为了进一步推动粗糙集理论在电力系统广泛和深入地应用,文中综述了近年来粗糙集理论在电力系统设备故障诊断、配电网故障诊断、暂态稳定评估、电压无功控制、数据挖掘等方面应用研究的主要成果与方法。探讨了粗糙集理论在电力市场数据挖掘中的巨大潜力,以及与专家系统、人工神经网络、模糊理论和多代理系统等其他人工智能技术的相互结合问题,并提出了若干需要进一步研究的问题。     

A knowledge-based electrical diagnostic system for mining machinemaintenance

To investigate the applicability of expert systems in the area of control circuit diagnostics, the US Bureau of Mines has developed a knowledge-based system to diagnose component malfunctions in the electrical control circuit of a continuous mining machine. The system leads the user through the appropriate procedures required to quickly identify the faulty control-circuit component. Graphical displays are incorporated in the system to assist the user in locating the various components and test points. Once the faulty component has been isolated, the system is capable of accessing a database which can provide mine personnel with information concerning specific component part numbers and the availability and location of spare parts. The expert system development tool used to build the system, the structure and development of the knowledge base, and the software used to implement and graphical display and equipment database are discussed     

变压器故障诊断中信息融合技术的应用

电力变压器的可靠性直接影响供电的稳定,为此结合电力变压器故障诊断的具体情况,从信息融合的角度提出了基于信号类型及不同特征向量组合的集成诊断模型。该模型利用基于故障机理内在因素的专家系统,采用匹配知识规则,通过模糊推理,得特征向量与变压器故障信息间的关联性质,完成故障诊断,且诊断完成后,利用数据挖掘技术将诊断过程中的特征量、推理过程、结果以编码形式存入专家系统规则库。该模型将油中溶解气体、电气参数等特征量结合作为故障判据,评估变压器状态,并利用评估结果丰富专家系统的规则库。在讨论了多传感器信息融合技术用于变压器在线故障诊断时的具体实现方法后通过实例进行分析说明:利用来自传感器的各种故障信息进行融合,作为变压器故障诊断的判据,提高了诊断的可靠性和准确性,这将对提高电网安全性能及电气设备的诊断自动化与智能化水平起到推动作用。     

矿用高压开关柜的弧光监测与保护系统

煤矿工业现场特殊的生产环境对电气设备的安全运行提出了更高的要求,尤其是以故障电弧为主的电气故障蕴含着巨大的安全隐患。传统的故障电弧监测和保护手段一般基于电流、电压、弧光等单一信号的提取和判断,虽然组合式监测方法已被提出,但往往实现复杂,成本较高。提出电流和弧光双判据的监测方法,通过光敏三极管阵列的传感措施,结合专家系统的评估方法,可以有效判断并定位高压开关柜中的故障电弧,及时切除故障,进而提高设备的工作寿命和安全可靠性,为煤矿电力系统的安全稳定运行提供保障。     

基于优先级诊断树的旋转机械故障诊断专家系统

针对旋转机械故障知识的膨胀导致的专家系统诊断效率低下以及知识库难以维护的问题,提出了一种新的、基于优先级诊断树的专家系统框架。将诊断设备分解建立诊断树并划分领域知识库,再利用模糊群组多属性决策方法排序诊断树导出元知识,并在弹性匹配模式基础上改进了规则的匹配方式。诊断时,推理机从优先级最高的节点开始,按照元知识进行规则的搜索、匹配,以此建立某设备动力与传动装置的故障诊断系统。研究表明,与传统专家系统相比,新系统具有更高的效率、并且诊断结论更可靠、可维护性也更好。     

Application of radio-frequency identification systems to collisionavoidance in metal/nonmetal mines

Collisions between haulage equipment and pedestrian workers or other vehicles claim an average of five lives each year in surface and underground metal/nonmetal mining operations. Many more workers are severely injured, Although technologies exist that could prevent these collisions, (radar, closed-circuit TV, and backup alarms), they do have limitations and are not being used widely. New developments in radio-frequency identification (RFID) systems show promise for reducing the number of collisions. This paper, originally presented in 1998, describes tests conducted on off-the-shelf RFID systems and the subsequent development of a custom RFID system that could be used for both surface and underground mining equipment     

基于大型集控站监控系统下的二次设备状态检修方案

就二次设备状态检修必要性和可行性进行了论证,提出了二次设备状态检修可以利用二次设备自身的智能诊断功能、网络监控和通讯功能,依靠集控站监控系统的数据采集和智能处理功能,实现对二次设备运行状态的在线监控,同时依靠专家系统和专业技术人员的经验完成对二次设备运行状态的健康评估,从而实现二次设备状态检修。本方案经过在汉中供电局的实施,使二次设备异常的发现率和故障的处理速度大幅提高,表明本方案在不需用大量投资的情况下可以实现二次设备状态检修的基本要求。     

Applying Bayes' theorem in medical expert systems

The authors think that the main problem with the application of Bayes' theorem in medical expert systems is that the formula itself cannot resolve the contradiction between frequency of disease manifestation and its specificity, especially for those manifestations that have a very low frequency but a high specificity. The authors have found in practice that the weighted summation method in its various application forms can handle these situations well. The diagnostic weight value of any manifestation can be adjusted by clinical experts, based on its actual importance for the diagnosis, as judged by theory and practical experiences. This method will be discussed more in detail in the authors' other paper. When adopting Bayes' method as the algorithm of a medical expert system, one must ensure that the theorem's two assumptions are satisfied as best as possible. There should be a sufficient quantity of cases of the diseases in the database, and the actual information should be as accurate as possible. When a system based on Bayes' formula is used in epidemiologically different populations, the a priori probability of the corresponding disease should be corrected. Especially, those manifestations with high specificity should be chosen as diagnostic indicators. In summary, applying Bayes' method can provide quite satisfactory results in many applications     

Coupling of Mine Grounds to Surface Grounds

The mining industry in the United States is unique in utilizing a separate mine ``safety ground' for the working area of the mine which is kept isolated from other ground systems used to ground lightning arrestors, static lines, or equipment frames in surface substations. It is kept isolated from the other grounds to prevent potentials which appear on these grounds as the result of lightning activity or faults outside the mine from energizing the frames of mining equipment, thereby posing a shock hazard to workers using that equipment. Although this separation of grounds is desirable and is required by MSHA regulations for many types of mining operations, the goal of preventing the coupling of potentials from one ground to the other can be difficult or almost impossible to achieve in some rather typical mine environments. Several ways in which coupling has been observed to occur are documented, and the extent of such coupling is estimated. The difficulties inherent in reducing this coupling are reviewed, along with some specific new hazards which may arise in so doing. Finally, estimates are presented which indicate that the absolute potentials of large structures are not as hazardous as similar potentials on much smaller structures.     

分布式网络化状态监测与故障诊断系统

该文提出了一个基于以专家系统为主要诊断方法的,由三级网络结构组成的分布式网络化状态监测和故障诊断系统的网络框架,适用于行业内重大设备的系统化状态监测和故障诊断,将为设备从定期维修向预测检修模式转变提供重要的技术保证。图４参４     

机载电子设备故障诊断专家系统的设计与实现

针对航空机载电子设备故障知识日益膨胀导致的故障诊断系统效率低下、难以快速有效地进行电子装备维护的问题,提出了一种新的、基于专家系统的机载电子设备故障诊断系统。分析了专家系统的原理和结构,研究了一般产生式规则与模糊产生式规则相结合的知识表示方法及精确推理与模糊推理相结合、基于规则推理、案例推理、模型推理及混合推理的推理机制。以Delphi7．0和Oracle9i为开发环境,开发了该专家系统。系统能快速分析故障现象,列出可能的故障原因,输出故障报告,提供故障处理指导。研究表明,新系统具有更高的效率、并且诊断结论也更可靠、可维护性也更好,在实际的航空机务维护工作中取得了良好的效果。     

Computer-based monitoring and remote control of a new highwallmining system

A new highwall mining system (HMS) for coal extraction in unreclaimed and active contour strip mines has been developed. The system is comprised of a computer-based remotely controlled thin-seam continuous miner, a multiple-unit continuous haulage system, and other support equipment located on the highwall bench. The mining process is controlled remotely by a single operator from a protected, ergonomically designed workstation. The HMS offers safe economical mining of unreclaimed coal resources. It has the potential to be competitive with other highwall coal extraction techniques, with a productivity goal of 22 ton/man-hour. Surface tests of the miner and haulage systems were completed at the US Bureau of Mines test facility. Specific results from these tests are included. Field protection trials of the HMS are being conducted     

Fundamentals in computer aided PD processing, PD patternrecognition and automated diagnosis in GIS

The partial discharge (PD) measurement is a sensitive method for testing and monitoring the insulation condition of HV apparatus. Digital PD measurements have become state of the art. Computer-based PD diagnostic systems nowadays can be used to increase the reliability of modern gas-insulated system (GIS). Also on-line monitoring of HV equipment is becoming increasingly important to enable prevention of a sudden breakdown of PD affected components. On-line monitoring must be done on-site, but an important problem of on-site PD measurement is the superposition of PD data and interference. Furthermore, reliable recognition of the type or nature of the insulation defect is necessary for any risk assessment. Traditionally, this is achieved with reference to expert knowledge. An alternative approach is presented in this paper, which treats the fundamentals of automated computer-based PD diagnosis, taking into account that successful noise suppression is essential for a successful on-site diagnosis     

Analysis Techniques in AC/DC Power Systems

Many present-day industrial power systems have combined ac/dc power distribution systems. A typical example is a coal mine power system, where ac is used for running the mining equipment and dc is used for track haulage, etc. Also, the topology of the dc network is constantly changing due to the movement of locomotives along the track. Methods are described that can be used to carry out load-flow and short-circuit analyses of such a system.     

The use of the CIGRE data format for PD diagnosis applications

A standardized format for partial discharge (PD) data recorded in gas-insulated switchgear (GIS) was proposed recently by a CIGRE Task Force (15.03.08). Being an open structure, the PD CIGRE data format can be used for all HV apparatus and equipment. Such a format is necessary to process PD measurements from any PD acquisition equipment by different PD analysis programs or expert systems. Furthermore, this format can decouple PD acquisition and PD evaluation. For easy handling, the PD data in the standardized format are encoded as plain ASCII text which can be processed by a text editor or a commercial spreadsheet program. In addition to an Electra publication where solely the structure of the data format is defined, this approach investigates the use of this format in practical PD applications. It discusses the options of the format and compares the diagnostic capability of different evaluation tools and gives examples. This discussion thus can assist a user to choose between the different graphs which are contemplated in the format     

神经网络在故障诊断中的应用

从神经网络充当广义模式匹配器进行故障诊断以及神经网络与基于模型故障诊断的融和两方面介绍了神经网络在故障诊断中的研究及应用现状。此外,还介绍了神经网络与模糊技术相结合以及神经网络与专家系统相结合而成的智能故障诊断系统。最后,探讨了神经网络故障诊断的新近发展趋势。     

Application of diagnostic systems for monitoring the state of heat-transfer and mechanical equipment at nuclear power stations

Experience gained from the use of monitoring and diagnostic systems for managing the lifetime characteristics of equipment at nuclear power stations is generalized. A need for development and putting into use at nuclear power stations of a comprehensive system for diagnosing heat-transfer and mechanical equipment is shown. It is also shown that the list of parameters tracked by monitoring and diagnostic systems needs to be broadened.