高分悬赏翻译
1. Introduction
Information fusion, when applied to fault diagnosis and defect inspection, revolves around two main ques- tions [1–3]:
(1) How to acquire precise and reliable information cues about potential faults by incorporating com- plementary, and possibly redundant, multiple sensors.
(2) How to fuse decisions that are derived based on
multi-sensor data, which can be imprecise, and conflicting.
In the context of engine diagnosis, the first question is concerned with extracting fault-reveling engine features from multiple sensors, and describing them in a coherent representation scheme. Furthermore, since information obtained from the sensors is inherently incomplete, uncertain, and imprecise, it is imperative that a fusion mechanism be devised so as to minimize such impreci- sion and uncertainty. The effectiveness of such mecha- nism depends to a large extent on how redundant and complementary are the information cues obtained from the sensors. It is equally important to decide at what level of abstraction the fusion process is to take place, e.g., at the measurement level, at the feature level, and/or at the decision level. Generally speaking, acquir-
ing precise and certain engine quality descriptors can be achieved by fusing sensory data at the feature level. Refs. [4–6] present some examples of this type of data fusion.
The second question is concerned with the quality of decisions made with respect to engine diagnosis. It is
quite conceivable that information obtained from differ- ent sensors leads to different and possibly conflicting decisions. The challenge in this case is how to detect conflicts among the sensors and how to fuse their deci- sions into one coherent decision. Addressing this issue constitutes the main scope of the paper. In formulating the multi-sensor decision fusion, the paper assumes the
scenario of two sensor modalities used to monitor the
quality of single piston engines in real-time. One modal- ity measures acoustics emitted by the engine; the other modality measures engine vibration. The two modalities are typically employed in the final stage of an engine assembly line. The acoustic modality monitors timing related performance, while the vibration modality mon- itors performance indices related to valve clearance. Fusing the two modalities can lead to reliable decisions with respect to the presence and absence of faults.
There has been a substantial amount of research work conducted in the area of decision fusion, most of which is built around Bayes theory. The basic strategy is that if the prior probabilities and conditional probabilities are determined in advance, then the posteriori probabilities
信息融合, 当适用于缺点诊断和瑕疵检查, 旋转大约二个主要问题[ 1–3]:
(1) 怎么获取精确和可靠的信息暗示关于潜在的缺点由合并补全, 和可能重复, 多个传感器。
(2) 怎么熔化被获得的决定根据了
多传感器数据, 可能不精确, 并且精读flict 。
就引擎诊断状况, first 问题与提取faultreveling 的引擎特点从多个传感器, 和描述有关他们在一份连贯表示法计划。此外, 因为信息被获得从传感器固有地残缺不全, 不定, 和不精确, 它是必要的, 融合机制构想以便使这样的impreci- sion 和不确定性减到最小。eff这样的机制的ectiveness 依赖到大规模范围于怎样重复和补全信息暗示被获得从传感器。它相等地重要决定在什么抽象的水平融合过程将发生, 即, 在测量水平, 在特点水平, 并且/或者在决定水平。一般而论, 获取精确和某些引擎质量形容标志可能由熔化达到知觉数据在特点水平。Refs 。[ 4–6] 礼物这类型一些例子数据融合。
第二个问题与决定的质量有关被做出谈到引擎诊断。它是
相当可以想像信息被获得从二ff唔ent 传感器导致二fferent 和可能精读flicting 的决定。挑战在这种情况下是怎么查出精读flicts 在传感器之中和怎么熔化他们的deci- sions 入一个连贯决定。论及这个问题构成本文的主要范围。在公式化多传感器决定融合, 本文承担
二种传感器形式情节过去经常监测
唯一活塞引擎的质量在实时。一种形式测量声学由引擎散发; 另一形式测量引擎振动。二种形式典型地被使用在 fi引擎装配线的nal 阶段。音响形式监测时间相关的表现, 当振动形式监测表现索引与阀门清除有关。熔化二种形式可能导致可靠的决定谈到出现和缺乏缺点。
有是一个大数额研究工作被举办在决定融合区域, 多数被建立在贝斯理论附近。基本的战略是如果预先的可能性和有条件可能性事先被确定, 然后posteriori 可能性
信息融合技术，应用到故障诊断和检查的缺陷，围绕着两个主要问题作了[ 1-3 ] ：
（ 1 ）如何获取准确和可靠的信息，线索潜在故障纳入com的不平衡，也可能是多余的，多传感器。
（ 2 ）如何决定的导火索是推导
多传感器数据，可以不精确，而con克.6 。
在上下文发动机诊断， fi rst的问题，是有关提取故障陶醉发动机采用多种传感器，并描述他们在一个连贯代表性的计划。此外，由于所得资料是传感器本身不完整，不确定，不精确，当务之急是一个融合机制设计，以减少此类impreci分成和不确定性。电子ff裂缝等机器-机理很大程度上取决于如何冗余和互补的信息线索所得的传感器。这是同样重要，以决定在什么级别的抽象融合过程，是发生在什么地方，例如，在测量水平，在功能层面，和/或在决策水平。一般来说，梭状-
荷兰准确和某些发动机质量指标可达到熔断感官数据功能的水平。参。 [ 4-6 ]现在一些例子，这种类型的数据融合。
第二个问题是有关决定的质量方面作出诊断引擎。它是
相当可以想象所得资料邸ff尔耳鼻喉科传感器导致邸ff erent可能con克.6决定。挑战，在这种情况下，是如何探测con克传播中的传感器和如何融合，决定制作在外成一个连贯的决定。解决这一问题的构成主要文件的范围。在制定多传感器决策融合，本文假定
假设两种方式传感器用来监测
优质单活塞引擎在实时。一态性措施声学排放引擎;其他方式的措施，发动机的振动。两个模式通常受聘于fi宇阶段，发动机装配生产线。声学模式定时监测相关性能，而振动模式孟itors性能指标与气门间隙。融合两种模式，可导致可靠的决策方面存在并没有故障。
已有大量研究工作的地区进行决策融合，其中大多数是围绕贝叶斯理论。基本战略是，如果事先概率和条件概率都是事先确定的，那么验概率
专业英语翻译师 为您服务
