تشخیص خطا با استفاده از نظریه مجموعه دقیق
|کد مقاله||سال انتشار||مقاله انگلیسی||ترجمه فارسی||تعداد کلمات|
|29477||2000||12 صفحه PDF||سفارش دهید||محاسبه نشده|
Publisher : Elsevier - Science Direct (الزویر - ساینس دایرکت)
Journal : Computers in Industry, Volume 43, Issue 1, 1 August 2000, Pages 61–72
The fault diagnosis on diesel engine is a difficult problem due to the complex structure of the engine and the presence of multi-excite sources. Usually, one method of fault diagnosis can only inspect one corresponding fault category. In this paper, a new method, Rough Sets Theory, is used to diagnose the valve fault for a multi-cylinder diesel engine. Through the analysis of the final reducts generated using Rough Sets Theory, it is shown that this new method is effective for valve fault diagnosis. Rough Sets analysis requires discretizing the fault condition attributes. However, in practice, some of the limits of these attributes are unknown. A new discretization method has been created and the method is found to be suitable for discretizing the attributes without a priori knowledge.
Fault diagnosis on machinery has been well researched . There are many effective methods that are used to diagnose accurately and quickly a certain category of faults . For instance, large-scale centrifugal compressor can be diagnosed by holospectrum technique . However, up to now, it is difficult to diagnose more than one category of faults. This is especially so in diagnosing the dynamic characteristics of reciprocating machinery, such as reciprocating compressor and diesel engine. This is due to the complex structure of the reciprocating machinery. Although many methods can be used to determine specific fault category, such as broken valve and cracked crankshaft , the results obtained from such fault specific method are not easy to interpret. There is a need to have a method that can diagnose more than one category of faults in a generic manner. In this paper, a method based on Rough Sets Theory is proposed and implemented. Z. Pawlak (Poland) first proposed Rough Sets Theory in 1982. This theory has been developed and used in many domains, such as medical diagnosis , stock market forecast , fault diagnosis in engineering domain , decision making for bank manager  and some other uses . The advantage of Rough Sets Theory is that it needs neither additional information about the data nor is it necessary to correct the inconsistencies manifested in data. Instead, rules generated are categorized into certain rules or possible rules. In this paper, the Rough Sets Theory  is used to analyze the decision table composed of attributes extracted from the vibration signals, which are collected from a 4135 diesel engine. The remainder of this paper is organized as follows. The characteristics of vibration signal of diesel engine will be analyzed in Section 2, then Rough Sets Theory is introduced in Section 3. The attributes field is established in Section 4, which is used to compose the decision table. A new discretization method, more suitable to discretize continuous attributes without a priori knowledge, is proposed in Section 5. The diagnosis results using Rough Sets Theory are discussed in Section 6 and at the end of this paper, conclusions based on the aforementioned analysis are given.
نتیجه گیری انگلیسی
In this paper, valve fault diagnosis using Rough Sets Theory is presented. Summarizing the formulation; first, the decision table is established. In this process, the attributes field has to be specified according to collected signals. Next, using a discretization method, either with expert experience or not, transform the continuous valued attributes to discrete ones. Finally, the Rough Sets Theory is used to get the final reducts and to extract the rules. These rules are used to distinguish the fault type or to inspect the dynamic characteristic of the machinery. Through the implementation and results, the following observations and conclusions are made: • The Rough Sets Theory used to diagnose the valve fault of a 4135 diesel engine has been found to be effective. • The lack of a priori knowledge in practice for fault diagnosis is very prevalent and therefore the new discretization method proposed in this paper will be very useful.