No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Fault Causation Analysis of Oil-Delivery Pump Based on Fuzzy Petri Net
Abstract
In oil-delivery pumps, impeller failure is a common cause leading to excessive vibration. This paper is aimed to analyze the fault causation of impeller failure in oil-delivery pumps by using fuzzy Petri net (FPN) theory. The longest path algorithm based on the forward reasoning was put forward and introduced into fuzzy Petri net. First, on the basis of various factors causing impeller failure, an FPN model of impeller failure in oil-delivery pumps was constructed. Then, by using the proposed algorithm, fault causation analysis of impeller failure was completed to calculate the credibility of impeller failure. Finally, the corresponding preventive measure was presented. The results indicate the key causing factor of impeller failure is mechanical impurities, and the credibility of impeller failure is 0.7342, which is consistent with the actual situation. The research finding demonstrates the flexibility and effectiveness of the FPN in fault causation analysis.
ResearchGate has not been able to resolve any citations for this publication.
In this paper, a fuzzy Petri net (FPN) approach to modeling fuzzy rule-based reasoning is proposed to determining confidence values for bases called in DNA sequencing. The proposed approach is to bring DNA bases-called within the framework of a powerful modeling tool FPN. The three input features in our fuzzy model-the height, the peakness, and the spacing of the first most likely candidate (the base called) and the peakness and height for the second likely candidate can be formulated as uncertain fuzzy tokens to determines the confidence values. The FPN components and functions are mapped from the different type of fuzzy operators of If-parts and Then-parts in fuzzy rules. The validation was achieved by comparing the results obtained with the FPN model and fuzzy logic using the MATLAB Toolbox; both methods have the same reasoning outcomes. Our experimental results suggest that the proposed models, can achieve the confidence values that matches, of available software.
An alterative approach to the backward reasoning is presented. In classical reasoning, both users and developers of many expert systems are dedicated to the forward reasoning. However, in many newly arising expert systems such as various diagnosis systems, the backward reasoning is of special interest and often preferable. In this paper, the fuzzy Petri nets are used to analytically represent the knowledge of fault diagnosis in manufacturing systems and an iterative algorithm based on max-algebra is used to deduce the consequence–antecedent relationship between their manifestation and antecedent. Finally, the legitimacy and efficiency of the proposed approach are proved and validated by an illustrative example.
Feed-forward neural networks used for pattern classification generally have one input layer, one output layer and several hidden layers. The hidden layers in these networks add extra non-linearity for realization of precise functional mapping between the input and the output layers, but semantic relations of the hidden layers with their predecessor and successor layers cannot be justified. This paper presents a novel scheme for supervised learning on a fuzzy Petri net that provides semantic justification of the hidden layers, and is capable of approximate reasoning and learning from noisy training instances. An algorithm for training a feed-forward fuzzy Petri net and an analysis of its convergence have been presented in the paper. The paper also examines the scope of the learning algorithm in object recognition from 2D geometric views.
One critical problem in the operations of chemical processes is the occurrence of abnormal events. Therefore, an effective process monitoring methodology that can help detect, diagnose and predict abnormal events becomes potentially very useful. For the purpose of knowledge representation of chemical abnormality, a specified type of timed fuzzy Petri net (tFPN) approach is explicitly introduced in this paper. The dominant feature of tFPN metrics can be recognized from the fact that a timing factor is assigned to each transition, as well as a degree of reliability is associated with each place, which allows accurately representing the dynamic nature of fuzzy knowledge pertaining to abnormal events. Following a procedure towards abnormal event monitoring, two efficient algorithms in terms of abnormality prognostication and diagnosis are exploited by means of reachability analysis of tFPN. The benefits of derived techniques and solutions are illustrated through a case study consisting in a polypropylene reactor.