Fault diagnosis for rotating machinery based on artificial immune algorithm and evidence theory

Hu, Qin; Zhang, Qinghua; Qin, Aisong; Shao, Longqiu

doi:10.1109/ccdc.2015.7162380

Cited by 7 publications

(4 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For this algorithm, it is advisable to use the average approach to determine the weight coefficients. Its advantages are ease of use, clarity of the distribution of importance characteristics, a large number of algorithms in which it is already used [20]. If necessary, the method can be changed.…”

Section: Methodsmentioning

confidence: 99%

Improving the Functioning Reliability of the Information Management System Elements, Using Built-in Diagnostic Tools

Kleiman

Freyman

2021

RIC

View full text Add to dashboard Cite

Context. In the modern world, information management systems have become widespread. This make it possible to automate the technological processes of enterprises of various sizes. Many information management systems include wireless and autonomous elements. Autonomy, in this case, means the ability of the system elements to function for a certain time without additional energy supply. In this regard, such a parameter of operational reliability as the battery life of a system element becomes one of the most important. One of the main tools for improving the reliability and fault tolerance of information management system elements – is the use of a modern diagnostic system. Objective. The aim of the work is to develop a method for increasing the reliability of the functioning of autonomous elements of information management systems. It includes the creation of a model of an information management system and an algorithm for reasonable redistribution of diagnostic functions, as well as a software implementation of the developed algorithm, which confirms its higher reliability indicators in comparison with other algorithms. Methods. The basic model was the Preparata-Metz-Chen model. On its basis, a new model of the system was built, including the structural and logical description of the elements and the determination of the way of their interaction. The elements were classified by the degree of criticality of the functions performed in the system. On the basis of the developed model and description of the elements, an algorithm was developed for the reasonable redistribution of the diagnostic load, which made it possible to reduce the average energy consumption of the elements and thereby improve the reliability indicators. A software implementation of the developed algorithm was created, which allows to numerically evaluate its advantages. The developed and existing algorithms were compared. Results. A model of information management system has been developed. In such a system, it is proposed to use an integrated test diagnostics system. This diagnostic system implements algorithms for redistributing the diagnostic load. To determine the importance of the characteristics taken into account, a linear criterion was chosen, as the most studied and fastest in application. A software model, that implements the developed algorithm and makes it possible to compare it with existing algorithms, has been developed. A study of the software model with various parameters was carried out and, based on the results of the software simulation, conclusions were drawn about the possibilities of improving the algorithm and directions for further scientific research were formulated. Conclusions. The usage of the developed algorithm makes it possible to increase such a characteristic of the reliability of the elements of the information and control system as the mean time of failure-free operation (mean time between failures) by increasing the operating time of autonomous elements without recharging. When carrying out software modeling of the developed and existing algorithms, the advantages of the first were confirmed, and theoretical possibilities for its improvement were formulated.

show abstract

Section: Methodsmentioning

confidence: 99%

Improving the Functioning Reliability of the Information Management System Elements, Using Built-in Diagnostic Tools

Kleiman

Freyman

2021

RIC

View full text Add to dashboard Cite

show abstract

“…There are eight types of antibody groups, including seven types of fault modes and a normal mode. The experiment process is that (1) the trained data are randomly generated, of which the total number is 8000, the number of the data belonged to each mode is 1000; testing data are randomly generated for the above seven modes and a new fault mode, respectively, of which the total number is 1000; (2) the aiNet + KNN + AT fault diagnosis algorithm is run eight times, when ε р is set as 0.1, 0.2, and 0.3, respectively; the results are shown in Table 1; (3) carry out improved fault diagnosis algorithm based on aiNet +KNN; the results are shown in Table 2; (4) carry out the fault diagnosis algorithm of aiNet model based on neighbourhood rough set, in cases that the threshold of IðM j 1 ; M j 2 Þ is set as 0.08, 0.15, 0.2 and 0.3, respectively, of which the results are shown in Table 3; (5) compare the results of step (3) with the one of step (4), the results of which are shown in Table 4.…”

Section: Methodsmentioning

confidence: 99%

“…Liu and Shang created a fault diagnosis frame model by simulating functions of T-cells and B-cells based on immunological principles [4]. Sun and Hu proposed five kinds of dimensionless immune detectors based on a negative selection algorithm [5]. Zhang and Liu proposed the bearing equipment rapid fusion diagnosis method based on an immune mechanism [6].…”

Section: Introductionmentioning

confidence: 99%

Improved fault diagnosis algorithm based on artificial immune network model and neighbourhood rough set theory

Zheng¹,

Li²,

Zhang

2021

Cognitive Comp and Systems

View full text Add to dashboard Cite

With the aim to identify new fault diagnosis and advanced robotic systems, this paper first proposes a fault diagnosis algorithm based on an artificial immune network model that can adjust the pruning threshold. Secondly, the algorithm is improved based on neighbourhood rough set theory, in which the relationships among the pruning threshold, misdiagnosis rate, and missed diagnosis rate in the shape space are discussed. In addition, an improved algorithm for adjusting the adaptively pruning threshold based solely on an observation index is described. The simulation experiments show that the algorithm can identify the new fault modes while keeping the misdiagnosis and missed diagnosis rates low.

show abstract

“…It has the characteristics of crossing, comprehensiveness and intelligence. The methods of fault identification can be divided into [7][8][9][10][11] comparative diagnosis, function diagnosis, simulation test diagnosis, fault tree diagnosis, fuzzy diagnosis, neural network diagnosis and expert system diagnosis. Each method has its own limitations.…”

Section: Introductionmentioning

confidence: 99%

Fault recognition method of smart grid data acquisition system based on FNN and sequential DS fusion

Qiao

Jiang

et al. 2021

Cognitive Comp and Systems

View full text Add to dashboard Cite

It is of significant practical importance to ensure the operational safety of the smart grid, which requires real-time fault diagnosis and identifying what causes it based on an enormous amount of data. This article further studies the intelligent fault-identification method based on the combination of multi-machine learning methods on the bases of researching on Fault Diagnosis of Smart Grid Data Acquisition System. Firstly, we should apply statistical analysis and feature extraction for fault data. Then, we can use fuzzy neural network (FNN) to calculate the probability of fault prediction of power distribution stations, manufacturers and operation businesses, and use the membership function to calculate the corresponding fault membership and uncertainty. Secondly, it makes use of Dempster/Shafer (DS) evidence sequential fusion method to realize fault membership fusion, and gives the corresponding decision criteria for failure causes. Thirdly, a fault-identification method of smart grid data-acquisition system is established based on FNN and DS Evidence Fusion. Finally, the experimental results based on the actual operation data of smart grid show that the new method has a very good application effect at fault cause identification. This is an open access article under the terms of the Creative Commons Attribution-NonCommercial-NoDerivs License, which permits use and distribution in any medium, provided the original work is properly cited, the use is non-commercial and no modifications or adaptations are made.

show abstract

Fault diagnosis for rotating machinery based on artificial immune algorithm and evidence theory

Cited by 7 publications

References 3 publications

Improving the Functioning Reliability of the Information Management System Elements, Using Built-in Diagnostic Tools

Improving the Functioning Reliability of the Information Management System Elements, Using Built-in Diagnostic Tools

Improved fault diagnosis algorithm based on artificial immune network model and neighbourhood rough set theory

Fault recognition method of smart grid data acquisition system based on FNN and sequential DS fusion

Contact Info

Product

Resources

About