Xuyun Fu

Xuyun Fu
Harbin Institute of Technology at Weihai · Department of Mechanical Engineering

PhD

About

52
Publications
9,558
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
553
Citations
Citations since 2016
33 Research Items
521 Citations
2016201720182019202020212022050100150200250
2016201720182019202020212022050100150200250
2016201720182019202020212022050100150200250
2016201720182019202020212022050100150200250
Introduction
Xuyun Fu currently works at the Department of Mechanical Engineering, Harbin Institute of Technology at Weihai. Xuyun does research in Intelligent Operation and Maintenance, Prognostics and Health Management.
Additional affiliations
January 2011 - present
Harbin Institute of Technology at Weihai
Position
  • Professor (Associate)

Publications

Publications (52)
Article
The particle swarm optimization (PSO) algorithm has received much attention from engineering and scientific fields since it was proposed. Nevertheless, when solving complex combinatorial optimization tasks such as the proposed shop visit balancing problem for repairable equipment (SVBPRE), the canonical PSO is still prone to fall into the local opt...
Article
Full-text available
For highly reliable gas turbines that rarely suffer faults, the overwhelming majority of historical data are collected under healthy state, while only a very small number of them are fault samples. However, traditional deep neural networks pay most attention to normal samples, resulting in a high missing diagnostic rate for fault samples. To addres...
Article
Full-text available
Anomaly detection of gas turbines is a typical binary classification problem under small sample size. In essence, the goal of classification is to discover the mapping that can map samples in different categories to disjoint codomains. The neural network has strong nonlinear mapping ability thus it has great potentialities in classification tasks....
Article
The healthy operations of mechanical systems are crucially important for ensuring human safety and economic benefits, so that there is a high demand on the automatic fault diagnosis techniques. However, the number of available faulty samples of mechanical systems is often far less than healthy samples, and thereby the traditional data-driven method...
Article
Tether satellite system (TSS) comprises two satellites connected by a flexible tether and has wide applications, such as orbital transferring, deep space exploration, and so on. In this paper, a variable-length element, based on the absolute nodal coordinate formulation (ANCF) in the framework of arbitrary Lagrangian-Eulerian (ALE) description, is...
Article
In general, deep learning based fault diagnosis methods need a large number of training samples, which are often not available in real applications. Aiming at this problem, this paper develops a new data augmentation method, i.e. randomized wavelet expansion, to generate a set of synthesis samples that share similar characteristics with the origina...
Article
Full-text available
Gas-path anomalies account for more than 90% of all civil aero-engine anomalies. It is essential to develop accurate gas-path anomaly detection methods. Therefore, a weakly supervised gas-path anomaly detection method for civil aero-engines based on mapping relationship mining of gas-path parameters and improved density peak clustering is proposed....
Article
Full-text available
The variations in gas path parameter deviations can fully reflect the healthy state of aero-engine gas path components and units; therefore, airlines usually take them as key parameters for monitoring the aero-engine gas path performance state and conducting fault diagnosis. In the past, the airlines could not obtain deviations autonomously. At pre...
Article
Through consideration of problems that the influence of the aero-engine state before shop visit and the adopted maintenance work scope on its performance after shop visit is complex and the sample size is small, we propose a lazy support vector machine regression (LSVMR) model for aero-engine performance prediction after shop visit based on the ε-s...
Article
Full-text available
Vibration signals under the same health state often have large differences due to changes in operating conditions. Likewise, the differences among vibration signals under different health states can be small under some operating conditions. Traditional deep learning methods apply fixed nonlinear transformations to all the input signals, which has a...
Article
Full-text available
This paper develops new deep learning methods, namely, deep residual shrinkage networks, to improve the feature learning ability from highly noised vibration signals and achieve a high fault diagnosing accuracy. Soft thresholding is inserted as nonlinear transformation layers into the deep architectures to eliminate unimportant features. Moreover,...
Article
Full-text available
Many existing aircraft engine fault detection methods are highly dependent on performance deviation data that are provided by the original equipment manufacturer. To improve the independent engine fault detection ability, Aircraft Communications Addressing and Reporting System (ACARS) data can be used. However, owing to the characteristics of high...
Article
Prediction problems with small sample size are problems which widely exist in engineering application. Because lazy prediction algorithms can utilize the information of predicted individual, it is often possible for them to achieve better predictive effect. Traditional lazy prediction algorithms generally use sample information directly, and theref...
Article
For the problem that single global modeling methods cannot get satisfactory aeroengine gas path parameter prediction results, ensemble algorithms with a combination method called dynamic weighted kernel density estimation(DWKDE) were proposed.Neighboring samples of the test samples were chosen. The weights of the base learners were dynamically calc...
Article
Full-text available
The opportunistic replacement of multiple Life-Limited Parts (LLPs) is a problem widely existing in industry. The replacement strategy of LLPs has a great impact on the total maintenance cost to a lot of equipment. This article focuses on finding a quick and effective algorithm for this problem. To improve the algorithm efficiency, six reduction ru...
Article
Full-text available
Considering total cost with the aim to minimize operation cost and maintenance cost in unit time, an aero-engine optimal operation performance interval determination model is proposed in this paper. Compared with previous researches, this model is more reasonable, because the model takes into consideration both operation cost and maintenance cost....
Article
A heuristic search algorithm was proposed to solve the lack of fast and effective problem-solving algorithm of opportunistic replacement of multiple life-limited parts (LLPs). At first, an optimization model of the opportunistic replacement problem of multiple LLPs was established to minimize the total LLP cost in the whole life cycle, and the solu...
Conference Paper
Full-text available
An improved latent correlation anomaly detection (LCAD) method is proposed to detect anomalies from condition monitoring datasets of industrial equipment. Above all, original data were segmented to various work cycles. Then, latent correlation vector (LCV) was used to denote the latent correlation among different parameters. Based on a latent corre...
Article
To make a scientific and reasonable maintenance workscope, an approach for civil aero-engine repair objective determination oriented towards the life cycle based on life limited parts was proposed. At first, a multi-objective optimization model was established to minimize shop visit times and total life limited parts cost, and maximize total object...
Article
To obtain a better accuracy, the time-varying fuzzy inference system theory was established, and a time-varying fuzzy neural network was created to solve the problem that the application was hard realized by too much parameters of the fuzzy inference system. The learning algorithm of the network structure was also designed. Mackey-Glass chaotic tim...
Article
To achieve the non-linear variables selection rapidly and accurately, the engine arguments parameters selection method for wavelet neural network's Mean Impact Value(MIV) was proposed based on the ideological of MIV and the advantages such as learning ability, fast convergence with adaptive and fault tolerance of wavelet neural network. According t...
Article
To make a scientific and reasonable maintenance workscope of civil aero-engine, an approach for aero-engine repair objective determination which was oriented to the life cycle based on performance state was proposed. The performance deterioration model and the relationship between the performance recovery and maintenance cost were studied. A multi-...
Chapter
Process family based on process platform provides an effective solution for rapid process design in mass customization production. Generally speaking, process platform includes three aspects: generic structure, generic planning and variety parameters. The essence of narrow sense process family is generic structure of generic process, in order to ac...
Conference Paper
The aeroengine is the heart of the aircraft. Its failure will affect the flight of the aircraft and even lead to catastrophic accidents, and its maintenance costs are a direct impact on the airline's operating costs. With the expansion of an airline's fleet, existing geographical boundaries are gradually broken. Thus, it is of great significance th...
Conference Paper
The turbine exhaust gas temperature (EGT) is an important parameter of the aeroengine and it represents the thermal health condition of the aeroengine. By predicting the EGT, the performance deterioration of the aeroengine can be deduced in advance and its remaining time-on-wing can be estimated. Thus, the flight safety and the economy of the airli...
Article
To keep the true mutation data which contained aero-engine fault or operation status information, a data smoothing technology was proposed by combining the outlier mining and similar exponential smoothing algorithm. The rolling sample outlier mining algorithm based on statistics was used to mine the outliers, and the similar double exponential smoo...
Article
Full-text available
The traditional aeroengine residual life prediction method assumes that all aeroengines have the same performance deterioration pattern in a fleet, which leads to a low prediction accuracy. On the basis that the aeroengine exhaust gas temperature margin (EGTM) is analyzed, the aeroengine residual life prediction method based on performance deterior...
Article
To reduce maintenance cost and improve performance after a shop visit, a decision-making method for civil aeroengine workscope under uncertain condition is proposed. Firstly, aeroengine overall performance restoration value for each module's maintenance level is expressed as a trapezoidal fuzzy number, and then a fuzzy chance constrained programmin...
Article
To improve prediction accuracy of aviation equipment cost under small sample size, a prediction model named information diffusion support vector machine is proposed after combining the information diffusion method and support vector machine. The topology and modeling process of the model are also described. The model parameters include both continu...
Article
It was difficult for the traditional methods to predict performance parameters effectively, aiming at this problem, a performance parameter prediction method based on the process neural network was proposed. Back Propagation (BP) learning algorithm was with low convergence speed and it was easy to a local minimum point. To solve these problems, a L...
Article
Full-text available
To improve prediction accuracy of aeroengine shop visit cost, the shop visit cost under contract of man hour and material was analyzed and redivided into the determinacy cost of type I, the determinacy cost of type II, the indeterminacy cost of type I and the indeterminacy cost of type II. Scrap probability model of important part and the cost prob...
Article
Full-text available
A objective-oriented method for module workscope decision-making was proposed to supply support for the aero-engine module workscope and achieve automatic and intelligent decision-making after analyzing the objectives of aero-engine shop visit. Module workscope was made through two steps from five aspects of life limited parts, airworthiness direct...
Article
Full-text available
The nonlinear multiple regression analysis based on kernel function was used to solve the baseline equation of Rolls-Royce's (RR's) engine. The standard kernel function was established and then the deviation model of performance parameters was established. The deviation calculated by factory system was used as target value, and other relevant param...
Article
To make reasonable maintenance plan, a multi-objective combinatorial optimization model for the aeroengine maintenance scheduling problem was constructed after analyzing influencing factors of aeroengine removal date and spare aeroengine selection. In order to describe the fitness of a spare aeroengine to an aircraft position, the concept and calcu...
Article
In order to conduct effective management on aero-engine maintenance data, according to multi-dimensional and evolutionary characteristics of aero-engine maintenance data, it was divided into configuration data, object-related data and class-related data. With the introduction of concepts of aero-engine physical state and module physical state, an a...
Conference Paper
The turbine exhaust gas temperature (EGT) is an important parameter of the aeroengine and it represents the thermal health condition of the aeroengine. By predicting the EGT, the performance deterioration of the aeroengine can be deduced in advance. Thus, the flight safety and the economy of the airlines can be guaranteed. However, the EGT is influ...

Network

Cited By