Fuzzy Analytic Hierarchy Process Evaluation Method of Gas Turbine Based on Health Degree

2018 ◽  
Author(s):  
Yunpeng Cao ◽  
Pan Hu ◽  
Qingcai Yang ◽  
Yinghui He ◽  
Shuying Li ◽  
...  
Keyword(s):  
Gas Turbine ◽  
Evaluation Method ◽  
Remaining Useful Life ◽  
Prediction Algorithm ◽  
Health State ◽  
Analytic Hierarchy ◽  
Data Set ◽  
Useful Life ◽  
Hierarchy Process ◽  
Evaluation Parameters

In this paper, a gas turbine fuzzy analytic hierarchy process based on health degree is proposed to determine the current health state and remaining useful life of the gas turbine. The concept of health degree is introduced to quantitatively represent the health state of gas turbine and its components and parameters. The probability density function is used to calculate the health degree of the evaluation parameters to avoid the complexity of evaluation caused by different orders of magnitude. This paper proposes the weights hiding method that reflects the inhomogeneity of the evaluation parameters and proposes a remaining useful life prediction algorithm based on the health degree. Finally, the training data set from the Commercial Modular Aero-Propulsion System Simulation (CMAPSS) simulator is used to validate the proposed health evaluation method and the remaining useful life prediction algorithm. The results show that the gas turbine health degree obtained by the method in this paper can be used to accurately predict the degradation trend of gas turbine, and the predicted remaining useful life coincides with the result of the test data set, thereby demonstrating the validity and practicability of the proposed method of using health degree to describe the gas turbine health state.

scholarly journals Predicting Remaining Useful Life of Rolling Bearings Based on Reliable Degradation Indicator and Temporal Convolution Network with the Quantile Regression

2021 ◽  
Vol 11 (11) ◽  
pp. 4773
Author(s):  
Qiaoping Tian ◽  
Honglei Wang
Keyword(s):  
Quantile Regression ◽  
Probability Density ◽  
Degradation Process ◽  
Remaining Useful Life ◽  
Health State ◽  
Rolling Bearings ◽  
Data Set ◽  
Time Frequency ◽  
Useful Life ◽  
Degradation Indicator

High precision and multi information prediction results of bearing remaining useful life (RUL) can effectively describe the uncertainty of bearing health state and operation state. Aiming at the problem of feature efficient extraction and RUL prediction during rolling bearings operation degradation process, through data reduction and key features mining analysis, a new feature vector based on time-frequency domain joint feature is found to describe the bearings degradation process more comprehensively. In order to keep the effective information without increasing the scale of neural network, a joint feature compression calculation method based on redefined degradation indicator (DI) was proposed to determine the input data set. By combining the temporal convolution network with the quantile regression (TCNQR) algorithm, the probability density forecasting at any time is achieved based on kernel density estimation (KDE) for the conditional distribution of predicted values. The experimental results show that the proposed method can obtain the point prediction results with smaller errors. Compared with the existing quantile regression of long short-term memory network(LSTMQR), the proposed method can construct more accurate prediction interval and probability density curve, which can effectively quantify the uncertainty of bearing running state.

scholarly journals A Genetic Algorithm Optimized RNN-LSTM Model for Remaining Useful Life Prediction of Turbofan Engine

Electronics ◽  
2021 ◽  
Vol 10 (3) ◽  
pp. 285
Author(s):  
Kwok Tai Chui ◽  
Brij B. Gupta ◽  
Pandian Vasant
Keyword(s):  
Genetic Algorithm ◽  
Feature Extraction ◽  
Prediction Model ◽  
Prediction Models ◽  
Remaining Useful Life ◽  
Prediction Algorithm ◽  
Short Term ◽  
Turbofan Engine ◽  
Term Prediction ◽  
Useful Life

Understanding the remaining useful life (RUL) of equipment is crucial for optimal predictive maintenance (PdM). This addresses the issues of equipment downtime and unnecessary maintenance checks in run-to-failure maintenance and preventive maintenance. Both feature extraction and prediction algorithm have played crucial roles on the performance of RUL prediction models. A benchmark dataset, namely Turbofan Engine Degradation Simulation Dataset, was selected for performance analysis and evaluation. The proposal of the combination of complete ensemble empirical mode decomposition and wavelet packet transform for feature extraction could reduce the average root-mean-square error (RMSE) by 5.14–27.15% compared with six approaches. When it comes to the prediction algorithm, the results of the RUL prediction model could be that the equipment needs to be repaired or replaced within a shorter or a longer period of time. Incorporating this characteristic could enhance the performance of the RUL prediction model. In this paper, we have proposed the RUL prediction algorithm in combination with recurrent neural network (RNN) and long short-term memory (LSTM). The former takes the advantages of short-term prediction whereas the latter manages better in long-term prediction. The weights to combine RNN and LSTM were designed by non-dominated sorting genetic algorithm II (NSGA-II). It achieved average RMSE of 17.2. It improved the RMSE by 6.07–14.72% compared with baseline models, stand-alone RNN, and stand-alone LSTM. Compared with existing works, the RMSE improvement by proposed work is 12.95–39.32%.

scholarly journals Remaining Useful Life Prediction Using Temporal Convolution with Attention

AI ◽  
2021 ◽  
Vol 2 (1) ◽  
pp. 48-70
Author(s):  
Wei Ming Tan ◽  
T. Hui Teo
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Time Series Data ◽  
Remaining Useful Life ◽  
Sensor Data ◽  
Series Data ◽  
Multiple Time ◽  
Data Set ◽  
Form Complex ◽  
Useful Life

Prognostic techniques attempt to predict the Remaining Useful Life (RUL) of a subsystem or a component. Such techniques often use sensor data which are periodically measured and recorded into a time series data set. Such multivariate data sets form complex and non-linear inter-dependencies through recorded time steps and between sensors. Many current existing algorithms for prognostic purposes starts to explore Deep Neural Network (DNN) and its effectiveness in the field. Although Deep Learning (DL) techniques outperform the traditional prognostic algorithms, the networks are generally complex to deploy or train. This paper proposes a Multi-variable Time Series (MTS) focused approach to prognostics that implements a lightweight Convolutional Neural Network (CNN) with attention mechanism. The convolution filters work to extract the abstract temporal patterns from the multiple time series, while the attention mechanisms review the information across the time axis and select the relevant information. The results suggest that the proposed method not only produces a superior accuracy of RUL estimation but it also trains many folds faster than the reported works. The superiority of deploying the network is also demonstrated on a lightweight hardware platform by not just being much compact, but also more efficient for the resource restricted environment.

Analysis of the Safety Factors of Municipal Road Undercrossing Existing Bridge Based on Fuzzy Analytic Hierarchy Process Methods

2021 ◽  
pp. 036119812110318
Author(s):  
Yonghong Yang ◽  
Yu Chen ◽  
Zude Tang
Keyword(s):  
Safety Assessment ◽  
Evaluation Method ◽  
Comprehensive Evaluation ◽  
Safety Evaluation ◽  
Safety Factors ◽  
Analytic Hierarchy ◽  
Road Engineering ◽  
Existing Bridges ◽  
Hierarchy Process ◽  
Engineering Projects

Increasing traffic volume and insufficient road lanes often require municipal roads to be reconstructed and expanded. Where a road passes under a bridge, the reconstruction and expansion project will inevitably have an impact on the bridge. To evaluate the safety impact of road engineering projects on bridges, this paper evaluates the safety of the roads and ancillary facilities of highway bridges involved in municipal road engineering projects. Based on a comprehensive analysis of the safety factors of municipal roads undercrossing existing bridges, a fuzzy comprehensive analytic hierarchy process (AHP) evaluation method for the influence of road construction on the safety of existing bridges is proposed. First, AHP is used to select 11 evaluation factors. Second, the target layer, criterion layer, and index layer of evaluation factors are established, then a safety evaluation factor system is formed. The three-scale AHP model is used to determine the weight of assessment indexes. Third, through the fuzzy comprehensive AHP evaluation model, the fuzzy hierarchical comprehensive evaluation is carried out for the safety assessment index system. Finally, the fuzzy comprehensive evaluation method is applied to the engineering example of a municipal road undercrossing an existing expressway bridge. The comprehensive safety evaluation of the existing bridge reflects the practicability and feasibility of the method. It is expected that, with further development, the method will improve the decision-making process in bridge safety assessment systems.

Integrated AHP-BPNN Model for Wind Farm Investment Evaluation

2014 ◽  
Vol 541-542 ◽  
pp. 966-971
Author(s):  
Xiang Feng Zhang ◽  
Tian Yu Liu ◽  
Bin Jiao
Keyword(s):  
Wind Farm ◽  
Evaluation Method ◽  
Back Propagation ◽  
Wind Farms ◽  
Back Propagation Neural Network ◽  
Analytic Hierarchy ◽  
Farm Investment ◽  
Hierarchy Process ◽  
Power Project ◽  
Bpnn Model

The construction of wind farms grows quickly in China. It is necessary for stakeholders to estimate investment costs and to make good decisions about a wind power project by making a budget for the investment. This paper proposed an evaluation method by integrating the analytic hierarchy process (AHP) with back-propagation neural network (BPNN) to evaluate wind farm investment. In the AHP-BPNN model, the AHP method is used to determine the factors of wind farm investment. The factors with high importance are reserved while those with low importance are eliminated, which can decrease the number of inputs of the BPNN. The experiment results show that the integrated model is feasible and effective.

Study of Evaluation Method in Terms of Structural Planes Mechanical Characteristics in Engineering Rock Mass

2013 ◽  
Vol 353-356 ◽  
pp. 384-387 ◽  
Author(s):  
Mu Dan Guo ◽  
Fu Sheng Zhu ◽  
Shu Hong Wang ◽  
Xi Jiang Mu
Keyword(s):  
Rock Mass ◽  
Stability Analysis ◽  
Efficient Method ◽  
Weight Distribution ◽  
Evaluation Method ◽  
Mechanical Characteristics ◽  
Significant Issue ◽  
Analytic Hierarchy ◽  
Intensity Parameters ◽  
Hierarchy Process

Study of mechanical characteristics of structural planes has been significant issue in engineering rock mass stability analysis. The factors that affect the mechanical behavior of structural planes are so complicated that it is quite essential to take an efficient method to quantificationally analyze these factors. Based on the basic principals of analytic hierarchy process (AHP), a structural plane classification method-CSPC method is proposed. It can conduct weight distribution in terms of the complicated factors, assess the structural planes comprehensively and also forecast the planes intensity parameters semiquantitatively. The classification and forecast parameters of structural planes appropriately fit the cases in engineering. Furthermore, the method is easy to master for the engineers and the application can be of great prospect.

scholarly journals A HYBRID MULTIPLE CRITERIA EVALUATION METHOD OF RANKING OF CULTURAL HERITAGE STRUCTURES FOR RENOVATION PROJECTS

2017 ◽  
Vol 21 (3) ◽  
pp. 318-329 ◽  
Author(s):  
Zenonas TURSKIS ◽  
Zydrune MORKUNAITE ◽  
Vladislavas KUTUT
Keyword(s):  
Cultural Heritage ◽  
Evaluation Method ◽  
Social Needs ◽  
Problem Solution ◽  
Analytic Hierarchy ◽  
State Institutions ◽  
The Social ◽  
Heritage Buildings ◽  
Multiple Criteria Evaluation ◽  
Hierarchy Process

Cultural heritage item preservation, renovation and adaptation to the social needs of people, as well as their passing from generation to generation, is a problem relevant from economic, historical, archeological, religious, technological, research and other perspectives. They are typical strategic multi-criteria decision-making problems. The state institutions and the owners and managers of the heritage items invest in their preservation. In fact, every country has a great number of the registered heritage structures. To ensure their effective management and renovation, a lot of implementation projects and strategies should be developed and evaluated. This work requires large investments and time. The paper presents a hybrid model developed for ranking the heritage buildings intended for renovation according to their value. The model for problem solution based on integrated using two MCDM methods Analytic Hierarchy Process and EDAS. A set of the criteria for evaluating the projects, concerning the renovation of cultural heritage items defined.

Sign in / Sign up

Export Citation Format

Share Document