• Title/Summary/Keyword: Performance degradation prediction

Search Result 154, Processing Time 0.028 seconds

Prediction of Compressor Fouling Using an Analytic Method (해석적 방법을 통한 압축기의 파울링 해석)

  • Song, Tae Won;Kim, Tong Seop;Kim, Jae Hwan;Ro, Sung Tack
    • 유체기계공업학회:학술대회논문집
    • /
    • 2000.12a
    • /
    • pp.176-183
    • /
    • 2000
  • The performance of gas turbines decreases as their operating hours increase. Compressor fouling is the main reason for this time-dependent performance degradation. Airborne particles adhere to the blade surface and results in the change in the blade shape. It is difficult to exactly analyze the mechanism of the compressor fouling because the growing process of the fouling is very slow and the dimension of the fouled depth is very small compared with blade dimensions. In this study, an analytic method to predict the motion of particles and their deposition inside axial flow compressors is proposed. The analytic model takes into account the blade shape and the flow within the blade passage. Comparison of simulation result with field data shows the feasibility of the model. Influence of the particle distribution on the compressor fouling is also examined.

  • PDF

Management Automation Technique for Maintaining Performance of Machine Learning-Based Power Grid Condition Prediction Model (기계학습 기반 전력망 상태예측 모델 성능 유지관리 자동화 기법)

  • Lee, Haesung;Lee, Byunsung;Moon, Sangun;Kim, Junhyuk;Lee, Heysun
    • KEPCO Journal on Electric Power and Energy
    • /
    • v.6 no.4
    • /
    • pp.413-418
    • /
    • 2020
  • It is necessary to manage the prediction accuracy of the machine learning model to prevent the decrease in the performance of the grid network condition prediction model due to overfitting of the initial training data and to continuously utilize the prediction model in the field by maintaining the prediction accuracy. In this paper, we propose an automation technique for maintaining the performance of the model, which increases the accuracy and reliability of the prediction model by considering the characteristics of the power grid state data that constantly changes due to various factors, and enables quality maintenance at a level applicable to the field. The proposed technique modeled a series of tasks for maintaining the performance of the power grid condition prediction model through the application of the workflow management technology in the form of a workflow, and then automated it to make the work more efficient. In addition, the reliability of the performance result is secured by evaluating the performance of the prediction model taking into account both the degree of change in the statistical characteristics of the data and the level of generalization of the prediction, which has not been attempted in the existing technology. Through this, the accuracy of the prediction model is maintained at a certain level, and further new development of predictive models with excellent performance is possible. As a result, the proposed technique not only solves the problem of performance degradation of the predictive model, but also improves the field utilization of the condition prediction model in a complex power grid system.

Improving the Water Level Prediction of Multi-Layer Perceptron with a Modified Error Function

  • Oh, Sang-Hoon
    • International Journal of Contents
    • /
    • v.13 no.4
    • /
    • pp.23-28
    • /
    • 2017
  • Of the total economic loss caused by disasters, 40% are due to floods and floods have a severe impact on human health and life. So, it is important to monitor the water level of a river and to issue a flood warning during unfavorable circumstances. In this paper, we propose a modified error function to improve a hydrological modeling using a multi-layer perceptron (MLP) neural network. When MLP's are trained to minimize the conventional mean-squared error function, the prediction performance is poor because MLP's are highly tunned to training data. Our goal is achieved by preventing overspecialization to training data, which is the main reason for performance degradation for rare or test data. Based on the modified error function, an MLP is trained to predict the water level with rainfall data at upper reaches. Through simulations to predict the water level of Nakdong River near a UNESCO World Heritage Site "Hahoe Village," we verified that the prediction performance of MLP with the modified error function is superior to that with the conventional mean-squared error function, especially maximum error of 40.85cm vs. 55.51cm.

Optimal Selection of Classifier Ensemble Using Genetic Algorithms (유전자 알고리즘을 이용한 분류자 앙상블의 최적 선택)

  • Kim, Myung-Jong
    • Journal of Intelligence and Information Systems
    • /
    • v.16 no.4
    • /
    • pp.99-112
    • /
    • 2010
  • Ensemble learning is a method for improving the performance of classification and prediction algorithms. It is a method for finding a highly accurateclassifier on the training set by constructing and combining an ensemble of weak classifiers, each of which needs only to be moderately accurate on the training set. Ensemble learning has received considerable attention from machine learning and artificial intelligence fields because of its remarkable performance improvement and flexible integration with the traditional learning algorithms such as decision tree (DT), neural networks (NN), and SVM, etc. In those researches, all of DT ensemble studies have demonstrated impressive improvements in the generalization behavior of DT, while NN and SVM ensemble studies have not shown remarkable performance as shown in DT ensembles. Recently, several works have reported that the performance of ensemble can be degraded where multiple classifiers of an ensemble are highly correlated with, and thereby result in multicollinearity problem, which leads to performance degradation of the ensemble. They have also proposed the differentiated learning strategies to cope with performance degradation problem. Hansen and Salamon (1990) insisted that it is necessary and sufficient for the performance enhancement of an ensemble that the ensemble should contain diverse classifiers. Breiman (1996) explored that ensemble learning can increase the performance of unstable learning algorithms, but does not show remarkable performance improvement on stable learning algorithms. Unstable learning algorithms such as decision tree learners are sensitive to the change of the training data, and thus small changes in the training data can yield large changes in the generated classifiers. Therefore, ensemble with unstable learning algorithms can guarantee some diversity among the classifiers. To the contrary, stable learning algorithms such as NN and SVM generate similar classifiers in spite of small changes of the training data, and thus the correlation among the resulting classifiers is very high. This high correlation results in multicollinearity problem, which leads to performance degradation of the ensemble. Kim,s work (2009) showedthe performance comparison in bankruptcy prediction on Korea firms using tradition prediction algorithms such as NN, DT, and SVM. It reports that stable learning algorithms such as NN and SVM have higher predictability than the unstable DT. Meanwhile, with respect to their ensemble learning, DT ensemble shows the more improved performance than NN and SVM ensemble. Further analysis with variance inflation factor (VIF) analysis empirically proves that performance degradation of ensemble is due to multicollinearity problem. It also proposes that optimization of ensemble is needed to cope with such a problem. This paper proposes a hybrid system for coverage optimization of NN ensemble (CO-NN) in order to improve the performance of NN ensemble. Coverage optimization is a technique of choosing a sub-ensemble from an original ensemble to guarantee the diversity of classifiers in coverage optimization process. CO-NN uses GA which has been widely used for various optimization problems to deal with the coverage optimization problem. The GA chromosomes for the coverage optimization are encoded into binary strings, each bit of which indicates individual classifier. The fitness function is defined as maximization of error reduction and a constraint of variance inflation factor (VIF), which is one of the generally used methods to measure multicollinearity, is added to insure the diversity of classifiers by removing high correlation among the classifiers. We use Microsoft Excel and the GAs software package called Evolver. Experiments on company failure prediction have shown that CO-NN is effectively applied in the stable performance enhancement of NNensembles through the choice of classifiers by considering the correlations of the ensemble. The classifiers which have the potential multicollinearity problem are removed by the coverage optimization process of CO-NN and thereby CO-NN has shown higher performance than a single NN classifier and NN ensemble at 1% significance level, and DT ensemble at 5% significance level. However, there remain further research issues. First, decision optimization process to find optimal combination function should be considered in further research. Secondly, various learning strategies to deal with data noise should be introduced in more advanced further researches in the future.

Probabilistic-based prediction of lifetime performance of RC bridges subject to maintenance interventions

  • Tian, Hao;Li, Fangyuan
    • Computers and Concrete
    • /
    • v.17 no.4
    • /
    • pp.499-521
    • /
    • 2016
  • In this paper, a probabilistic- and finite element-based approach to evaluate and predict the lifetime performance of reinforced concrete (RC) bridges undergoing various maintenance actions is proposed with the time-variant system reliability being utilized as a performance indicator. Depending on their structural state during the degradation process, the classical maintenance actions for RC bridges are firstly categorized into four types: Preventive type I, Preventive type II, Strengthening and Replacement. Preventive type I is used to delay the onset of steel corrosion, Preventive type II can suppress the corrosion process of reinforcing steel, Strengthening is the application of various maintenance materials to improve the structural performance and Replacement is performed to restore the individual components or overall structure to their original conditions. The quantitative influence of these maintenance types on structural performance is investigated and the respective analysis modules are written and inputted into the computer program. Accordingly, the time-variant system reliability can be calculated by the use of Monte Carlo simulations and the updated the program. Finally, an existing RC continuous bridge located in Shanghai, China, is used as an illustrative example and the lifetime structural performance with and without each of the maintenance types are discussed. It is felt that the proposed approach can be applied to various RC bridges with different structural configurations, construction methods and environmental conditions.

Development of Delay Compensator for Network Based Real-time Control Systems (네트워크 기반 실시간 제어 시스템을 위한 지연 보상기 개발)

  • Kim, Seung-Yong;Kim, Hong-Ryeol;Kim, Dae-Won
    • Proceedings of the KIEE Conference
    • /
    • 2004.11c
    • /
    • pp.82-85
    • /
    • 2004
  • This paper proposes the development of delay compensator to minimize performance degradation caused by time delays in network-based real-time control systems. The delay compensator uses the time-stamp method as a direct delay measuring method to measure time delays generated between network nodes. The delay compensator predicts the network time delays of next period in the views point of time delays and minimizes performance degradation from network through considering predicted time delays. Control output considering network time delays is generated by the defuzzification of probable time delays of next period. The time delays considered in the delay compensator are modeled by using a timed Petri net model. The proposed delay prediction mechanism for the delay compensator is evaluated through some simulation tests by measuring deviation of the predicted delays from simulated delays.

  • PDF

A Life Prediction of Insulation Degradation Using Neural Networks (신경회로망을 이용한 절연열화의 수명추정)

  • 이영상;김성홍;심종탁;윤헌주;임윤석;김재환;박재준
    • Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
    • /
    • 1998.06a
    • /
    • pp.297-300
    • /
    • 1998
  • In this paper, we obtained the data, which is required in training the neural network and diagnosing the degradation degree, by introducing the AE detection that is effective method in ordinary degradation diagnosis on activation. Automatic detection system to detect acoustic. As the results of generalization tests by appling neural network to the unknown AE patterns obtained from specimens, firstly as to evaluate an objective performance of neural network, the recognition ratio for no-void specimen is appeared. Also, in the evaluation for the adaptability of neural network with a untrained type of no-void specimen, it is confirmed that the result appears.

  • PDF

Plurality Rule-based Density and Correlation Coefficient-based Clustering for K-NN

  • Aung, Swe Swe;Nagayama, Itaru;Tamaki, Shiro
    • IEIE Transactions on Smart Processing and Computing
    • /
    • v.6 no.3
    • /
    • pp.183-192
    • /
    • 2017
  • k-nearest neighbor (K-NN) is a well-known classification algorithm, being feature space-based on nearest-neighbor training examples in machine learning. However, K-NN, as we know, is a lazy learning method. Therefore, if a K-NN-based system very much depends on a huge amount of history data to achieve an accurate prediction result for a particular task, it gradually faces a processing-time performance-degradation problem. We have noticed that many researchers usually contemplate only classification accuracy. But estimation speed also plays an essential role in real-time prediction systems. To compensate for this weakness, this paper proposes correlation coefficient-based clustering (CCC) aimed at upgrading the performance of K-NN by leveraging processing-time speed and plurality rule-based density (PRD) to improve estimation accuracy. For experiments, we used real datasets (on breast cancer, breast tissue, heart, and the iris) from the University of California, Irvine (UCI) machine learning repository. Moreover, real traffic data collected from Ojana Junction, Route 58, Okinawa, Japan, was also utilized to lay bare the efficiency of this method. By using these datasets, we proved better processing-time performance with the new approach by comparing it with classical K-NN. Besides, via experiments on real-world datasets, we compared the prediction accuracy of our approach with density peaks clustering based on K-NN and principal component analysis (DPC-KNN-PCA).

An Efficient Mode Decision Method for Fast Intra Prediction of SVC (SVC에서 빠른 인트라 예측을 위한 효율적인 모드 결정 방법)

  • Cho, Mi-Sook;Kang, Jin-Mi;Chung, Ki-Dong
    • Journal of KIISE:Computing Practices and Letters
    • /
    • v.15 no.4
    • /
    • pp.280-283
    • /
    • 2009
  • To improve coding performance of scalable video coding which is an emerging video coding standard as an extension of H.264/AVC, SVC uses not only intra prediction and inter prediction but inter-layer prediction. This causes a problem that computational complexity is increased. In this paper, we propose an efficient intra prediction mode decision method in spatial enhancement layer to reduce the computational complexity. The proposed method selects Inra_BL mode using RD cost of Intra_BL in advance. After that, intra mode is decided by only comparing DC modes. Experimental results show that the proposed method reduces 59% of the computation complexity of intra prediction coding, while the degradation in video quality is negligible.

Optimization of Plasma Process to Improve Plasma Gas Dissolution Rate using Three-neck Nozzle (3구 노즐을 이용한 플라즈마 가스 용존율 향상을 위한 플라즈마 공정의 최적화)

  • Kim, Dong-Seog;Park, Young-Seek
    • Journal of Environmental Science International
    • /
    • v.30 no.5
    • /
    • pp.399-406
    • /
    • 2021
  • The dissolution of ionized gas in dielectric barrier plasma, similar to the principle of ozone generation, is a major performance-affecting factor. In this study, the plasma gas dissolving performance of a gas mixing-circulation plasma process was evaluated using an experimental design methodology. The plasma reaction is a function of four parameters [electric current (X1), gas flow rate (X2), liquid flow rate (X3) and reaction time (X4)] modeled by the Box-Behnken design. RNO (N, N-Dimethyl-4-nitrosoaniline), an indictor of OH radical formation, was evaluated using a quadratic response surface model. The model prediction equation derived for RNO degradation was shown as a second-order polynomial. By pooling the terms with poor explanatory power as error terms and performing ANOVA, results showed high significance, with an adjusted R2 value of 0.9386; this indicate that the model adequately satisfies the polynomial fit. For the RNO degradation, the measured value and the predicted values by the model equation agreed relatively well. The optimum current, gas flow rate, liquid flow rate and reaction time were obtained for the highest desirability for RNO degradation at 0.21 A, 2.65 L/min, 0.75 L/min and 6.5 min, respectively.