Fault isolation in nonlinear systems with structured partial principal component analysis and clustering analysis

2000 ◽  
Vol 78 (3) ◽  
pp. 569-577 ◽  
Author(s):  
Yunbing Huang ◽  
Thomas J. Mcavoy ◽  
Janos Gertler
Keyword(s):  
Principal Component Analysis ◽  
Nonlinear Systems ◽  
Clustering Analysis ◽  
Principal Component ◽  
Component Analysis ◽  
Fault Isolation

scholarly journals Mathematical modeling - food price analysis

2018 ◽  
Vol 1 (1) ◽  
Author(s):  
Bingxian Leng ◽  
Yunfei Fu ◽  
Siyuan Li
Keyword(s):  
Principal Component Analysis ◽  
Clustering Analysis ◽  
Principal Component ◽  
Component Analysis ◽  
Food Prices ◽  
Food Price ◽  
Analysis Model ◽  
Correlation Matrices ◽  
Gray Prediction ◽  
Spss Software

This paper mainly uses the idea of pedigree clustering analysis, gray prediction and principal component analysis. The clustering analysis model, GM (1,1) model and principal component analysis model were established by using SPSS software to analyze the correlation matrices and principal component analysis. MATLAB software was used to calculate the correlation matrices. In January, The difference in price changes of major food prices in cities is calculated, and had forecasted the various food prices in June 2016. For the first issue, the main food is classified and the data are processed. After that, the SPSS software is used to classify the 27 kinds of food into four categories by using the pedigree cluster analysis model and the system clustering. The four categories are made by EXCEL. The price of food changes over time with a line chart that analyzes the characteristics of food price volatility. For the second issue, the gray prediction model is established based on the food classification of each kind of food price. First, the original data is cumulated, test and processed, so that the data have a strong regularity, and then establish a gray differential equation, and then use MATLAB software to solve the model. And then the residual test and post-check test, have C <0.35, the prediction accuracy is better. Finally, predict the price trend in June 2016 through the function. For the third issue, we analyzed the main components of 27 kinds of food types by celery, octopus, chicken (white striped chicken), duck and Chinese cabbage by using the data of principal given and analyzed by principal component analysis. It can be detected by measuring a small amount of food, this predict CPI value relatively accurate. Through the study of the characteristics of the region, select Shanghai and Shenyang, by looking for the relevant CPI and food price data, using spss software, principal component analysis, the impact of the CPI on several types of food, and then calculated by matlab algorithm weight, and then the data obtained by the analysis and comparison, different regions should be selected for different types of food for testing.

scholarly journals Pengelompokan Kabupaten/Kota di Indonesia Berdasarkan Informasi Kemiskinan Tahun 2020 Menggunakan Metode K-Means Clustering Analysis

2021 ◽  
Vol 1 (1) ◽  
pp. 190-199
Author(s):  
Rijalul Fikri ◽  
Aswin Mushardiyanto ◽  
Mochamad Naufal Laudza’Banin ◽  
Kristiana Maureen ◽  
Harry Patria
Keyword(s):  
Principal Component Analysis ◽  
Clustering Analysis ◽  
Principal Component ◽  
Severity Index ◽  
Component Analysis ◽  
Silhouette Coefficient ◽  
Cluster 2

Berdasarkan dataset tentang informasi kemiskinan kabupaten/kota tahun 2020 yang dikeluarkan oleh Badan Pusat Statistik Indonesia, dipilih variabel bebas sebanyak dua puluh variabel yang digunakan dalam penelitian ini. Kemudian dilakukan uji korelasi antar variabel bebas tersebut dan diketahui terdapat variabel yang berkorelasi dikategorikan berkorelasi sangat tinggi, dengan nilai korelasi sebesar 0,921 (Persentase Penduduk Miskin - P1 (Poverty Gap Index)) dan 0,964 (P1 (Poverty Gap Index) - P2 (Proverty Severity Index)). Variabel yang memiliki korelasi sangat tinggi jika digunakan akan menyebabkan terjadinya multikolinearitas, sehingga opsi untuk menghilangkan multikolinearitas adalah dengan menggunakan Principal Component Analysis (PCA). Dengan menggunakan Proporsi Kumulatif Varians dan minimum persentase keragaman data sebesar 80% maka didapatkan output berupa dimensi data baru PCA sebanyak tiga dimensi data atau tiga variabel bebas baru. Dengan menggunakan variabel input baru berupa PCA 0, PCA 1 dan PCA 2 dilakukanlah penentuan jumlah cluster dengan metode Silhouette Coefficient dan analisa clustering menggunakan metode K-Means didapatkanlah empat kelompok/cluster, dengan jumlah anggota cluster 1 sebanyak 117 Kabupaten/Kota, cluster 2 sebanyak 154 Kabupaten/Kota, cluster 3 sebanyak 173 Kabupaten/Kota dan cluster 4 sebanyak 70 Kabupaten/Kota.

Diagnostics of Mechanical Faults of Loudspeakers Using Principal Component Analysis and Fisher’s Discriminant Analysis

2011 ◽  
Author(s):  
Jaewon Choi ◽  
Michael D. Bryant
Keyword(s):  
Principal Component Analysis ◽  
Discriminant Analysis ◽  
Principal Component ◽  
Component Analysis ◽  
Fault Isolation ◽  
Model Based ◽  
Mechanical Faults ◽  
Fisher’S Discriminant Analysis ◽  
Baseline Estimation

This study illustrates a novel model based FDI method for the common mechanical faults arising during the manufacture of loudspeakers. To overcome the drawbacks of the conventional signal based approaches, the Bayesian classification of impulse responses based on a model based fault symptom database is proposed. The loudspeaker model is estimated via IRES and ARMA techniques. The fault symptom database is constructed with a novel nonlinear loudspeaker model. The performances of Principal Component Analysis (PCA) and Fisher’s Discriminant Analysis (FDA) are compared. The results show the effectiveness of the proposed method. It is also shown that the FDA based classifier performs better than PCA in terms of the accuracy and consistency of the healthy baseline estimation. However, the fault isolation is difficult due to the similarities of fault signatures.

Fault detection and isolation in nonlinear systems with partial Reduced Kernel Principal Component Analysis method

2016 ◽  
Vol 40 (4) ◽  
pp. 1289-1296 ◽  
Author(s):  
Ines Jaffel ◽  
Okba Taouali ◽  
Mohamed Faouzi Harkat ◽  
Hassani Messaoud
Keyword(s):  
Principal Component Analysis ◽  
Fault Detection ◽  
Principal Component ◽  
Component Analysis ◽  
Fault Isolation ◽  
Fault Detection And Isolation ◽  
Kernel Principal Component Analysis ◽  
Continuous Stirred Tank Reactor ◽  
Analysis Method ◽  
Continuous Stirred Tank

In this article, we suggest an extension of our proposed method in fault detection called Reduced Kernel Principal Component Analysis (RKPCA) (Taouali et al., 2015) to fault isolation. To this end, a set of structured residues is generated by using a partial RKPCA model. Furthermore, each partial RKPCA model was performed on a subset of variables to generate structured residues according to a properly designed incidence matrix. The relevance of the proposed algorithm is revealed on Continuous Stirred Tank Reactor.

Fault Detection and Identification in NPP Instruments Using Kernel Principal Component Analysis

2010 ◽  
Author(s):  
Jianping Ma ◽  
Jin Jiang
Keyword(s):  
Principal Component Analysis ◽  
Fault Detection ◽  
Power Plants ◽  
Principal Component ◽  
Component Analysis ◽  
Fault Isolation ◽  
Kernel Principal Component Analysis ◽  
Isolation And Identification ◽  
Detection And Identification ◽  
Fault Detection And Identification

In this paper, kernel principal component analysis (KPCA) is studied for fault detection and identification in the instruments of nuclear power plants. We propose to use mean values of the sensor reconstruction errors of a KPCA model for fault isolation and identification. They provide useful information about the directions and magnitudes of detected faults, which are usually not available from other fault isolation techniques. The performance of the method is demonstrated by applications to real NPP measurements.

scholarly journals Research on Economic Periodicity Based on Principal Component-Weighted Distance and Clustering Analysis

2020 ◽  
Vol 214 ◽  
pp. 03003
Author(s):  
Jiayi Yan ◽  
Qian Pu ◽  
Junfei Liu
Keyword(s):  
Principal Component Analysis ◽  
Principal Components ◽  
Clustering Analysis ◽  
Pearson Correlation ◽  
Principal Component ◽  
Component Analysis ◽  
The United States ◽  
Economic Situation ◽  
Analysis Model ◽  
Weighted Distance

Based on the knowledge of economics, this paper selects 22 macroeconomic indicators that best reflect the overall economic situation of the United States. After differential, logarithmic and exponential preprocessing of the original data, this paper, based on the power spectral analysis model, adaptively identifies the periodicity of the selected economic indicators, and visualize the results. As a result, it screens out 11 indicators with obvious periodicity. In the process of solving the weighted distance based on principal component analysis, correlation test is first conducted on the selected 11 single indicators of periodicity to obtain Pearson correlation heatmap. Then, the principal components are extracted by selecting the first five principal components as the virtual indicators to represent the monthly economic situation, and calculating the weighted distance value between months for visualization. Finally, we select the results of 36 months’ smoothing for analysis, figure out the time intervals with similar economic situation, and verify the conjecture of economic periodicity. Finally, based on K-MEAN clustering analysis, the economic conditions of 352 months are classified into 3 clusters by using the weighted distance after 36 months’ smoothing. From the visualized results, it is found that there are two complete cycles, i.e. red-yellow-blue and red-yellow-blue, which is consistent with the conclusion of principal component analysis model, and proves the existence of economic cycle again. In conclusion, based on the above PCA weighted distance and clustering analysis, it can be concluded that the economic period is around 176 months, in favor of medium long periodicity theory.

Sign in / Sign up

Export Citation Format

Share Document