Stable Hybrid Feature Selection Method for Compressor Fault Diagnosis

Solichin, Mochammad; Kang, Young-Jin; Noh, Yoojeong; Park, Sunhwa; Ahn, Byeongha

doi:10.1109/access.2021.3092884

Cited by 13 publications

(5 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Zhang et al [ 5 ] and Liang et al [ 27 ] first used the Filter method to obtain a pre-selected subset and then further searched for optimal features using a genetic algorithm and particle swarm optimization, respectively. Mochammad et al [ 28 ] first selected five features from each of the original feature sets using three different Filter models and then searched for the optimal subset by exhausting the combinations among these features. Ganjie et al [ 29 ] first ranked the features according to their relevance to class labels, then applied different clustering methods to divide them into multiple subsets, and finally obtained the optimal subset by traversing all subsets.…”

Section: Motivation and Literature Reviewmentioning

confidence: 99%

A Hybrid Feature Selection and Multi-Label Driven Intelligent Fault Diagnosis Method for Gearbox

Liu

Zhang

et al. 2023

Sensors

View full text Add to dashboard Cite

Gearboxes are utilized in practically all complicated machinery equipment because they have great transmission accuracy and load capacities, so their failure frequently results in significant financial losses. The classification of high-dimensional data remains a difficult topic despite the fact that numerous data-driven intelligent diagnosis approaches have been suggested and employed for compound fault diagnosis in recent years with successful outcomes. In order to achieve the best diagnostic performance as the ultimate objective, a feature selection and fault decoupling framework is proposed in this paper. That is based on multi-label K-nearest neighbors (ML-kNN) as classifiers and can automatically determine the optimal subset from the original high-dimensional feature set. The proposed feature selection method is a hybrid framework that can be divided into three stages. The Fisher score, information gain, and Pearson’s correlation coefficient are three filter models that are used in the first stage to pre-rank candidate features. In the second stage, a weighting scheme based on the weighted average method is proposed to fuse the pre-ranking results obtained in the first stage and optimize the weights using a genetic algorithm to re-rank the features. The optimal subset is automatically and iteratively found in the third stage using three heuristic strategies, including binary search, sequential forward search, and sequential backward search. The method takes into account the consideration of feature irrelevance, redundancy and inter-feature interaction in the selection process, and the selected optimal subsets have better diagnostic performance. In two gearbox compound fault datasets, ML-kNN performs exceptionally well using the optimal subset with subset accuracy of 96.22% and 100%. The experimental findings demonstrate the effectiveness of the proposed method in predicting various labels for compound fault samples to identify and decouple compound faults. The proposed method performs better in terms of classification accuracy and optimal subset dimensionality when compared to other existing methods.

show abstract

Section: Motivation and Literature Reviewmentioning

confidence: 99%

A Hybrid Feature Selection and Multi-Label Driven Intelligent Fault Diagnosis Method for Gearbox

Liu

Zhang

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…Chi-square adalah metode statistik yang melakukan uji signifikansi data terhadap hubungan antara nilai suatu fitur dengan kelas target [46]- [49]. Nilai chi-square yang tinggi menunjukkan suatu fitur memiliki hubungan yang signifikan dengan kelas target [50], [54]- [57]. Chi-square umumnya diterapkan pada data kategori ataupun campuran [37], [49], [58].…”

Section: Chi-squareunclassified

“…Jika kedua kelas dapat dipisahkan secara linier, model klasifikasi linier diterapkan. Jika tidak, maka model klasifikasi nonlinier yang akan diterapkan [57]. Selain itu, SVM efektif dalam menangani kasus kumpulan data yang berdimensi tinggi.…”

Section: Support Vector Machineunclassified

Seleksi Fitur pada Supervised Learning: Klasifikasi Prestasi Belajar Mahasiswa Saat dan Pasca Pandemi COVID-19

Rahmadeyan

Mustakim

2023

TEKNOSI

View full text Add to dashboard Cite

Dampak pandemi COVID-19 membuat lembaga pendidikan mengubah metode belajar menjadi pembelajaran jarak jauh secara daring. Banyak perguruan tinggi menyatakan keprihatinannya pada prestasi akademik mahasiswanya selama selama periode tersebut, namun disisi lain terdapat mahasiswa yang merasa puas dan nyaman. Di masa pasca pandemi terjadi transisi bertahap untuk kembali ke pembelajaran tatap muka. Ini dilakukan karena pembelajaran tatap muka dianggap lebih efektif dibandingkan pembelajaran daring. Untuk meningkatkan dan memantau kemajuan prestasi akademik mahasiswa demi menghasilkan lulusan yang berkualitas, maka diperlukan analisis terkait perilaku dan prestasi belajar mahaiswa, salah satunya dengan menggunakan teknik data mining. Penelitian ini bertujuan untuk menemukan pola dan faktor yang mempengaruhi prestasi akademik mahasiswa saat dan pasca pandemi COVID-19. Chi-Square dan Mutual Information diterapkan sebagai seleksi fitur untuk menentukan fitur paling berpengaruh pada data. Data dengan fitur optimal akan dilakukan klasifikasi dengan algoritma NBC, CART, RF, dan SVM. Berdasarkan hasil dan analisis yang dilakukan, dapat disimpulkan seleksi fitur efektif dalam meningkatkan kemampuan model dan mempercepat waktu komputasi. Pemodelan dengan 4 algoritma dan 2 metode seleksi fitur menghasilkan CART dengan Chi-Square pada 2 fitur sebagai model terbaik dengan akurasi 89,00%, precision 87,72%, recall 93,57% dan waktu komputasi 0,01814s. Dibandingkan tanpa seleksi fitur, performa CART dengan Chi-Square mengalami peningkatan akurasi sebesar 3% dan waktu komputasi 0,00629s. Chi-Square menjadi seleksi fitur yang efektif pada penelitian ini, yang mana Chi-Square unggul pada rara-rata recall dan waktu komputasi dibandingkan Mutual Information.

show abstract

“…Multiphase motors are also fault tolerant because such machines remain functional even if failures affect certain phases (Riveros et al , 2018; Arahal et al , 2010). For this reason, multiphase motors are often used for actuation in industrial systems and harsh operating conditions (Lu et al , 2016; Mochammad et al , 2021; Soleymani et al , 2019).…”

Section: Introductionmentioning

confidence: 99%

Nonlinear optimal control for the five-phase induction motor-based traction system of electric vehicles

Rigatos,

Siano,

Al-Numay

et al. 2024

COMPEL

View full text Add to dashboard Cite

Purpose The purpose of this article is to treat the nonlinear optimal control problem in EV traction systems which are based on 5-phase induction motors. Five-phase permanent magnet synchronous motors and five-phase asynchronous induction motors (IMs) are among the types of multiphase motors one can consider for the traction system of electric vehicles (EVs). By distributing the required power in a large number of phases, the power load of each individual phase is reduced. The cumulative rates of power in multiphase machines can be raised without stressing the connected converters. Multiphase motors are also fault tolerant because such machines remain functional even if failures affect certain phases. Design/methodology/approach A novel nonlinear optimal control approach has been developed for five-phase IMs. The dynamic model of the five-phase IM undergoes approximate linearization using Taylor series expansion and the computation of the associated Jacobian matrices. The linearization takes place at each sampling instance. For the linearized model of the motor, an H-infinity feedback controller is designed. This controller achieves the solution of the optimal control problem under model uncertainty and disturbances. Findings To select the feedback gains of the nonlinear optimal (H-infinity) controller, an algebraic Riccati equation has to be solved repetitively at each time-step of the control method. The global stability properties of the control loop are demonstrated through Lyapunov analysis. Under moderate conditions, the global asymptotic stability properties of the control scheme are proven. The proposed nonlinear optimal control method achieves fast and accurate tracking of reference setpoints under moderate variations of the control inputs. Research limitations/implications Comparing to other nonlinear control methods that one could have considered for five-phase IMs, the presented nonlinear optimal (H-infinity) control approach avoids complicated state-space model transformations, is of proven global stability and its use does not require the model of the motor to be brought into a specific state-space form. The nonlinear optimal control method has clear implementation stages and moderate computational effort. Practical implications In the transportation sector, there is progressive transition to EVs. The use of five-phase IMs in EVs exhibits specific advantages, by achieving a more balanced distribution of power in the multiple phases of the motor and by providing fault tolerance. The study’s nonlinear optimal control method for five-phase IMs enables high performance for such motors and their efficient use in the traction system of EVs. Social implications Nonlinear optimal control for five-phase IMs supports the deployment of their use in EVs. Therefore, it contributes to the net-zero objective that aims at eliminating the emission of harmful exhaust gases coming from human activities. Most known manufacturers of vehicles have shifted to the production of all-electric cars. The study’s findings can optimize the traction system of EVs thus also contributing to the growth of the EV industry. Originality/value The proposed nonlinear optimal control method is novel comparing to past attempts for solving the optimal control problem for nonlinear dynamical systems. It uses a novel approach for selecting the linearization points and a new Riccati equation for computing the feedback gains of the controller. The nonlinear optimal control method is applicable to a wider class of dynamical systems than approaches based on the solution of state-dependent Riccati equations.

show abstract

Stable Hybrid Feature Selection Method for Compressor Fault Diagnosis

Cited by 13 publications

References 45 publications

A Hybrid Feature Selection and Multi-Label Driven Intelligent Fault Diagnosis Method for Gearbox

A Hybrid Feature Selection and Multi-Label Driven Intelligent Fault Diagnosis Method for Gearbox

Seleksi Fitur pada Supervised Learning: Klasifikasi Prestasi Belajar Mahasiswa Saat dan Pasca Pandemi COVID-19

Nonlinear optimal control for the five-phase induction motor-based traction system of electric vehicles

Contact Info

Product

Resources

About