Hasil Pencarian  ::  Simpan CSV :: Kembali

"IFToMM conferences have a history of success due to the various advances achieved in the field of rotor dynamics over the past three decades. These meetings have since become a leading global event, bringing together specialists from industry and academia to promote the exchange of knowledge, ideas, and information on the latest developments in the dynamics of rotating machinery. The scope of the conference is broad, including e.g. active components and vibration control, balancing, bearings, condition monitoring, dynamic analysis and stability, wind turbines and generators, electromechanical interactions in rotor dynamics and turbochargers. The proceedings are divided into four volumes. This second volume covers the following main topics: condition monitoring, fault diagnostics and prognostics; modal testing and identification; parametric and self-excitation in rotor dynamics; uncertainties, reliability and life predictions of rotating machinery; and torsional vibrations and geared systems dynamics. "

"Rotating Machinery, Optical Methods & Scanning LDV Methods, Volume 6: Proceedings of the 37th IMAC, A Conference and Exposition on Structural Dynamics, 2019, the sixth volume of eight from the Conference brings together contributions to this important area of research and engineering. The collection presents early findings and case studies on fundamental and applied aspects of Structural Health Monitoring, including papers on:- Novel Techniques- Optical Methods,- Scanning LDV Methods- Photogrammetry & DIC- Rotating Machinery"

"Rotating Machinery, Vibro-Acoustics & Laser Vibrometry, Volume 7: Proceedings of the 36th IMAC, A Conference and Exposition on Structural Dynamics, 2018, the seveth volume of nine from the Conference brings together contributions to this important area of research and engineering. The collection presents early findings and case studies on fundamental and applied aspects of Rotating Machinery, Hybrid Testing, Vibro-Acoustics & Laser Vibrometry, including papers on; Rotating Machinery, Vibro-Acoustics, Experimental Techniques, and Scanning Laser Doppler Vibrometry Methods."

"Rotating machinery dalam industri minyak dan gas merupakan aset kritis yang beroperasi dalam medan kerja yang berat, sehingga beberapa bagian umum rentan mengalami fault. Fault merupakan anomali yang menunjukkan penyimpangan dari kondisi operasi normal pada suatu sistem, sehingga perlu dideteksi lebih dini, secara akurat, dan terotomasi. Salah satu metode yang dapat digunakan adalah dengan machine learning. Data yang digunakan dalam penelitian ini adalah sensor condition monitoring aset rotating machinery yang diperoleh dari sebuah perusahaan minyak dan gas di Indonesia. Data sensor yang diperoleh mencakup 3 operation parameters yakni kecepatan, suhu, dan vibrasi. Algoritme klasifikasi pada penelitian ini menggunakan supervised learning yakni Support Vector Machine (SVM), Random Forest (RF), dan K-Nearest Neighbors (KNN). Kinerja model machine learning dievaluasi menggunakan metrik accuracy, precision, F1 score, dan matthews correlation coefficient (MCC). Hasil model klasifikasi random forest menunjukkan hasil yang sangat baik dengan akurasi 98,5%, presisi 98,6%, f1-score 98,5%, dan MCC sebesar 97,2%. Analisis SHAP Explainer secara global mampu menjelaskan feature importance dan secara lokal yang memperlihatkan kontribusi variabel-variabel operating parameter yang berkontribusi paling besar pada kelas normal, alert, dan fault.

---

Rotating machinery in the oil and gas industry is a critical asset that operates in a tough work environment, where some of the common parts are prone to faults. Fault is an anomaly that indicates a deviation from the normal operating conditions of a system, so it needs to be detected early, accurately, and automated. The data used in this study is obtained from a condition monitoring sensor of rotating machinery in an oil and gas company in Indonesia. The acquired sensor data includes 3 operating parameters: speed, temperature, and vibration. The classification algorithms used in this research are supervised learning methods, namely Support Vector Machine (SVM), Random Forest (RF), and K-Nearest Neighbors (KNN). The performance of the machine learning models is evaluated using metrics such as accuracy, precision, F1 score, and Matthews correlation coefficient (MCC). The results of the random forest classification model show very good results with an accuracy of 98.5%, a precision of 98.6%, an f1-score of 98.5%, and an MCC of 97.2%. SHAP Explainer in global explanation is able to explain the feature importance and also locally which shows the contribution of operating parameter variables that contribute the most to the normal, alert, and fault classes."

"Peralatan putar memegang peranan penting dalam menjaga kesinambungan produksi di industri petrokimia. Meskipun kegagalan pada peralatan ini tergolong jarang terjadi, dampaknya dapat menimbulkan gangguan operasional yang signifikan, termasuk downtime produksi dan kerugian finansial yang besar. Penelitian ini bertujuan untuk mengembangkan kerangka kerja berbasis deep learning yang terintegrasi guna meningkatkan akurasi deteksi kegagalan pada kondisi data yang tidak seimbang dan input sensor yang kompleks. Permasalahan utama yang diangkat adalah ketidakseimbangan data kegagalan serta keterbatasan interpretabilitas pada metode machine learning konvensional. Pendekatan yang diusulkan menggabungkan Wasserstein Generative Adversarial Network (WGAN) untuk menghasilkan data sintetik pada kelas kegagalan, dan TabNet sebagai model klasifikasi deep learning yang dapat diinterpretasikan untuk data sensor terstruktur. Model ini dilatih menggunakan data historis sensor dari tahun 2015 hingga 2024, mencakup 147 variabel proses seperti suhu, tekanan, aliran, getaran, dan kecepatan. Model gabungan WGAN-TabNet menunjukkan kinerja yang unggul dibanding algoritma pembanding (Logistic Regression, SVM, dan XGBoost) dengan akurasi 96,01%, presisi 93,25%, recall 93,14%, F1-score 93,20%, dan AUC 93,13%. Untuk interpretasi model, digunakan SHAP (SHapley Additive exPlanations) yang berhasil mengidentifikasi variabel penting seperti suhu oli dan laju aliran gas. Keunggulan dalam fitur pembeda, kemampuan penyeimbangan data, akurasi prediksi yang tinggi, dan interpretabilitas model memungkinkan deteksi dini gejala kegagalan secara efektif. Model ini dinilai layak untuk diterapkan dalam sistem pemantauan waktu nyata guna mendukung perawatan prediktif di lingkungan industri yang kritis. Pendekatan ini juga berpotensi diterapkan pada jenis peralatan putar lainnya dan perlu divalidasi lebih lanjut dalam penelitian mendatang.

---

Rotating machinery plays a critical role in sustaining production continuity in the petrochemical industry. Although failures in such equipment are relatively rare, they can cause operational disruptions leading to significant production downtime and financial losses. The objective of this study is to develop an integrated deep learning-based framework to improve fault detection accuracy under conditions of data imbalance and complex sensor input. The research addresses the problem of imbalanced fault data and limited interpretability in conventional machine learning methods. An integrated model approach is proposed by combining Wasserstein Generative Adversarial Network (WGAN) to generate synthetic failure data, and TabNet as an interpretable deep learning classifier for structured sensor data. The model was trained using historical sensor readings collected from 2015 to 2024, comprising 147 process variables such as temperature, pressure, flow, vibration, and speed. The proposed WGAN-TabNet model outperformed benchmark algorithms (Logistic Regression, SVM, and XGBoost) with accuracy of 96.01%, precision of 93.25%, recall of 93.14%, F1-score of 93.20%, and AUC of 93.13%. SHAP (SHapley Additive exPlanations) was employed to interpret the model, identifying key contributing variables such as oil temperature and gas flow rate. These distinctive features, data balancing capability, high predictive performance, and model interpretability enabled effective detection of early failure symptoms. The model is suitable for practical deployment in real-time monitoring systems, supporting predictive maintenance in critical industrial environments. This approach also holds potential to be applied to other types of rotating equipment, which should be validated in future studies."

"IFToMM conferences have a history of success due to the various advances achieved in the field of rotor dynamics over the past three decades. These meetings have since become a leading global event, bringing together specialists from industry and academia to promote the exchange of knowledge, ideas, and information on the latest developments in the dynamics of rotating machinery. The scope of the conference is broad, including e.g. active components and vibration control, balancing, bearings, condition monitoring, dynamic analysis and stability, wind turbines and generators, electromechanical interactions in rotor dynamics and turbochargers. The proceedings are divided into four volumes. This fourth volume covers the following main topics: aero-engines; turbochargers; eolian (wind) generators; automotive rotating systems; and hydro power plants. "

"IFToMM conferences have a history of success due to the various advances achieved in the field of rotor dynamics over the past three decades. These meetings have since become a leading global event, bringing together specialists from industry and academia to promote the exchange of knowledge, ideas, and information on the latest developments in the dynamics of rotating machinery. The scope of the conference is broad, including e.g. active components and vibration control, balancing, bearings, condition monitoring, dynamic analysis and stability, wind turbines and generators, electromechanical interactions in rotor dynamics and turbochargers. The proceedings are divided into four volumes. This third volume covers the following main topics: dynamic analysis and stability; electromechanical interactions in rotordynamics; nonlinear phenomena in rotordynamics; rotordynamics of micro, nano and cryogenic machines; and fluid structure interactions in rotordynamics. "

"IFToMM conferences have a history of success due to the various advances achieved in the field of rotor dynamics over the past three decades. These meetings have since become a leading global event, bringing together specialists from industry and academia to promote the exchange of knowledge, ideas, and information on the latest developments in the dynamics of rotating machinery. The scope of the conference is broad, including e.g. active components and vibration control, balancing, bearings, condition monitoring, dynamic analysis and stability, wind turbines and generators, electromechanical interactions in rotor dynamics and turbochargers. The proceedings are divided into four volumes. This first volume covers the following main topics: Active Components and Vibration Control; Balancing; Bearings: Fluid Film Bearings, Magnetic Bearings, Rolling Bearings and Seals; and Blades, Bladed Systems and Impellers. "

"This book provides readers with a timely snapshot of the potential offered by and challenges posed by signal processing methods in the field of machine diagnostics and condition monitoring. It gathers contributions to the first Workshop on Signal Processing Applied to Rotating Machinery Diagnostics, held in Setif, Algeria, on April 9-10, 2017, and organized by the Applied Precision Mechanics Laboratory (LMPA) at the Institute of Precision Mechanics, University of Setif, Algeria and the Laboratory of Mechanics, Modeling and Manufacturing (LA2MP) at the National School of Engineers of Sfax. The respective chapters highlight research conducted by the two laboratories on the following main topics: noise and vibration in machines; condition monitoring in non-stationary operations; vibro-acoustic diagnosis of machinery; signal processing and pattern recognition methods; monitoring and diagnostic systems; and dynamic modeling and fault detection."