A wavelet-based dynamic mode decomposition for modeling mechanical systems from partial observations

Krishnan, Manu; Gugercin, Serkan; Tarazaga, Pablo A.

doi:10.1016/j.ymssp.2022.109919

Cited by 6 publications

(3 citation statements)

References 66 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Such studies have demonstrated the effectiveness of signal processing-based IDSs in SCADA-based power grids. For example, in [17], the authors proposed a waveletbased IDS for the detection of intrusions into the power grid, which demonstrated high accuracy and low false positive rates. Similarly, in [18], authors developed a Fourier-based IDS for power grid security that achieved high detection rates and low false alarm rates.…”

Section: Background and Literature Reviewmentioning

confidence: 99%

Validation of a Machine Learning-Based IDS Design Framework Using ORNL Datasets for Power System With SCADA

Zaman,

Upadhyay,

Lung

2023

IEEE Access

View full text Add to dashboard Cite

Supervisory Control and Data Acquisition (SCADA) systems are widely used for remote monitoring and control of industrial processes, such as oil and gas production, power generation, transmission and distribution, and water treatment. Despite the enhanced accessibility, control, and data availability afforded by recent advances in communication technologies, the utilization of these technologies exposes critical infrastructures such as power systems to potential cyber threats. A Machine Learning (ML)based Intrusion Detection System (IDS) seems promising; however, the development of ML models often requires custom methodologies for data preprocessing and training. This strategic approach is necessary for creating high-performance models that can be robustly evaluated and seamlessly integrated into real-time systems. As a result, we propose an ML-based IDS design framework for a SCADA-based power system incorporating effective modeling aspects, such as dataset preprocessing to ensure accurate representation, data augmentation for achieving a balanced dataset, automated feature selection to reduce dimensionality, and rigorous model training and testing procedures. To substantiate our proposed design framework, we conducted a series of experiments using a publicly available ORNL (Oak Ridge National Laboratory) dataset for . The evaluation process encompasses efficient validation techniques with unseen data. Furthermore, the augmented dataset emerged through the aggregation of readings from four Phasor Measurement Units (PMUs) collected over a specific time span into a unified dataset. Among the assessed classifiers, the Random Forest (RF) model, trained on an augmented and balanced dataset, outperformed others, yielding an F1 score of 94.09% during testing with unseen data.

show abstract

Section: Background and Literature Reviewmentioning

confidence: 99%

Validation of a Machine Learning-Based IDS Design Framework Using ORNL Datasets for Power System With SCADA

Zaman,

Upadhyay,

Lung

2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…The results show that physically guided convolutional neural network (PGCNN) with rectangular input shape and rectangular convolutional kernel works better than baseline convolutional neural network with higher accuracy and less uncertainty. Manu Krishnan et al [6] proposed a new method for modeling dynamic systems by combining wavelets with input-output dynamic modal decomposition (ioDMD). The experimental results show that the algorithm still performs well under the influence of noise.…”

Section: Introductionmentioning

confidence: 99%

Fault Diagnosis Strategy Based on BOA-ResNet18 Method for Motor Bearing Signals with Simulated Hydrogen Refueling Station Operating Noise

Liu,

Chen,

Chen

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

The harsh working environment of hydrogen refueling stations often causes equipment failure and is vulnerable to mechanical noise during monitoring. This limits the accuracy of equipment monitoring, ultimately decreasing efficiency. To address this issue, this paper presents a motor bearing vibration signal diagnosis method that employs a Bayesian optimization (BOA) residual neural network (ResNet). The industrial noise signal of the hydrogenation station is simulated and then combined with the motor bearing signal. The resulting one-dimensional bearing signal is processed and transformed into a two-dimensional signal using Fast Fourier Transform (FFT). Afterwards, the signal is segmented using the sliding window translation method to enhance the data volume. After comparing signal feature extraction and classification results from various convolutional neural network models, ResNet18 yields the best classification accuracy, achieving a training accuracy of 89.50% with the shortest computation time. Afterwards, the hyperparameters of ResNet18 such as InitialLearnRate, Momentum, and L2Regularization Parameter are optimized using the Bayesian optimization algorithm. The experiment findings demonstrate a diagnostic accuracy of 99.31% for the original signal model, while the accuracy for the bearing signal, with simulated industrial noise from the hydrogenation station, can reach over 92%.

show abstract

“…Some of the projection-based techniques mentioned above (and employed in this paper) have been extended to the structured models we consider here; see, e.g., Ref. [14][15][16][17][18][19] and the references therein for some of the data-driven approaches to structured dynamics. However, this is not our focus in this paper and these considerations are left to future work.…”

Section: Introductionmentioning

confidence: 99%

Application of Interpolatory Methods of Model Reduction to an Elevated Railway Pier

Bertero¹,

Gugercin²,

Sarlo³

2023

Proceedings of the 21th LACCEI International Multi-Conference for Engineering, Education and Technology (LACCEI 2023): “Leaders

View full text Add to dashboard Cite

Be it due to time constraints or insufficient processing power -or a combination of both -the use of models with large numbers of degrees of freedom (DoF) may be unsuitable to provide a client with results in a timely manner. The use of physics-based reduced models -or proxy structures -are popular among practitioners to solve this issue, as they keep intact all the underlying properties of the second order problems at a fraction of the cost. In this paper, interpolatory methods of model reduction are explored as an alternative, and applied to a 3D Space Frame. The methods chosen allow for structure-preserving reduced models and differ mainly on the selection of interpolation points. A comparison between the response of these reduced models and a proxy structure against two different types of inputs show that interpolatory methods are a viable, more flexible option when it comes to reducing the internal DoF's of a structural model, though engineering judgement helps to ensure it adequately captures the most relevant aspects of the response for the specific application.

show abstract

A wavelet-based dynamic mode decomposition for modeling mechanical systems from partial observations

Cited by 6 publications

References 66 publications

Validation of a Machine Learning-Based IDS Design Framework Using ORNL Datasets for Power System With SCADA

Validation of a Machine Learning-Based IDS Design Framework Using ORNL Datasets for Power System With SCADA

Fault Diagnosis Strategy Based on BOA-ResNet18 Method for Motor Bearing Signals with Simulated Hydrogen Refueling Station Operating Noise

Application of Interpolatory Methods of Model Reduction to an Elevated Railway Pier

Contact Info

Product

Resources

About