Predicting octane numbers relying on principal component analysis and artificial neural network

Tipler, Steven; D’Alessio, Giuseppe; Haute, Quentin Van; Parente, Alessandro; Contino, Francesco; Coussement, Axel

doi:10.1016/j.compchemeng.2022.107784

Cited by 13 publications

(8 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…When LPCA is used for dimensionality reduction, different strategies are available to choose a priori the optimal number of eigenvectors to be retained, i.e., to discard only the redundant information and/or the noise in the dataset. The aforementioned strategies include evaluating the explained variance in each cluster (i.e., the ratio between the cumulative sum of the eigenvalues and their sum), or the concurrent evaluation of the singular values and the dimensionality of the input matrix [42,43]. Nevertheless, when LPCA is employed for clustering, there are no available methods to choose this parameter a priori other than user expertise, and the same holds for the number of clusters, k. Moreover, as also shown in Fig.…”

Section: Clustering Via Local Principal Component Analysismentioning

confidence: 99%

Automated adaptive chemistry for Large Eddy Simulations of turbulent reacting flows

Amaduzzi,

D’Alessio,

Pagani

et al. 2024

Combustion and Flame

View full text Add to dashboard Cite

Section: Clustering Via Local Principal Component Analysismentioning

confidence: 99%

Automated adaptive chemistry for Large Eddy Simulations of turbulent reacting flows

Amaduzzi,

D’Alessio,

Pagani

et al. 2024

Combustion and Flame

View full text Add to dashboard Cite

“…A principal component analysis (PCA) is an unsupervised learning method of feature extraction and dimensional reduction (moving p-dimensional data to a lower-dimensional m-dimensional linear subspace), retaining the original features of the data and selecting their key properties [42,[51][52][53]. It analyses a data table in which observations are described by several intercorrelated quantitative dependent variables and is widely used due to its ability to extract interpretable information by efficiently removing redundancies [54,55].…”

Section: Background 21 Principal Component Analysis (Pca)mentioning

confidence: 99%

Predicting the Health Status of a Pulp Press Based on Deep Neural Networks and Hidden Markov Models

et al. 2023

View full text Add to dashboard Cite

The maintenance paradigm has evolved over the last few years and companies that want to remain competitive in the market need to provide condition-based maintenance (CBM). The diagnosis and prognosis of the health status of equipment, predictive maintenance (PdM), are fundamental strategies to perform informed maintenance, increasing the company’s profit. This article aims to present a diagnosis and prognosis methodology using a hidden Markov model (HMM) classifier to recognise the equipment status in real time and a deep neural network (DNN), specifically a gated recurrent unit (GRU), to determine this same status in a future of one week. The data collected by the sensors go through several phases, starting by cleaning them. After that, temporal windows are created in order to generate statistical features of the time domain to better understand the equipment’s behaviour. These features go through a normalisation to produce inputs for a feature extraction process, via a principal component analysis (PCA). After the dimensional reduction and obtaining new features with more information, a clustering is performed by the K-means algorithm, in order to group similar data. These clusters enter the HMM classifier as observable states. After training using the Baum–Welch algorithm, the Viterbi algorithm is used to find the best path of hidden states that represent the diagnosis of the equipment, containing three states: state 1—“State of Good Operation”; state 2—“Warning State”; state 3—“Failure State”. Once the equipment diagnosis is complete, the GRU model is used to predict the future, both of the observable states as well as the hidden states coming out from the HMM. Thus, through this network, it is possible to directly obtain the health states 7 days ahead, without the necessity to run the whole methodology from scratch.

show abstract

“…In literature, it is possible to find many applications exploiting PCA to speed-up computational fluid dynamics (CFD) simulations of reacting systems by reducing the number of the differential equations to be solved for combustion or atmospheric re-entry applications [7][8][9][10]. In addition, the algorithm and its local formulation were recently validated for clustering in chemical kinetics applications [11,12], for data analysis of Direct Numerical Simulation (DNS) of reacting jets [13,14], and for feature extraction and selection to enhance the classification and regression accuracy of Artificial Neural Networks (ANN) [15,16].…”

Section: Introductionmentioning

confidence: 99%

Hierarchical Higher-Order Dynamic Mode Decomposition for Clustering and Feature Selection

Corrochano¹,

D’Alessio²,

Parente³

et al. 2023

Preprint

View full text Add to dashboard Cite

In this work, a new algorithm based on the application of higher-order dynamic mode decomposition (HODMD) is proposed for feature selection and variables clustering in reacting flow simulations. The hierarchical HODMD (h-HODMD) performs a reduction of the model order, followed by the iterative selection of the best reconstructed variables thus creating clusters of features which can eventually be associated with distinct dynamical phenomena. Firstly, h-HODMD is combined with different data pre-processing techniques to assess their influence on the algorithm in terms of reconstruction error. Afterwards, the proposed algorithm is applied to analyze three different databases obtained from numerical simulations of a non-premixed co-flow methane flame, and its performance are compared with the standard HODMD in terms of the achievable degree of reduction as well as in terms of reconstruction error. Two detailed kinetic mechanisms are used for the simulations, and different time horizons are considered to assess the influence of the number of considered cycles on the accuracy of the reduced model. Results show that h-HODMD improves the reconstruction for all the variables when compared to the standard HODMD algorithm. This condition is achieved thanks to the iterative variables' clustering: finding dedicated modes for a specific group of features does in fact lead to a better reconstruction of the dynamics with respect to the case when the same (global) modes are used to reconstruct the entire set of variables.Finally, the clusters of variables found by means of h-HODMD are analyzed, and it is observed that the algorithm can group, in an unsupervised fashion, chemical species whose behavior is also consistent from a kinetic point of view. In fact, radicals responsible for fast chemistry processes (such as propagation and branching reactions) are grouped together, and the same happens for nitrogen oxides (whose chemical timescales are instead order of magnitudes slower). The possibility to identify and to describe correctly the main dynamics with reduced order models for these two classes of chemical species is extremely important for practical applications in combustion. In fact, it allows for the possibility to formulate inexpensive reduced dynamical models for predicting flames liftoff, as well as for identifying the formation of local extinction and blowout conditions, to formulate accurate reduced models to describe the formation of pollutants in aviation, and for control purposes.

show abstract

Predicting octane numbers relying on principal component analysis and artificial neural network

Cited by 13 publications

References 24 publications

Automated adaptive chemistry for Large Eddy Simulations of turbulent reacting flows

Automated adaptive chemistry for Large Eddy Simulations of turbulent reacting flows

Predicting the Health Status of a Pulp Press Based on Deep Neural Networks and Hidden Markov Models

Hierarchical Higher-Order Dynamic Mode Decomposition for Clustering and Feature Selection

Contact Info

Product

Resources

About