On etudie l'observation et le controle de l'equation des plaques en utilisant des mesures... more On etudie l'observation et le controle de l'equation des plaques en utilisant des mesures de defaut.
In the present paper, a method of defining the industrial process parameters for a new product us... more In the present paper, a method of defining the industrial process parameters for a new product using machine learning algorithms will be presented. The study will describe how to go from the product characteristics till the prediction of the suitable machine parameters to produce a good quality of this product, and this is based on an historical training dataset of similar products with their respective process parameters. In the first part of our study, we will focus on the ultrasonic welding process definition, welding parameters and on how it operate. While in second part, we present the design and implementation of the prediction models such multiple linear regression, support vector regression, and we compare them to an artificial neural networks algorithm. In the following part, we present a new application of Convolutional Neural Networks (CNN) to the industrial process parameters prediction. In addition, we will propose the generalization approach of our CNN to any predictio...
Dataset generated from running the ant colony system for the multi objective problems using the c... more Dataset generated from running the ant colony system for the multi objective problems using the concept of the collective knowledge center, the four SQL dump files indicate the simulation of the ant colony tackling for a 50 random graphs of size equal respectively to 100, and 300 for the process of learning, and then tackling of the two tsp graph file euclideAB100.tsp and euclideAB300.tsp for evaluating the model performance. The learning process and the feeding of the knowledge center is done through the commitment of 110 ants subdivided into 11 groups of 10 ants. The members of the colony share a set of parameters of the MOACS algorithm, namely local and global evaporation respectively ρ, γ, fixed on the value 0.001, an exploitation value q_0= 0.9, and the maximum number of search cycles is 200 cycles.
On adapte la methode d'unicite hilbertienne au probleme d'elastodynamique et on donne une... more On adapte la methode d'unicite hilbertienne au probleme d'elastodynamique et on donne une condition necessaire et suffisante pour que ce systeme soit exactement controlable
In this article, we present a new approach to construct smoothing approximations for piecewise sm... more In this article, we present a new approach to construct smoothing approximations for piecewise smooth functions. This approach proposes to formulate any piecewise smooth function as the expectation of a random variable. Based on this formulation, we show that smoothing all elements of a defined space of piecewise smooth functions is equivalent to smooth a single probability distribution. Furthermore, we propose to use the Boltzmann distribution as a smoothing approximation for this probability distribution. Moreover, we present the theoretical results, error estimates, and some numerical examples for this new smoothing method in both one-dimensional and multiple-dimensional cases.
The overall equipment effectiveness (OEE) is a performance measurement metric widely used. Its ca... more The overall equipment effectiveness (OEE) is a performance measurement metric widely used. Its calculation provides to the managers the possibility to identify the main losses that reduce the machine effectiveness and then take the necessary decisions in order to improve the situation. However, this calculation is done a-posterior which is often too late. In the present research, we implemented different Machine Learning algorithms namely; Support vector machine, Optimized Support vector Machine (using Genetic Algorithm), Random Forest, XGBoost and Deep Learning to predict the estimate OEE value. The data used to train our models was provided by an automotive cable production industry. The results show that the Deep Learning and Random Forest are more accurate and present better performance for the prediction of the overall equipment effectiveness in our case study.
On etudie la propagation et la reflexion des singularites H* microlocales du probleme d'elast... more On etudie la propagation et la reflexion des singularites H* microlocales du probleme d'elasticite avec une condition de bord libre
In the present paper, a method of defining the industrial process parameters for a new product us... more In the present paper, a method of defining the industrial process parameters for a new product using machine learning algorithms will be presented. The study will describe how to go from a final product characteristics till the prediction of the suitable machine parameters to produce a good quality of this product, and this is based on an historical training data set of similar products with their respective process parameters. In the first part of our study, we will focus on the ultrasonic welding process definition, welding parameters and on how it operates. While in second part, we will present the design and the implementation of the prediction models such as multiple linear regression, support vector regression, and we will compare them to the artificial neural networks algorithm. In the following part, we will present a new application of Convolutionnal Neural Networks (CNN) algorithm to the industrial process parameters prediction. In addition, we will propose the generalizat...
On considere la methode de penalisation pour le probleme de valeurs propres d'une membrane en... more On considere la methode de penalisation pour le probleme de valeurs propres d'une membrane encastree sur le bord. La condition de Dirichlet est remplacee par une condition de troisieme espece (ou de Fourier-Robin). On montre la convergence H 2 des fonctions propres lorsque le parametre de penalisation tend vers l'infini.
Cette these contient une serie de contributions consacrees au controle des problemes de mecanique... more Cette these contient une serie de contributions consacrees au controle des problemes de mecanique des milieux continus. Les problemes : on a d'abord observe que l'etude theorique de beaucoup de problemes de controlabilite exacte se ramenait a la preuve d'estimations a priori sur les solutions des problemes homogenes adjoints. Ces estimations correspondent selon l'intuition a la stabilite de l'observation. Ceci est bien sur un des resultats et ingredients essentiels de la methode d'unicite Hilbertienne Hum due a J. L. Lions (Lio). Bien entendu, la pertinence des equations depend de la taille des parametres caracteristiques du probleme ; l'exemple le plus fondamental dans notre domaine etant l'equation des plaques bidimensionnelles qui est obtenue comme cas limite de l'elasticite tridimensionnelle lorsque l'epaisseur tend vers zero (voir les travaux de Ph. G. Ciarlet et ses collaborateurs pour une etude systematique). Il est alors naturel d'...
We propose in this paper a new document representation in Text Mining based on signal representat... more We propose in this paper a new document representation in Text Mining based on signal representation and spectral processing by Wavelets Transform. Our method gives a solution of syntactic and semantic descriptor dependency problem, without deleting information. This can be done by grouping dependent descriptors in clusters with a single representative. Thereafter each class is represented by a discrete signal giving different degrees of dependence between descriptors, we then take advantage of the Multi Resolution Analysis properties of the Wavelet Transform. We show that we are able to achieve higher precision when compared to Vector Space Model representation and Latent Semantic Analysis in the context of Arabic Text Classification.
The overall equipment effectiveness (OEE) is a performance measurement metric widely used. Its ca... more The overall equipment effectiveness (OEE) is a performance measurement metric widely used. Its calculation provides to the managers the possibility to identify the main losses that reduce the machine effectiveness and then take the necessary decisions in order to improve the situation. However, this calculation is done a-posterior which is often too late. In the present research, we implemented different Machine Learning algorithms namely; Support vector machine, Optimized Support vector Machine (using Genetic Algorithm), Random Forest, XGBoost and Deep Learning to predict the estimate OEE value. The data used to train our models was provided by an automotive cable production industry. The results show that the Deep Learning and Random Forest are more accurate and present better performance for the prediction of the overall equipment effectiveness in our case study.
Machine Learning automatically creates analytical models that adapt to what is in the data. After... more Machine Learning automatically creates analytical models that adapt to what is in the data. After a while, the algorithm is used to deliver accurate results, whether it’s making smarter credit decisions, entering into retail deals, medical diagnostics, or detecting fraud. The use of Deep Learning technology as a new machine learning tool has experienced considerable success in digital image processing in recent years.
On etudie l'observation et le controle de l'equation des plaques en utilisant des mesures... more On etudie l'observation et le controle de l'equation des plaques en utilisant des mesures de defaut.
In the present paper, a method of defining the industrial process parameters for a new product us... more In the present paper, a method of defining the industrial process parameters for a new product using machine learning algorithms will be presented. The study will describe how to go from the product characteristics till the prediction of the suitable machine parameters to produce a good quality of this product, and this is based on an historical training dataset of similar products with their respective process parameters. In the first part of our study, we will focus on the ultrasonic welding process definition, welding parameters and on how it operate. While in second part, we present the design and implementation of the prediction models such multiple linear regression, support vector regression, and we compare them to an artificial neural networks algorithm. In the following part, we present a new application of Convolutional Neural Networks (CNN) to the industrial process parameters prediction. In addition, we will propose the generalization approach of our CNN to any predictio...
Dataset generated from running the ant colony system for the multi objective problems using the c... more Dataset generated from running the ant colony system for the multi objective problems using the concept of the collective knowledge center, the four SQL dump files indicate the simulation of the ant colony tackling for a 50 random graphs of size equal respectively to 100, and 300 for the process of learning, and then tackling of the two tsp graph file euclideAB100.tsp and euclideAB300.tsp for evaluating the model performance. The learning process and the feeding of the knowledge center is done through the commitment of 110 ants subdivided into 11 groups of 10 ants. The members of the colony share a set of parameters of the MOACS algorithm, namely local and global evaporation respectively ρ, γ, fixed on the value 0.001, an exploitation value q_0= 0.9, and the maximum number of search cycles is 200 cycles.
On adapte la methode d'unicite hilbertienne au probleme d'elastodynamique et on donne une... more On adapte la methode d'unicite hilbertienne au probleme d'elastodynamique et on donne une condition necessaire et suffisante pour que ce systeme soit exactement controlable
In this article, we present a new approach to construct smoothing approximations for piecewise sm... more In this article, we present a new approach to construct smoothing approximations for piecewise smooth functions. This approach proposes to formulate any piecewise smooth function as the expectation of a random variable. Based on this formulation, we show that smoothing all elements of a defined space of piecewise smooth functions is equivalent to smooth a single probability distribution. Furthermore, we propose to use the Boltzmann distribution as a smoothing approximation for this probability distribution. Moreover, we present the theoretical results, error estimates, and some numerical examples for this new smoothing method in both one-dimensional and multiple-dimensional cases.
The overall equipment effectiveness (OEE) is a performance measurement metric widely used. Its ca... more The overall equipment effectiveness (OEE) is a performance measurement metric widely used. Its calculation provides to the managers the possibility to identify the main losses that reduce the machine effectiveness and then take the necessary decisions in order to improve the situation. However, this calculation is done a-posterior which is often too late. In the present research, we implemented different Machine Learning algorithms namely; Support vector machine, Optimized Support vector Machine (using Genetic Algorithm), Random Forest, XGBoost and Deep Learning to predict the estimate OEE value. The data used to train our models was provided by an automotive cable production industry. The results show that the Deep Learning and Random Forest are more accurate and present better performance for the prediction of the overall equipment effectiveness in our case study.
On etudie la propagation et la reflexion des singularites H* microlocales du probleme d'elast... more On etudie la propagation et la reflexion des singularites H* microlocales du probleme d'elasticite avec une condition de bord libre
In the present paper, a method of defining the industrial process parameters for a new product us... more In the present paper, a method of defining the industrial process parameters for a new product using machine learning algorithms will be presented. The study will describe how to go from a final product characteristics till the prediction of the suitable machine parameters to produce a good quality of this product, and this is based on an historical training data set of similar products with their respective process parameters. In the first part of our study, we will focus on the ultrasonic welding process definition, welding parameters and on how it operates. While in second part, we will present the design and the implementation of the prediction models such as multiple linear regression, support vector regression, and we will compare them to the artificial neural networks algorithm. In the following part, we will present a new application of Convolutionnal Neural Networks (CNN) algorithm to the industrial process parameters prediction. In addition, we will propose the generalizat...
On considere la methode de penalisation pour le probleme de valeurs propres d'une membrane en... more On considere la methode de penalisation pour le probleme de valeurs propres d'une membrane encastree sur le bord. La condition de Dirichlet est remplacee par une condition de troisieme espece (ou de Fourier-Robin). On montre la convergence H 2 des fonctions propres lorsque le parametre de penalisation tend vers l'infini.
Cette these contient une serie de contributions consacrees au controle des problemes de mecanique... more Cette these contient une serie de contributions consacrees au controle des problemes de mecanique des milieux continus. Les problemes : on a d'abord observe que l'etude theorique de beaucoup de problemes de controlabilite exacte se ramenait a la preuve d'estimations a priori sur les solutions des problemes homogenes adjoints. Ces estimations correspondent selon l'intuition a la stabilite de l'observation. Ceci est bien sur un des resultats et ingredients essentiels de la methode d'unicite Hilbertienne Hum due a J. L. Lions (Lio). Bien entendu, la pertinence des equations depend de la taille des parametres caracteristiques du probleme ; l'exemple le plus fondamental dans notre domaine etant l'equation des plaques bidimensionnelles qui est obtenue comme cas limite de l'elasticite tridimensionnelle lorsque l'epaisseur tend vers zero (voir les travaux de Ph. G. Ciarlet et ses collaborateurs pour une etude systematique). Il est alors naturel d'...
We propose in this paper a new document representation in Text Mining based on signal representat... more We propose in this paper a new document representation in Text Mining based on signal representation and spectral processing by Wavelets Transform. Our method gives a solution of syntactic and semantic descriptor dependency problem, without deleting information. This can be done by grouping dependent descriptors in clusters with a single representative. Thereafter each class is represented by a discrete signal giving different degrees of dependence between descriptors, we then take advantage of the Multi Resolution Analysis properties of the Wavelet Transform. We show that we are able to achieve higher precision when compared to Vector Space Model representation and Latent Semantic Analysis in the context of Arabic Text Classification.
The overall equipment effectiveness (OEE) is a performance measurement metric widely used. Its ca... more The overall equipment effectiveness (OEE) is a performance measurement metric widely used. Its calculation provides to the managers the possibility to identify the main losses that reduce the machine effectiveness and then take the necessary decisions in order to improve the situation. However, this calculation is done a-posterior which is often too late. In the present research, we implemented different Machine Learning algorithms namely; Support vector machine, Optimized Support vector Machine (using Genetic Algorithm), Random Forest, XGBoost and Deep Learning to predict the estimate OEE value. The data used to train our models was provided by an automotive cable production industry. The results show that the Deep Learning and Random Forest are more accurate and present better performance for the prediction of the overall equipment effectiveness in our case study.
Machine Learning automatically creates analytical models that adapt to what is in the data. After... more Machine Learning automatically creates analytical models that adapt to what is in the data. After a while, the algorithm is used to deliver accurate results, whether it’s making smarter credit decisions, entering into retail deals, medical diagnostics, or detecting fraud. The use of Deep Learning technology as a new machine learning tool has experienced considerable success in digital image processing in recent years.
Uploads