Oussama Djedidi

Bio: Oussama Djedidi is an academic researcher from Aix-Marseille University. The author has contributed to research in topics: Redundancy (engineering) & System on a chip. The author has an hindex of 3, co-authored 9 publications receiving 21 citations. Previous affiliations of Oussama Djedidi include University of the South, Toulon-Var & Centre national de la recherche scientifique.

Accurate detection and discrimination of pollutant gases using a temperature modulated MOX sensor combined with feature extraction and support vector classification

Abstract: Gas detection and discrimination have been, until recently, sensors-specific, with different sensors and techniques used for each of the gases. In this work, we describe a novel approach relying on a single physical sensor in conjunction with data-driven algorithms for detecting the presence of one of the three dangerous gases: CO, NO 2 , and O 3 individually or in mixtures. The approach uses a single Metal Oxide (MOX) sensor coupled with two heaters in its hardware part. Then, its software part uses a supervised machine learning model. The sensor is exposed to the different gases and their mixtures and would react accordingly with a change in its electric signals. These raw signals, along with the readings from the heaters, constitute the primary dataset for the discrimination. To further enhance the classification results, the raw dataset is augmented by calculating several time-domain features of each of the measurements. Then, the features are ranked, and the ones with the best results to solve the classification problem are selected. Once the pretreatment of the data is finished, the selected features are used to train and validate a multi-Support Vector Machine model. Finally, the results showcased in this paper highlight the effectiveness of the proposed approach.

A temporal-based SVM approach for the detection and identification of pollutant gases in a gas mixture

Abstract: Air toxicity and pollution phenomena are on the rise across the planet. Thus, the detection and control of gas pollution are nowadays major economic and environmental challenges. There exists a wide variety of sensors that can detect gas pollution events. However, they are either gas-specific or weak in the presence of gas mixtures. This paper handles this issue by presenting method based on a Temporal-based Support Vector Machine for for the detection and identification of several toxic gases in a gas mixture. The considered gases are carbon monoxide (CO), ozone (O3) and nitrogen dioxide (NO2). Furthermore, an incremental algorithm is proposed in this paper for the selection of the best performing kernel function in terms of accuracy and simplicity of implementation. Then, a decision-making algorithm based on the rate of appearance of a class on a moving window is proposed to improve decision making in presence of uncertainties. This algorithm allows the user to master the false-alarms and no-detection dilemma, and quantify the level of confidence attributed to the decision. Experimental results, obtained with different gas mixtures, show the effectiveness of the proposed approach with 100% of accuracy in the learning and testing stages.

Failure Prognosis Based on Relevant Measurements Identification and Data-Driven Trend-Modeling: Application to a Fuel Cell System

Abstract: Fuel cells are key elements in the transition to clean energy thanks to their neutral carbon footprint, as well as their great capacity for the generation of electrical energy by oxidizing hydrogen. However, these cells operate under straining conditions of temperature and humidity that favor degradation processes. Furthermore, the presence of hydrogen—a highly flammable gas—renders the assessment of their degradations and failures crucial to the safety of their use. This paper deals with the combination of physical knowledge and data analysis for the identification of health indices (HIs) that carry information on the degradation process of fuel cells. Then, a failure prognosis method is achieved through the trend modeling of the identified HI using a data-driven and updatable state model. Finally, the remaining useful life is predicted through the calculation of the times of crossing of the predicted HI and the failure threshold. The trend model is updated when the estimation error between the predicted and measured values of the HI surpasses a predefined threshold to guarantee the adaptation of the prediction to changes in the operating conditions of the system. The effectiveness of the proposed approach is demonstrated by evaluating the obtained experimental results with prognosis performance analysis techniques.

Modélisation Incrémentale des Processeurs Embarqués pour l'Estimation des Caractéristiques et le Diagnostic

Abstract: Les systemes-sur-puce (Systems on Chip, SoC) sont de plus en plus embarques dans des systemes a risque comme les systemes aeronautiques et les equipements de production d’energie. Cette evolution technologique permet un gain de temps et de performance, mais presente des limites en termes de fiabilite et de securite. Ainsi, le developpement d’outils de surveillance et de diagnostic des systemes electroniques embarques, en particuliers les SoC, est devenu l’un des verrous scientifiques a lever pour assurer une large utilisation de ces systemes dans les equipements a risque en toute securite. Ce travail de these s’inscrit dans ce contexte, et a pour objectif le developpement d’une approche de detection et identification des derives des performances des SoC embarques. L’approche proposee est basee sur un modele incremental, construit a partir de modules reutilisables et echangeables pour correspondre a la large gamme de SoC existants sur le marche. Le modele est ensuite utilise pour estimer un ensemble de caracteristiques relatives a l’etat de fonctionnement du SoC. L’algorithme de diagnostic developpe dans ce travail consiste a generer des indices de derives par la comparaison en ligne des caracteristiques estimees a celles mesurees. L’evaluation des residus et la prise de decision sont realisees par des methodes statistiques appropriees a la nature de chaque indice de derive. L’approche developpee a ete validee experimentalement sur des SoC differents, ainsi que sur un demonstrateur developpe dans le cadre de ce travail. Les resultats experimentaux obtenus, montrent l’efficacite et la robustesse de l’approche developpee

Real-time sensors for indoor air monitoring and challenges ahead in deploying them to urban buildings

Abstract: Household air pollution is ranked the 9th largest Global Burden of Disease risk (Forouzanfar et al., The Lancet 2015). People, particularly urban dwellers, typically spend over 90% of their daily time indoors, where levels of air pollution often surpass those of outdoor environments. Indoor air quality (IAQ) standards and approaches for assessment and control of indoor air require measurements of pollutant concentrations and thermal comfort using conventional instruments. However, the outcomes of such measurements are usually averages over long integrated time periods, which become available after the exposure has already occurred. Moreover, conventional monitoring is generally incapable of addressing temporal and spatial heterogeneity of indoor air pollution, or providing information on peak exposures that occur when specific indoor sources are in operation. This article provides a review of the new air pollution sensing methods to determine IAQ and discusses how real-time sensing could bring a paradigm shift in controlling the concentration of key air pollutants in billions of urban houses worldwide. However, we also show that besides the opportunities, challenges still remain in terms of maturing technologies, or data mining and their interpretation. Moreover, we discuss further research and essential development needed to close gaps between what is available today and needed tomorrow. In particular, we demonstrate that awareness of IAQ risks and availability of appropriate regulation are lagging behind the technologies.

Accurate detection and discrimination of pollutant gases using a temperature modulated MOX sensor combined with feature extraction and support vector classification

Abstract: Gas detection and discrimination have been, until recently, sensors-specific, with different sensors and techniques used for each of the gases. In this work, we describe a novel approach relying on a single physical sensor in conjunction with data-driven algorithms for detecting the presence of one of the three dangerous gases: CO, NO 2 , and O 3 individually or in mixtures. The approach uses a single Metal Oxide (MOX) sensor coupled with two heaters in its hardware part. Then, its software part uses a supervised machine learning model. The sensor is exposed to the different gases and their mixtures and would react accordingly with a change in its electric signals. These raw signals, along with the readings from the heaters, constitute the primary dataset for the discrimination. To further enhance the classification results, the raw dataset is augmented by calculating several time-domain features of each of the measurements. Then, the features are ranked, and the ones with the best results to solve the classification problem are selected. Once the pretreatment of the data is finished, the selected features are used to train and validate a multi-Support Vector Machine model. Finally, the results showcased in this paper highlight the effectiveness of the proposed approach.

Multi-Sensor Fusion by CWT-PARAFAC-IPSO-SVM for Intelligent Mechanical Fault Diagnosis

Abstract: A new method of multi-sensor signal analysis for fault diagnosis of centrifugal pump based on parallel factor analysis (PARAFAC) and support vector machine (SVM) is proposed. The single-channel vibration signal is analyzed by Continuous Wavelet Transform (CWT) to construct the time–frequency representation. The multiple time–frequency data are used to construct the three-dimension data matrix. The 3-level PARAFAC method is proposed to decompose the data matrix to obtain the six features, which are the time domain signal (mode 3) and frequency domain signal (mode 2) of each level within the three-level PARAFAC. The eighteen features from three direction vibration signals are used to test the data processing capability of the algorithm models by the comparison among the CWT-PARAFAC-IPSO-SVM, WPA-PSO-SVM, WPA-IPSO-SVM, and CWT-PARAFAC-PSO-SVM. The results show that the multi-channel three-level data decomposition with PARAFAC has better performance than WPT. The improved particle swarm optimization (IPSO) has a great improvement in the complexity of the optimization structure and running time compared to the conventional particle swarm optimization (PSO.) It verifies that the proposed CWT-PARAFAC-IPSO-SVM is the most optimal hybrid algorithm. Further, it is characteristic of its robust and reliable superiority to process the multiple sources of big data in continuous condition monitoring in the large-scale mechanical system.

A Review on the Lifecycle Strategies Enhancing Remanufacturing

Abstract: Remanufacturing is a domain that has increasingly been exploited during recent years due to its numerous advantages and the increasing need for society to promote a circular economy leading to sustainability. Remanufacturing is one of the main end-of-life (EoL) options that can lead to a circular economy. There is therefore a strong need to prioritize this option over other available options at the end-of-life stage of a product because it is the only recovery option that maintains the same quality as that of a new product. This review focuses on the different lifecycle strategies that can help improve remanufacturing; in other words, the various strategies prior to, during or after the end-of-life of a product that can increase the chances of that product being remanufactured rather than being recycled or disposed of after its end-of-use. The emergence of the fourth industrial revolution, also known as industry 4.0 (I4.0), will help enhance data acquisition and sharing between different stages in the supply chain, as well boost smart remanufacturing techniques. This review examines how strategies like design for remanufacturing (DfRem), remaining useful life (RUL), product service system (PSS), closed-loop supply chain (CLSC), smart remanufacturing, EoL product collection and reverse logistics (RL) can enhance remanufacturing. We should bear in mind that not all products can be remanufactured, so other options are also considered. This review mainly focuses on products that can be remanufactured. For this review, we used 181 research papers from three databases; Science Direct, Web of Science and Scopus.