Search

Our investigation within the framework of this study is carried out on three marine species fished off in Moroccan coasts namely: a fish, the sole (Solea Vulgaris), a cephalopod, the cuttlefish (Sepia Officinalis) and a crustacean, the pink shrimp (Parapenaeus Longirostris). The aims of this study is to assess the level of concentration in these three marine species, of three metallic trace elements: Lead (Pb), Cadmium (Cd) and Mercury (Hg) and giving a reflection on the way in which Moroccan deep-sea fishing professionals can join a food safety management system to ensure the safety of their product and promote their competitiveness. Sampling is carried out at the port of Agadir city after landing of the deep-sea fishing boats which operate beyond 10 nautical miles, offshoring the seabed of Agadir for pink shrimp (Parapenaeus Longirostris), and in Dakhla city offshore for sole (Solea Vulgaris) and cuttlefish (Sepia Officinalis). Trace metal analysis were performed on individual muscles belonging to the three species. The results of our investigations show that the Pb content varies between 0.01 ppm and 0.27 ppm in Solea Vulgaris; between 0.015 ppm and 0.16 ppm in Sepia Officinalis and between 0.022 ppm and 0.38 ppm for Parapenaeus Longirostris. For the Cd, the concentrations vary between 0.0047 ppm and 0.050 ppm in Solea Vulgaris; between 0.0025 ppm and 0.254 ppm in Sepia Officinalis and between 0.0065 ppm and 0.11 ppm in Parapenaeus Longirostris. Concerning Hg, the contents vary between 0.0006 ppm and 0.075 ppm in Solea Vulgaris; between 0.0008 ppm and 0.05 ppm in Sepia Officinalis and between 0.0016 ppm and 0.09 ppm in Parapenaeus Longirostris. It appears from this study that the metal contents detected at the level of the three species of seafood investigated are below the regulatory thresholds. These results can be considered as the first basis for validating the control measure linked to the absence of metallic contamination of the three species in the sites studied.

Downtimes due to ice formation on rotor blades reduce the economic efficiency of wind turbines. An accurate ice prediction is required to operate active de-icing measures such as blade heating as an anti-icing system. Building upon our previous research, this paper proposes the use of a convolutional neural network model with dual inputs and one-dimensional convolution filters using historical data from the wind turbine as well as weather forecasts to predict the ice situation for the next 24 hours. The model is validated using data from three different wind farms and shows an average balanced accuracy of 97.9%.

In the era of digitalization, electronic Kanban (e-Kanban) extends the traditional Kanban with additional data and information sharing that allows for more flexible and optimized inventory planning. The lack of automated fill level measurements for load carriers still hinders the full automation of the process. Our aim is to develop a self-learning e-Kanban system that automatically triggers replenishment orders using machine learning and data from low cost, autonomous sensor modules that measure the fill level of load carriers. This paper explains the concept and presents a first version of the mentioned sensor module that consists of an Intel Realsense sensor and an NVIDIA Jetson Nano. An evaluation is presented as well using small load carriers, which shows the suitability of the proposed method.

Ice formation on rotor blades of wind turbines cause significant downtimes in cold regions. Existing ice sensors can detect, but cannot predict ice. Therefore, our research aims to develop an ice prediction system based on historical and forecasted data. In a first step, the detection process is analyzed in this research paper. Two machine learning models are trained using minimalistic input parameters. A full-factorial experiment design is performed for the models, using the fl-score as the response variable. The most significant input parameter was the external temperature for both models.

Ice formed on wind turbines not only causes economic damage but also poses a risk to nearby humans. Countermeasuring ice formation requires reliable detection systems. Existing ice detection solutions have improved with time, but are still not sufficiently accurate. This paper investigates the use of different convolutional neural networks (CNNs) and RGB images taken from cameras installed on the nacelle of wind turbines to detect ice on the rotor blades. In our research, the VGG19 model achieved the best performance with an accuracy and an f1-score of (96 ± 2) %.

In cold regions like Northern Europe or Northern America, formation of ice on wind turbines not only reduces the power output of the system, but also leads to wind turbine breakdowns and poses a risk to nearby vehicles and people. Economical solutions for anti-icing systems such as preventive heating are required. Purely meteorological icing predictions are not sufficient to accurately predict icing on wind turbines. Therefore, this paper proposes an icing prediction approach that uses historical weather data and data from a supervisory control and data acquisition (SCADA) system plus methods from supervised machine learning to predict the risk of icing. The first results of the prediction model show its capability to predict most of the icing events. The discussion shows that the model should consider more meteorological data that describe the icing risk such as humidity or liquid water content to achieve better prediction results. The final aim is a prediction system that will use real-time data to determine icing risks hours beforehand, allowing the operation of existing anti-icing systems more efficiently.

This present contribution examines by means of a discrete event and agent-based simulation the potential of a joint use of resources in the installation phase of offshore wind energy. To this end, wind farm projects to be installed simultaneously are being examined, the impact of weather restrictions on the processes of loading, transport and installation are also taken into consideration, and both the wind farm specific resource allocation and the approach of a resource pool or resource sharing, respectively, are being implemented. This study is motivated by the large number of wind farms that will be installed in the future and by the potential savings that might be realized through resource sharing. While, so far, the main driver of the resource sharing approach has been the end consumer market, it has been applied in more and more areas, even in relatively conservative industries such as logistics. After the presentation of the backgrounds and of the underlying methodology, and the description of the prior art in this context, the network of the offshore wind energy installation phase will be described. This is the basis for the subsequent determination of the savings potential of a shared resource utilization, which is determined by the performance indicators such as the total installation time and degree of utilization of the resources. The results of the simulation show that weather restrictions have a significant effect on the installation times and the usage times of the resources as well as on their degree of utilization. In addition, the resource sharing approach, has been identified to have significant savings potential for the offshore wind energy installation.

The costs of the installation phase of the production system offshore wind energy plant have a considerable influence on the electricity production costs. For this reason, there are efforts undertaken to reduce the installation costs. The resources (e.g. installation vessels) and information (e.g. weather forecasts) play a vital role in the logistics installation network. This paper investigates the potential of a shared use of resources and the sharing of different information in the installation phase of the offshore wind energy by means of an event discrete, agent-based simulation. This is motivated by the large number of wind parks still to be installed in the future. To this end, simultaneously installed wind farm projects are examined and the effects of exchange of different information are investigated. The impact of weather restrictions on the processes of loading, transport and installation is taken into consideration. By means of the resource and information sharing approaches, significant savings potential was identified for the offshore wind energy installation.

Demand forecasting of fashion apparel products has to cope with serious difficulties in order to get more accurate forecasts early enough to influence production decisions. Demand has to be anticipated at an early date due to long production lead times. Due to the absence of historical sales data for new products, standard statistical forecasting methods, like, e.g., regression, cannot easily be applied. This contribution applies selected methods into improve forecasting customer demand of fashion or seasonal apparel products. We propose a model which uses retailer pre-orders of seasonal apparel articles before the start of their production to estimate later, additional post-orders of the same articles during the actual sales periods. This allows forecasting of total customer demand based on the pre-orders. The results show that under certain circumstances it is possible to find correlations between the pre-orders and post-orders of those articles, and thus better estimate total demand. The model contributes to the improvement of production volumes of apparel articles, and thus can help reduce article stock-outs or unwanted surpluses.

The aim of this study was to assess aquatic environmental quality of Oued Souss (Agadir, Morocco). This estuary has been subjected for a long time to large amounts of sewage discharges and industrial effluents. Since November 2002, no waste outlets have been discharged in this site due to their connection to a wastewater purification plant. Firstly, we have compared metal tolerance of the annelid polychaete (Nereis diversicolor) originating from Oued Souss and a relatively clean site (Oualidia, Morocco). Secondly, we have evaluated with a multi-marker approach (acetylcholinesterase [AChE], glutathione-S-transferases [GSTs], catalase, thiobarbituric acid reactive substances [TBARs]) responses of worms to the pollution gradient. Results have shown that worms from Oued Souss have acquired tolerance to copper and zinc due to a long-term sub-lethal metal exposure and this metal tolerance was maintained in spite of the end of wastewater discharges in this site. Higher catalase, GSTs and TBARs values have been observed in worms from Oued Souss sampled before implantation of wastewater treatment. The multi-marker approach confirms that these worms have been submitted to various contaminants. In contrast, high inhibition in AChE activities measured in worms from Oued Souss could be explained by the continuous agricultural influence of nearest areas. The level of contamination was probably maintained since biomarker values were generally higher in worms from Oued Souss when compared to Oualidia.

During the functioning period of a sand filter, 254 and 234 faecal-coliform strains were isolated from raw wastewater and reclaimed effluent, respectively. When tested for their susceptibility to ampicillin, kanamycin, chloramphenicol, streptomycin and tetracycline, 53% of the strains from the raw sewage and 84% of those isolated from the effluent were resistant to at least one antibiotic. The high incidence of drug resistance in the effluent was connected with a high proportion of Klebsiella pneumoniae, Enterobacter cloacae and Citrobacter freundii.

Most fault detection systems (FDS) have proved their efficiency in the detection of anomalies and disruptions in technical systems. However, the detection of these anomalies and disruptions is time consuming and not applicable to real-time applications. Moreover many technical systems like e.g. machines and plants require a real-time decision support for emergency shutdowns in order to enable human machine interactions and avoid cost-intensive machine breakdowns. Thereby, anomalies and system changes have to be detected in a fast and secure way. In this context, conventional FDS are not designed for real-time control of sensor networks. Such networks continuously generate a large volume of data and are vulnerable for sensor failures. Therefore, it is a challenging task to derive appropriate information and analyze them in real time. In this paper we propose an event-driven fault detection systems (ED-FDS) using complex event processing (CEP) approach, which provides a robust detection mechanism for severe machine failures in real-time. The idea of ED-FDS is based on discretization of continuous sensor signals by applying an event scheme for sensor data changes. The event scheme includes several event rules, which are generated by applying of data mining methods. Thereby, relevant features are extracted and uncommon behavior of the system is described by event rules. One emphasis of the paper is the combination of different basic events to complex events in a way that different warning levels can be processed. The evaluation of the proposed system is performed on a test-bed demonstrator, which allows the tuning of different disruptions.