Among the levers carried in the era of Industry 4.0, there is that of using Artificial Intelligence models to serve the energy interests of industrial companies. The aim of this paper is to estimate the active electrical power generated by industrial units that self-produce electricity. To do this, we conduct a case study of the historical data of the variables influencing this parameter to support the construction of three analytical models three analytical models based on Deep Learning algorithms, which are Long Short-Term Memory (LSTM), Convolutional Neural Network (CNN), as well as the hybrid CNN algorithm coupled with LSTM (CNN-LSTM). Subsequently, and thanks to the evaluation of the created models through three mathematical metrics which are Root Mean Square Error (RMSE), Mean Square Error (MSE), and the variance score (R-squared), we were able to make a comparative study between these models. According to the results of this comparison, we attested that the hybrid model is the one that gives the best prediction results, with the following findings: the variance score was about 98.29%, the value of RMSE was exactly 0.1199 MW, and for MSE the error was equal to 0.0143 MW. The obtained results confirm the reliability of the hybrid model, which can help industrial managers save energy by acting upstream of the process parameters influencing the target variable and avoiding substantial energy bills.

The implementation of energy savings strategies has become a necessity and improving the performance of industrial facilities is no longer a prestige, it has now become mandatory for all industrial companies. This paper includes a critical analysis and energy management problems in a typical pumping station, which usually causes excessive energy consumption. Based on the results of energy auditing and energy performance of the most energy-consuming equipment an approach has been developed, which achieves optimal combination to answer such a water demand, while taking into account having optimal flow, minimum consumption and with maximum efficiency. The results showed that this pumping station consumed a monthly average electrical energy of 15 422MWh and having a potential to save 1 313MWh of energy, a 8.30% electrical energy saving potential. The benefits of implementing the energy efficiency measures related to electricity and water are substantial both in terms of energy savings and in terms of cost savings.

The reversed magnetic shear is the most important factor in the study of the plasmas of a tokamak. In this paper we focus our research, as a first stage, on the control of the improved confinement regimes by studying the influence of the reversed shear on its quality in the plasma of a tokamak and especially in reducing the anomalous transport in ITER. Then we study the influence of the perturbation modes on the particle diffusion. At the end, a comparison between simulation results obtained using ITER and TEXT parameters is carried out.

Global gyrokinetic Vlasov simulations for trapped ion modes indicate that the ion temperature gradient (ITG) instability saturates via nonlinear toroidal coupling. Trapped Ion modes were studied by solving a Vlasov equation averaged over the cyclotron and bounce motion of trapped ions. The distribution function, for trapped ions, is then calculated in a two-dimensional phase space, parametrized by two adiabatic invariants, the longitudinal action and the magnetic moment, in presence of a magnetic shear. Our model can be viewed as a kinetic version of the standard one-field Hasegawa-Mima-type and a broad frequency spectrum can originate from model for trapped-ion driven turbulence. Some interesting new features, which appear in the nonlinear regime of the instability, are then discussed.

This paper presents potential energy savings by installing high-efficiency motors instead of existing ones and their impact on greenhouse gases emissions reductions. This research study of the energy efficiency of electric motors has been performed in a typical thermal power plant. In the literature, the focus has been mainly on separate and away electric motors from operating facilities. The important advantage of this paper over other studies is that it uses the actual motors’ efficiency in the evaluation. The gains both in terms of electrical energy savings and in terms of financial economy by using high-efficiency motors have been discussed. As a result, the energy saving can be expected as 12.6% at the operating rate. This excellent result also reduces greenhouse gas emission by 1,423 tons every year. The analysis of the data provided an overview on energy losses often generated by the degradation and rewinding of electrical motors. This study represents very encouraging results that will help energy managers of industrial plants to become more involved in energy efficiency strategies.

This article proposes a methodology to improve the magneto-electric effect of a poly(vinylidene fluoride-co-trifluoroethylene) P(VDF-TrFe) copolymer, doped with nanoparticles of nickel (Ni) and nickel iron (NiFe). The preparation of the composite films were achieved through the solvent casting approach. First, P(VDF-TrFe) powders and (Ni and NiFe) nanoparticles are dispersed in dimethyl formamide (DMF) as a solvent to form a homogeneous solution. Then, the solution obtained is deposited on a flexible substrate by a spin coating process. After that, the NiFe doped composites are corona polarized, to improve the magneto-electric response of these composites. The purpose of this work is to investigate the influence of the magnetic charges added in the P(VDF-TrFe) copolymer, and to reveal the effect of corona charging (polarization) on the magneto-electric behavior of the used composites. The obtained results in this article show that both the doping and the electric polarization (piezo coefficient) significantly affect the generated alternating current during the application of an alternating magnetic field. However, the magneto-electric response of composites increases by doping and charging via corona poling effect and also by increasing the excitation frequency and the magnetic field amplitude. In addition, the magneto-electric responses of all composites after corona polarization were also discussed. This indicates that the magneto-electric coefficient and the current can be increased with polarized composites. A good response is observed for P(VDF-TrFe) + 3% Ni with a piezoelectric coefficient d33 = 21.2 (pC/N)