Application of an Artificial Neural Network Method for the Prediction of the Tube-Side Fouling Resistance in a Shell-And-Tube Heat Exchanger

The accumulation of undesirable deposits on the heat exchange surface represents a critical issue in industrial heat exchangers.Taking experimental measurements of the fouling is relatively difficult and,often,this method does not lead to precise results.To overcome these problems,in the present study,a new approach based on an Artificial Neural Network(ANN)is used to predict the fouling resistance as a function of specific measurable variables in the phosphoric acid concentration process.These include:the phosphoric acid inlet and outlet temperatures,the steam temperature,the phosphoric acid density,the phosphoric acid volume flow rate circulating in the loop.Some statistical accuracy indices are employed simultaneously to justify the interrelation between these independent variables and the fouling resistance and to select the best training algorithm allowing the determination of the optimal number of hidden neurons.In particular,the BFGS quasi-Newton back-propagation approach is found to be the most performing of the considered training algorithms.Furthermore,the best topology ANN for the shell and tube heat exchanger is obtained with a network consisting of one hidden layer with 13 neurons using a tangent sigmoid transfer function for the hidden and output layers.This model predicts the experimental values of the fouling resistance with AARD%=0.065,MSE=2.168×10^(−11),RMSE=4.656×10^(−6)and r^(2)=0.994.

An Investigation of Thermomechanical Behavior of Tunisian Luffa Sponges’ Fibers

This work is realized in the context of valorizing natural and local resources, in particular, luffa plant fruit (luffa sponge). The raw fibers of the luffa sponge have a short lifetime. Hence, when they are chemically treated, it constitutes a solution is prepared to limit their degradation in the long term and to improve their mechanical characteristics. Therefore, this paper studies the effect of the chemical treatment on the mechanical properties of the luffa sponge’s fibers (fibers of luffa Sponge). The chemical process consists of dipping a brunch of luffa in various concentrations of sodium hydroxide (NaOH) at different time intervals and at different temperature conditions. The luffa sponge’s fibers were mechanical. Characterized before and after the treatment, mechanically (micro traction test). It has been shown that an optimum of 61% increase in mechanical properties (tensile strength) has been reached in the following conditions: treatment with 1% concentration for 90 min at 50°C.

Characterization of Nano-Silica Local Metakaolin Based-Geopolymer: Microstructure and Mechanical Properties

The current study focused on the utilization of local clay for synthesis and characterization of meta-kaolin based geopolymers with and without nano-silica. The control geopolymers, for a compressive strength of 30 MPa, were optimized by using Liquid/Solid ratio of 0.55, NaOH concentration of 10 M and curing at 80°C. The nano silica was added in an extended range of 1%, 2%, 3%, 5%, 7% and 10%. The synthesized nano-silica metakaolin based geopolymers was investigated by using compressive strength, XRD, XRF, FTIR, SEM, MIP, TG, UV/VIS spectroscopy, in addition to density, water absorption and initial setting times. The results indicated an increase in the compressive strength value with the incorporation of nano-silica in geopolymer mixes until the optimum percentage of 5%, while the 10% addition of nano-silica decreased the compressive strength by 5% as compared to the control geopolymer. The increase in the compressive strength was accredited to the increase in the content of N-A-S-H gel and the amorphous structure as shown by XRD and FTIR analysis. In addition, the optical transmittance analysis, MIP and SEM scans along with the results of density and water absorption have clearly shown the densification of the matrix formed for the optimal percentage of nano-silica. However, the initial setting time was found to reduce substantially with increase of nano-silica content. Moreover, the TG results have shown the 5% nano-added geopolymers to have greater thermal stability as compared to reference geopolymers. Finally, the adopted methodology in this research has shown that 5% nano-silica, is the optimal result for the synthesis and the production of local meta kaolin based geopolymer, with regard to the improvement of physical properties, micro structure and compressive strength.

Advanced Control of a PMSG Wind Turbine

In this work, an intelligent artificial control of a variable speed wind turbine (PMSG) is proposed. First, a mathematical model of turbine written at variable speed is established to investigate simulations results. In order to optimize energy production from wind, a pitch angle and DC bus control law is synthesized using PI controllers. Then, an intelligent artificial control such as fuzzy logic and artificial neural network control is applied. Its simulated performances are then compared to those of a classical PI controller. Results obtained in MATLAB/Simulink environment show that the fuzzy and the neuro control is more robust and has superior dynamic performance and hence is found to be a suitable replacement of the conventional PI controller for the high performance drive applications.

Modelisation and Optimization of a Microbial Desalination Cell System

In this work, we used a hybrid system composed of a Microbial Desalination Cell (MDC). This system allows, at the same time, the treatment of wastewater and the production of electrical energy for the desalination of saltwater. MDC is a cleaning technology used to purify wastewater. This process has been driven by converting organic compounds contained in wastewater into electrical energy through biological, chemical, and electrochemical processes. The produced electrical energy was used to desalinate the saline water. The objective of this work is the desalination or pre-desalination of seawater. For this, we have established a theoretical model consisting of differential equations describing the behavior of this system. Subsequently, we developed a program on MAT-LAB software to simulate and optimized the operation of this system and to promote the production of electrical energy in order to improve the desalination efficiency of the MDC. The theoretical result shows that the electrical current production is maximal when the methanogenic growth rate equal to zero, increases with the increasing of influent substrate concentration and the efficiency of desalination increased with flow rate of saline water.

Performance Improving of a Concentrating Photovoltaic System by Using a New Optical Adhesive

The objective of this present study is to manufacture a new silicone-based adhesive which is used for gluing and bonding the second optical elements (SOE) with Concentrating Photovoltaic solar cell (CPV) in order to guarantee a thickness that can provide a good silicone adherence to obtain long term stability and keeping a good solar transmittance performance, too. This new adhesive is made up of a mixture of silicone and transparent glass balls. The experimental part consists of the choice of the best size of glass balls with the suitable proportion of the glass balls weight in the mixture. For this purpose, ten samples were manufactured for every category of glass balls and weight ratio. Glass ball sizes between 100 and 1100 μm, and weight ratios between 1 and 10% were analyzed. For each category of glass balls, four proportions were mixed with the silicone. The thicknesses and transmittance of every sample were measured with appropriate instruments. The experimental results illustrate that the mixture containing balls with sizes inferior to 106 μm, is the best mixture which assures adhesive minimum thickness value necessary for an efficient mechanical bond and preserves also a good transmittance of solar irradiance.

太阳能/地热联合有机朗肯循环电厂的能量和火用优化

对突尼斯南部一个太阳能和地热能驱动的有机朗肯循环(ORC)电厂进行了能量和火用分析。分别研究了在冬季和夏季2天内主要运行参数对太阳能/地热联合ORC系统的影响,确定了系统的质量、能量和火用平衡。结果表明,系统不可逆性的主要来源是抛物面通流收集器。为了减少火用损耗,优化系统性能,采用多项式回归分析方法进行优化。由此建立了传热流体的质量流量和入口温度与太阳辐射的关系。该优化方案可使系统的火用效率在冬季提高2.06%~5.44%,在夏季提高1.00%~4.10%。此外,分析显示,在冬季,总能源效率和净功率分别提高了26.6%和21.0%。

MPPT Design Using PSO Technique for Photovoltaic System Control Comparing to Fuzzy Logic and P&O Controllers

The Maximum Power Point Tracker (MPPT) is the optimum operating point of a photovoltaic module. It plays a very important role to obtain the maximum power of a solar panel as it allows an optimal use of a photovoltaic system, regardless of irradiation and temperature variations. In this research, we present a novel technique to improve the control’s performances optimization of the system consisting of a photovoltaic panel, a buck converter and a load. Simulations of different parts of the system are developed under Matlab/Simulink, thus allowing a comparison between the performances of the three studied controllers: “Fuzzy TS”, “P&O” and “PSO”. The three algorithms of MPPT associated with these techniques are tested in different meteorological conditions. The obtained results, in different operating conditions, reveal a clear improvement of controlling performances of MPPT of a photovoltaic system when the PSO tracking technique is used.

PMSG Wind Energy Conversion System: Modeling and Control

In this paper, a model of a variable speed wind turbine using a permanent magnet synchronous generator (PMSG) is presented and the control schemes are proposed. The model presents the aerodynamic part of the wind turbine, the mechanic and the electric parts. Simulations have been conducted with Matlab/Simulink to validate the model and the proposed control schemes.

An Efficient HW/SW Design for Text Extraction from Complex Color Image

In the context of constructing an embedded system to help visually impaired people to interpret text,in this paper,an efficient High-level synthesis(HLS)Hardware/Software(HW/SW)design for text extraction using the Gamma Correction Method(GCM)is proposed.Indeed,the GCM is a common method used to extract text from a complex color image and video.The purpose of this work is to study the complexity of the GCM method on Xilinx ZCU102 FPGA board and to propose a HW implementation as Intellectual Property(IP)block of the critical blocks in this method using HLS flow with taking account the quality of the text extraction.This IP is integrated and connected to the ARM Cortex-A53 as coprocessor in HW/SW codesign context.The experimental results show that theHLS HW/SW implementation of the GCM method on ZCU102 FPGA board allows a reduction in processing time by about 89%compared to the SW implementation.This result is given for the same potency and strength of SW implementation for the text extraction.

Towards Securing Machine Learning Models Against Membership Inference Attacks

From fraud detection to speech recognition,including price prediction,Machine Learning(ML)applications are manifold and can significantly improve different areas.Nevertheless,machine learning models are vulnerable and are exposed to different security and privacy attacks.Hence,these issues should be addressed while using ML models to preserve the security and privacy of the data used.There is a need to secure ML models,especially in the training phase to preserve the privacy of the training datasets and to minimise the information leakage.In this paper,we present an overview of ML threats and vulnerabilities,and we highlight current progress in the research works proposing defence techniques againstML security and privacy attacks.The relevant background for the different attacks occurring in both the training and testing/inferring phases is introduced before presenting a detailed overview of Membership Inference Attacks(MIA)and the related countermeasures.In this paper,we introduce a countermeasure against membership inference attacks(MIA)on Conventional Neural Networks(CNN)based on dropout and L2 regularization.Through experimental analysis,we demonstrate that this defence technique can mitigate the risks of MIA attacks while ensuring an acceptable accuracy of the model.Indeed,using CNN model training on two datasets CIFAR-10 and CIFAR-100,we empirically verify the ability of our defence strategy to decrease the impact of MIA on our model and we compare results of five different classifiers.Moreover,we present a solution to achieve a trade-off between the performance of themodel and the mitigation of MIA attack.

A New Industrial Hydrogen Production Process

This study was proposed to develop a new method for hydrogen production in significant amounts. It consisted in using sulfur dioxide (SO2), and discharged from the sulfuric acid (H2SO4) production unit. This process could be considered as an alternative to many classical processes for air quality treatment resulting in as afer environment. Furthermore, it was an innovative method for hydrogen production. In fact, SO2 was fed into a PEM electrolyzer stack. The dissolved SO2 was oxidized at the anode which led to the production of sulfuric acid;whereas, hydrogen (H2) was produced at the cathode. This new method was able to treat 3.7 t/day of SO22 in order to produce 0.116 t/day of hydrogen and recover 5.6 t/day of 35 wt.% H2SO4. Results showed that the studied procedure was more economical in terms of energy consumption than the Westinghouse hybrid process. Hence, 67% of the energy needed for the decomposition step was reduced by our proposed process. After the presentation of the principles of the new process design, each part of the process was sized. The calculations showed that the number of electrolyzers could be calculated using the same formula used for the number of electrolyzers for water electrolysis or flux cell.

Induction Motor Modeling Based on a Fuzzy Clustering Multi-Model—A Real-Time Validation

This paper discusses a comparative study of two modeling methods based on multimodel approach. The first is based on C-means clustering algorithm and the second is based on K-means clustering algorithm. The two methods are experimentally applied to an induction motor. The multimodel modeling consists in representing the IM through a finite number of local models. This number of models has to be initially fixed, for which a subtractive clustering is necessary. Then both C-means and K-means clustering are exploited to determine the clusters. These clusters will be then exploited on the basis of structural and parametric identification to determine the local models that are combined, finally, to form the multimodel. The experimental study is based on MATLAB/SIMULINK environment and a DSpace scheme with DS1104 controller board. Experimental results approve that the multimodel based on K-means clustering algorithm is the most efficient.

A DFIM Sensor Faults Multi-Model Diagnosis Approach Based on an Adaptive PI Multiobserver—Experimental Validation

This paper studies the problem of diagnosis strategy for a doubly fed induction motor (DFIM) sensor faults. This strategy is based on unknown input proportional integral (PI) multiobserver. Thecontribution of this paper is on one hand the creation of a new DFIM model based on multi-model approach and, on the other hand, the synthesis of an adaptive PI multi-observer. The DFIM Volt per Hertz drive system behaves as a nonlinear complex system. It consists of a DFIM powered through a controlled PWM Voltage Source Inverter (VSI). The need of a sensorless drive requires soft sensors such as estimators or observers. In particular, an adaptive Proportional-Integral multi-observer is synthesized in order to estimate the DFIM’s outputs which are affected by different faults and to generate the different residual signals symptoms of sensor fault occurrence. The convergence of the estimation error is guaranteed by using the Lyapunov’s based theory. The proposed diagnosis approach is experimentally validated on a 1 kW Induction motor. Obtained simulation results confirm that the adaptive PI multiobserver consent to accomplish the detection, isolation and fault identification tasks with high dynamic performances.

A New Sliding Function for Discrete Predictive Sliding Mode Control of Time Delay Systems

The control of time delay systems is still an open area for research. This paper proposes an enhanced model predictive discrete-time sliding mode control with a new sliding function for a linear system with state delay. Firstly, a new sliding function including a present value and a past value of the state, called dynamic surface, is designed by means of linear matrix inequalities （LMIs）. Then, using this dynamic function and the rolling optimization method in the predictive control strategy, a discrete predictive sliding mode controller is synthesized. This new strategy is proposed to eliminate the undesirable effect of the delay term in the closed loop system. Also, the designed control strategy is more robust, and has a chattering reduction property and a faster convergence of the system s state. Finally, a numerical example is given to illustrate the effectiveness of the proposed control.

New LMI Conditions for Reduced-order Observer of Lipschitz Discrete-time Systems: Numerical and Experimental Results

The objective of this paper is to propose a reduced-order observer for a class of Lipschitz nonlinear discrete-time systems.The conditions that guarantee the existence of this observer are presented in the form of linear matrix inequalities(LMIs). To handle the Lipschitz nonlinearities, the Lipschitz condition and the Young′s relation are adequately operated to add more degrees of freedom to the proposed LMI. Necessary and sufficient conditions for the existence of the unbiased reduced-order observer are given. An extension to H_∞ performance analysis is considered in order to deal with H_∞ asymptotic stability of the estimation error in the presence of disturbances that affect the state of the system. To highlight the effectiveness of the proposed design methodology, three numerical examples are considered. Then, high performances are shown through real time implementation using the ARDUINO MEGA 2560 device.

New Results on Discrete-time Delay Systems Identification

A new approach for simultaneous online identification of unknown time delay and dynamic parameters of discrete-time delay systems is proposed in this paper.The proposed algorithm involves constructing a new generalized regression vector and defining the time delay and the rational dynamic parameters in the same vector.The gradient algorithm is used to deal with the identification problem.The effectiveness of this method is illustrated through simulation.

Second Order Sliding Mode Control for Discrete Decouplable Multivariable Systems via Input-output Models

The problem of the chattering phenomenon is still the main drawback of the classical sliding mode control. To resolve this problem, a discrete second order sliding mode control via input-output model is proposed in this paper. The proposed control law is synthesized for decouplable multivariable systems. A robustness analysis of the proposed discrete second order sliding mode control is carried out. Simulation results are presented to illustrate the effectiveness of the proposed strategy.