scholarly journals Comparison of Optimization of Exergy Efficiency of a Crude Distillation Unit Using Artificial Neural Network (ANN) and Response Surface Methods (RSM)

2020 ◽  
pp. 1-14
Author(s):  
M. N. Braimah
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Exergy Efficiency ◽  
Operating Conditions ◽  
Distillation Unit ◽  
Optimum Operating ◽  
Base Case ◽  
Operating Variables ◽  
Port Harcourt ◽  
Artificial Neural

The study carried out simulation of the Crude Distillation Unit (CDU) of the New Port Harcourt Refinery (NPHR) and performed exergy analysis of the Refinery. The Crude Distillation Unit (CDU) of the New Port Harcourt refinery was simulated using HYSYS (2006.5). The Atmospheric Distillation Unit (ADU) which is the most inefficient unit and where major separation of the crude occurs was focused on. The simulation result was exported to Microsoft Excel Spreadsheet for exergy analysis. The ADU was optimized using statistical method and Artificial Neural Network. Box-Behnken model was applied to the sensitive operating variables that were identified. The statistical analysis of the RSM was carried out using Design Expert (6.0). Matlab software was used for the Artificial Neural Network. All the operating variables were combined to give the best optimum operating conditions. Exergy efficiency of the ADU was 51.9% and 52.4% when chemical exergy was included and excluded respectively. The optimum operating conditions from statistical optimization (RSM) are 586.1 K for liquid inlet temperature, 595.5 kPa for liquid inlet pressure and condenser pressure of 124 kPa with exergy efficiency of 69.6% which is 33.0% increment as compared to the base case. For the ANN optimization, the exergy efficiency of the ADU was estimated to be 70.6%. This gave an increase of 34.9% as compared to the base case. This study concluded that enormous improvement can be achieved both in design feasibility and improved efficiency if the feed operating parameters and other sensitive parameters are carefully chosen. Furthermore, ANN optimization gave better exergy efficiency of 70.6% than RSM optimization of 69.6%.

scholarly journals Application of Artificial Neural Network (ANN) in the Optimization of Crude Oil Refinery Process: New Port-Harcourt Refinery

2020 ◽  
pp. 26-38
Author(s):  
M. N. Braimah
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Product Quality ◽  
Exergy Efficiency ◽  
Oil Refinery ◽  
Distillation Unit ◽  
Optimum Operating ◽  
Port Harcourt ◽  
Artificial Neural ◽  
Artificial Neural Network Ann

Background: Optimizing the process conditions of the crude distillation unit is a main challenge for each refinery. Optimization increases profit by producing the required range of distillates at maximum yield and at minimum cost. To achieve an acceptable control of product quality an artificial neural network (ANN) can be used. ANNs are used for engineering purposes, such as pattern recognition, forecasting, and data compression. In the petroleum refinery industry, ANN has been used as controller in for the crude distillation unit. The aim of the current study was to use ANN to optimize and achieve control of product quality of crude distillation unit of an oil   refinery. Materials: The research was carried out using the following materials; The design flowchart and the operating data of the crude distillation unit of the New Port Harcourt refinery, Simulation software (HYSYS 2006.5) and Matlab for the ANN. Results: The ANN predicted the optimum operating conditions at which the atmospheric distillation unit (ADU) can operate with the least irreversibility and without changing the design and compromising the products quality. The corresponding exergy efficiency after optimization with ANN for the input variable combinations was 70.6% which was a great improvement because the exergy efficiency increased as compared to the base case of 51.9%. Conclusion: Optimization using ANN, improved the efficiency of the ADU with the least irreversibility and without changing the design and compromising the products quality.

scholarly journals Fixed bed utilization for the isolation of xylene vapor: Kinetics and optimization using response surface methodology and artificial neural network

2020 ◽  
Vol 26 (2) ◽  
pp. 200105-0
Author(s):  
Kaushal Naresh Gupta ◽  
Rahul Kumar
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Response Surface Methodology ◽  
Response Surface ◽  
Flow Rate ◽  
Operating Conditions ◽  
Optimum Operating ◽  
Operating Parameters ◽  
Bed Height ◽  
Artificial Neural

This paper discusses the isolation of xylene vapor through adsorption using granular activated carbon as an adsorbent. The operating parameters investigated were bed height, inlet xylene concentration and flow rate, their influence on the percentage utilization of the adsorbent bed up to the breakthrough was found out. Mathematical modeling of experimental data was then performed by employing a response surface methodology (RSM) technique to obtain a set of optimum operating conditions to achieve maximum percentage utilization of bed till breakthrough. A fairly high value of R2 (0.993) asserted the proposed polynomial equation’s validity. ANOVA results indicated the model to be highly significant with respect to operating parameters studied. A maximum of 76.1% utilization of adsorbent bed was found out at a bed height of 0.025 m, inlet xylene concentration of 6,200 ppm and a gas flow rate of 25 mL.min-1. Furthermore, the artificial neural network (ANN) was also employed to compute the percentage utilization of the adsorbent bed. A comparison between RSM and ANN divulged the performance of the latter (R2 = 0.99907) to be slightly better. Out of various kinetic models studied, the Yoon-Nelson model established its appropriateness in anticipating the breakthrough curves.

Optimization of the exergy efficiency, exergy destruction, and engine noise index in an engine with two direct injectors using NSGA-II and artificial neural network

2021 ◽  
pp. 146808742110577
Author(s):  
Saeid Shirvani ◽  
Sasan Shirvani ◽  
Seyed Ali Jazayeri ◽  
Rolf Reitz
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Exergy Efficiency ◽  
Base Case ◽  
Optimal Solutions ◽  
Exergy Destruction ◽  
Engine Noise ◽  
Nsga Ii ◽  
Noise Index ◽  
Artificial Neural

Direct Dual Fuel Stratification (DDFS) strategy is a novel Low Temperature Combustion (LTC) strategy that has comparable thermal efficiency to the Reactivity Controlled Compression Ignition (RCCI) strategy, while it offers more control over the combustion process and the rate of heat release. The DDFS strategy uses two direct injectors for the low- and high-reactivity fuels (gasoline and diesel) to benefit from the RCCI concept. In this study, the injection strategy of the injectors of a gasoline/diesel DDFS engine was optimized from the thermodynamic perspective to maximize exergy efficiency and minimize exergy destruction and an engine noise index. An artificial neural network was developed with 576 samples from a CFD code to predict the DDFS mode behavior, and the non-dominated sorting genetic algorithm (NSGA-II) was used to obtain the Pareto Front and the optimal solutions. Compared to the base case, the exergy efficiency of the optimal cases increased by up to 2%, exergy destruction and Peak Pressure Rise Rate (PPRR) reduced by about 2.3%, and 2 bar/deg, respectively, in the optimal solutions. NOX and soot emissions were reduced by 40% and 35%, respectively, in the best-case scenarios.

Search for Optimum Operating Conditions for a Water Purification Process Integrated to a Heat Transformer with Energy Recycling using Artificial Neural Network Inverse Solved by Genetic and Particle Swarm Algorithms

2012 ◽  
Vol 7 (1) ◽  
Author(s):  
Youness El Hamzaoui ◽  
Bassam Ali ◽  
J. Alfredo Hernandez ◽  
Obed Cortez Aburto ◽  
Outmane Oubram
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Water Purification ◽  
Particle Swarm ◽  
Optimization Methods ◽  
Operating Conditions ◽  
Optimum Operating ◽  
Purification Process ◽  
Artificial Neural ◽  
Heat Transformer

The coefficient of performance (COP) for a water purification process integrated to an absorption heat transformer with energy recycling was optimized using the artificial intelligence. The objective of this paper is to develop an integrated approach using artificial neural network inverse (ANNi) coupling with optimization methods: genetic algorithms (GAs) and particle swarm algorithm (PSA). Therefore, ANNi was solved by these optimization methods to estimate the optimal input variables when a COP is required. The paper adopts two cases studies to accomplish the comparative study. The results illustrate that the GAs outperforms the PSA. Finally, the study shows that the GAs based on ANNi is a better optimization method for control on-line the performance of the system, and constitutes a very promising framework for finding a set of “good solutions”.

Modeling and Analysis of Hot Extrusion Metal Forming Process Using Artificial Neural Network and ANOVA

2010 ◽  
Author(s):  
Iman Zohourkari ◽  
Saeed Assarzadeh ◽  
Mehdi Zohoor
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Analysis Of Variance ◽  
Neural Model ◽  
Operating Conditions ◽  
Optimum Operating ◽  
Extrusion Force ◽  
Data Set ◽  
Artificial Neural ◽  
Anova Technique

In this paper, a feed-forward back-propagation artificial neural network (BP-ANN) and analysis of variance (ANOVA) are applied to a hot metal extrusion process, establishing a black box model as well as analyzing the effects of relevant process parameters on required forging load, under different operating conditions. Some finite element simulation data on extruding ck-45 steel, adopted from a published research paper, were used to train the neural model employing Levenberg-Marquardt learning algorithm. Die angle (15°–75°), friction coefficient between billet-die material pair (0.4–0.8), punch velocity (168–203 mm/s), and billet temperature (1000°C–1260°C) were selected as the inputs, while the extrusion load (tone) was considered as the network’s output. Based on the results during modeling attempts, a 4-10-10-1 size neural network has been decided on as the appropriate architecture of the process model. Testing predictive accuracy of the developed model was also done using a new data set (8 data samples), which has not been used in the training phase. The comparative errors with respect to the desired FEM simulations are all in acceptable ranges (less than 12%) thereby the network’s generalization capabilities were confirmed. Having established the appropriate neural model, analysis of variance (ANOVA) technique was then applied to the original training data base to find and recognize the level of importance of each parameters and their possible dual interactions on the extrusion loading force within 95% of confidence interval (α = 0.05). Based on the obtained inferences, the best optimal combination of parametric settings which leads to the minimum required extruding load was then revealed and recommended. The optimally minimized extrusion force was then predicted by the trained network model. Neural network tool box (NNET) of the Matlab software and design of experiments module of Minitab software were employed as platforms to develop neural simulations and ANOVA technique, respectively. The overall results indicate the feasibility and effectiveness of the proposed approach in a real manufacturing environment and eliminate the need to carry out expensive as well as time consuming trial and error experimentations to reach to the optimum operating conditions.

scholarly journals A Unified Control Strategy of Distributed Generation for Grid-Connected and Islanded Operation Conditions Using an Artificial Neural Network

2021 ◽  
Vol 13 (11) ◽  
pp. 6388
Author(s):  
Karim M. El-Sharawy ◽  
Hatem Y. Diab ◽  
Mahmoud O. Abdelsalam ◽  
Mostafa I. Marei
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Control System ◽  
Distributed Generation ◽  
Control Strategy ◽  
Current Control ◽  
Operating Conditions ◽  
Pi Controllers ◽  
Artificial Neural ◽  
The Stability

This article presents a control strategy that enables both islanded and grid-tied operations of a three-phase inverter in distributed generation. This distributed generation (DG) is based on a dramatically evolved direct current (DC) source. A unified control strategy is introduced to operate the interface in either the isolated or grid-connected modes. The proposed control system is based on the instantaneous tracking of the active power flow in order to achieve current control in the grid-connected mode and retain the stability of the frequency using phase-locked loop (PLL) circuits at the point of common coupling (PCC), in addition to managing the reactive power supplied to the grid. On the other side, the proposed control system is also based on the instantaneous tracking of the voltage to achieve the voltage control in the standalone mode and retain the stability of the frequency by using another circuit including a special equation (wt = 2πft, f = 50 Hz). This utilization provides the ability to obtain voltage stability across the critical load. One benefit of the proposed control strategy is that the design of the controller remains unconverted for other operating conditions. The simulation results are added to evaluate the performance of the proposed control technology using a different method; the first method used basic proportional integration (PI) controllers, and the second method used adaptive proportional integration (PI) controllers, i.e., an Artificial Neural Network (ANN).

Development of a Hybrid Artificial Neural Network and Genetic Algorithm Model for Regime Identification of Slurry Transport in Pipelines

2009 ◽  
Vol 4 (1) ◽  
Author(s):  
Sandip K Lahiri ◽  
Kartik Chandra Ghanta
Keyword(s):  
Neural Network ◽  
Genetic Algorithm ◽  
Artificial Neural Network ◽  
Operating Conditions ◽  
Misclassification Error ◽  
Wide Range ◽  
Artificial Neural ◽  
Artificial Neural Network Ann ◽  
Pipeline Design ◽  
Hybrid Artificial Neural Network

Four distinct regimes were found existent (namely sliding bed, saltation, heterogeneous suspension and homogeneous suspension) in slurry flow in pipeline depending upon the average velocity of flow. In the literature, few numbers of correlations has been proposed for identification of these regimes in slurry pipelines. Regime identification is important for slurry pipeline design as they are the prerequisite to apply different pressure drop correlation in different regime. However, available correlations fail to predict the regime over a wide range of conditions. Based on a databank of around 800 measurements collected from the open literature, a method has been proposed to identify the regime using artificial neural network (ANN) modeling. The method incorporates hybrid artificial neural network and genetic algorithm technique (ANN-GA) for efficient tuning of ANN meta parameters. Statistical analysis showed that the proposed method has an average misclassification error of 0.03%. A comparison with selected correlations in the literature showed that the developed ANN-GA method noticeably improved prediction of regime over a wide range of operating conditions, physical properties, and pipe diameters.

KNT-artificial neural network model for flux prediction of ultrafiltration membrane producing drinking water

2004 ◽  
Vol 50 (8) ◽  
pp. 103-110 ◽  
Author(s):  
H.K. Oh ◽  
M.J. Yu ◽  
E.M. Gwon ◽  
J.Y. Koo ◽  
S.G. Kim ◽  
...  
Keyword(s):  
Neural Network ◽  
Experimental Data ◽  
Artificial Neural Network ◽  
Correlation Coefficient ◽  
Network Model ◽  
Operating Conditions ◽  
Transmembrane Pressure ◽  
Feed Water ◽  
Permeate Flux ◽  
Artificial Neural

This paper describes the prediction of flux behavior in an ultrafiltration (UF) membrane system using a Kalman neuro training (KNT) network model. The experimental data was obtained from operating a pilot plant of hollow fiber UF membrane with groundwater for 7 months. The network was trained using operating conditions such as inlet pressure, filtration duration, and feed water quality parameters including turbidity, temperature and UV254. Pre-processing of raw data allowed the normalized input data to be used in sigmoid activation functions. A neural network architecture was structured by modifying the number of hidden layers, neurons and learning iterations. The structure of KNT-neural network with 3 layers and 5 neurons allowed a good prediction of permeate flux by 0.997 of correlation coefficient during the learning phase. Also the validity of the designed model was evaluated with other experimental data not used during the training phase and nonlinear flux behavior was accurately estimated with 0.999 of correlation coefficient and a lower error of prediction in the testing phase. This good flux prediction can provide preliminary criteria in membrane design and set up the proper cleaning cycle in membrane operation. The KNT-artificial neural network is also expected to predict the variation of transmembrane pressure during filtration cycles and can be applied to automation and control of full scale treatment plants.

scholarly journals Thermodynamic analysis and simulation of a new combined power and refrigeration cycle using artificial neural network

2011 ◽  
Vol 15 (1) ◽  
pp. 29-41 ◽  
Author(s):  
Abdolreza Fazeli ◽  
Hossein Rezvantalab ◽  
Farshad Kowsary
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Heat Source ◽  
Exergy Efficiency ◽  
Combined Cycle ◽  
Cycle Performance ◽  
Working Fluid ◽  
Refrigeration Cycle ◽  
Water Mixture ◽  
Artificial Neural

In this study, a new combined power and refrigeration cycle is proposed, which combines the Rankine and absorption refrigeration cycles. Using a binary ammonia-water mixture as the working fluid, this combined cycle produces both power and refrigeration output simultaneously by employing only one external heat source. In order to achieve the highest possible exergy efficiency, a secondary turbine is inserted to expand the hot weak solution leaving the boiler. Moreover, an artificial neural network (ANN) is used to simulate the thermodynamic properties and the relationship between the input thermodynamic variables on the cycle performance. It is shown that turbine inlet pressure, as well as heat source and refrigeration temperatures have significant effects on the net power output, refrigeration output and exergy efficiency of the combined cycle. In addition, the results of ANN are in excellent agreement with the mathematical simulation and cover a wider range for evaluation of cycle performance.

Sign in / Sign up

Export Citation Format

Share Document