12/14/2023 0 Comments Xlstat excel linear regression![]() The combining approaches (PLS and ANN) were successfully applied by several researchers in the field of processes modeling. It is used in situations where a response is influenced by several independent variables. PLS is a powerful statistical parameter tool which can explore the mathematical correlation between input and output variables based on input matrix 7. to develop the predictive models to estimate the fouling resistance in order to predict a cleaning schedule and to control operation of the phosphoric acid concentration plant 7.Īnother mentionable approach to depict the relation between inputs and output variables is Partial Least Square (PLS) regression. Besides, the ANN method was used by Jradi. predicted fouling resistance in cross flow 6, 9 and in shell and tube 1 heat exchanger in order to plan suitable cleaning schedules. One of the most advantages of this method is their ability to learn massive amounts of data 10.īy using ANN approach, Jradi et al. Artificial neural networks is a technique that can provide useful tools for modeling and correlating practical heat transfer problems. Among these methods, artificial neural networks are used in order to establish a relation between affecting factors of the process as input variables and fouling resistance as output variable 1, 8, 9. Recently, the application of proficient methods are used to counter this problem. Several factors can influence the formation of fouling in the heat exchanger such as the operating parameters, fouling fluid properties and design parameters of the heat exchanger 6. To this day, fouling remaining the main unresolved problem in heat transfer and an almost universal problem in the design and operation of heat exchanger equipment. Fouling deposition tends to reduce the free space for flow movement, which degrades the hydraulic performance and can include additional problems such as higher maintenance costs for removal of fouling deposits and replacement of corroded equipment 2, 7. The fouling layer can cause also erosion of heat exchanger surfaces and may even cause a catastrophic failure of heat exchanger 2. The presence of this deposit on heat exchanger surface causes an additional thermal resistance which leads to reducing heat transfer efficiency 6. This phenomenon has an adverse impact on the thermal and hydraulic performances of the heat exchanger 4, 5. It is defined as the accumulation of any unwanted deposit such as crystalline, biological, particulate or chemical reaction product on the surface of the heat exchanger. This phenomenon is commonly known as fouling 3. The major mechanism is the phenomenon of dirt deposition on the heat exchange walls of heat exchangers. Several mechanism can affect the proper functioning of these equipment. In the aim to better suit their various applications, heat exchangers are widely used in industry in different configurations and sizes. ![]() The functioning of these equipment is made by two modes of heat transfer as either directly, where two fluids exchange heat between them without any separation, or indirectly where the hot fluid gives up its heat through a material that separates it from the cold fluid 2. This supply is generally carried out by various equipment such as heat exchangers 1. The supply of heat is a vital step in production chains for almost all industrial activities. Results indicated that acid inlet and outlet temperatures were the high relative important parameters on fouling resistance with importance equal to 56% and 15.4%, respectively. The Garson’s equation was applied to determine the sensitivity of input parameters on fouling resistance based on ANN results. A network containing 6 hidden neurons trained with Broyden–Fletcher–Goldfarb–Shanno (BFGS) algorithm and hyperbolic tangent sigmoid transfer function for the hidden and output layers was selected to be the optimal configuration. 361 experimental data points was used to design and train the network. In order to improve the results obtained by PLS method, an ANN model was developed. The values of correlation coefficient (r 2) and predictive ability which are equal to 0.992 and 87%, respectively showed a good prediction of the developed PLS model. Principal Component Analysis (PCA) and Step Wise Regression (SWR) were preceded the modeling in order to determine the highest relation between operating parameters with the fouling resistance. In this study, estimation of fouling resistance in a cross-flow heat exchanger was solved using a linear and non linear methods. This problem causes a reduction of the performance of this equipment and an increase of energy losses which lead to damage the apparatus. One of the most frequent problem in phosphoric acid concentration plant is the heat exchanger build-up.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |