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.

Mathematical Modelling of Operating Temperature Variations of Shell-and-Tube Heat Exchanger (10-E-01)

The technique of modeling operating temperature variations of shell-and-tube heat exchanger 10-E-01 of kerosene-crude oil streams of Port Harcourt refinery crude distillation unit is presented in this research. Appropriate first-order model equations were developed applying principles of energy balance. The differential equations developed for the process streams which exchanged heat was evaluated numerically to predict the temperature variations as a function of time. The relevant parameters associated with typical heat exchanger works were calculated using plant data of 10-E-02. The model strives to predict the final kerosene temperature from 488 to 353.6 K. While the crude oil streams temperature rose from 313 to 353.6 K. The developed model enables the operator to predict the final temperature at the kerosene hydro-treating unit and thereby prevent regular emergency shutdowns due to excessive temperature rise.

Corrosion risk analysis of tube-and-shell heat exchangers and design of outlet temperature control system

This study deals with the high-risk shell-and-tube heat exchangers in the effluent system of hydrogenation reaction of the petrochemical industry.The process of hydroprocessing reactor effluent system is simulated in Aspen Plus to study the distribution of corrosive medium in the three phases of oil,gas and water.The least-squares method is utilized to calculate the ammonium salt crystallization temperature.Then,the heat exchanger with risk of ammonium salt crystal corrosion is identified.Dynamic mathematical modeling of the heat exchanger is established to determine the transfer function.A temperature control system with proportional integral derivative(PID)control of the heat exchanger outlet is designed,and fuzzy logic is used to implement self-tuning of PID parameters.After MATLAB simulation,the results show the control system can achieve rapid control of the heat exchanger outlet temperature.

Flow mechanism and heat transfer enhancement in longitudinal-flow tube bundle of shell-and-tube heat exchanger

The flow disturbance and heat transfer mechanism in the tube bundle of rod baffle shell-and-tube heat exchanger were analyzed, on the basis of which and combined with the concept of heat transfer enhancement in the core flow, a new type of shell-and-tube heat exchanger with combination of rod and van type spoiler was designed. Corresponding mathematical and physical models on the shell side about the new type heat exchanger were established, and fluid flow and heat transfer characteristics were numerically analyzed. The simulation results showed that heat transfer coefficient of the new type of heat exchanger approximated to that of rod baffle heat exchanger, but flow pressure drop was much less than the latter, indicating that comprehensive performance of the former is superior to that of the latter. Compared with rod baffle heat exchanger, heat transfer coefficient of the heat exchanger under investigation is higher under same pressure drop, especially under the high Reynolds numbers.

Prediction of Heat Transfer Rates for Shell-and-Tube Heat Exchangers by Artificial Neural Networks Approach

This work used artificial neural network(ANN)to predict the heat transfer rates of shell-and-tube heatexchangers with segmental baffles or continuous helical baffles,based on limited experimental data.The BackPropagation (BP) algorithm was used in training the networks.Different network configurations were alsostudied.The deviation between the predicted results and experimental data was less than 2%.Comparison withcorrelation for prediction shows ANN superiority.It is recommended that ANN can be easily used to predict theperformances of thermal systems in engineering applications,especially to model heat exchangers for heattransfer analysis.

Characteristics of Fluid Flow and Heat Transfer in the Shell Side of the Trapezoidal-like Tilted Baffles Heat Exchanger

Periodic whole cross-section computation models are established for segmental baffle heat exchanger, shutter baffle heat exchanger, and trapezoid-like tilted baffle heat exchanger. The reliability of models is verified by comparing the simulated results to the results obtained from the Bell-Delaware method. Due to the orthogonal assembly of the baffles, the shell side fluid shows the twisty flow of trapezoid-like tilted baffle heat exchanger. The essential mechanism on disturbing flow and heat transfer enhancement is revealed by defining the non-dimensional factor η of the shell side fluid flow direction of heat exchanger and the field synergy principle. The results show that at the same Reynolds number, the shell side fluid convection heat transfer coefficient of trapezoid-like tilted baffle heat exchanger is 12.43%-24.33% and 6.71%-11.51% higher than those of segmental baffle heat exchanger and shutter baffle heat exchanger, respectively. The shell side fluid flow velocity field and the pressure gradient field of trapezoid-like tilted baffle heat exchanger and shutter baffle heat exchanger decreases compared with that of segmental baffle heat exchanger, so the shell side fluid flow resistance and pressure drop is increased; the shell side comprehensive performance of trapezoid-like tilted baffle heat exchanger is 5.85%-9.06% higher than that of segmental baffle heat exchanger, and 15.27%-23.28% higher than that of shutter baffle heat exchanger. In this study, a baffle structure with higher efficiency of the energy utilization for the heat exchanger is provided.

Numerical simulation and optimization design of the EGR cooler in vehicle

The EGR (exhaust gas recirculation) technique can greatly reduce the NOx emission of diesel engines, especially when an EGR cooler is employed. Numerical simulations are applied to study the flow field and temperature distributions inside the EGR cooler. Three different models of EGR cooler are investigated, among which model A is a traditional one, and models B and C are improved by adding a helical baffle in the cooling area. In models B and C the entry directions of cooling water are different, which mostly influences the flow resistance. The results show that the improved structures not only lengthen the flow path of the cooling water, but also enhance the heat exchange rate between the cool and hot media. In conclusion we suggest that the improved structures are more powerful than the traditional one.