Application of Neural Network Algorithm in Propylene Distillation

Artificial neural network modeling does not need to consider the mechanism. It can map the implicit relationship between input and output and predict the performance of the system well. At the same time, it has the advantages of self-learning ability and high fault tolerance. The gas-liquid two phases in the rectification tower conduct interphase heat and mass transfer through countercurrent contact. The functional relationship between the product concentration at the top and bottom of the tower and the process parameters is extremely complex. The functional relationship can be accurately controlled by artificial neural network algorithms. The key components of the propylene distillation tower are the propane concentration at the top of the tower and the propylene concentration at the bottom of the tower. Accurate measurement of them plays a key role in increasing propylene yield in ethylene production enterprises. This article mainly introduces the development process of neural network model and its application progress in propylene distillation tower.

Pre-design of Biphenyl Chemical Factory from Benzene with Capacity of 10.000 Ton Per Year

The design of a biphenyl chemical plant from benzene with a capacity of 10,000 tons/year will be built in Tuban, East Java with a land area of ​​10,010 m2. The raw material in the form of Benzene is obtained from Trans-Pacific Petrochemical Indotama (TPPI), Tuban. The factory is designed to operate continuously for 330 days, 24 hours per day, and requires 214 employees. Biphenyl preparation begins with reacting benzene (2,807.74 kg/hour) in a Pipe Flow Reactor (R-01) at a reactor temperature of 377 oC and a pressure of 2 atm. This reaction takes place with a conversion of 90% and is endothermic so that a Hitech heater is used to maintain the operating temperature. The products that come out of the reactor are biphenyl and hydrogen. It is then cooled and condensed in a Partial Condenser (CD-01) to a temperature of 151 oC. Then enter into Separator-02 (SP-02) to separate hydrogen from a mixture of benzene, toluene and biphenyl. Hydrogen in the gas phase as a result of the separtor. The bottom product in the form of benzene, toluene and biphenyl in the liquid phase is pumped and put into a distillation tower (MD-01) to purify the product with the bottom product in the form of biphenyl with a purity of 99.3%. The result of the distillation tower is benzene and its impurities are recycled as feed into the reactor with a temperature of 83 oC and a pressure of 1 atm. This factory requires Fixed Capital (FC) Rp. 34,341,856,338,- + US$ 4,195,836, Working Capital (WC) (Rp. 127,536,505,173,- + US$ 170,019), Manufacturing Cost (MC) (Rp. 254,092,040,390,- + US$ 816,090), and General Expenses (GE) (Rp. 33,990,417,539,- + US$ 81,609). Economic analysis shows the value of ROI before tax is 50.38 % and the value of ROI after tax is 32.75%. POT before tax is 1.65 years and POT after tax is 2.34 years. The BEP value is 43.11% and the SDP value is 23.75%. The interest rate in DCF for 10 years is 19% on average. Thus, from a technical and economic point of view, a biphenyl plant from benzene with a capacity of 10,000 tons/year is worthy of consideration.

Review of Neural Network Algorithm and its Application in Temperature Control of Distillation Tower

Distillation process is a complex process of conduction, mass transfer and heat conduction, which is mainly manifested as follows: The mechanism is complex and changeable with uncertainty; the process is multivariate and strong coupling; the system is nonlinear, hysteresis and time-varying. Therefore, traditional control methods are difficult to accurately control, but neural networks can greatly improve this problem. This article introduces the basic concepts of distillation tower temperature control, comprehensively introduces the application of various neural network algorithms in distillation tower temperature control, and compares their advantages and disadvantages and their effect. At present, there are many researches on neural network control of distillation tower temperature. The methods are different and each has its own merits. This article has carried out a systematic review to provide reference for the development of related industries.

ASU Simulation in Separating Air Components by Refrigeration Distillation (Oxygen and Nitrogen) Using ASPEN HYSYS (Case Study: SIAD Company)

Currently, air separation units (ASUs) have become very important in various industries, particularly oil and petrochemical industries which provide feed and utility services (oxygen, nitrogen, etc.). In this study, a new industrial ASU was evaluated by collecting operational and process information needed by the simulator by means of HYSYS software (ASPEN-ONE). The results obtained from this simulator were analyzed by ASU data and its error rate was calculated. In this research, the simulation of ASU performance was done in the presence of an expansion turbine in order to provide pressure inside the air distillation tower. Likewise, the cooling capacity of the cooling compartment and the data were analysed. The results indicated that expansion turbine is costly effective. Notably, it not only reduces the energy needed to compress air and supply power of the equipment, but also provides more cooling power and reduces air temperature. Moreover, turbines also increase the concentration of lighter gas products, namely nitrogen.

Design of Multivariable Control System of a Distillation Tower via Simulation Using MATLAB/Simulink

This paper deals with the multivariable control system of the distillation tower by applying multi-structures in MATLAB/Simulink for a binary mixture of benzene and toluene. Four structures configurations of the distillation are applied based on the level and temperature variables. The PID controller is used in all structures in multivariable. These structures are compared with different disturbances. The integral absolute error is a criterion to test the controller\\\’s performance under step change disturbances. The controller\\\’s performance was investigated by recording responses to disturbances in set-point of reflux ratio, flow-rate of top and bottom products. The step testing appears to be the single-ended temperature control with bottom and top-level structures to regulate the flow rate of the bottom and top products. The best structure is top-level, bottom level and condenser temperature because the column made more stable, the integral absolute error is minimum value and fast access to set-point value.