Artificial intelligence approach in crude distillation unit operation

This study incorporates the use of Artificial Intelligence in the monitoring of atmospheric distillation unit of large scale refining operation using Google AutoML tables, Jupyter, and Python software. The process involved training, evaluation, improvement, and deployment of the models based on the input data. The predicted yield (vol %) for the models were: Auto ML model: liquefied petroleum gas (LPG) - 1.41 , straight run gasoline (SRG)– 4.96, straight run naphtha (SRN) – 17.87, straight run kerosene (SRK) – 14.5, light diesel oil (LDO) – 26.47, heavy diesel oil (HDO) – 2.7, and atmospheric residue (AR) –30.03; Jupyter Model: LPG – (0.93), SRG – (4.69), SRN – (17.24), SRK – (14.39), LDO – (26.43), HDO – (2.7), and AR – (30.18); and Python Model:LPG – (1.66) , SRG – (7.58), SRN – (11.68), SRK – (14.92), LDO – (24.77), HDO – (4.59), and AR – (24.59). The coefficient of determination (R2) values of 0.99981, 0.99943, and 0.93078 and Standard Error values of 0.240918, 0.419291, 3.536064, were obtained for the 3 models, respectively. All the software gave good predictions of the actual yield, although the Google Auto ML Table gave the best prediction. The training of the model is fundamental to its performance and precision.

Investigation of Heavy and Trace Metals in Some Kurdistan Region Crude Oils by Spectroscan MAX-G

Four types of Kurdistan crude oils have been studied to determine the heavy and trace metals. The significance of determining trace elements that exist in crude oils is helpful for further information about exploration, production and the refining process. In this work crude oil can be separated into products such as (gasoline, kerosene, diesel, and atmospheric distillation residue +350°C) by using atmospheric distillation unit and vacuum distillation unit. The trace metals can be determined with acceptable accuracy and precision by spectroscan MAX-G. However, the values of Ni concentration were the best in accuracy among the group of metals of interest. The average values of the results will be employed as reference values of the trace metal content in the coming discussion and using Ni and V as test elements. The crude oil samples are characterized by with a dominance of V over Ni with a V/Ni ratio of 3.7 to 2.5. Trace element analysis of the five metals in crude oils and atmospheric distillation residues +350°C, for each crude oils and atmospheric distillation residues +350°C is investigated, samples of these areas has not been previously examined for trace element contents. In this study to find the relation between metals in crude oils and atmospheric distillation residue of samples. To detect the concentration of trace elements by using this instrument.

Experimentally Investigated the Development and Performance of a Parabolic Trough Solar Water Distillation Unit Concerning Angle-Wise

The PTC performance was evaluated at four (i.e., 25o, 35o, 45o, and 55o) different adjusting Angles and it clearly showed that the adjusting Angles is highly significant, affecting the efficiency of the collector. The PTC received mean solar radiation 513 kJ.m-2.hr-1 with the absorbing temperature of the absorber in PTC was noted 123oC, 115oC, and 113oC consecutively the months of the year with the adjusting angles of 25o, 35o, and 45o respectively. Distilled water from the solar water distillation unit was found to improve the laboratory’s quality and wash equipment in the hospital. PTC’s efficiency noted 26.9%, 26.3%, and 26.1% with the distilled water up to 217, 313, and 343 ml.m-2.day-1 for the adjusting Angles of 25o, 45o, and 35o respectively. From the result, it concluded that to obtain maximum distilled water, the PTC should be set on adjusting Angles of 25o, 35o, and 45o. The average unit price of distillate from the solar still is assessed as Rs. 2.64/L-m2 with a payback period is 365 days. The unit distillate cost is seen to reduce significantly from Rs. 4.92/L to Rs. 1.57/L. It concluded from results that the distilled water of PTC relatively decent quality.

A Practical Approach to Energy Optimization Using Pinch Analysis: A Case Study of an Oil Refinery

The objective of this paper is to perform an energy optimization study using pinch analysis on the Heat Exchanger Network (HEN) of a Crude Distillation Unit to maximum heat recovery, minimize energy consumption and increase refining margin. The heat exchanger network (HEN) considered comprises exchangers from the pre-heat section of the atmospheric distillation unit, which recovers heat from the product streams to incrementally heat the crude oil feed stream before entering the furnace. This paper illustrates how to perform a detailed HEN retrofitting study using an established design method known as Pinch Analysis to reduce the operating cost by increasing energy savings of the HEN of an existing complex refinery of moderate capacity. Analysis and optimization were carried out on the HEN of the CDU consist a total of 19 heat exchangers which include: process to process (P2P) heat exchangers, heaters and coolers. In the analysis, different feasible retrofit scenarios were generated using the pinch analysis approach. The retrofit designs included the addition of new heat exchangers, rearrangement of heat exchanger (re-sequencing) and re-piping of existing exchangers. Aspen Hysys V9 was used to simulate the CDU and Aspen Energy Analyser was used to perform pinch analysis on the HEN of the pre-heat train. Several retrofit scenarios were generated, the optimum retrofit solution was a trade-off between the capital cost of increasing heat exchanger surface area, payback time, energy / operating cost savings of hot and cold utilities. Results indicated that by rearrangement (Re-sequencing), the pre-heat train can reduce hot (fired heat) and cold (air and cooling water) utilities consumption to improve energy savings by 8% which includes savings on fired heat of about 4.6 MW for a payback period of 2 years on capital investment. The results generated were based on a ΔTmin of 10°C and pinch temperature of 46.3°C. Initial sensitivity analysis on the ΔTmin indicated that variation of total cost index is quite sensitive and increases with increase in ΔTmin at the temperature range of 14.5-30°C, however total cost index remains constant and minimal at a temperature range between 10°C-14.5°C for the CDU preheat train under study. In addition, the implementation of the optimum retrofit result is straightforward and feasible with minimum changes to the existing base case/design.