A new technique based on Tikhonov regularization, for converting time-concentration data into concentration-reaction rate data, was applied to a novel pyrolysis investigation carried out by Susu and Kunugi [1]. The re...A new technique based on Tikhonov regularization, for converting time-concentration data into concentration-reaction rate data, was applied to a novel pyrolysis investigation carried out by Susu and Kunugi [1]. The reaction which involves the thermal decomposition of n-eicosane using synthesis gas for K2CO3-catalyzed shift reaction was reported to be autocatalytic. This result was confirmed by applying Tikhonov regularization to the experimental data (conversion vs. time) presented by Susu and Kunugi [1]. Due to the ill-posed nature of the problem of obtaining reaction rates from experimental data, conventional methods will lead to noise amplification of the experimental data. Hence, Tikhonov regularization is preferably employed because it is entirely independent of reaction rate model and it also manages to keep noise amplification under control, thus, leading to more reliable results. This is shown by the agreement of the kinetic parameters obtained using the resulting conversion-reaction rate profile, with the Ostwald-type process for autocatalysis suggested by Susu and Kunugi [1].展开更多
This research work investigated comparative studies of expert system design and control of crude oil distillation column (CODC) using artificial neural networks based Monte Carlo (ANNBMC) simulation of random processe...This research work investigated comparative studies of expert system design and control of crude oil distillation column (CODC) using artificial neural networks based Monte Carlo (ANNBMC) simulation of random processes and artificial neural networks (ANN) model which were validated using experimental data obtained from functioning crude oil distillation column of Port-Harcourt Refinery, Nigeria by MATLAB computer program. Ninety percent (90%) of the experimental data sets were used for training while ten percent (10%) were used for testing the networks. The maximum relative errors between the experimental and calculated data obtained from the output variables of the neural network for CODC design were 1.98 error % and 0.57 error % when ANN only and ANNBMC were used respectively while their respective values for the maximum relative error were 0.346 error % and 0.124 error % when they were used for the controller prediction. Larger number of iteration steps of below 2500 and 5000 were required to achieve convergence of less than 10-7?for the training error using ANNBMC for both the design of the CODC and controller respectively while less than 400 and 700 iteration steps were needed to achieve convergence of 10-4?using ANN only. The linear regression analysis performed revealed the minimum and maximum prediction accuracies to be 80.65% and 98.79%;and 98.38% and 99.98% when ANN and ANNBMC were used for the CODC design respectively. Also, the minimum and maximum prediction accuracies were 92.83% and 99.34%;and 98.89% and 99.71% when ANN and ANNBMC were used for the CODC controller respectively as both methodologies have excellent predictions. Hence, artificial neural networks based Monte Carlo simulation is an effective and better tool for the design and control of crude oil distillation column.展开更多
People in the rural areas do not have access to specialist medical care, and when they have complications of stroke, they do not have specialists to look at them and they cannot afford to travel to the cities. The pri...People in the rural areas do not have access to specialist medical care, and when they have complications of stroke, they do not have specialists to look at them and they cannot afford to travel to the cities. The primary health care centers are not equipped with sophisticated equipments. Medicine is about medication, treatment and management. In rural areas treatment is not available either because of accessibility or affordability. Even the few doctors that are available are not in primary health care centres. Well conserved one-dimensional non-linear equations of blood flow describing blood flow in distensible blood vessels were used to develop software. This model could describe discontinuities and disruption in blood flow. The computer software can be used for detecting artherosclerosis, stenosis and differentiation of haemorrhagic and ischaemic strokes for stroke management from simple measurements. The software developed is capable of computing the Siriraj and the Allen clinical scores. These scores have been proposed to help clinicians in making decisions while waiting for results of computerized tomography, hence clinicians can start anti-thrombotic treatment while waiting for the scan results. It is capable of simulating stenosis at different position and depth of flow along the arterial length, and can be used for diagnosis. The medical emphasis is on avoiding possible occurrence, every individual can know his status by inputting the required data such as flow and geometry of their arteries into the developed interface and such measurements can be obtained from simple Doppler measurements.展开更多
文摘A new technique based on Tikhonov regularization, for converting time-concentration data into concentration-reaction rate data, was applied to a novel pyrolysis investigation carried out by Susu and Kunugi [1]. The reaction which involves the thermal decomposition of n-eicosane using synthesis gas for K2CO3-catalyzed shift reaction was reported to be autocatalytic. This result was confirmed by applying Tikhonov regularization to the experimental data (conversion vs. time) presented by Susu and Kunugi [1]. Due to the ill-posed nature of the problem of obtaining reaction rates from experimental data, conventional methods will lead to noise amplification of the experimental data. Hence, Tikhonov regularization is preferably employed because it is entirely independent of reaction rate model and it also manages to keep noise amplification under control, thus, leading to more reliable results. This is shown by the agreement of the kinetic parameters obtained using the resulting conversion-reaction rate profile, with the Ostwald-type process for autocatalysis suggested by Susu and Kunugi [1].
文摘This research work investigated comparative studies of expert system design and control of crude oil distillation column (CODC) using artificial neural networks based Monte Carlo (ANNBMC) simulation of random processes and artificial neural networks (ANN) model which were validated using experimental data obtained from functioning crude oil distillation column of Port-Harcourt Refinery, Nigeria by MATLAB computer program. Ninety percent (90%) of the experimental data sets were used for training while ten percent (10%) were used for testing the networks. The maximum relative errors between the experimental and calculated data obtained from the output variables of the neural network for CODC design were 1.98 error % and 0.57 error % when ANN only and ANNBMC were used respectively while their respective values for the maximum relative error were 0.346 error % and 0.124 error % when they were used for the controller prediction. Larger number of iteration steps of below 2500 and 5000 were required to achieve convergence of less than 10-7?for the training error using ANNBMC for both the design of the CODC and controller respectively while less than 400 and 700 iteration steps were needed to achieve convergence of 10-4?using ANN only. The linear regression analysis performed revealed the minimum and maximum prediction accuracies to be 80.65% and 98.79%;and 98.38% and 99.98% when ANN and ANNBMC were used for the CODC design respectively. Also, the minimum and maximum prediction accuracies were 92.83% and 99.34%;and 98.89% and 99.71% when ANN and ANNBMC were used for the CODC controller respectively as both methodologies have excellent predictions. Hence, artificial neural networks based Monte Carlo simulation is an effective and better tool for the design and control of crude oil distillation column.
文摘People in the rural areas do not have access to specialist medical care, and when they have complications of stroke, they do not have specialists to look at them and they cannot afford to travel to the cities. The primary health care centers are not equipped with sophisticated equipments. Medicine is about medication, treatment and management. In rural areas treatment is not available either because of accessibility or affordability. Even the few doctors that are available are not in primary health care centres. Well conserved one-dimensional non-linear equations of blood flow describing blood flow in distensible blood vessels were used to develop software. This model could describe discontinuities and disruption in blood flow. The computer software can be used for detecting artherosclerosis, stenosis and differentiation of haemorrhagic and ischaemic strokes for stroke management from simple measurements. The software developed is capable of computing the Siriraj and the Allen clinical scores. These scores have been proposed to help clinicians in making decisions while waiting for results of computerized tomography, hence clinicians can start anti-thrombotic treatment while waiting for the scan results. It is capable of simulating stenosis at different position and depth of flow along the arterial length, and can be used for diagnosis. The medical emphasis is on avoiding possible occurrence, every individual can know his status by inputting the required data such as flow and geometry of their arteries into the developed interface and such measurements can be obtained from simple Doppler measurements.
