The performance of sewage pumps stations affected by many factors through its work time which produce undesired transportation efficiency. This paper is focus on the use of artificial neural network and multiple linear regression (MLR) models for prediction the major sewage pump station in Baghdad city. The data used in this work were obtained from Al-Habibia sewage pump station during specified records- three years in Al-Karkh district, Baghdad. Pumping capability of the stations was recognized by considering the influent input importance of discharge, total suspended solids (TSS) and biological oxygen demand (BOD). In addition, the chemical oxygen demands (COD), pH and chloride (Cl). The proposed model performance has compared with the correlation coefficient (r). The suitable structure design of neural network model is examined through many trials, error, preparations and evaluation steps. Two prediction models of organic and sediment loading are presented. Result found that the estimating of the organic and sediment loading by ANN model could be successful. Moreover, results showed that influent discharge rate have more effect on organic and sediment loading predicting to other parameters.
The most significant function in oil exploration is determining the reservoir facies, which are based mostly on the primary features of rocks. Porosity, water saturation, and shale volume as well as sonic log and Bulk density are the types of input data utilized in Interactive Petrophysics software to compute rock facies. These data are used to create 15 clusters and four groups of rock facies. Furthermore, the accurate matching between core and well-log data is established by the neural network technique. In the current study, to evaluate the applicability of the cluster analysis approach, the result of rock facies from 29 wells derived from cluster analysis were utilized to redistribute the petrophysical properties for six units of Mishri
... Show MoreConcentrations of four heavy metals, Zinc , Copper , Lead and Cadimium were determed in water and sediment samples collected bi-weekly from six sampling sites on the lower part of River Diyala during low flow period (August to October) and high flow period (April to June). A reference point site (1) was situated upstream the effects of the effluent. Present work describes the e
... Show MoreThe general approach of this research is to assume that the small nonlinearity can be separated from the linear part of the equation of motion. The effect of the dynamic fluid force on the pump structure system is considered vibrates at its natural frequency but the amplitude is determined by the initial conditions. If the motion of the system tends to increase the energy of the pump structure system, the vibration amplitude will increase and the pump structure system is considered to be unstable. A suitable MATLAB program was used to predict the stability conditions of the pump structure vibration. The present research focuses on fluid pump problems, namely, the role played by damping coefficient C, damping factor
... Show MoreField experiments were carried out for the autumn season 2022- 2021 in the field of College of Agricultural Engineering Sciences - University of Baghdad - Jadiriyah Complex –Station A- to study a combination of organic fertilizer (Vermicompost) and cow manure as well as a control treatment (soil only) intertwined with Spraying with silicon, calcium and distilled water (control) in the growth and production of three cultivars of beet (Cylindra, Dark Red, Red) within the design of Completely Randomized Block Design at three replications, The number of treatments was 9 for each replicate. The means were compared according to the least significant difference (L.S.D) at a probability lev
The map of permeability distribution in the reservoirs is considered one of the most essential steps of the geologic model building due to its governing the fluid flow through the reservoir which makes it the most influential parameter on the history matching than other parameters. For that, it is the most petrophysical properties that are tuned during the history matching. Unfortunately, the prediction of the relationship between static petrophysics (porosity) and dynamic petrophysics (permeability) from conventional wells logs has a sophisticated problem to solve by conventional statistical methods for heterogeneous formations. For that, this paper examines the ability and performance of the artificial intelligence method in perme
... Show MoreThis study presents the findings of a 3D finite element modeling on the performance of a single pile under various slenderness ratios (25, 50, 75, 100). These percentages were assigned to cover the most commonly configuration used in such kind of piles. The effect of the soil condition (dry and saturated) on the pile response was also investigated. The pile was modeled as a linear elastic, the surrounded dry soil layers were simulated by adopting a modified Mohr-Coulomb model, and the saturated soil layers were simulated by the modified UBCSAND model. The soil-pile interaction was represented by interface elements with a reduction factor (R) of 0.6 in the loose sand layer and 0.7 in t
In this research, a study is introduced on the effect of several environmental factors on the performance of an already constructed quality inspection system, which was designed using a transfer learning approach based on convolutional neural networks. The system comprised two sets of layers, transferred layers set from an already trained model (DenseNet121) and a custom classification layers set. It was designed to discriminate between damaged and undamaged helical gears according to the configuration of the gear regardless to its dimensions, and the model showed good performance discriminating between the two products at ideal conditions of high-resolution images. So, this study aimed at testing the system performance at poo
... Show MoreIn this research, a study is introduced on the effect of several environmental factors on the performance of an already constructed quality inspection system, which was designed using a transfer learning approach based on convolutional neural networks. The system comprised two sets of layers, transferred layers set from an already trained model (DenseNet121) and a custom classification layers set. It was designed to discriminate between damaged and undamaged helical gears according to the configuration of the gear regardless to its dimensions, and the model showed good performance discriminating between the two products at ideal conditions of high-resolution images.
So, this study aimed at testing the system performance at poor s
... Show More