Search

Machine learning (ML) is a subset of artificial intelligence (AI) and computer science that employs data and algorithms and mimics human learning to self-enhance its accuracy. In biofuel research, butanol is widely recognized as a prospective alternative biofuel. Butanol addition in diesel or combustion engine has been more and more studied recently. Gaining a comprehensive comprehension of butanol performance and emission characteristics using machine learning approach is an essential milestone in investigating alcohol-based biofuel addition in diesel engines. However, few studies investigated butanol effect on diesel engine emissions using machine learning for optimization. A novel optimization study is needed. This work aims to investigate the newly developed and efficient machine learning, weighted superposition attraction (WSA) algorithm, to optimize the emission and performance of diesel engines fuelled with butanol-diesel biofuel. Mathematical modeling between the factors (butanol (vol.%) and BMEP (bar)) and the responses (BTE (%), BSFC (g/kWh), Exhaust Temperature Texh (oC), NOx (g/kWh), CO (g/kWh), HC (g/kWh), and Smoke Opacity (%)) are governed using regression modeling. The optimized and best factor levels are determined employing the machine learning of WSA Algorithm. Confirmations are carried out. Optimization results indicate that the BTE is maximized, and the remainder of the responses are minimized.

The goal of this paper is to optimize the rotor design parameters of 4000 rpm permanent magnet synchronous generator. The factors namely embrace, offset, outer diameter, and magnet thickness are selected as the design parameters those will be optimized in order to hold the magnetic flux density (MFD) distribution and the flux density on stator teeth and stator yoke within a desirable range while maximizing efficiency. The numerical simulations are carried out in the Maxwell environment for this purpose. The mathematical relationships between the responses and the factors are then derived using regression modeling over the simulation data. Following the modeling phase, the moth flame optimization is applied to these regression models to optimize the rotor design parameters. The motivation is determining mathematical relation between the important design parameters of the high speed generator and the measured responses, when standard M530-50A lamination material is used and then to demonstrate the utility of MFO to the readers on this design problem. The optimum factor levels for embrace, offset, outer diameter, and magnet thickness are calculated as 0.68, 30, 161.56, and 8.92 respectively. Additionally, confirmations are done by using Maxwell and the efficiency is calculated as 94.85%, and magnetic distributions are calculated as 1.64, 0.26, and 0.93 Tesla for stator teeth flux density, stator yoke flux density, and MFD; respectively. The results show that the efficiency is maximized and the magnetic distributions are kept within an appropriate range.

Scheduling is an important decision-making problem in production planning and the resulting decisions have a direct impact on reducing waste, including energy and idle capacity. Batch scheduling problems occur in various industries from automotive to food and energy. This paper introduces the parallel p-batch scheduling problem with batch delivery, content-dependent loading/unloading times and energy-aware objective function. The problem has been motivated by a real system used for freezing products in a food processing company. A mixed-integer linear programming model (MILP) has been developed and explained through a numerical example. As it is not practical to solve large-size instances via a mathematical model, the discrete differential evolution algorithm has been improved (iDDE) and hybridised with the genetic algorithm (GA). A release-oriented vector generation procedure and a heuristic batch formation mechanism have been developed to efficiently solve the problem. The performance of the proposed approach (iDDEGA) has been compared with CPLEX, iDDE and GA through a comprehensive computational study. A case study was conducted based on real data collected from the freezing process of the company, which also verified the practical use and advantages of the proposed methodology. [ABSTRACT FROM AUTHOR]

Objectives A critical factor in β-thalassemia trait screening is a hemoglobin A2 (HbA2) level of 3.5% or higher. In children with iron deficiency, HbA2 levels decrease, and diagnosis may be missed. Studies with adult carriers have yielded conflicting results on this issue. The effectiveness of HbA2–based thalassemia screening in carrier children with iron deficiency has not been studied before. Methods In this study, among 213 children with β-thalassemia trait, those with iron deficiency were determined based on ferritin value (<15 ng/mL), and their HbA2 levels were examined. We compared HbA2 levels of iron-deficient and iron-sufficient carriers and examined the correlation between low HbA2 levels and ferritin level. Because ferritin is an acute-phase reactant, similar evaluations were made by using transferrin saturation as the criterion for iron deficiency. Results The median HbA2 value of iron-deficient carrier children was 4.1% and within the diagnostic range (≥3.5%) in the majority of children. Median HbA2 levels in iron-deficient carriers differed from levels in iron-sufficient carriers (4.1% vs 4.9%, P <.007). No correlation was present between low HbA2 levels and ferritin levels (0.226). Furthermore, among children without iron deficiency, there were individuals with low HbA2 levels (26.9%). Similar results were obtained when transferrin saturation was used. Conclusions Hemoglobin A2 can be used as a screening test in children with β-thalassemia trait, despite accompanying iron deficiency. Low HbA2 levels in these children may be the result of underlying thalassemia mutation, not the result of accompanying iron deficiency. Therefore, in suspected cases of β-thalassemia trait, evaluation should continue, regardless of iron status or treatment. [ABSTRACT FROM AUTHOR]

The aim of this study is to calculate the optimum factor levels for the design parameters namely slot pitch, center slot pitch, and damper width to keep the magnetic flux density distribution in a desired range while minimizing the total harmonic distortion (THD). For this purpose, the numerical simulations are performed in the Maxwell environment. Then by the aid of regression modeling over this simulation results; the mathematical equations between the responses (THD and magnetic flux density distribution) and the factors are calculated. After the modeling phase, grasshopper optimization algorithm (GOA) is run through these regression equations to determine the optimum values of the rotor design parameters (factors). The confirmations are also performed in the Maxwell environment and the result indicated that the THD is minimized and the magnetic flux density distribution on the teeth is kept in a desired range.

A recently invented algorithm known as the grasshopper optimization algorithm (GOA) was employed to optimize diesel engine performance and emission operated with ternary fuel (ethanol-biodiesel-diesel) blends. Using the regression modelling over these experimental results; the mathematical equations between the factors i.e., ethanol ratio (vol%), biodiesel ratio (vol%), engine load (Nm)) and the responses i.e., BSFC (g/kWh), BTE (%), HC (ppm), CO2 (%), NOx (ppm), CO (%) were calculated. Grasshopper optimization algorithm was then run through these regression equations to calculate the optimum factor levels. The confirmation results suggested that the BTE was maximized and the other responses were minimized successfully. For the ANOVA results, under the 95% confidence level with α = 5% (=0.05), the p-value for all the regression models was less than 0.05, which indicated the significance of the regression models. In terms of the performance tests of the models, the regression models good fit the given observations with a low prediction error. The grasshopper optimization algorithm showed that ethanol-biodiesel-diesel blend in the ratio of 10%, 7.5%, 82.5% run at 7 Nm engine load gave the optimum results for diesel engine performance and emission characteristics. These findings have important implications for the potential of grasshopper optimization algorithm to improve engine performance and emission characteristics.

Nikel krom kaplama süreçlerinin önemli maliyet parametrelerinden biri olan nikelin verimli kullanımı rekabet için zorunludur. Bu çalışmada, metal üzerine nikel-krom kaplama yapan bir üreticinin nikel banyolarının verimliliğini arttırmak amacıyla, proses parametreleri eniyilenmeye çalışılmıştır. Bu amaçla, deney tasarımı ve eniyileme tekniklerinden biri olan yanıt yüzey yönteminden (YYY) yararlanılmıştır. Nikel banyolarında; iş parçasının yüzeyine yapışan nikel oranı maksimize edilirken; süreci etkileyen faktörler olarak, sıcaklık, nikel sülfat (NiSO4) oranı, nikel klorür (NiCl2) oranı, borik asit (H3BO3) oranı, pH ve parlatıcı oranı seçilmiştir. Çalışmanın sonunda, banyolardaki verimli kullanılan nikel oranı %80’den %95’e çıkarılmıştır.

Nikel krom kaplama süreçlerinin önemli maliyet parametrelerinden biri olan nikelin verimli kullanımı rekabet için zorunludur. Bu çalışmada, metal üzerine nikel-krom kaplama yapan bir üreticinin nikel banyolarının verimliliğini arttırmak amacıyla, proses parametreleri eniyilenmeye çalışılmıştır. Bu amaçla, deney tasarımı ve eniyileme tekniklerinden biri olan yanıt yüzey yönteminden (YYY) yararlanılmıştır. Nikel banyolarında; iş parçasının yüzeyine yapışan nikel oranı maksimize edilirken; süreci etkileyen faktörler olarak, sıcaklık, nikel sülfat (NiSO4) oranı, nikel klorür (NiCl2) oranı, borik asit (H3BO3) oranı, pH ve parlatıcı oranı seçilmiştir. Çalışmanın sonunda, banyolardaki verimli kullanılan nikel oranı %80’den %95’e çıkarılmıştır.

Dünyada yonga levha üretiminde yaşanan yoğun rekabet, maliyetler üzerinde etkili önemli parametrelerden biri olan işlem sürelerinin enküçüklenmesini zorunlu kılmaktadır. Bu çalışmada, deney tasarımı tekniklerinden yaygın olarak kullanılan yanıt yüzey yöntemi (YYY)’nin matematiksel alt yapısı kullanılarak, üretim hızını arttırmak amacıyla pres süresinin enküçüklenmesi amaçlanmıştır. Bu amaçla yonga levhanın pres süresi üzerinde etkili değişkenlerden; yonga levhanın rutubeti, banyo jeli süresi, yonga levhanın altı için gravür jeli süresi, yonga levhanın üstü için gravür jeli süresi, akış, final ağırlığı, kağıdın rutubeti, üreformaldehit (UF) miktarı, melamin formaldehit (MF) miktarı, pres yoğunluğu, pres basıncı ve pres sıcaklığı girdilerinin optimum değerleri araştırılmıştır. Bu sayede pres süresi azaltılırken, üretim miktarı ve hattın verimliliğinin arttırılması amaçlanmıştır. Modelleme amacıyla, her biri 5 tekrarlı 56 tane gözlem değeri kullanılarak girdilerle pres süresi arasındaki matematiksel ilişki belirlenmiş ve ardından eniyileme yapılmıştır. Çalışmanın sonunda, hali hazırda seçilen ürün tipi için gözlenen en düşük pres süresi olan 13.57 sn. 11 sn. kadar düşürülmüştür.

Dünyada yonga levha üretiminde yaşanan yoğun rekabet, maliyetler üzerinde etkili önemli parametrelerden biri olan işlem sürelerinin enküçüklenmesini zorunlu kılmaktadır. Bu çalışmada, deney tasarımı tekniklerinden yaygın olarak kullanılan yanıt yüzey yöntemi (YYY)’nin matematiksel alt yapısı kullanılarak, üretim hızını arttırmak amacıyla pres süresinin enküçüklenmesi amaçlanmıştır. Bu amaçla yonga levhanın pres süresi üzerinde etkili değişkenlerden; yonga levhanın rutubeti, banyo jeli süresi, yonga levhanın altı için gravür jeli süresi, yonga levhanın üstü için gravür jeli süresi, akış, final ağırlığı, kağıdın rutubeti, üreformaldehit (UF) miktarı, melamin formaldehit (MF) miktarı, pres yoğunluğu, pres basıncı ve pres sıcaklığı girdilerinin optimum değerleri araştırılmıştır. Bu sayede pres süresi azaltılırken, üretim miktarı ve hattın verimliliğinin arttırılması amaçlanmıştır. Modelleme amacıyla, her biri 5 tekrarlı 56 tane gözlem değeri kullanılarak girdilerle pres süresi arasındaki matematiksel ilişki belirlenmiş ve ardından eniyileme yapılmıştır. Çalışmanın sonunda, hali hazırda seçilen ürün tipi için gözlenen en düşük pres süresi olan 13.57 sn. 11 sn. kadar düşürülmüştür.

In this study, the electrical energy consumption of an apartment building was calculated depending on different design parameters. The electrical energy consumption was found according to the population information of each of four cities selected to represent different climatic regions. The calculations took into account, firstly, the application of different insulation materials; secondly, the state of the building: discrete, surrounded by trees or adjacent to another building; and, thirdly, different glazing types. Using the Taguchi method, experimental designs were conducted for each representative city. Then, the most suitable building design parameters were determined for each city according to signal-to-noise ratios. In the study, pollutant emissions, such as carbon dioxide (CO2), sulfur dioxide (SO2), nitrogen oxides (NOx) and particulate matter, released to the atmosphere were investigated. It was observed that there was a 50% reduction in energy consumption and emissions based on the most suitable building design parameter determined by the Taguchi method. [ABSTRACT FROM AUTHOR]

In this study regression modeling is proposed for calculating the heating and cooling load of the buildings by considering the outdoor meteorological data. For this pupose, Balikesir University Rectorate Building is selected as the case building. In the winter months, measurements were made in the hot water boiler in the basement of the building for the heating energy load. For the cooling energy load, measurements were made in the chiller groups near the building. As climate data, eight variables were considered: outdoor temperature, solar radiation, relative humidity, wind speed, atmospheric pressure, sunshine duration, steam pressure, and 1 m underground temperature. The Minitab statistical analysis program was used to perform the modeling. 55 samples were used for mathematically modeling the heating load, while 37 samples are used for modeling the cooling load. The R2 (coefficient of determination) values are calculated as 96.2% and 98.94% for cooling load and heating load, respectively. In addition to these findings, ANOVA results for both models were examined and both models were found to be significant. [ABSTRACT FROM AUTHOR]