Currently, the modeling of complex chemical-physical processes is drastically influencing industrial development. Therefore, the analysis and study of the combustion process of the boilers using machine learning (ML) techniques are vital to increase the efficiency with which this equipment operates and reduce the pollution load they contribute to the environment. This work aims to predict the emissions of CO, CO2, NOx, and the temperature of the exhaust gases of industrial boilers from real data. Different ML algorithms for regression analysis are discussed. The following are input variables: ambient temperature, working pressure, steam production, and the type of fuel used in around 20 industrial boilers. Each boiler's emission data was collected using a TESTO 350 Combustion Gas Analyzer. The modeling, with a machine learning approach using the Gradient Boosting Regression algorithm, showed better performance in the predictions made on the test data, outperforming all other models studied. It was achieved with predicted values showing a mean absolute error of 0.51 and a coefficient of determination of 99.80%. Different regression models (DNN, MLR, RFR, GBR) were compared to select the most optimal. Compared to models based on Linear Regression, the DNN model has better prediction performance. The proposed model provides a new method to predict CO2, CO, NOx emissions, and exhaust gas outlet temperature.
12 May 2020 in The International Journal of Advanced Manufacturing Technology
The influence of polarity during resistance spot weld (RSW) of dissimilar lap joints on mechanical properties and failure mode is assessed in this work. A dissimilar lap joint was set using DP 600 dual phase steel with AISI 304 stainless steel. The experiments were performed on a medium-frequency direct current spot welding machine with proper data acquisition of voltage and welding current. Temperature evolution was also acquired by using IR camera. The mechanical properties of spot welds were evaluated by using a coach peel testing. The effect of welding current and welding time on mechanical properties was also evaluated. Correlations between polarity with the welding nugget size, failure mode, tensile strength, temperature evolution and dynamic resistance were analysed. The analysis confirmed that the polarity on dissimilar lap joints affects the behaviour of dissimilar RSWs.
17 February 2022 in The International Journal of Advanced Manufacturing Technology
This paper researches the influence of zinc coating of galvanized DP600 steel (DP600G) on the nugget development and mechanical properties of dissimilar DP600 - AISI304 welded joints obtained by resistance spot welding process (RSW). The RSW evaluations consisted of determining, from the dynamic resistance curves, the different stages involved in nugget formation. The experimental results showed that the zinc coating on the DP600G steel has a significant influence on the time needed for the start of the nugget formation, two times higher than that used for non-galvanized steel. The expulsion time was delayed by 1.12 times. The presence of Zn in the DP600G/AISI304 welded joints produced smaller nugget diameters compared to the DP600/AISI304 joints for the same experimental conditions, however higher peak failure load values were obtained for the first. The causes of this unusual behavior are also analyzed in this paper.
29 December 2023 in Trends in Agricultural and Environmental Sciences
This study presents an innovative approach to segmenting pores in low-quality industrial radiographic images using advanced image processing and adaptive segmentation techniques. The process involves several steps, including conversion of the image to grayscale to simplify analysis. Gaussian and median filters are then applied to improve image quality and enable more accurate segmentation. The methodology is based on adaptive thresholding and edge detection using the Canny algorithm, achieving accurate pore area measurements, even for those unnoticed by experts, with measurement errors of less than 0.1 mm². This high accuracy supports the method's effectiveness in pore detection and measurement. The resulting tool has great potential in industrial radiography applications, from quality control to defect analysis. While recognizing the need for continued research to improve contrast and illumination, as well as to address potential sources of error, these refinements promise to further elevate an already reliable and accurate method with a wide reach in the industry.