Predicting the gross calorific value of coal based on support vector machine and partial least squares algorithm

Proximate analysis based prediction of gross calorific value of coals: A comparison of support vector machine, alternating conditional expectation and artificial neural network

The calorific value of coal is an important factor for the economic operation of coal fired power plant. However calorific value is tremendous difference between the different coal, and even if coal is from the same mine. Restricted by the coal market, most of coal fired power plants can not burn the designed-coal by now in China. The properties of coal as received are changing so frequently that pulverized coal firing is always with the unexpected condition. Therefore, the researches on the on-line prediction of calorific value of coal has a profound significance for the economic operation of power plants. Aiming at the problem of uncertainty of calorific value of coal, a soft measurement model for calorific value of coal is proposed based on the RBF neural network. And combined with the thought of k-cross validation, the genetic algorithm constructed a fitness function to optimize the RBF network parameters. It is shown by an example that the optimized model is concise and accurate, with good training accuracy and generalization ability. The model could provide a good guidance for the calculation of the calorific value of coal and optimization operation of coal fired power plants.

Biomass is increasingly employed in diverse applications to achieve and enhance energy efficiency, owing to its carbon-neutral nature. This is attributed to the fact that the quantity of CO2 released during its combustion corresponds precisely to the amount absorbed by biomass during its growth. The objective of this study is to assess the energy efficiency of biomass derived from analysed clones of fast-growing willow species in co-combustion processes with lignite at varying percentage ratios. The primary goal is to enhance the calorific value of lignite, optimize combustion and mitigate the harmful effects of combustion. The obtained results indicate that the calorific value of willow is higher than the calorific value of coal. The calorific value of coal (lignite) depends on the location of the coal deposit (field), while the calorific value of willows depends on the type of willow. Notably, clones 347 and NS 73/6 of white willow (Salix alba), have the highest energy potential compared to clones B-44 of white willow and basket willow (Salix viminalis).

This study to determine the effect in the difference of coal calori value on power plants. Currently, coal-fired power plants dominate power plants in Indonesia with 42.38%. With the dominance of coal-fired power plants, the need for coal in Indonesia remains high. In the electricity production process, calori value is an important in the electricity production process. This study discusses the effect of coal on power plants. In this study, coal received two types of treatment, namely by heating with sunlight and oven. Then in this study, research was conduct on the calori value of coal on several parameters such as Specific fuel consumption (SFC), coal flow, boiler efficiency and NPHR. From the results of the research conduct, the drying process in the sun for 10 days can reduce the water content by 28% and reduce the weight of coal from 150 grams to 108 grams. Changes in calories due to a reduction in the water content value in coal by 28% to 5414 kcal / kg. In the coal combustion test, the calorific value of coal is inversely proportional to the NPHR value and coalflow of the PLTU.

PT Binuang Mitra Bersama Blok Dua (PT BMBBD) operates in the coal mining industry with a focus on blending coal to meet market specifications. The main challenge faced by the company is maintaining the consistency of the coal's calorific value, targeted between 4000-4200 Kcal/kg. Variations in coal quality resulting from different seams, along with an optimal blending process not yet in place, lead to discrepancies between production results and the set standards. This research aims to analyze the suitability of the calorific value of PT BMBBD's coal in line with marketing targets, evaluate the effectiveness of the blending process implemented, and optimize the mixing of coal to achieve more consistent results that align with market specifications. The data used in this study includes primary data from field sampling and laboratory tests, as well as secondary data obtained from coal quality reports and internal company information. Data analysis is conducted using proximate analysis methods according to ASTM standards, along with optimization of the blending process using Microsoft Excel's Solver. The research results indicate that there is a discrepancy between the coal quality produced and the calorific value targets set by the company. Some seams produce coal with lower quality than the expected standards, highlighting the need for blending process optimization. By applying optimization methods, the results of the coal blending can be better aligned with market needs, thereby improving the consistency of calorific values and production efficiency. This study provides significant contributions to the operational improvement of PT BMBBD, particularly in efforts to enhance coal quality and consistency. The findings are expected to serve as a reference for the company in optimizing the blending process and managing coal quality more effectively in accordance with market demands.

Coal-quality deterioration in a coal stack of a power station

Characteristics of polycyclic aromatic hydrocarbon release during spontaneous combustion of coal and gangue in the same coal seam

The kernel function plays a basic role in support vector machines (SVM) algorithms. This paper presents an automatic method for selecting the parameters of the Gaussian radial basis function (GRBF) kernel which is one of the commonly used forms in SVM regression algorithms. The proposed method uses the expectation maximization (EM) algorithm for the automatic selection. The SVM regression algorithm is used to solve two major problems in remote sensing image segmentation: the density estimation problem and the Markov random field modeling problem. The density estimation is used for class conditional probabilities in Bayesian setups. The MRF is used for region modeling in boosting the Bayesian image segmentation. The proposed algorithms are integrated in a framework for remote sensing image segmentation. Experimental evaluation of the proposed algorithms using synthetic data set and hyperspectral data set illustrates the outstanding performance of the proposed algorithms.

The eastern Indonesian province has coal reserves of 368.49 million tons spread in the provinces of South Sulawesi, Central Sulawesi, North Maluku and Papua. Whereas South Sulawesi has coal reserves of around 231.12 million tons spread in 9 districts. The largest coal reserves in the districts of Maros, Barru, Bone and Sidrap Sidrap have explored around 20.06% of the total reserves. The remaining 79.94% is of low quality coal, making it less profitable for investors. While the need for coal energy sources for transportation and industry is experiencing a very rapid development, and only relies on high quality coal. The Low rank coal has a high water content, ash content, flying substance content and sulfur content, which will cause the coal's calorific value to be low so that the cost of burning coal per unit of calories becomes higher, and the impact of environmental pollution is also not good. To overcome this, research is carried out to improve the quality of coal or upgrading coal using chemical solutions and coal heating at temperature of 200oC. The Proximate analysis results obtained by the coal from the upgrading process using 20% of Hydrochloric acid and 20% of Sodium Hydroxide solution as well as the drying process at 200 oC can reduce water content up to 39.47 - 51.89%, ash content 48.15 - 57.93%, sulfur content 66.96 - 85.52%, flying substances 33.97 - 50.13%, and increasing carbon content up to 36.60 -60.42% and heating values up to 22.53 -34.68%.

Semi-enclosed bays are greatly affected by human activities and have undergone drastic changes in their ecological environment, which requires our continuous attention. Laizhou Bay (LZB) is a typical semi-closed bay that is greatly influenced by human activities, and it is highly representative on a global scale. Investigating the multi-scale variation in nutrient concentrations in semi-enclosed bays can provide scientific support for environmental management and policy adjustments. To address the limitations of in situ data and the high cost of field surveys, this study utilizes machine learning methods to construct MODIS remote sensing models for quantitatively analyzing the concentrations of dissolved inorganic nitrogen (DIN) and dissolved inorganic phosphorus (DIP) in the surface water of LZB, as well as the spatiotemporal factors influencing them. Among various methods tested, the Support Vector Machine Regression (SVR) algorithm demonstrated the best performance in retrieving nutrient concentrations in LZB. The R2 values of the DIN and DIP retrieval results based on the SVR algorithm are 0.91 and 0.92, respectively, while the RMSE values are 5.43 and 0.08 μmol/L, respectively. The retrieval results indicate that nearshore nutrient concentrations are significantly higher than those in offshore areas. Temporally, from 2003 to 2024, the DIN concentration in l has decreased at a rate of 0.4 μmol/L/yr, while the DIP concentration has remained relatively stable. Given sufficient observation data, the proposed machine learning and remote sensing approach can be effectively applied to other bays, offering the advantages of long time series, high spatial resolution, and a low cost.

The industrial robot is a highly nonlinear and highly coupled device, and the calculation of the dynamic model needs to spend a lot of time, which result in difficult to achieve dynamic control. Using of intelligent algorithm to model the robot dynamics has been the field of robotics research focus. This paper proposes a method based on support vector machine regression algorithm to model the robot dynamics. The angle acceleration coefficient, and the centripetal acceleration and Coriolis acceleration coefficient, and the gravity in the robot dynamics equation are predicted based on support vector machine regression. When the support vector machine is trained, parameters in the robot dynamics equation don’t rely on the position of each joint any more. Modeling process was described in detail by using a two degree of freedom robot. All the parameters are simulated. Simulation results show that the method has the characteristic of high precision, and short training time.

As prior information for precise nitrogen fertilization management, plant nitrogen content (PNC), which is obtained timely and accurately through a low-cost method, is of great significance for national grain security and sustainable social development. In this study, the potential of the low-cost unmanned aerial vehicle (UAV) RGB system was investigated for the rapid and accurate estimation of winter wheat PNC across the growing season. Specifically, texture features were utilized as complements to the commonly used spectral information. Five machine learning regression algorithms, including support vector machines (SVMs), classification and regression trees, artificial neural networks, K-nearest neighbors, and random forests, were employed to establish the bridge between UAV RGB image-derived features and ground-truth PNC, with multivariate linear regression serving as the reference. The results show that both spectral and texture features had significant correlations with ground-truth PNC, indicating the potential of low-cost UAV RGB images to estimate winter wheat PNC. The H channel, S4O6, and R_SE and R_EN had the highest correlation among the spectral indices, Gabor texture features, and grey level co-occurrence matrix texture features, with absolute Pearson’s correlation coefficient values of 0.63, 0.54, and 0.69, respectively. When the texture features were used together with spectral indices, the PNC estimation accuracy was enhanced, with the root mean square error (RMSE) decreasing from 2.56 to 2.24 g/kg, for instance, when using the SVM regression algorithm. The SVM regression algorithm with validation achieved the highest estimation accuracy, with a coefficient of determination (R2) of 0.62 and an RMSE of 2.15 g/kg based on the optimal feature combination of B_CON, B_M, G_DIS, H, NGBDI, R_EN, R_M, R_SE, S3O7, and VEG. Overall, this study demonstrated that the low-cost UAV RGB system could be successfully used to map the PNC of winter wheat across the growing season.

The rapid and accurate estimation of leaf chlorophyll content (LCC), an important indicator of crop photosynthetic capacity and nutritional status, is of great significance for precise nitrogen fertilization management. To explore the existence of a versatile regression model that can be successfully used to estimate the LCC for different varieties under different growth stages and nitrogen stress conditions, a study was conducted in 2023 across the growing season for winter wheat with five species and five nitrogen application levels. Two machine learning regression algorithms, support vector machine (SVM) and random forest (RF), were used to establish the bridge between UAV-derived multispectral vegetation indices and ground truth LCC (relative chlorophyll content, SPAD), taking the multivariate linear regression (MLR) algorithm as a reference. The results show that the visible atmospherically resistant index, vegetative index, and normalized difference vegetation index had the highest correlation with ground truth LCC, with a Pearson’s correlation coefficient of 0.95. All three regression algorithms (MLR, RF, and SVM) performed well on the training dataset (R2: 0.932–0.944, RMSE: 3.96 to 4.37), but performed differently on validation datasets with different growth stages, species, and nitrogen application levels. Compared to winter wheat species and nitrogen application levels, the growth stages had the greatest influence on the generalization ability of LCC estimation models, especially for the dough stage. At the dough stage, compared to MLR and RF, SVM performed best, with R2 increasing by 0.27 and 0.10, respectively, and RMSE decreasing by 1.13 and 0.46, respectively. Overall, this study demonstrated that the combination of UAV-derived multispectral VIs and the SVM regression algorithm could be successfully applied to map the LCC of winter wheat for different species, growth stages, and nitrogen stress conditions. Ultimately, this research is significant as it shows the successful application of UAV data for mapping the LCC of winter wheat across diverse conditions, offering valuable insights for precision nitrogen fertilization management.

One of the main components in a steam power plant is a boiler, which has the function to produce steam. Boiler efficiency is defined as the ratio of the amount of heat energy of the fuel to produce steam compared to the amount of fuel input to the boiler. Changes in coal quality influence combustion system settings, boiler efficiency, and impact on the environment. Research with an experimental method is needed to adjust combustion air with a variation of load and O2 trim values to get a complete combustion and optimum boiler efficiency and to see the effect on temperature and emission of flue gas. This paper has presented the data experiments, analyzing the effect of variations of O2 trim on the thermal efficiency of the boilers, flue gas temperature, and emission of the flue gas: NOx, CO, and CO2. It can be concluded that using the 4100 kcal/kg calorific value of coal, the optimum value of O2 trim of boiler efficiency at 72, 80, and 88% loads is 2%. Boiler efficiency will increase as the load increases. Boiler loads at 72%, 80%, and 88%, the maximum boiler efficiency is 83.33%, 83.42%, and 83.49%, respectively.KeywordsBoiler efficiencyO2 trimFlue gasExperimental

Artificial neural networks, which hold considerable potential for recognising and classifying spatial and temporal patterns, have been used as an efficient method for automatic traffic surveillance, which is an important research topic of intelligent transport systems. An important element in the performance of the neural networks is the composition of the input and output vectors, as well as the network architecture. However, there has been little research on the performance in relation to the attributes of the input and output vectors. In this research, various input vector properties were applied to the backpropagation model, which is the most popular neural network model, to see how the general performance would be affected by the different types of input vector. Experiments were performed with the inclusion of various grey levels, image sizes, edge detection images and combinations of edge and pixel grey information as the input vectors. The experimental results showed that the network performance, in terms of computing cost for training and prediction accuracy, was highly dependent on the characteristics of the input vectors. Two combined input vectors, the grey scale pixels and edge detection image, produced better prediction performance than either the grey values on the pixel or edges alone.