“…Hybrid modelling or multiple methods in combination approach has also attracted the attention of scholars. For instance, Yi et al [ 16 ] proposed a hybrid model based on BPNN and radial basis function (RBF) to implement NOx emission prediction from the sintering plants. Okoji et al [ 17 ] coupled ANN networks and fuzzy logic to develop an adaptive neuro‐fuzzy inference system for NOx emission prediction.…”
Accurately predicting trends in NOx emission is essential for effectively controlling pollution in municipal solid waste incineration (MSWI) power plants. However, the MSWI process exhibits notable dynamic nonlinearity, time series characteristics, and fluctuations that are distinct from those present in fossil fuel combustion processes. Therefore, the model must possess excellent capabilities in handling time series and nonlinear features while achieving adaptive updates to account for complex working conditions. To address these issues, we have developed a robust prediction model for NOx emission trends using the bi‐directional long short‐term memory (Bi‐LSTM) deep learning algorithm. This model encompasses maximum information coefficient and expert experience for input variables selection, parameter optimization using the linear inertial weight particle swarm algorithm (LDWPSO), and an adaptive update strategy based on probabilistic statistics. The prediction performance of this model was compared to that of the traditional and widely used backpropagation neural network (BPNN), extreme learning machine (ELM), and LSTM. Furthermore, we verified the adaptive update effect of the proposed model using additional data. The results demonstrate that the proposed model exhibits robust prediction and adaptive capabilities. This study's originality is presenting a satisfactory trend prediction for NOx emission from the MSWI process using an adaptive LDWPSO‐(Bi‐LSTM) model. It will be essential for the optimization and control of NOx emissions from the MSWI process.
“…Hybrid modelling or multiple methods in combination approach has also attracted the attention of scholars. For instance, Yi et al [ 16 ] proposed a hybrid model based on BPNN and radial basis function (RBF) to implement NOx emission prediction from the sintering plants. Okoji et al [ 17 ] coupled ANN networks and fuzzy logic to develop an adaptive neuro‐fuzzy inference system for NOx emission prediction.…”
Accurately predicting trends in NOx emission is essential for effectively controlling pollution in municipal solid waste incineration (MSWI) power plants. However, the MSWI process exhibits notable dynamic nonlinearity, time series characteristics, and fluctuations that are distinct from those present in fossil fuel combustion processes. Therefore, the model must possess excellent capabilities in handling time series and nonlinear features while achieving adaptive updates to account for complex working conditions. To address these issues, we have developed a robust prediction model for NOx emission trends using the bi‐directional long short‐term memory (Bi‐LSTM) deep learning algorithm. This model encompasses maximum information coefficient and expert experience for input variables selection, parameter optimization using the linear inertial weight particle swarm algorithm (LDWPSO), and an adaptive update strategy based on probabilistic statistics. The prediction performance of this model was compared to that of the traditional and widely used backpropagation neural network (BPNN), extreme learning machine (ELM), and LSTM. Furthermore, we verified the adaptive update effect of the proposed model using additional data. The results demonstrate that the proposed model exhibits robust prediction and adaptive capabilities. This study's originality is presenting a satisfactory trend prediction for NOx emission from the MSWI process using an adaptive LDWPSO‐(Bi‐LSTM) model. It will be essential for the optimization and control of NOx emissions from the MSWI process.
“…In recent years, many scholars have started to use machine learning and deep learning methods to study sintered flue gas management. In sintering production, neural network algorithms have achieved better results in production monitoring [6,7], quality prediction [8,9], environmental protection [10], etc. In summary, it can be seen that the source prediction of sulphur oxide and nitrogen oxide in sinter flue gas can be empowered by big data technology to adjust the desulphurization and denitrification operation in time.…”
In the long process of iron and steel, the sintering process has the largest amount of flue gas emissions, many types of pollutants and high concentrations. The source control of SO 2 and NOx in sintering flue gas through digital technology has become a new emission reduction technology. In this study, the BP neural network model (BP-NN) is optimized by using the particle swarm algorithm (PSO) to form the PSO-BPNN model, which effectively improves the characteristics of BP-NN with slow convergence speed and easily falls into local minima, and improves the learning ability and generalization. The test results show that the PSO-BP-NN algorithm not only has fast convergence speed and high prediction accuracy, but also has smaller training and inspection errors. In addition, this model combines process theory and feature engineering selection of parameters, which effectively improves the accuracy of the model and the interpretability of the results based on the linkage of process knowledge, and has certain analytical significance for the source management and post-treatment of sintered flue gas.
“…RBF neural network is widely used in many places, and it is nonlinear multilayer feedforward networks, both are approximators, which can approximate any continuous, nonlinear function. Similarly, for any RBF neural network, there will always be a BP neural network corresponding to it, but there are many differences between the two [ 27 – 29 ]. Therefore, in this paper, first of all, the detection and tracking of moving objects: the detection of moving objects is realized through background modeling.…”
In sports, because the movement of the human body is composed of the movements of the human limbs, and the complex and changeable movements of the human limbs lead to various and complicated movement modes of the entire human body, it is not easy to accurately track the human body movement. The recognition of human characteristic behavior belongs to a higher level computer vision topic, which is used to understand and describe the characteristic behavior of people, and there are also many research difficulties. Because the radial basis fuzzy neural network has the characteristics of parallel processing, nonlinearity, fault tolerance, self-adaptation, and self-learning, it has the advantage of high recognition efficiency when it is applied to the recognition of intersecting features and incomplete features. Therefore, this paper applies it to the analysis of the human body information recognition model in sports. The research results show that the human body information recognition model proposed in this paper has a high recognition accuracy and can detect the movement state of people in sports in real time and accurately.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.