Prediction of PCDDs/PCDFs emissions from municipal incinerators by genetic programming and neural network modeling

Abstract

The potential emissions of PCDDs/PCDFs from municipal incinerators have received wide attention in the last decade. Concerns were frequently addressed in the scienti®c community with regard to the aspects of health risk assessment, combustion criteria, and the public regulations. Without accurate prediction of PCDD/PCDF emissions, however, reasonable assessment of the health risk and essential appraisal of the combustion criteria or public regulations cannot be achieved. Previous prediction techniques for PCDD/PCDF emissions were limited by the linear models based on a least-square-based analytical framework, such that the inherent non-linear features cannot be explored via advanced system identi®cation techniques. Recent development of genetic algorithms and neural network models has resulted in a dramatic growth of the use of non-linear structure for optimization and prediction analyses. Such approaches with the inherent thinking of arti®cial intelligence were found useful in this study for the identi®cation of non-linear structure in relation to the PCDD/PCDF emissions from municipal incinerators. Examples were drawn from the emission test of PCDDs/ PCDFs through the¯ue gas discharge from several municipal incinerators in both Europe and North America. Although the neural network model may exhibit better predictive results based on the performance indexes of percentage error and mean square error, model structure cannot be directly identi®ed and expressed for illustrating the possible chemical mechanism with respect to the PCDD/PCDF emissions. However, the tree-structured genetic algorithms, or so-called genetic programming, can rapidly screen out those applicable non-linear models as well as identify the optimal system parameters simultaneously in a highly complex system based on a small set of samples.

Soil moisture estimation in a semiarid watershed using RADARSAT‐1 satellite imagery and genetic programming

“…The search for the best result in the evolutionary process involves applying the Darwinian principle of nature selection (survival of the fittest) including crossover, mutation, duplication, and deletion. Regression models generated from the GP are free from any particular model structure [ Chang and Chen , 2000]. It could be the best solver for searching highly nonlinear spaces for global optima via adaptive strategies.…”

“…It could be the best solver for searching highly nonlinear spaces for global optima via adaptive strategies. In recent years, the GP has been proved useful for solving highly nonlinear environmental problems [ Chang and Chen , 2000].…”

An Overview of Artificial Intelligence Application for Optimal Control of Municipal Solid Waste Incineration Process

“…Studies utilizing neural network algorithms include BPNN based on genetic programming for parameter identification [117], and BPNN based on the genetic algorithm to optimize parameters [37]. The studies utilizing the SVR algorithm include SVR based on the mechanism for feature selection [47] and selective ensemble SVR based Clearly, the aforementioned detection process of DXN concentration lacks real-time capabilities, making it challenging to support the intelligent optimal control of the MSWI process with dynamic changes in operating conditions.…”

Formation, Measurement, and Control of Dioxins from the Incineration of Municipal Solid Wastes: Recent Advances and Perspectives

“…Most of the results showed the t -ratios at the 5% level of significance and satisfactory R 2 and F values. Then, they put forward nonlinear models with the help of genetic algorithms using the same database and made progress compared to previous research . Bunsan et al selected five input variables through principal component analysis (PCA) and performed a three-layer back-propagation neural network analysis to forecast the dioxin emission of a municipal solid waste incinerator in Taiwan successfully.…”