This paper presents modelling of a post-combustion CO2 capture process using bootstrap aggregated extreme learning machine （ELM）. ELM randomly assigns the weights between input and hidden layers and obtains the weig...This paper presents modelling of a post-combustion CO2 capture process using bootstrap aggregated extreme learning machine （ELM）. ELM randomly assigns the weights between input and hidden layers and obtains the weights between the hidden layer and output layer using regression type approach in one step. This feature allows an ELM model being developed very quickly. This paper proposes using principal component regression to obtain the weights between the hidden and output layers to address the collinearity issue among hidden neuron outputs. Due to the weights between input and hidden layers are randomly assigned, ELM models could have variations in performance. This paper proposes combining multiple ELM models to enhance model prediction accuracy and reliability. To predict the CO2 production rate and CO2 capture level, eight parameters in the process were utilized as model input variables： inlet gas flow rate, CO2 concentration in inlet flow gas, inlet gas temperature, inlet gas pressure, lean solvent flow rate, Jean solvent temperature, lean loading and reboiler duty. The bootstrap re-sampling of training data was applied for building each single ELM and then the individual ELMs are stacked, thereby enhancing the model accuracy and reliability. The bootstrap aggregated extreme learning machine can provide fast learning speed and good generalization performance, which will be used to optimize the CO2 capture process.展开更多
基金The work was supported by the EU through the project ＂Research and Development in Coal-fired Supercritical Power Plant with Post-combustion Carbon Capture using Process Systems Engineering techniques＂ （Project No. PIRSES-GA-2013-612230） and National Natural Science Foundation of China （61673236）.
文摘This paper presents modelling of a post-combustion CO2 capture process using bootstrap aggregated extreme learning machine （ELM）. ELM randomly assigns the weights between input and hidden layers and obtains the weights between the hidden layer and output layer using regression type approach in one step. This feature allows an ELM model being developed very quickly. This paper proposes using principal component regression to obtain the weights between the hidden and output layers to address the collinearity issue among hidden neuron outputs. Due to the weights between input and hidden layers are randomly assigned, ELM models could have variations in performance. This paper proposes combining multiple ELM models to enhance model prediction accuracy and reliability. To predict the CO2 production rate and CO2 capture level, eight parameters in the process were utilized as model input variables： inlet gas flow rate, CO2 concentration in inlet flow gas, inlet gas temperature, inlet gas pressure, lean solvent flow rate, Jean solvent temperature, lean loading and reboiler duty. The bootstrap re-sampling of training data was applied for building each single ELM and then the individual ELMs are stacked, thereby enhancing the model accuracy and reliability. The bootstrap aggregated extreme learning machine can provide fast learning speed and good generalization performance, which will be used to optimize the CO2 capture process.
