Related Experiment Videos
Predicting the heating value of MSW with a feed forward neural network
Changqing Dong1, Baosheng Jin, Daji Li
1Ministry of Education Key Laboratory on Clean Coal Power Generation and Combustion Technology, Thermoenergy Engineering Research Institute, Southeast University, Nanjing, 210096, PR China. bsjin@seu.edu.cn
Waste Management (New York, N.Y.)
|March 8, 2003
Summary
Predicting the heating value of municipal solid waste (MSW) using a feed forward neural network (FFNN) offers superior accuracy compared to traditional methods. This approach enhances the combustion efficiency of MSW incinerators.
Area of Science:
- Waste Management
- Combustion Engineering
- Artificial Intelligence
Background:
- The heating value of municipal solid waste (MSW) is crucial for optimizing the combustion efficiency of incinerators.
- Accurate determination of MSW heating value relies on its elementary chemical composition.
- Current methods for heating value determination include calorimetric measurements and empirical models.
Purpose of the Study:
- To investigate the correlation between the physical composition of MSW and its low heating value (LHV).
- To evaluate the efficacy of a feed forward neural network (FFNN) in predicting MSW's heating value based on its physical composition.
Main Methods:
- Analysis of the relationship between MSW physical composition and its low heating value (LHV).
- Development and application of a feed forward neural network (FFNN) model for LHV prediction.
- Comparison of FFNN prediction accuracy against conventional models.
Main Results:
- The study established a clear relationship between the physical composition of MSW and its LHV.
- The feed forward neural network (FFNN) demonstrated a strong capability in predicting the LHV of MSW.
- FFNN predictions of MSW's LHV significantly outperformed conventional prediction models.
Conclusions:
- Feed forward neural networks (FFNNs) provide a highly effective tool for predicting the low heating value (LHV) of municipal solid waste (MSW).
- Utilizing FFNNs for LHV prediction can lead to improved combustion efficiency in MSW incinerators.
- This AI-driven approach offers a more accurate alternative to traditional methods for assessing MSW heating value.