Drying is essential for the production of fibre after retting process. Flax fibre was subjected to microwave drying at controlled temperatures to study the change in drying rate and qualities. The rate of drying was t...Drying is essential for the production of fibre after retting process. Flax fibre was subjected to microwave drying at controlled temperatures to study the change in drying rate and qualities. The rate of drying was then compared with conventional hot air drying. The product temperature was maintained at 40 ℃, 60 ℃or 80 ℃ for both microwave and hot air drying. The initial moisture content of flax fibre was about 60% （wet basis）. The microwave drying was conducted in a microwave apparatus which recorded mass, product temperature, incident microwave power, reflected microwave power and inlet/outlet air temperature. The final moisture content was set to 9% （wet basis）. Microwave-convective drying ensured about 30% to 70% reduction of drying time for drying flax fibre as compared to hot air drying. Curve fitting with different mathematical models were carried out. While a significant difference in colorimeter-assessed co/our existed between microwave-convective dried flax fibre and hot air dried flax fibre. The tensile strength of flax fibre, measured with an Instron apparatus, increased with an increase in the processing temperature of both processes. Hot air dried flax fibre showed the greatest tensile strength and modulus of elasticity at processing temperatures of 60 ℃ and 80 ℃.展开更多
Artificial neural network has unique advantages for massively parallel processing, distributed storage capacity and self-learning ability. The paper mainly constructs neural network identifier and neural network contr...Artificial neural network has unique advantages for massively parallel processing, distributed storage capacity and self-learning ability. The paper mainly constructs neural network identifier and neural network controller for system identification and control on temperature and hmnidity of heating and drying system of materials. And the paper introduces the structure and principles of neural network, and focuses on analyzing learning algorithm, training algorithm and limitation of the most widely applied multi-layer feed-forward neural network （ BP network） , based on which the paper proposes introducing momentum to improve BP network.展开更多
文摘Drying is essential for the production of fibre after retting process. Flax fibre was subjected to microwave drying at controlled temperatures to study the change in drying rate and qualities. The rate of drying was then compared with conventional hot air drying. The product temperature was maintained at 40 ℃, 60 ℃or 80 ℃ for both microwave and hot air drying. The initial moisture content of flax fibre was about 60% （wet basis）. The microwave drying was conducted in a microwave apparatus which recorded mass, product temperature, incident microwave power, reflected microwave power and inlet/outlet air temperature. The final moisture content was set to 9% （wet basis）. Microwave-convective drying ensured about 30% to 70% reduction of drying time for drying flax fibre as compared to hot air drying. Curve fitting with different mathematical models were carried out. While a significant difference in colorimeter-assessed co/our existed between microwave-convective dried flax fibre and hot air dried flax fibre. The tensile strength of flax fibre, measured with an Instron apparatus, increased with an increase in the processing temperature of both processes. Hot air dried flax fibre showed the greatest tensile strength and modulus of elasticity at processing temperatures of 60 ℃ and 80 ℃.
文摘Artificial neural network has unique advantages for massively parallel processing, distributed storage capacity and self-learning ability. The paper mainly constructs neural network identifier and neural network controller for system identification and control on temperature and hmnidity of heating and drying system of materials. And the paper introduces the structure and principles of neural network, and focuses on analyzing learning algorithm, training algorithm and limitation of the most widely applied multi-layer feed-forward neural network （ BP network） , based on which the paper proposes introducing momentum to improve BP network.
