Limits...
A novel memristive multilayer feedforward small-world neural network with its applications in PID control.

Dong Z, Duan S, Hu X, Wang L, Li H - ScientificWorldJournal (2014)

Bottom Line: More specially, a mathematical closed-form charge-governed memristor model is presented with derivation procedures and the corresponding Simulink model is presented, which is an essential block for realizing the memristive synapse and the activation function in electronic neurons.Furthermore, we investigate a more intelligent memristive PID controller by incorporating the proposed MFSNN into intelligent PID control based on the advantages of the memristive MFSNN on computation speed and accuracy.Finally, numerical simulations have demonstrated the effectiveness of the proposed scheme.

View Article: PubMed Central - PubMed

Affiliation: School of Electronics and Information Engineering, Southwest University, Chongqing 400715, China.

ABSTRACT
In this paper, we present an implementation scheme of memristor-based multilayer feedforward small-world neural network (MFSNN) inspirited by the lack of the hardware realization of the MFSNN on account of the need of a large number of electronic neurons and synapses. More specially, a mathematical closed-form charge-governed memristor model is presented with derivation procedures and the corresponding Simulink model is presented, which is an essential block for realizing the memristive synapse and the activation function in electronic neurons. Furthermore, we investigate a more intelligent memristive PID controller by incorporating the proposed MFSNN into intelligent PID control based on the advantages of the memristive MFSNN on computation speed and accuracy. Finally, numerical simulations have demonstrated the effectiveness of the proposed scheme.

Show MeSH
The simulation results of the memristive neural network PID controller (rin(k) = 1.0) under a different rewiring probability P. (a) The step response curve. (b) The error curves. (c) The curves of the control parameters when the rewiring probability P = 0.08.
© Copyright Policy - open-access
Related In: Results  -  Collection


getmorefigures.php?uid=PMC4150482&req=5

fig12: The simulation results of the memristive neural network PID controller (rin(k) = 1.0) under a different rewiring probability P. (a) The step response curve. (b) The error curves. (c) The curves of the control parameters when the rewiring probability P = 0.08.

Mentions: Figure 12(a) shows the input signal (step response curve rin(k) = 1.0) and the output curves under a different rewiring probability P. As can be seen from the figure, when the time t = 0.5 s, the whole system reaches the steady state. Making a further analysis, we can conclude that when the rewiring probability P = 0, the memristive neural network keeps regularly in architecture. Its respond speed is slower than that of network when the rewiring probability P = 0.08 and P = 0.1. Moreover, Figure 12(b) exhibits the error curves between the input signal and the output signal correspondingly. When the rewiring probability P = 0.08 and P = 0.1, the network spends less time on approaching the predefined approximation error than the regular network (when P = 0). Figure 12(c) shows the output variables of the memristive multilayer feedforward small-world neural network when P = 0.08 which are the control parameters kp, ki, and kd, correspondingly.


A novel memristive multilayer feedforward small-world neural network with its applications in PID control.

Dong Z, Duan S, Hu X, Wang L, Li H - ScientificWorldJournal (2014)

The simulation results of the memristive neural network PID controller (rin(k) = 1.0) under a different rewiring probability P. (a) The step response curve. (b) The error curves. (c) The curves of the control parameters when the rewiring probability P = 0.08.
© Copyright Policy - open-access
Related In: Results  -  Collection

Show All Figures
getmorefigures.php?uid=PMC4150482&req=5

fig12: The simulation results of the memristive neural network PID controller (rin(k) = 1.0) under a different rewiring probability P. (a) The step response curve. (b) The error curves. (c) The curves of the control parameters when the rewiring probability P = 0.08.
Mentions: Figure 12(a) shows the input signal (step response curve rin(k) = 1.0) and the output curves under a different rewiring probability P. As can be seen from the figure, when the time t = 0.5 s, the whole system reaches the steady state. Making a further analysis, we can conclude that when the rewiring probability P = 0, the memristive neural network keeps regularly in architecture. Its respond speed is slower than that of network when the rewiring probability P = 0.08 and P = 0.1. Moreover, Figure 12(b) exhibits the error curves between the input signal and the output signal correspondingly. When the rewiring probability P = 0.08 and P = 0.1, the network spends less time on approaching the predefined approximation error than the regular network (when P = 0). Figure 12(c) shows the output variables of the memristive multilayer feedforward small-world neural network when P = 0.08 which are the control parameters kp, ki, and kd, correspondingly.

Bottom Line: More specially, a mathematical closed-form charge-governed memristor model is presented with derivation procedures and the corresponding Simulink model is presented, which is an essential block for realizing the memristive synapse and the activation function in electronic neurons.Furthermore, we investigate a more intelligent memristive PID controller by incorporating the proposed MFSNN into intelligent PID control based on the advantages of the memristive MFSNN on computation speed and accuracy.Finally, numerical simulations have demonstrated the effectiveness of the proposed scheme.

View Article: PubMed Central - PubMed

Affiliation: School of Electronics and Information Engineering, Southwest University, Chongqing 400715, China.

ABSTRACT
In this paper, we present an implementation scheme of memristor-based multilayer feedforward small-world neural network (MFSNN) inspirited by the lack of the hardware realization of the MFSNN on account of the need of a large number of electronic neurons and synapses. More specially, a mathematical closed-form charge-governed memristor model is presented with derivation procedures and the corresponding Simulink model is presented, which is an essential block for realizing the memristive synapse and the activation function in electronic neurons. Furthermore, we investigate a more intelligent memristive PID controller by incorporating the proposed MFSNN into intelligent PID control based on the advantages of the memristive MFSNN on computation speed and accuracy. Finally, numerical simulations have demonstrated the effectiveness of the proposed scheme.

Show MeSH