Academia.eduAcademia.edu

Figure 3 – uploaded by Abdul Halim

See full PDFdownloadDownload figure
Back propagation derivation of Jacobian matrix weight arameters is described by the following function.

Figure 3 Back propagation derivation of Jacobian matrix weight arameters is described by the following function.

Related Figures (4)

Based on the input power measurement, a direct neural network control reference model of efficiency optimization is developed. The block diagram of the proposed neural network controller for efficiency optimization of a variable speed compressor drive is presented in Fig. 1. The controller is implemented through the use of a digital signal processor as indicated by dashed outline in Fig. 1. Fig. 1. Diagram block model reference neural network efficiency optimization of a scalar control induction motor drive system
Based on the input power measurement, a direct neural network control reference model of efficiency optimization is developed. The block diagram of the proposed neural network controller for efficiency optimization of a variable speed compressor drive is presented in Fig. 1. The controller is implemented through the use of a digital signal processor as indicated by dashed outline in Fig. 1. Fig. 1. Diagram block model reference neural network efficiency optimization of a scalar control induction motor drive system
Fig. 2. Diagram block of neural network efficiency optimization controller Basically, to design the neural network controller, the number of inputs and outputs neuron at each layer are equal to the number of input and outpu respective y. Further the number of signals of the system hidden layers and the total neurons is depended on the complexity of the system and the required training accuracy. Based on the type of the task to be performed, the structure of the controller is shown in Fig.2. proposed neural network
Fig. 2. Diagram block of neural network efficiency optimization controller Basically, to design the neural network controller, the number of inputs and outputs neuron at each layer are equal to the number of input and outpu respective y. Further the number of signals of the system hidden layers and the total neurons is depended on the complexity of the system and the required training accuracy. Based on the type of the task to be performed, the structure of the controller is shown in Fig.2. proposed neural network
Fig. 3. Simulation results when the controller was switched from the NNV/f to the NNEOC at 3 s: (a) the speed response, (b) the stator voltage response and (c) the input power response.
Fig. 3. Simulation results when the controller was switched from the NNV/f to the NNEOC at 3 s: (a) the speed response, (b) the stator voltage response and (c) the input power response.
Fig. 4. Experimental results when the controller was switched from the NNV/f to the NNEOC at 1 s: (a) the speed response, (b) the stator voltage response and (c) the input power response Fig. 4 show responses of the rotor speed, electromagnetic torque, stator voltage and input power motor when the controller is switched from the neural network constant Volt per Hertz to the proposed controller at a speed reference command of 500 rpm.
Fig. 4. Experimental results when the controller was switched from the NNV/f to the NNEOC at 1 s: (a) the speed response, (b) the stator voltage response and (c) the input power response Fig. 4 show responses of the rotor speed, electromagnetic torque, stator voltage and input power motor when the controller is switched from the neural network constant Volt per Hertz to the proposed controller at a speed reference command of 500 rpm.
Related topics:
Electric Machines and DrivesInduction MotorNeural network control
580 California St., Suite 400
San Francisco, CA, 94104
© 2025 Academia. All rights reserved