| URN | etd-0806119-111750 | Statistics | This thesis had been viewed 136 times. Download 5 times. |
| Author | Chieh-cheng Yang | ||
| Author's Email Address | benny0204@kimo.com | ||
| Department | Institute Of Mechanical Engineering | ||
| Year | 2018 | Semester | 2 |
| Degree | Master | Type of Document | Master's Thesis |
| Language | zh-TW.Big5 Chinese | Page Count | 63 |
| Title | Artificial Neural Networks Applied to Temperature Control for A Variable Frequency Freezer | ||
| Keyword | |||
| Abstract | The modern freezer systems apply variable frequency driver techniques for Energy saving, which also called variable refrigerant flow (VRF) freezer systems. The VRF freezer systems can change the refrigerant flow by changing the compressor speed, and usually applied to refrigeration. In this study, the dynamic model for a variable frequency freezer is established, and a conventional PI controller designed to temperature control for the freezer. The design of PID controller is difficult, because the cooling load of freezer is usually varied and the nonlinear dynamic model of freezer is difficult to be obtained. ¡@¡@The modern VRF freezer systems applied variable speed compressors with nonlinear characteristics, and the varied freezer space and refrigerating load requirements lead the PID control becomes insufficient for modern VRF freezer systems. This study utilizes the neural network controls applied to VRF freezer system for temperature control, which can enhance the adaptability and saving energy. The proposed neural network has three layers, and the hidden layer outputs are functional by bipolar sigmoid function on output layer to be the output signal. The simulation results reveal that the proposed neural control system can enhance the adaptability and be available with better energy saving performance than conventional PID control. |
||
| Advisor Committee | |||
| Files | indicate access worldwide | ||
| Date of Defense | 2019-06-18 | Date of Submission | 2019-08-06 |