查詢結果分析
相關文獻
- 使用粒子群聚演算法最佳化PID控制器
- Design and Analysis of a New Pid Fuzzy Controller
- Spacecraft Attitude Tracking Control: Robust PID Design Approach
- Robust D-Stability Analysis of Linear Uncertain Discrete Time-Delay Systems
- 以Mixed Gain Scheduling/MRAC控制器應用於超精密定位系統之研究
- 公開金鑰型密碼系統安全協定強健性分析
- Design of PID Controller for DC Servomotor Systems
- Tuning PID Controllers for Processes with Inverse Response Using Artificial Neural Networks
- Designing Optimal PID Controllers for Interval Plants
- Fuzzy Controller Design and Application in Aerospace Engineering
頁籤選單縮合
題名 | 使用粒子群聚演算法最佳化PID控制器=Using the Particle Swarm Algorithm to Optimize the PID Controller |
---|---|
作者姓名(中文) | 蔡貴夙; 陳詩豐; | 書刊名 | 龍華科技大學學報 |
卷期 | 19 民94.09 |
頁次 | 頁1-12 |
分類號 | 448.942 |
關鍵詞 | PID控制器; 粒子群聚演算法; 最佳化控制; 適應函數; 強健性; PID control; Particle swarm algorithm; Optimization control; Fitness function; Robustness; |
語文 | 中文(Chinese) |
中文摘要 | 在本研究中試著將粒子群聚最佳化(Particle Swarm Optimization, PSO)演算法運用在搜尋PID控制器的參數上,而在搜尋的過程中以不同的性能指標去做為判斷性能優劣的依據。在性能指標方面採用下列三種,積分平方誤差法(Integral square-error)、積分絕對值誤差(Integral absolute-error)、積分時間乘絕對值誤差(Integral-of-time-multiplied absolute-error)。在論文中包括使用系統參數鑑定的方式得到直流伺服馬達的轉移函數,並利用粒子群聚演算法搜尋PID參數,另外在將模擬的結果跟遺傳基因演算法來做比較。結果提出以粒子群聚演算法來調整PID參數所得到的運算時間比遺傳基因演算法運算時間還要快速。另一方面,此以粒子群聚演算法來最佳化PID參數之系統針對不同適應函數的差異也被證明具有強健性。 |
英文摘要 | In this paper, the particle swarm optimization (PSO), a new nature-inspired optimization technique; therefore, is used to search for the parameters of PID controllers. Through the search period, the system performance of the time response is evaluated by the fitness function that is computed via the ISE (Integral Square-Error), IAE (Integral Absolute-Error), or ITAE (Integral-of-time-multiplied Absolute-Error). In addition, the optimization results of the PID controller by the particle swarm algorithm are compared with those by the Genetic Algorithm. The results of the experiment and simulation show that the seeking time to tune the PID parameters by using the particle swarm algorithm is faster than by using the GA method. On the other hand, the system is proven for robustness with respect to the different fitness functions. |
本系統之摘要資訊系依該期刊論文摘要之資訊為主。