查詢結果分析
相關文獻
- 類神經網路於爆震偵測之應用
- 應用非監督性類神經網路於SPOT衛星影像分類之研究
- 鑽削加工的顫振控制與抑制
- 模糊自適應共振類神經網路在大地工程之應用
- 類神經網路技術介紹
- 資料探勘中集群模式與分類模式之建構--模糊自適應共振理論網路、分類迴歸樹與類神經網路之整合與應用
- 以學術部落格為主之個人化推薦系統
- 以行動用戶為主之多階段推薦系統
- Fuzz-ART Neural Networks for Predicting Chi-Chi Earthquake Induced Liquefaction in Yuan-Lin Area
- Neural Network Procedures for Taguchi's Dynamic Problems
頁籤選單縮合
題名 | 類神經網路於爆震偵測之應用= |
---|---|
作者 | 邱國慶; |
期刊 | 雲林工專學報 |
出版日期 | 19970600 |
卷期 | 16 1997.06[民86.06] |
頁次 | 頁233-251 |
分類號 | 462.15 |
語文 | chi |
關鍵詞 | 壓縮比; 點火提前; 快速傅立葉轉換; 類神經網路; 適應共振理論; Compression ratio; Spark advance; Knock; Signal processing; Fast fourier transform; Pattern recognition; Neural network; Adaptive resonance theory; |
中文摘要 | 現代火星塞引擎,在符合NOx及HC排量限制下,希望能將動力輸出提升至最大,並 盡量降低耗油量;此最佳狀況,可藉由增大壓縮比及提前點火角度來達成。更高的壓縮比及 點火提前,將使引擎的運轉更接近爆震底限。為了避免爆震發生,必須有一套可靠的爆震檢 測方法以做為控制點火提前角度之依據。 本文提出一種結合信號處理 - 快速傅立葉轉換 (fast fourier transform, FFT) 及類神經網路 - 適應共振理論 (Adaptive Resonance Theory, ART-2) 的爆震檢測方法,期能將引擎控制於最佳之狀況。 |
英文摘要 | Rising demands in development of modern spark ignited engines are to reduce fuel consumption under the condition of achieving maximum power output and at the same time keeping NOx and HC emission to an acdeptable mimimum. This optimization work can be done by increasing compression ratio and spark advance. As higher compression ratio means operating the engine closes to the knock limit and damage to the engine due to knock had to be avoided, a reliable algorithm had to be found for on line knock detection. In this paper, a approach was proposed for detecting knock. This strategy consists of signal processing based on Fast Fourier Transform (FFT) and pattern recognition based on neural network. The neural network architecture employed is based on the Adaptive Resonance Theory (ART-2) proposed by Carpenter and Grossberg. |
本系統之摘要資訊系依該期刊論文摘要之資訊為主。