頁籤選單縮合
題 名 | A Combination of Neural Network and Fuzzy Logic Algorithms for Adaptive Control of Arterial Blood Pressure |
---|---|
作 者 | Chen,Chin-te; Lin,Win-li; Kuo,Te-son; Chen,Po-quang; | 書刊名 | 醫學工程 |
卷 期 | 10:3 1998.06[民87.06] |
頁 次 | 頁21-32 |
分類號 | 410.1644 |
關鍵詞 | Neural network; Back-propagation; Fuzzy logic algorithm; Blood pressure control; |
語 文 | 英文(English) |
英文摘要 | The fast-acting drug sodium nitroprusside (SNP) is often administered to lower mean arterial blood pressure (MABP) in hospitalized patients. Closed-loop feedback controllers is necessary to maintain MABP near a desired level because of disturbances that perturb blood pressure, the changing condition of patient and the wide range of response characteristics among patients. The traditional control theory is difficult to implement on the nonlinear time-varying model of a patient's MABP under the inference of SNP infusion. In this paper, a new hybrid intelligent control strategy is proposed by combining neural neural and fuzzy logic algorithms to control the time-varying single-input/single-outpu (SISO) system. A parallel two-model multilayer neural net-work (MNN) controller with modified back-propagation training algorithm is designed to adoptively control MABP. The controller is associated with a fuzzy logic unit (FLU) to determine an incremental value and update the output weighting factor of the parallel two-model MNN controller for adequate control action. Extensive computer simulations indicate satisfactory performance and robustness of the proposed controller in the presence of much noise, over the full range of plant parameters, large variation of parameters, and no requirement of system parameters identification a priori. |
本系統中英文摘要資訊取自各篇刊載內容。