Minimized sodium nitroprusside for mean arterial pressure regulation based on fuzzy rules emulated networks

Abstract

An automatic regulation of mean arterial pressure (MAP) through the intravenous infusion of sodium nitroprusside (SNP) based on self adjustable networks called Multi-input Fuzzy Rules Emulated Networks (MIFREN) and its proposed learning algorithm is introduced in this article. To optimize the regulation performance and SNP dose, the estimated cost function is obtained by the first self adjustable network used to design the nearly optimum controller. The second network is designed as the direct controller via the human knowledge through the defined If-Then rules. The infusion rate of SNP is generated as the control effort to regulate MAP with the possible minimized drug level. All designed parameters such as the learning rates and some constant parameters have been selected to guarantee the system stability and bounded signals by the proof of the proposed theorem. The satisfied performance of the proposed controller is represented by computer simulations and comparison results with other control techniques are demonstrated the lower level of SNP at the steady state.