CAJ | 학술논문

针对非线性系统的模型预测控制问题，提出了一种基于线性近似和神经网络逼近的控制算法。用Taylor 级数展开法对非线性系统进行线性近似时，要求对象系统中的非线性函数必须连续可微。为了突破这一限制，引入了 Stirling 插值公式线性近似法，拓展了可处理的非线性系统范围。通过对线性化过程中产生的非线性高阶项进行径向基函数（radial basis function，RBF）神经网络逼近，显著提高了对象系统模型精确度。为了降低数值计算复杂度，将控制性能指标函数重构为易于处理的二次型最优化问题，通过对该二次型最优化问题的求解得到了最优控制序列。控制过程考虑了约束条件的影响以模拟真实的工业生产过程。仿真结果证明了所提出预测控制方案的有效性。
침대비선성계통적모형예측공제문제，제출료일충기우선성근사화신경망락핍근적공제산법。용Taylor 급수전개법대비선성계통진행선성근사시，요구대상계통중적비선성함수필수련속가미。위료돌파저일한제，인입료 Stirling 삽치공식선성근사법，탁전료가처리적비선성계통범위。통과대선성화과정중산생적비선성고계항진행경향기함수（radial basis function，RBF）신경망락핍근，현저제고료대상계통모형정학도。위료강저수치계산복잡도，장공제성능지표함수중구위역우처리적이차형최우화문제，통과대해이차형최우화문제적구해득도료최우공제서렬。공제과정고필료약속조건적영향이모의진실적공업생산과정。방진결과증명료소제출예측공제방안적유효성。
A constrained model predictive control algorithm is proposed based on linearization and neural network approach.The nonlinear system must be continuously differentiable when using the Taylor series ex-pansion linearization method.In order to break through this restriction,we introduce Stirling’s interpolation formula method.In the interest of improving the precision of the model,we estimate the high-order terms asso-ciated with the linearization using a radial basis function (RBF)neural network.For the sake of reducing the complexity of computation,we reformulate the control performance index to a quadratic optimization problem, and obtain the optimization control sequences by solving the quadratic optimization problem.The constraint con-ditions are considered during the control process to simulate actual industrial production processes.The simula-tion results demonstrate the effectiveness of the proposed model predictive control scheme.