倒立摆是一种复杂、时变、非线性、强耦合、自然不稳定的高阶系统，许多抽象的控制理论概念都可以通过倒立摆实验直观的表现出来。基于人工神经网络BP算法的倒立摆小车实验仿真训练模型，其倒立摆BP网络为4输入3层结构。输入层分别为小车的位移和速度、摆杆偏离铅垂线的角度和角速度。隐含层单元数16个。输出层设置为1个输出单元。输入层采用Tansig函数，隐含层采用Logsig函数，输出层采用Purelin函数。用Matlab 6.5数值计算软件对模型进行学习训练，并与线性反馈控制逻辑算法对比，表明倒立摆控制BP算法精度高、收敛快，在非线性控制、鲁棒控制等领域具有良好的应用前景。 -Inverted pendulum is a complex, time-varying, nonlinear, strong coupling, the natural instability of the high-end systems, many of the abstract concept of control theory to pass through the inverted pendulum experiment demonstrated intuitive. Based on artificial neural network BP algorithm inverted pendulum experiment simulation training model car, the Inverted Pendulum BP network input 3-layer structure of 4. Input layer, respectively, for the car s displacement and speed of deviation from the plumb line placed under the angle and angular velocity. Hidden layer unit number 16. Output layer is set to an output unit. Tansig function using input layer, hidden layer Logsig function used, the output layer Purelin function. Numerical calculation using Matlab 6.5 software for learning and training model, and linear feedback control logic algorithm comparison, show that the inverted pendulum control of BP algorithm and high precision, fast convergence in nonlinear control, robust control and