An overview of the vehicle design along with description of all major hardware components and sensors is given . the arithmetic of auv control and navigation system is discussed in the paper . the methods of the implementation of gps and electronic compass aided heading control is provided 设计了水下航行器的总体导航与控制方案：采用gps与磁通门传感器相结合的路径规划与航向控制系统；以深度信息为参量的深度控制系统。
Aimed at overcoming the shortage of basic fuzzy controller , a kind of two stage fuzzy controller with scaling factors self - regulating and fuzzy pi controller is presented . when it is used in course control system , system " s anti - disturbance and response speed are satisfied 针对基本模糊控制器的不足，提出一种带模糊pi控制的参数自调整的双级模糊控制器，应用于船舶航向控制系统时，系统的抗扰性和响应速度方面均获得满意效果。
The paper is based on the project of national natural science foundation " the intelligent control system of ship on bumping and avoiding bumping " and " the study based on the impulsion response of light duty configuration , control and experiment method of high speed ship " . the fuzzy adaptive control is applied to ship steering . it is significant to improve automation technology of ship in china 本论文以国家自然科学基金项目“船舶碰撞与避碰的运动机理及计算机智能模拟系统研究”和“基于高速船轻型结构流体冲击响应、控制与实验方法研究”为依托，将模糊自适应控制应用于船舶的航向控制，这些研究将对我国船舶自动化水平的提高具有较大现实意义。
Based on the integration of fuzzy logic system and neural networks the thesis constructs a fuzzy neural network controller , which is used in ship course self - studying adaptive control system . because the fuzzy logic system is realized in neural network , the fuzzy neural network controller " s self - studying ability is raised greatly . substituting improved genetic algorithm for back propagation algorithm in fuzzy neural network controller ship course fuzzy neural network control system " s real - time ability is raised 针对模糊逻辑系统有很强的知识表达能力和逻辑推理能力，但自学习能力比较差，而人工神经网络在自学习和函数逼近方面又具有独特的优越性，将两者结合，用神经网络来实现模糊逻辑系统，构造了一个基于模糊神经网络控制武汉理工大学博士学位论文器的船舶航向自学习型自适应控制系统，提出用改进的遗传算法代替神经网络中经典的bp算法实现模糊神经网络的学习，综合船舶航向控制性能和节能要求，建立了系统的适应度函数。
In ship steering controller design , the nonlinear ship model should be written in siso strict feedback form . we start the recursive design with the system first state variable and continue with the second one . by introducing a change of coordinates , we choose lyapunov functions to stabilize the system and obtain the control law 在船舶航向控制方面，考虑船舶的稳态回转非线性，应用backstepping方法设计：首先把系统化成单入单出的严格反馈控制形式(呈下三角结构) ，假设系统后一个状态变量是前一个状态变量的虚拟控制，通过适当的变量代换，在每一步构造李亚普诺夫函数，使前一子系统在虚拟控制下渐近稳定，逐步递推出控制器控制规律，使整个系统在平衡点满足一致渐近稳定性。
To involve this problem , neural network algorithm combined the pid algorithm format a neuron pid algorithm , and a psd algorithm of adaptive control of autopilot of submarine is applicator to control the submarine ' s direction . the genetic algorithm was used to search for the optimize parameter of the pid algorithm 为了解决这一问题，本文讨论了利用神经网络学习理论结合pid算法而形成的神经元pid ，神经元自适应psd和神经网络pid控制算法并将之应用到了船舶的航向控制。
