Risk probability predictions for coal enterprise infrastructure projects in countries along the Belt and Road Initiative

The Belt and Road Initiative has significantly promoted the construction and development of coal enterprises along the Belt and Road through the building of a new platform that encourages global economic cooperation. This study examines problems caused by the uncertainty of risk occurrence during the process of coal enterprise construction as part of the Belt and Road Initiative. Consequently, the study identifies and classifies various risk factors. In total, 11 types of risks and 39 risk factors involved in the construction process are summarized. These include natural, cultural, religious, marketing, and outsourcing-related risks. A prediction indicator system was also established to apply to the risk occurrence probability related to coal mine construction along the Belt and Road. In this regard, the study embedded an improved artificial fish swarm algorithm (IAFSA) into a cerebellar model articulation controller (CMAC) neural network model and collected risk probability details for the construction of the Barapukuria Coal Mine in Bangladesh from 2013 to 2018 as sample data. By researching the model and sample, this study obtained various risk occurrence probability intervals. Moreover, diversified risk probabilities were verified and predicted. Finally, this study empirically proves that an IAFSA–CMAC parallel coupling algorithm is able to achieve precise predictions about risks. This finding has great significance for risk management and control in the coal enterprises of countries along the Belt and Road.     

Robust CMAC control schemes for dynamic trajectory following

Abstract

Improved robust CMAC control schemes are proposed for tracing dynamic trajectories in this paper. There are two main structures in the proposed control schemes: one is the robust controller and the other is the improved CMAC network. The robust controller technique can achieve a certain goal without concern for instability of the controlled system in the presence of significant plant uncertainties if the nominal parameter is roughly estimated. Next, in order to reduce the tracing error, a suitable nominal parameter needs to be chosen. Thus, the improved CMAC learning approach under the robust control structure, using the concept of credit assignment, will be employed to determine control variables that can trace other states repeatedly during control processes. Finally, simulation results demonstrate the capability of the proposed control schemes to trace dynamic trajectories.     

CMAC改进算法在电动负载模拟器的应用

在电动负载模拟器的控制系统设计中,其参数优化一般需要大量试验.根据负载模拟器的工作原理建立了伺服电机的数学模型,在分析CMAC神经网络控制结构的基础上,引入了更新系数和补偿环节,提出了一种基于CMAC神经网络的改进算法.对各控制参数进行了寻优,获得了参数的选择域.通过对系统的数字仿真表明,该方法可稳定地跟踪非线性输入,...     

基于CMAC滑模控制的双马达同步技术研究

以大型起重机双卷扬系统为研究对象,针对起升过程中存在的双马达同步误差问题,提出一种基于小脑神经网络(CMAC)滑模控制方法,充分利用CMAC响应速度快及滑模变结构控制(SMC)抗干扰能力强的特点,以解决传统控制方法鲁棒性差的问题;在控制过程中采用交叉耦合控制方式,并根据液压系统动态特性将液压泵出口压力差以及吊钩的倾斜角度作为控制指标进行仿真,最后以起升工况进行实验研究。结果表明:与传统方法相比,所提出的控制策略能有效提高两个马达的同步控制精度,抗干扰能力强,满足实际工况需要。     

CMAC与卡尔曼滤波复合控制AVR的优化研究

电力系统的动态稳定已成为现代电力系统工程中一个关键性问题。同步发电机自动电压调节器(Automatic Voltage Regular, AVR)对于电力系统的稳定发挥着重要作用。为使AVR系统适应更加复杂的工作环境,增强AVR抵抗外界随机干扰和快速跟随输入信号的能力,提出了小脑模型神经网络、积分分离式 (Proportional Integral Differential, PID)控制器和卡尔曼滤波器复合控制的策略。通过对云南某水电厂的一台发电机AVR模型的仿真研究可知:该控制策略对于方波输入信号有很强的跟随能力,系统响应速度快,调节时间短,并且对控制通道和测量通道的干扰有很强的抑制作用。仿真结果充分验证了该控制策略的可行性,有助于电力系统的稳定。     

小脑模型神经网络控制器在天线跟踪指向控制中的应用

分析了天线跟踪指向控制系统的特点和影响系统跟踪性能的主要因素,建立了系统数学模型。根据系统特点,给出了小脑模型神经网络控制器(CMAC)和PID相结合的复合自适应控制方法的设计过程,并分析了该算法适用于天线跟踪指向控制系统的优势。该方法利用传统的PID控制,结合CMAC神经网络算法的快速自学习、精确逼近的优点,既满足了天线跟踪指向控制系统快速实时跟踪的要求,又提高了跟踪精度和跟踪平稳性。仿真结果表明,该方法对摩擦力矩有很好的抑制作用,跟踪精度较单独采用PID控制提高一个数量级,且输出稳定,具有较强的鲁棒性。     

堆垛机速度智能控制的优化研究

采用模糊控制技术与小脑模型神经网络(CMAC)相结合的方式进行堆垛机的速度控制,克服单独运用模糊控制或CMAC神经网络的缺点,使系统既具有模糊控制的灵活性和强适应性,又兼具神经网络的学习能力,并且采用遗传算法对控制器的输入输出比例因子及连接权值进行寻优.仿真结果表明:该控制系统提高了系统的稳定性、鲁棒性和控制精度,使系统的综合性能得到显著改善.     

混合系统CMAC直接逆模型控制

CMAC神经网络是一种具有线性结构、算法简单的局部逼近网络.考虑混合系统中参数不确定等因素影响,研究了一类混合系统的CMAC神经网络控制器的设计,采用直接逆模型控制方式,不仅可以缩短网络训练时间,而且实现了一类混合系统的快速跟踪控制.理论分析和仿真结果均表明该控制策略对于混合系统控制的有效性.     

基于PSO算法的FCMAC控制器及其在主汽温控制中的应用

模糊CMAC神经控制器能反映人脑认知的模糊性和连续性,它采用高斯函数作为模糊隶属函数,利用CMAC神经网络实现模糊推理,并可对隶属函数进行实时调整,从而使它具有自适应和学习能力.文中讨论了这种控制器参数的PSO学习算法,对电厂锅炉主蒸汽温度控制的仿真表明了FCMAC控制器及其PSO学习算法的可行性和有效性.     

主蒸汽温度的串级CMAC学习控制策略

结合CMAC学习控制器和串级控制系统，提出了主蒸汽温度的串级CMAC学习控制策略，其自适应性强，非常适合于计算机实时控制。仿真研究表明，该策略的控制品质良好，远远优于PID控制。