共查询到19条相似文献，搜索用时 218 毫秒
1.
介绍了Elman神经网络的结构,并将Elman神经网络应用于我国电信业务量预测。仿真结果和BP神经网络对比表明,Elman神经网络的预测结果更精确。 相似文献
2.
《科技通报》2016,(7)
通过对中压配电的优化配置提高电力调度的控制能力和分配能力,传统方法中对中压配电控制采用神经网络控制方法,构建PID神经网络系统实现的中压配电的优化调度,但是该方法在中压配电过程中的收敛性不好。提出一种基于改进PID算法的中压配电优化控制方法。首先分析系统结构组成,得到中压配电控制系统的结构模型,对中压配电系统的控制参数进行特征分析,根据中压配电控制过程中电压参数的时变性、电流扰动性的特点,构建改进的三层PID前向中压配电前向神经网络控制系统,进行对中压配电过程中电压、电流和功率等信号变化特征进行定量分析,采用前向三层PID神经网络控制算法进行控制算法改进。仿真结果表明,采用该方法进行中压配电控制,对各个用户通道的电压输出具有较好的适应性,提高配电控制精度,提高了电压输出的稳定性。 相似文献
3.
4.
《科技通报》2015,(10)
风力发电机在复杂自然环境运行中,通常受到强烈的外部环境干扰,需要进行风机抗干扰模糊PID控制设计,提高风机的智能反馈控制能力,提高风机的效率。传统的控制方法采用变结构神经网络控制,需要实时监测各参数,对风机控制权重进行调整过程中导致失真,性能不好。提出一种基于微分线性组合的风机抗干扰模糊PID控制方法,采用微分线性组合控制方法,改变发电机的电磁转矩,得到模糊PID神经网络的学习输入向量,设计三层前向神经元PID变结构网络,提高转速调节器的控制性能。根据已经建立的知识库,对模糊输入数据进行处理,构建微分线性组合PID变结构网络,实现控制算法改进。仿真实验表明,该算法能有效提高风机的控制性能,功率控制跟踪精度较高,抗干扰性能较好,风机发电效率高于传统方法,具有较好的可靠性和鲁棒性。 相似文献
5.
基于战略管理理论、竞争力分析理论和计算实验逻辑框架,以江苏淮安若干地方智库为研究对象,运用神经网络模型（包括三层BP神经网络模型和Elman神经网络模型）、遗传算法对地方智库进行竞争力评估.研究结果表明：运用遗传算法约简得到的少数评估指标可以有效地评估智库竞争力,以上两种神经网络模型均可适用于地方智库的评估工作,Elman模型相对略优. 相似文献
6.
本文在MATLAB/SIMULINK环境下实现了使用C语言编写的BPPID控制器。通过结合BP神经网络和PID控制方法,充分利用了BP神经网络具有逼近任意连续非线性函数的能力,比较适合被控系统比较复杂或不确定度情况下。文中采用了3-3-3解构的三层BP神经网络和增量式PID算法。在对仿真目标进行跟踪时取得了较好的结果,同时使用C语言的实现方式也更贴近实际应用。 相似文献
7.
8.
9.
《科技通报》2015,(10)
研究非线性系统的鲁棒性,在大扰动条件下,提高系统的稳定控制性能。传统的控制方法采用PID神经网络控制,在参数自适应过程中产生控制偏差。提出一种基于单神经元纠偏控制的非线性系统鲁棒性改进方法。控制结构是一个三层前向神经元网络,采用单神经元纠偏控制,自适应调节神经元输入输出层权重,给定模型的不确定性分为参数的不确定性和未建模的动态特性不确定性,由此得到偏移控制非线性小扰动方程,进行控制系统鲁棒性和稳健性证明。仿真结果表明,采用该算法实现对非线性系统的控制,自适应调节时间短,超调量小,纠偏性能较好,自适应跟踪控制性能优越,误差减少,控制精度较高,鲁棒性较优。 相似文献
10.
本文以衡阳铜管厂轧钢分厂的加热炉作为具体的研究对象,针对加热炉PID控制系统存在的一些缺点,结合国内外先进理论和技术,提出了一种基于改进BP神经网络的PID参数控制方法。将改进后方法用于加热炉控制,并与常规的PID控制方法进行对比：仿真的结果表明该算法具有较好的控制效果： 相似文献
11.
神经网络和传统线性模型结合为处理混沌时间序列提供了新的途径。将Elman神经网络和单整自回归移动平均模型结合起来,同时分析我国进出口贸易量时间序列中的线性和非线性两部分,得到更准确的预测精度。实证表明,复合模型吸收两类方法的优点,较单一模型能够更有效地预测我国进出口数据。 相似文献
12.
《Journal of The Franklin Institute》2019,356(12):5944-5960
Due to the unknown system structure of the froth flotation process and frequent fluctuations in production conditions, design of control strategy is a challenging problem. As a result, manual operation is still widely applied in practice by observing froth image features. However, since the manual observation is subjective and the production conditions are time-varying, the manual operation cannot make decisions quickly and accurately. In this paper, a data-driven-based adaptive fuzzy neural network control strategy is developed to implement the automatic control of the antimony flotation process. The strategy is composed of fuzzy neural network (FNN) controllers, a data-driven model, and an on-line adaptive algorithm. The FNN is constructed to derive the control laws of the reagent dosages. The parameters of the FNN controllers are tuned by gradient descent algorithm. To obtain the real-time error feedback information, the data-driven model is established, which integrates the long short term memory (LSTM) network and radial basis function neural network (RBFNN). The LSTM network is utilized as a primary model, and the RBFNN is used as an error compensation model. To handle the challenges of the frequent fluctuations in the production conditions, the on-line adaptive algorithm is proposed to tune the parameters of the FNN controllers. Simulations and experiments are carried out in a real-world antimony flotation plant in China. The results demonstrate that the proposed adaptive fuzzy neural network control strategy produces better control performance than the other two existing methods. 相似文献
13.
14.
15.
《Information processing & management》2022,59(2):102873
Because the innovation level of enterprise clusters in various regions of China is generally low, this research is focused on the process of knowledge integration of regional innovation subjects. We research, explore and analyze the different connection states between nodes and their impact on the knowledge symbiosis or knowledge spillover ability of the entire innovation network, learn from the characteristics of neurons in the neural network and the information transmission model to investigate the connection between various nodes in innovation network. We then determine the knowledge association mechanism and transmission relationship, and then analyze the trigger conditions of fusion and the transformation model of innovative knowledge flow under this condition, laying the foundation for further theoretical or practical research. Second, we built a model of the knowledge transfer connection that will be used in the innovation process. and select a path of knowledge transfer. Based on the mechanism of multi-agent innovation, we analyzed the incentive relationship of knowledge transfer in the innovation process, constructed the principles of knowledge transfer, analyzed the mutual transfer relationship between different innovation nodes, and analyze the simulation innovation network through certain examples. The knowledge fusion process in China lays the foundation for the improvement of the overall collaborative innovation level of the regional multi-agent innovation network. From the overall structure of the article, this research analyzes the regional innovation network from a new perspective on the basis of domestic and foreign research in knowledge flow management and control technology, knowledge exchange under social networks, and neural network optimization algorithms. The process of knowledge symbiosis or knowledge spillover in the process of innovation, exploring the incentive relationship of knowledge transfer throughout the primary parts innovation process, optimizing the degree of connection or relationship between different main agents, optimizing the knowledge exchange relationship from one node in the innovation network to another and improving the collaborative innovation of the regional mesh lay a theoretical foundation for the level. 相似文献
16.
17.
18.
【目的/意义】突发疫情环境下将形成大量网络舆情,准确把握网络舆情传播趋势可为突发疫情环境下的社
会保障应急机制提供参考依据。【方法/过程】本文从网络舆情信息交互影响要素、网络舆情信息交互机理两方面分
析突发疫情环境下网络舆情信息交互机理;并从网络舆情传播趋势特点考虑,以新冠病毒肺炎李文亮事件为例,采
用Elman 神经网络模型,选取网络信息数量以及情绪总量和主导情绪作为网络舆情传播趋势预测主要变量和辅助
变量,对突发疫情环境下的网络舆情传播趋势进行预测分析,针对预测结果制定相关社会保障应急机制。【结果/结
论】研究提出可通过完善网络舆情相关法律机制、社会参与机制、信息披露机制、社会监督机制、责任追究机制五项
社会保障应急机制,以期为突发疫情环境下维持社会稳定性提供依据。【局限/创新】未来研究中可结合更多相关实
例进行分析,从而使研究结论进一步得到丰富与深化。 相似文献