人工神经网络与煤发热量的测量

【作者】 于海华；

【导师】 张国生；

【作者基本信息】 黑龙江大学 ， 控制理论与控制工程， 2003， 硕士

【摘要】 人工神经网络是对生理学上人类大脑神经网络的结构、功能以及若干基本特性的某种理论抽象、简化和模拟而构成的一种信息系统。神经网络从两方面获得它的计算能力，一是大规模并行分布式结构。二是学习以及由此产生的推广能力。 煤质快速分析仪采用γ射线、电容、压力和温度传感器来测量煤样的灰分、水分、密度和温度计数值，通过PC-7606数据采集卡把四路计数值传入计算机。本文的目的在于利用人工神经网络建立发热量与各计数值之间的模型，快速准确地计算发热量。 根据这一需要，本文建立了三层神经网络，第一层起分类作用，采用基于记忆学习算法，第二、三层采用误差反馈学习算法。最后本文还对该模型进行了检验，证明该模型是合理的。更多还原

【Abstract】 Artificial neural network is a information system that is established by theoretically abstracting, simplifying and simulating the structure, function and some fundamental properties of human brain neural networks. A neural network derives its computing power through, first, its massively parallel distributed structure and, second, its ability to learn and therefore generalize.The coal quality analysis apparatus measures the count value of ash, water, density and temperature of coal sample with the y-ray sensor, capacitance sensor, pressure sensor and temperature sensor respectively, and inputs the four count values to the computer by pc-7606 data collection chip. The goal of this paper is establish the model of calorific value of coal and the count values to forecast the value quickly and exactly.To achieve this goal, this paper design a neural network with three layers in which the first layer play a classifier role and learn with the memory-based learning algorithm while the second and third layers learn with the error back-propagation algorithm. Finally, this paper generalize the model and testify that the model is rational.更多还原