共查询到19条相似文献,搜索用时 65 毫秒
1.
建立了预测磨损自补偿状态下润滑剂运动粘度对 45钢 /锡青铜副摩擦特性的影响规律的BP神经网络模型 ,该网络可较准确地预测润滑剂粘度对摩擦副摩擦系数的影响规律 ,为摩擦学设计的程序化计算和分析提供方便且有效的工具。 相似文献
2.
基于神经网络的摩擦学设计知识表达方法 总被引:4,自引:0,他引:4
本文以神经网络理论为基础,提出了摩擦学设计知识表达理论。结合摩擦学设计知识的特点,研究了基于神经网络知识表达方法的实现技术,并给出具体表达实例。实践证明这种方法是行之有效的。 相似文献
3.
4.
研究了汽轮发电机组轴承转子系统摩擦学设计知识获取的神经网络方法,通过分析BP网络权重,得到网络输入与输出的函数关系,并定义了关系系数C.由关系系数C的大小和正负可以确定输入与输出的关系。 相似文献
5.
6.
摩擦系数是一个很复杂的参数,它受到多种因素的影响和制约。因此,对摩擦系数进行神经网络分析,采用神经网络优化算法,建立以轧件温度、粘度、轧制速度为输入,以摩擦系数为输出的神经网络结构并对其进行神经网络预报。 相似文献
7.
8.
滑动轴承摩擦系统动力学仿真研究 总被引:1,自引:0,他引:1
在分析了滑动轴承内部摩擦学系统和摩擦学系统过程的基础上,基于摩擦学系统方法构建滑动轴承内部的摩擦磨损动力学模型,对滑动轴承的摩擦磨损特性进行了研究,并通过仿真试验研究了轴承内部温升和热量之间的关系.试验结果表明仿真结果与理论模型计算结果相吻合. 相似文献
9.
10.
BP神经网络在摩擦学设计计算中的应用 总被引:2,自引:0,他引:2
用双隐层BP人工神经网络,建立了丝杆螺母副的磨损率与滑动速度关系的数学模型。该模型可用于准确地计算丝杆螺母副和蜗轮蜗杆副的磨损率,可十分方便地用于摩擦学程序设计。采用L-M规则进行神经网络学习训练可使网络收敛快,误差小。风络输出结果与实验结果比较有极好的吻合性。该神经网络为工程设计人员,在摩擦学设计时提供有效的计算工具。 相似文献
11.
Shin Mi-Kyeong Jo Woo Jin Cha Hye Min Lee Soo-Hong 《Journal of Mechanical Science and Technology》2020,34(6):2507-2514
Journal of Mechanical Science and Technology - There are two main causes of plant accidents: poor maintenance management and human error. In this study, we implemented a smart plant maintenance... 相似文献
12.
13.
本文应用MATALB/XPC实时仿真工具测量了贴有压电元件的复合材料薄壁结构的振动响应。并对其进行神经网络的离线建模和预测。比较了几种网络的优缺点。选择了引进外部反馈的前向BP网络作为非线性系统建模的方法,有望推广用于智能结构的健康监测和振动主动控制。 相似文献
14.
本文介绍了神经网络在图象压缩领域的应用,并且对前馈神经网络模型及其学习算法进行改进。在改进的模型中,隐层的每个神经元都附加上一个基于Logistic映射的伴随神经元。能够产生混沌现象。同时论述了这种混沌神经网络用于图像压缩的模型、原理、算法及关键技术。并通过仿真实验将这种模型应用于图像压缩中。其中的关键是算法,激活函数和压缩率等参数的选择。在固定压缩率和激活函数的条件下。将这种模型和最常用于图像压缩的标准BP网络模型进行了比较,结果表明这种混沌神经网络在压缩率。失真率等方面性能更好。从而使得重建图像效果更好。 相似文献
15.
E. Santner 《Lubrication Science》1996,2(3):267-280
As in all other areas of research today, so in tribology, computers play an important role. The exact analysis of tribological systems needs finite element methods (FEM) for calculation. Analysis of worn surfaces by SEM, AUGER, ESCA, XRS and the interpretation and documentation of measurements is performed with computers. The new approach to the basis of tribology by the use of scanning tunnelling microscopy (STM) and lateral force microscopy (LFM) would not be possible without computers. This paper points out the opportune tasks for computers in tribological simulation tests, such as complex test cycles, long time runs, automatic sensor calibration, measurements of fast varying signals, control and correction of mutual influences, and mentions the databases TRIBO (Tribology Index) for literature and Tribocollect for tribological data. 相似文献
16.
重载丝杆螺母副的神经网络摩擦学模型的建立 总被引:1,自引:0,他引:1
用BP人工神经网络建立了重载丝杆螺母副的摩擦学特性与载荷之间关系的磨损自补偿教学模型。结果表明:用L-M规则进行神经网络学习训练可使网络收敛快,误差小。网络输出结果与实验结果比较有极好吻合性。该神经网络可为工程设计人员在摩擦学设计时提供有效的计算工具。 相似文献
17.
A. Noorul Haq T. Radha Ramanan 《The International Journal of Advanced Manufacturing Technology》2006,30(11-12):1132-1138
This paper considers the sequencing of jobs that arrive in a flow shop in different combinations over time. Artificial neural network (ANN) uses its acquired sequencing knowledge in making the future sequencing decisions. The paper focuses on scheduling for a flow shop with ‘m’ machines and ‘n’ jobs. The authors have used the heuristics proposed by Campbell et al.(1970, A heuristic algorithm for n-jobs m-machines sequencing problem) to find a sequence and makespan (MS). Then a pair wise interchange of jobs is made to find the optimal MS and total flow time (TFT). The obtained sequence is used for giving training to the neural network and a matrix called neural network master matrix (NNMM) is constructed, which is the basic knowledge of the neurons obtained after training. From the matrix, interpretations are made to determine the optimum sequence for the jobs that arrive in the future over a period of time. The results obtained by the ANN are compared with a constructive heuristics and an improvement heuristics. The results show that the quality of the measure of performance is better when ANN approach is used than obtained by constructive or improvement heuristics. It is found that the system’s efficiency (i.e., obtaining the optimal MS and TFT) increases with increasing numbers of training exemplars. 相似文献
18.
As a treatment for Parkinsonian resting tremors, deep brain stimulation (DBS) has been reported to be more effective than levodopa, and of the forms of DBS, subthalamic nucleus (STN) DBS has been reported to be more effective than internal globus pallidus (GPi) DBS. To assess the veracity of these claims, this study compared the effectiveness of DBS and levodopa and of STN DBS and GPi DBS in relieving resting tremors using a novel methodology consisting of wavelet transform (WT) technology and a neural network with weighted fuzzy membership functions (NEWFM). This simplified methodology offers the advantages of efficiency, low cost, and ease of use. The results indicate that subjects with high-amplitude resting tremors obtained almost the same relief from on-DBS and off-levodopa treatment than on-DBS and on-levodopa treatment; that subjects with low-amplitude resting tremors experienced greater relief from on-DBS and off-levodopa treatment than on-DBS and on-levodopa treatment, indicating that relief could be relieved by DBS administration alone; and that DBS had stronger effects on subjects with high-amplitude resting tremors than subjects with low-amplitude resting tremors. This study’s successful employment of WT technology and NEWFM to compare treatment effects demonstrated the utility of a simplified approach that even non-experts can utilize. 相似文献
19.