耙吸挖泥船疏浚作业控制参数优化研究与应用

发布时间：2018-05-14 14:30

本文选题：耙吸挖泥船 + 密度预测　；参考：《江苏科技大学》2017年硕士论文

【摘要】：随着经济的不断发展,近年来,我国耙吸挖泥船的建造和疏浚技术已经取得了较大的进步,国内的耙吸挖泥船正朝着自动化的方向发展。随着国内港口疏浚工程量的日益增加,耙吸挖泥船疏浚作业的高效化越来越受到疏浚行业的关注。然而,国内有关研究提高疏浚作业效率的成果尚少。因此,如何根据现场施工条件来提高耙吸挖泥船疏浚效率已成为国内疏浚行业的重点研究方向,本文通过研究耙吸挖泥船疏浚作业过程,对施工控制参数进行优化。本文在中交疏浚技术装备国家工程研究中心基金项目的支持下,对如何提高疏浚效率进行了研究。文中采用遗传神经网络的方法对耙头密度进行了预测,使用多种群遗传算法对疏浚土质参数进行了估算并对施工参数进行优化,开发了耙吸挖泥船疏浚界面,为施工人员提供了疏浚数据和施工控制参数的参考。本文主要研究如下:首先,本文对耙吸挖泥船耙头疏浚机理进行了分析研究,根据流量、航速、波浪补偿器压力等参数使用遗传神经网络对吸入密度进行预测。通过从厦门港获得的实测数据对预测密度进行仿真验证,仿真结果表明:该方法具有很高的预测准确性,可以为施工人员提供吸入密度参考,以便船员调整施工参数,避免因吸入密度过大使得泥泵发生气蚀而损坏。其次,本文对耙吸挖泥船疏浚过程中泥舱沉积模型进行了分析研究,使用多种群遗传算法对装舱质量进行拟合,从而给出当前疏浚工况的土壤参数,然后,根据土质参数判断土质类型。仿真结果表明:该方法能够准确地拟合装舱质量,可为施工人员提供疏浚土质类型的参考。最后,本文结合耙头模型和泥舱沉积模型使用多种群遗传算法给出优化的航速、流量,提高了疏浚效率。最终,开发了耙吸挖泥船疏浚界面,该界面实现了当前疏浚产量和优化产量的对比。此外,该界面给出了最佳疏浚周期的控制参数,可为施工人员提供参考。
[Abstract]:With the development of economy, in recent years, the construction of suction dredger and dredging technology have made great progress in our country, and the domestic suction dredger is developing towards the direction of automation. With the increasing amount of dredging engineering in domestic ports, the high efficiency of dredging operation of rake suction dredger has been paid more and more attention by dredging industry. However, there are few achievements in improving the efficiency of dredging operation in China. Therefore, how to improve dredging efficiency of suction dredger according to site construction conditions has become the key research direction of domestic dredging industry. In this paper, the construction control parameters are optimized by studying the dredging process of suction dredger. This paper studies how to improve the dredging efficiency with the support of the National Research Center for dredging Technology and equipment. In this paper, the method of genetic neural network is used to predict the density of the rake head, the parameters of dredged soil are estimated and the construction parameters are optimized by using the multi-population genetic algorithm, and the dredging interface of the rake suction dredger is developed. The reference of dredging data and construction control parameters is provided for the construction personnel. The main contents of this paper are as follows: firstly, the dredging mechanism of suction dredger head is analyzed and studied in this paper. The suction density is predicted by genetic neural network according to the parameters of flow, speed and pressure of wave compensator. The simulation results show that the proposed method has a high prediction accuracy and can provide a reference for the construction personnel to adjust the construction parameters by using the measured data obtained from Xiamen Port, and the simulation results show that the proposed method can provide a reference for the construction personnel to adjust the construction parameters. Avoid cavitation damage due to excessive suction density. Secondly, the sediment model of mud tank in dredging process of rake suction dredger is analyzed and studied, and the loading quality is fitted by multi-population genetic algorithm, and then the soil parameters of current dredging condition are given, and then, The soil type is judged according to the soil quality parameters. The simulation results show that the method can accurately fit the loading quality and provide reference for the dredged soil type. Finally, combined with the rake head model and the mud tank sediment model, the optimal speed and flow rate of the dredging are obtained by using multi-population genetic algorithm, and the dredging efficiency is improved. Finally, the dredging interface of the rake suction dredger is developed, which realizes the comparison between the current dredging yield and the optimized output. In addition, the control parameters of the optimal dredging period are given at the interface, which can be used as a reference for the constructors.
【学位授予单位】：江苏科技大学
【学位级别】：硕士
【学位授予年份】：2017
【分类号】：U674.31;TP18

【参考文献】