基于Plant Simulation的装配车间仿真优化研究与应用

针对纺机装配车间装配线不平衡的问题,通过使用Plant Simulation仿真软件建立符合纺机装配车间实际情况的仿真模型,以车间实际生产数据为输入验证仿真模型的可信性,建立方便交互的可视化交互界面,方便模型复用和生产参数的调整。通过仿真模型结合启发式算法优化各工位的装配工序,装配线生产节拍缩短10.7%,提供了一种使用仿真软件进行装配线优化的可行方案。

Variational quantum simulation of thermal statistical states on a superconducting quantum processer

Quantum computers promise to solve finite-temperature properties of quantum many-body systems,which is generally challenging for classical computers due to high computational complexities.Here,we report experimental preparations of Gibbs states and excited states of Heisenberg X X and X X Z models by using a 5-qubit programmable superconducting processor.In the experiments,we apply a hybrid quantum–classical algorithm to generate finite temperature states with classical probability models and variational quantum circuits.We reveal that the Hamiltonians can be fully diagonalized with optimized quantum circuits,which enable us to prepare excited states at arbitrary energy density.We demonstrate that the approach has a self-verifying feature and can estimate fundamental thermal observables with a small statistical error.Based on numerical results,we further show that the time complexity of our approach scales polynomially in the number of qubits,revealing its potential in solving large-scale problems.

Efficient Stochastic Simulation Algorithm for Chemically Reacting Systems Based on Support Vector Regression

The stochastic simulation algorithm （SSA） accurately depicts spatially homogeneous wellstirred chemically reacting systems with small populations of chemical species and properly represents noise, but it is often abandoned when modeling larger systems because of its computational complexity. In this work, a twin support vector regression based stochastic simulations algorithm （TS^3A） is proposed by combining the twin support vector regression and SSA, the former is a well-known robust regression method in machine learning. Numerical results indicate that this proposed algorithm can be applied to a wide range of chemically reacting systems and obtain significant improvements on efficiency and accuracy with fewer simulating runs over the existing methods.

Monte Carlo simulation of sequential structure control of AN-MA-IA aqueous copolymerization by different operation modes

The regulation of polyacrylonitrile(PAN)copolymer composition and sequence structure is the precondition for producing high-quality carbon fiber high quality.In this work,the sequential structure control of acrylonitrile(AN),methyl acrylate(MA)and itaconic acid(IA)aqueous copolymerization was investigated by Monte Carlo(MC)simulation.The parameters used in Monte Carlo were optimized via machine learning(ML)and genetic algorithms(GA)using the experimental data from batch copolymerization.The results reveal that it is difficult to control the aqueous copolymerization to obtain PAN copolymer with uniform sequence structure by batch polymerization with one-time feeding.By contrary,it is found that the PAN copolymer with uniform composition and sequence structure can be obtained by adjusting IA feeding quantity in each reactor of a train of five CSTRs.Hopefully,the results obtained in this work can provide valuable information for the understanding and optimization of AN copolymerization process to obtain high-quality PAN copolymer precursor.

Simulated Annealing Algorithm to Minimize Makespanin Single Machine Scheduling Problem withUniform Parallel Machines

This paper presents a simulated annealing algorithm to minimize makespan of single machine scheduling problem with uniform parallel machines. The single machine scheduling problem with uniform parallel machines consists of n jobs, each with single operation, which are to be scheduled on m parallel machines with different speeds. Since, this scheduling problem is a combinatorial problem;usage of a heuristic is inevitable to obtain the solution in polynomial time. In this paper, simulated annealing algorithm is presented. In the first phase, a seed generation algorithm is given. Then, it is followed by three variations of the simulated annealing algorithms and their comparison using ANOVA in terms of their solutions on makespan.

Design and Comparison of Simulated Annealing Algorithm and GRASP to Minimize Makespan in Single Machine Scheduling with Unrelated Parallel Machines

This paper discusses design and comparison of Simulated Annealing Algorithm and Greedy Randomized Adaptive Search Procedure (GRASP) to minimize the makespan in scheduling n single operation independent jobs on m unrelated parallel machines. This problem of minimizing the makespan in single machine scheduling problem with uniform parallel machines is NP hard. Hence, heuristic development for such problem is highly inevitable. In this paper, two different Meta-heuristics to minimize the makespan of the assumed problem are designed and they are compared in terms of their solutions. In the first phase, the simulated annealing algorithm is presented and then GRASP (Greedy Randomized Adaptive Search procedure) is presented to minimize the makespan in the single machine scheduling problem with unrelated parallel machines. It is found that the simulated annealing algorithm performs better than GRASP.

A customized system for simulation of welding thermal process

This paper presents a customized simulation system for analyzing welding temperature field, which is based on Finite elementary Analysis software MSC. Marc. The system has the functions of robustly hexahedral meshing, automated loading of dynamic heat source models for various welding methods and convenient post-processing for welding temperature field. A gene unit algorithm is presented to achieve robust simulation for assembled structure. High order routine method is used to generate various customized routines robustly, which includes Fortran subroutines for welding heat source, Marc command routines for automated modeling, and python subroutines for post-processing etc. With the system, simulation of welding temperature fields can be easily conducted with simple operations.

基于Plant Simulation的机械加工单元设备布局研究

以物流量最小和顺流程度最优为目标函数,构建了机械加工单元设备布局的数学模型,使得在单元内加工零件的总物流成本最小且流程最顺畅;以Plant Simulation为仿真平台,基于遗传算法求解"U"型布置时的设备最优序列,并建立了单元内布局设计模型和交互界面。通过工程设计实例验证了本方法的有效性,为工程设计中设备布局提供了有效参考。

Hot spot temperature prediction and operating parameter estimation of racks in data center using machine learning algorithms based on simulation data

In this paper,models to predict hot spot temperature and to estimate cooling air’s working parameters of racks in data centers were established using machine learning algorithms based on simulation data.First,simulation models of typical racks were established in computational fluid dynamics(CFD).The model was validated with field test results and results in literature,error of which was less than 3%.Then,the CFD model was used to simulate thermal environments of a typical rack considering different factors,such as servers’power,which is from 3.3 kW to 20.1 kW,cooling air’s inlet velocity,which is from 1.0 m/s to 3.0 m/s,and cooling air’s inlet temperature,which is from 16℃ to 26℃ The highest temperature in the rack,also called hot spot temperature,was selected for each case.Next,a prediction model of hot spot temperature was built using machine learning algorithms,with servers’power,cooling air’s inlet velocity and cooling air’s inlet temperature as inputs,and the hot spot temperatures as outputs.Finally,based on the prediction model,an operating parameters estimation model was established to recommend cooling air’s inlet temperatures and velocities,which can not only keep the hot spot temperature at the safety value,but are also energy saving.

基于高维混合模型的离心泵叶轮子午面优化设计

为提高离心泵在设计工况下的运行效率和扬程,提出一种基于高维混合模型的离心泵叶轮优化设计方法.选取一台比转数为157的单级离心泵作为研究对象,通过CFturbo软件对优化变量进行参数化,然后结合数值模拟获得高维混合模型的训练集.在此基础上采用获取的训练集通过MATLAB机器学习得出效率、扬程与优化参数之间关于支持向量回归的高维模型,并采用遗传算法寻优.在设计工况下,所拟合的高维混合模型预测的效率和扬程值比原模型分别高1.5%和3.2 m,数值模拟验证优化方案的效率和扬程分别比原模型高0.9%和2.1 m.算例研究表明,将高维混合模型应用于离心泵叶轮的优化设计中可以实现快速寻优并提高离心泵水力性能.

模拟退火遗传算法在自由曲面数控加工中的实验

在自由曲面的加工中,一直面临着加工时间长的问题,本研究以提高加工效率为目的,通过分析待加工自由曲面的面曲率、残余高度等参数,计算出合理的加工步长和行距,并以此为依据将待加工曲面离散成点云即为刀触点。将刀具路径规划问题转化为求解TSP问题的最优解,为避免遗传算法早熟陷入局部最优解,引入了模拟退火算法进行改进,使用改进后的混合算法进行刀具路径寻优。对优化方法进行了仿真加工、实验加工及测量,结果表明优化方法相比传统方法刀路长度最多减少303.4mm,相对缩短了12.3%,加工效率提升较为明显,并且加工表面也取得了较好的加工效果。

MRMR-SA-EGA-ELM的叶绿素a浓度预测模型研究

为提高叶绿素a浓度的预测精度,以南太湖区域-湖州市新塘港2020年5月至11月份的水质监测数据为原始样本数据,使用最大相关最小冗余算法(MRMR)从原始样本数据中选取效果更优的特征值,作为预测模型的输入数据,将精英遗传算法(EGA)与模拟退火算法(SA)组合优化极限学习机(ELM)网络的初始参数,最终构建MRMR-SA-EGA-ELM叶绿素a浓度预测模型。实验结果表明,MRMR-SA-EGA-ELM模型预测叶绿素a浓度的平均绝对误差(MAE)、均方误差(MSE)、决定系数(R^(2))分别为1.009、1.607、0.903,而ELM模型预测结果的MAE、MSE、R^(2)分别为2.078、8.249、0.562,MRMR-SA-EGA-ELM模型的效果得到显著提升,可实现对叶绿素a浓度的准确预测。

摆线齿轮成形磨削机床立柱的多级优化研究

针对摆线轮成形磨床立柱优化过程中的复杂性,提出一种综合拓扑优化、结构仿生、尺寸优化的多级多目标优化设计方法,实现了立柱质量、一阶固有频率、最大应力及变形位移综合目标优化。以应变能最小为目标函数,以体积分数为约束,采用拓扑优化设计方法,确定了复杂载荷下摆线轮成形磨床立柱材料的最佳分布。以王莲叶脉和芭蕉叶柄为仿生目标,采用结构仿生优化设计方法,在立柱内部仿生空间设计仿生筋板,最大限度提升立柱整体性能。采用响应面模型遗传算法对立柱内部复杂结构尺寸进行优化,得到尺寸最优解。结果表明:在受载相同的情况下,优化后的立柱质量减轻18.4%,立柱最大应力减少23.6%,变形位移减少0.6%,一阶固有频率有所提升。

基于虚拟仿真技术的高精度数控机床自动控制系统

为实现高精度数控加工,设计基于虚拟仿真技术的高精度数控机床自动控制系统。该系统依托SolidWorks、Deep Exploration等软件,建立数控机床虚拟仿真三维模型,设计数控机床控制约束关系,获取数控机床运行数据,并将该数据内的跟随误差、误差积分、误差微分等作为控制输入变量,设计由神经网络和PID组成的混合控制器,利用该混合控制器输出数控机床自动控制量,实现高精度数控机床自动控制。实验表明:该系统在各种运行环境下的软件移植完整程度均超过95%,在控制数控机床运动速度时,跟随误差始终保持在-50~50 mm/min,应用效果较为显著。

基于GRA-GASA-SVM的煤层瓦斯含量预测方法研究

为提升煤层瓦斯含量预测精度,提出一种采用遗传模拟退火算法混合优化支持向量机(SVM)参数的瓦斯含量预测模型(GRA-GASA-SVM模型)。该模型将GA和SA整合为遗传模拟退火算法协同优化SVM的参数,以解决传统网格寻优算法取值范围无法确定和单一智能算法优化程度有限等问题。利用灰色关联分析(GRA)压缩数据集维度,建立瓦斯含量预测参数体系并作为GASA-SVM的输入数据集。结果表明:SVM模型、GA-SVM模型和GASA-SVM模型10折交叉验证瓦斯含量预测总平均相对误差分别为15.98%、13.55%和10.58%。相比SVM模型和GA-SVM模型,GASA-SVM模型预测稳定性更优、预测精准度更高且对新样本泛化能力更强。

多机协同作业全覆盖路径规划

多机协同作业能够提升作业效率,节约作业时间,减少了农作物因收获不及时导致的粮食浪费。为此,以总的非工作距离和最长单车行驶距离为目标函数,建立虚拟的农田模型,将多机协同作业全覆盖路径规划问题转化为VRP问题,并使用改进的蚁群算法求解。仿真结果表明:改进后的算法有效;对比遗传算法和传统的蚁群算法,改进后的算法平均目标函数值分别降低了25.0%和11.25%;对比模拟退火算法,改进后的算法平均目标函数值降低了1.5%,算法稳定性更好,适用于更大规模农田的多机协同作业全覆盖路径规划问题求解。

青贮机铁磁性金属异物智能检测报警系统

[目的/意义]青贮机作业时,田间遗落的铁丝等铁磁性金属异物如果混入其喂入系统,将会对青贮机的关键零部件和牲畜脏器造成严重损伤。为了确保青贮机在田间作业时能准确、高效地检测出金属异物,本研究开发了一套性能优良的金属探测系统。[方法]首先分析了青贮机金属检测原理,然后对平面螺旋线圈与圆柱线圈进行了仿真计算,选择平面螺旋线圈作为研究对象,通过使用非支配排序遗传算法(Nondominated Sorting Genetic Algorithm-Ⅱ,NSGA-Ⅱ)结合有限元仿真分析的方式,确定了线圈的线径、内径、外径、层数以及频率,并对弯曲线圈与未弯曲线圈以及阵列线圈进行了仿真计算。最后进行了系统集成,搭建了青贮机模拟试验台进行了模拟试验。[结果和讨论]仿真分析结果显示,平面螺旋线圈磁通密度模变化范围明显大于圆柱线圈,且其电感灵敏度、电阻灵敏度和被测物涡流损耗要明显高于圆柱线圈;另一方面,平面线圈弯曲后电感灵敏度、电阻灵敏度大幅度提高,有利于增强探测线圈的响应度。通过模拟台架试验,验证了该金属探测系统在探测距离小于70mm,对直径0.6 mm、长度20 mm铁丝报警率达到100%,且经过计算,系统响应时间为0.105 0 s,小于安全运输时间,系统可以在金属物到达切碎系统前及时停止。[结论]本研究设计出了一套青贮机金属异物探测系统,提出了一套金属探测线圈的优化方法,并开发了相应的金属探测软硬件系统,通过试验验证了金属探测系统的功能,为青贮机安全运行提供了有力技术支撑。

基于机器学习算法的中国近地面臭氧浓度模拟

目的探索基于多种机器学习模型的我国近地面臭氧浓度高精度模拟方法。方法基于2013—2017年的多源数据,建立基于多种机器学习算法的全国近地面臭氧浓度模拟模型。结果随机森林(random forest,RF)模型的性能最佳,R^(2)为0.752,RMSE和MAE分别为23.264和16.094μg/m^(3)。地面下沉短波辐射为近地面臭氧浓度模拟的最关键因素。结论基于气象、地理、排放等多元变量的RF模型可实现近地面臭氧高精度模拟。未来可进一步引入空气污染物的自然源排放量数据以提高模型精度。

基于增强模拟退火算法的动车所调车作业计划多目标优化方法

尽头式动车所调车作业存在多种可选作业模式,且在调车作业时需考虑作业总时间及转线复杂度等多性能指标,合理制定综合上述情况下的动车所调车作业计划,对提高动车所检修能力具有重要意义。为此,以最小调车作业时间及转线复杂度为目标,构建带咽喉区股道约束的动车所调车作业混合整数线性规划模型,并提出一种增强多目标模拟退火算法(EMOSA)。该算法融合基于启发式规则的解码设计,以消除股道占用在时空上的冲突,面向调车作业进行股道合理分配;设计与问题规模相关的帕累托前沿解集重启机制,避免算法陷入局部最优。对不同规模的多个案例进行测试,验证了所提改进算子的有效性。最后,以某动车运用所的调车作业计划编制为例,验证了模型和算法的实用性和正确性。

基于混沌云量子蝙蝠CNN-GRU大坝变形智能预报方法研究

针对大坝变形影响因素复杂、精准预报难度较大问题,为了提高在大坝安全管理过程中大坝变形的预报精度,本文从大坝变形非线性动力系统时间序列的强非线性出发,引入深度卷积神经网络,对大坝变形及其空间影响特性进行挖掘,引入门控循环单元,对大坝变形的时域特性进行挖掘,构建应用于大坝变形预报的深度卷积神经网络-门控循环单元大坝变形组合深度学习网络;同时,为了获取深度卷积神经网络-门控循环单元组合网络的最佳超参,引入了混沌云量子蝙蝠算法,建立了基于混沌云量子蝙蝠算法算法的深度卷积神经网络-门控循环单元组合网络超参优选方法;最后,提出了深度卷积神经网络-门控循环单元-混沌云量子蝙蝠算法大坝变形组合深度学习智能预报方法。基于实测数据开展预报研究,对比结果表明:与对比模型相比,提出的深度卷积神经网络-门控循环单元-混沌云量子蝙蝠算法预报方法取得了更精确的预报结果,混沌云量子蝙蝠算法算法用于超参优选获得了更佳的超参组合。