A Min-Max Strategy to Aid Decision Making in a Bi-Objective Discrete Optimization Problem Using an Improved Ant Colony Algorithm

A multi-objective optimization problem has two or more objectives to be minimized or maximized simultaneously. It is usually difficult to arrive at a solution that optimizes every objective. Therefore, the best way of dealing with the problem is to obtain a set of good solutions for the decision maker to select the one that best serves his/her interest. In this paper, a ratio min-max strategy is incorporated (after Pareto optimal solutions are obtained) under a weighted sum scalarization of the objectives to aid the process of identifying a best compromise solution. The bi-objective discrete optimization problem which has distance and social cost (in rail construction, say) as the criteria was solved by an improved Ant Colony System algorithm developed by the authors. The model and methodology were applied to hypothetical networks of fourteen nodes and twenty edges, and another with twenty nodes and ninety-seven edges as test cases. Pareto optimal solutions and their maximum margins of error were obtained for the problems to assist in decision making. The proposed model and method is user-friendly and provides the decision maker with information on the quality of each of the Pareto optimal solutions obtained, thus facilitating decision making.

A Length-Adaptive Non-Dominated Sorting Genetic Algorithm for Bi-Objective High-Dimensional Feature Selection

As a crucial data preprocessing method in data mining,feature selection(FS)can be regarded as a bi-objective optimization problem that aims to maximize classification accuracy and minimize the number of selected features.Evolutionary computing(EC)is promising for FS owing to its powerful search capability.However,in traditional EC-based methods,feature subsets are represented via a length-fixed individual encoding.It is ineffective for high-dimensional data,because it results in a huge search space and prohibitive training time.This work proposes a length-adaptive non-dominated sorting genetic algorithm(LA-NSGA)with a length-variable individual encoding and a length-adaptive evolution mechanism for bi-objective highdimensional FS.In LA-NSGA,an initialization method based on correlation and redundancy is devised to initialize individuals of diverse lengths,and a Pareto dominance-based length change operator is introduced to guide individuals to explore in promising search space adaptively.Moreover,a dominance-based local search method is employed for further improvement.The experimental results based on 12 high-dimensional gene datasets show that the Pareto front of feature subsets produced by LA-NSGA is superior to those of existing algorithms.

基于MIC特征提取与BO-CatBoost的航空发动机RUL预测

针对航空发动机传感器监测的退化参数提取困难,易受噪声干扰及发动机剩余使用寿命预测精度不足等问题,利用最大信息系数、贝叶斯优化算法和类别特征梯度提升算法,提出了一种新的发动机剩余使用寿命预测模型。首先,为有效解决特征提取不足的问题,对采集的传感器历史监测特征进行最大信息系数相关性计算,提取出对发动机寿命运行周期影响较大的关键退化特征。其次,为解决剩余使用寿命预测中的梯度偏差及预测偏移问题,使用基于贝叶斯优化的类别特征梯度提升方法对航空发动机进行剩余使用寿命预测。最后,在美国航空航天局提供的商用模块化航空推进系统仿真数据集上进行实验,结果表明所提预测方法的性能较好,验证了该方法的有效性。

基于CEEMDAN-BO-BiGRU的矿井涌水量预测研究

为提高矿井涌水量预测的准确度,基于涌水量数据的不稳定性及随机性,提出一种自适应噪声完备集合经验模态分解(complete ensemble empirical mode decomposition with adaptive noise,CEEMDAN)、贝叶斯优化(Bayesian optimization,BO)与双向门控循环单元(bi-directional gated recurrent unit,BiGRU)相结合的矿井涌水量预测模型CEEMDAN-BO-BiGRU。所提模型通过CEEMDAN将涌水量数据分解为多个较平稳的固有模态分量(intrinsic mode function,IMF)和残差分量(residual components,Res),过滤数据噪声,提取数据不同时间尺度波动特征,降低预测误差。利用贝叶斯优化对BiGRU模型多个超参数进行迭代寻优,进一步提高模型的预测精度。之后对各分量进行超前1~3步预测,最终将各分量预测结果加和得到涌水量多步预测结果。以小庄煤矿矿井涌水量数据进行试验,并将CEEMDAN-BO-BiGRU预测结果与其他多种预测模型结果进行对比分析。结果表明:采用CEEMDAN-BO-BiGRU组合网络模型对矿井涌水量预测结果更准确,该方法对涌水量的短时预测提供了一种新思路。

Accelerated solution of the transmission maintenance schedule problem:a Bayesian optimization approach

To maximize the maintenance willingness of the owner of transmission lines,this study presents a transmission maintenance scheduling model that considers the energy constraints of the power system and the security constraints of on-site maintenance operations.Considering the computational complexity of the mixed integer programming(MIP)problem,a machine learning(ML)approach is presented to solve the transmission maintenance scheduling model efficiently.The value of the branching score factor value is optimized by Bayesian optimization(BO)in the proposed algorithm,which plays an important role in the size of the branch-and-bound search tree in the solution process.The test case in a modified version of the IEEE 30-bus system shows that the proposed algorithm can not only reach the optimal solution but also improve the computational efficiency.

A Novel Two-Level Optimization Strategy for Multi-Debris Active Removal Mission in LEO

Recent studies of the space debris environment in Low Earth Orbit(LEO)have shown that the critical density of space debris has been reached in certain regions.The Active Debris Removal(ADR)mission,to mitigate the space debris density and stabilize the space debris environment,has been considered as a most effective method.In this paper,a novel two-level optimization strategy for multi-debris removal mission in LEO is proposed,which includes the low-level and high-level optimization process.To improve the overall performance of the multi-debris active removal mission and obtain multiple Pareto-optimal solutions,the ADR mission is seen as a Time-Dependant Traveling Salesman Problem(TDTSP)with two objective functions to minimize the total mission duration and the total propellant consumption.The problem includes the sequence optimization to determine the sequence of removal of space debris and the transferring optimization to define the orbital maneuvers.Two optimization models for the two-level optimization strategy are built in solving the multi-debris removal mission,and the optimal Pareto solution is successfully obtained by using the non-dominated sorting genetic algorithm II(NSGA-II).Two test cases are presented,which show that the low level optimization strategy can successfully obtain the optimal sequences and the initial solution of the ADR mission and the high level optimization strategy can efficiently and robustly find the feasible optimal solution for long duration perturbed rendezvous problem.

基于ASWPD-BO-GRU的月径流量预测模型

为提高月径流量预测精度,并针对传统分解集成径流预测模型错误使用未来数据的问题,提出并建立了基于自适应小波包分解(ASWPD)和贝叶斯优化(BO)的门控循环单元(GRU)月径流量预测模型(ASWPD-BO-GRU)。首先,利用ASWPD对原始月径流量时间序列进行分解,在不使用未来数据的前提下得到4个相对规律的分解子序列,以降低预测难度;然后,利用BO优选分解后的子序列对应的GRU模型超参数;最终,对每个子序列进行预测,将预测结果相加重组得出月径流量预测结果。将提出并建立的模型应用于黑河流域莺落峡水文站月径流量预测中,并与GRU、BO-GRU、WPD-BO-GRU模型(基于传统分解思想对原始月径流量时间序列整体进行分解的预测模型)的预测结果进行对比。结果表明:ASWPD-BO-GRU模型的纳什效率系数(NSE)为0.89,在实例应用中预测精度最高,说明ASWPD-BO-GRU模型在正确分解的前提下具有较高的预测精度和更强的泛化能力。

Multi-fidelity Bayesian algorithm for antenna optimization

In this work,the multi-fidelity(MF)simulation driven Bayesian optimization(BO)and its advanced form are proposed to optimize antennas.Firstly,the multiple objective targets and the constraints are fused into one comprehensive objective function,which facilitates an end-to-end way for optimization.Then,to increase the efficiency of surrogate construction,we propose the MF simulation-based BO(MFBO),of which the surrogate model using MF simulation is introduced based on the theory of multi-output Gaussian process.To further use the low-fidelity(LF)simulation data,the modified MFBO(M-MFBO)is subsequently proposed.By picking out the most potential points from the LF simulation data and re-simulating them in a high-fidelity(HF)way,the M-MFBO has a possibility to obtain a better result with negligible overhead compared to the MFBO.Finally,two antennas are used to testify the proposed algorithms.It shows that the HF simulation-based BO(HFBO)outperforms the traditional algorithms,the MFBO performs more effectively than the HFBO,and sometimes a superior optimization result can be achieved by reusing the LF simulation data.

Bi-objective optimization models for mitigating traffic congestion in urban road networks

Traffic congestion in road transportation networks is a persistent problem in major metropolitan cities around the world.In this context,this paper deals with exploiting underutilized road capacities in a network to lower the congestion on overutilized links while simultaneously satisfying the system optimal flow assignment for sustainable transportation.Four congestion mitigation strategies are identified based on deviation and relative deviation of link volume from the corresponding capacity.Consequently,four biobjective mathematical programming optimal flow distribution(OFD)models are proposed.The case study results demonstrate that all the proposed models improve system performance and reduce congestion on high volume links by shifting flows to low volumeto-capacity links compared to UE and SO models.Among the models,the system optimality with minimal sum and maximum absolute relative-deviation models(SO-SAR and SO-MAR)showed superior results for different performance measures.The SO-SAR model yielded 50%and 30%fewer links at higher link utilization factors than UE and SO models,respectively.Also,it showed more than 25%improvement in path travel times compared to UE travel time for about 100 paths and resulted in the least network congestion index of1.04 compared to the other OFD and UE models.Conversely,the SO-MAR model yielded the least total distance and total system travel time,resulting in lower fuel consumption and emissions,thus contributing to sustainability.The proposed models contribute towards efficient transportation infrastructure management and will be of interest to transportation planners and traffic managers.

基于KECA和BO-SVDD的滚动轴承早期故障检测

为了实现更早地检测出滚动轴承发生故障,提出一种基于核熵成分分析(KECA)和贝叶斯优化(BO)算法优化支持向量数据描述(SVDD)的滚动轴承早期故障检测方法。提取轴承振动信号的时域、频域特征以及小波包分解节点能量特征,组成多维特征矩阵;利用KECA对多维特征矩阵进行降维处理,进而提取有效特征;最后,选取轴承正常状态的特征指标训练模型,利用BO算法确定SVDD的惩罚因子和核宽度,进而得到早期故障检测模型。利用该模型对XJTU-SY数据集中不同工况下的轴承进行早期故障检测,结果表明:KECA能够有效地提取特征信息,减少冗余信息的干扰;该模型整体上能够较早检测出故障的发生,并且有较好的鲁棒性和泛化能力。

BO-AUC多类分类评估方法

分类技术是数据挖掘研究的核心技术之一,分类评估也是研究热点,基于AUC评估方法是分类评估领域的研究热点,其中B-AUC评估算法可以有效地评估分类器性能,但该评估方法有不足之处。该分类评估方法建立在不对称的两个类别上,影响了评价结果;根据非完全二叉树思想存储,浪费了存储空间;基于偏二叉树的搜索效率不高。利用完全二叉树的构造思想提出了BO-AUC评估方法,该方法将n个类别的分类问题分解为独立的二类进行成对的计算,可以有效地解决B-AUC的不足,进一步扩展基于AUC的评估标准,在MBNC实验上编程实现该方法,实验结果表明BO-AUC方法的有效性。

基于贝叶斯优化-卷积神经网络-双向长短期记忆神经网络的锂电池健康状态评估

准确估计电池健康状态是设备稳定运行的关键。针对当前健康状态研究中容量难以直接测量、估计模型调参费时等问题,提出基于多健康特征的贝叶斯优化(BO)算法优化卷积神经网络(CNN)与双向长短期记忆(BiLSTM)神经网络预测模型。基于NASA公开锂电池数据,提取3种健康特征。将CNN与BiLSTM结合,提高时间序列数据处理能力,加入BO算法自动搜寻最优参数集,避免组合网络模型陷入局部最优,从而减少评估时间。对比分析相关神经网络模型,结果表明所提方法预测准确度最高,可有效估计锂电池的健康状态,平均绝对误差和方均根误差均在1%以内。

基于BO-GRU的混凝土坝变形预测模型

针对混凝土坝变形具有较强的非线性特点、目前大坝变形预测模型出现参数过多及易陷入局部最优等问题,提出了一种深度学习中的门控制循环单元(GRU)模型,并结合贝叶斯优化算法(BO)对门控制循环单元的超参数进行优化,建立BO-GRU模型应用于混凝土坝变形预测。为检验模型的可行性,以实测变形监测数据为基础,并与极限学习机、相关向量机和基于遗传算法优化的支持向量机等模型预测结果进行对比。结果表明:该模型的泛化能力强、运行效率高,能有效运用于混凝土坝的变形预测。

基于FCM聚类与BO算法的PEMFC故障分类

针对质子交换膜燃料电池(PEMFC)故障分类问题,提出基于模糊C均值(FCM)聚类和贝叶斯优化(BO)算法的故障分类方法。用Randles等效电路模型拟合210组阻抗谱实验数据,并用最小二乘法辨识模型各元件参数,选取特征向量构成数据样本。用FCM聚类算法求得数据样本的聚类中心,划分故障类别,剔除10组隶属度不足的数据。采用BO算法对60组训练数据建模,并验证分析140组测试数据。该方法可快速识别正常、膜干和水淹状态,分类准确率达97.86%。

Bi-objective Layout Optimization for Multiple Wind Farms Considering Sequential Fluctuation of Wind Power Using Uniform Design

The fluctuation of wind power brings great challenges to the secure,stable,and cost-efficient operation of the power system.Because of the time-correlation of wind speed and the wake effect of wind turbines,the layout of wind farm has a significant impact on the wind power sequential fluctuation.In order to reduce the fluctuation of wind power and improve the operation security with lower operating cost,a bi-objective layout optimization model for multiple wind farms considering the sequential fluctuation of wind power is proposed in this paper.The goal is to determine the optimal installed capacity of wind farms and the location of wind turbines.The proposed model maximizes the energy production and minimizes the fluctuation of wind power simultaneously.To improve the accuracy of wind speed estimation and hence the power calculation,the timeshifting of wind speed between the wind tower and turbines’locations is also considered.A uniform design based two-stage genetic algorithm is developed for the solution of the proposed model.Case studies demonstrate the effectiveness of this proposed model.

Research on a stock-matching trading strategy based on bi-objective optimization

In recent years,with strict domestic financial supervision and other policy-oriented factors,some products are becoming increasingly restricted,including nonstandard products,bank-guaranteed wealth management products,and other products that can provide investors with a more stable income.Pairs trading,a type of stable strategy that has proved efficient in many financial markets worldwide,has become the focus of investors.Based on the traditional Gatev-Goetzmann-Rouwenhorst(GGR,Gatev et al.2006)strategy,this paper proposes a stock-matching strategy based on bi-objective quadratic programming with quadratic constraints(BQQ)model.Under the condition of ensuring a long-term equilibrium between pairedstock prices,the volatility of stock spreads is increased as much as possible,improving the profitability of the strategy.To verify the effectiveness of the strategy,we use the natural logs of the daily stock market indices in Shanghai.The GGR model and the BQQ model proposed in this paper are back-tested and compared.The results show that the BQQ model can achieve a higher rate of returns.

基于高斯过程回归的机翼/短舱一体化气动优化

为了解决机翼/短舱一体化气动设计的高维非线性优化问题,基于高斯过程回归(GPR)模型提出新型优化设计方法.采用类别形状函数变换(CST)方法对机翼/短舱一体化构型中的翼型进行几何参数化建模;通过控制机翼形状参数、短舱形状参数和短舱安装参数实现机翼/短舱构型变形,该参数化建模过程共计包含50个设计参数.通过GPR模型构建机翼/短舱设计参数与气动性能之间的代理模型,并采用贝叶斯优化(BO)算法实现代理模型的自更新和最优气动外形的获取.结果表明:优化后一体化构型的阻力系数下降了10.95%,通过流场分析发现机翼外形和短舱外形的优化改善了表面流场结构,短舱安装位置的优化减弱了机翼和短舱间的气动干扰.

基于贝叶斯优化BiLSTM模型的输电塔损伤识别

结构的加速度响应可以反映结构的状态信息,蕴含结构的损伤特征。针对目前输电塔健康监测系统产生大量数据而无法有效分析和诊断输电塔损伤的问题,利用结构输出加速度响应数据的时序关系,提出了基于双向长短时记忆网络(bi-directional long and short-term memory,BiLSTM)的损伤识别方法,并采用概率寻优方法贝叶斯优化(Bayesian optimization,BO)确定网络模型超参数。首先描述了BiLSTM的基本原理,给出基于贝叶斯优化的超参数选取策略,从而提出了基于BO-BiLSTM模型的损伤识别方法。然后使用该方法对输电塔有限元模型进行了损伤定位与模式识别,测试集的整体识别准确率达到94.2%。为了验证该方法对实际结构的损伤识别效果,提出基于异源数据的损伤识别方式:将输电塔有限元模型数据作为模型训练的样本训练BO-BiLSTM模型,使用试验数据用作验证集检验损伤识别效果。识别结果表明BO-BiLSTM可以较为准确的识别真实结构的损伤情况,识别效果较BiLSTM以及BO-LSTM更稳定。

基于ForGAN的高速电梯制动器失效预测方法

针对高速电梯制动器失效率及维护决策方面的研究目前仍存在明显的不足。为了解决目前高速电梯在制动器失效率预测上存在结果准确性和可靠性不足的问题,对高速电梯制动器失效模式和机理进行了分析,确定了影响制动器失效的主要原因和相关参数,提出了一种经贝叶斯超参数优化后的预测性生成对抗网络(ForGAN)模型。首先,采集了高速电梯制动器工作性能数据,并对其进行了归一化处理;然后,利用主成分分析法进行了理论失效率计算,并采用了基于BO+ForGAN的模型对制动器失效率进行了预测和分析;最后,将所得结果与SVM、BiLSTM等传统预测模型所得结果进行了分析对比,并选取绝对误差、均方根误差、决定系数(R2)对上述各个预测结果的精度进行了评估。研究结果表明:基于BO+ForGAN模型的制动器失效率预测效果最好,泛化能力最高,能适应不同的实验工况,且贝叶斯超参数寻优算法能够找到一组最优的超参数。评估结果显示,高速电梯制动器失效率预测值的准确率达到了98.1%,从而验证了基于BO+ForGAN模型(方法)的有效性。

一种利用贝叶斯优化的蓝藻遥感分类方法

利用Sentinel-2遥感卫星影像,结合遥感优势以光谱、指数、纹理等14种多种特征信息为输入,依托贝叶斯优化算法,设计了一种能自动获取最优超参数组合的BO-XGBoost方法,并将其成功应用于2021年阳澄湖蓝藻信息提取。结果表明:①通过贝叶斯优化算法获取最优超参数组合,进行训练得到BO-XGBoost蓝藻分类模型,其训练结果在测试集和训练集上表现效果良好,准确率高达96.07%;②将BO-XGBoost应用于参与样本集构建的影像,其蓝藻识别结果与人工解译成果对比,2种方法得到的蓝藻空间分布情况基本一致,交并比最低为41.31%;③为评价该分类模型在其他时相的适用性,选择其他时相影像数据进行蓝藻提取,BO-XGBoost与人工解译2种方法蓝藻空间分布情况基本一致,交并比最低为43.85%。