To address the issue of abnormal energy consumption fluctuations in the converter steelmaking process,an integrated diagnostic method combining the gray wolf optimization(GWO)algorithm,support vector machine(SVM),and ...To address the issue of abnormal energy consumption fluctuations in the converter steelmaking process,an integrated diagnostic method combining the gray wolf optimization(GWO)algorithm,support vector machine(SVM),and K-means clustering was proposed.Eight input parameters—derived from molten iron conditions and external factors—were selected as feature variables.A GWO-SVM model was developed to accurately predict the energy consumption of individual heats.Based on the prediction results,the mean absolute percentage error and maximum relative error of the test set were employed as criteria to identify heats with abnormal energy usage.For these heats,the K-means clustering algorithm was used to determine benchmark values of influencing factors from similar steel grades,enabling root-cause diagnosis of excessive energy consumption.The proposed method was applied to real production data from a converter in a steel plant.The analysis reveals that heat sample No.44 exhibits abnormal energy consumption,due to gas recovery being 1430.28 kg of standard coal below the benchmark level.A secondary contributing factor is a steam recovery shortfall of 237.99 kg of standard coal.This integrated approach offers a scientifically grounded tool for energy management in converter operations and provides valuable guidance for optimizing process parameters and enhancing energy efficiency.展开更多
针对局部阴影情况下光伏阵列输出功率多峰值导致传统灰狼优化算法跟踪最大功率点收敛速度慢、搜索精度低且易陷入局部最优的问题,提出1种嵌入莱维飞行的改进灰狼优化和变步长扰动观察法算法。全局搜索中提出的新型非线性收敛因子提升了...针对局部阴影情况下光伏阵列输出功率多峰值导致传统灰狼优化算法跟踪最大功率点收敛速度慢、搜索精度低且易陷入局部最优的问题,提出1种嵌入莱维飞行的改进灰狼优化和变步长扰动观察法算法。全局搜索中提出的新型非线性收敛因子提升了灰狼优化算法的收敛速度和搜索精度,通过初始化种群正态分布进一步提升灰狼搜索效率;嵌入莱维飞行增加了全局搜索随机性,避免了搜索过程陷入局部最优;局部搜索中通过变步长扰动观察法实现全局最大功率点快速捕获。为验证算法的有效性,构建了已发表灰狼优化GWO(grey wolf optimization)算法和嵌入莱维飞行的改进GWO和变步长扰动观察ILGWO-VP&O(improved Levy-flight GWO and variable-step perturbation&observation)算法的光伏发电系统,并进行实验验证。实验结果表明,提出的ILGWO-VP&O算法动态响应速度最快,稳态控制精度最优。展开更多
针对局部遮阴情况(PSC:Partial Shading Conditions)下光伏阵列输出功率呈现多峰值特征导致传统最大功率点跟踪(MPPT:Maximum Power Point Tracking)算法存在跟踪速度慢、跟踪精度低等问题,提出一种基于改进灰狼优化算法(GWO:Grey Wolf ...针对局部遮阴情况(PSC:Partial Shading Conditions)下光伏阵列输出功率呈现多峰值特征导致传统最大功率点跟踪(MPPT:Maximum Power Point Tracking)算法存在跟踪速度慢、跟踪精度低等问题,提出一种基于改进灰狼优化算法(GWO:Grey Wolf Optimizer)和变步长电导增量法(VINC:Variable step-size Incremental Conductance)相结合的复合算法。首先,通过分析峰值点对应电压位置,在灰狼优化算法中加入峰值电压初始化策略;其次,引入非线性收敛因子以提升灰狼优化算法的全局搜索能力。该复合算法先利用改进灰狼优化算法进行全局搜索,再切换至引入dP/dU的变步长电导增量法进行局部搜索。Matlab/Simulink仿真结果表明,所提复合算法在静态和动态局部遮阴情况下均能提升跟踪速度与精度,同时减小输出功率振荡幅度。展开更多
The grey wolf optimizer(GWO)is a swarm-based intelligence optimization algorithm by simulating the steps of searching,encircling,and attacking prey in the process of wolf hunting.Along with its advantages of simple pr...The grey wolf optimizer(GWO)is a swarm-based intelligence optimization algorithm by simulating the steps of searching,encircling,and attacking prey in the process of wolf hunting.Along with its advantages of simple principle and few parameters setting,GWO bears drawbacks such as low solution accuracy and slow convergence speed.A few recent advanced GWOs are proposed to try to overcome these disadvantages.However,they are either difficult to apply to large-scale problems due to high time complexity or easily lead to early convergence.To solve the abovementioned issues,a high-accuracy variable grey wolf optimizer(VGWO)with low time complexity is proposed in this study.VGWO first uses the symmetrical wolf strategy to generate an initial population of individuals to lay the foundation for the global seek of the algorithm,and then inspired by the simulated annealing algorithm and the differential evolution algorithm,a mutation operation for generating a new mutant individual is performed on three wolves which are randomly selected in the current wolf individuals while after each iteration.A vectorized Manhattan distance calculation method is specifically designed to evaluate the probability of selecting the mutant individual based on its status in the current wolf population for the purpose of dynamically balancing global search and fast convergence capability of VGWO.A series of experiments are conducted on 19 benchmark functions from CEC2014 and CEC2020 and three real-world engineering cases.For 19 benchmark functions,VGWO’s optimization results place first in 80%of comparisons to the state-of-art GWOs and the CEC2020 competition winner.A further evaluation based on the Friedman test,VGWO also outperforms all other algorithms statistically in terms of robustness with a better average ranking value.展开更多
滚动轴承作为机械设备的重要部件,对其进行剩余使用寿命预测在企业的生产过程中变得越来越重要。目前,虽然主流的卷积神经网络(convolutional neural network, CNN)可以自动地从轴承的振动信号中提取特征,却不能给特征分配不同的权重来...滚动轴承作为机械设备的重要部件,对其进行剩余使用寿命预测在企业的生产过程中变得越来越重要。目前,虽然主流的卷积神经网络(convolutional neural network, CNN)可以自动地从轴承的振动信号中提取特征,却不能给特征分配不同的权重来提高模型对重要特征的关注程度,对于长时间序列容易丢失重要信息。另外,神经网络中隐藏层神经元个数、学习率以及正则化参数等超参数还需要依靠人工经验设置。为了解决上述问题,提出基于灰狼优化(grey wolf optimizer, GWO)算法、优化集合CNN、双向长短期记忆(bidirectional long short term memory, BiLSTM)网络和注意力机制(Attention)轴承剩余使用寿命预测方法。首先,从原始振动信号中提取时域、频域以及时频域特征指标构建可选特征集;然后,通过构建考虑特征相关性、鲁棒性和单调性的综合评价指标筛选出高于设定阈值的轴承退化敏感特征集,作为预测模型的输入;最后,将预测值和真实值的均方误差作为GWO算法的适应度函数,优化预测模型获得最优隐藏层神经元个数、学习率和正则化参数,利用优化后模型进行剩余使用寿命预测,并在公开数据集上进行验证。结果表明,所提方法可在非经验指导下获得最优的超参数组合,优化后的预测模型与未进行优化模型相比,平均绝对误差与均方根误差分别降低了28.8%和24.3%。展开更多
The widespread penetration of distributed energy sources and the use of load response programs,especially in a microgrid,have caused many power system issues,such as control and operation of these networks,to be affec...The widespread penetration of distributed energy sources and the use of load response programs,especially in a microgrid,have caused many power system issues,such as control and operation of these networks,to be affected.The control and operation of many small-distributed generation units with different performance characteristics create another challenge for the safe and efficient operation of the microgrid.In this paper,the optimum operation of distributed generation resources and heat and power storage in a microgrid,was performed based on real-time pricing through the proposed gray wolf optimization(GWO)algorithm to reduce the energy supply cost with the microgrid.Distributed generation resources such as solar panels,diesel generators with battery storage,and boiler thermal resources with thermal storage were used in the studied microgrid.Also,a combined heat and power(CHP)unit was used to produce thermal and electrical energy simultaneously.In the simulations,in addition to the gray wolf algorithm,some optimization algorithms have also been used.Then the results of 20 runs for each algorithm confirmed the high accuracy of the proposed GWO algorithm.The results of the simulations indicated that the CHP energy resources must be managed to have a minimum cost of energy supply in the microgrid,considering the demand response program.展开更多
火电厂在稳定运行的同时,不可避免地会排放大量污染气体,尤其是NOx。针对传统测量方法的不足,该文提出一种基于灰狼优化反向传播神经网络(grey wolf optimized-back propagation,GWO-BP)的NOx排放量软测量模型。首先使用典型相关性分析(...火电厂在稳定运行的同时,不可避免地会排放大量污染气体,尤其是NOx。针对传统测量方法的不足,该文提出一种基于灰狼优化反向传播神经网络(grey wolf optimized-back propagation,GWO-BP)的NOx排放量软测量模型。首先使用典型相关性分析(canonical correlation analysis,CCA)将任意两个相关度较高的变量归为一组,并去掉其中一个,从而选择了对NOx排放量影响最大的4个变量作为软测量模型的输入;然后,建立了反向传播(back propagation,BP)神经网络模型以对输入变量和NOx排放量做映射;最后,采用灰狼优化(grey wolf optimizer,GWO)算法优化了所提软测量模型的权重和偏置值,提升了模型的精度。实验结果表明,所提软测量模型可以准确测量NOx的排放量,在传感器故障或伴有噪声的时候很好地替代了传感器的角色,为优化算法及深度学习方法在工业现场的应用提供了参考。展开更多
Grey Wolf Optimization (GWO) is a nature-inspired metaheuristic algorithm that has gained popularity for solving optimization problems. In GWO, the success of the algorithm heavily relies on the efficient updating of ...Grey Wolf Optimization (GWO) is a nature-inspired metaheuristic algorithm that has gained popularity for solving optimization problems. In GWO, the success of the algorithm heavily relies on the efficient updating of the agents’ positions relative to the leader wolves. In this paper, we provide a brief overview of the Grey Wolf Optimization technique and its significance in solving complex optimization problems. Building upon the foundation of GWO, we introduce a novel technique for updating agents’ positions, which aims to enhance the algorithm’s effectiveness and efficiency. To evaluate the performance of our proposed approach, we conduct comprehensive experiments and compare the results with the original Grey Wolf Optimization technique. Our comparative analysis demonstrates that the proposed technique achieves superior optimization outcomes. These findings underscore the potential of our approach in addressing optimization challenges effectively and efficiently, making it a valuable contribution to the field of optimization algorithms.展开更多
基金support from the National Key R&D Program of China(Grant No.2020YFB1711100).
摘要To address the issue of abnormal energy consumption fluctuations in the converter steelmaking process,an integrated diagnostic method combining the gray wolf optimization(GWO)algorithm,support vector machine(SVM),and K-means clustering was proposed.Eight input parameters—derived from molten iron conditions and external factors—were selected as feature variables.A GWO-SVM model was developed to accurately predict the energy consumption of individual heats.Based on the prediction results,the mean absolute percentage error and maximum relative error of the test set were employed as criteria to identify heats with abnormal energy usage.For these heats,the K-means clustering algorithm was used to determine benchmark values of influencing factors from similar steel grades,enabling root-cause diagnosis of excessive energy consumption.The proposed method was applied to real production data from a converter in a steel plant.The analysis reveals that heat sample No.44 exhibits abnormal energy consumption,due to gas recovery being 1430.28 kg of standard coal below the benchmark level.A secondary contributing factor is a steam recovery shortfall of 237.99 kg of standard coal.This integrated approach offers a scientifically grounded tool for energy management in converter operations and provides valuable guidance for optimizing process parameters and enhancing energy efficiency.
摘要针对局部阴影情况下光伏阵列输出功率多峰值导致传统灰狼优化算法跟踪最大功率点收敛速度慢、搜索精度低且易陷入局部最优的问题,提出1种嵌入莱维飞行的改进灰狼优化和变步长扰动观察法算法。全局搜索中提出的新型非线性收敛因子提升了灰狼优化算法的收敛速度和搜索精度,通过初始化种群正态分布进一步提升灰狼搜索效率;嵌入莱维飞行增加了全局搜索随机性,避免了搜索过程陷入局部最优;局部搜索中通过变步长扰动观察法实现全局最大功率点快速捕获。为验证算法的有效性,构建了已发表灰狼优化GWO(grey wolf optimization)算法和嵌入莱维飞行的改进GWO和变步长扰动观察ILGWO-VP&O(improved Levy-flight GWO and variable-step perturbation&observation)算法的光伏发电系统,并进行实验验证。实验结果表明,提出的ILGWO-VP&O算法动态响应速度最快,稳态控制精度最优。
摘要针对局部遮阴情况(PSC:Partial Shading Conditions)下光伏阵列输出功率呈现多峰值特征导致传统最大功率点跟踪(MPPT:Maximum Power Point Tracking)算法存在跟踪速度慢、跟踪精度低等问题,提出一种基于改进灰狼优化算法(GWO:Grey Wolf Optimizer)和变步长电导增量法(VINC:Variable step-size Incremental Conductance)相结合的复合算法。首先,通过分析峰值点对应电压位置,在灰狼优化算法中加入峰值电压初始化策略;其次,引入非线性收敛因子以提升灰狼优化算法的全局搜索能力。该复合算法先利用改进灰狼优化算法进行全局搜索,再切换至引入dP/dU的变步长电导增量法进行局部搜索。Matlab/Simulink仿真结果表明,所提复合算法在静态和动态局部遮阴情况下均能提升跟踪速度与精度,同时减小输出功率振荡幅度。
摘要The grey wolf optimizer(GWO)is a swarm-based intelligence optimization algorithm by simulating the steps of searching,encircling,and attacking prey in the process of wolf hunting.Along with its advantages of simple principle and few parameters setting,GWO bears drawbacks such as low solution accuracy and slow convergence speed.A few recent advanced GWOs are proposed to try to overcome these disadvantages.However,they are either difficult to apply to large-scale problems due to high time complexity or easily lead to early convergence.To solve the abovementioned issues,a high-accuracy variable grey wolf optimizer(VGWO)with low time complexity is proposed in this study.VGWO first uses the symmetrical wolf strategy to generate an initial population of individuals to lay the foundation for the global seek of the algorithm,and then inspired by the simulated annealing algorithm and the differential evolution algorithm,a mutation operation for generating a new mutant individual is performed on three wolves which are randomly selected in the current wolf individuals while after each iteration.A vectorized Manhattan distance calculation method is specifically designed to evaluate the probability of selecting the mutant individual based on its status in the current wolf population for the purpose of dynamically balancing global search and fast convergence capability of VGWO.A series of experiments are conducted on 19 benchmark functions from CEC2014 and CEC2020 and three real-world engineering cases.For 19 benchmark functions,VGWO’s optimization results place first in 80%of comparisons to the state-of-art GWOs and the CEC2020 competition winner.A further evaluation based on the Friedman test,VGWO also outperforms all other algorithms statistically in terms of robustness with a better average ranking value.
摘要滚动轴承作为机械设备的重要部件,对其进行剩余使用寿命预测在企业的生产过程中变得越来越重要。目前,虽然主流的卷积神经网络(convolutional neural network, CNN)可以自动地从轴承的振动信号中提取特征,却不能给特征分配不同的权重来提高模型对重要特征的关注程度,对于长时间序列容易丢失重要信息。另外,神经网络中隐藏层神经元个数、学习率以及正则化参数等超参数还需要依靠人工经验设置。为了解决上述问题,提出基于灰狼优化(grey wolf optimizer, GWO)算法、优化集合CNN、双向长短期记忆(bidirectional long short term memory, BiLSTM)网络和注意力机制(Attention)轴承剩余使用寿命预测方法。首先,从原始振动信号中提取时域、频域以及时频域特征指标构建可选特征集;然后,通过构建考虑特征相关性、鲁棒性和单调性的综合评价指标筛选出高于设定阈值的轴承退化敏感特征集,作为预测模型的输入;最后,将预测值和真实值的均方误差作为GWO算法的适应度函数,优化预测模型获得最优隐藏层神经元个数、学习率和正则化参数,利用优化后模型进行剩余使用寿命预测,并在公开数据集上进行验证。结果表明,所提方法可在非经验指导下获得最优的超参数组合,优化后的预测模型与未进行优化模型相比,平均绝对误差与均方根误差分别降低了28.8%和24.3%。
基金This work was supported in part by an International Research Partnership“Electrical Engineering—Thai French Research Center(EE-TFRC)”under the project framework of the Lorraine Universitéd’Excellence(LUE)in cooperation between Universitéde Lorraine and King Mongkut’s University of Technology North Bangkok and in part by the National Research Council of Thailand(NRCT)under Senior Research Scholar Program under Grant No.N42A640328.
摘要The widespread penetration of distributed energy sources and the use of load response programs,especially in a microgrid,have caused many power system issues,such as control and operation of these networks,to be affected.The control and operation of many small-distributed generation units with different performance characteristics create another challenge for the safe and efficient operation of the microgrid.In this paper,the optimum operation of distributed generation resources and heat and power storage in a microgrid,was performed based on real-time pricing through the proposed gray wolf optimization(GWO)algorithm to reduce the energy supply cost with the microgrid.Distributed generation resources such as solar panels,diesel generators with battery storage,and boiler thermal resources with thermal storage were used in the studied microgrid.Also,a combined heat and power(CHP)unit was used to produce thermal and electrical energy simultaneously.In the simulations,in addition to the gray wolf algorithm,some optimization algorithms have also been used.Then the results of 20 runs for each algorithm confirmed the high accuracy of the proposed GWO algorithm.The results of the simulations indicated that the CHP energy resources must be managed to have a minimum cost of energy supply in the microgrid,considering the demand response program.
摘要火电厂在稳定运行的同时,不可避免地会排放大量污染气体,尤其是NOx。针对传统测量方法的不足,该文提出一种基于灰狼优化反向传播神经网络(grey wolf optimized-back propagation,GWO-BP)的NOx排放量软测量模型。首先使用典型相关性分析(canonical correlation analysis,CCA)将任意两个相关度较高的变量归为一组,并去掉其中一个,从而选择了对NOx排放量影响最大的4个变量作为软测量模型的输入;然后,建立了反向传播(back propagation,BP)神经网络模型以对输入变量和NOx排放量做映射;最后,采用灰狼优化(grey wolf optimizer,GWO)算法优化了所提软测量模型的权重和偏置值,提升了模型的精度。实验结果表明,所提软测量模型可以准确测量NOx的排放量,在传感器故障或伴有噪声的时候很好地替代了传感器的角色,为优化算法及深度学习方法在工业现场的应用提供了参考。
摘要Grey Wolf Optimization (GWO) is a nature-inspired metaheuristic algorithm that has gained popularity for solving optimization problems. In GWO, the success of the algorithm heavily relies on the efficient updating of the agents’ positions relative to the leader wolves. In this paper, we provide a brief overview of the Grey Wolf Optimization technique and its significance in solving complex optimization problems. Building upon the foundation of GWO, we introduce a novel technique for updating agents’ positions, which aims to enhance the algorithm’s effectiveness and efficiency. To evaluate the performance of our proposed approach, we conduct comprehensive experiments and compare the results with the original Grey Wolf Optimization technique. Our comparative analysis demonstrates that the proposed technique achieves superior optimization outcomes. These findings underscore the potential of our approach in addressing optimization challenges effectively and efficiently, making it a valuable contribution to the field of optimization algorithms.