Locating and maintaining multiple Pareto optimal sets (PSs) in the decision space simultaneously is a challenging issue in solving multimodal multiobjective optimization problems (MMOPs). To deal with this challenge, this paper proposed a multipopulation particle swarm optimization based on divergent guidance and knowledge transfer (MPPSO-DGKT). First, a divergent guidance strategy is proposed to utilize the information of superior and inferior particles in the subpopulation. This strategy can alleviate the premature convergence due to the excessive influence of the global Pareto optimal solutions found so far. Second, a knowledge transfer strategy is developed to promote the knowledge transfer between different subpopulations, which can enhance the exploitation ability of the population. Finally, the update and selection strategy is used to keep more promising nondominated solutions, which can help the algorithm to obtain global and local PSs. To verify the effectiveness of the proposed algorithm, MPPSO-DGKT is compared with seven state-of-the-art multimodal multiobjective optimization algorithms on CEC2020 competition. Experimental results indicate that the proposed algorithm is more competitive than its competitors when solving MMOPs with both global and local PSs.

Competitive swarm optimizer (CSO) has been concerned in recent years due to its achievements in solving global optimization problems. However, the CSO algorithm still suffers from issues such as low solution precision and premature convergence since it only relies on the winners to guide the population evolution. To address this issue, an improved competitive swarm optimizer with super-particle-leading is proposed in this paper. First, the super particle obtained by the cumulative learning strategy is used to provide a promising evolution direction for the population. Next, the weight-based dynamic omnidirectional strategy is employed to enhance the population exploration ability. Finally, CEC2017 benchmark problems are used to evaluate the efficiency of the proposed algorithm. The experimental results demonstrate that the proposed algorithm is competitive with the contender algorithms due to its better balance between exploration and exploitation.

为了提高齿轮泵行星轮的典型故障诊断精度,提出了一种基于经验模态分解(EEMD)和双向长短时记忆网络(Bi-LSTM)的行星齿轮泵故障诊断方法.研究结果表明:通过模型精度和耗时的最优参数为节点数200和网络层数4层.本网络损失小于1％,满足良好稳定性的条件,可以实现精确识别齿面磨损和缺齿故障,断齿、正常齿的轮识别率都达到了93％以上,齿根裂纹故障识别率达到了86.5％.对信号EEMD分解后,可以促进Bi-LTSM模型所有分量都获得更优的时序性,促使模型诊断精度得到显著提升.Bi-LTSM模型到达后期迭代过程时,可以更快拟合,获得高于LTSM的验证精度.该研究对提高机械传动设备的故障识别能力,具有一定的理论指导意义.

The rapid development of communication and computer has brought many application scenarios to the fingerprint identification technology of communication equipment. The technology is of great significance in electronic countermeasures, wireless network security, and other fields and has been widely studied in recent years. The fingerprint identification technology of communication equipment is mainly based on the fingerprint characteristics represented on the transmitted signals of the equipment, which are different from other devices, and the connection between the characteristics and the hardware equipment is established, so as to realize the purpose of identifying the communication equipment. In this paper, the author studies the key technologies related to fingerprint recognition of communication equipment, including signal acquisition, signal feature extraction, and classifier design, and transient signal recognition equipment. In this paper, the integrated learning and deep learning based on fingerprint recognition are taken as the main research contents of communication equipment, and the fingerprint recognition scheme of communication equipment is given; the proposed scheme is verified by the measured data. Aiming at the transient signal of communication equipment, an algorithm using the short-term periodicity of signal is presented. The feature extraction of steady-state signal is realized. The autoencoder feature and four kinds of integral bispectrum feature are analyzed and visualized. Research on communication equipment individual recognition technology is based on ensemble learning. An individual recognition scheme for communication devices based on Extreme Gradient Boosting (XGBoost) classification model is studied. The Gradient Boosting Decision Tree (GBDT) model with different parameters was used as the primary learner of stacking classifier. The steady-state signal recognition of mobile phones based on deep learning is studied. The results show that the stacking recognition rate improved by about 2% compared with GBDT using multiple GBDT models with different parameters as the primary learner.

To gain a more comprehensive and systematic understanding of the impact of government assistance to poor households on poverty reduction targets, a targeted poverty alleviation information statistics and analysis integrated with big data mining algorithm is proposed. Combined with the big data knowledge of the new era, according to the machine learning (ML) pipeline module in spark, a big data computing framework, combined with known data mining algorithms, massive sample data are used to replace random stratified sampling data for modeling and analysis, and random forest model, logistic model, and newly proposed waterfall model are constructed for poor households. Finally, through the comparative evaluation of several poor household identification models, the results show that when 100 real data test the accuracy of the three poor household models, the random forest model and logistic model are slightly reduced, which are 82% and 72%, respectively, but the waterfall model is basically unchanged, which is 83%, and the three models have little change. The new waterfall design proposed in this article has the advantage of a high percentage of sample reuse and can effectively prevent overfitting, and there is no need for massive data. It is a stable and reliable new model. The combination of targeted poverty reduction algorithms and big information technology and mining data can get the most common causes more accurate and convincing results. The right rib trunk and rib are often separated from the common cause because of the population.

In multimodal multi-objective optimization, the key issue is to find as many Pareto optimal solutions as possible and select promising solutions in the environmental selection. This paper proposes a multimodal multi-objective particle swarm optimization algorithm based on multi-directional guidance (MM-PSO-MG) to solve these problems. In the proposed algorithm, multi-directional guidance strategy is introduced to avoid premature convergence and find more Pareto optimal solutions. Moreover, the rank-based special crowding distance strategy is used to select promising solutions. 11 multimodal multi-objective test problems are used to verify the performance of the proposed algorithm. The results show that the proposed algorithm is competitive.