为了从船舶压载水系统中有效挖掘数据信息，降低极限学习机（ELM）初始参数随机性对故障诊断精度的影响，提出基于改进麻雀搜索算法（ISSA）优化ELM的船舶压载水系统故障诊断模型。首先，使用自适应加权策略和Levy飞行策略改进发现者位置公式，获得ISSA并验证其性能；而后利用改进后的麻雀搜索算法对ELM的初始输入权重和阈值进行优化，建立基于ISSA-ELM的故障诊断模型。结果表明，ISSA-ELM模型的故障诊断精度为96.6%，比SSA-ELM、PSO-ELM、GWO-ELM模型高出1.8%、3.5%和2.6%，比ELM和SVM模型高出4.5%和7.1%。
In order to effectively mine data information from ship ballast water systems and reduce the impact of initial parameter randomness of Extreme Learning Machine (ELM) on fault diagnosis accuracy, a ship ballast water system fault diagnosis model based on improved Sparrow Search Algorithm (ISSA) optimized ELM is proposed. Firstly, using adaptive weighting strategy and Levy flight strategy to improve the discoverer position formula, obtaining ISSA and verifying its performance; Then, the improved sparrow search algorithm is used to optimize the initial input weights and thresholds of ELM, and a fault diagnosis model based on ISSA-ELM is established. The experimental results show that the fault diagnosis accuracy of ISSA-ELM model is 96.6%, which is 1.8%, 3.5%, and 2.6% higher than SSA-ELM, PSO-ELM, and GWO-ELM models, and 4.5% and 7.1% higher than ELM and SVM models.
2024,46(19): 36-41 收稿日期：2023-12-14
DOI：10.3404/j.issn.1672-7649.2024.19.007
分类号：U664.83
基金项目：辽宁省自然资源厅项目（1638882993269）；辽宁省科技厅项目（2022JH1/10800097）
作者简介：王曼绮(1997-),女,硕士研究生,研究方向为故障诊断与优化算法
参考文献：
[1] 杨咏, 王晓, 兑红炎, 等. 船舶压载水系统可靠性分析[J]. 舰船科学技术, 2023, 45(12): 35–39.
YANG Yong, WANG Xiao, DUI Hong-Yan, et al. Reliability analysis of ship ballast water system[J]. Ship Science and Technology, 2023, 45(12): 35–39.
[2] 石大亮, 张毅然, 湛日景, 等. 基于关联规则分类的船用柴油机故障诊断[J]. 内燃机学报, 2023, 41(4): 369–375.
[3] KOWALSKI J, KRAWCZYK B, WO?NIAK M. Fault diagnosis of marine 4-stroke diesel engines using a one-vs-one extreme learning ensemble[J]. Engineering Applications of Artificial Intelligence, 2017, 57: 134–141.
[4] XI W, LI Z, TIAN Z, et al. A feature extraction and visualization method for fault detection of marine diesel engines[J]. Measurement, 2018, 116: 429–437.
[5] 王泷德, 曹辉, 魏来. 不平衡数据下船舶主机在线故障诊断研究[J]. 中国舰船研究, 2023, 18(5): 269-275.
[6] 王忠巍, 袁志国, 马修真, 等. 一种不依赖特征样本的柴油机故障诊断方法研究[J]. 哈尔滨工程大学学报, 2017, 38(6): 881–886.
[7] FENG D, LI Y. Research on intelligent diagnosis method for large-scale ship engine fault in non-deterministic environment[J]. Polish Maritime research, 2017, 24(1): 200-206.
[8] HUANG G. What are extreme learning machines? Filling the gap between frank rosenblatt’s dream and john von neumann’s puzzle[J]. Cognitive Computation, 2015, 7(3): 263–278.
[9] CHENGTIAN O, YAXIAN Q, DONGLIN Z. Adaptive spiral flying sparrow search algorithm[J]. Scientific Programming, 2021(6): 1–16.
[10] GUANGBIN H, HONGMING Z, XIAOJIAN D, et al. Extreme learning machine for regression and multiclass classification[J]. IEEE transactions on systems, man, and cybernetics, 2012, 42(2): 513–517.
[11] XUE J, SHEN B. A novel swarm intelligence optimization approach: sparrow search algorithm[J]. Systems Science & Control Engineering, 2020, 8(1): 2144–2158.
[12] LI J, AN Q, LEI H, et al. Survey of lévy flight-based metaheuristics for optimization[J]. Mathematics, 2022, 10(15): 27–85.
[13] YI L, HUIBING G, YUJIN C, et al. Research on fault prediction of marine diesel engine based on attention-LSTM[J]. Proceedings of the Institution of Mechanical Engineers, 2023, 237(2): 6–13.
[14] MENG Y, ZHANG X, LIU Z, et al. Support vector regression ship motion identification modeling based on grey wolf optimizer[C]//中国自动化学会控制理论专业委员会, 2021.
[15] 尹文哲, 夏虹, 彭彬森, 等. 基于CNN-SVM的核电厂轴承故障诊断方法[J]. 哈尔滨工程大学学报, 2023, 44(3): 410–417.
[16] CAO H, ZHANG J, CAO X, et al. Optimized SVM-driven multi-class approach by improved abc to estimating ship systems state[J]. IEEE access, 2020, 8: 206719–206733.
[17] 王志超, 夏虹, 彭彬森, 等. PSO-LSSVM的核电站破口故障程度评估方法[J]. 哈尔滨工程大学学报, 2021, 42(12): 1748–1753.
[18] LIU T, FAN Q, KANG Q, et al. Extreme learning machine based on firefly adaptive flower pollination algorithm optimization[J]. Processes, 2020, 8(12): 15–83.
