任志玲,张景智.多策略融合 LSSVM-NGO 的滑动电接触失效诊断[J].电子测量与仪器学报,2023,37(12):37-47 |
多策略融合 LSSVM-NGO 的滑动电接触失效诊断 |
Multi-strategy fusion of LSSVM-NGO for slidingelectrical contact failure diagnosis |
|
DOI: |
中文关键词: 弓网系统 载流稳定系数 北方苍鹰算法 最小二乘支持向量机 接触失效 |
英文关键词:pantograph-catenary system current-carrying stability factor northern hawk algorithm least squares support vector
machine contact failure |
基金项目:国家自然科学基金(52104160)项目资助 |
|
|
摘要点击次数: 366 |
全文下载次数: 615 |
中文摘要: |
为提高弓网滑动电接触失效判断的准确率,提出了一种多策略融合改进北方苍鹰优化算法(INGO)和最小二乘支持向
量机(LSSVM)的滑动电接触失效诊断模型。 首先,通过自制的滑动电接触摩擦磨损实验机进行载流条件下的滑动摩擦实验,
分析载流稳定系数在不同工况条件下的变化规律,确定弓网接触失效判据;其次,采用 tent 混沌映射、均匀分布的动态自适应权
重,以及黄金正弦算法和非线性收敛因子多种融合策略综合改进 NGO。 通过测试函数对其进行仿真测试,结果证明 INGO 算法
收敛速度和稳定性更优;最后,使用 INGO 算法进行模型参数寻优,构建滑动电接触失效诊断模型。 将本文所提模型与其他诊
断模型对比,诊断精度分别提高了 16. 67%、12. 5%、8. 33%,进一步证明该诊断模型具有较高的准确率和泛化能力。
关键词: 弓网系统;载流稳定系数;北方苍鹰算法;最小二乘支持向量机;接触失效 |
英文摘要: |
In order to improve the accuracy of sliding electric contact failure judgement of the pantograph-catenary, a multi-strategy
fusion of improved northern goshawk optimisation algorithm (INGO) and least squares support vector machine (LSSVM) sliding electric
contact failure diagnosis model is proposed. Firstly, the self-made sliding electric contact testing machine is used to carry out friction
experiments, analyse the change rule of the current-carrying stability coefficient under different working conditions, and determine the
criteria for the pantograph-catenary contact failure; secondly, the tent chaotic mapping, uniformly distributed dynamic adaptive weights,
and the golden sinusoidal algorithm and the nonlinear convergence factor are used to improve the deficiencies in the NGO, and the
simulation is carried out through the test function. Test, the results prove that the improved northern wing algorithm ( INGO)
convergence speed and stability is better; finally, using the improved northern eagle optimisation algorithm on the model’ s parameter
optimisation, to establish the sliding electrical contact failure diagnostic model. Comparing the proposed model with other diagnostic
models, the diagnostic accuracy is improved by 16. 67%, 12. 5% and 8. 33% respectively, which further proves that the diagnostic
model has high accuracy and generalisation ability. |
查看全文 查看/发表评论 下载PDF阅读器 |
|
|
|