基于CSSA-F-SVM模型的矿用卡车发动机智能故障诊断

针对矿用卡车发动机小样本故障数据导致诊断精度不足的问题，提出了一种基于改进的麻雀搜索算法优化基于凸半径边缘的SVM模型(F-SVM)的矿用卡车发动机智能故障诊断方法。首先，针对麻雀搜索算法中全局搜索能力不足的问题引入链式搜索策略。其次，遵循位置最优原则，对加入者位置更新进行改进，以提高其收敛性能。最后，使用改进后的麻雀算法对F-SVM的核参数g和惩罚因子C进行寻优，进而构建矿用卡车发动机故障诊断模型。实验结果表明，本文CSSA-F-SVM模型方法的预测准确度更高，分别较传统SVM和F-SVM模型提高了21.5%和4.1%。该模型能够较好地实现矿用卡车发动机常见故障的诊断，适用于小样本数据的故障预测，可为矿山机械设备的智能故障诊断提供参考。

Intelligent Fault Diagnosis of Mining Truck Engine Based on CSSA-F-SVM Model

Aiming at the problems that mining truck engine have poor fault diagnosis accuracy in the case of small samples, a mining truck engine intelligent failure diagnosis method based on the improved sparrow search algorithm optimizing convex radius-margin-based SVM model (F-SVM) was proposed. Firstly, a chain search strategy was introduced to solve the problem of insufficient global search ability in the sparrow search algorithm. Secondly, following the principle of optimal location, the location update of the joiners was optimized to improve its convergence performance. Finally, the improved sparrow algorithm was adopted to optimize the kernel parameter g and penalty factor C of F-SVM, and then a fault diagnosis model of mining truck engine was constructed. The experimental results prove that the prediction accuracy of the proposed method is higher, which is 21.5% and 4.1% higher than the traditional SVM and F-SVM models, respectively. The model can better realize the diagnosis of common faults of mining truck engines. It is suitable for fault prediction of small sample data, and provides a reference for intelligent fault diagnosis of mining machinery and equipment.