The invention discloses an intelligent fault diagnosis method and system for a production line lifting appliance based on PCA-SVDD (Principal Component Analysis-Singular Value Decomposition Decomposition), and aims to quickly and accurately diagnose a short-circuit fault of an automobile production line lifting appliance. The method comprises the following steps: firstly, acquiring voltage data of the lifting appliance, sampling the acquired data by using a sliding time window, secondly, preprocessing the data, inputting the data into a PCA model for dimensionality reduction and feature extraction, and finally, inputting the extracted features into an SVDD model for fault diagnosis, and judging the current state of the lifting appliance. Tests show that the fault lifting appliance can be quickly and accurately positioned, the missing report rate and the error report rate can be reduced, the shutdown loss can be reduced, meanwhile, the method has higher sensitivity, robustness and adaptive capacity, and a scientific basis can be provided for decision making of workers.
本发明公开了一种基于PCA‑SVDD的产线吊具智能故障诊断方法及系统,旨在对汽车生产线吊具的短路故障进行快速和精准的诊断。本发明首先采集吊具的电压数据并使用滑动时间窗口对采集到的数据进行取样处理,其次对数据进行预处理并输入到PCA模型中进行降维和特征提取,最后将提取到的特征输入到SVDD模型中进行故障诊断,判断吊具当前所处的状态。经过测试发现,本发明可以实现对于故障吊具的快速精准定位,降低漏报率和错报率,减少停机损失,同时具有更高的灵敏度、鲁棒性和自适应能力,可以为工作人员决策提供科学依据。
PCA-SVDD-based production line lifting appliance intelligent fault diagnosis method and system
一种基于PCA-SVDD的产线吊具智能故障诊断方法及系统
2024-01-16
Patent
Elektronische Ressource
Chinesisch
Fault diagnosis of ZDJ7 railway point machine based on improved DCNN and SVDD classification
DOAJ | 2023
|Patch SVDD: Patch-Level SVDD for Anomaly Detection and Segmentation
British Library Conference Proceedings | 2021
|Visual lifting appliance intelligent management system
Europäisches Patentamt | 2021
|