Abstract
Various faults occurred in the continuous bulk materials weighing equipment (CBMWE) usually lead to more economic loss and waste of human resources inevitably. A new approach based on the improved DBSCAN (Density-Based Spatial Clustering of Applications with Noise) clustering and Bayesian regularization neural network (BRNN) is proposed for online fault detection and diagnosis of CBMWE--electronic belt weigher (BW). Firstly, in view of the fault data varying with equipment flow, an improved DBSCAN clustering algorithm is developed to realize the online fault detection by extracting the fault data with the clustering analysis of the real-time data. Secondly, BRNN is proposed as a classifier to identify the fault pattern with the extracted fault data. Both the models of online fault detection and diagnosis are realized using MATLAB. Finally, the test result shows that the proposed online fault detection and diagnosis model is able to cope with the online fault detection and diagnosis of BW and also yields great diagnostic accuracy. In general, this approach for online fault detection and diagnosis of BW has a great significance to bulk weighing equipment.DOI: http://dx.doi.org/10.5755/j01.mech.21.1.8560
Highlights
Continuous bulk materials weighing equipment (CBMWE) is measuring equipment for bulk materials trade, widely used in ports, docks, power plant, metallurgy, building materials, electronics, chemical, food, mining, etc
We propose an improved DBSCAN, and build a fault diagnosis machine of belt weigher (BW) by combining the improved DBSCAN with artificial neural networks (ANN)
During the experiments of BW, the study finds that the accuracy of model based on back propagation neural network (BPNN) or RBF is very sensitive to the normalization, but the accuracy of model based on Bayesian regularization neural network (BRNN) is not
Summary
Continuous bulk materials weighing equipment (CBMWE) is measuring equipment for bulk materials trade, widely used in ports, docks, power plant, metallurgy, building materials, electronics, chemical, food, mining, etc. Hesam proposed an online fault detection method based on WFCM clustering [5]. They both need to specify the number of clusters in advance, and K-means can only discover spherical clusters. Xiaoyue et al introduced probability neural network as the classifier of fault diagnosis [20] They are only based on empirical risk minimization principle, and the experiment data of CBMWE or BW is relatively difficult to collect.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
