ABSTRACT
The track condition of a bridge crane directly affects the production efficiency and life safety. Due to the limitation of harsh environment, the traditional detection methods include high altitude danger, difficult operation and low efficiency. In this paper, according to the on-line inspection of wheel track wear, the acoustic signal of electric converter is used to collect the sound signal. The method of failure detection based on power spectrum is proposed, and the BIF feature selection combined with Fisher criterion is used to select the best special collection, and the problem of many characteristics is solved. Finally, we use the two classification logic regression to achieve the mathematical modeling between the feature set and the wear volume, and use the H function as the basis of failure judgement. The results show that the failure probability value of the system is more than 0.8 when the wheel wear is serious and close to failure, which is approximately equal to the real value. It can provide a reliable basis for the detection of wheel track.
- 1] Peng Shaoliang , Li Shanshan , Peng Yuxing , etal . Energy2 efficient and fast met hod on storage and querying in wireless sensor network [J ] . Journal on Communications , 2017 , 29(11) : 128-138Google Scholar
- RN Calheiros, R Ranjan.CloudSim: a toolkit for modeling and simulation of cloud computing environments and evaluation of resource provisioning algorithms.Software: Practice and Experience, 2016, 41(1):23∼50Google ScholarDigital Library
- Hugo Simao, Warren Powell.Approximate dynamic programming for management of high-value spare parts.Journal of Manufacturing Technology Management, 2016, 20(2):147∼160Google ScholarCross Ref
- Guilin , Gao Hong. A load balance data storage method based on ring for sensor networks [J ] . Journal of Software ,2007 , 18 (5) : 1173-1185Google Scholar
- 5]Prabh K S , Abdelzaher T F. Energy2conserving data cache placement in sensor networks [J ] . ACM Trans on Sensor Networks , 2005 , 1 (2) : 1782203Google Scholar
- 6 ] Shah R C , Roy S , Jain S , . Modeling a three2tier architecture for sparse sensor networks [ C] Proc of the 1st IEEE Intl. Workshop on Sensor Network Protocols and Applications ( SPNA ) . Los Alamitos , CA : IEEE Computer Society , 2003 : 30-41Google Scholar
- 7 ] Shen B , Li Q , Mao W. Data storage placement in sensor networks [C] Proc of Mobile Hoc. Los Alamitos , CA : IEEE Computer Society , 2006Google Scholar
- Zhang Changqing. Acoustic Emission Detection of Wheel Damage [J], Modular Machine Tool and Automatic Machining Technology 2002,20(4):266-270Google Scholar
- Zhou Zhanxue,Wang Bin. Using FFT power spectrum to analyze machine tool noise signal [J, Journal of Hebei Institute of Mechanical and Electrical Technology,2011,47(1):177-181Google Scholar
- Zhiqiang,Zhang Ruiping. Design of prop condition monitoring system based on wavelet packet and fuzzy neural network [J], manufacturing automation 2003,25,273-277.Google Scholar
- Hengliang Shi, Lintao Zheng, Shibao Sun, Lei Zhang, Lei Wang.Research on wire rope wear detection based on computer vision [J], The Journal of Engineering,2020,35(17),354-359.Google Scholar
- He K, Zhang X, Ren S, Deep Residual Learning for Image Recognition[C]//Computer Vision and Pattern Recognition. IEEE, 2016:770-778.Google Scholar
- Gao H, Zhuang L, Maaten L V D, Densely Connected Convolutional Networks[C]// IEEE Conference on Computer Vision & Pattern Recognition. 2017.Google Scholar
- Iandola F N, Han S, Moskewicz M W, SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size[J]. 2016.Google Scholar
- Howard A G , Zhu M , Chen B , MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications[J]. 2017.Google Scholar
- He Y , Zhang X , Sun J . Channel Pruning for Accelerating Very Deep Neural Networks[J]. 2017.Google ScholarCross Ref
- Girshick R , Donahue J , Darrell T , Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation[C]// 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE Computer Society, 2014Google Scholar
Recommendations
Fault detection in autonomous robots based on fault injection and learning
In this paper, we study a new approach to fault detection for autonomous robots. Our hypothesis is that hardware faults change the flow of sensory data and the actions performed by the control program. By detecting these changes, the presence of faults ...
Trim-to-Coherence Fourier Transform
We introduce a discrete Fourier transform technique which extracts more spectral information from a given time series data set than conventional discrete Fourier transform (DFT). Valid information is obtained between the spectral bins of conventional ...
Representation of the Fourier Transform by Fourier Series
The analysis of the mathematical structure of the integral Fourier transform shows that the transform can be split and represented by certain sets of frequencies as coefficients of Fourier series of periodic functions in the interval $$[0,2\pi)$$ . In this paper we ...
Comments