Scholarly record
TRACKING OPERATION REGIMES OF THE LHD MACHINES BASED ON HYDRAULIC SIGNAL - SIGNAL SMOOTHING ISSUES
Abstract
The development of advanced analytics for data measured by SCADA systems is crucial from the viewpoint of process monitoring, management, and optimization. Many mining assets are characterized by cyclical operations performed with a fixed sequence of their course. An example is the Load Haul Dump (LHD) machine transporting material from the mining face to the dumping point, where the material is preloaded into a further means of transport - a conveyor belt. For wheel loader, the basic signal is pressure signal measured at a bucket?s hydraulic cylinder in which we can distinguish the particular sub-processes of haulage ? loading, driving with a full bucket, return to mining face. In the literature, there are known many methods of signal segmentation that are able to recognize these regimes automatically. Unfortunately, in the case of the raw hydraulic pressure signal, we are dealing with various artifacts and noises, which makes the segmentation task very difficult or even impossible. In this article, we present the review of signal smoothing methods and check their efficiency, especially in terms of retaining informative trends in the signals. All of the methods have been validated on real-life data from the LHD vehicles working in mining conditions. Each of the smoothing methods was tested for two samples, one shorter, containing a period of one hour and one longer - two hours. Comprehensive comparative analysis has been performed between presented methods - for a more accurate comparison, several statistics were determined based on the number and duration of designated cycles.
Publication Impact Profile
- Citations
- CrossRef - Citation Indexes: 2
- Scopus - Citation Indexes: 2
- Captures
- Mendeley - Readers: 2
Publication details
References11
Wodecki, J., Michalak, A., & Stefaniak, P. (2018). Review of smoothing methods for enhancement of noisy data from heavy-duty LHD mining machines. In E3S Web of Conferences (Vol. 29, p. 00011). EDP Sciences.
Koperska, W., Skoczylas, A., & Stefaniak, P. (2020). A sample method of haulage cycles detection of for LHD machine.
Mulloy, P. (1994). Smoothing Data with Faster Moving Averages by Patrick G. Mulloy. Technical Analysis of Stocks & Commodities magazine, 12(1), 37-70.
Letchford, A., Gao, J., & Zheng, L. (2012, June). Optimizing the moving average. In The 2012 International Joint Conference on Neural Networks (IJCNN) (pp. 1-8). IEEE.
Cleveland, W. S. (1979). Robust locally weighted regression and smoothing scatterplots. Journal of the American statistical association, 74(368), 829-836.
Cleveland, W. S., & Devlin, S. J. (1988). Locally weighted regression: an approach to regression analysis by local fitting. Journal of the American statistical association, 83(403), 596-610.
Hirschman, I. I., & Widder, D. V. (2012). The convolution transform. Courier Corporation.
Bracewell, R. N., & Bracewell, R. N. (1986). The Fourier transform and its applications (Vol. 31999). New York: McGraw-Hill.
Pawel, Stefaniak et. al "Development of test rig for robotization of mining technological processes–oversized rock breaking process case." In IOP Conference Series: Earth and Environmental Science, vol. 95, no. 4, p. 042028. IOP Publishing, 2017.
Welch, G., & Bishop, G. (1995). An introduction to the Kalman filter.
K?dzierski, J., & KoNaR, K. N. R. (2007). Filtr Kalmana-zastosowania w prostych uk?adach sensorycznych. Artyku? ko?a naukowego KoNaR Politechnika Wroc?awska.
Citing literature
Number of times cited according to Crossref: 2
View or Download full articleAccess options
SWS access login
Login as SWS Scientific CommitteeLogin as SWS Scientific PartnerLogin as SWS AuthorAuthors and approved SWS contributors will read and export their own linked papers after identity matching by SWS profile, email and SGEM GlobalID.
For librarian assistance: [email protected]
Purchase Instant Access
- Article can be downloaded after successful payment.
- Article may be used according to SWS library access terms.
- Article cannot be redistributed.