Development and evaluation of a weighing system for forestry cranes based on artificial neural networks
DOI:
https://doi.org/10.15150/lt.2019.3213Abstract
In both log and chip logistics, important reference data for logistic purposes are often lacking, as they are usually completed with insufficiently accurate estimates. In order to obtain higher quality information on the moving timber quantities, optional crane scales can be mounted between the telescope and the grapple of the forwarder. However, this has a negative effect on the crane kinematics and manoeuvrability while at the same time machine productivity is reduced due to an interruption in the loading process necessary for measurement.
In this paper, a data-based method is presented which allows dynamic weighing in a continuous loading process for modern forestry cranes without the need to install an additional hardware component on the machine. This allows a cost-effective and comprehensive application. In the course of this method, a loading cycle is automatically detected, and the loaded mass is estimated by means of an artificial neural network (ANN). Signals from sensors installed as standard on modern forwarders serve as input variables. The Long Short-Term Memory (LSTM) architecture for the neural network has proven itself for handling these time-based sensor data. Based on LSTM cells, an appropriate network was designed, trained and subsequently optimized. The test shows an average full-scale error of 1.5% per 1,000 kg for a single loading cycle. For a fully loaded forwarder, this results in a total mass error of less than 1.2%.
References
Bennett, N.; Walawalkar, A.; Schindler, C. (2014): Payload Estimation in Excavators: Model-Based Evaluation of Current Payload Estimation System. In: Proceedings of the 3rd Commercial Vehicle Technology Symposium (CVT2014)
Berg, S.; Fischbach, J.; Brüchert, F.; Poissonnet, M.; Pizzirani, S.; Varet, A.; Sauter, U.H. (2012): Towards assessing the sustainability of European logging operations. European Journal of Forest Research 131(1), S. 81–94, https://doi.org/10.1007/s10342-011-0561-x
Bodelschwingh, E. v. (2006): Analyse der Rundholzlogistik in der Deutschen Forst- und Holzwirtschaft – Ansätze für ein übergreifendes Supply Chain Management. Dissertation, TU München
Cacot, E.; Bigot, M.; Cuchet, E. (2006): Developing full-mechanized harvesting systems for broadleaved trees: a challenge to face the reduction of the manual workforce and to sustain the supply of hardwood industries. In: 2006 Council on Forest Engineering (COFE) Conference Proceedings: “Working Globally – Sharing Forest Engineering Challenges and Technologies Aroun
Deutscher Forstwirtschaftsrat e. V. und Deutscher Holzwirtschaftsrat e. V. (2015): Rahmenvereinbarung für den Rohholzhandel in Deutschland (RVR)
Erler, J.; Purfürst, T.; Dög, M. (2010): Präzise Forstwirtschaft. Reihe Technikmanagement in der Forstwirtschaft, Tharandt, Fachinstitut für Waldarbeit
Fodor, S. (2017): Towards semi-automation of forestry cranes. Automated trajectory planning and active vibration damping. Dissertation, Department of applied physics and electronics, Umeå University
Frederic, B. (2015): Dynamic, Continuous, and Center of Gravity Independent Weighing with a Loader. Dissertation, Technischen Universität Kaiserslautern
Ge, R.; Huang, F.; Jin, C.; Yuan, Y. (2015): Escaping From Saddle Points -- Online Stochastic Gradient for Tensor Decomposition. In: JMLR: Workshop and Conference Proceedings, Conference on Learning Theory, 3–6 July 2015, Paris, France vol 40, pp. 797–842
Geiger, C.; Geimer, M. (2017): Efficiency Optimisation of a Forestry Crane by Implement Hydraulics with Energy Recovery. In: VDI-MEG – 75th International Conference on Agricultural Engineering, LAND.TECHNIK AgEng 2017 - The Forum for Agricultural Engineering Innovations, Hannover, 10–11 November 2017, pp. 117–125
Geiger, C.; Starke, M.; Greff, D.; Geimer, M. (2018): The potential of a weight detection system for forwarders using an artificial neural network. In: FORMEC 2018 – Improved Forest Mechanisation: mobilizing natural resources and preventing wildfires, Proceedings
Goodfellow, I.; Bengio, Y.; Courville, A. (2016): Deep Learning. Cambridge, USA, MIT Press
Graves, A. (2012): Supervised Sequence Labelling with Recurrent Neural Networks. Springer Verlag
Heinimann, H.R. (1994): Beiträge zur forstlichen Verfahrenstechnik. Tagungsbericht über das 28. Internationale Symposium „Mechanisierung der Waldarbeit“ vom 28.08.–02.09.1994 in Langnau i.E., Schweiz, Zürich, Verl. der Fachvereine an den schweizer. Hochschulen u. Techniken
Hinton, G.E.; Srivastava, N.; Krizhevsky, A.; Sutskever, I.; Salakhutdinov, R.R. (2012): Improving neural networks by preventing co-adaptation of feature detectors. https://arxiv.org/pdf/1207.0580.pdf, accessed on 19 Sept 2019
Hochreiter, S.; Schmidhuber, J. (1997): Long Short-Term Memory. Neural Computation 9(8), pp. 1735–1780, https://doi.org/10.1162/neco.1997.9.8.1735
Hohenloher Spezial-Maschinenbau GmbH & Co. KG. (2014): DE 202014006861, Hohenlohe, F.
Komatsu (2019): Options Forwarders. https://www.komatsuforest.com/forest-machines/our-forwarders/forwarder-options, accessed on 13 Apr 2019
Korten, S.; Kaul, C. (2012): Optimierung der Transportprozesse bei Holzernte und Rundholztransport durch den Einsatz von Wechselbrücken. Schlussbericht, Lehrstuhl für Forstliche Arbeitswissenschaft und Angewandte Informatik der TU München
Kuptz, D.; Turowski, P.; Hartmann, H.; Schulmeyer, F. (2015): Optimale Bereitstellungsverfahren für Holzhackschnitzel. Berichte aus dem TFZ, Technologie- und Förderzentrum (TFZ) im Kompetenzzentrum für Nachwachsende Rohstoffe
Manner, J.; Palmroth, L.; Nordfjell, T.; Lindroos, O. (2016): Load level forwarding work element analysis based on automatic follow-up data. Silva Fennica 50(3), https://doi.org/10.14214/sf.1546
Masters, D.; Luschi, C. (2018): Revisiting Small Batch Training for Deep Neural Networks. CoRR, https://arxiv.org/pdf/1804.07612.pdf, accessed on 19 Sept 2019
Morales, D.O.; La Hera, P.; Westerberg, S.; Freidovich, L.B.; Shiriaev, A.S. (2015): Path-Constrained Motion Analysis: An Algorithm to Understand Human Performance on Hydraulic Manipulators. IEEE Transactions on Human-Machine Systems 45(2), pp. 187–199, https://doi.org/10.1109/THMS.2014.2366873
Nurminen, T.; Korpunen, H.; Uusitalo, J. (2006): Time consumption analysis of the mechanized cut-to-length harvesting system. Silva Fennica 40(2), https://doi.org/10.14214/sf.346
Perrone, M.P.; Cooper, L.N. (1995): When networks disagree: Ensemble methods for hybrid neural networks. In: How We Learn; How We Remember: Toward an Understanding of Brain and Neural Systems – Selected Papers of Leon N Cooper. World Scientific Series in 20th Century Physics: Volume 10, pp. 342–358, https://doi.org/10.1142/9789812795885_0025
Ponsse (2010): Ponsse attachments add value to your machine. http://www.toimilgruas.com/pdf/Attachment_ENGL.pdf , accessed on 13 Apr 2019
Savia, M.; Koivo, H. (2002): On-line payload determination of a moving loader using neural networks. IFAC Proceedings Volumes 35(1), pp. 37–42, https://doi.org/10.3182/20020721-6-ES-1901.01157
Walawalkar, A; Heep, S.; Schneider, F.; Schüßler, J.; Schindler, C. (2016): A method for payload estimation in excavators. In: Proceedings of the 4th Commercial Vehicle Symposium (CVT 2016), 8–10 March 2016, University of Kaiserslautern, Germany, pp. 424–437
Walawalkar, A.; Heep, S.; Schindler, C.; Leifeld, R.; Frank, M. (2018): Validation of an analytical method for payload estimation in excavators. In: Commercial Vehicle Technology 2018, Eds. Berns K. et al., Proceedings, Springer Vieweg, Wiesbaden, pp. 3–16
Wide, M.I. (2012): Väg rätt redan i skogen. Skogforsk, https://www.skogforsk.se/cd_48e558/contentassets/d161ed005cd04d9dbcbb3302102a39ae/nr15_jh_4s_high.pdf, accessed on 19 Sept 2019
Yung, I. (2017): Automation of Front-End Loaders. Electronic Self Leveling and Payload Estimation. Dissertation, Umeå University
