Return to search

Optimization of operation strategy for primary torque based hydrostatics drivetrain using artificial intelligence

A new primary torque control concept for hydrostatics mobile machines was introduced in 2018 [1]. The mentioned concept controls the pressure in a closed circuit by changing the angle of the hydraulic pump to achieve the desired pressure based on a feedback system. Thanks to this concept, a series of advantages are expected [2]. However, while working in a Y cycle, the primary torque controlled wheel loader has worse performance in efficiency compared to secondary controlled earthmover due to lack of recuperation ability. Alternatively, we use deep learning algorithms to improve machines’ regeneration performance. In this paper, we firstly make a potential analysis to show the benefit by utilizing the regeneration process, followed by proposing a series of CRDNNs, which combine CNN, RNN, and DNN, to precisely detect Y cycles. Compared to existing algorithms, the CRDNN with bidirectional LSTMs has the best accuracy, and the CRDNN with LSTMs has a comparable performance but much fewer training parameters. Based on our dataset including 119 truck loading cycles, our best neural network shows a 98.2 % test accuracy. Therefore, even with a simple regeneration process, our algorithm can improve the holistic efficiency of mobile machines up to 9% during Y cycle processes if primary torque concept is used.

Identiferoai:union.ndltd.org:DRESDEN/oai:qucosa:de:qucosa:71073
Date23 June 2020
CreatorsXiang, Yusheng, Geimer, Marcus
ContributorsDresdner Verein zur Förderung der Fluidtechnik e. V. Dresden
PublisherTechnische Universität Dresden
Source SetsHochschulschriftenserver (HSSS) der SLUB Dresden
LanguageEnglish
Detected LanguageEnglish
Typeinfo:eu-repo/semantics/publishedVersion, doc-type:conferenceObject, info:eu-repo/semantics/conferenceObject, doc-type:Text
Rightsinfo:eu-repo/semantics/openAccess
Relation10.25368/2020.6, urn:nbn:de:bsz:14-qucosa2-709160, qucosa:70916

Page generated in 0.002 seconds