Search

In the field of precision agriculture, weed detection models combined with selective spraying by ground or aerial robotics are seen as promising approaches for increasing yield harvests while simultaneously minimizing herbicide use. The available labeled training data are a major bottleneck for developing and applying supervised deep learning models, and more automated methods for labeled data generation are therefore needed. Our research aims to address this need by introducing a rule-based method for label data generation for perennial weeds. For this research, a dataset of a barley field was collected using an unmanned aerial vehicle (UAV) with a flight altitude of 10 m. A multispectral and a thermal camera were used for the data collection. The preprocessed dataset consists of multispectral and thermal orthomosaic images along with a canopy height model. The methodological part of this article introduces a proposed rule-based method for labeled data generation for perennial weeds based on the Normalized Difference Vegetation Index (NDVI), and this approach is further used to generate labels for the measured data. The preprocessed data combined with the generated labels was used to train U-net models. Three data combinations are used for the training and testing: multispectral, multispectral–thermal and multispectral–thermal–canopy–height–model. This approach was used to evaluate whether additional data improve model performance. To evaluate the models on ground truth labels, they are tested on a manually annotated test dataset, which consists of 10% of the whole dataset. The tested models achieved an F1 score of 0.82–0.83 on the test dataset. This finding demonstrates that the rule-based labeling method generates valid labels for the perennial weed detection task. Furthermore, our study shows that data fusion improved the model slightly. The data combination of multispectral–thermal–canopy–height–model as input resulted in the best-performing model, with an F1 score of 0.835. [ABSTRACT FROM AUTHOR]

This paper presents a modal analysis of different drivetrain configurations in electric vehicles; 1) an in – wheel motor, 2) direct drive, and 3) an electric motor with a reduction gear and a differential gear. A specific simulation model was developed to analyze the vibrations while taking into account the traction motor, possible mechanical reduction gears, and the driveshaft, as well as a Rigid Ring Model (RRM) to describe the tire. On the basis of the simulation results, the frequency responses were calculated for each drivetrain configuration and also for a non-drive, free-rolling tire. The analyzed results show interesting differences between the different drivetrain configurations. However, most of the negative aspects can be compensated for if identified in the early design phase. For instance, the frequency response of the in-wheel motor configuration indicated that the vibrations that occur might cause negative effects in terms of driving comfort and wheel speed signal noise. The direct drive configuration has an additional mode at 24 Hz, and the differential configuration at 4 Hz. It is possible that these modes would resonate strongly if some drivetrain design parameters were poorly defined. [ABSTRACT FROM AUTHOR]

The objective of this paper is to evaluate technical requirements for electrochemical energy storage systems (ESSs) in hybrid mining loaders. These requirements take into account power and energy capacity, costs, life cycle, and safety-related requirements. The evaluation of the requirements is based on the characteristics of the current energy storage technology and vehicle simulation results. The evaluation shows that lithium-based batteries offer sufficient power and energy capacity; meanwhile, the requirements for cost and cycle life durability are dependent on the operating strategy and configuration of the loader. In particular, the power-intensive duty cycle of a mining loader can be challenging for batteries in terms of cycle life and thermal management. [ABSTRACT FROM PUBLISHER]