Accurately positioning and identifying coal gangue under the heterogeneous complex scenarios of production is a key difficult problem for sorting robot. This paper proposes an image processing based method further develops identification system. The samples are selected from Hancheng Coal Mine, China's Shaanxi province. Three automatic threshold segmentation methods used binarization comparative analysis shows that clustering outperforms others. Particle carried out by using morphological...

As for image-based recognition of coal and gangue, the image features are susceptible to environment, which makes gangue difficult recognize locate. We build a simulation experiment platform construct an dataset covering scenarios different illuminance, moisture, belt speed. Moreover, in combination YOLOv4 target detection algorithm mixed domain attention mechanism, we develop model trained using our dataset. The accuracy coal, combined 98.2%, 99.0%, 97.3%, respectively, time was 32 ms. then...

Image-based separation of coal and gangue is susceptible to the external environment. This paper studies effects illuminance moisture on grayscale texture features images. We first build an image acquisition system construct dataset coals gangues under different moisture. Secondly, we extract four parameters including gray value corresponding maximum frequency, average, variance, skewness entropy, contrast, energy, correlation these Thirdly, compare by normalizing values gangue. The result...

Picking gangue from raw coal is a crucial step of production. Due to the potential for replacing manual workers, study pick-up robot attracting much interest. Pick-up robots usually work in fixed working areas where types coals and gangues are unitary. Based on this fact, paper proposes simple, fast, easily implemented approach classification which LS-SVM (Least Square Support Vector Machine) based using gray scale texture as features. We firstly sampled image dataset Han City, Shaanxi...

ABSTRACTTo reveal the effects of illuminance and spectral band changes on coal gangue image parameters, to provide fundamental data for using multispectral images in recognition research, this paper analyzes parameters (standard deviation, skewness, entropy, contrast) parameter experimental methods, compares differences between values. First, we analyze variations find that as increases, fluctuate shorter bands but change slightly longer ones, while increases across all bands; wavelength...

To guarantee the secure and steady performance of an optical storage microgrid, implementation sophisticated control techniques dependable communication networks is imperative. The voltage stability at Point Common Coupling (PCC) becomes increasingly critical factor. As power system embraces a wider range distributed supply modes, remaining capacity grid reallocated, as well input shutdown loads in can cause fluctuations microgrid. Traditional microgrid PCC methods cannot fully solve...

In this research, we developed a saturation compensator based disturbance observer control structure for piezo driven nanopositioning systems. By regarding the effects of hysteresis nonlinearities, model uncertainties, motion coupling and external disturbances as lumped added to channel, is established system purpose compensating disturbance, such that improved performance obtained unsaturated system. On top specific observer, robust employed deal with unexpected actuator saturations. basis...

Accurate temperature measurement is very important in industrial production and household electric control temperature. In practical applications, it crucial to precisely know the of target object be measured, Bat not convenient directly measure a certain part. This kind often predicted by measuring surrounding part measured condacting experimental modeling. However, existing linear or nonlinear models have difficulties such as big error poor robustness. order address aforementioned issues,...