Search

In this study, a deep learning-based system for apple defect detection and quality grading was developed, integrating various advanced image-processing technologies and machine learning algorithms to enhance the automation and accuracy of apple quality monitoring. Experimental validation demonstrated the superior performance of the proposed model in handling complex image tasks. In the defect-segmentation experiments, the method achieved a precision of 93%, a recall of 90%, an accuracy of 91% and a mean Intersection over Union (mIoU) of 92%, significantly surpassing traditional deep learning models such as U-Net, SegNet, PSPNet, UNet++, DeepLabv3+ and HRNet. Similarly, in the quality-grading experiments, the method exhibited high efficiency with a precision of 91%, and both recall and accuracy reaching 90%. Additionally, ablation experiments with different loss functions confirmed the significant advantages of the Jump Loss in enhancing model performance, particularly in addressing class imbalance and improving feature learning. These results not only validate the effectiveness and reliability of the system in practical applications but also highlight its potential in automating the detection and grading processes in the apple industry. This integration of advanced technologies provides a new automated solution for quality control of agricultural products like apples, facilitating the modernization of agricultural production. [ABSTRACT FROM AUTHOR]

A novel deep learning model, DiffuCNN, is introduced in this paper, specifically designed for counting tobacco lesions in complex agricultural settings. By integrating advanced image processing techniques with deep learning methodologies, the model significantly enhances the accuracy of detecting tobacco lesions under low-resolution conditions. After detecting lesions, the grading of the disease severity is achieved through counting. The key features of DiffuCNN include a resolution enhancement module based on diffusion, an object detection network optimized through filter pruning, and the employment of the CentralSGD optimization algorithm. Experimental results demonstrate that DiffuCNN surpasses other models in precision, with respective values of 0.98 on precision, 0.96 on recall, 0.97 on accuracy, and 62 FPS. Particularly in counting tobacco lesions, DiffuCNN exhibits an exceptional performance, attributable to its efficient network architecture and advanced image processing techniques. The resolution enhancement module based on diffusion amplifies minute details and features in images, enabling the model to more effectively recognize and count tobacco lesions. Concurrently, filter pruning technology reduces the model's parameter count and computational burden, enhancing the processing speed while retaining the capability to recognize key features. The application of the CentralSGD optimization algorithm further improves the model's training efficiency and final performance. Moreover, an ablation study meticulously analyzes the contribution of each component within DiffuCNN. The results reveal that each component plays a crucial role in enhancing the model performance. The inclusion of the diffusion module significantly boosts the model's precision and recall, highlighting the importance of optimizing at the model's input end. The use of filter pruning and the CentralSGD optimization algorithm effectively elevates the model's computational efficiency and detection accuracy. [ABSTRACT FROM AUTHOR]

The Zhen'an-Xunyang Basin is a late Paleozoic rifted basin with a series of Au-Hg-Sb deposits that have been found, mostly along the Nanyangshan fault. Recently discovered large- and medium-sized gold deposits such as the Xiaohe and Wangzhuang deposits exhibit typical characteristics of Carlin-type gold deposits. Therefore, it is imperative to select a typical deposit for an in-depth study of its metallogenic mechanism to support future prospecting efforts targeting the Carlin-type gold deposits within the area. Based on detailed field investigation and microphotographic observation, four ore-forming stages are identified: I, low-sulfide quartz stage, characterized by euhedral, subhedral pyrite, and fine veins of quartz injected parallel to the strata; II, arsenopyrite–arsenian pyrite–quartz stage, the main mineralization stage characterized by strongly silicified zones of reticulated quartz, disseminated arsenopyrite, fine-grained pyrite; III, low-sulfide quartz stage, characterized by large quartz veins cutting through the ore body or fine veins of quartz; Ⅳ, carbonate–quartz stage, characterized by the appearance of a large number of calcite veins. In situ analysis of trace elements and S isotopes of typical metal sulfides was carried out. The results show significant variations in the trace element compositions of metal sulfides in different stages, among which the main mineralization stage differs notably from those of the Au- and As-low surrounding strata. In situ S isotope analysis reveals δ34S values ranging from 15.78‰ to 28.71‰ for stage I metal sulfides, 5.52‰ to 11.22‰ for stage II, and 0.3‰ to 5.25‰ for stage III, respectively, revealing a gradual decrease in S isotopic values from the pre-mineralization stage to post-mineralization stage, similar to those observed in the Xiaohe gold deposit. These features indicate a distinct injection of relatively low 34S hydrothermal fluids during the mineralization process. The element anomalies of the 1:50,000 stream sediment in the region revealed ore-forming element zonation changing in W→Au (W)→Hg, Sb (Au) anomalies from west to east, manifested by the discovery of tungsten, gold, and mercury–antimony deposits in the area. Moreover, conspicuous Cr-Ni-Ti-Co-Mo anomalies were observed on the western side of the Wangzhuang and Xiaohe gold deposits, indicating a potential concealed pluton related to these deposits. These lines of evidence point to a magmatic–hydrothermal origin for the Carlin-type gold deposits in this area. Furthermore, hydrothermal tungsten deposits, Carlin-type gold deposits, and low-temperature hydrothermal mercury–antimony deposits in this region are probably controlled by the same magma–hydrothermal system. [ABSTRACT FROM AUTHOR]

The effect of graphite powder on the machining characteristics in graphite-powder-mixed electrochemical discharge machining of microholes was still not clear. How the discharge mechanism changed with the addition of graphite powder into the electrolyte, which further led to changes in the morphology of the machined holes, remained to be revealed. In this study, a series of microhole machining experiments were conducted in glass. Comparisons of the discharge energy, microhole entrance diameter, hole taper, and tool electrode morphology after machining were made when machining in the electrolytes with and without graphite powder. Experimental results revealed that there were a lot of small pulse currents distributed on the current waveform when machining with the graphite-powder-mixed electrolyte. The average discharge energy of the small pulse current was 2.8 times as much as that of the general electrochemical discharge. After introducing graphite powder into the electrolyte, the entrance diameter of the hole became larger when the hole depth was deeper than 200 μm. The HAZ width increased with increasing hole depth at the voltage of 37–41 V, while it decreased at the voltage of 43 V. A reduction in hole taper angle with a range of 0.5° to 2.3° was achieved. In addition, after machining in electrolytes with and without graphite powder, the tool electrode surfaces showed different morphologies due to different discharges. [ABSTRACT FROM AUTHOR]

Electrochemical discharge machining (ECDM) is a promising non−traditional processing technology used to machine non−conductive materials, such as glass and ceramic, based on the evoked electrochemical discharge phenomena around the tool electrode. The discharge in ECDM is a key factor that affects the removal of material. Moreover, the discharge current is an important indicator reflecting the discharge state. However, the discharge characteristics remain an open topic for debate and require further investigation. There is still confusion regarding the distinction of the discharge current from the electrochemical reaction current in ECDM. In this study, high−speed imaging technology was applied to the investigation of the discharge characteristics. By comparing the captured discharge images with the corresponding discharge current, the discharge can be classified into three types. The observations of the discharge effect on the gas film indicate that a force was exerted on the gas film during the discharge process and the shape of the gas film was changed by the force. In addition, the energies released by different types of discharge were calculated according to the voltage and current waveforms. The discharge frequency was found to increase with the increase in applied voltage and the frequency of the second type of discharge was approximately equal to that of the third type when the applied voltage was higher than 40 V. [ABSTRACT FROM AUTHOR]

Low-grade vanadiferous titanomagnetite ore (LVTM) is as an important mineral resource for sintering ore manufacturing. Furthermore, TiO2 has a significant effect on the sintering process of iron ore fines. The effects of TiO2 on the metallurgical properties, microstructure, and mineral composition of LVTM sinter were investigated by sintering pot tests, X-ray diffraction (XRD), scanning electron microscopy (SEM), and mineral phase microanalysis. The results were as follows: as the TiO2 content increased from 1.75% to 4.55%, the flame front speed and productivity decreased, while the reduction degradation index (RDI) and softening properties deteriorated. In addition, the tumbler index (TI) values reached a maximum at TiO2 = 1.75%. In addition, with increasing TiO2 content, an increase in the magnetite and perovskite phase, and a decrease in calcium ferrite and hematite were found with an increase in TiO2 content. Thus, the lower the TiO2 content, the better the quality of the sinter. [ABSTRACT FROM AUTHOR]

Basicity has an important effect on the behavior of high-chromium vanadium-titanium magnetite (HCVTM) sinter. The effect of basicity on sintering, reduction, and softening-melting properties was investigated in an experiment-scale sinter pot. The results showed that with the basicity increasing from 1.7 to 2.5, the vertical sinter speed, the productivity, the particle size, the reduction disintegration index (RDI), and the reducibility index (RI) increased. The yield increased first and then decreased, while the tumble index (TI) had the opposite trend. The perovskite content increased first and then stabilized, and the silico-ferrite of calcium and aluminum (SFCA) increased from the basicity of 2.3. The HCVTM sinter had a better tendency of the softening behavior with the basicity increase. In addition, the melt droplet comprehensive index S increased, which indicated that the increase in basicity negatively affected the droplet performance. As the basicity increased, the comprehensive index value increased. Considering the adverse effect of basicity on softening-melting properties, the best recommended value is 2.3. [ABSTRACT FROM AUTHOR]

High-chromium vanadium-titanium magnetite (HCVTM) in the Hongge region has been used as an essential mineral resource in ironmaking. The effects of MgO on sintering performance and metallurgical properties were investigated by sintering pot tests, X-ray diffraction (XRD), and scanning electron microscopy-energy dispersive spectroscopy (SEM-EDS). HCVTM sinters with varying MgO contents (2.7–3.5%), which was achieved by adding dolomite, were tested for yield, strength, reduction degradation index (RDI), reduction index (RI), and softening-melting properties. The productivity and the comprehensive index were evaluated. The results show that yield and productivity increased, while the vertical sintering speed and the tumbler index (TI) initially increased then decreased with the increase of MgO content. The mineral structure of HCVTM sinter changed from a non-uniform state to a uniform state with increased MgO content. Most of the Mg2+ entered the magnetite lattice, while a small amount entered the perovskite and the calcium silicate. The increase of MgO content improved RDI and softening-melting properties while reducing RI. The best recommended amount of MgO was 3.3% from the comprehensive index. [ABSTRACT FROM AUTHOR]

This study discusses the oxidation induration and swelling behavior of chromium-bearing vanadium titanomagnetite pellets (CVTP) with Co2O3 additions. The reduction swelling index (RSI) and compressive strength of reduced CVTP (CSRC) were investigated with simulated coke oven gas (COG). The results show that the compressive strength (CS) of CVTP decreases from 2448 to 1983 N and the porosity of CVTP increases from 14.86 to 22.49% with increasing Co2O3 additions. The Co2O3 mainly exists in the form of CoFe2O4 in both of CVTP and reduced CVTP, and the CoFe2O4 is hard to be reduced by thermodynamic calculation. The Co-bearing phase mainly distributes on gap edges and among adjacent hematite grains. Many cracks and pores distribute along the grain boundaries and damage the connection of hematite grains. The CSRC decreases from 901 to 376 N, and RSI of reduced CVTP increases from 5.87 to 9.05% with increasing Co2O3 additions. The Co2O3 addition facilitates the aggregation and diffusion of metallic iron particles, and the aggregations of metallic iron thicken the lamellar crystals. The pores and interval of grains enlarge with increasing Co2O3 additions. This study can supply the theoretical and technical basis for the utilization of CVTP and waste residue-bearing cobalt with COG recyclable technology. [ABSTRACT FROM AUTHOR]

The sintering pot test was used to investigate the effect of TiO2 on the sintering behavior of chromium-bearing vanadium–titanium magnetite (CVTM) sinter. The main characterization methods of X-ray fluorescence (XRF), X-ray diffraction (XRD), scanning electron microscopy-energy disperse spectroscopy (SEM-EDS), and metallographic microscopy were employed. In this study, yield, tumbler index (TI), vertical sintering speed, productivity, reduction degradation index (RDI), and reduction index (RI) were tested and calculated. The yield first increases from 82.87% to 84.37% and then decreases to 83.65%, vertical sintering speed first increases from 17.00 mm·min−1 to 23.45 mm·min−1 and then decreases to 20.61 mm·min−1, and productivity first increases from 2.33 t·m−2·h−1 to 3.14 t·m−2·h−1 and then decreases to 2.69 t·m−2·h−1 with increasing TiO2 content. The TI increases from 45.81% to 52.09%, and RDI increases from 74.99% to 96.74%, while RI decreases from 67.92% to 47.15% with increasing TiO2 content. [ABSTRACT FROM AUTHOR]