Banana fruits are typically harvested and transported while still green and hard, referred to as green bananas. However, frequent collisions often occur between fruit fingers, working parts, and adjacent fruit fingers during this stage. This study aims to investigate the mechanical properties of fruit fingers at different growth positions. The experimental material was selected as the finger of the banana plant (Musa spp.) on a supporting platform created by 3D printing technology. A complete factorial experiment was performed using a pendulum method. The test conditions included three impact energies (0.27, 0.52, and 0.88 J) and three repeated times (1, 5, and 10) across three growth positions (the inner rows of the first and second nodes, the outer rows of the first and second nodes, and the inner and outer rows of the last nodes) within a green banana bunch. Mechanical parameters were calculated, such as peak acceleration, coefficient of restitution (CoR), bruise area (BA), bruise volume (BV), and bruise susceptibility (BS). Among them, the BS represented the ratio of BV to the total absorbed impact energy. A multi-way analysis of variance was also conducted at a significance level of 5% to determine the statistical significance of the mean values of the parameters. The results demonstrated that there was a strong positive correlation between peak acceleration and bruise sizes, and a strong negative correlation between the CoR and BS. Specifically, the higher peak acceleration resulted in the more severe damage to the fruit fingers, whereas the smaller CoR made the green bananas more susceptible to damage. Moreover, the impact energy, repeated times, their interaction, and the location of banana growth significantly dominated the mechanical parameters of the BA, BV, and BS. The higher impact energy led to the greater peak acceleration, BA, BV, and BS, whereas, the lower CoR was observed. Consequently, the higher impact energy tended to increase the susceptibility of banana fruit to damage. Once the impact energy was below the threshold for the plastic deformation of green bananas, the peak acceleration and CoR were improved non-linearly with each impact up to the first five impacts, after which the increment decreased progressively for each subsequent impact. Similar trends were observed for the BA and BV, while the opposite was true for the BS. Therefore, the susceptibility of banana fruit decreased with the increasing impacts. It is challenging for the reduced number of impacts to less than five during production. Fruit damage can be minimized to reduce the energy required to hit the banana fingers. Once the impact energy exceeded the threshold, an initial increase in the peak acceleration and CoR was followed by a decrease, due to the plastic deformation and ductile fracture of the banana finger from continued impacts. Both BV and the rate of increase were enhanced with the number of repetitions. Furthermore, the BS of banana fingers in the outer row was generally smaller than that in the inner row, indicating that the inner row was more susceptible to impact-induced bruise damage. These findings can provide a strong reference to managing the protective measures and risk factors during banana harvesting and transportation.

China is the largest fruit producer and consumer in the world, while most orchards in the south of China are located in hilly areas. The ropeways can be expected for transporting orchards in mountainous areas. But the harsh working environment can often lead to machine failures in recent years. Therefore, it is of great significance to investigate and solve the problems at the initial stage of failures. Generally, the conventional bearing fault diagnosis system includes five links: signal acquisition, feature extraction, state identification, diagnosis analysis. and decision intervention. Deep learning is widely applied for bearing fault detection in recent years. Traditional machine learning also needs to manually extract the fault features at present, depending mainly on the deep professional knowledge. However, it is high demand for the high performance of fault diagnosis, particularly for simple structures and less calculation during feature extraction. This study aims to realize the fault diagnosis of ropeway drive system bearings in the mountain orchards with poor network environment, in order to ensure the safe and stable operation of ropeway in the mountain orchards. A one-dimensional end-to-end lightweight CNN detection, 1D-MRL-CNN was established to directly detect the one-dimensional vibration signals for the mountain ropeways. Specifically, the new model was established using residual structure and depth separable convolution. The depth separable convolution was applied to greatly reduce the parameter and calculation amount of the improved model. In addition, the residual structure was applied to make up for the accuracy loss caused by depth separable convolution. The parameter amount and complexity of the model were reduced significantly while ensuring the detection accuracy. The stem block and BN layer were then introduced to improve the robustness and generalization ability of the new model suitable for the variable load working state of the ropeway. Finally, the hard_swish activation function was also adopted in the model. The channel attention mechanism was added to the last layer of the main module, in order to improve the feature extraction ability of the network model. Two datasets (Paderborn University and Case Western Reserve University) were used to verify the comprehensive performance, stability under variable load and anti-noise interference performance. The Paderborn University dataset showed that the fault classification accuracy of the improved model was 99.43%, which was 0.56, 0.99, and 1.23 percentage points higher than those of the one-dimensional classical CNN, similar optimal network, and the lightweight CNN architecture optimal network. The parameters and floating-point calculations were 83.44 kb and 0.20 M, which were 2.19%, 1.18%, 0.75%, and 0.83% of the one-dimensional classical CNN classification network architectures (such as Resnet18, Resnet34, Resnet50 and VGG16), 6.19% and 30.40% of the same type of networks 1D-Lenet5 and 1D-Inception, while 4.2%, 2.07%, 2.84%, 3.32% and 5.16% of the one-dimensional lightweight CNN architecture MobileNetV1, MobileNetV2, MobileNetV3-Large, ShuffleNetV1 and EfficientNet-1. In addition, the Case Western Reserve University dataset showed that the average accuracy rate of the improved model was 96.70% in six load scenarios, which was 9.1, 4.7, and 10.5 percentage points higher than those of Resnet18, WDCNN, and MobileNetV3-Large, respectively. The average recognition accuracy was 99.14% under four noise conditions, which was 4.74, 1.24, and 5.51 percentage points higher than those of Resnet18, WDCNN and MobileNetV3-Large, respectively. Finally, the fault classification of the improved model under actual working conditions was verified by the established ropeway dataset, where only 2 fault samples out of 1 400 samples were predicted incorrectly. The new network model was suitable for the bearing fault detection of mountain orchard transport ropeway, due to the small parameters, high accuracy and robustness under variable load and noisy working conditions.

Conventional estimation of banana hands and fingers has often been confined to the complex, interlocked structures and frequent occlusions impeding. This research aims to develop a non-destructive, accurate, and rapid estimation of the mass of the entire banana hands and individual fingers. Imaging and computational techniques were also selected as an alternative to the manual or inadequate automated approaches. The more efficient post-harvest processing and grading were facilitated in the banana industry. Firstly, the morphology and geometry were acquired to predict the mass. The registered color and depth (RGB-D) images of the banana hands were captured from the convex and concave viewpoints using a controlled laboratory setup. Secondly, the individual fingers were then precisely segmented using the Segment Anything Model (SAM), a zero-shot instance segmentation. The occlusions were also managed without requiring the task-specific training datasets. The depth information was acquired to convert into the three-dimensional (3D) point clouds. The computational efficiency was then optimized using voxel grid down-sampling. The statistical outlier was also removed for the data integrity. Thirdly, the comprehensive features were extracted from the color images, including the two-dimensional (2D) morphology and size descriptors (such as pixel area, contour perimeter, and aspect ratio). The 3D geometric properties (including principal dimensions, surface area, and convex hull volume) were obtained from the processed point clouds. These multi-modal features were generated for the whole banana hands and each segmented finger. Finally, the mass prediction models were developed with a multiple linear regression (MLR) model as a baseline. Five non-linear machine learning algorithms were also used, including support vector regression (SVR), k-nearest neighbors (KNN), gradient boosting (GB), random forest (RF), and backpropagation neural network (BPNN). Model performance was assessed using R², RMSE (root mean squared error), and MAPE (mean absolute percentage error). Furthermore, the importance analysis was carried out to eliminate the recursive features, thus focusing primarily on the RF model. The influential predictors were then identified to construct and optimize the models. The comparative analysis showed that the RF model outperformed the rest. The non-linear approaches were then required to capture the relationships between extracted features and banana mass. In the mass estimation of the whole banana hand, the concave view was achieved in better performances (R² = 0.984, RMSE = 77.78 g, and MAPE=5.37%) with the RF model after optimization. The 3D features, particularly surface area and convex hull volume, were the most critical for the accurate prediction of the hand mass. In individual finger mass, the RF model was more accurate for the exposed outer fingers (viewed convexly; optimized RF: R² = 0.794, RMSE = 13.14 g, MAPE = 6.12%) than that for the occluded inner fingers (viewed concavely; optimized RF: R² = 0.668, RMSE = 17.47 g, MAPE = 9.07%). Interestingly, the 2D features (like pixel area and contour perimeter) dominated the mass prediction on the outer fingers. There was the differential feature importance of the finger position and visibility. Two strategies of mass estimation were also evaluated: An average finger mass was calculated (from the predicted total hand mass divided by actual finger count), and then directly predicted the individual finger mass. Both derived average finger mass (using the best hand model) and directly predicted outer finger mass was achieved with high accuracy (relative error <10% for ~80% of samples). The average mass method was better suited to assess the overall quality. While the direct prediction was offered the detailed data for accessible outer fingers. The computational efficiency showed that the direct estimation of the finger mass was faster (~7.7 s per hand), including the SAM segmentation step (~1 s), compared with the average mass estimation on the complex point cloud of the entire hand (~76.6 s per hand). The 3D features were calculated from the multiple simple point clouds which the less computationally demanding than those from single, large, and intricate ones. There was the "divide and conquer" benefit from the SAM-based segmentation. The RGB-D imaging and machine learning were integrated to validate the accurate, non-destructive mass determination of the banana hands and fingers. The utility of the SAM was obtained for the complex fruit segmentation in the agricultural contexts. The RF was the better modeling choice than the rest. Differential contributions of the 2D and 3D features were gained to quantify the varying viewpoint impacts. The direct estimation of the individual finger can offer detailed information and higher computational efficiency than before. The banana grading can also be developed to enhance post-harvest operations. While the 3D feature computation from the complex point clouds can be identified as the primary bottleneck in real-time industrial applications.

Banana fusarium wilt has a significant adverse effect on the banana industry. It is worth noting that fusarium oxysporum f.sp. cubense 4(Foc4) is one of the most devastating and widespread pathogens of banana fusarium wilt in the world. It is a catastrophic threat to the global banana industry. At present, there is still no technology that can cure bananas infected with banana fusarium wilt. Therefore, it is extremely important for banana planting industry to detect banana fusarium wilt in time and do a good job in prevention and control. In order to realize the early accurate detection of banana fusarium wilt race 4, this study proposed a detection method of double probe paper-based sensor based on colloidal gold, which increased the use of signal enhancement probes to increase the binding amount of colloidal gold, thereby reducing the detection limit. Two kinds of colloidal gold particles with different particle sizes were combined with the corresponding detection probes and signal enhancement probes to form a double gold label probe system. The large particle size colloidal gold was used with the detection probe, while the small particle size colloidal gold was paired with the signal enhancement probe. The sample being tested was mixed with this double gold-labeled probe system. The Foc4 target sequence in the sample would be paired with the double gold-labeled probe to form a ' gold-labeled probe-target sequence-T-line probe ' complex, which continued to migrate to the water-absorbing pad. The complex was captured on the test area of the sensor. Within 10 minutes, the test paper would generate a visible target product that could be observed by the naked eye at both the test line and the quality control line areas, thus achieving qualitative detection. For quantitative detection of Foc4, the light intensity of the test strip would be further analyzed using software. The light intensity peak area was obtained and substituted into the standard curve to obtain the concentration of Foc4 detected and realize quantitative detection. Experimental results demonstrate that the detection limit of the dual-probe paper-based sensor is 0.001 nmol/L, which is 100 times of that of the traditional paper-based sensor, and the detection sensitivity is improved. The sensitivity test results demonstrated a strong linear relationship between the concentration of Foc4 and the peak area of the test line light intensity within the concentration range of 0.001-1000.000 nmol/L. This finding suggests that the sensor can be effectively employed for quantitative detection. To assess specificity, a high concentration of non-complementary probe was utilized as the target sequence for detection and compared with the detection results of samples containing Foc4. The experiment revealed the absence of a red band at the test line when the test paper was detected by the non-complementary sequence. Importantly, this observation indicated that the presence of the non-complementary sequence had minimal impact on the detection effect, thus affirming the sensor's excellent specificity. Finally, the paper-based sensor was used to detect Foc4 in banana leaves. The average recovery rate was 77.6%-102.3%, and the relative standard deviation was 7.4%-7.7%, indicating that it can be used for on-site detection of Foc4. The detection technology possesses the characteristics of being low-cost and easy to operate. In comparison to traditional detection methods, it enables timely, rapid and accurately determination of the presence of Foc4. Compared with the existing molecular detection technology, the detection can be completed without the need of expensive equipment or specialized personnel. This feature makes it highly suitable for widespread use. The dual-probe paper-based sensor realizes the combination of nucleic acid lateral chromatography detection technology and banana fusarium wilt detection. Its potential for widespread adoption in the early disease warning system of the banana industry is substantial. Furthermore, this technology can be combined with traditional polymerase chain reaction (PCR) and other techniques to facilitate on-site detection of Foc4.

Lifting and transportation equipment can greatly contribute to the harvesting of mountain bananas in the agricultural industry. However, some challenges still remain during post-harvest transportation, such as high labor intensity and cost, easy damage to fruits, and safety accidents. In this study, an Unmanned aerial vehicle (UAV) autonomous lifting and transportation equipment was designed to harvest the mountain bananas. The autonomous grasping and unloading of banana shafts were realized during the lifting and transportation. Manual participation was effectively reduced to ensure the safety of operators. The grasping mechanism, lifting gear, guide mechanism, and connecting parts were designed, according to the measured morphological features of the mountain banana. The specific needs were fully met by the postharvest transportation of mountain bananas. A three-dimensional model of the equipment was established using SOLIDWORKS software. The communication system of the upper and lower machines was also built. The key components of lifting and transportation equipment were simulated and theoretically calculated, using the explicit dynamics and magnetostatic analysis of ANSYS Workbench software. The parameters of an electromagnet and steering gear were determined to meet the requirements. The simulation highlighted that the better performance of equipment was achieved for subsequent testing. A laboratory experiment was then carried out to validate the efficacy of the equipment. The success rates of lifting and transportation were 92.59%, 96%, and 88.89%, respectively. The average time of grasping and unloading was 63.8 and 20.8 s, respectively. The effectiveness of equipment was verified to transport the mountain bananas. Furthermore, the field experiment UAV was carried out on the lifting and transportation equipment. The success rate of lifting and transportation was 83.33%, the total time of grasping and unloading was 90.8 s, and the average speed of lifting and transportation was 0.99 m/s, which was more than three times that of manual carrying speed (0.17~ 0.33 m/s). Because the banana bunch was suspended under the equipment without contacting with other objects, there was no damage to the fruit finger, indicating the better quality of the fruits during transportation. Nevertheless, the equipment produced a large lateral swing on the positioning and grasping of the banana shaft, due mainly to the strong wind field under the UAV. Therefore, there were some differences between the field test and the indoor experiment, but the expected performance was achieved anyway. The structure can be further optimized to improve the success rate of lifting and transportation of the equipment for less operation time. In conclusion, the equipment can fully meet the operational requirements for the autonomous lifting and transportation of mountain bananas by UAV. Overall, these findings can provide a strong reference for efficient, low-loss, and safe unmanned lifting and transportation equipment. A reliable and efficient solution can be offered for autonomous lifting and transportation in the banana industry towards sustainable growth and productivity.