Waterless and low temperature transportation is a green and efficient way for the transportation of live fish. However, waterless and low temperature conditions could lead to a stress response in live fish, resulting in reduced transport survival rates. It is still a challenge to intelligently monitor the breath stress state of live fish under adversity stress. Temperature (T), relative humidity (RH), oxygen (O2) and carbon dioxide (CO2) signals can reflect changes in adversity stress environment; while the breath angle sensors can monitor the gill opening and closing angle (breath angle) to reflect changes in fish breath. In this work, microenvironment and breath angle sensor systems were designed and developed to comprehensively evaluate the breath stress state of fish. Meanwhile, the Kalman filter-quaternion-fast Fourier transform method was established to process the breath angle signal. The breath angle signal indicated that the sturgeon had three levels of breath stress: acute fluctuation stage (0–2.5h), organismal regulation stage (2.5–16h) and cumulative stress stage (>16h). In addition, linear regression (LR), back propagation neural network (BPNN), support vector regression (SVR), and radial basis function neural network (RBFNN) models were established for breath efficiency signal prediction. The R2 of the RBFNN (0.9544) model was significantly higher than the LR (0.8092), BPNN (0.9289), and SVR (0.9428) models. This study provided a reference for further intelligent monitoring and management of the fish breath stress state under waterless and low temperature conditions.
The detection of crop rows is crucial for achieving visual navigation and is one of the key technologies for enabling autonomous management of maize fields. However, the current mainstream approach to maize crop row detection often involves two steps - feature extraction followed by post-processing. While useful, this method is inefficient, and the heuristic rules designed by humans limit the scalability of these methods. To simplify the solution and enhance its generality, crop row detection is defined as a process of approximating curves. Polynomial parameter learning is adopted to constrain the parameters of crop row shapes, and utilise a model built on the Transformer architecture to learn the elongated structures and global context of crop rows, achieving end-to-end output of crop row shape parameters. The proposed approach has achieved rapid and excellent detection results in complex field environments, even in the presence of curved crop rows.
To suppress the influence of complex field path excitation on the seeding quality of a corn no-till planter, a method for optimising the parameters of connecting parts is proposed in this study. Firstly, a twelve degrees of freedom model of the whole tractor-planter is established, and the corresponding differential equations are solved for the vibration characteristics. Then the key parameters of vibration characteristics are determined by sensitivity analysis based on the Matlab/Simulink model. On this basis, the gray wolf optimisation algorithm is introduced to address the global optimal solutions of connecting part parameters. Finally, the effectiveness of the proposed method is verified through numerical simulations and field experiments. The simulation results indicate that compared with the results before the optimisation, the vibration accelerations of corn no-till planter in the vertical, roll and pitch directions are reduced by 15.8%, 14.3% and 16.4%, respectively. The field experiment results further verify the validity of the proposed method.
Microalgae reactors provide an efficient and clean alternative for the production of biofuels, nutritional and cosmetic bioproducts, wastewater treatment, and mitigation of industrial gases to reduce greenhouse gas emissions. The main control objective in these systems is productivity optimisation. For this reason, real-time monitoring of key biological performance indicators affecting microalgae production such as microalgae growth rate, biomass concentration, dissolved oxygen, pH level or total inorganic carbon is crucial. However, there are no sufficiently robust solutions on the market to estimate or measure all of these variables, especially for open reactors on an industrial scale. This paper presents a new online state estimator, based on a robust sliding mode observer combined with a nonlinear dynamic model endowed with a minimum number of states to capture dynamics of key biological performance indicators. This soft-sensor has been verified with a realistic reactor model that has been experimentally tested. Simulations showed promising results in terms of accuracy (with mean values of the state estimation errors in the order of 10−4 g m−3 for the biomass concentration, 10−5 to 10−13 mol m−3 for the other states and deviations in the order of 10−4 g m−3 for the biomass concentration, 10−5 to 10−10 mol m−3 for the other states) and robustness with respect to signal noise, state deviations, initial errors and parametric uncertainty.
Judicious assessment of ripeness is crucial for ensuring the quality and commercial value of apples. However, when it comes to detecting apples spectrally under different seasonal variations, there are limitations in the application of calibration models that are built for a single season. Therefore, it is necessary to implement model updating. In this study, a large dataset was acquired of apple visible and near-infrared spectra spanning four seasons and assessed the ripeness of the samples based on computer vision tools. After completing a series of data processing and parameter optimisation, a one-dimensional convolution neural network was built on the initial seasonal dataset. Subsequently, model transfer between seasons was completed using deep transfer learning. Further, multi-seasonal model updating of apple ripeness classification models was achieved in two scenarios with and without historical data. The results indicated that by retraining the network’s convolution layer, the classification accuracies for the three new seasons improved by 4%, 18%, and 15% respectively, while remaining stable for the original season. Combining 5%–20% new season samples with cumulative historical data, the model’s classification performance improves by up to 54% and 55% on the two new seasons. This study contributes to the updating of the multi-seasonal spectral database model for fruit quality control.
Accurate determination of microscopic parameters is crucial for employing the discrete element method in addressing practical engineering challenges. The angle of repose calibration method for bulk materials is employed but frequently relies on subjective human measurements, potentially resulting in errors. This paper introduces a parameter calibration method that utilises a convolutional neural network to enhance standardisation, universality, and accuracy in predicting particle material behaviour. Firstly, the angle of repose simulations are conducted to establish training and test datasets. Next, sensitivity analysis is performed to determine the evaluation index. Subsequently, the performance differences in prediction accuracy among various input data types and network models, including one-dimensional convolutional, two-dimensional convolutional, and fully connected networks were compared. Finally, the influence of particle size and material type on the trained network model was investigated. The experimental results demonstrate that convolutional neural networks outperform traditional parameter calibration methods, in terms of feature extraction capabilities. According to the evaluation indicators in this paper, the conventional method achieves the highest prediction accuracy of 63.33%, whereas the deep learning method achieves a prediction accuracy of 86.67%. Additionally, the accuracy of one-dimensional convolutional network predictions is relatively high when compared to two-dimensional convolutional and fully connected networks. Furthermore, contour feature data exhibits superiority over slope data. Specifically, when the network input data consists of contour data, the prediction accuracy is further enhanced by 6.67% due to its inclusion of more effective features. This study provides new insights into the angle of repose parameter calibration.
A comprehensive modelling methodology is proposed to describe wheat seeds using the discrete element method. By analysing the geometrical characteristics of wheat seeds, the multi-sphere approach is employed to establish 7-, 11-, 15-, 19-, and 23-sphere models based on ellipsoids. The physical and mechanical characteristics of wheat grain are measured and calibrated. Then, the proposed model is verified with several assessment criteria by contrasting the results of the experiment and simulation, including the wheat seed volume fraction, static angle of repose, hopper discharge, rotating drum and “self-flow screening”. By balancing the accuracy of the multi-sphere model and computational efficiency, the 7-sphere or 11-sphere model is found to be the optimal model for determining the static stacking behaviour and hopper discharge of wheat seeds. For the rotating drum and the “self-flow screening”, there is a considerable discrepancy between the simulation and experimental findings due to the surface roughness of the 7- and 11-sphere models. However, 15-, 19-, and 23-sphere models show a high accuracy, which can be applied for drying seeds of the rotating drum and accurately reproducing the sieve permeability of the “self-flow screening” experiment. In summary, the proposed multi-sphere method can be extended to related industry fields by demonstrating satisfactory accuracy in several validation tests.
Base-cutting is essential in sugarcane harvesting, and violent collisions between the base-cutter and stalk can cause stubble damage. Therefore, it is necessary to study the base-cutting mechanism to reduce stubble damage. Based on the mechanical analysis method, this study analysed the base-cutting process of sugarcane vascular bundles and stems from fibber and macro perspectives, respectively. In addition, the base-cutting process was simulated based on Discrete Element Method, and field experiments were conducted to validate the analysis results. The tensile length function L (z) of the vascular bundle was derived from a fibber perspective. A mechanical model of the cutting force on the entire stem was obtained from a macro perspective. From the equations, it can be found that the kinematic parameters of the base-cutter have a significant influence on the cutting force. The simulation test revealed that the cutting force increased sharply when the blade was cut into stems, and the maximum cutting force reached 146.9N. Field tests were conducted to explore the relationship between these factors and the stubble damage rate. To decrease the damage rate to a smaller level, the single-factor test results showed that the forward speed of harvester, rotational speed of disc, and cutting depth should be controlled in the range of 0.8–1.4 m s−1, 600–1000 r·min−1, and 60–120 mm, respectively. The response surface test showed that the order of the effect of each factor on stubble damage was forward speed > rotational speed > cutting depth. The lowest stubble damage rate was 6.20% when the forward speed, rotational speed of disc, and cutting depth were 1.4 m s−1, 800 r·min−1, and 79.07 mm, respectively. After experimental field verification, the damage rate met the harvesting standard.
A self-exchange aquaculture vessel stands as an environmentally sustainable solution for fish farming, capitalising on seawater utilization and minimising the risk of fish escapes through the implementation of perforated culture tanks. This research aims to lay the groundwork for the conceptual design, modelling, and simulation analysis of such vessels, focusing on how near-bottom perforation placement affects flow field characteristics within the culture tank. This paper presents a computational study using Computational Fluid Dynamics (CFD) to analyse self-exchange aquaculture vessels under both head and beam current conditions. The solution of conservation equations governing tank hydrodynamics is achieved using an implicit unsteady second-order Eulerian (finite volume) technique on optimised trimmed meshes. Experimental and predicted values for the vessel model's total resistance were evaluated using uncertainty analysis, validating the numerical model. It was found that proper positioning of perforations near the bottom significantly enhances the synergistic effect of fluid within the culture tank and the mixing characteristics of the flow field. To enhance water circulation, it is recommended to install two or more rows of perforations on the sides of self-exchange aquaculture vessels. The coordination between perforation placement and vessel structure should be considered to determine the optimal layout. By offering valuable insights into the effects of perforation placement, this study contributes to the development of more efficient and environmentally friendly aquaculture practices.
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：