Agricultural robots have demonstrated significant potential in enhancing farm operational efficiency and reducing manual labour. However, unstructured and complex farm environments present challenges to the precise localisation and navigation of robots in real time. Furthermore, the high costs of navigation systems in agricultural robots hinder their widespread adoption in cost-sensitive agricultural sectors. This study compared two localisation methods that use the Error State Kalman Filter (ESKF) to integrate data from wheel odometry, a low-cost inertial measurement unit (IMU), a low-cost real-time kinematic global navigation satellite system (RTK-GNSS) and the LiDAR-Inertial Odometry via Smoothing and Mapping (LIO-SAM) algorithm using a low-cost IMU and RoboSense 16-channel LiDAR sensor. These two methods were tested on unstructured farm environments for the first time in this study. Experiment results show that the ESKF sensor fusion method without a LiDAR sensor could save 36% of the cost compared to the method that used the LIO-SAM algorithm while maintaining high accuracy for farming applications.

The organic Rankine cycle (ORC)-based waste heat recovery (WHR) system operating under a supercritical condition has a higher potential of thermal efficiency and work output than a traditional subcritical cycle. However, the operation of supercritical cycles is more challenging due to the high pressure in the system and transient behavior of waste heat sources from industrial and automotive engines that affect the performance of the system and the evaporator, which is the most crucial component of the ORC. To take the transient behavior into account, the dynamic model of the evaporator using renowned finite volume (FV) technique is developed in this paper. Although the FV model can capture the transient effects accurately, the model has a limitation for real-time control applications due to its time-intensive computation. To capture the transient effects and reduce the simulation time, a novel fuzzy-based nonlinear dynamic evaporator model is also developed and presented in this paper. The results show that the fuzzy-based model was able to capture the transient effects at a data fitness of over 90%, while it has potential to complete the simulation 700 times faster than the FV model. By integrating with other subcomponent models of the system, such as pump, expander, and condenser, the predicted system output and pressure have a mean average percentage error of 3.11% and 0.001%, respectively. These results suggest that the developed fuzzy-based evaporator and the overall ORC-WHR system can be used for transient simulations and to develop control strategies for real-time applications.

This paper presents a control-oriented neuro-fuzzy model of brazed-plate evaporators for use in organic Rankine cycle (ORC) engines for waste heat recovery from exhaust-gas streams of diesel engines, amongst other applications. Careful modelling of the evaporator is both crucial to assess the dynamic performance of the ORC system and challenging due to the high nonlinearity of its governing equations. The proposed adaptive neuro-fuzzy inference system (ANFIS) model consists of two separate neuro-fuzzy sub-models for predicting the evaporator output temperature and evaporating pressure. Experimental data are collected from a 1-kWe ORC prototype to train, and verify the accuracy of the ANFIS model, which benefits from the feed-forward output calculation and backpropagation capability of the neural network, while keeping the interpretability of fuzzy systems. The effect of training the models using gradient-descent least-square estimate (GD-LSE) and particle swarm optimisation (PSO) techniques is investigated, and the performance of both techniques are compared in terms of RMSEs and correlation coefficients. The simulation results indicate strong learning ability and high generalisation performance for both. Training the ANFIS models using the PSO algorithm improved the obtained test data RMSE values by 29% for the evaporator outlet temperature and by 18% for the evaporator outlet pressure. The accuracy and speed of the model illustrate its potential for real-time control purposes.

Crop height is a vital indicator of growth conditions. Traditional drone image-based crop height measurement methods primarily rely on calculating the difference between the Digital Elevation Model (DEM) and the Digital Terrain Model (DTM). The calculation often needs more ground information, which remains labour-intensive and time-consuming. Moreover, the variations of terrains can further compromise the reliability of these ground models. In response to these challenges, we introduce G-DMD, a novel method based on Gated Recurrent Units (GRUs) using DEM and multispectral drone images to calculate the crop height. Our method enables the model to recognize the relation between crop height, elevation, and growth stages, eliminating reliance on DTM and thereby mitigating the effects of varied terrains. We also introduce a data preparation process to handle the unique DEM and multispectral image. Upon evaluation using a cotton dataset, our G-DMD method demonstrates a notable increase in accuracy for both maximum and average cotton height measurements, achieving a 34% and 72% reduction in Root Mean Square Error (RMSE) when compared with the traditional method. Compared to other combinations of model inputs, using DEM and multispectral drone images together as inputs results in the lowest error for estimating maximum cotton height. This approach demonstrates the potential of integrating deep learning techniques with drone-based remote sensing to achieve a more accurate, labour-efficient, and streamlined crop height assessment across varied terrains.