A novel adaptive robust icing and fault tolerant composite control for the trajectory tracking problem of a large blended-wing-body (BWB) aircraft with ice accretion, actuator faults, unknown disturbances and uncertainties is proposed. Firstly, a linear parameter varying (LPV) model is developed from the nonlinear dynamics of the BWB aircraft, and a neural network (NN) based LPV controller is investigated for the trajectory tracking. The disturbance observer is designed to overcome the effect of external unknown disturbances. For the actuator faults of the aircraft, a low-complexity fault tolerant controller is developed by fault estimation. To improve the anti-icing performance of the BWB aircraft system, a new icing adaptive compensator is proposed. Simulation scenarios are presented to illustrate that the proposed composite controller has better performances on trajectory tracking under both icing and actuator faults.

Two-phase flow regime identification is an essential transdisciplinary topic that spans digital signal processing, artificial intelligence, chemical engineering, and energy. Multiphase flow systems significantly impact pipeline safety, heat transfer, and pressure drop; therefore, precisely identifying the governing flow regime is crucial for effective modeling and design. However, it is challenging due to the geometrical complexity of flow regimes in multiphase flow. With the advances in sensor measurement and machine learning, applying non-destructive tests and self-supervised learning to practical industrial problems has become technically feasible and cost-effective. This study applies a weak-supervised learning-based two-phase flow regime identification solution using a non-destructive tests ultrasonic sensor in an S-shape riser experimental bed by proposing a self-supervised feature extraction algorithm. The proposed self-supervised feature extraction algorithm reduces time/labor consumption and human error in data annotation using SSL, which provides full supervision without manual annotation. The self-supervised feature extraction algorithm uses a bottlenecked neural network and encoder-decoder structure to extract compact features. The self-supervised feature extraction algorithm performance is evaluated using an established convolutional neural network-based classifier. The source data was collected from a 10×50 meter riser experimental rig. The dataset is made available to the community as part of this study. The performance of the approach is comparable with state-of-the-art methods and is also the first successful attempt to apply self-supervised learning to multiphase flow regime ultrasonic signal identification. This study achieved 98.84%, 0.000663, 0.00312, and 7.71×105 in accuracy, root mean square error, categorical cross-entropy, and model complexity, respectively. The practical experiment justifies the robustness, fairness, and practicability in the practical application environment. The proposed self-supervised feature extraction brings new approaches and inspirations for the feature extraction step in identifying a two-phase flow regime, and it will be beneficial to generalize this study in different riser shapes in the future.

The problem of classifying gas-liquid two-phase flow regimes from ultrasonic signals is considered. A new method, belt-shaped features (BSFs), is proposed for performing feature extraction on the preprocessed data. A convolutional neural network (CNN/ConvNet)-based classifier is then applied to categorize into one of the four flow regimes: 1) annular; 2) churn; 3) slug; or 4) bubbly. The proposed ConvNet classifier includes multiple stages of convolution and pooling layers, which both decrease the dimension and learn the classification features. Using experimental data collected from an industrial-scale multiphase flow facility, the proposed ConvNet classifier achieved 97.40%, 94.57%, and 94.94% accuracy, respectively, for the training set, testing set, and validation set. These results demonstrate the applicability of the BSF features and the ConvNet classifier for flow regime classification in industrial applications.

In this paper, a bio-inspired monocular vision perception method combined with a learning-based reaction local planner for obstacle avoidance of micro UAVs is presented. The system is more computationally efficient than other vision-based perception and navigation methods such as SLAM and optical flow because it does not need to calculate accurate distances. To improve the robustness of perception against illuminance change, the input image is remapped using image moment which is independent of illuminance variation. After perception, a local planner is trained using deep reinforcement learning for mapless navigation. The proposed perception and navigation methods are evaluated in some realistic simulation environments. The result shows that this light-weight monocular perception and navigation system works well in different complex environments without accurate depth information.

The complexity of linear, fixed-point arithmetic, digital controllers is investigated from a Kolmogorov-Chaitin perspective. Based on the idea of Kolmogorov-Chaitin complexity, practical measures of complexity are developed for both state-space realizations, and for parallel and cascade realizations. The complexity of solutions to a restricted complexity controller benchmark problem is investigated using this measure. The results show that, from a Kolmogorov-Chaitin viewpoint, higher-order controllers with a shorter word-length may have a lower complexity but a better performance than lower-order controllers with longer word-length.

The backpropagation (BP) algorithm is commonly used in many applications, including robotics, automation and weight changes of artificial neural networks (ANNs). This paper proposes the addition of an extra term, a proportional factor (PF), to the standard BP algorithm to speed up the weight adjusting process. The proposed algorithm is tested and the results show that the proposed algorithm outperforms the conventional BP algorithm in convergence speed and the ability to escape from learning stalls. The paper presents a convergence analysis of the three-term BP algorithm. It is shown that if the learning parameters of the three-term BP algorithm satisfies certain conditions given in this paper, then it is guaranteed that the system is stable and will converge to a local minimum. The paper shows that all the local minima of the cost function are stable for the three-term backpropagation algorithm.

Feedback controller implementations with fixed-point arithmetic offer the advantages of speed, memory space, cost and simplicity compared to floating-point arithmetic. Thus, to date, fixed-point processors dedicated for digital controller implementations are still the dominant architecture in many modern digital control engineering applications, particularly for automotive, consumer, military and medical applications. However, most control design methodologies assume that the designed controller will be implemented with infinite precision. Thus, when the controller is implemented on a fixed-point platform, rounding errors can cause a performance degradation and even instability. Hence, there is a trade-off between the cost of the controller in terms of word-length, memory and computation requirements (the controller compactness) and the performance of the system. This paper presents an approach to designing finite word-length feedback controller structures by means of a multi-objective genetic algorithm. The approach provides a set of solutions that are (near) Pareto optimal with respect to minimal word-length and memory requirements and to closed-loop performance. The method is applied to the design of finite word-length controller structures for two examples, a PID controller for a rolling strip mill, and a controller for the IFAC93 benchmark problem.