Water-fertilizer integrated regulation system aims to to improve crop yield, nutrient use efficiency (NUE), and water use efficiency (WUE). This study develops an intelligent control system with a cloud server network to centralize data management and process. The system contains of the monitoring module, the intelligent cloud platform module, and the control terminal. In the monitoring module, the sensor network and phenotypic monitoring method were utilized to collect real-time crop and environment data. In the intelligent cloud platform module, a perception-computing-control integrated computing optimization framework was constructed to achieve the localization of control tasks by analyzing perceived data, training predictive control models, and optimizing deep reinforcement learning algorithms. The control terminal contains of task scheduling, equipment control, and data collection drive, as well as a reasonable deployment pipeline in the cloud. Our developed control model has increased crop productivity nearly 9% and achieved water resource savings nearly 15.6%. Multi-modal large models will be applied to adjust model parameters in different environments.

With the rapid expansion of global logistics networks, container terminals, as critical nodes in the logistics chain, exert significant influence on the overall performance of supply chains. In terminal operations, container stacking strategies and equipment configuration are core factors determining operational efficiency. However, due to the complexity of terminal operations and the existence of multi-layered feedback mechanisms, there is currently a lack of systematic and quantitative evaluation methods to analyze the advantages and disadvantages of stacking strategies and equipment configurations. To address this gap, this study proposes a data-driven analytical framework. By processing real-world terminal operation data, the framework constructs a digital yard feature model, extracts key spatiotemporal operational features, and integrates the spatial feature extraction capability of 3D Convolutional Neural Networks (3DCNN) with the advantages of Boosting algorithms in handling non-linear relationships and feature importance. The study introduces a novel Deep-Tree Cascaded Regression (DTCR) algorithm to predict vessel handling efficiency, a highly uncertain and nonlinear indicator, to quantitatively assess the practical impact of different stacking strategies and equipment configurations. Experimental results demonstrate that the proposed model accurately captures the key correlations between container stacking and terminal operations, predicts vessel handling efficiency within a reasonable accuracy range, and realistically reflects the terminal’s operational processes. These findings provide a scientific basis for optimizing yard stacking strategies and equipment operation workflows, effectively improving overall terminal operational efficiency. Additionally, this research offers technical support and practical insights for the development of smart ports.

Given that transportation contributes to 23% of global energy-related greenhouse gas emissions, the electrification of the transport sector is an inevitable trend. This paper presents a hybrid energy management method that utilizes the Deep Deterministic Policy Gradient (DDPG) algorithm. To enhance its exploration capability and balance exploration and exploitation, the Locality Sensitive Hashing (LSH) algorithm and Prioritized Experience Replay (PER) algorithm are introduced. DDPG, being a deterministic strategy, typically explores the environment by adding noise to the action space, which lacks effective exploration capability. Therefore, the LSH algorithm is employed for approximate counting of state variables in high-dimensional continuous state spaces. This encourages agents to explore less frequently occurring state variables, thereby improving the algorithm’s exploration ability. Additionally, the integration of the PER algorithm enables more efficient utilization of limited sample data during experience replay, leading to improved learning efficiency and stability. In addition, periodic updates are used to compensate for the additional computational consumption caused by counting. Simulation results on driving cycles from the typical road conditions demonstrate that the proposed algorithm has stronger exploration ability and better management performance comparing with EMSs based on DDPG, DQN and Q-Learning. The LSH-PER-DDPG based EMS achieves a significant 8.5% reduction in lithium battery power consumption, a 6.25% increase in supercapacitor recovery, and a substantial 15.7% reduction in instantaneous fluctuation of lithium battery output current.

With the development of modern communication technology, traditional Internet of Things systems could not provide sufficient support for large data flow, hardware resource, power consumption, and security during transmission. Especially when it comes to the Industrial Internet of Things (IIoT), where the limitations of hardware resource and power consumption are more strict; the requirements of network security and hardware security are much higher. This paper implements a User Datagram Protocol (UDP) communication system, which is encrypted with one of the Lightweight Cryptography, Xoodyak. We aim to design a lightweight encrypted communication platform. Compared with a public key encryption system, our implementation costs much less hardware resource and power consumption, while providing excellent side-channel attack (SCA) protection. Besides, when there is a large burst length of data flow, two asynchronous FIFO can restore those data respectively, so our design can maintain throughput and data integrity in extreme cases. Based on the above properties, our design is relatively ideal in IIoT encryption scenarios.

Detecting defects on the wine bottle surface is a challenging task due to these factors: (1) tiny defects on the surface, (2) visually similar defects with design patterns on bottles, (3) reflective (metallic) bottle surface, (4) real-time requirement. In this paper, we propose an efficient and light-weight detector for the defects. To this end, we adopt EfficientNet- B3 [1] as the backbone of the detector and YOLO [2] as the detection head. In addition, we use channel pruning approach [3] to obtain a more compact model. In the experiments, we obtain a score of 0.77 on the validation dataset, similar performance comparing to the two-stage methods[23]. The parameters of our detector are only 5. 8M, which are about one tenth of the YOLO's [2]. The proposed detector achieves a good balance between speed and accuracy.

This note investigates the asynchronous control issue for Markov jump nonlinear systems using sliding mode approach. An interesting hidden Markov model based mapping mechanism is used to simulate the asynchronous phenomenon and quantify its degree. It is extended to the continuous-time case for Markov jump nonlinear systems by utilizing sliding mode approach. Sufficient conditions are derived ensuring the stochastic stability of the closed loop dynamic and its H∞noise attenuation performance. The obtained results are verified by a LCR circuit in the end.

The paper investigated the global synchronization control problem of dynamic networks with discrete-time communications and input saturation. Based on a geometrical criterion of certain non-linear non-autonomous systems, we proposed a sufficient condition for stability of saturating linear control for a linear networked system. The stability could be ensured simply from a range of gains rather than a complex Lyapunov function. A numerical example is offered to show the effectiveness and the relative analysis.

State-of-charge (SOC) estimation is the key to the BMS of lithium-ion batteries. At present, data-driven methods are more popularly used to estimate the SOC. Among them, the deep learning technology especially recurrent neural networks (RNNs) performed very well. In this paper, we proposed a bidirectional long short-term memory (Bi-LSTM) neural network to perform SOC estimation. The bidirectional LSTM layer is employed to catch the forward and backward temporal dependencies of battery sequential states, and shows better performance in SOC estimation of LiBs. With a public dataset of vehicle driving cycles, we separately train our proposed network at three different constant temperatures (0 °C, 10 °C, and 25 °C), and the evaluated MAEs are 0.498%, 0.411 %, 0.738%. Besides, the Bi-LSTM network trained with overall datasets at three temperatures achieves a mean absolute error (MAE) of 0.616% and maximum absolute error (MaxE) of 3.809%. It shows that the proposed method is robust and accurate in SOC estimation.

Multi‐task cascaded convolutional neural network (MTCNN) is a human face detection architecture which uses a cascaded structure with three stages (P‐Net, R‐Net and O‐Net). The authors intend to reduce the computation time of the whole process of the MTCNN. They find that the non‐maximum suppression (NMS) processes after the P‐Net occupy over half of the computation time. Therefore, the authors propose a self‐fine‐tuning method which makes the control of computation time for the NMS process easier. Self‐fine‐tuning is a training trick which uses hard samples generated by P‐Net to retrain P‐Net. After self‐fine‐tuning, the distribution of human face probabilities generated by P‐Net is changed, and the tail of distribution becomes thinner. The control of the number of NMS input boxes can be made easier when the distribution has a thinner tail, and choosing a suitable threshold to filter the face boxes will generate less boxes. So the computation time can be reduced. In order to keep the performance of MTCNN, the authors still propose a landmark data set augmentation, which can enhance the performance of the self‐fine‐tuned MTCNN. From the experiments, it is found that the proposed scheme can significantly reduce the computation time of MTCNN.

This paper addresses the problem of quantized feedback control of nonlinear Markov jump systems (MJSs). The nonlinear plant is represented by a class of fuzzy MJSs with time-varying delay based on a Takagi-Sugeno fuzzy model. The quantized signal is utilized for control purpose and the sector bound approach is exploited to deal with quantization errors. By constructing a Lyapunov function which depends both on mode information and fuzzy basis functions, the reciprocally convex approach is used to derive the criterion which is able to ensure the stochastic stability with a predefined l2- l∞performance of the resulting closed-loop system. The design of the quantized feedback controller is then converted to a convex optimization problem, which can be handled through the linear matrix inequality technique. Finally, a simulation example is presented to verify the effectiveness and practicability of the proposed new design techniques.

Recently, trajectory misalignment of tunnel boring machine (TBM) has become a key research area. Although TBMs have been extensively applied in tunneling, hunting motion remains due to inhomogeneous ground encountered during tunneling, TBM structures and ambiguity in attitude correction mechanism. In this paper, TBM attitude correction and motion are studied, and optimized fuzzy rule is obtained by taking into account various TBM constraints and the universe of fuzzy control; then, cooperative control over cylinders in various sections is proposed to reduce TBM trajectory tracking deviation from designed tunnel axis; moreover, a cascade control system combining outer-loop trajectory tracking and inner-loop pressure control is developed to enable unmanned automatic tunneling of the TBM. The practical application results reveal that the proposed system demonstrated accurate TBM attitude correction, high stability, strong engineering applicability and feasible real-time control.

The complexity of real-world industrial control systems is growing rapidly. This raises significant challenges for the use of embedded systems in control applications, since embedded platforms are generally resource limited. In this work we develop a Scilab/Scicos based embedded controller on which various control software can be easily modeled, simulated, implemented, and evaluated to meet the ever-expanding requirements of complex industrial control applications. It is built on the Cirrus Logic EP9315 ARM9 systems-on-chip board. With the developed platform, it is possible to design and implement complex embedded control systems that employ advanced control strategies in a rapid and cost-efficient fashion. Thanks to the free and open source nature of the software packages used, the cost of the embedded controller is minimized.

A PSO with increasing inertia weight, distinct from a widely used PSO with decreasing inertia weight, is proposed in this paper. Four standard test functions with asymmetric initial range settings are used to confirm its validity. From the experiments, it is clear that a PSO with increasing inertia weight outperforms the one with decreasing inertia weight, both in convergent speed and solution precision, with no additional computing load compared with the PSO with a decreasing inertia weight.

Minimax problem is significant topic in signal process (e.g. filter design) and process control (e.g. controller design), which is relevant to robustness, parameters uncertainty, and signal noise etc. However, efficient algorithms are scarce, especially those for general minimax problem with equality and inequality nonlinear constraints. In this paper a novel neural network for general minimax problem has been constructed based on a penalty function approach. The unique request on objective function and constraint functions is that they are first-order differentiable. A Lyapunov function is established for the global stability analysis. The network is simulated and its validity is illustrated by numerical examples. Simulation results show that minimax neural network, which computes in second, is more efficient than the previous GA/SGA algorithms, which computes in minutes.

In process control fields it is hard to build precise model due to complexity and nonlinear of industrial process. To solve this problem, this paper proposes a framework for modeling and controlling systems integrating continuous variable linear model and rules. A predictive control scheme is proposed which is able to stabilize this framework on desired reference trajectories. This problem can be solved as Mixed-integer Linear Programming/ Constraint Programming (MILP/CP). We use MILP to optimize and find partial solutions and CP to check feasibility and produce complete solutions. An example demonstrates how problems can be modeled and solved using this framework.