With the rising global energy consumption, the energy use of heating, ventilation, and air conditioning (HVAC) systems has become a critical concern. Existing deep reinforcement learning control methods for HVAC systems often exhibit slow convergence and poor adaptability to dynamic environments, resulting in significant indoor temperature fluctuations, inefficient temperature control strategies, and consequently, energy waste and failure to meet thermal comfort requirements. To address these challenges, this study proposes a novel HVAC control method based on the Soft Actor-Critic with Intrinsic Reward and Correlation-Aware CNN (SAC-IRCNet) model. The model incorporates cooling load prediction as a constraint to enable on-demand cooling supply. It integrates an Elliptical Dynamics Exploration intrinsic reward mechanism, which accelerates SAC convergence through elliptical exploration rewards and inverse dynamics models, thereby reducing energy waste. Additionally, the Correlation-Aware CNN enhances SAC’s feature extraction capability by leveraging state correlations to better understand contextual information, enabling more accurate responses to environmental changes and improved thermal comfort. Experimental results show that SAC-IRCNet achieves a 3.94% faster reward convergence and a 5.78% higher maximum cumulative reward within five episodes compared to SAC. It reduces energy consumption by up to 17.25% (21,837.58 kW) and lowers thermal discomfort violations by up to 6.44%, demonstrating excellent generalization ability across two datasets.

We consider the problem of resilient control of linear time-varying cyber-physical systems (CPSs) over a finite horizon in the presence of hybrid threats via a game approach. Hybrid attacks, including denial of service (DoS) and false data injection (FDI) attacks, can restrict data messaging in CPSs by deliberately altering information. To mitigate damage caused by attacks, this paper constructs a control mechanism incorporating a compensation strategy. A game model is introduced to compensate for performance losses incurred by attacks, describing the interactive behaviour between attackers and defenders. An algorithm for designing resilient controllers is proposed to explore the system’s optimal defence strategy, satisfying theH∞performance condition from attack signals to controlled outputs. Finally, simulation examples are provided to validate the effectiveness of the proposed resilient controller design scheme.

This work presents a novel adaptive sampled-data backstepping control method for the fractional-order air handling units (AHUs) in the building heating, ventilating, and air conditioning (HVAC) systems to achieve indoor temperature regulation. The control for fractional incommensurate AHUs, which relieve computational costs for implementing control and thus enhance building energy efficiency due to the concise and precise form of the system model in comparison to the integer-order case, are studied for the first time. By strictly considering the infinite-memory and hereditary characteristics of fractional-order systems, the temperature control scheme, which novelly combines the sampled-data scheme with the backstepping technique for reducing control and transmission resources, is proposed. It is proven on the basis of Lyapunov stability analysis to be effective with the indoor temperature being able to track the target temperature accurately while all the closed-loop signals remain globally bounded even with practically time-varying AHUs system uncertainties and external disturbances. Simulation studies verify the efficacy of the proposed strategy and validate the established results.

Electroencephalogram (EEG) can record the elec-trical activity of large neural populations and has been widely applied to emotion recognition. Many existing methods leverage EEG signals from tens or even hundreds of electrodes (referred to as full-channel EEG) to develop emotion recognition algorithms, achieving promising results. In recent years, portable and miniature EEG devices equipped with only a few electrodes (referred to as few-channel EEG) have begun to emerge. However, emotion recognition from few-channel EEG data remains challenging due to the sparsity and limited information in the signals. Moreover, full-channel algorithms cannot be directly applied to few-channel EEG signals due to differences in channel configuration and signal characteristics. To address these challenges, this paper pro-poses a reciprocal knowledge distillation based network, named RKD-Net, for few-channel EEG emotion recognition. In RKD-Net, knowledge is transferred from a teacher network trained on full-channel EEG signals to a student network based on few-channel EEG inputs, and the teacher is continuously updated based on the student's feedback and predictions, thus forming a reciprocal interaction. Furthermore, to capture complementary emotional features across both local and global temporal dynam-ics, the hybrid time-frequency EEG representations are fused with wavelet-based time-frequency diagrams at multiple scales. Extensive experiments on two public EEG datasets demonstrate the superiority of RKD-Net in few-channel emotion recognition.

This study introduces a new asynchronous sampled-data distributed consensus control protocol for nonlinear fractional-order multiagent systems (MASs) containing system uncertainties along with time-varying disturbances. With strict consideration of the hereditary and infinite-memory characteristics of fractional-order systems, a novel adaptive backstepping-based distributed sampled-data control scheme is developed for individual agents with asynchronous sampling mechanisms. Through Lyapunov stability analysis, it is demonstrated that the proposed strategy guarantees the stability of the entire closed-loop system, meaning that all signals will remain within bounds and each agent can achieve output consensus with the specified time-varying reference trajectory. The efficacy of the proposed approach is illustrated through simulation studies, which also serve to validate the results obtained.

In compound fault diagnosis, the scarcity of samples leads to a low fault diagnosis rate. Existing zero-shot compound fault diagnosis methods lack the ability to simultaneously recognize both seen and unseen fault classes, especially when aligning attributes of unseen faults, where a dimensionality explosion occurs. To counter the deficiencies of traditional zero-shot compound fault diagnosis methods, this article introduces an innovative generalized zero-shot compound fault diagnosis approach. This approach pioneers the use of an attribute transformation strategy, establishing a knowledge bridge between single and compound faults through a semantic label definition module, thereby creating a fault attribute set. The fault generation module is then utilized to ingeniously convert the attribute set into training samples that are rich in fault characteristics. These samples are employed to train a multilabel classification module, enabling the model to identify compound faults, including those of unseen classes. Experiments conducted on two real-world bearing datasets have validated the effectiveness and strong generalization capabilities of this method, offering a novel solution and technical support for current zero-shot rotating machinery fault diagnosis.

Memtranstor (MT) is proposed as a complement to the concept of memory element, which is conceived based on a direct correlation between magnetic flux φ and charge q. The electrical characteristics of MT is different from other memory elements, which enables MT to have more application scenarios. Thus, we design a floating MT emulator containing a constitutive DC control voltage vs to mimic a hardware MT. In this emulator, the inverse memtranstance (MT-1) can be directly measured and divided into two different states, namely, state 1: MT-1 is always positive or always negative, state 2: MT-1 is either positive or negative. We propose a control method of changing the direction and magnitude of the electric field of vs to achieve these two different states. For the proposed MT emulator, we also analyze typical nonlinear characteristics of pinched hysteresis loops (PHLs) and the variation of MT-1 under different vs and sinusoidal excitation frequencies. The correctness and feasibility of the emulator have been systematically validated through theoretical analysis, PSpice simulation, and hardware experiments. To further demonstrate the potential application of MT, we verify artificial synaptic plasticity of the MT emulator by experiments. The experiments results show that MT emulator can resemble long-term potentiation and long-term depression. The proposed MT emulator has a certain reference value for future research of MT-based nonlinear dynamics and can facilitate MT-based application research.

This article studies the distributed quantized tracking control problem with prescribed output performance requirements for uncertain nonlinear integer high-order multiagent systems (MASs) with both Denial-of-Service (DoS) attacks and external unknown disturbances under data-rate-constrained communication networks. A hierarchical control framework including a quantized resilient distributed observer layer and a decentralized quantized adaptive fractional-order controller layer is proposed for solving the considered control problem. Specifically, quantized resilient distributed observers are designed at the observer layer for each agent to guarantee the availability of observing the reference system under the influence of data-rate-constrained communication and DoS attacks. Based on the designed observers, smooth reference trajectories with the existence of high-order derivatives, which ensure the applicability of the backstepping technique, are then constructed at the decentralized controller layer, where a novel adaptive fractional-order prescribed performance-based backstepping quantized control strategy is proposed for high-order integer uncertain systems, resulting in an enhanced control scheme with the integration of fractional calculus. It is theoretically proven that under data-rate constraints and DoS attacks, the output tracking error of each agent in relation to the reference signal will constantly stay strictly within the predefined performance limit under the proposed control scheme, with all closed-loop signals remaining bounded. Simulation studies are provided as evidence to establish the efficacy of the proposed distributed quantized fractional adaptive prescribed performance-based control strategy.

Bearing fault diagnosis is of great significance to the reliability and stability of modern petrochemical systems. The existing dimensionless index-based bearing fault diagnosis methods suffer from several shortcomings, which are associated with excessive dependence on expert knowledge, insufficient sensitivity in fault feature extraction, and low diagnostic accuracy of nonstationary nonlinear dynamic signals. In this article, a data preprocessing by mutual dimensionless and similar Gram matrix in fault diagnosis is proposed. In this preprocessing, the vibration signal of bearing fault is treated by the mutual dimensionless theory and similar Gram matrix, which is further integrated with the convolutional neural network. The proposed method is tested on two datasets, including a multistage centrifugal fan dataset from our laboratory and a motor bearing dataset from the Case Western Reserve University, achieving an average prediction accuracy of 89.65% and 97.21%, respectively, while reducing the training time significantly. Moreover, the proposed method is compared with other deep learning and traditional methods, including recurrent neural network, support vector machines, and multigenetic algorithm. The experimental results demonstrated that this method can effectively identify fault types by combining various intelligent methods, and compared to traditional dimensionless fault diagnosis methods, the average diagnosis accuracy is significantly improved. The results are also compared with results reported in the literature, indicating that the proposed method can improve fault diagnosis accuracy in an effective and stable way.

The high cost of maintaining radio map is a major hurdle for wide application of WLAN fingerprint-based indoor localization. The development of mobile crowd sensing provides new possibilities, however the features of normal users such as moving freely and non -professional bring new challenges. In this paper, a radio map self-updating algorithm is proposed to resolve three key problems: the localization accuracy, determination of fingerprints need to be updated, and capture of new fingerprints. First we design the localization matrix mechanism and periodic adaptive estimate algorithm to ensure the localization accuracy. Second we propose the fingerprint integrity assessment algorithm to detect the access points changed and the periodic adaptive estimate algorithm to decide the update period for each reference point. Finally we design the active fingerprint collecting mode to update the radio map efficiently. The algorithm proposed has been deployed for real-world testing over 30 days, our studies show that it detects the network changes in indoor environment correctly in 98% cases, and automatically judges the localization accuracy in 95% cases. Meanwhile, the localization accuracy is stable and improved by over 40% even after long terms of deployment, and the overhead of user terminals is reduced over 40%.