Intelligent fault diagnosis of rotating machinery is essential for predictive maintenance, yet conventional deep learning models suffer from limited generalization under noisy and cross-domain conditions. Furthermore, their lack of interpretability restricts industrial trust and deployment. To address these challenges, we propose Conformer-PhyFaultNet, a novel physics-informed spectral attention Conformer that seamlessly integrates domain knowledge with advanced sequence modeling. The method embeds characteristic fault frequencies (BPFO, BPFI, FTF) directly into the spectral attention layer, guiding the network toward physically meaningful patterns rather than spurious features. A set of physics-guided tokens is introduced into the Conformer encoder, which persist across layers and acts as stable descriptors of defect signatures. The hybrid spectral attention + physics tokens mechanism enables the model to simultaneously capture local fault harmonics and long-range dependencies across time–frequency representations. Unlike conventional CNN or Transformers, proposed approach ensures interpretability by aligning attention distributions with analytic harmonics and providing layer-wise token activations as diagnostic evidence. This dual mechanism represents the key novelty, bridging analytic fault modeling with modern deep architectures for the first time in a unified framework. Extensive experiments on CWRU, Paderborn, and HUST datasets demonstrate the superiority of the proposed method: in-domain accuracy reaches 93.75, cross-domain transfer achieves 86.75 (CWRU→Paderborn) and 84.3% (HUST→CWRU), while noise robustness remains above 87% at 10 dB and 81% at 0 dB, outperforming CNN, RNN, Transformer and physics-informed baselines by significant margins. The proposed Conformer-PhyFaultNet therefore offers a technically rigorous, interpretable and noise-robust solution that can substantially enhance the reliability and adoption of intelligent predictive maintenance in industrial environments, while also enabling real-time monitoring and edge deployment in industrial IoT systems through low-latency inference (< 5 ms per segment).

The Internet of Natural Things (IoNT) is the extension of the Internet of Things (IoT) concept to natural environments, with the ability to monitor the environment in real-time using integrated sensor networks, Artificial Intelligence (AI), and remote sensing. IoNT can offer solutions to the ecological crisis that is facing the world today, such as climate change, loss of biodiversity, and depletion of resources. The survey addresses the technology behind the IoNT and its different applications in disaster management, forest conservation, biodiversity monitoring, and agriculture, among others. IoNT has been successfully applied to monitor the quality of water in remote river ecosystems and to irrigate precision agriculture. Furthermore, pilot projects have demonstrated that IoNT can be used to make decisions based on real-time data analytics so that it is possible to manage resources sustainably. The other aspect discussed in the survey is the consistency between the IoNT sensors and the commercial sensors, according to some case studies presented in the literature. In those works, it is also identified that the processes are experimental in sensor testing, data synchronization, and the functioning of standard metrics, which ensure the reliability and strength of IoNT sensor systems. Despite the fact that the IoNT has great strengths, it is still possible to encounter issues concerning data security, energy efficiency, and interoperability. The survey addresses these issues and identifies new trends, such as blockchain and autonomous systems, that can make IoNT applications more scalable and efficient to manage the sustainable ecosystem.

The convergence of blockchain with Industry 5.0 technologies presents significant opportunities for healthcare data management; however, current systems face challenges related to scalability, privacy, and energy efficiency. This article introduces an innovative framework that leverages ciphertext-policy attribute-based encryption (CP-ABE), Ethereum smart contracts, and decentralized IPFS storage to address these challenges. The framework presents three main innovations: 1) a human-centric authentication system that ensures security without sacrificing cryptographic integrity; 2) post-quantum Kyber-786 algorithms paired with CP-ABE, which minimizes computational overhead by 27% while facilitating 32 ms key generation; and 3) an energy-efficient Proof of Stake (PoS) consensus mechanism that reduces energy consumption by 98% (0.05 kW/transaction) compared to traditional blockchain systems. Thorough testing demonstrates 99.5% resistance to man-in-the-middle attacks, a throughput of 15.6 MB/min at scale, and an emergency access latency of under 120 ms, which is essential for practical healthcare applications. By consolidating decentralized pseudo-identities for patient anonymity, secure audit logs, and GDPR/HIPAA-compliant data governance, this research establishes a new standard for secure, sustainable, and patient-focused health data ecosystems in the Industry 5.0 landscape.

Over the last 20 years, numerous experts in the manufacturing companies have become interested in controllingflexible joint robots. The control design process using a networked framework has played a significant role in the industrial sector. This research addresses theself–triggeredcontrol problem forTakagi–Sugeno (T–S) fuzzy systemsbased on time delay is established in this research. A newself–triggeredmechanism determines when the plant state is transmitted. Instead of continuously tracking predefined triggering conditions, theself–triggeredsystem determines the next triggering instant based on the most recently triggered state information. Theself–triggeredmechanism relying onT–S fuzzy controlleris then created using the triggered state, allowing for flexible configuration of its fuzzy rules andmembership operations (MOs)that are not dependent on the controlled fuzzy system. Furthermore, it precisely demonstrates the interaction between the triggered condition and the plant state under the constraint of mismatched premise variables. To ensure system stability and performance, delay–dependent requirements are derived using a novelLyapunov–Krasovskii functionalbased on fuzzy concepts to develop the fuzzy control design. The presence of the required controller is then shown underLMI–based conditions. Lastly, a simulation of a flexible robotic arm example is provided along with an evaluation of other triggered methods.

In nonlinear systems, monitoring control behavior, fault occurrence, and latency factor continue to be major obstacles. Traditional control models frequently handle edge–case situations inaccurately and are unable to adjust to dynamic changes. Reinforcement learning control is a novel intelligent framework that incorporates sophisticated modules for nonlinear models in order to overcome these constraints. First, an innovative approach to solving the adaptive tracking algorithm for a type of T–S fuzzy plant is presented in this research. Furthermore, the authors examine time–varying delay with the actuator failure for complex systems that are generally represented by the T–S fuzzy plant. Second, it has been demonstrated that the chosen performance index solves the delayed algebraic Riccati formula, which can be resolved by scheme of repetition methods, when the resultant plant with the tracking signal is constructed under the decoupling delayed T–S fuzzy framework. Third, the coupled delayed algebraic Riccati formulas are then solved using a Reinforcement Learning (RL) technique that makes use of complex model dynamics knowledge. Furthermore, the fundamental RL iteration technique’s convergence is demonstrated. Lastly, the power sector and a F–16 airplane flight examples are provided to demonstrate how the online repetition method outperforms the offline one in terms of tracking accuracy and effectiveness.

Over the past 20 years, many specialists in the business have become interested in managing flexible joint robotics. Considering flexibility in joints in the control scheme of inflexible robots is challenging because it eliminates certain structural properties that facilitate control, such as full activation, distinct control for every socket, and passivity of the torque generated by the motor for coupling velocity. In this research, the authors analyze asymptotic stability for neural models of fixed stochastic process that have time-varying delays, which depend on jumping modes; their derivatives no longer need to be smaller than one. Secondly, by applying a stochastic setup, the researchers explore fixed neutral models with Markovian jump variables based upon mode-dependent time-varying delays for modeling flexible joint robots. Thirdly, this research develops various stability circumstances with delay-dependent conditions based on linear matrix inequalities (LMIs) by combining the novel Lyapunov theory with the convex polyhedron technique, concluding with two numerical examples illustrating their use. As a result, an optimization problem can be addressed to calculate a control law created for implementing the stochastically stable platform. As a final step, the proposed method is verified using a quadruple-tank model and for modeling flexible joint robots. Note to Practitioners—Neural network controllers are frequently employed in the medical field, automation industry, robotics sector, and other industries where certain jobs cannot be completed by autonomous or human robotics. By increasing flexibility, refining control technique, relaxing stability conditions, and promoting human-robot collaboration, this research seeks to create novel solutions to important problems in industrial robotic manipulators. In order to maintain the system’s stability in both motion states-coupling velocity and torque motion and meet the associated position and velocity synchronization goals, this paper suggests a NN-based control technique that can manage random process and variable time-delays signals. More straightforward structures, fewer tuning factors, and improved control behaviors are some of the benefits of this approach that make engineering applications easier. Lastly, a simulation using a realistic strategy is demonstrated to validate the theoretical assertions.

The Internet of Robotic Things (IoRT) is growing rapidly with new applications. Co-operatory robotics enables the sharing of information, autonomy, and fail-safe interaction with environment, humans, and other robots. They can also self-maintain, self-aware, and self-heal. To provide reliable and robust online monitoring of the industrial manipulator joint status, this article proposes a new IoRT architecture based on transfer learning (TL) techniques to detect manipulator fault. Robotic manipulator joint status are detected with high accuracy using a hybrid 1-D multichannel convolutional neural network (1D-MCNN), including matrix kernels and recurrent neural network (MCNN-RNN) technique. Moreover, a timestamp mapping method addresses the challenges associated with inconsistencies in sensor data timestamps. Existing data-driven methods struggle with the diverse operating conditions of industrial robots, where load and speed constantly fluctuate. To address this limitation, we propose a novel TL-based MCNN-RNN approach for joint fault diagnosis under varying work conditions. This method leverages the adaptability of TL while incorporating the inherent relations between different failure modes, enhancing the TL process. To demonstrate the performance of the suggested IoRT topology, various experimental scenarios are performed with data acquisition on six degree-of-freedom (DOF) UR16e (universal robot) manipulator. Based on the results, the proposed IoRT architecture can effectively visualize the joint fault status of the manipulator. As a result, TL architecture combined with MCNN-RNN provides an excellent accuracy of 99.03%in detecting faults on manipulator joints, which is significantly higher than traditional convolutional neural network (CNN), deep belief network (DBN), domain adversarial neural network (DANN), and conditional domain-adversarial network (CDAN).