Different scent delivery methods may influence how scents are perceived in interactive systems. This study presents PlayScent, a custom-built research prototype comprising our in-house multi-module driver (UniODriver) and an integrated 3D-printed apparatus. Using a single-outlet design, PlayScent enables controlled comparison of atomizer, air pump, heater, and fan-based delivery methods under shared spatial conditions. Through a mixed-methods study, we develop a preliminary perceptual mapping and an initial perception vocabulary for scent delivery methods, relating user descriptions to measured physical parameters and identifying distinct perceptual tendencies across methods. Exploratory expert feedback further reflects on the possible relevance of these findings for design practice. Building on the empirical results, we outline illustrative design scenarios for future exploration. Together, this work offers an early design-oriented account of how delivery methods may be considered alongside scent selection in olfactory interaction design.

We present a breath-driven odor display device that enables spatial odor perception in virtual reality, relying on users’ natural inhalation rather than pumps or fans. The device supports rapid concentration adjustment through two models: a continuous gradient (monotonic concentration change with position) and a plume (intermittent, fluctuating patterns resembling natural dispersal). To explore its potential, we conducted a proof-of-concept evaluation across four tasks: concentration discrimination, direction and distance localization, and integrated position searching. Results show that the device can dynamically modulate odor concentration for spatial olfactory perception. Our findings further reveal complementary strengths and limitations of the two models—gradients support stable, precise cues, whereas plumes better emulate natural variability. This work introduces a simple yet effective method for simulating spatial odor experiences in VR, offering a lightweight, energy-efficient pathway that expands the design space for olfactory interaction research in virtual environments.

Large language models guided evolutionary frameworks for program synthesis have demonstrated strong results across combinatorial benchmarks; however, such frameworks have not been widely explored for robotic control systems. This article presents an automated framework for synthesizing control logic and optimizing numerical coefficients, enabling the deployment of generated controllers onto robotic platforms. To produce deployable controllers, the framework separates control logic synthesis from numerical parameter optimization, with controller coefficients optimized via particle swarm optimization using a Markov decision process reward signal. The resulting controllers are evaluated in a custom uncrewed aerial vehicles (UAV) simulation environment, validated using PX4 software-in-the-loop, and subsequently deployed on a physical UAV. Controller performance is evaluated on lemniscate and lissajous trajectory-tracking tasks and compared against proportional–integral–derivative with disturbance observer and linear quadratic regulator baselines. Across both trajectories, the framework-generated control law achieves improved tracking accuracy relative to the baseline controllers, with a minimum reduction in mean squared error of approximately 38% in real-world experiments. These results demonstrate the feasibility of deploying automatically synthesized control logic on a physical UAV, bridging automated program synthesis and real-world control deployment.

To detect the demagnetization fault (DF) of a dual-sided permanent magnet synchronous linear motor, a new method based on deep feature fusion of external stray flux signal (ESFS) is proposed. First, finite element models under ideal materials and assembly conditions are established to extract ESFS to reflect DF information. Second, Markov transition field and recurrence plot transform 1-D signals into 2-D images, to realize DF feature visual enhancement. Low-rank representation networks can merge the advantages of both methods by image fusion. Then, an accurate diagnosis framework, as efficient channel attention-MobileNetV3, is proposed to conduct deep feature extraction and realize diagnosis in both qualitative fault type classification and fault degree evaluation aspects. The classification accuracy reaches 98.50%, and the evaluation indexR2reaches 0.96, superior to other frameworks. Finally, a tunnel magnetoresistance sensor is applied to realize ESFS noninvasive online measurement, and an experimental platform is built to certify the superiority.

Edge computing has become increasingly important to fulfill the diversified Quality-of-Service (QoS) or Quality-of-Experience (QoE) demands for Industrial Internet of Things (IIoT) applications, such as machine condition monitoring, fault diagnosis, intelligent production scheduling, and production quality control. Due to the heterogeneity of IIoT systems, it is of urgent necessity to concentrate on the cloud–edge–end cooperative partial task offloading and resource allocation (CPTORA) problem for realizing workload balancing, efficient resource utilization, and better QoS/QoE of IIoT applications. However, the challenge lies in how to make real-time, accurate, decentralized task offloading (TO) and resource allocation (RA) decisions for dynamic and device-intensive IIoT. Therefore, this work examines the CPTORA problem for IIoT, aiming at minimizing its long-run overall delay and energy costs. To lower the problem complexity, this problem is decomposed into the TO subproblem and the RA subproblem. Then, an improved soft actor–critic-based decentralized multiagent deep reinforcement learning (MADRL) algorithm is proposed to address the TO subproblem, where each IIoT device can learn its globally optimal policy and make its decisions independently. This algorithm innovatively combines the divergence regularization, the distributional reinforcement learning, and the value function decomposition methods to improve convergence speed and accuracy of the existing MADRL methods. After receiving the TO decisions of every IIoT device, every edge server employs the Lagrange multiplier method and Karush–Kuhn–Tucker condition to solve its RA subproblem. The experimental results show that the proposed algorithm decreases the overall delay and energy costs more effectively, compared to the other state-of-the-art MADRL approaches.

Intelligent fault diagnosis of rolling bearings has advanced significantly with the increase in labeled industrial data. However, the limited data for unknown working conditions poses a challenge to the generalization capabilities of current deep learning methods. Therefore, this article proposes a novel approach to domain generalization, leveraging a combination of covariance loss and graph convolutional networks to realize feature augmentation for intelligent fault diagnosis. This method employs random receptive field layers in feature extractors to project inputs from each source domain into distinct feature spaces. Moreover, a covariance loss is incorporated to ensure the dissimilarity of feature representations. Consequently, the augmented features contribute to the construction of an expanded adjacency matrix and prototypes within graph convolutional networks, thereby enhancing the model's capacity to generalize to unknown domains. Results on both a public dataset and an experimental dataset of rolling bearings have shown the superiority of the proposed approach.

Underwater acoustic sensor networks (UASNs) are data driven, and the data generation is infeasible without source nodes, sensors, and equipment deployed underwater. However, underwater acoustic communication between nodes is especially vulnerable to malicious attacks, which could cause the source data packets to be tracked and indirectly expose the locations of source nodes. Once the source node is located, the security of the network and the monitored object will be considered threatened. A collision-free transmission-based source location privacy protection algorithm in UASNs under time slot allocation (CFTSLP-TSA) is proposed in this article. First, we select suitable fake source nodes to generate fake data packets, aiming at concealing the traffic of the source data packets. Then, different transmission time slots are arranged for the source and the fake data packets, in order to avoid interference in the transmission between one another. In addition, a handshake-based relay node selection strategy is presented. This not only makes the paths more diverse but also requires a higher requirement for the attacker to track the flow of source packets while the source packets are transmitted without collisions. The performance of the simulation shows that the CFTSLP-TSA produces both a greater source location privacy protection level and a better data packet delivery rate compared with the other state-of-the-art schemes.

As a prototype of the underwater Internet of Things-enabled maritime transportation systems, multi-Autonomous Underwater Vehicle (AUV)-based Underwater Wireless Networks (UWNs) have become an important research topic due to their distribution and robustness. In this paper, the concept of multi-AUV-based UWNs is first defined, where AUV is regarded as a network node, and communication among the AUVs is the potential network links. Then, to improve network scalability and controllability, a paradigm of Software Defined multi-AUV-based UWNs (SD-UWNs) is proposed, where the Software Defined Network (SDN) technique is used to upgrade the UWN architecture by directing intelligent network functions. Topology and artificial potential field theories are applied to construct a network control model for the SD-UWNs. Based on the efficient data sharing ability of the SD-UWNs, an early warning obstacle avoidance-enabled path planning scheme is proposed to guarantee safe sailing of the SD-UWNs, where comprehensive obstacle avoidance scenarios are taken into account. Simulation results demonstrate that the proposed method is effective in planning the cooperative operation for the SD-UWNs and is capable of performing accurate and reliable obstacle avoidance tasks.

As the research topics in ocean emerge, underwater acoustic sensor networks (UASNs) have become ever more relevant. Consequently, challenges arise with the security and privacy of the UASNs. Compared to the active attacks, the characteristics of passive attacks are more difficult to discriminate. Thus, the focus of this study is on the passive attacks in UASNs, where a push-based probabilistic method for source location privacy protection (PP-SLPP) is proposed. The fake packet technology and the multipath technology are utilized in the PP-SLPP scheme to counter the passive attacks, so as to protect the source location privacy in UASNs. Moreover, the Ekman drift current model is employed to simulate the underwater environment. And the mean shift algorithm and the k-means algorithm are adopted in the dynamic layer and static layer of the Ekman drift current model, respectively, to increase the stability of the clusters. Finally, an autonomous underwater vehicle (AUV) swarm is implemented to collect data in clusters. Through the comparison with existing data collection schemes in UASNs, the simulation results have demonstrated that the PP-SLPP scheme can achieve a longer safety period, with a minor compromise of energy consumption and delay.

Intelligent equipment and flexible production lines are at the cores of smart manufacturing. Meanwhile, Internet of Things and Artificial Intelligence have provided new solutions for the intelligent equipment management and maintenance in mixed model assembly (MMA). This article focuses on knowledge-driven techniques, and it proposes a knowledge sharing-enabled multirobot collaboration (KS-enabled MRC) strategy for preventive maintenance of robots in MMA. First, a formal semantic environment for MMA is constructed by way of ontology-enabled semantic modeling. Then,task-related action primitives and ontology-based robot skill bases are established according to robot capability and task environment. Finally, the Wu-Palmer similarity metric and first-order logic are leveraged to match and reason new tasks according to the semantic rules, and a knowledge sharing and update mechanism are developed for this application. Experimental results demonstrate that the proposed KS-enabled MRC can reduce unscheduled downtime and assist in achieving a load balance for robots in MMA. The studied MRC can potentially avoid severe equipment degradation, thus acting as a preventive maintenance paradigm of complex equipment. Furthermore, it is applicable across different platforms and exhibits high deployment efficiency without intense programming requirements.

In this paper, a reliable online destination prediction methodology is presented. The destination prediction methodology consists of a novel sequential complete diameter distance limited clustering method and an ensemble of random forest classifiers employing a one-vs-rest binarization strategy. Through the use of a novel OvR Uncertainty metric, predictions with high uncertainty could be withheld, thus increasing the overall reliability of the predictions made. The methodology was validated on 778 journeys from two real non-commuter vehicles based in the UK. These datasets allowed the methodology to be tested on real, yet challenging-to-predict journeys and irregular driver behavior. The sequential complete diameter distance limited clustering method was found to be a fast and effective method for sequentially clustering GPS coordinates into clusters that correspond to geographical locations. Prediction results showed that while only an overall mean prediction accuracy of 52% and 34% could be achieved on the two datasets, mean prediction accuracy could be significantly increased to over 90% and 73% respectively by only providing predictions with low uncertainty.

Industrial Internet of Things inevitably leads to the implementation of highly data-intensive devices, where the associated sensing nodes accelerate the energy consumption rate, which ultimately produces an energy bottleneck. To address this issue, this article proposes adynamic collaborative charging algorithmthat acts on both the mobile nodes and the static nodes in a sensing node network. The proposed scheme is to design a collaborative group of charging robots that can rendezvous with the sensing nodes. The group includes aerial charging vehicles (ACVs)—able to charge the underpowered mobile nodes, and terrestrial charging vehicles (TCVs), which charge their targeted static nodes. The aim of this study is to optimize the charging effect and the energy cost in the rendezvous process. This approach consists of two subalgorithms: 1) a charging algorithm for mobile nodes (CAMNs) and 2) a charging algorithm for static nodes (CASNs). The CAMNs is designed so that each underpowered mobile node can be charged by a dedicated ACV. For this purpose, a deep learning model is trained to divide the underpowered mobile nodes into appropriate clusters, each of which is equipped with a mobile base station. The rendezvous process is then constructed as a mixed continuous/discrete optimization problem, which is solved by using the firefly algorithm. In addition, the CASNs ensures that the TCVs traverse their routes, charging static nodes as they proceed. This traversing process was formulated as a multiobjective optimization problem, solved by using genetic algorithm. Through various experiments and case studies, the results have demonstrated both the feasibility and the efficiency of the proposed algorithms.

The aim of this article is to develop a methodology for measuring thedegree of unpredictabilityin dynamical systems with memory, i.e., systems with responses dependent on a history of past states. The proposed model is generic, and can be employed in a variety of settings, although its applicability here is examined in the particular context of an industrial environment: gas turbine engines. The given approach consists in approximating the probability distribution of the outputs of a system with a deep recurrent neural network; such networks are capable of exploiting the memory in the system for enhanced forecasting capability. Once the probability distribution is retrieved, theentropyormissing informationabout the underlying process is computed, which is interpreted as the uncertainty with respect to the system's behavior. Hence, the model identifies how far the system dynamics are from its typical response, in order to evaluate the system reliability and to predict system faults and/ornormal accidents. The validity of the model is verified with sensor data recorded from commissioning gas turbines, belonging to normal and faulty conditions.

The existing intelligent fault diagnosis methods of rotor-bearing system mainly focus on vibration analysis under steady operation, which has low adaptability to new scenes. In this article, a new framework for rotor-bearing system fault diagnosis under varying working conditions is proposed by using modified convolutional neural network (CNN) with transfer learning. First, infrared thermal images are collected and used to characterize the health condition of rotor-bearing system. Second, modified CNN is developed by introducing stochastic pooling and Leaky rectified linear unit to overcome the training problems in classical CNN. Finally, parameter transfer is used to enable the source modified CNN to adapt to the target domain, which solves the problem of limited available training data in the target domain. The proposed method is applied to analyze thermal images of rotor-bearing system collected under different working conditions. The results show that the proposed method outperforms other cutting edge methods in fault diagnosis of rotor-bearing system.

Permutation Entropy (PE) has been widely applied as a non-linear statistical indicator to estimate the change of complexity in time series. Though it is conceptually simple and computationally fast, PE encounters a few limitations. For example, the amplitude differences in time series are neglected, and the symbolic sequences generated from equal values are according to their emergence order. In this paper, an Edge Permutation Entropy (EdgePE) measure is proposed to improve the performance of PE, mainly overcoming its lack of ability to differentiate between amplitude differences in motifs that correspond to the same order pattern. The advantage of EdgePE relies on that amplitude change information can be identified and distinguished by the information underlying in the “edge” distance between data points in the reconstructed embedded vectors. To demonstrate its improvement, the proposed EdgePE is compared with other related improved PE approaches, for analyzing synthetic time series and experimental rolling bearing data sets, respectively. The results indicate that the EdgePE can effectively characterize amplitude changes in time series (e.g., for spike and stuck detection) and improve the accuracy of pattern recognition for rolling bearing fault diagnosis, compared to those of the other related PE measures.

In this paper, a methodology for assessing the unpredictability of systems with memory was developed. The proposed approach consists in approximating the probability distribution exhibited by the response of a system, understood as a stochastic process, with a deep recurrent neural network; such networks offer increased forecasting capability by exploiting an accumulative register of previous system states. Once the probability distribution is computed, the uncertainty or entropy of the underlying process is measured. This measure determines the degree of regularity in the system, and identifies how atypical the system dynamics are. The proposed model was validated by identifying industrial gas turbine engine faults from recorded sensor data.

Multiscale Permutation Entropy (MPE) has been applied as a non-linear measure for estimating the complexity of time series. Nevertheless, the coarse-grained procedure in MPE only takes low-frequency information into account. To overcome this shortcoming, in this paper, a new entropy measure, named Fine-to-Coarse Multiscale Permutation Entropy (F2CMPE), is proposed to provide stable and reliable results by offering both low-frequency and high-frequency information. Firstly, the F2C signals are created based on the reconstruction of selected wavelet coefficients using wavelet packet decomposition. Then, permutation entropy is used to estimate the complexity and dynamic change of the F2C signals. Experimental analysis is carried out to investigate and compare the performance of the proposed F2CMPE with that of the MPE. Results indicate that the proposed method can give consistent and stable entropy measure for rolling bearing fault diagnosis.

The aim of this paper is to estimate and monitor the human response delay in manual control tasks. A probability distribution analysis is applied on the response delay, based on experimental data collected from human subjects controlling a dynamic system and responding to visually perceived errors via joystick or steering wheel. The distribution analysis includes firstly a sliding segment method, to extract the delay time for each slice of data. Then, probability distributions of the delay time are fitted by using a bootstrap based goodness-of-fit test. For both manual-control cases, with a joystick and a steering wheel respectively, the experimental data can be explained reasonably by a Gamma distribution. Consequently, the Gamma distribution parameters for different human subjects are compared. Based on these findings, an online monitoring method of the level of attention in the human-operator - or applied workload - is proposed, which could be of interest for relevant shared-control applications.

In this paper, an off-design performance prediction model for a single shaft industrial gas turbine (IGT) using Microsoft Excel with Visual Basic for Applications (VBA) programming is presented. The modelling architecture is comprised of fundamental thermodynamic equations describing the performance of IGTs. A graphical user interface has been constructed to allow an easy interaction of the model to predict IGT performance at different operating conditions. Component characteristic maps for the compressor and turbine with a bilinear interpolation method have been implemented in the Excel modelling architecture. A commercial thermodynamic toolbox (Thermolib, EUtech Scientific Engineering GmbH) which is compatible with Simulink environment has been considered to validate Excel model of the IGT system. This Excel modelling architecture could be a valuable reference tool for engineers and students to understand IGT performance at different ambient and operating conditions.

Fault diagnosis of incipient crack failure in rotating shafts allows the detection and identification of performance degradation as early as possible in industrial plants, such as downtime and potential injury to personnel. The present work studies the performance and effectiveness of crack fault detection by means of applying wavelet packet decomposition (WPD) and empirical mode decomposition (EMD) on fault diagnosis of rotating shafts using multiscale entropy (MSE). After WPD and EMD, the most sensitive reconstruction vectors and intrinsic mode functions (IMFs) are selected using Shannon entropy. Then, these feature vectors are fed into support vector machine (SVM) for fault classification, where the entropy features represent the complexity of vibration signals with different scales. Experimental results have demonstrated that WPD combined with MSE can achieve an accuracy of 97.3% for crack fault detection in rotating shafts, whilst EMD combined with MSE has shown a higher detection rate of 98.5%.

Fault diagnosis of roller bearings in rotating machinery is of great significance to identify latent abnormalities and failures in industrial plants. This paper presents a new self-adaptive fault diagnosis system for different conditions of roller bearings using InfraRed Thermography (IRT). In the first stage of the proposed system, 2-Dimensional Discrete Wavelet Transform (2D-DWT) and Shannon entropy are applied respectively to decompose images and seek for the desired decomposition level of the approximation coefficients. After that, the histograms of selected coefficients are used as an input of the feature space selection method by using Genetic Algorithm (GA) and Nearest Neighbor (NN), for the purpose of selecting two salient features that can achieve the highest classification accuracy. The results have demonstrated that the proposed scheme can be employed effectively as an intelligent system for bearing fault diagnosis in rotating machinery.

To prove to a customer that a new or overhauled gas turbine satisfies its contractual performance, mechanical and emissions target, an acceptance test is normally performed by the manufacturer. Such acceptance tests typically involve running the turbine through its operational envelope based on a predefined test schedule, with information regarding the thermodynamic and mechanical performance as well as exhaust emission levels gathered. Decisions relating to acceptance and subsequent certification are made on the basis of agreed criteria. At present, these tests proceed in a time-consuming, sequential manner which relies heavily on manual intervention. Proposed is an automated system for acceptance testing which will directly address the aforementioned issues through improvements in efficiency and throughput. The proposed system will provide a data archive and access system which will automate data acquisition, facilitate real-time fault diagnostics and create and manage all test documentation. In this paper, an overview of the requirements for acceptance testing is presented and the principal components of an automated system for industrial gas turbine acceptance testing are identified.

The objective of this paper is to estimate the compressor discharge temperature measurements on an industrial gas turbine that is undergoing commissioning at site, using a data-driven model which is built using the test bed measurements of the engine. This paper proposes a Bayesian neuro-fuzzy modelling (BNFM) approach, which combines the adaptive neuro-fuzzy inference system (ANFIS) and variational Bayesian Gaussian mixture model (VBGMM) techniques. A data-driven compressor model is built using ANFIS, and VBGMM is applied in the set-up stage to automatically select the number of input membership functions in the fuzzy system. The efficacy of the proposed BFNM approach is established through experimental trials of a sub-15MW gas turbine, and the results, from the model that is built using test bed data, are shown to be promising for estimating the compressor discharge temperatures on the gas turbine during commissioning.

Piecewise Aggregate Approximation (PAA) provides a powerful yet computationally efficient tool for dimensionality reduction and Feature Extraction (FE) on large datasets compared to previously reported and well-used FE techniques, such as Principal Component Analysis (PCA). Nevertheless, performance can degrade as a result of either regional information insufficiency or over-segmentation, and because of this, additional relatively complex modifications have subsequently been reported, for instance, Adaptive Piecewise Constant Approximation (APCA). To recover some of the simplicity of the original PAA, whilst addressing the known problems, a distance-based Hierarchical Clustering (HC) technique is now proposed to adjust PAA segment frame sizes to focus segment density on information rich data regions. The efficacy of the resulting hybrid HC-PAA methodology is demonstrated using two application case studies viz. fault detection on industrial gas turbines and ultrasonic biometric face identification. Pattern recognition results show that the extracted features from the hybrid HC-PAA provide additional benefits with regard to both cluster separation and classification performance, compared to traditional PAA and APCA alternatives. The method is therefore demonstrated to provide a robust and readily implemented algorithm for rapid FE and identification for datasets.

An online two-dimensional changepoint detection algorithm for sensor-based fault detection is proposed. The methodology consists of a differential detector, which looks for characteristics across datasets at a particular instant, and a standard detector, which when combined can identify anomalies and meaningful changepoints while maintaining low rates of false-alarm generation. A key aspect of changepoint detection methodologies is the setting of relevant thresholds, which are typically based on empirical trial and error. Here, a statistical methodology is adopted, which provides the engineer with a tradeoff between correct detection and false-alarm rates, thereby informing decision making at the design stage. The efficacy of the techniques is demonstrated through application to two industry case studies of fault detection on industrial gas turbines, and are shown to readily provide an early warning indicator of impending failures.

This paper presents a novel methodology for modeling human lane keeping control by characterizing a unique concept of elementary steering pulses, which are motor primitives in man-vehicle systems. The novelty of the paper is the introduction of elementary steering pulses that have been evidently extracted from naturalistic driving data through machine learning techniques (data-driven modeling), and are incorporated into an alternative steering control scheme. This newly proposed hybrid-open-closed-loop control scheme starts an elementary steering pulse with an open-loop steering actuation, representing real human's reflex responses triggered by human lane keeping errors, and adjusts it back with the traditional closed-loop control. This shows a significant improvement on both the stability and the matching performance to real driving events. Online measurement of the key metrics in the steering process provides a new tool for monitoring driver states, and the biofidelic steering model may provide human-like qualities for future automated lane keeping systems. Both will add to the array of tools available for achieving autonomous and semiautonomous driving systems, which greatly benefits the current vehicle industry.

The paper presents a new system identification methodology for industrial systems. Using the original Mamdani fuzzy rule based system (FRBS), an adaptive Mamdani fuzzy modeling (AMFM) is introduced in this paper. It differs from the original Mamdani FRBS in that it applies different membership functions and a denazification mechanism that is `differentiable' with respect to the membership function parameters. The proposed system also includes a back error propagation (BEP) algorithm that is used to refine the fuzzy model. The efficacy of the proposed AMFM approach is demonstrated through the experimental trails from a compressor in an industrial gas turbine system.