We present a new study on the design of a robust control scheme for a large Pressurized Heavy Water Reactor (PHWR) which is a 70th order MIMO, coupled and open-loop unstable dynamical system. The presence of uncertainties and disturbances in such systems may lead the process to instability if the controller is unable to quickly and effectively reject these uncertainties and disturbances. However, complex, coupled and unstable dynamics of the process make it challenging to design such a robust controller with an additional capability of closely tracking reference signals. To achieve the aforementioned control objectives, we propose a novel cross-coupled conditional sliding surface based simplified fuzzy control scheme. We first consider a Single Input Fuzzy Logic Control (SI-FLC) and transform it to a partial state feedback Simplified-Sliding Fuzzy Control (S-SFC) architecture. Then, we introduce the idea of cross-coupled terms into the sliding surfaces to obtain a partial state feedback Cross-Coupled Sliding Fuzzy Control (CC-SFC). Finally, an addition of conditional-integrators to the CC-SFC results in a partial state feedback Conditional CC-SFC (CCC-SFC). To achieve an output feedback design, we introduce a MIMO High Gain Observer (HGO). A closed-loop analysis is provided in order to assure robust stability of a closed-loop system. Extensive simulations have been performed which show that the HGO-based CCC-SFC causes the output trajectories of PHWR to closely follow the reference signals, whilst effectively rejecting the process uncertainties and disturbances.

The problem of observer design using a dynamic event-triggered signals is studied for estimating the states and faults simultaneously of descriptor systems with disturbances. The system is first transformed into a structure that is convenient to analyse. A DETM is implemented to reduce the number of transmissions from the system to the observers. The first observer is designed to produce an initial estimate of the states. Signals from this observer are then fed into a sliding mode observer, which estimates the fault as well as the estimation error of the first observer. The estimated errors are used to improve the state estimates from the first observer. Linear matrix inequalities are used to design both observers such that the L2 gain from the disturbances to the state and fault estimation errors are minimised. Finally, a simulation example is utilised to showcase the performance of the proposed scheme.

Despite the development of numerous soft grippers designed to handle deformable objects, hardness sensing remains a challenge, yet it is essential for various applications such as product selection or sorting, assessing fruit ripeness, or food quality control. This research introduces GripDepthSense3DNet, an innovative approach integrating 3D depth sensing with machine learning for accurate hardness sensing during grasping. Leveraging a dataset comprising of depth images of diverse objects undergoing deformation, the proposed novel network is trained to capture intricate spatial-temporal deformation features from a series of depth images. GripDepthSense3DNet outperforms state-of-the-art networks, exhibiting a commendable mean absolute percentage error of 0.46% for trained shapes and hardness. Specifically, the model achieves a reduction in parameters of approximately 94.8% compared to ResNet-50, with a training time that is around 92.9% shorter on equivalent hardware. Different depth ranges and intervals were studied to eventually arrive at an optimal configuration. Through dynamic tuning, the network's ability to seamlessly incorporate new shapes, new hardness, and even intricate arbitrary objects highlights the adaptability of the approach.

To develop applications for assisting Parkinson’s disease (PD) patients, extracting Parkinsonian tremors from the raw signal is crucial; however, conventional methods such as filtering require a preset frequency range, and a poorly set frequency range may lead to the inclusion of undesired signals. AI algorithms can potentially overcome the heterogenous tremor characteristics in different patients, but they have been applied in the disease or tremor type classification rather than in tremulous-voluntary motion classification. Hence, this study presents an approach to automatically differentiate between voluntary and tremulous motions in PD patients, achieved by combining ensemble empirical mode decomposition (EEMD) and convolutional bi-directional long short-term memory (LSTM). Non-labelled raw hand-arm orientation data collected from PD patients was decomposed into sub-signals via EEMD to replace the conventional filtering techniques. A convolutional layer automatically extracted key features from these sub-signals to train the deep learning classifier, eliminating the need for manual feature engineering. The proposed method can be generalized to identify tremors from motion signals obtained during daily activities without pre-identified features. The proposed approach accurately extracted Parkinsonian tremors from raw signals across various activities, achieving low root-mean-square error and 94.2 ± 1.1% accuracy in differentiating voluntary and tremulous motions in PD patients.

Higher-order sensor networks are more accurate in characterizing the nonlinear dynamics of sensory time-series data in modern industrial settings by allowing multi-node connections beyond simple pairwise graph edges. In light of this, we propose a deep spatio-temporal hypergraph convolutional neural network for soft sensing (ST-HCSS). In particular, our proposed framework is able to construct and leverage a higher-order graph (hypergraph) to model the complex multi-interactions between sensor nodes in the absence of prior structural knowledge. To capture rich spatio-temporal relationships underlying sensor data, our proposed ST-HCSS incorporates stacked gated temporal and hypergraph convolution layers to effectively aggregate and update hypergraph information across time and nodes. Our results validate the superiority of ST-HCSS compared to existing state-of-the-art soft sensors, and demonstrates that the learned hypergraph feature representations aligns well with the sensor data correlations. The code is available at https://github.com/htew0001/ST-HCSS.git

Accurate prediction of Parkinson’s disease tremor (PDT) is crucial for developing assistive technologies; however, this is challenging due to the nonlinear, stochastic, and nonstationary characteristics of PDT, which substantially vary among patients and their activities. Moreover, most models only have one-step prediction capabilities, which causes delays in real-time applications. This paper proposes a self-attention deep temporal convolutional network (SADTCN) model for the real-time prediction of hand-arm PDT signals from different activities and joint angular motions. The SADTCN can capture both short- and long-term dependencies and complex temporal and spatial dynamics of PDT signals and hence, can effectively adapt to varying tremor characteristics. The performance of the proposed model is evaluated using experimental hand-arm PDT data. The results show that the SADTCN outperforms existing deep learning (DL) models by accurately predicting varying tremor amplitudes and frequencies multi-step ahead. Moreover, we performed spectrum analysis on the measured and predicted signal using the short-time Fourier transform (STFT) as a measure of potential active tremor control and found that SADTCN can accurately determine the transience of tremor amplitude in frequency and time. Finally, we run the Wilcoxon signed-rank statistical test and the results show a statistically significant improvement in the proposed model over the other DL models in all conditions. Therefore, the SADTCN can overcome the nonstationary, nonlinear, and stochastic nature of PDT to perform multi-step prediction with high accuracy, robustness, and generalizability in unseen testing data.

This brief presents a novel active fault-tolerant control (FTC) scheme for an unstable three-degree-of-freedom (3-DOF) helicopter subject to motor faults. The helicopter is instrumented only with angular position sensors and has no independent velocity sensors, which makes its FTC design more challenging. Although some works have developed FTC for helicopters using only angular information, they required stringent assumptions on the system. To circumvent this problem, a reduced-order sliding mode observer (SMO) is first introduced to obtain auxiliary signals, which become the outputs of an analytical system. Next, an interval observer (IO) is designed for the analytical system, and a fault-tolerant controller is established, and their parameters are jointly optimized to ensure that the helicopter performs at an acceptable level, whether there is a fault or not. The IOs use adaptive parameters, which provide tighter bounds, resulting in more accurate estimation of faults. Finally, simulations and experiments on a 3-DOF helicopter platform are conducted to demonstrate the efficacy of our proposed scheme.

Unmanned aerial vehicle (UAV) networks, which carry vital information, are prone to various attacks, and hence security issues are a major concern. In this paper, we design and implement a novel covert attack detection and secure control scheme, which operates between the UAV (the physical layer) and ground control station (GCS) (the cyber layer). Covert attacks can alter the UAV states, and yet cause the signals seen by the controller to appear unchanged, resulting in these attacks being more difficult to detect, and hence more dangerous compared to other types of attacks. To unmask the covert attacks, we construct and inject auxiliary signals to both the controller output and the UAV input. The auxiliary signals cause information of the attack to appear in the controller input, which is then fed to a detection observer to detect the attack. Next, we propose an integrated estimation and secure control scheme, comprising a reconstruction observer (which is a sliding mode observer (SMO)) that estimates the system states and attack signal, and an output-feedback controller that utilizes the estimated signals. We perform a series of transformations to the system, such that the design parameters of both reconstruction observer and secure controller are placed in a framework that is solvable using Linear Matrix Inequalities (LMIs). We also prove that the proposed integrated secure controller causes the output tracking errors to satisfy an H(infinity )performance index. We also rigorously analyze the system performance, and present the necessary conditions for the scheme to be feasible. Finally, simulations are conducted to verify the effectiveness of the proposed scheme.

Soft sensing of hard-to-measure variables is often crucial in industrial processes. Current practices rely heavily on conventional modeling techniques that show success in improving accuracy. However, they overlook the non-linear nature, dynamics characteristics, and non-Euclidean dependencies between complex process variables. To tackle these challenges, we present a framework known as a Knowledge discovery graph Attention Network for effective Soft sensing (KANS). Unlike the existing deep learning soft sensor models, KANS can discover the intrinsic correlations and irregular relationships between the multivariate industrial processes without a predefined topology. First, an unsupervised graph structure learning method is introduced, incorporating the cosine similarity between different sensor embedding to capture the correlations between sensors. Next, we present a graph attention-based representation learning that can compute the multivariate data parallelly to enhance the model in learning complex sensor nodes and edges. To fully explore KANS, knowledge discovery analysis has also been conducted to demonstrate the interpretability of the model. Experimental results demonstrate that KANS significantly outperforms all the baselines and state-of-the-art methods in soft sensing performance. Furthermore, the analysis shows that KANS can find sensors closely related to different process variables without domain knowledge, significantly improving soft sensing accuracy.

The tremors of Parkinson's disease (PD) and essential tremor (ET) are known to have overlapping characteristics that make it complicated for clinicians to distinguish them. While deep learning is robust in detecting features unnoticeable to humans, an opaque trained model is impractical in clinical scenarios as coincidental correlations in the training data may be used by the model to make classifications, which may result in misdiagnosis. This work aims to overcome the aforementioned challenge of deep learning models by introducing a multilayer BiLSTM network with explainable AI (XAI) that can better explain tremulous characteristics and quantify the respective discovered important regions in tremor differentiation. The proposed network classifies PD, ET, and normal tremors during drinking actions and derives the contribution from tremor characteristics, (i.e., time, frequency, amplitude, and actions) utilized in the classification task. The analysis shows that the XAI-BiLSTM marks the regions with high tremor amplitude as important in classification, which is verified by a high correlation between relevance distribution and tremor displacement amplitude. The XAI-BiLSTM discovered that the transition phases from arm resting to lifting (during the drinking cycle) is the most important action to classify tremors. Additionally, the XAI-BiLSTM reveals frequency ranges that only contribute to the classification of one tremor class, which may be the potential distinctive feature to overcome the overlapping frequencies problem. By revealing critical timing and frequency patterns unique to PD and ET tremors, this proposed XAI-BiLSTM model enables clinicians to make more informed classifications, potentially reducing misclassification rates and improving treatment outcomes.

Most works on joint state and unknown input (UI) estimation require the assumption that the UIs are linear; this is potentially restrictive as it does not hold in many intelligent autonomous systems. To overcome this restriction and circumvent the need to linearize the system, we propose a derivative-free Unknown Input Sigma-point Kalman Filter (SPKF-nUI) where the SPKF is interconnected with a general nonlinear UI estimator that can be implemented via nonlinear optimization and data-driven approaches. The nonlinear UI estimator uses the posterior state estimate which is less susceptible to state prediction error. In addition, we introduce a joint sigma-point transformation scheme to incorporate both the state and UI uncertainties in the estimation of SPKF-nUI. An in-depth stochastic stability analysis proves that the proposed SPKF-nUI yields exponentially converging estimation error bounds under reasonable assumptions. Finally, two case studies are carried out on a simulation-based rigid robot and a physical soft robot, i.e., robots made of soft materials with complex dynamics to validate effectiveness of the proposed filter on nonlinear dynamic systems. Our results demonstrate that the proposed SPKF-nUI achieves the lowest state and UI estimation errors when compared to the existing nonlinear state-UI filters.

A practical and reliable online vehicle mass estimation scheme is crucial to effectively control an automated and intelligent vehicle. The Recursive Least Squares with Multiple Forgetting Factors (RLSMFF) algorithm has been shown to demonstrate great accuracy and computational efficiency in estimating vehicle mass. Nevertheless, our analysis on the convexity and convergence of the RLSMFF algorithm revealed significant inaccuracies at low sampling rates, as well as an estimation bias when the initial estimate is poor. Thus, the RLSMFF needs high-frequency data and an accurate initial estimate (both which could be challenging to obtain) to generate an accurate estimate. Additionally, the robustness of the RLSMFF algorithm to impulsive disturbances (such as braking, which is a common and inevitable driving maneuver) remains a challenge. To address the aforementioned issues, this article proposes a robust Recursive Least M-Squares with Multiple Forgetting Factors (RLM-SMFF) algorithm for reliable vehicle mass estimation in the presence of impulsive disturbance. In particular, a restructured longitudinal dynamics model and a bias reduction strategy are introduced to enhance the accuracy of the mass estimation even when the sampling rate is low. An M-estimator is incorporated to suppress the effects of the impulsive disturbance. The stability of our proposed algorithm is also verified mathematically. We evaluated our proposed algorithm using extensive simulations, which showed that our method demonstrates superior accuracy compared to existing mass estimation algorithms, at low computational demand.

With the advancements of sensor hardware, traffic infrastructure and deep learning architectures, trajectory prediction of vehicles has established a solid foundation in intelligent transportation systems. However, existing solutions are often tailored to specific traffic networks at particular time periods. Consequently, deep learning models trained on one network may struggle to generalize effectively to unseen networks. To address this, we proposed a novel spatial-temporal trajectory prediction framework that performs cross-domain adaption on the attention representation of a Transformer-based model. A graph convolutional network is also integrated to construct dynamic graph feature embeddings that accurately model the complex spatial-temporal interactions between the multi-agent vehicles across multiple traffic domains. The proposed framework is validated on two case studies involving the cross-city and cross-period settings. Experimental results show that our proposed framework achieves superior trajectory prediction and domain adaptation performances over the state-of-the-art models.

In this paper, an output feedback-based active fault tolerant control (FTC) scheme is proposed for an unstable three degree-of-freedom (3-DOF) helicopter equipped only with angular position sensors, of which a single sensor can be faulty. Limited by the available outputs, existing fault estimation (FE) and FTC schemes cannot be applied to this helicopter because when the sensor measuring the elevation or travel angle is faulty, it does not satisfy the minimum-phase and matching conditions required by standard observers. To circumvent this problem, an adaptive interval observer is firstly designed as a fault detection and isolation (FDI) unit to indicate the occurrence and location of a fault, in contrast to the existing FDI methods that require a bank of observers and incur a high computational cost. Then a high-gain observer is combined with a sliding mode observer to form an FE unit that does not require the matching and minimum-phase conditions. Based on the estimate of the fault, an FTC scheme is constructed to ensure an $\mathcal{H}_{\infty}$ performance of the faulty system. Finally, physical experiments on the 3-DOF helicopter verify the effectiveness of the proposed scheme. Note to Practitioners —The 3-DOF lab helicopter serves as an ideal experimental platform for control strategies. In this paper, an active fault tolerant control (FTC) scheme is developed for a 3-DOF lab helicopter when any single sensor can be faulty. The helicopter is nonlinear and subject to external disturbances. There are only encoders measuring the attitude angles and no sensors for angular velocities. In this paper, we firstly design a fault detection and isolation (FDI) unit based on an adaptive interval observer to detect the fault and identify its location; it incurs a lower computational cost compared to existing methods that use a bank of observers. Then a high-gain observer is combined with a sliding mode observer to estimate the fault. Based on the estimate of the fault, an FTC scheme is constructed and designed using Linear Matrix Inequalities to ensure an $\mathcal{H}_{\infty}$ performance of the faulty system.

Transport equity, which emphasises fair and equitable distribution to reach various significant activities and opportunities such as work and healthcare, has greatly interested researchers and practitioners. Enhancing first-mile and last-mile travel and commuting experiences augment an individual's travel satisfaction. However, challenges with first-mile and last-mile travel lead to social exclusion and inequity concerns in accessing services and a reduction in the utilisation of public transport. There is limited insight regarding commuters' experiences and challenges in this context, particularly in developing countries. This dearth of knowledge makes it difficult to implement measures to enhance connectivity and accessibility. Thus, we investigate the first-mile and last-mile experiences and challenges of commuters in Ghana using qualitative and quantitative data from semi-structured interviews and questionnaire survey, which are rare in this subject's study. The analysis through the logit model showed that commuters with increasing distances for the first and last miles have difficulty with transport accessibility. The results showed that demographic factors like age and gender did not significantly affect first-mile and last-mile accessibility, suggesting that the challenges are experienced across different groups. The thematic analysis revealed five essential themes: (i) cost, (ii) limited accessibility, (iii) safety, long walking distances and (v) temporal factors like weather as challenges commuters encounter with their first-mile and last-mile trips. This research contributes to the extant literature on the experiences and challenges of first-mile and last-mile commutes. It provides depth to the literature by offering perspectives from a developing country. It also holds practical significance for transport authorities and government departments and agencies.

Soft sensors are widely used in many industrial systems to monitor key variables that are difficult to measure, using measurements from other available physical sensors. Because physical sensors are susceptible to faults, it is crucial for soft sensor models to be robust against them. Recently, deep learning has shown promising results in developing data-driven soft sensors for various applications. However, existing learning-based soft sensors are still vulnerable to sensor faults, which could deteriorate the performance of the models. In this article, we propose a deep learning-based modeling framework for developing soft sensor models that are robust to sensor faults. Due to the difficulty in obtaining datasets that cover all possible sensor fault characteristics, the proposed framework is developed to be zero-shot such that the model can be trained with only fault-free dataset without requiring any sensor fault patterns, thus greatly saving the time and resources needed to collect such data. Instead, adversarial examples are used as a proxy for faulty sensor inputs so that the model can learn to be adaptive through the proposed two-stage, uncertainty-aware recurrent neural network architecture. We demonstrate our approach to the TE benchmark process and a real industrial multiphase flow process and show that robustness is achieved as the accuracy does not degrade significantly when sensor faults are present during the model evaluation.

In industrial robots, a performance issue is backlash, which is the clearance between mating gears of its joints. Over time, backlash grows through wear and tear, causing inaccuracies in robot positioning. Current methods in backlash detection are performed in low-speed and laboratory settings, or require offline diagnostics. These methods are impractical in actual manufacturing environments, where industrial robots operate continuously at high speeds. Other methods require additional sensors unavailable in typical industrial robots. In this article, we present an online method to quantify backlash and predict the remaining useful life (RUL) in an industrial robot performing cyclic production tasks, using only standard available sensors. To achieve the robot's target position, the input torque oscillates; these oscillations grow as the backlash becomes more severe. We modeled the oscillations as an unknown input, and used an unknown input observer to estimate them and detect/quantify the backlash. Then, a health indicator (HI) is plotted over time and a failure threshold is set based on historical data. Finally, an exponential degradation model is used to predict the RUL of the robot joint. The UIO successfully detected and quantified the backlash through the HI. The degradation model gave a good estimate of the RUL with an accuracy of 20 days after 250 days of operation.

—Data-driven soft sensors are essential for achieving accurate perception through reliable state inference. However, developing representative soft sensor models is challenged by issues such as missing labels, domain adaptability, and temporal coherence in data. To address these challenges, we propose a deep Particle Flow Bayes (DPFB) framework for cross-domain soft sensor modeling in the absence of target state labels. In particular, a sequential Bayes objective is first formulated to perform the maximum likelihood estimation underlying the cross- domain soft sensing problem. At the core of the framework, we incorporate a physics-inspired particle flow that optimizes the sequential Bayes objective to perform an exact Bayes update of the model extracted latent and hidden features. As a result, these contributions enable the proposed framework to learn a cohesive approximate posterior feature representation capable of characterizing complex cross-domain system dynamics and performing effective time series unsupervised domain adaptation (UDA). Finally, we validate the framework on a complex industrial multiphase flow process system with complex dynamics and multiple operating conditions. The results demonstrate that the DPFB framework achieves superior unsupervised cross-domain soft sensing performance, outperforming state-of-the-art deep UDA and normalizing flow approaches.

The integration of solar power generation using photovoltaic (PV) panels and increasing energy consumption has resulted in rapid voltage fluctuations in the distribution network. During peak demand and peak sun hours, the voltage fluctuation increases rapidly. These voltage deviations can cause undervoltage or overvoltage in the power grid, which are conventionally tackled using On-Load Tap-Changers (OLTCs). However, OLTCs have a slow response and causes frequent voltage instability, which affects the electrical power quality. Moreover, it can damage electrical equipment connected to the network and impose risk on service personnel. In conventional method, the tap changer of OLTC controls the voltage; however, in game theory method, an algorithm based on internal game theory is incorporated into the tap changer of OLTC to improve the voltage regulation. A 74-bus network is modelled in MATLAB to study the effectiveness of the two methods in regulating voltage during peak hours. In comparison to conventional method, game theory method decreased occurrence of voltage instability by an average of 69.4% and 61.6% during peak demand hour and peak sun hours respectively. Furthermore, it achieved a faster response by an average of 50% during peak demand hours and an average of 62.2% during peak sun hours.

Circadian misalignment is experienced by travelers, shift workers, and people with irregular sleep patterns. Circadian misalignment leads to lower cognitive alertness and increases the risk of poor health outcomes. Since the circadian system is highly responsive to light, circadian rhythms can be realigned using lighting interventions in a built environment. However, inter-individual differences pose an unsolved problem in the implementation of such lighting interventions, particularly for individuals in a shared living space. Here, we present a novel method to converge on schedules of light exposure that can align the circadian rhythms of a group of individuals with different intrinsic circadian periods, within an optimal time. We used an experimentally validated limit-cycle oscillator model of the human circadian system to set a target in the phase and amplitude of the circadian oscillator. An iterative process then changes the switching times of a light/dark bang-bang input to minimize the difference in circadian amplitude and phase to arrive at the target. The proposed method successfully generated schedules of light exposures that optimized the time required for re-entrainment of multiple individuals with circadian phase shifts up to 12 h advance or delay. This method offers a novel solution to improve circadian entrainment under the practical constraint of multiple individuals in a shared living space.