Online Adaptation Research Articles

Research on the application of personalized recommendation

With the development of the Internet, people have more opportunities to be exposed to personalized recommendations, and the heat of related topics has increased. The purpose of this paper is to summarize the application principle and use of personalized recommendations by analyzing the relevant data, so that people can have a better understanding of personalized recommendations and make preparations for future related research. This paper first introduces the general development context of the personalized recommendation system and its uniqueness. The analysis finds that personalized recommendations can provide users with the most relevant and valuable information, goods, or services according to their interests, preferences, and behaviors. Secondly, this paper explores the application scenarios of personalized recommendation systems in different fields, including but not limited to video content, e-commerce, and online learning. In addition, this paper also lists the application of YouTube and Netflix in video content recommendation, as well as personalized recommendation services in e-commerce and online learning platforms. In particular, the rise of intelligent adaptive online learning systems and their adaptability in the field of education and training are analyzed in detail. Through this research, it can be found that a personalized recommendation system is very beneficial to people's production and life, but at present, personalized recommendation is still in the development stage, and there are many problems to be solved.

Exploring online social platform affordances for digital creators: a multi-method approach using qualitative and configurational analysis

PurposeThis study explores the key platform affordances that online social platform providers need to offer digital creators to strengthen the creator ecosystem, one of the leading accelerators for platform growth. Specifically, it aims to investigate how these affordances make the dynamic combinations for high platform quality across diverse platform types and demographic characteristics of digital creators.Design/methodology/approachThis study adopts a multi-method approach. Drawing upon the affordance theory, Study 1 aims to identify the key affordances of online social platforms based on relevant literature and the qualitative interview data collected from 22 digital creators, thereby constructing a conceptual framework of key platform affordances for digital creators. Building on the findings of Study 1, Study 2 explores the dynamic combinations of these platform affordances that contribute to platform quality using a configurational approach. Data from online surveys of 185 digital creators were analyzed using fuzzy set qualitative comparative analysis (fsQCA).FindingsThe results of Study 1 identified key online social platform affordances for digital creators, including Storytelling, Socialization, Design, Development, Promotion, and Protection affordance. Study 2 showed that the combinations of these platform affordances for digital creators are diverse according to the types of platforms, creators’ gender, and their professionality.Research limitations/implicationsLike many studies, this research also has several limitations. One limitation of the research is the potential constraint of the extent of how well the data samples represent the group of creators who are actively producing digital content. Despite the addition of screening questions and meticulous data filtering, it is possible that we did not secure sufficient data from creators who are actively engaged in creative activities. In future research, it is worth contemplating the acquisition of data from actual groups of creators, such as creator communities. Future researchers anticipate obtaining more in-depth and accurate data by directly involving and collaborating with creators.Practical implicationsThis study highlights the need for online social platforms to enhance features for storytelling, socializing, design, development, promotion, and protection, fostering a robust digital creator ecosystem. It emphasizes clear communication of these affordances, ensuring creators can effectively utilize them. Importantly, platforms should adapt these features to accommodate diverse creator profiles, considering differences in gender and expertise levels, especially in emerging spaces like the Metaverse. This approach ensures an equitable and enriching experience for all users and creators, underlining the importance of dynamic interaction and inclusivity in platform development and creator support strategies.Social implicationsThis study underscores the social implications of evolving digital creator ecosystems on online platforms. Identifying six key affordances essential for digital creators highlights the need for platforms to enhance storytelling, socializing, design, development, promotion, and product protection. Crucially, it emphasizes inclusivity, urging platforms to consider diverse creator profiles, including gender and expertise differences, particularly in transitioning from traditional social media to the Metaverse. This approach nurtures a more robust creator ecosystem and fosters an equitable and enriching experience for all users. It signals a shift towards more dynamic, adaptive online environments catering to diverse creators and audiences.Originality/valueFor academics, this study builds the conceptual framework of online social platform affordances for digital creators. Using the configurational approach, this study identified various interdependent relationships among the affordances, which are nuanced by specific contexts, and suggested novel insights for future studies. For practices, the findings specified by creators and platform types are expected to guide platform providers in developing strategies to support digital creators and contribute to platform growth.

Technical feasibility of novel immunostimulatory low-dose radiation for polymetastatic disease with CBCT-based online adaptive and conventional approaches.

A workflow/planning strategy delivering low-dose radiation therapy (LDRT) (1Gy) to all polymetastatic diseases using conventional planning/delivery (Raystation/Halcyon="conventional") and the AI-based Ethos online adaptive RT (oART) platform is developed/evaluated. Using retrospective data for ten polymetastatic non-small cell lung cancer patients (5-52 lesions each) with PET/CTs, gross tumor volumes (GTVs) were delineated using PET standardized-uptake-value (SUV) thresholding. A 1cm uniform expansion of GTVs to account for setup/contour uncertainty and organ motion-generated planning target volumes (PTVs). Dose optimization/calculation used the diagnostic CT from PET/CT. Dosimetric objectives were: Dmin,0.03cc ≥ 95% (acceptable variation (Δ) ≥ 90%), V100% ≥ 95% (Δ ≥ 90%), and D0.03cc ≤ 120% (Δ ≤ 125%). Additionally, online adaptation was simulated. When available, subsequent diagnostic CT was used to represent on-treatment CBCT. Otherwise, the CT from PET/CT used for initial planning was deformed to simulate clinically representative changes. All initial plans generated, both for Raystation and Ethos, achieved clinical goals within acceptable variation. For all patients, Dmin,0.03cc ≥ 95%, V100% ≥ 95%, and D0.03cc ≤ 120% goals were achieved for 84.8%/99.5%, 97.7%/98.7%, 97.4%/92.3%, in conventional/Ethos plans, respectively. The ratio of 50% isodose volume to PTV volume (R50%), maximum dose at 2cm from PTV (D2cm), and the ratio of the 100% isodose volume to PTV volume (conformity index) in Raystation/Ethos plans were 7.9/5.9; 102.3%/88.44%; and 0.99/1.01, respectively. In Ethos, online adapted plans maintained PTV coverage whereas scheduled plans often resulted in geographic misses due to changes in tumor size, patient position, and body habitus. The average total duration of the oART workflow was 26:15 (min:sec) ranging from 6:43 to 57:30. The duration of each oART workflow step as a function of a number of targets showed a low correlation coefficient for influencer generation and editing (R2=0.04 and 0.02, respectively) and high correlation coefficient for target generation, target editing and plan generation (R2=0.68, 0.63 and 0.69, respectively). This study demonstrates feasibility of conventional planning/treatment with Raystation/Halcyon and highlights efficiency gains when utilizing semi-automated planning/online-adaptive treatment with Ethos for immunostimulatory LDRT conformally delivered to all sites of polymetastatic disease.

Efficient derivation of optimal signal schedules for multimodal intersections

Tramways decrease time, cost, and environmental impact of urban transport, while requiring multimodal intersections where trams arriving with nominal periodic timetables may have right of way over road vehicles. Quantitative evaluation of stochastic models enables early exploration and online adaptation of design choices, identifying operational parameters that mitigate impact on road transport performance.We present an efficient analytical approach for offline scheduling of traffic signals at multimodal intersections among road traffic flows and tram lines with right of way, minimizing the maximum expected percentage of queued vehicles of each flow with respect to sequence and duration of phases. To this end, we compute the expected queue size over time of each vehicle flow through a compositional approach, decoupling analyses of tram and road traffic. On the one hand, we define microscopic models of tram traffic, capturing periodic tram departures, bounded delays, and travel times with general (i.e., non-Exponential) distribution with bounded support, open to represent arrival and travel processes estimated from operational data. On the other hand, we define macroscopic models of road transport flows as finite-capacity vacation queues, with general vacation times determined by the transient probability that the intersection is available for vehicles, efficiently evaluating the exact expected queue size over time. We show that the distribution of the expected queue size of each flow at multiples of the hyperperiod, resulting from temporization of nominal tram arrivals and vehicle traffic signals, reaches a steady state within few hyper-periods. Therefore, transient analysis starting from this steady-state distribution and lasting for the hyper-period duration turns out to be sufficient to characterize road transport behavior over time intervals of arbitrary duration.We implemented the proposed approach in the novel OMNIBUS Java library, and we compared against Simulation of Urban MObility (SUMO). Experimental results on case studies of real complexity with time-varying parameters show the approach effectiveness at identifying optimal traffic signal schedules, notably exploring in few minutes hundreds of schedules requiring tens of hours in SUMO.

Dosimetric benefit of online treatment plan adaptation in stereotactic ultrahypofractionated MR-guided radiotherapy for localized prostate cancer.

Apart from superior soft tissue contrast, MR-guided stereotactic body radiation therapy (SBRT) offers the chance for daily online plan adaptation. This study reports on the comparison of dose parameters before and after online plan adaptation in MR-guided SBRT of localized prostate cancer. 32 consecutive patients treated with ultrahypofractionated SBRT for localized prostate cancer within the prospective SMILE trial underwent a planning process for MR-guided radiotherapy with 37.5 Gy applied in 5 fractions. A base plan, derived from MRI simulation at an MRIdian Linac, was registered to daily MRI scans (predicted plan). Following target and OAR recontouring, the plan was reoptimized based on the daily anatomy (adapted plan). CTV and PTV coverage and doses at OAR were compared between predicted and adapted plans using linear mixed regression models. In 152 out of 160 fractions (95%), an adapted radiation plan was delivered. Mean CTV and PTV coverage increased by 1.4% and 4.5% after adaptation. 18% vs. 95% of the plans had a PTV coverage ≥95% before and after online adaptation, respectively. 78% vs. 100% of the plans had a CTV coverage ≥98% before and after online adaptation, respectively. The D0.2cc for both bladder and rectum were <38.5 Gy in 93% vs. 100% before and after online adaptation. The constraint at the urethra with a dose of <37.5 Gy was achieved in 59% vs. 93% before and after online adaptation. Online adaptive plan adaptation improves target volume coverage and reduces doses to OAR in MR-guided SBRT of localized prostate cancer. Online plan adaptation could potentially further reduce acute and long-term side effects and improve local failure rates in MR-guided SBRT of localized prostate cancer.

Ensemble adaptive online machine learning in data stream: a case study in cyber intrusion detection system

Ensemble adaptive online machine learning in data stream: a case study in cyber intrusion detection system

Design of a novel neuro‐adaptive excitation control system for power systems

AbstractThis manuscript proposes a robust excitation control strategy for synchronous generators using backstepping theory and an artificial neural network with a radial basis function to improve power system performance during disturbances and parametric uncertainties. The artificial neural network is used to estimate unmeasurable quantities and unknown internal parameters of a recursive backstepping control. Lyapunov theory is used to carry out the stability analysis and to deduce the online adaptation laws of artificial neural network parameters (weights, centres and widths). To validate the performance of this approach, simulations are performed on an IEEE 9 bus multi‐machine power system. Different test results, compared with those of an existing non‐linear adaptive controller, confirm the high robustness of the proposed method against disturbances and uncertainties.

COVID-19 Increased Mortality Salience, Collectivism, and Subsistence Activities: A Theory-Driven Analysis of Online Adaptation in the United States, Indonesia, Mexico, and Japan

How does a life-threatening pandemic affect a culture? The Theory of Social Change, Cultural Evolution, and Human Development predicts that danger, as indicated by rising death rates and narrowing social worlds, shifts human psychology and behavior toward that found in small-scale, collectivistic, and rural subsistence ecologies. In particular, mortality salience, collectivism, and engagement in subsistence activities should increase as death rates rise and the social world retracts. Studies on the psychological response to the pandemic in the United States confirmed these predicted increases. The present study sought to generalize these previous findings by comparing the frequency of conceptually relevant linguistic terms used in Google searches and Twitter posts in the United States, Japan, Indonesia, and Mexico for 30 days before the coronavirus pandemic began in each country with frequencies of the same terms for 30 days after. Generally, we found that mortality salience increased to the extent that countries experienced excess COVID mortality; collectivism increased to the extent that countries experienced excess COVID mortality and increased mortality salience; and subsistence activities increased to the extent that countries experienced excess COVID mortality and/or stay-at-home-policies. Almost all these increases went beyond the general increase in internet use, which was a control variable in all analyses. These findings support a growing body of research documenting a human response to ecological danger.

Social Evaluation in Emerging Adults: Associations with Interpretation Bias and Perceived Social Support.

Social anxiety symptoms are one of the most common mental health concerns across the lifespan (Bandelow and Michaelis in Dialogues Clin Neurosci 17(3):327-335, 2015. https://doi.org/10.31887/DCNS.2015.17.3/bbandelow ) and are especially relevant during emerging adulthood, when social feedback occurs daily (Auxier and Anderson in Social media use in 2021, 2021. https://www.pewresearch.org/internet/2021/04/07/social-media-use-in-2021/ ) as emerging adults navigate new social environments. Two cognitive processes have been identified as relevant to social anxiety: high threat interpretation bias (i.e., the tendency to appraise threat from ambiguity; Rozenman et al. in Behav Ther 45(5):594-605, 2014. https://doi.org/10.1016/j.beth.2014.03.009 ; J Anxiety Disord 45:34-42, 2017. https://doi.org/10.1016/j.janxdis.2016.11.004 ) is associated with high social anxiety, whereas high perceived social support is associated with low social anxiety. In this study, emerging adults (N = 303) completed an online adaptation of the Chatroom task (Guyer et al. in Arch Gener Psychiatry 65(11):1303-1312, 2008. https://doi.org/10.1001/archpsyc.65.11.1303 ), an experimental paradigm designed to simulate social acceptance and rejection, as well as a performance-based measure of interpretation bias (Word Sentence Association Paradigm; Beard and Amir in Behav Res Ther 46(10):1135-1141, 2008. https://doi.org/10.1016/j.brat.2008.05.012 ), and a self-report measure of perceived social support (Multidimensional Scale of Perceived Social Support; Zimet et al. in J Pers Assess 52(1), 30-41, 1988. https://doi.org/10.1207/s15327752jpa5201_2 ). Social anxiety symptoms did not increase as a function of acceptance or rejection during the Chatroom task. However, there were significant interactions between each cognitive predictor and social anxiety change: emerging adults with low interpretation bias towards threat and emerging adults with high perceived social support both experienced decreases in social anxiety from pre- to post-Chatroom task, regardless of whether they were accepted or rejected during the Chatroom task. If replicated, low interpretation bias and high perceived social support may serve as promotive factors in social interactions for emerging adults.

Stabilization control of rotary inverted pendulum using a novel EKF-based fuzzy adaptive sliding-mode controller: design and experimental validation

This article methodically develops an improved self-regulating fuzzy-adaptive Sliding Mode Controller (SMC) that strengthens the disturbance compensation capacity of the nonlinear rotary pendulum systems while effectively attenuating the chattering content and curbing the control energy consumption. The article contributes to augmenting the SMC with online adaptation tools to achieve the said objectives. It employs the conventional Gao’s power-rate reaching law as the baseline. The scaling gain and the power rate of the said reaching law are adaptively modulated via a pre-calibrated two-input state-error-driven fuzzy nonlinear function. Additionally, the sign function in the law is also replaced with an odd-symmetric nonlinear fuzzy function to address the hard limits imposed by the former. Finally, the membership functions of the fuzzy function are self-regulated using the Extended-Kalman-Filter to improve the compensator’s adaptability in handling the system’s rapidly changing control requirements under exogenous disturbances. The aforementioned propositions are verified by performing customized and reliable hardware-in-loop experiments on the Quanser single-link rotary pendulum platform. As compared to baseline SMC law, the proposed control procedure contributes a ∼45.2%, ∼48.5%, and ∼34.8% reduction in position-regulation errors, control energy consumption, and peak overshoots, respectively. The experimental assessment validates the proposed control system’s enhanced robustness and chattering-suppression capability.

Adaptive Online Learning and Robust 3-D Shape Servoing of Continuum and Soft Robots in Unstructured Environments.

In this article, we present a novel and generic data-driven method to servo-control the 3-D shape of continuum and soft robots based on proprioceptive sensing feedback. Developments of 3-D shape perception and control technologies are crucial for continuum and soft robots to perform tasks autonomously in surgical interventions. However, owing to the nonlinear properties of continuum robots, one main difficulty lies in the modeling of them, especially for soft robots with variable stiffness. To address this problem, we propose a versatile learning-based adaptive shape controller by leveraging proprioception of 3-D configuration from fiber Bragg grating (FBG) sensors, which can online estimate the unknown model of continuum robot against unexpected disturbances and exhibit an adaptive behavior to the unmodeled system without priori data exploration. Based on a new composite adaptation algorithm, the asymptotic convergences of the closed-loop system with learning parameters have been proven by Lyapunov theory. To validate the proposed method, we present a comprehensive experimental study using two continuum and soft robots both integrated with multicore FBGs, including a robotic-assisted colonoscope and multisection extensible soft manipulators. The results demonstrate the feasibility, adaptability, and superiority of our controller in various unstructured environments, as well as phantom experiments.

Co-creating value in entrepreneurship: an exploratory study of Lebanese women

ABSTRACT This study aims to amplify theory and practice at the marketing/entrepreneurship interface (MEI) by proposing a revision to the key concept of value creation. Advances in marketing research suggest that value is co-created by means of multiple actors, who integrate their resources within ecosystems. This study, therefore, investigates value co-creation from a MEI perspective. The study is based in Lebanon, a country encountering turbulence and disruption, providing a MENA context. In recognition of local conditions, the methodology is contextually congruent, using socially mediated interviews and panel discussions. Analysis of these data uncovers emergent practices of VCC that are captured in two dimensions of adaptive marketing and online interactions that take place within a digitally enabled but imbalanced entrepreneurial ecosystem. The study offers a revision to theory at the MEI by extending value creation to value co-creation and by showing how value co-creation may be adapted and reconfigured according to local circumstances.

Adaptive solution to transfer learning of neural network controllers from earth to space environments

AbstractCompliant manipulation has long been a major constraint for grappling in robotic manipulators. To adopt robotic manipulators in space for the prospect of capturing space junk and transforming them into salvageable assets for re‐use, robust adaptive manipulation would be key. We believe that a bio‐inspired approach could provide human‐like tactility required for robustness and adaptability in robotic manipulation. Given the similarity in form and dynamics between earth‐based and space‐based robotic manipulators, we first explored the transfer learning of neural network controllers as an avenue to address the challenges of limited computation resources onboard the spacecraft (space manipulator). We introduced a pre‐trained and learned feedforward neural network for modelling the control error a priori. While the results were encouraging, there are major limitations of neural networks' capability to ensuring the transfer learning of similar earth‐based dynamics to space‐based dynamics, given that the parameters of contrast are fairly straightforward. We have demonstrated these limitations by presenting a novel approach that is inspired by human motor control. We explored the adaptability through a practical problem of transferring a neuro‐controller from earth to space. With the results not as plausible as expected, an alternative adaptive controller has been learned to demonstrate a viable solution. The controller was trained entirely in simulation via rapid online adaptation of the robot's controller to the object's properties and environmental dynamics using only proprioception history. As a notable step, we have shown that appropriate models can be learned in this manner by training the control policy via reinforcement learning, which provides avenue for transferring the learned model from earth to space environments.

Mixed-Up Experience Replay for Adaptive Online Condition Monitoring

Data-driven predictive maintenance reduces manufacturing downtime, and complex process-sensing relationships encourage the use of Deep Learning to automatically extract features. However, labeled training data is often lacking, and novel fault conditions may occur. Practical deployments must learn from unlabeled data, adapt to emerging conditions, and do so without prior knowledge of when the condition changes. Combining state-of-the-art Self-Supervised Learning (SSL) with Continual Learning (CL) facilitates adaptation as new conditions are observed. This study proposes a framework for adaptive online condition monitoring based on Barlow Twins SSL and novel Mixed-Up Experience Replay (MixER) for unsupervised CL. Tailored for 1D sensing data, Barlow Twins effectively clusters unlabeled data. When combined with MixER, the system outperforms state-of-the-art unsupervised CL on a motor health condition data set, reaching 92.4% classification accuracy. Future work will demonstrate human-in-the-loop integration for real manufacturing environments.

Data-Driven Distributed Grid Topology Identification Using Backtracking Jacobian Matrix Approach

The topology identification of distribution system is the foundation of state estimation and system analyses. However, the lack of sufficient measurement devices in practice makes full-scale identification of distributed grid hardly achievable. On the other hand, the high-scale distributed renewable energy grid-connected aggravates the complex associations between nodal injection power and voltage. Taking full advantage of it, this paper proposes a novel data-driven approach to identify the topology by backtracking Jacobian matrix from the voltage and power data from gird terminal units. Specifically, a data-driven power-to-voltage mapping model is proposed. It uses the adaptive online deep learning algorithm based on hedge backpropagation to model the mapping relationship of terminal active power, reactive power, and voltage. Then, Backtracking the mapping model, a Jacobian matrix consisting of the partial derivative of voltage to the active and reactive power is obtained, which reflects the connectivity between nodes. Finally, through the Jacobian matrix, a maximum connectivity screening algorithm is developed to generate the topology of medium distribution systems. The effectiveness of the proposed method is verified on IEEE 33-node, IEEE 123-node, and actual distribution systems.

Online Inverse Optimal Control for Time-Varying Cost Weights.

Inverse optimal control is a method for recovering the cost function used in an optimal control problem in expert demonstrations. Most studies on inverse optimal control have focused on building the unknown cost function through the linear combination of given features with unknown cost weights, which are generally considered to be constant. However, in many real-world applications, the cost weights may vary over time. In this study, we propose an adaptive online inverse optimal control approach based on a neural-network approximation to address the challenge of recovering time-varying cost weights. We conduct a well-posedness analysis of the problem and suggest a condition for the adaptive goal, under which the weights of the neural network generated to achieve this adaptive goal are unique to the corresponding inverse optimal control problem. Furthermore, we propose an updating law for the weights of the neural network to ensure the stability of the convergence of the solutions. Finally, simulation results for an example linear system are presented to demonstrate the effectiveness of the proposed strategy. The proposed method is applicable to a wide range of problems requiring real-time inverse optimal control calculations.

Dynamic Via-points and Improved Spatial Generalization for Online Trajectory Generation with Dynamic Movement Primitives

Dynamic Movement Primitives (DMP) have found remarkable applicability and success in various robotic tasks, which can be mainly attributed to their generalization, modulation and robustness properties. However, the spatial generalization of DMP can be problematic in some cases, leading to excessive overscaling and in turn large velocities and accelerations. While other DMP variants have been proposed in the literature to tackle this issue, they can also exhibit excessive overscaling as we show in this work. Moreover, incorporating intermediate points (via-points) for adjusting the DMP trajectory to account for the geometry of objects related to the task, or to avoid or push aside objects that obstruct a specific task, is not addressed by the current DMP literature. In this work we tackle these unresolved so far issues by proposing an improved online spatial generalization, that remedies the shortcomings of the classical DMP generalization, and moreover allows the incorporation of dynamic via-points. This is achieved by designing an online adaptation scheme for the DMP weights which is proved to minimize the distance from the demonstrated acceleration profile to retain the shape of the demonstration, subject to dynamic via-point and initial/final state constraints. Extensive comparative simulations with the classical and other DMP variants are conducted, while experimental results validate the practical usefulness and efficiency of the proposed method.

Online Learning-Based Adaptive Device-Free Localization in Time-Varying Indoor Environment

With the widespread use of WiFi devices and the availability of channel state information (CSI), CSI-based device-free localization (DFL) has attracted lots of attention. Fingerprint-based localization methods are the primary solutions for DFL, but they are faced with the fingerprint similarity problem due to the complex environment and low bandwidth of the commercial WiFi. Meanwhile, fingerprints may change unpredictably due to multipath WiFi signal propagation in time-varying environments. To tackle these problems, this paper proposes an adaptive online learning DFL method, which adaptively updates the localization model to ensure long-term accuracy and adaptability. Specifically, the CSI signals of the target located at different reference points are first collected and transformed to discriminable fingerprints using the weights of Multilayer Online Sequence Extreme Learning Machine (ML-OSELM). After that, an online learning DFL model is built to adapt to the changes of the environment. Experimental results in a time-varying indoor environment validate the adaptability of the proposed method against environmental changes and show that our method can achieve 10% improvement over other methods.

Online distortion simulation using generative machine learning models: A step toward digital twin of metallic additive manufacturing

In the era of Industry 4.0 and smart manufacturing, Wire Arc Additive Manufacturing (WAAM) stands at the forefront, driving a paradigm shift towards automated, digitalized production. However, online simulation remains a technical barrier toward building a Digital Twin (DT) for metallic AM due to the prolonged computing time of numerical simulations and limitations in accuracy of current data-driven models. This study addresses these issues by introducing an adaptive online simulation model for predicting distortion fields, utilizing a diffusion model architecture for distortion process modelling with a Vector Quantized Variational AutoEncoder coupled with Generative Adversarial Network (VQVAE-GAN) backbone for spatial feature extraction, complemented by a Recurrent Neural Network (RNN) for time-scale result fusion. Pretrained offline with Finite Element Method (FEM) simulated distortion fields, the model successfully predicts distortion fields online using laser-scanned point clouds during the deposition process. Experimental validation on seven thin-wall structures demonstrated its superior performance, achieving a Root Mean Square Error (RMSE) below 0.9 m, outperforming FEM by 143 % and Artificial Neural Networks (ANN) based methods by 151 %, marking a significant stride towards realizing an AM-DT.

Fractional-order fuzzy sliding mode control of uncertain nonlinear MIMO systems using fractional-order reinforcement learning

This paper introduces a novel approach aimed at enhancing the control performance of a specific class of unknown multiple-input and multiple-output nonlinear systems. The proposed method involves the utilization of a fractional-order fuzzy sliding mode controller, which is implemented through online fractional-order reinforcement learning (FOFSMC-FRL). First, the proposed approach leverages two Takagi–Sugeno–Kang (TSK) fuzzy neural network actors. These actors approximate both the equivalent and switch control parts of the sliding mode control. Additionally, a critic TSK fuzzy neural network is employed to approximate the value function of the reinforcement learning process. Second, the FOFSMC-FRL parameters undergo online adaptation using an innovative fractional-order Levenberg–Marquardt learning method. This adaptive mechanism allows the controller to continuously update its parameters based on the system’s behavior, optimizing its control strategy accordingly. Third, the stability and convergence of the proposed approach are rigorously examined using Lyapunov theorem. Notably, the proposed structure offers several key advantages as it does not depend on knowledge of the system dynamics, uncertainty bounds, or disturbance characteristics. Moreover, the chattering phenomenon, often associated with sliding mode control, is effectively eliminated without compromising the system’s robustness. Finally, a comparative simulation study is conducted to demonstrate the feasibility and superiority of the proposed method over other control methods. Through this comparison, the effectiveness and performance advantages of the approach are validated.