Adaptive Tuning Research Articles

Adaptive parameters tuning based on energy-preserving splitting integration for Hamiltonian Monte Carlo Method

Splitting schemes, a class of numerical integrators for Hamiltonian problems, offer a favorable alternative to the Störmer–Verlet method in Hamiltonian Monte Carlo (HMC) methodology. However, the performance of HMC is highly sensitive to the adopted step size. In this paper, we propose a novel approach for selecting the step size h for advancing with the method defined by the free parameter b, within the family of one-parameter second order splitting procedures. Our methodology utilizes a designated function hb of the parameter b to determine the step size, i.e. h=hb(b). By appropriately restricting the domain of hb to a suitable interval I, the pairs (b,hb) with b∈I ensure both stability and Hamiltonian preservation when sampling from Gaussian distributions. As a result, our technique never rejects a sample within the HMC process, and this characteristic is the key factor behind its superior performance compared to similar methods recently introduced in other studies. Additionally, we assess the effectiveness of the methods defined by the pairs (b,hb) for general not-Gaussian distribution sampling. In this case we also present a technique based on an adaptive selection of the b parameter for improving the HMC performance. The effectiveness of the proposed approach is evaluated through benchmark examples from literature and experiments involving the Log-Gaussian Cox process and Bayesian Logistic Regression.

Signal Integration and Adaptive Sensory Diversity Tuning in Escherichia coli Chemotaxis.

In uncertain environments, phenotypic diversity can be advantageous for survival. However, as the environmental uncertainty decreases, the relative advantage of having diverse phenotypes decreases. Here, we show how populations of E. coli integrate multiple chemical signals to adjust sensory diversity in response to changes in the prevalence of each ligand in the environment. Measuring kinase activity in single cells, we quantified the sensitivity distribution to various chemoattractants in different mixtures of background stimuli. We found that when ligands bind uncompetitively, the population tunes sensory diversity to each signal independently, decreasing diversity when the signal ambient concentration increases. However, amongst competitive ligands the population can only decrease sensory diversity one ligand at a time. Mathematical modeling suggests that sensory diversity tuning benefits E. coli populations by modulating how many cells are committed to tracking each signal proportionally as their prevalence changes.

LEAP: LLM instruction-example adaptive prompting framework for biomedical relation extraction.

To investigate the demonstration in large language models (LLMs) for biomedical relation extraction. This study introduces a framework comprising three types of adaptive tuning methods to assess their impacts and effectiveness. Our study was conducted in two phases. Initially, we analyzed a range of demonstration components vital for LLMs' biomedical data capabilities, including task descriptions and examples, experimenting with various combinations. Subsequently, we introduced the LLM instruction-example adaptive prompting (LEAP) framework, including instruction adaptive tuning, example adaptive tuning, and instruction-example adaptive tuning methods. This framework aims to systematically investigate both adaptive task descriptions and adaptive examples within the demonstration. We assessed the performance of the LEAP framework on the DDI, ChemProt, and BioRED datasets, employing LLMs such as Llama2-7b, Llama2-13b, and MedLLaMA_13B. Our findings indicated that Instruction + Options + Example and its expanded form substantially improved F1 scores over the standard Instruction + Options mode for zero-shot LLMs. The LEAP framework, particularly through its example adaptive prompting, demonstrated superior performance over conventional instruction tuning across all models. Notably, the MedLLAMA_13B model achieved an exceptional F1 score of 95.13 on the ChemProt dataset using this method. Significant improvements were also observed in the DDI 2013 and BioRED datasets, confirming the method's robustness in sophisticated data extraction scenarios. The LEAP framework offers a compelling strategy for enhancing LLM training strategies, steering away from extensive fine-tuning towards more dynamic and contextually enriched prompting methodologies, showcasing in biomedical relation extraction.

A Single Image High-Perception Super-Resolution Reconstruction Method Based on Multi-layer Feature Fusion Model with Adaptive Compression and Parameter Tuning

We propose a simple image high-perception super-resolution reconstruction method based on multi-layer feature fusion model with adaptive compression and parameter tuning. The aim is to further balance the high and low-frequency information of an image, enrich the detailed texture to improve perceptual quality, and improve the adaptive optimization and generalization of the model in the process of super-resolution reconstruction. First, an effective multi-layer fusion super-resolution (MFSR) basic model is constructed by the design of edge enhancement, refine layering, enhanced super-resolution generative adversarial network and other sub-models, and effective multi-layer fusion. This further enriches the image representation of features of different scales and depths and improves the feature representation of high and low-frequency information in a balanced way. Next, a total loss function of the generator is constructed with adaptive parameter tuning performance. The overall adaptability of the model is improved through adaptive weight distribution and fusion of content loss, perceptual loss, and adversarial loss, and improving the error while reducing the edge enhancement model. Finally, a fitness function with the evaluation perceptual function as the optimization strategy is constructed, and the model compression and adaptive tuning of MFSR are carried out based on the multi-mechanism fusion strategy. Consequently, the construction of the adaptive MFSR model is realized. Adaptive MFSR can maintain high peak signal to noise ratio and structural similarity on the test sets Set5, Set14, and BSD100, and achieve high-quality reconstructed images with low learned perceptual image patch similarity and perceptual index, while having good generalization capabilities.

Predefined-Time Platoon Control of Unmanned Aerial Vehicle with Range-Limited Communication

In this paper, the predefined-time platoon control for multiple uncertain unmanned aerial vehicles (UAVs) under range-limited communication and external disturbance constraints is considered. A novel control scheme, which can guarantee communication connectivity, collision avoidance, and the predefined convergence time simultaneously, is proposed. To achieve disturbance robustness, an observer-based distributed control law is firstly proposed with a time-varying gain. Then, a radial basis function neural network (RBFNN) with an adaptive tuning law is applied to approximate uncertainties of the system. Under the time and error transformation techniques, uniformly ultimate boundedness (UUB) stability of the closed-loop system is guaranteed within predefined convergence time. Compared with the existing results, the proposed method allows the system to have UUB within any predefined time without depending on the initial conditions or system parameters. Finally, simulation results are presented to verify the derived theorem.

An innovative approach for cluster head selection and Energy Optimization in wireless sensor networks using Zebra Fish and Sea Horse Optimization techniques

In recent times, Wireless Sensor Networks (WSNs) have become an indispensable technology across various industries, offering diverse applications and services. Among the crucial performance metrics for WSNs, optimal cluster head (CH) selection and energy efficiency are paramount for cost-effective network operations. This paper proposes a novel approach for WSNs that tackles both challenges using Zebra Fish Optimization (ZFO) and Sea Horse Optimization (SHO) algorithms. The proposed approach focuses on dynamic cluster formation and CH selection. The ZFO algorithm, enhanced with a new multi-level threading technique, dynamically selects the most suitable CH based on a fitness function. Subsequently, the SHO algorithm, equipped with an innovative adaptive parameter tuning mechanism, optimizes energy consumption within the network. This two-phased approach ensures balanced performance. Performance evaluation is validated using key metrics like packet delivery ratio (PDR), throughput, network lifetime, and residual energy. Experimental results and statistical analysis demonstrate that the proposed hybrid scheme outperforms existing popular algorithms in all these metrics. The improvements range from 1.8 % to 6.9 % for PDR, 6.7 % to 24 % for throughput, 1.86 % to 7.40 % for network lifetime, and 9.65 % to 37.95 % for residual energy. These advancements are attributed to the innovative modifications introduced in both ZFO and SHO algorithms, ultimately contributing to the enhanced performance of the entire system.

Distributed Adaptive Formation Tracking for a Class of Uncertain Nonlinear Multiagent Systems: Guaranteed Connectivity Under Moving Obstacles.

This article explores a guaranteed network connectivity problem during moving obstacle avoidance within a distributed formation tracking framework for uncertain nonlinear multiagent systems with range constraints. We investigate this problem based on a new adaptive distributed design using nonlinear errors and auxiliary signals. Within the detection range, each agent regards other agents and static or dynamic objects as obstacles. The nonlinear error variables for formation tracking and collision avoidance are presented, and the auxiliary signals in formation tracking errors are introduced to maintain network connectivity under the avoidance mechanism. The adaptive formation controllers using command-filtered backstepping are constructed to ensure closed-loop stability with collision avoidance and preserved connectivity. Compared with the previous formation results, the resulting features are as follows: 1) the nonlinear error function for the avoidance mechanism is considered an error variable, and an adaptive tuning mechanism for estimating the dynamic obstacle velocity is derived in a Lyapunov-based control design procedure; 2) network connectivity during dynamic obstacle avoidance is preserved by constructing the auxiliary signals; and 3) owing to neural networks-based compensating variables, the bounding conditions of time derivatives of virtual controllers are not required in the stability analysis.

Improving Ship Response Estimation using Neural Networks

The feasibility of a data-adaptive multi-fidelity seakeeping model is assessed for use in early stage design in this study. Data adaptive tuning (or correction) of lower-fidelity model predictions are implemented based on training with higher fidelity ship motion response data. Long Short-Term Memory (LSTM) neural networks are incorporated as part of a multi-fidelity approach for prediction of 6 degree of freedom (6-DOF) ship motion responses in waves. LSTM networks are trained and tested with Large Amplitude Motion Program (LAMP)simulations as a target, and SimpleCode simulations and wave time series as inputs. LSTM networks improve the fidelity of SimpleCode seakeeping predictions relative to LAMP, while retaining the computational efficiency of a lower-fidelity simulation tool.

Beyond conventional bounds: Surpassing system limits for stereotactic ablative (SAbR) lung radiotherapy using CBCT-based adaptive planning system.

Online adaptive radiotherapy relies on a high degree of automation to enable rapid planning procedures. The Varian Ethos intelligent optimization engine (IOE) was originally designed for conventional treatments so it is crucial to provide clear guidance for lung SAbR plans. This study investigates using the Ethos IOE together with adaptive-specific optimization tuning structures we designed and templated within Ethos to mitigate inter-planner variability in meeting RTOG metrics for both online-adaptive and offline SAbR plans. We developed a planning strategy to automate the generation of tuning structures and optimization. This was validated by retrospective analysis of 35 lung SAbR cases (total 105 fractions) treated on Ethos. The effectiveness of our planning strategy was evaluated by comparing plan quality with-and-without auto-generated tuning structures. Internal target volume (ITV) contour was compared between that drawn from CT simulation and from cone-beam CT (CBCT) at time of treatment to verify CBCT image quality and treatment effectiveness. Planning strategy robustness for lung SAbR was quantified by frequency of plans meeting reference plan RTOG constraints. Our planning strategy creates a gradient within the ITV with maximum dose in the core and improves intermediate dose conformality on average by 2%. ITV size showed no significant difference between those contoured from CT simulation and first fraction, and also trended towards decreasing over course of treatment. Compared to non-adaptive plans, adaptive plans better meet reference plan goals (37%vs. 100% PTV coverage compliance, for scheduled and adapted plans) while improving plan quality (improved GI (gradient index) by 3.8%, CI (conformity index) by 1.7%). We developed a robust and readily shareable planning strategy for the treatment of adaptive lung SAbR on the Ethos system. We validated that automatic online plan re-optimization along with the formulated adaptive tuning structures can ensure consistent plan quality. With the proposed planning strategy, highly ablative treatments are feasible on Ethos.

Investigation of Legendre polynomials expanded adaptive controller with inverse compensation for high frequency tracking of electro-hydraulic force systems

Accurate force tracking of an electro-hydraulic force system (EHFS) is of great significance in various industrial applications. As the EHFS is inevitably confronted with hydraulic nonlinearities, dynamic variations and uncertain disturbances, the real-time force tracking performance is generally unsatisfactory, especially for high frequency command force signals. For reducing the force tracking error with relatively high frequency inputs, a Legendre polynomials expanded adaptive controller with inverse compensation is proposed in this paper. The proposed controller is constructed by introducing an offline designed inverse compensation (IC) controller and an online adaptive controller to the EHFS governed by traditional Proportional Integral (PI) controller, in which the former IC controller is acting as the inner loop controller and the latter adaptive controller is regarded as an outer controller. The inner loop IC controller with fixed control parameters is offline designed on the basis of traditional PI controller by means of the generalized projection identification algorithm and the zero magnitude error tracking technology, focusing on extending the real-time force tracking bandwidth of the EHFS. The outer loop online adaptive controller is developed by Legendre polynomials expanded adaptive filters with nonlinear mapping ability, whose weights are online updated by an adaptive tuning algorithm with the aim of handling system’s dynamic variations, nonlinearities and uncertain disturbances. The proposed controller is implemented on a real EHFS test rig by the xPC/Target rapid prototyping technique, and comparative experimental results demonstrate that the proposed controller can achieve much higher high frequency tracking performance than the traditional PI and IC controller commonly used in industry.

Active Damping for Dynamic Improvement of Multiple Grid-Tied Virtual Synchronous Generators

To eliminate low-frequency oscillations, this paper proposes an active-damping method for multiple grid-tied virtual synchronous generators (VSGs) in a power plant. Firstly, using the Lyapunov's indirect method, the damping ratio of multiple VSGs in parallel is analyzed. The average damping ratio reveals that this multi-VSG power plant can be poorly damped in a wide range of inertia and damping settings. Then, self- and mutual-damping controllers are developed to suppress self- and mutually induced low-frequency power oscillations, respectively. For the practical implementation, an adaptive tuning algorithm that enables automatic realization is proposed. Through a reassessment, a remarkable damping-ratio improvement is validated. Moreover, the inertial response improvement is validated by the frequency response analysis. Finally, simulations in Digsilent/PowerFactory and experiments are performed to demonstrate the accuracy of the analyses and the effectiveness of the proposed method.

An adaptive electrodynamic metamaterial for the absorption of structural vibration

This paper presents an adaptive shunted electrodynamic metamaterial, for broadband robust vibration control. The study considers a unit cell of 12 miniature, low-cost proof-mass actuators for the control of vibration in a three degree-of-freedom structure subject to parametric uncertainty. In order to modify their dynamic responses, each actuator is connected to a shunt circuit consisting of a parallel resistor and a switched in/out inductor and capacitor. Provided the impedance of the actuator is cancelled out using a negative impedance, the shunt circuit is capable of tuning the resonance of the actuator up or down in frequency. An adaptive tuning approach is proposed, whereby the shunted actuator resonance frequencies are periodically switched to the centre frequencies of the highest magnitude bins of a real-time frequency analysis of the velocity measured on the structure. This approach is compared to a blind swept tuning method and a fixed-shunt tuning in terms of the robustness to parametric uncertainty, and in practical terms for realisation using analogue or digital shunt impedances.

Variable Power Tracking Control Strategy of Doubly Fed Induction Generators for Fast Frequency Responses

Frequency regulation and droop control of doubly fed induction generators (DFIGs) can quickly respond to frequency changes and reduce the maximum rate of frequency (MROFF) in power systems. However, due to real-time dynamic changes in the MPPT control loop, the ability to improve the lowest frequency point is limited. Therefore, this article first describes an in-depth analysis of the dynamic characteristics of the incremental power of frequency regulation with droop control using an equivalent linear model. The limitations of improving the lowest frequency point under the influence of dynamic changes in the MPPT control loop are revealed. Secondly, to address the impact of these dynamics, an improved decoupling frequency regulation (IDFR) strategy based on power tracking is proposed, aiming to increase the maximum frequency deviation (MFD) and MROCOF. Then, in order to overcome the difficulty of adjusting control coefficients in the IDFR strategy, an adaptive control coefficient tuning fuzzy control method based on frequency deviation and ROCOF was proposed to flexibly adjust control requirements under various working conditions, thereby improving the control stability and performance of the system and effectively solving the problem of control coefficient allocation. Finally, to verify the frequency regulation performance of the proposed IDFR strategy under various operating conditions, simulations were conducted based on different disturbances and wind conditions. The results show that the proposed IDFR strategy significantly improves the system MFD and MROCOF improvement ability under various conditions.

Quantization-based distributed design strategy for adaptive consensus tracking of asynchronously switched nonlinear multiagent systems

We propose a quantization-based distributed consensus tracking design to resolve the unknown control direction problem of uncertain switched nonlinear multiagent systems under a fully quantized environment. All feedback and communication signals for the local control design are quantized and the control coefficient functions and directions of agents are unknown. Differing from the previous literature results, the primary contribution of this work is to present a quantization-based distributed design solution to the unknown control direction problem of asynchronously switched agents in the consensus tracking field. The non-differentiability problem of virtual control laws using quantized feedback signals is addressed by employing the filter-based recursive method and developing the analysis technique of the quantization errors of Nussbaum functions. Quantization effects in local adaptive neural control laws are compensated via the adaptive tuning mechanism using quantized states. The practical stability of the overall closed-loop system is established by the common Lyapunov theory. Illustrative simulations verify the efficacy of the proposed quantization-based consensus tracking approach.

Holistic coordination of transactive energy and carbon emission right trading for heterogenous networked multi-energy microgrids: A fully distributed adaptive consensus ADMM approach

The paradigm of multi-energy microgrids (MEMGs) with internal energy sharing and trading is considered a promising option to empower low-carbon energy transitions. In this work, a holistic and efficient optimization framework is proposed to coordinate electricity, heat, and carbon emission right (CER) trading activities among multiple MEMGs. The proposed framework captures the heterogeneity of MEMGs, peer-to-peer transactive energy of different forms, and CER trading and network constraints together in a holistic fashion. To preserve the privacy of MEMGs and ensure transparency of CER trading, a fully distributed adaptive consensus alternating direction method of multipliers (AC-ADMM) is proposed, based on the combination of parallel computation capability of C-ADMM and the penalty parameters adaptive tuning mechanism. Case studies demonstrate the effectiveness of the proposed AC-ADMM method and reveal significant economic and environmental benefits for MEMGs by coordinating different forms of energy and CER trading in local transactive markets, while satisfying the network constraints. The superior convergence performance of the proposed method is also validated against conventional ADMM and C-ADMM methods.

Signal Compensation Control With DDPG-Based Tuning Strategy for Electronic Throttle System

The electronic throttle system (ETS) is one of the important components of an automobile engine that adjust the engine air intake to directly affect the combustion power of the engine. In practical scenarios, Proportional-Integral-Derivative (PID) is a common and effective method. However, the traditional PID is difficult to satisfy the ETS performance requirements, e.g., the system response overshoot is not allowed to exist. Moreover, the controller gains are also difficult to tune manually. To tackle the above-mentioned issues, we propose a signal compensation control framework with an adaptive gain tuning strategy for the electronic throttle system, which consists of an upper-level to tune controller gains and a lower-level signal compensation controller to eliminate the nonlinear terms. The main feature of the signal compensation controller relies on two nonlinear compensators to remove the strong nonlinearity and uncertainty in the actual throttle system. Furthermore, we develop an adaptive gain tunning strategy based on Deep Deterministic Policy Gradient (DDPG) algorithm, and we analyze the corresponding stability and convergence properties of the proposed method. Finally, we illustrate the proposed algorithm on benchmarks and the tracking control problem using the real-world experiment platform of the ETS to show the effectiveness of the proposed algorithm.

Noncontact Infant Apnea Detection for Hypoxia Prevention With a K-Band Biomedical Radar.

Annually, a significant number of premature infants suffer from apnea, which can easily cause a drop in oxygen saturation levels, leading to hypoxia. However, infant cardiopulmonary monitoring using conventional methods often necessitates skin contact, and they are not suitable for long-term monitoring. This article introduces a non-contact technique for infant cardiopulmonary monitoring and an adjustable apnea detection algorithm. These are developed using a custom-designed K-band continuous-wave biomedical radar sensor system, which features a DC-coupled adaptive digital tuning function. By using radar technology to detect chest motions without physical contact, it is feasible to extract significant biological information regarding an infant's respiration and heartbeat. The proposed algorithm utilizes an adaptively adjusted threshold and personalized apnea warning time to automatically measure the total number of apneic events and their respective durations. Experiments have been conducted in clinical environment, demonstrating that both the accurate cardiopulmonary signals and the apneas of varying durations can be effectively monitored using this method, which suggest that the proposed technique has potential applications both inside and outside of clinical settings.

Auditory-inspired adaptive frequency tracking

One of the best frequency trackers to date is the human (mammalian) auditory system, which has evolved through millions of years of resolving classification problems. It is a versatile, elegant and powerful sound processing unit. It excels in detecting, estimating, and classifying multiple targets simultaneously even in noisy environments. Hence, mimicking even some features of the auditory system could be beneficial in developing superior frequency tracking and classification algorithms. An auditory inspired adaptive synchrony capture filterbank (SCFB) signal processing architecture for tracking signal frequency components was proposed in a related paper [JASA-2013]. The SCFB architecture consists of a fixed array of traditional, passive linear, gammatone filters in cascade with a bank of three adaptively tunable bandpass filters that form a frequency-discriminator-loop (FDL). The SCFB exhibits many desirable properties for processing speech, music, and other complex sounds. In recent work [Dec2021], the algorithm was modified using adaptive tuning parameters, and a generalized way to determine/suppress voiced and unvoiced (silent) regions. This modified algorithm estimates frequencies with higher accuracy even in the presence of closely spaced input tones. Preliminary analysis with synthetic, human speech and humpback/whale-call signals demonstrates that the revised algorithm performs well. This talk will focus on follow-on work.

Control of a Path Following Cable Trench Caterpillar Robot Based on a Self-Coupling PD Algorithm

Underground cable trench inspection robots work in narrow, variable friction coefficient, and complex road environments. The running trajectory easily deviates from the desired path and leads to a collision, or even the destruction of the robot or cable. Addressing this problem, a path-following control method for the dual-tracked chassis robot based on a self-coupling PID (SCPID) control algorithm was developed. The caterpillar robot dynamics were modelled and both the unknown dynamics and external bounded disturbances were defined as sum disturbances, thus mapping the nonlinear system into a linearly disturbed system, then the self-coupling PD (SCPD) controller was designed. The system proved to be a robust stability control system and only one parameter, the velocity factor, needed to be tuned to achieve parameter calibration. Meanwhile, to solve the problem that the error-based speed factor is not universal and to improve the adaptive ability of the SCPD controller, an iterative method was used for adaptive tuning. The simulation results showed that the SCPID can achieve better control. The field test results showed that the SCPD’s maximum offset angle was 56.7% and 10.3% smaller than incremental PID and sliding mode control (SMC), respectively. The inspection time of the SCPD was 20% faster than other methods in the same environment.

Towards an optimized heat transfer process in vaporizing liquid microthrusters using pulsed heating control

The Institute for Microelectronics and Microsystems of the Italian National Research Council (Italy) has designed and fabricated a water-fed MEMS vaporizing liquid microthruster (VLM) in collaboration with the University of Salento (Italy) and KU Leuven (Belgium). Previous studies have demonstrated the device’s functioning and highlighted the presence of a strong thermoelectric-hydraulic coupling that severely affects the heating and propulsive efficiencies and reliability of the device. In this regard, the current work provides a preliminary experimental investigation of a pulsed heating system actively controlled by temperature using PI-D logic (proportional and integrative actions applied to the error; derivative action applied to the output). The overall performance assessment focuses on evaluating power consumption during steady-state operation and analyzing the dynamic response of the VLM undergoing such an actively controlled pulsed heating, which has been built using both manual and data-driven offline adaptive tuning of the PID parameters. Concerning the steady-state operation, results highlight a promising enhancement of the heating efficiency to values above 0.9. The dynamic response analysis shows that operating with a single set of fixed PID parameters is not feasible and that the manual tuning is a trial-and-error approach highly dependent on the operator’s experience, operating conditions, and reference temperature profile. Furthermore, shorter rise and response times require a higher proportional gain, and the overshoot experienced when crossing the saturation temperature cannot be avoided. In this paper, we show that the response of the data-driven adaptive controller solves these issues, exhibiting a reduced maximum settling time from around 59 s to less than 10 s, while the overshoot is avoided thanks to the temporal adjustment of the PID parameters.