Real-time Control Applications Research Articles

Continuous adaptive nonlinear model predictive control using spiking neural networks and real-time learning

Model predictive control (MPC) is a prominent control paradigm providing accurate state prediction and subsequent control actions for intricate dynamical systems with applications ranging from autonomous driving to star tracking. However, there is an apparent discrepancy between the model’s mathematical description and its behavior in real-world conditions, affecting its performance in real-time. In this work, we propose a novel neuromorphic (brain-inspired) spiking neural network for continuous adaptive non-linear MPC. Utilizing real-time learning, our design significantly reduces dynamic error and augments model accuracy, while simultaneously addressing unforeseen situations. We evaluated our framework using real-world scenarios in autonomous driving, implemented in a physics-driven simulation. We tested our design with various vehicles (from a Tesla Model 3 to an Ambulance) experiencing malfunctioning and swift steering scenarios. We demonstrate significant improvements in dynamic error rate compared with traditional MPC implementation with up to 89.15% median prediction error reduction with 5 spiking neurons and up to 96.08% with 5,000 neurons. Our results may pave the way for novel applications in real-time control and stimulate further studies in the adaptive control realm with spiking neural networks.

Data-Driven Identification of Crane Dynamics Using Regularized Genetic Programming

The meaningful problem of improving crane safety, reliability, and efficiency is extensively studied in the literature and targeted via various model-based control approaches. In recent years, crane data-driven modeling has attracted much attention compared to physics-based models, particularly due to its potential in real-time crane control applications, specifically in model predictive control. This paper proposes grammar-guided genetic programming with sparse regression (G3P-SR) to identify the nonlinear dynamics of an underactuated crane system. G3P-SR uses grammars to bias the search space and produces a fixed number of candidate model terms, while a local search method based on an l0-regularized regression results in a sparse solution, thereby also reducing model complexity as well as reducing the probability of overfitting. Identification is performed on experimental data obtained from a laboratory-scale overhead crane. The proposed method is compared with multi-gene genetic programming (MGGP), NARX neural network, and Takagi-Sugeno fuzzy (TSF) ARX models in terms of model complexity, prediction accuracy, and sensitivity. The G3P-SR algorithm evolved a model with a maximum mean square error (MSE) of crane velocity and sway prediction of 1.1860 × 10−4 and 4.8531 × 10−4, respectively, in simulations for different testing data sets, showing better accuracy than the TSF ARX and MGGP models. Only the NARX neural network model with velocity and sway maximum MSEs of 1.4595 × 10−4 and 4.8571 × 10−4 achieves a similar accuracy or an even better one in some testing scenarios, but at the cost of increasing the total number of parameters to be estimated by over 300% and the number of output lags compared to the G3P-SR model. Moreover, the G3P-SR model is proven to be notably less sensitive, exhibiting the least deviation from the nominal trajectory for deviations in the payload mass by approximately a factor of 10.

Model predictive path-following control for truck–trailer systems with specific guidance points — design and experimental validation

This article presents an experimental validation of a model predictive path-following control algorithm (PF-MPC ) applied to a truck–trailer system, encompassing both forward and backward motions. The proposed controller is designed to precisely follow a predefined path generated by a path planner, with a designated guidance point positioned on either the truck or the trailer. The algorithm’s performance is assessed through implementation and validation on a model-scaled truck–trailer system, where MPC, state estimation, and low-level control are executed on a microcontroller (MCU ). The experimental results demonstrate the effectiveness of the proposed control approach in achieving highly accurate path-following performance, even when operating in the challenging context of unstable backward motion, and with the involvement of up to two trailers. Moreover, the successful implementation of the algorithm on a microcontroller underscores its suitability for real-time control applications. The results of this study collectively highlight the promising potential of the proposed control algorithm for practical utilization in autonomous driving systems.

Numerical and experimental investigation of stratified water storage tanks: An enhanced adaptive-grid model

Stratified water storage tanks are key in thermal energy systems, effectively balancing energy supply with heat demand, thus facilitating operational flexibility. Accurately modeling both energy balance and thermocline evolution with minimal computational effort is essential for models implementation in real-time control applications. One-dimensional, static-grid models are favored for their easy implementation; however, they require dense grids in order to minimize numerical diffusion and to represent mixing effect correctly, resulting in rather expensive computational effort. This study introduces an adaptive-grid model that comprehensively represents the water storage tank’s geometrical features, including inlet and outlet duct heights and dead volume sizes. It also details the spatially discretized heat diffusion and characterizes the inflow region’s mixing using an empirical equation. Implemented in both TRaNsient SYstem Simulation (TRNSYS) and Modelica environments, the model is validated through laboratory experiments with a hot water storage tank operating under various mass flow and temperature conditions, representative of heat pump-driven heating systems. The results indicate improvements in computational efficiency compared to static-grid models, specifically a 55% reduction in simulation duration with the same level of uncertainty.

Embedded Systems Basics

Embedded systems play a pivotal role in modern technological advancements, integrating computing capabilities into various devices and systems. This paper presents an abstract of an embedded system designed for real-time monitoring and control applications in industrial automation. The system utilizes a combination of microcontroller-based hardware and software components to achieve reliable and efficient operation.

Application of Patient-Based Real-Time Quality Control Based on Artificial Intelligence Monitoring Platform in Continuously Quality Risk Monitoring of Down Syndrome Serum Screening.

Patient-based real-time quality control (PBRTQC) has gained attention because of its potential to continuously monitor the analytical quality insituations wherein internal quality control (IQC) is less effective. Therefore, we tried to investigate the application of PBRTQC method based on an artificial intelligence monitoring (AI-MA) platform in quality risk monitoring of Down syndrome (DS) serum screening. The DS serum screening item determination data and relative IQC data from January 4 to September 7 in 2021 were collected. Then, PBRTQC exponentially weighted moving average (EWMA) and moving average (MA) procedures were built and optimized in the AI-MA platform. The efficiency of the EWMA and MA procedures with intelligent and traditional control rules were compared. Next, the optimal EWMA procedures that contributed to the quality assurance of serum screening were run and generated early warning cases were investigated. Optimal EWMA and MA procedures on the AI-MA platform were built. Comparison results showed the EWMA procedure with intelligent QC rules but not traditional quality rules contained the best efficiency. Based on the AI-MA platform, two early warning cases were generated by using the optimal EWMA procedure, which finally found were caused by instrument failure. Moreover, the EWMA procedure could truly reflect the detection accuracy and quality insituations wherein traditional IQC products were unstable or concentrations were inappropriate. The EWMA procedure built by the AI-MA platform could be a good complementary control tool for the DS serum screening by truly and timely reflecting the detection quality risks.

Active control of thermoacoustic oscillation based on the x-nlms algorithm

Thermoacoustic oscillations, caused by the coupling of unsteady heat release and pressure fluctuation, can result in severe damage to the combustion chamber of gas turbines. This paper presents a novel approach to active control of thermoacoustic oscillations, which is based on a Filtered-X normalized least mean square algorithm (X-NLMS). The controller employs the pressure magnitude at a predetermined axial position preceding the flame as the control variable, which is acquired through microphones installed around the combustor periphery. Control is accomplished by modifying the output frequency and phase of a loudspeaker. The performance of the control system is evaluated through simulations on a Rijke tube, with the classical PID method used as a comparison. The experimental results showcase the efficacy of the X-NLMS algorithm in actively controlling thermoacoustic oscillations. By adaptively estimating and attenuating pressure fluctuations, the algorithm effectively suppresses the undesired acoustic disturbances associated with thermoacoustic instabilities. Comparative analysis reveals that the X-NLMS algorithm outperforms PID control in terms of oscillation suppression and system stability. Its ability to adapt to time-varying dynamics and its low computational complexity make it a promising candidate for real-time thermoacoustic control applications.

Inter-discharge optimization for fast, reliable access to ASDEX Upgrade advanced tokamak scenario

Rapid inter-discharge simulation and optimization using the RAPTOR code have allowed the development of a reliable and reproducible early heating strategy for an advanced tokamak (AT) scenario on ASDEX Upgrade. Solving for electron heat and current diffusion in RAPTOR with ad-hoc formulas for heat transport and electron cyclotron current drive (ECCD) efficiency is found to robustly recover the coupled dynamics of Te and q, while maintaining model parameters fixed for all discharges. The pedestal top boundary condition in pre-shot simulations is set by a newly derived scaling law for the electron pressure at ρ = 0.8, using a data set of previous AT discharges. RAPTOR simulations have allowed to develop an understanding of the onset of 3/2 tearing modes, which were observed to have a detrimental impact on confinement when low magnetic shear conditions are present at the rational surface during the high-β phase. Delaying the NBI heating, by a specific time interval found via simulations, has led to avoiding these modes. A non-linear optimization scheme has been applied to optimize the ECCD deposition radii to reach a stationary state with qmin>1 at the beginning of the flat-top phase, while ensuring a non-zero magnetic shear at q = 1.5 throughout the high-β phase, and has been successfully tested in experiment. However, further experiments, aiming for qmin>1.5 , have highlighted limitations of the present feedforward control approach in the presence of shot-to-shot variations that are not included in the applied model. Application of real-time model-based control is proposed to overcome model-reality mismatches in future work.

Machine learning-based real-time kinetic profile reconstruction in DIII-D

Kinetic equilibrium reconstruction plays a vital role in the physical analysis of plasma stability and control in fusion tokamaks. However, the traditional approach is subjective and prone to human biases. To address this, the consistent automatic kinetic equilibrium reconstruction (CAKE) method was introduced, providing objective results. Nonetheless, its offline nature limits its application in real-time plasma control systems (PCSs). To address this limitation, we present RTCAKENN, a machine learning model that approximates 7 CAKE-level output profiles, namely pressure, inverse q, toroidal current density, electron temperature and density, carbon ion impurity temperature and rotation profiles, using real-time available inputs. The deep neural network consists of an encoder layer, where the scalars and interdependent inputs such as plasma boundary coordinates and motional Stark effect data are encoded using multi-layer perceptrons (MLPs), while profile inputs are encoded by 1D convolutional layers. The encoded data is passed through a MLP for latent feature extraction, before being decoded in the decoding layers, which consist of upsampling and convolutional layers. RTCAKENN has been implemented in the DIII-D PCS and our model achieves accuracy comparable to CAKE and surpasses existing real-time alternatives. Through clever dropout training, RTCAKENN exhibits robustness and can operate even in the absence of Thomson scattering data or charge exchange recombination data. It executes in under 8 ms in the real-time environment, enabling future application in real-time control and analysis.

Application of G.hn Broadband Powerline Communication for Industrial Control Using COTS Components

Broadband powerline communication is a technology developed mainly with consumer applications and bulk data transmission in mind. Typical use cases include file download, streaming, or last-mile internet access for residential buildings. Applications gaining momentum are smart metering and grid automation, where response time requirements are relatively moderate compared to industrial (real-time) control. This work investigates to which extent G.hn technology, with existing, commercial off-the-shelf components, can be used for real-time control applications. Maximum packet rate and latency statistics are investigated for different G.hn profiles and MAC algorithms. An elevator control system serves as an example application to define the latency and throughput requirements. The results show that G.hn is a feasible technology candidate for industrial IoT-type applications if certain boundary conditions can be ensured.

An opto-electronic control system for real-time complete (re)shaping of cardiac action potentials on a multicellular scale

Abstract Background Cardiomyocytes maintain a membrane potential (Vm), which fulfills essential regulatory roles in various biological functions, including not only action potential (AP) propagation and mechanical contraction, but also homeostatic regulation. In-depth studies into these roles have been severely hampered by the lack of research methods allowing full control over Vm, especially in multicellular cardiac preparations. Purpose We aimed to unlock new research possibilities by the development of an experimental system (APqr) capable of full Vm control, including instantaneous modulation of AP morphology on a multicellular level. Methods Immortalized human atrial myocytes (hiAMs) grown in monolayer format (n=7) were genetically modified to express the blue light-activatable cation channel Cheriff and the red light-sensitive inward chloride pump Jaws for depolarizing and hyperpolarizing effects, respectively. Real-time Vm readout was obtained by patch clamp electrophysiology. Dynamic Vm control was achieved by a custom closed-coop controller calculating Vm deviations from reference values. A 470-nm and a 617-nm LED were modulated by the controller in a Vm deviation-dependent manner, selectively activating Cheriff and Jaws. To explore the feasibility of AP restoration, electrical disturbances were introduced by non-selective potassium channel blockade (4-aminopyridine, 4AP, 200 µM) or by a preprogrammed blue-light pulse creating abnormal cation influx during the repolarization phase of the hiAM AP. Results 4AP induced a 82.4 ± 27.8 ms increase of AP duration at 90% repolarization (APD90) values in hiAM monolayers. Using APs recorded under control conditions (CTL) as reference, the APqr maneuver reduced this APD90 difference to 1.9 ± 3.1 ms. Similarly, APqr suppressed the effects of light-induced abnormal cation influx on APD90 (CTL: 342.9 ± 51.7 ms, blue-light pulse: 700.8 ± 64.5 ms, APqr: 338.3 ± 68 ms) effectively, with Vm deviation less than 2.5 mV in 96.7% of the time. APqr could also be applied for the enforcement of arbitrary AP shapes. In these experiments, the Vm references consisted of AP shapes of hiAM monolayers exposed to drugs with APD-prolonging (4AP) or shortening (carbachol) effects. APqr was able to enforce these reference APs, that were distinctly different from the endogenous AP shapes, on hiAM monolayers with great accuracy, with Vm deviations less than 2.5 mV in 95.8% and 94.4% of the time, respectively. Conclusions APqr restores AP morphologies in the presence of electrical perturbations of different origin without any prior knowledge about the disturbance and enforces arbitrary AP morphologies with high accuracy in an immediate and self-regulatory manner. Collectively, these results set the stage for in-depth investigations into the regulatory roles of Vm in healthy and diseased cardiomyocytes via the application of such real-time opto-electronic control systems.Real-time (re)shaping of cardiac APs

BioRTC model enables exploration of real time control strategies for stormwater biofilters

Biofilters with real time control (RTC) have great potential to remove microbes from stormwater to protect human health for uses such as swimming and harvesting. However, RTC strategies need to be further explored and optimised for each specific location or end-use. This paper demonstrates that the newly developed BioRTC model can fulfil this requirement and allow effective and efficient exploration of the potential of RTC applications. We describe the development of BioRTC as the first RTC model for stormwater biofilters, including: selection of a ‘base’ model for microbial removal prediction, its modification to include RTC capabilities, as well as calibration and validation. BioRTC adequately predicted the performance of two previously developed RTC strategies, with Nash Sutcliffe Efficiency (Ec) ranging from 0.65 to 0.80. In addition, high parameter transferability was demonstrated during model validation, where we employed the parameter sets calibrated for another biofilter study without RTC to predict the performance of RTC biofilters. We then employed the BioRTC model to explore RTC applications on a hypothetical biofilter system located at the outlet of an existing catchment. With different scenarios, we tested the impact of input parameters such as RTC set-points and design characteristics, and evaluated the influence of operational conditions on the microbial removal performance of the hypothetical biofilter with RTC. The results showed that strategy rules, set-point values, and biofilter design all govern the performance of RTC biofilters, and that operational conditions could impact the suitability of different RTC strategies. Particularly, the presence of Pareto fronts established that muti-objective optimisation is necessary to balance competing needs. These results underscore the importance of RTC, which allows for local experimentation, climate change adaptation, and adjustment to changing demands for the harvested water. Furthermore, they illustrate the practical use of the newly developed BioRTC model, enabling researchers and practitioners to explore and assess potential RTC strategies and scenarios quickly and cost-effectively.

The effect of ratios upon improving patient-based real-time quality control (PBRTQC) performance.

Large biological variation hinders application of patient-based real-time quality control (PBRTQC). The effect of analyte ratios on the ability of PBRTQC to improve error detection was investigated. Four single analyte-ratio pairs (alanine aminotransferase [ALT] vs. ALT to aspartate aminotransferase ratio [RALT]; creatinine [Cr] vs. Cr to cystatin C ratio [RCr]; lactate dehydrogenase [LDH] vs. LDH to hydroxybutyrate dehydrogenase ratio [RLDH]; total bilirubin [TB] vs. TB to direct bilirubin ratio [RTB]) were chosen for comparison. Various procedures, including four conventional algorithms (moving average [MA], moving median [MM], exponentially weighted moving average [EWMA] and moving standard deviation [MSD]) were assessed. A new algorithm that monitors the number of defect reports per analytical run (NDR) was also evaluated. When a single analyte and calculated ratio used the same PBRTQC parameters, fewer samples were needed to detect systematic errors (SE) by taking ratios (p<0.05). Application of ratios in MA, MM and EWMA significantly enhanced their ability to detect SE. The influence of ratio on random error (RE) detection depended upon the analytes and PBRTQC parameters, as consistent advantage was not demonstrated. The NDR method performed well when appropriate parameters were used, but was only effective for unilateral SE. Rearrangement of sample order led to a significant deterioration of conventional algorithms' performance, while NDR remained almost unaffected. For analytes with large variation and poor PBRTQC performance, using ratios as PBRTQC indexes may significantly improve performance and achieve better anti-interference ability, providing a new class of monitoring indicators for PBRTQC.

Energy Efficient Resource Allocation in 5G RAN Slicing with Grey Wolf Optimization

The massive connections and the real time control applications have different requirement on delay, energy, rate and reliability of the system. In order to meet the diversified 5G requirements, network slicing technique guarantees on the wide scale applications. In this paper, we have proposed a dynamic resource allocation system with two time scale. The one time scale is used for the resource allocation in the system and the other is used for optimized use of latency and power. Lyapunov drift function is used for the balance between the power consumption and the user satisfaction. Further, Grey Wolf Optimization (GWO) is used for the resource allocation strategy so as to gain the reliability of the system with heterogeneous requirements. The proposed methodology shows the improvement of 27% in user satisfaction and 17.5% in power consumption. The proposed framework can be utilized for the rate as well as latency sensitive applications in 5G.

Static-to-kinematic modeling and experimental validation of tendon-driven quasi continuum manipulators with nonconstant subsegment stiffness

Continuum robots with high flexibility and compliance have the capability to operate in confined and cluttered environments. To enhance the load capacity while maintaining robot dexterity, we propose a novel non-constant subsegment stiffness structure for tendon-driven quasi continuum robots (TDQCRs) comprising rigid-flexible coupling subsegments. Aiming at real-time control applications, we present a novel static-to-kinematic modeling approach to gain a comprehensive understanding of the TDQCR model. The analytical subsegment-based kinematics for the multisection manipulator is derived based on screw theory and product of exponentials formula, and the static model considering gravity loading, actuation loading, and robot constitutive laws is established. Additionally, the effect of tension attenuation caused by routing channel friction is considered in the robot statics, resulting in improved model accuracy. The root-mean-square error between the outputs of the static model and the experimental system is less than 1.63% of the arm length (0.5 m). By employing the proposed static model, a mapping of bending angles between the configuration space and the subsegment space is established. Furthermore, motion control experiments are conducted on our TDQCR system, and the results demonstrate the effectiveness of the static-to-kinematic model.

Adaptive control concepts using radial basis functions and a Kalman filter for embedded control applications

Look-up tables or semi-physical models are used in engine control application to enhance the transient control performance. However, the calibration of these look-up tables and/or semi-physical models is highly data dependent, requires significant calibration effort, and does not account for effects such as hardware aging, drifts, fuel variations, etc. To address these challenges, this paper presents a generic adaptive control concept for real-time engine control applications. The boundary conditions for the operation on a state-of-the-art engine control unit (ECU) are considered and Radial Basis Function (RBF)-based neural networks are identified for the approximation of non-linear models. To ensure optimal convergence and un-susceptibility to signal noise, a Kalman filter (KF) is exploited for training the RBF network and a modified approximation is derived in this work. The derived KF approximation shows ∼30% better training performance in comparison to the approximation without variable noise consideration. The developed control concept is validated on an engine test bench and a demonstrator vehicle using a Rapid Control Prototyping (RCP) system. The potential of the developed control concept to ensure optimal control response and robustness has been demonstrated.

MI-based BCI with accurate real-time three-class classification processing and light control application.

The use of brain-computer interfaces (BCIs) to control intelligent devices is a current and future research direction. However, the challenges of low accuracy of real-time recognition and the need for multiple electroencephalographic channels are yet to be overcome. While a number of research teams have proposed many ways to improve offline classification accuracy, the potential problems in real-time experiments are often overlooked. In this study, we proposed a label-based channel diversion preprocessing to solve the problem of low real-time classification accuracy. The Tikhonov regularised common spatial-pattern algorithm (TRCSP) and one vs rest support vector machine (OVR-SVM) were used for feature extraction and pattern classification. High accuracy was achieved in real-time three-class classification using only three channels (average real-time accuracy of 87.46%, with a maximum of 90.33%). In addition, the stability and reliability of the system were verified through lighting control experiments in a real environment. Using the autonomy of MI and real-time feedback of light brightness, we have built a fully autonomous interactive system. The improvement in the real-time classification accuracy in this study is of great significance to the industrialisation of BCI.

Energy-Aware Real-Time Scheduling of Multiple Periodic DAGs on Heterogeneous Systems

Many of today’s complex Cyber-Physical Systems (CPSs) are represented as a set of independent co-executing real-time control applications, where each such application is represented as a precedence-constrained task graph. The applications execute in infinite loops, periodically acquiring data from the environment through sensors at a particular frequency, processing the same, and then producing processed data via actuators. These CPSs often execute under stringent resource constraints (such as limited energy budgets) in distributed networked environments and may be heterogeneous to be able to satisfactorily meet stipulated performance specifications. This work presents a list-based energy-aware scheduler called DPMRS for a set of real-time control applications co-executing in a heterogeneous distributed environment. DPMRS introduces a novel approach for the integrated behavioural representation of a set of co-executing real-time DAG-structured applications. Each task in this integrated representation is then scheduled by determining its relative execution start time on a particular processor, which operates at an appropriately chosen frequency when the task runs on this processor. The overall objective of DPMRS is to minimize aggregate energy consumed in the execution of all tasks. The efficacy of the proposed scheduler has been exhibited through extensive simulation experiments using benchmark task graphs from different application domains. Additionally, a case study on automotive control systems has been included to show the applicability of the proposed work in real world settings.

A deep-learning-technique-based data-driven model for accurate and rapid flood predictions in temporal and spatial dimensions

Abstract. An accurate and rapid urban flood prediction model is essential to support decision-making for flood management. This study developed a deep-learning-technique-based data-driven model for flood predictions in both temporal and spatial dimensions, based on an integration of long short-term memory (LSTM) network, Bayesian optimization, and transfer learning techniques. A case study in northern China was applied to test the model performance, and the results clearly showed that the model can accurately predict the maximum water depths and flood time series for various hyetograph inputs, with substantial improvements in the computation time. The model predicted flood maps 19 585 times faster than the physically based hydrodynamic model and achieved a mean relative error of 9.5 %. For retrieving the spatial patterns of water depths, the degree of similarity of the flood maps was very high. In a best case scenario, the difference between the ground truth and model prediction was only 0.76 %, and the spatial distributions of inundated paths and areas were almost identical. With the adoption of transfer learning, the proposed model was well applied to a new case study and showed robust compatibility and generalization ability. Our model was further compared with two baseline prediction algorithms (artificial neural network and convolutional neural network) to validate the model superiority. The proposed model can potentially replace and/or complement the conventional hydrodynamic model for urban flood assessment and management, particularly in applications of real-time control, optimization, and emergency design and planning.

Demonstration of ITER Real-Time Framework with application of PF coil control in KSTAR

ITER Real-Time Framework (RTF) is a middleware for developing fast real-time control applications such as plasma control system (PCS). In this framework, applications are built by creating and assembling Function Blocks (FBs) as atomic components of the application. The RTF can easily configure the application to be operated with multi-thread, multi-process, or multi-node processing under real-time mode. In this paper, we demonstrated capability of the RTF on the Poloidal Field (PF) coil Magnetic Power Supply (MPS) system of KSTAR. First, we fully implemented the KSTAR PF coil control logic from the KSTAR PCS into an independent RTF application. By configuring the real-time mode and multi-thread processing, 11 PF coils can be simultaneously controlled with a 20 KHz execution cycle. Second, we applied a built-in exception handler in the RTF to implementing protection from specified off-normal events such as PF Power Supply Fault (PSF) and PF OverCurrent Fault (OCF). Third, we integrated the standard real-time network interfaces of the KSTAR, the Reflective Memory (RFM) network, with the RTF application. Finally, we made a shot automation interface in order to run the RTF application according to the KSTAR shot sequence stages. This interface also has a snapshot functionality to store and load all experimental parameters for each shot number. We evaluated the effectiveness of the RTF application through a single PF MPS test connected with a 40 mH dummy load coil.