Model Adaptive Control Research Articles

Automated vehicle’s behavior decision making using deep reinforcement learning and high-fidelity simulation environment

Automated vehicles (AVs) are deemed to be the key element for the intelligent transportation system in the future. Many studies have been made to improve AVs’ ability of environment recognition and vehicle control, while the attention paid to decision making is not enough and the existing decision algorithms are very preliminary. Therefore, a framework of the decision-making training and learning is put forward in this paper. It consists of two parts: the deep reinforcement learning (DRL) training program and the high-fidelity virtual simulation environment. Then the basic microscopic behavior, car-following (CF), is trained within this framework. In addition, theoretical analysis and experiments were conducted to evaluate the proposed reward functions for accelerating training using DRL. The results show that on the premise of driving comfort, the efficiency of the trained AV increases 7.9% and 3.8% respectively compared to the classical adaptive cruise control models, intelligent driver model and constant-time headway policy. Moreover, on a more complex three-lane section, we trained an integrated model combining both CF and lane-changing behavior, with the average speed further growing 2.4%. It indicates that our framework is effective for AV’s decision-making learning.

SYNTHESIS AND ANALYSIS OF ARC FURNACE ELECTRICAL MODE CONTROL SYSTEM ON THE BASIS OF THREE-DIMENSIONAL PHASE CURRENTS VECTOR DISTRIBUTION

Goal. The purpose of the article is to create the method for the operative synthesis of an arc steel-melting furnace (ASF) electric mode (EM) control signal on the basis of a three-dimensional arc currents vector, which takes into account the stochastic nature of the processes in the melting space and power circuit and has low sensitivity to the control object parameters changes, as well as development of the control system structure for its implementation. Method. The basis of the created control method is formed on the statistical theory of dynamical systems, as well as the provisions of the statistical theory of optimal control based on the Fokker-Planck-Kolmogorov equation, which enables to synthesize operational control by the criterion of approaching the regulated coordinate distribution density to the d-function, that is to minimize the dispersion of the three-dimensional furnace phases arc currents vector. Results. The system of equations for operational real-time calculation of control influences of the thyristor switch of phase inductors, included in the power supply circuits of three-phase arcs, and the structural scheme of the adaptive contour for the formation of three-dimensional phase currents vector dispersion for the implementation of adaptive optimal control were obtained. Scientific novelty. For the first time, based on the Fokker-Planck-Kolmogorov equation, we obtain a system of equations representing a mathematical model of a stochastic adaptive optimal control of the arc furnace electric mode by the criterion of a minimum dispersion of three-dimensional phase (arcs) currents vector, which enables, in comparison with known methods, to increase dynamic precision of the arc currents stabilization at the level set by the criteria of energy efficiency and electromagnetic compatibility values. Practical value. The use of the proposed adaptive optimal control model and structural system scheme for its implementation allows, in comparison with the serial arc power regulators, to improve the dynamic accuracy of the arc current currents stabilization at the level of given optimal settings and, based on this, to improve the energy efficiency and electromagnetic compatibility indices of the arc furnace and power supply network.

High-throughput LC-MS quantitation of cell culture metabolites

Monitoring cell culture metabolites, including media components and cellular byproducts, during bio manufacturing is critical for gaining insights into cell growth, productivity and product quality. Historically, cell culture metabolite analysis was a complicated process requiring several orthogonal methods to cover the large number of metabolites with diverse properties over wide concentration ranges. These off-line analyses are time consuming and not suitable for real time bioreactor monitoring. In this study, we present a high-throughput LC-MS method with a 17-min cycle time that is capable of simultaneously monitoring 93 cell culture metabolites, including amino acids, nucleic acids, vitamins, sugars and others. This method has high precision and accuracy and has been successfully applied to the daily profiling of bioreactors and raw material qualification. Information obtained in these studies has been used to identify limiting amino acids during production, which guided adjustments to the feed strategy that prevented the potential misincorporation of amino acids. This type of metabolite profiling can be further utilized to build predictive process models for adaptive feedback control and pave the road for continuous manufacturing and real-time release testing.

ANALYTICAL MODEL FOR COMPENSATING MOTION ERROR IN THE ADAPTIVE MOTION CONTROL OF THE BIOMECHANICAL SYSTEM

Aim. The article deals with developing software to simulate the motion of an object with the given parameters of initial and final phase status. Materials and methods. A motion error in sports exercise is the result of kinematic deviation from the parameters of a given motion program. The mathematical apparatus of adaptive control allows neutralizing motion mistakes between a program and a real trajectory. It is based on utilising the information about current parameters of a phase status of a moving object in a mathematical structure of the control function. The article proposes and experimentally proves the hypothesis about the computer synthesis of motions in biomechanical systems based on the mathematical apparatus of adaptive control. In the computational experiments, a mathematical description of an object is based on a well-established law of open-time approximation (A.P. Batenko, 1977), which requires that both velocity and coordinates simultaneously take the given values. Motion time in this law is an uncontrolled parameter. The mathematical model of a moving object is built as a system of a first-order differential equation. Results. A mathematical model describing the motion of a material point with given phase coordinates at the initial and final points in time is implemented in a computer program. The program works based on the integrated development environment Visual Studio Express 2013 and the Visual Basic 2010 language environment. Conclusion. The developed computer model of adaptive control achieves the aim of any motion, which implies transferring an object from a given initial state to the required final state.

Stability analysis and the fundamental diagram for mixed connected automated and human-driven vehicles

With the development of connected automated vehicles (CAVs), traffic flow on the road is generally mixed with human-driven vehicles (HDVs) and CAVs. In this paper, the full velocity difference (FVD) model and cooperative adaptive cruise control (CACC) model validated by PATH laboratory of University of California, Berkeley, are used to describe the car-following (CF) driving behavior of HDVs and CAVs, respectively. Firstly, an analytical method for the stability of mixed traffic flow is developed and the stability conditions under different penetration rates of CAVs are obtained. Then, the fundamental diagram model of mixed traffic flow under different penetration rates is derived and the influence factors of the fundamental diagram are analyzed. Finally, a simulation experiment is designed to verify the effectiveness of the proposed model. The simulation results show that there are some differences between the simulation data and the theoretical results under different penetration rates. The simulation data are fluctuating, but they are both on the theoretical curve. The overall trend is consistent with the theoretical results, which proves the validity of the fundamental diagram analysis results.

Analyzing Passive BCI Signals to Control Adaptive Automation Devices.

Brain computer interfaces are currently considered to greatly enhance assistive technologies and improve the experiences of people with special needs in the workplace. The proposed adaptive control model for smart offices provides a complete prototype that senses an environment’s temperature and lighting and responds to users’ feelings in terms of their comfort and engagement levels. The model comprises the following components: (a) sensors to sense the environment, including temperature and brightness sensors, and a headset that collects electroencephalogram (EEG) signals, which represent workers’ comfort levels; (b) an application that analyzes workers’ feelings regarding their willingness to adjust to a space based on an analysis of collected data and that determines workers’ attention levels and, thus, engagement; and (c) actuators to adjust the temperature and/or lighting. This research implemented independent component analysis to remove eye movement artifacts from the EEG signals and used an engagement index to calculate engagement levels. This research is expected to add value to research on smart city infrastructures and on assistive technologies to increase productivity in smart offices.

Time-delay feedback cooperative adaptive cruise control of connected vehicles by heterogeneous channel transmission

In this paper, we consider the cooperative adaptive cruise control problem of connected autonomous vehicles networked by heterogeneous wireless channel transmission. The cooperative adaptive cruise control model with variable input delays is established to describe the varying time-delays induced from vehicular actuators and heterogeneous channel transmission. Then a set of decentralized time-delay feedback cooperative adaptive cruise control controllers is computed in such way that each vehicle evaluates its own adaptive cruise control strategy using only neighborhood information. In order to establish string stability of the connected vehicle platoon with the decentralized controllers, the sufficient conditions are obtained in the form of linear matrix inequalities. The scenarios, consisting of four different cars with three heterogeneous wireless channels, are used to demonstrate the effectiveness of the presented method.

A novel adaptive model predictive controller for load frequency control of power systems integrated with DFIG wind turbines

With the rapid growth of renewable energy resources, wind energy system is getting more interest everywhere throughout the world. However, its extensive use in power systems prompts many power system dynamics and stability problems. Load variation and anomalous operating conditions prompt inconsistencies in frequency and planned power trades. These inconsistencies should be remedied by load frequency control. This paper introduces a novel frequency control system utilizing a mix of adaptive model predictive controller (AMPC) and recursive polynomial model estimator (RPME) integrated with double fed induction generator wind turbines. Inside each control duration, the RPME is identifying a discrete-time online autoregressive exogenous model. The latter is used through the AMPC to update the interior plant model in order to achieve a successful nonlinear control. The performance of the proposed system has been verified and contrasted with the conventional MPC system through a computer simulation-based MATLAB/SIMULINK. The simulation results demonstrated the superiority of the proposed system as for the conventional MPC system.

Research of the Mathematical Model of Adaptive Control of Conflict Flows of Inhomogeneous demands

Research of the Mathematical Model of Adaptive Control of Conflict Flows of Inhomogeneous demands

Research on the Adaptive Control in Sugar Evaporative Crystallization Using LSSVM and SaDE-ELM

Abstract The process of sugar evaporative crystallization is a nonlinear process with large time lag and strong coupling. It is difficult to establish a reasonable mechanism model. In this paper, we use the data driving modeling method to establish an Adaptive Control model for batch boiling sugar crystallization process. First, by analyzing the main influencing factors of the evaporative crystallization process of intermittent boiling sugar, the most important two parameters, brix and liquid level, are selected as the control object. The self-adaptive differential evolution Extreme Learning Machine (SaDE-ELM) is used to construct the control model. A least squares support vector machine (LSSVM) is established and connected in the control loop to control the opening of the feed valve so that to control the feed flowrate according to the objective values of syrup Brix and liquid level. Experiments are conducted and the obtained data are used to train and verify the learning machines. Experiments indicate that the learning machines are able to realize adaptive control to key parameters of the crystallization process. Comparison of different neural networks indicates that the LSSVM performs better than BP, RBF and ELM and SaDE-ELM with prediction error of below 0.01, and training time of below 0.05 s.

Design of Adaptive Internal Control Model on Binary Distillation Column

The binary distillation column is one of the most important operating units in chemical engineering. Wood & Berry binary distillation columns separate feed streams (F, XF) into top products (D, XD) and bottom products (B, XB). The control design in the binary distillation column has several constraints caused by non-linearity of the process, multivariable interactions, and presence of a disturbance. Based on that constraints, it needs a modern control method that can make the system response to track the set point change and reduce or eliminate the disturbances, so the product composition output as desired. Adaptive Internal Model Control 2 Degree of Freedom (AIMC 2 DoF) method is one of the modern control methods that are capable of controlling multivariable plants and reduce or eliminate existing disturbances. Based on all the tests performed, the AIMC 2 DoF controller using Skogestad filter parameter tuning method has the smallest IAE value compared to the other methods.

A Two-Level Rolling Optimization Model for Real-time Adaptive Signal Control

Recently, dynamic traffic flow prediction models have increasingly been developed in a connected vehicle environment, which will be conducive to the development of more advanced traffic signal control systems. This paper proposes a rolling optimization model for real-time adaptive signal control based on a dynamic traffic flow model. The proposed method consists of two levels, i.e., barrier group and phase. The upper layer optimizes the length of the barrier group based on dynamic programming. The lower level optimizes the signal phase lengths with the objective of minimizing vehicle delay. Then, to capture the dynamic traffic flow, a rolling strategy was developed based on a real-time traffic flow prediction model. Finally, the proposed method was compared to the Controlled Optimization of Phases (COP) algorithm in a simulation experiment. The results showed that the average vehicle delay was significantly reduced, by as much as 17.95%, using the proposed method.

Fuzzy Logic with Expert Judgment to Implement an Adaptive Risk-Based Access Control Model for IoT

The Internet of Things (IoT) is becoming the future of the Internet with a large number of connected devices that are predicted to reach about 50 billion by 2020. With proliferation of IoT devices and need to increase information sharing in IoT applications, risk-based access control model has become the best candidate for both academic and commercial organizations to address access control issues. This model carries out a security risk analysis on the access request by using IoT contextual information to provide access decisions dynamically. This model solves challenges related to flexibility and scalability of the IoT system. Therefore, we propose an adaptive risk-based access control model for the IoT. This model uses real-time contextual information associated with the requesting user to calculate the security risk regarding each access request. It uses user attributes while making the access request, action severity, resource sensitivity and user risk history as inputs to analyze and calculate the risk value to determine the access decision. To detect abnormal and malicious actions, smart contracts are used to track and monitor user activities during the access session to detect and prevent potential security violations. In addition, as the risk estimation process is the essential stage to build a risk-based model, this paper provides a discussion of common risk estimation methods and then proposes the fuzzy inference system with expert judgment as to be the optimal approach to handle risk estimation process of the proposed risk-based model in the IoT system.

Tuning and Feasibility Analysis of Classical First-Order MIMO Non-Linear Sliding Mode Control Design for Industrial Applications

Model-based control techniques have been gaining more and more interest these days. These complex control systems are mostly based on theories, such as feedback linearization, model predictive control, adaptive and robust control. In this paper the latter approach is investigated, in particular, sliding mode (SM) control is analyzed. While several works on the description and application of SM control on single-input single-output systems can easily be found, its application on multi-input multi-output systems is not examined in depth at the same level. Hence, this work aims at formalizing some theoretical complements about the necessary conditions for the feasibility of the SM control for multi-input-multi-output systems. Furthermore, in order to obtain the desired performance from the control system, a method for parameter tuning is proposed in the particular case in which the relative degree of the controlled channels is equal to one. Finally, a simple control problem example is shown with the aim of stressing the benefits derived from the application of the theoretical complements described here.

Adaptive Human Control Model and its Usability in Modeling of Human-in-the-loop Cyber Physical Systems

This paper discusses usability of an adaptive human control model in the context of a simple Human-in-the-loop Cyber Physical Systems (HiLCPS). The first part of the paper characterizes human factor assessment with an emphasis on the modeling of human behavior. This section is followed by a description of the human control model structure, including a definition of the individual components and their roles during the control phases. Exploiting relevant theoretical background, the authors present an example of a human controller comprising the feedback component and two different implementations of a pursuit controller. The parameters of the controllers are obtained from data measured on a flight simulator controlled by a pilot during the defined task. The first results presented in this paper indicate the possibility of use the described human control structure in HiLCPS modeling and its potential for other, more complex experiments within human factor assessment.

A simplified model of gas turbine unit adaptive control

The article explores the possibilities of building automatic control systems for gas turbine power plants. The use of the principles of adaptive control with a reference model and a signal effect is being studied. As an adaptation method, a method based on the Lyapunov function is used, in order to reduce the time for searching for an extremum. There is a need to ensure the specified indicators of electricity the quality in a constantly changing electrical load and changes in operating modes of the power plant in gas turbine units. The article presents a model of a gas turbine installation for the study of adaptive control. It is shown that the improvement of one coordinate is possible to obtain due to some deterioration of the other coordinate. For further study of this problem, a simplified second-order dynamic model has been constructed. With the help of such a model, complex studies of various stages of adaptive control were carried out. Results were obtained by varying the parameters of adaptive control and simulation parameters. The research results are designed to find the optimal ratios of adaptive automatic control systems parameters for power industry gas turbine plants.

A risk adaptive access control model based on Markov for big data in the cloud

The main problems of the application of access control in the cloud are the necessary flexibility and scalability to support a large number of users and resources in a dynamic and heterogeneous environment, with collaboration and information sharing needs. This paper proposes a risk self-adaptive dynamic access control model, based on Markov chain and Shannon information theory, for big data that stored and processed by cloud. In this model, a simple formal adversary model, a modification of XACML framework including some new and enhanced components, Markov-based methods for calculating the risk values of access requests, and an incentive mechanism for supervising all the access behaviours of subjects are proposed, successively. Our method is easy to deploy and the administrator just need to label the object data. This method is more effective and suitable to control the access in large-scale information system, and protect the sensitive and privacy data.

Networked Model for Cooperative Adaptive Cruise Control

This paper proposes a cooperative adaptive cruise control model, adding a communication network structure to an existing model that has been shown to capture real commercial adaptive cruise control vehicle behavior. The proposed model is interesting because it only requires minimal information sharing, facilitating the creation of platoons comprised of vehicles from different manufacturers. We prove the stability of the model and discuss string stability. Algorithms for estimating the velocity of the vehicles locally and for estimating the velocities of all the vehicles in the platoon are presented. We simulate vehicle platoon control with the lead vehicle following an experimentally collected trajectory, showing that adding communication can cause a string unstable platoon to become stable.

A risk adaptive access control model based on Markov for big data in the cloud

The main problems of the application of access control in the cloud are the necessary flexibility and scalability to support a large number of users and resources in a dynamic and heterogeneous environment, with collaboration and information sharing needs. This paper proposes a risk self-adaptive dynamic access control model, based on Markov chain and Shannon information theory, for big data that stored and processed by cloud. In this model, a simple formal adversary model, a modification of XACML framework including some new and enhanced components, Markov-based methods for calculating the risk values of access requests, and an incentive mechanism for supervising all the access behaviours of subjects are proposed, successively. Our method is easy to deploy and the administrator just need to label the object data. This method is more effective and suitable to control the access in large-scale information system, and protect the sensitive and privacy data.

Analysis of models applied for modeling of adaptive control for thermal energy storage system. Part 1. Models of solar collector

Analysis of models applied for modeling of adaptive control for thermal energy storage system. Part 1. Models of solar collector