A deep reinforcement learning approach to gasoline blending real-time optimization under uncertainty

The gasoline inline blending process has widely used real-time optimization techniques to achieve optimization objectives,such as minimizing the cost of production.However,the effectiveness of real-time optimization in gasoline blending relies on accurate blending models and is challenged by stochastic disturbances.Thus,we propose a real-time optimization algorithm based on the soft actor-critic(SAC)deep reinforcement learning strategy to optimize gasoline blending without relying on a single blending model and to be robust against disturbances.Our approach constructs the environment using nonlinear blending models and feedstocks with disturbances.The algorithm incorporates the Lagrange multiplier and path constraints in reward design to manage sparse product constraints.Carefully abstracted states facilitate algorithm convergence,and the normalized action vector in each optimization period allows the agent to generalize to some extent across different target production scenarios.Through these well-designed components,the algorithm based on the SAC outperforms real-time optimization methods based on either nonlinear or linear programming.It even demonstrates comparable performance with the time-horizon based real-time optimization method,which requires knowledge of uncertainty models,confirming its capability to handle uncertainty without accurate models.Our simulation illustrates a promising approach to free real-time optimization of the gasoline blending process from uncertainty models that are difficult to acquire in practice.

Dynamic Resistance and Energy Absorption of Sandwich Beam via a Micro-Topology Optimization

The current research of sandwich structures under dynamic loading mainly focus on the response characteristic of structure.The micro-topology of core layers would sufficiently influence the property of sandwich structure.However,the micro deformation and topology mechanism of structural deformation and energy absorption are unclear.In this paper,based on the bi-directional evolutionary structural optimization method and periodic base cell(PBC)technology,a topology optimization frame work is proposed to optimize the core layer of sandwich beams.The objective of the present optimization problem is to maximize shear stiffness of PBC with a volume constraint.The effects of the volume fraction,filter radius,and initial PBC aspect ratio on the micro-topology of the core were discussed.The dynamic response process,core compression,and energy absorption capacity of the sandwich beams under blast impact loading were analyzed by the finite element method.The results demonstrated that the overpressure action stage was coupled with the core compression stage.Under the same loading and mass per unit area,the sandwich beam with a 20%volume fraction core layer had the best blast resistance.The filter radius has a slight effect on the shear stiffness and blast resistances of the sandwich beams.But increasing the filter radius could slightly improve the bending stiffness.Upon changing the initial PBC aspect ratio,there are three ways for PBC evolution:The first is to change the angle between the adjacent bars,the second is to further form holes in the bars,and the third is to combine the first two ways.However,not all three ways can improve the energy absorption capacity of the structure.Changing the aspect ratio of the PBC arbitrarily may lead to worse results.More studies are necessary for further detailed optimization.This research proposes a new topology sandwich beam structure by micro-topology optimization,which has sufficient shear stiffness.The micro mechanism of structural energy absorption is clarified,it is significant for structural energy absorption design.

Stability and accuracy of central difference method for real-time dynamic substructure testing considering mass participation coefficient

For real-time dynamic substructure testing(RTDST),the influence of the inertia force of fluid specimens on the stability and accuracy of the integration algorithms has never been investigated.Therefore,this study proposes to investigate the stability and accuracy of the central difference method(CDM)for RTDST considering the specimen mass participation coefficient.First,the theory of the CDM for RTDST is presented.Next,the stability and accuracy of the CDM for RTDST considering the specimen mass participation coefficient are investigated.Finally,numerical simulations and experimental tests are conducted for verifying the effectiveness of the method.The study indicates that the stability of the algorithm is affected by the mass participation coefficient of the specimen,and the stability limit first increases and then decreases as the mass participation coefficient increases.In most cases,the mass participation coefficient will increase the stability limit of the algorithm,but in specific circumstances,the algorithm may lose its stability.The stability and accuracy of the CDM considering the mass participation coefficient are verified by numerical simulations and experimental tests on a three-story frame structure with a tuned liquid damper.

An adaptive machine learning-based optimization method in the aerodynamic analysis of a finite wing under various cruise conditions

Conventional wing aerodynamic optimization processes can be time-consuming and imprecise due to the complexity of versatile flight missions.Plenty of existing literature has considered two-dimensional infinite airfoil optimization,while three-dimensional finite wing optimizations are subject to limited study because of high computational costs.Here we create an adaptive optimization methodology built upon digitized wing shape deformation and deep learning algorithms,which enable the rapid formulation of finite wing designs for specific aerodynamic performance demands under different cruise conditions.This methodology unfolds in three stages:radial basis function interpolated wing generation,collection of inputs from computational fluid dynamics simulations,and deep neural network that constructs the surrogate model for the optimal wing configuration.It has been demonstrated that the proposed methodology can significantly reduce the computational cost of numerical simulations.It also has the potential to optimize various aerial vehicles undergoing different mission environments,loading conditions,and safety requirements.

Electric Vehicle Charging Load Optimization Strategy Based on Dynamic Time-of-Use Tariff

Electric vehicle(EV)is an ideal solution to resolve the carbon emission issue and the fossil fuels scarcity problem in the future.However,a large number of EVs will be concentrated on charging during the valley hours leading to new load peaks under the guidance of static time-of-use tariff.Therefore,this paper proposes a dynamic time-of-use tariff mechanism,which redefines the peak and valley time periods according to the predicted loads using the fuzzy C-mean(FCM)clustering algorithm,and then dynamically adjusts the peak and valley tariffs according to the actual load of each time period.Based on the proposed tariff mechanism,an EV charging optimization model with the lowest cost to the users and the lowest variance of the grid-side load as the objective function is established.Then,a weight selection principle with an equal loss rate of the two objectives is proposed to transform the multi-objective optimization problem into a single-objective optimization problem.Finally,the EV charging load optimization model under three tariff strategies is set up and solved with the mathematical solver GROUBI.The results show that the EV charging load optimization strategy based on the dynamic time-of-use tariff can better balance the benefits between charging stations and users under different numbers and proportions of EVs connected to the grid,and can effectively reduce the grid load variance and improve the grid load curve.

Optimization and Performance Analysis of Intelligent Video AI Dynamic

In today’s information age,video data,as an important carrier of information,is growing explosively in terms of production volume.The quick and accurate extraction of useful information from massive video data has become a focus of research in the field of computer vision.AI dynamic recognition technology has become one of the key technologies to address this issue due to its powerful data processing capabilities and intelligent recognition functions.Based on this,this paper first elaborates on the development of intelligent video AI dynamic recognition technology,then proposes several optimization strategies for intelligent video AI dynamic recognition technology,and finally analyzes the performance of intelligent video AI dynamic recognition technology for reference.

Suitable region of dynamic optimal interpolation for efficiently altimetry sea surface height mapping

The dynamic optimal interpolation(DOI)method is a technique based on quasi-geostrophic dynamics for merging multi-satellite altimeter along-track observations to generate gridded absolute dynamic topography(ADT).Compared with the linear optimal interpolation(LOI)method,the DOI method can improve the accuracy of gridded ADT locally but with low computational efficiency.Consequently,considering both computational efficiency and accuracy,the DOI method is more suitable to be used only for regional applications.In this study,we propose to evaluate the suitable region for applying the DOI method based on the correlation between the absolute value of the Jacobian operator of the geostrophic stream function and the improvement achieved by the DOI method.After verifying the LOI and DOI methods,the suitable region was investigated in three typical areas:the Gulf Stream(25°N-50°N,55°W-80°W),the Japanese Kuroshio(25°N-45°N,135°E-155°E),and the South China Sea(5°N-25°N,100°E-125°E).We propose to use the DOI method only in regions outside the equatorial region and where the absolute value of the Jacobian operator of the geostrophic stream function is higher than1×10^(-11).

Dynamics modeling and optimal control for multi-information diffusion in Social Internet of Things

As an ingenious convergence between the Internet of Things and social networks,the Social Internet of Things(SIoT)can provide effective and intelligent information services and has become one of the main platforms for people to spread and share information.Nevertheless,SIoT is characterized by high openness and autonomy,multiple kinds of information can spread rapidly,freely and cooperatively in SIoT,which makes it challenging to accurately reveal the characteristics of the information diffusion process and effectively control its diffusion.To this end,with the aim of exploring multi-information cooperative diffusion processes in SIoT,we first develop a dynamics model for multi-information cooperative diffusion based on the system dynamics theory in this paper.Subsequently,the characteristics and laws of the dynamical evolution process of multi-information cooperative diffusion are theoretically investigated,and the diffusion trend is predicted.On this basis,to further control the multi-information cooperative diffusion process efficiently,we propose two control strategies for information diffusion with control objectives,develop an optimal control system for the multi-information cooperative diffusion process,and propose the corresponding optimal control method.The optimal solution distribution of the control strategy satisfying the control system constraints and the control budget constraints is solved using the optimal control theory.Finally,extensive simulation experiments based on real dataset from Twitter validate the correctness and effectiveness of the proposed model,strategy and method.

Optimal Design of the Modular Joint Drive Train for Enhancing Cobot Load Capacity and Dynamic Performance

Automation advancements prompts the extensive integration of collaborative robot(cobot)across a range of industries.Compared to the commonly used design approach of increasing the payload-to-weight ratio of cobot to enhance load capacity,equal attention should be paid to the dynamic response characteristics of cobot during the design process to make the cobot more flexible.In this paper,a new method for designing the drive train parameters of cobot is proposed.Firstly,based on the analysis of factors influencing the load capacity and dynamic response characteristics,design criteria for both aspects are established for cobot with all optimization design criteria normalized within the design domain.Secondly,with the cobot in the horizontal pose,the motor design scheme is discretized and it takes the joint motor diameter and gearbox speed ratio as optimization design variables.Finally,all the discrete values of the optimization objectives are obtained through the enumeration method and the Pareto front is used to select the optimal solution through multi-objective optimization.Base on the cobot design method proposed in this paper,a six-axis cobot is designed and compared with the commercial cobot.The result shows that the load capacity of the designed cobot in this paper reaches 8.4 kg,surpassing the 5 kg load capacity commercial cobot which is used as a benchmark.The minimum resonance frequency of the joints is 42.70 Hz.

Dynamic optimal allocation of energy storage systems integrated within photovoltaic based on a dual timescale dynamics model

Energy storage systems(ESSs)operate as independent market participants and collaborate with photovoltaic(PV)generation units to enhance the flexible power supply capabilities of PV units.However,the dynamic variations in the profitability of ESSs in the electricity market are yet to be fully understood.This study introduces a dual-timescale dynamics model that integrates a spot market clearing(SMC)model into a system dynamics(SD)model to investigate the profit-aware capacity growth of ESSs and compares the profitability of independent energy storage systems(IESSs)with that of an ESS integrated within a PV(PV-ESS).Furthermore,this study aims to ascertain the optimal allocation of the PV-ESS.First,SD and SMC models were set up.Second,the SMC model simulated on an hourly timescale was incorporated into the SD model as a subsystem,a dual-timescale model was constructed.Finally,a development simulation and profitability analysis was conducted from 2022 to 2040 to reveal the dynamic optimal range of PV-ESS allocation.Additionally,negative electricity prices were considered during clearing processes.The simulation results revealed differences in profitability and capacity growth between IESS and PV-ESS,helping grid investors and policymakers to determine the boundaries of ESSs and dynamic optimal allocation of PV-ESSs.

Data network traffic analysis and optimization strategy of real-time power grid dynamic monitoring system for wide-frequency measurements

The application and development of a wide-area measurement system(WAMS)has enabled many applications and led to several requirements based on dynamic measurement data.Such data are transmitted as big data information flow.To ensure effective transmission of wide-frequency electrical information by the communication protocol of a WAMS,this study performs real-time traffic monitoring and analysis of the data network of a power information system,and establishes corresponding network optimization strategies to solve existing transmission problems.This study utilizes the traffic analysis results obtained using the current real-time dynamic monitoring system to design an optimization strategy,covering the optimization in three progressive levels:the underlying communication protocol,source data,and transmission process.Optimization of the system structure and scheduling optimization of data information are validated to be feasible and practical via tests.

Transmission Dynamics and Optimal Control Strategies of a Hand-Foot-Mouth Disease Model with Treatment and Vaccination Interventions

In this article, the transmission dynamics of a Hand-Foot-Mouth disease model with treatment and vaccination interventions are studied. We calculated the basic reproduction number and proved the global stability of disease-free equilibrium when R0 R0 > 1. Meanwhile, we obtained the optimal control strategies minimizing the cost of intervention and minimizing the infected person. We also give some numerical simulations to verify our theoretical results.

Evolutionary-assisted reinforcement learning for reservoir real-time production optimization under uncertainty

Production optimization has gained increasing attention from the smart oilfield community because it can increase economic benefits and oil recovery substantially.While existing methods could produce high-optimality results,they cannot be applied to real-time optimization for large-scale reservoirs due to high computational demands.In addition,most methods generally assume that the reservoir model is deterministic and ignore the uncertainty of the subsurface environment,making the obtained scheme unreliable for practical deployment.In this work,an efficient and robust method,namely evolutionaryassisted reinforcement learning(EARL),is proposed to achieve real-time production optimization under uncertainty.Specifically,the production optimization problem is modeled as a Markov decision process in which a reinforcement learning agent interacts with the reservoir simulator to train a control policy that maximizes the specified goals.To deal with the problems of brittle convergence properties and lack of efficient exploration strategies of reinforcement learning approaches,a population-based evolutionary algorithm is introduced to assist the training of agents,which provides diverse exploration experiences and promotes stability and robustness due to its inherent redundancy.Compared with prior methods that only optimize a solution for a particular scenario,the proposed approach trains a policy that can adapt to uncertain environments and make real-time decisions to cope with unknown changes.The trained policy,represented by a deep convolutional neural network,can adaptively adjust the well controls based on different reservoir states.Simulation results on two reservoir models show that the proposed approach not only outperforms the RL and EA methods in terms of optimization efficiency but also has strong robustness and real-time decision capacity.

A strategy for lightweight designing of a railway vehicle car body including composite material and dynamic structural optimization

Rolling stock manufacturers are finding structural solutions to reduce power required by the vehicles,and the lightweight design of the car body represents a possible solution.Optimization processes and innovative materials can be combined in order to achieve this goal.In this framework,we propose the redesign and optimization process of the car body roof for a light rail vehicle,introducing a sandwich structure.Bonded joint was used as a fastening system.The project was carried out on a single car of a modern tram platform.This preliminary numerical work was developed in two main steps:redesign of the car body structure and optimization of the innovated system.Objective of the process was the mass reduction of the whole metallic structure,while the constraint condition was imposed on the first frequency of vibration of the system.The effect of introducing a sandwich panel within the roof assembly was evaluated,focusing on the mechanical and dynamic performances of the whole car body.A mass saving of 63%on the optimized components was achieved,corresponding to a 7.6%if compared to the complete car body shell.In addition,a positive increasing of 17.7%on the first frequency of vibration was observed.Encouraging results have been achieved in terms of weight reduction and mechanical behaviour of the innovated car body.

ROS2 Real-time Performance Optimization and Evaluation

Real-time interaction with uncertain and dynamic environments is essential for robotic systems to achieve functions such as visual perception,force interaction,spatial obstacle avoidance,and motion planning.To ensure the reliability and determinism of system execution,a flexible real-time control system architecture and interaction algorithm are required.The ROS framework was designed to improve the reusability of robotic software development by providing a distributed structure,hardware abstraction,message-passing mechanism,and application prototypes.Rich ecosystems for robotic development have been built around ROS1 and ROS2 architectures based on the Linux system.However,because of the fairness scheduling principle of the default Linux system design and the complexity of the kernel,the system does not have real-time computing.To achieve a balance between real-time and non-real-time computing,this paper uses the transmission mechanism of ROS2,combines it with the scheduling mechanism of the Linux operating system,and uses Preempt_RT to enhance the real-time computing of ROS1 and ROS2.The real-time performance evaluation of ROS1 and ROS2 is conducted from multiple perspectives,including throughput,transmission mode,QoS service quality,frequency,number of subscription nodes and EtherCAT master.This paper makes two significant contributions:firstly,it employs Preempt_RT to optimize the native ROS2 system,effectively enhancing the real-time performance of native ROS2 message transmission;secondly,it conducts a comprehensive evaluation of the real-time performance of both native and optimized ROS2 systems.This comparison elucidates the benefits of the optimized ROS2 architecture regarding real-time performance,with results vividly demonstrated through illustrative figures.

Modified Differential Evolution Algorithm for Solving Dynamic Optimization with Existence of Infeasible Environments

Dynamic constrained optimization is a challenging research topic in which the objective function and/or constraints change over time.In such problems,it is commonly assumed that all problem instances are feasible.In reality some instances can be infeasible due to various practical issues,such as a sudden change in resource requirements or a big change in the availability of resources.Decision-makers have to determine whether a particular instance is feasible or not,as infeasible instances cannot be solved as there are no solutions to implement.In this case,locating the nearest feasible solution would be valuable information for the decision-makers.In this paper,a differential evolution algorithm is proposed for solving dynamic constrained problems that learns from past environments and transfers important knowledge from them to use in solving the current instance and includes a mechanism for suggesting a good feasible solution when an instance is infeasible.To judge the performance of the proposed algorithm,13 well-known dynamic test problems were solved.The results indicate that the proposed algorithm outperforms existing recent algorithms with a margin of 79.40%over all the environments and it can also find a good,but infeasible solution,when an instance is infeasible.

TopSTO:a 115-line code for topology optimization of structures under stationary stochastic dynamic loading

The use of topology optimization in structural design under dynamic excitation is becoming more prevalent in the literature.While many such applications utilize frequency or time domain formulations,relatively few consider stochastic dynamic excitations.This paper presents an efficient and compact code called TopSTO for structural topology optimization considering stationary stochastic dynamic loading using a method derived from random vibration theory.The theory,described in conjunction with the implementation in the provided code,is illustrated for a seismically excited building.This work demonstrates the efficiency of the approach in terms of both the computational resources and minimal amount of code required.This code is intended to serve as a baseline for understanding the theory and implementation of this topology optimization approach and as a foundation for additional applications and developments.

A Smooth Bidirectional Evolutionary Structural Optimization of Vibrational Structures for Natural Frequency and Dynamic Compliance

A smooth bidirectional evolutionary structural optimization(SBESO),as a bidirectional version of SESO is proposed to solve the topological optimization of vibrating continuum structures for natural frequencies and dynamic compliance under the transient load.A weighted function is introduced to regulate the mass and stiffness matrix of an element,which has the inefficient element gradually removed from the design domain as if it were undergoing damage.Aiming at maximizing the natural frequency of a structure,the frequency optimization formulation is proposed using the SBESO technique.The effects of various weight functions including constant,linear and sine functions on structural optimization are compared.With the equivalent static load(ESL)method,the dynamic stiffness optimization of a structure is formulated by the SBESO technique.Numerical examples show that compared with the classic BESO method,the SBESO method can efficiently suppress the excessive element deletion by adjusting the element deletion rate and weight function.It is also found that the proposed SBESO technique can obtain an efficient configuration and smooth boundary and demonstrate the advantages over the classic BESO technique.

WiFi6 Dynamic Channel Optimization Method for Fault Tolerance in Power Communication Network

As the scale of power networks has expanded,the demand for multi-service transmission has gradually increased.The emergence of WiFi6 has improved the transmission efficiency and resource utilization of wireless networks.However,it still cannot cope with situations such as wireless access point(AP)failure.To solve this problem,this paper combines orthogonal fre-quency division multiple access(OFDMA)technology and dynamic channel optimization technology to design a fault-tolerant WiFi6 dynamic resource optimization method for achieving high quality wireless services in a wirelessly covered network even when an AP fails.First,under the premise of AP layout with strong coverage over the whole area,a faulty AP determination method based on beacon frames(BF)is designed.Then,the maximum signal-to-interference ratio(SINR)is used as the principle to select AP reconnection for the affected users.Finally,this paper designs a dynamic access selection model(DASM)for service frames of power Internet of Things(IoTs)and a schedul-ing access optimization model(SAO-MF)based on multi-frame transmission,which enables access optimization for differentiated services.For the above mechanisms,a heuristic resource allocation algorithm is proposed in SAO-MF.Simulation results show that the method can reduce the delay by 15%and improve the throughput by 55%,ensuring high-quality communication in power wireless networks.

A Scheme Library-Based Ant Colony Optimization with 2-Opt Local Search for Dynamic Traveling Salesman Problem

The dynamic traveling salesman problem(DTSP)is significant in logistics distribution in real-world applications in smart cities,but it is uncertain and difficult to solve.This paper proposes a scheme library-based ant colony optimization(ACO)with a two-optimization(2-opt)strategy to solve the DTSP efficiently.The work is novel and contributes to three aspects:problemmodel,optimization framework,and algorithmdesign.Firstly,in the problem model,traditional DTSP models often consider the change of travel distance between two nodes over time,while this paper focuses on a special DTSP model in that the node locations change dynamically over time.Secondly,in the optimization framework,the ACO algorithm is carried out in an offline optimization and online application framework to efficiently reuse the historical information to help fast respond to the dynamic environment.The framework of offline optimization and online application is proposed due to the fact that the environmental change inDTSPis caused by the change of node location,and therefore the newenvironment is somehowsimilar to certain previous environments.This way,in the offline optimization,the solutions for possible environmental changes are optimized in advance,and are stored in a mode scheme library.In the online application,when an environmental change is detected,the candidate solutions stored in the mode scheme library are reused via ACO to improve search efficiency and reduce computational complexity.Thirdly,in the algorithm design,the ACO cooperates with the 2-opt strategy to enhance search efficiency.To evaluate the performance of ACO with 2-opt,we design two challenging DTSP cases with up to 200 and 1379 nodes and compare them with other ACO and genetic algorithms.The experimental results show that ACO with 2-opt can solve the DTSPs effectively.