Scheduling Storage Process of Shuttle-Based Storage and Retrieval Systems Based on Reinforcement Learning

The Shuttle-Based Storage and Retrieval System(SBS/RS)has been widely studied because it is currently the most efficient automated warehousing system.Most of the related existing studies are focused on the prediction and improvement of the efficiency of such a system at the design stage.Hence,the control of existing SBS/RSs has been rarely investigated.In existing SBS/RSs,some empirical rules,such as storing loads column by column,are used to control or schedule the storage process.The question is whether or not the control of the storage process in an existing system can be improved further by using a different approach.The storage process is controlled to minimize the makespan of storing a series of loads into racks.Empirical storage rules are easy to control,but they do not reach the minimum makespan.In this study,the performance of a control system that uses reinforcement learning to schedule the storage process of an SBS/RS with fixed configurations is evaluated.Specifically,a reinforcement learning algorithm called the actor-critic algorithm is used.This algorithm is made up of two neural networks and is effective in making decisions and updating itself.It can also reduce the makespan relative to the existing empirical rules used to improve system performance.Experiment results show that in an SBS/RS comprising six columns and six tiers and featuring a storage capacity of 72 loads,the actor-critic algorithm can reduce the makespan by 6.67%relative to the column-by-column storage rule.The proposed algorithm also reduces the makespan by more than 30%when the number of loads being stored is in the range of 7–45,which is equal to 9.7%–62.5%of the systems’storage capacity.

Brain-Controlled Multi-Robot at Servo-Control Level Based on Nonlinear Model Predictive Control

Using a brain-computer interface(BCI)rather than limbs to control multiple robots(i.e.,brain-controlled multi-robots)can better assist people with disabilities in daily life than a brain-controlled single robot.For example,one person with disabilities can move by a brain-controlled wheelchair(leader robot)and simultaneously transport objects by follower robots.In this paper,we explore how to control the direction,speed,and formation of a brain-controlled multi-robot system(consisting of leader and follower robots)for the first time and propose a novel multi-robot predictive control framework(MRPCF)that can track users'control intents and ensure the safety of multiple robots.The MRPCF consists of the leader controller,follower controller,and formation planner.We build a whole brain-controlled multi-robot physical system for the first time and test the proposed system through human-in-the-loop actual experiments.The experimental results indicate that the proposed system can track users'direction,speed,and formation control intents when guaranteeing multiple robots’safety.This paper can promote the study of brain-controlled robots and multi-robot systems and provide some novel views into human-machine collaboration and integration.

Low-Carbon Routing Based on Improved Artificial Bee Colony Algorithm for Electric Trackless Rubber-Tyred Vehicles

Trackless rubber-tyerd vehicles are the core equipment for auxiliary transportation in inclined-shaft coal mines,and the rationality of their routes plays the direct impact on operation safety and energy consumption.Rich studies have been done on scheduling rubber-tyerd vehicles driven by diesel oil,however,less works are for electric trackless rubber-tyred vehicles.Furthermore,energy consumption of vehicles gives no consideration on the impact of complex roadway and traffic rules on driving,especially the limited cruising ability of electric trackless rubber-tyred vehichles(TRVs).To address this issue,an energy consumption model of an electric trackless rubber-tyred vehicle is formulated,in which the effects from total mass,speed profiles,slope of roadways,and energy management mode are all considered.Following that,a low-carbon routing model of electric trackless rubber-tyred vehicles is built to minimize the total energy consumption under the constraint of vehicle avoidance,allowable load,and endurance power.As a problem-solver,an improved artificial bee colony algorithm is put forward.More especially,an adaptive neighborhood search is designed to guide employed bees to select appropriate operator in a specific space.In order to assign onlookers to some promising food sources reasonably,their selection probability is adaptively adjusted.For a stagnant food source,a knowledge-driven initialization is developed to generate a feasible substitute.The experimental results on four real-world instances indicate that improved artificial bee colony algorithm(IABC)outperforms other comparative algorithms and the special designs in its three phases effectively avoid premature convergence and speed up convergence.

Distributed Flexible Job-Shop Scheduling Problem Based on Hybrid Chemical Reaction Optimization Algorithm

Economic globalization has transformed many manufacturing enterprises from a single-plant production mode to a multi-plant cooperative production mode.The distributed flexible job-shop scheduling problem(DFJSP)has become a research hot topic in the field of scheduling because its production is closer to reality.The research of DFJSP is of great significance to the organization and management of actual production process.To solve the heterogeneous DFJSP with minimal completion time,a hybrid chemical reaction optimization(HCRO)algorithm is proposed in this paper.Firstly,a novel encoding-decoding method for flexible manufacturing unit(FMU)is designed.Secondly,half of initial populations are generated by scheduling rule.Combined with the new solution acceptance method of simulated annealing(SA)algorithm,an improved method of critical-FMU is designed to improve the global and local search ability of the algorithm.Finally,the elitist selection strategy and the orthogonal experimental method are introduced to the algorithm to improve the convergence speed and optimize the algorithm parameters.In the experimental part,the effectiveness of the simulated annealing algorithm and the critical-FMU refinement methods is firstly verified.Secondly,in the comparison with other existing algorithms,the proposed optimal scheduling algorithm is not only effective in homogeneous FMUs examples,but also superior to existing algorithms in heterogeneous FMUs arithmetic cases.

Model Construction and Numerical Simulation for Hydroplaning of Complex Tread Tires

Euler-Lagrange coupling method is used to establish the fluid-structure interaction model for tires with different tread patterns by obtaining the grounding mark and normal contact force between tire and the road surface during tire rolling.The altering of load force,tire pressure,and water film thickness in relation to the effect on tire-road force during both constant speed and critical hydroplaning speed was analyzed.Results show that the critical hydroplaning speed and normal contact force between tire and the road surface are positively correlated with vehicle load and tire pressure and negatively correlated with water film thickness.Python language is used to develop the pre-processing plug-ins to achieve parametric modeling and rapid creation of Finite Element Analysis(FEA)model to reduce time costs,and the effectiveness of the plug-ins is verified through comparative tests.

A Hybrid Algorithm Based on Comprehensive Search Mechanisms for Job Shop Scheduling Problem

The research on complex workshop scheduling methods has important academic significance and has wide applications in industrial manufacturing.Aiming at the job shop scheduling problem,a hybrid algorithm based on comprehensive search mechanisms(HACSM)is proposed to optimize the maximum completion time.HACSM combines three search methods with different optimization scales,including fireworks algorithm(FW),extended Akers graphical method(LS1+_AKERS_EXT),and tabu search algorithm(TS).FW realizes global search through information interaction and resource allocation,ensuring the diversity of the population.LS1+_AKERS_EXT realizes compound movement with Akers graphical method,so it has advanced global and local search capabilities.In LS1+_AKERS_EXT,the shortest path is the core of the algorithm,which directly affects the encoding and decoding of scheduling.In order to find the shortest path,an effective node expansion method is designed to improve the node expansion efficiency.In the part of centralized search,TS based on the neighborhood structure is used.Finally,the effectiveness and superiority of HACSM are verified by testing the relevant instances in the literature.

Biased Bi-Population Evolutionary Algorithm for Energy-Efficient Fuzzy Flexible Job Shop Scheduling with Deteriorating Jobs

There are many studies about flexible job shop scheduling problem with fuzzy processing time and deteriorating scheduling,but most scholars neglect the connection between them,which means the purpose of both models is to simulate a more realistic factory environment.From this perspective,the solutions can be more precise and practical if both issues are considered simultaneously.Therefore,the deterioration effect is treated as a part of the fuzzy job shop scheduling problem in this paper,which means the linear increase of a certain processing time is transformed into an internal linear shift of a triangle fuzzy processing time.Apart from that,many other contributions can be stated as follows.A new algorithm called reinforcement learning based biased bi-population evolutionary algorithm(RB2EA)is proposed,which utilizes Q-learning algorithm to adjust the size of the two populations and the interaction frequency according to the quality of population.A local enhancement method which combimes multiple local search stratgies is presented.An interaction mechanism is designed to promote the convergence of the bi-population.Extensive experiments are designed to evaluate the efficacy of RB2EA,and the conclusion can be drew that RB2EA is able to solve energy-efficient fuzzy flexible job shop scheduling problem with deteriorating jobs(EFFJSPD)efficiently.

Cascading Failures in Power Grids: A Load Capacity Model with Node Centrality

Power grids,due to their lack of network redundancy and structural interdependence,are particularly vulnerable to cascading failures,a phenomenon where a few failed nodes—having their loads exceeding their capacities—can trigger a widespread collapse of all nodes.Here,we extend the cascading failure(Motter-Lai)model to a more realistic perspective,where each node’s load capacity is determined to be nonlinearly correlated with the node’s centrality.Our analysis encompasses a range of synthetic networks featuring small-world or scale-free properties,as well as real-world network configurations like the IEEE bus systems and the US power grid.We find that fine-tuning this nonlinear relationship can significantly enhance a network’s robustness against cascading failures when the network nodes are under attack.Additionally,the selection of initial nodes and the attack strategies also impact overall network robustness.Our findings offer valuable insights for improving the safety and resilience of power grids,bringing us closer to understanding cascading failures in a more realistic context.

Gaussian Process Based Modeling and Control of Affine Systems with Control Saturation Constraints

Model-based methods require an accurate dynamic model to design the controller.However,the hydraulic parameters of nonlinear systems,complex friction,or actuator dynamics make it challenging to obtain accurate models.In this case,using the input-output data of the system to learn a dynamic model is an alternative approach.Therefore,we propose a dynamic model based on the Gaussian process(GP)to construct systems with control constraints.Since GP provides a measure of model confidence,it can deal with uncertainty.Unfortunately,most GP-based literature considers model uncertainty but does not consider the effect of constraints on inputs in closed-loop systems.An auxiliary system is developed to deal with the influence of the saturation constraints of input.Meanwhile,we relax the nonsingular assumption of the control coefficients to construct the controller.Some numerical results verify the rationality of the proposed approach and compare it with similar methods.

A Threshold-Control Generative Adversarial Network Method for Intelligent Fault Diagnosis

Fault diagnosis plays the increasingly vital role to guarantee the machine reliability in the industrial enterprise.Among all the solutions,deep learning(DL)methods have achieved more popularity for their feature extraction ability from the raw historical data.However,the performance of DL relies on the huge amount of labeled data,as it is costly to obtain in the real world as the labeling process for data is usually tagged by hand.To obtain the good performance with limited labeled data,this research proposes a threshold-control generative adversarial network(TCGAN)method.Firstly,the 1D vibration signals are processed to be converted into 2D images,which are used as the input of TCGAN.Secondly,TCGAN would generate pseudo data which have the similar distribution with the limited labeled data.With pseudo data generation,the training dataset can be enlarged and the increase on the labeled data could further promote the performance of TCGAN on fault diagnosis.Thirdly,to mitigate the instability of the generated data,a threshold-control is presented to adjust the relationship between discriminator and generator dynamically and automatically.The proposed TCGAN is validated on the datasets from Case Western Reserve University and Self-Priming Centrifugal Pump.The prediction accuracies with limited labeled data have reached to 99.96%and 99.898%,which are even better than other methods tested under the whole labeled datasets.

Emergency Supply Control from the Perspectives of Peacetime and Wartime:A System Dynamics Simulation

The supply of emergency materials is the fundament of emergency rescues.In view of the demand for emergency materials in major calamities,in this paper,a system dynamics model of emergency materials is constructed from the perspectives of wartime and peacetime.By setting and controlling the relevant parameters and variables,the influence of a variable on the demand and supply of emergency materials and the influence of government strategies on the quantity and provision of emergency material supply are analyzed.We explore the measures that can better ensure the supply to stabilize the social and economic security of the country.The results show that the emergency degree of an event will lead to increases in the amount of government expenditures and in the duration of such expenditures.Meanwhile,the increase in emergency cases will increase the variation range of the supply and demand deviation curve,lengthen the response time to demand,and fasten the growth trend of material supply.The Chinese government adopts comprehensive regulation and control mode,which make the supply and demand reach the equilibrium state more than twice as fast as other control methods.In addition,the promotion of publicity will improve the number of civil materials.A high inflation rate will lead to high imports of government materials,which will consequently affect the supply of emergency materials.The above research findings have important reference significance for the government’s emergency materials management.

Simulation Research on Fire Evacuation of Large Public Buildings Based on Building Information Modeling

Reasonable evacuation strategies are important in reducing casualties in the event of a fire.In this work,we conduct a simulation of a fire evacuation of a large public building based on the building information modeling technology to find the best evacuation strategy.We identify the tolerance limit of evacuees in case of a fire as the basis of the simulation using the fire dynamics simulator software.The following four evacuation strategies are proposed and simulated:stratified evacuation only by stairs,stratified evacuation mainly by stairs and supplemented by fire elevators,holistic evacuation only by stairs,and holistic evacuation mainly by stairs and supplemented by fire elevators.The case study of a college canteen shows that if 10%of evacuees(mainly elderly people who walk slowly and children who take up less space)are instructed to evacuate via fire elevators and the other 90%of evacuees(young men and women who move fast)use the stairs,the evacuation time can be reduced to a minimum.Some improvements in the design drawing result in the enhanced efficiency of the proposed strategy.The findings of this work are of great significance for the optimization of the structural design of large public buildings and provide some references for emergency evacuation.

A Multi-Objective Hybrid Algorithm for the Casting Scheduling Problem with Unrelated Batch Processing Machine

The casting production process typically involves single jobs and small batches,with multiple constraints in the molding and smelting operations.To address the discrete optimization challenge of casting production scheduling,this paper presents a multi-objective batch scheduling model for molding and smelting operations on unrelated batch processing machines with incompatible job families and non-identical job sizes.The model aims to minimise the makespan,number of batches,and average vacancy rate of sandboxes.Based on the genetic algorithm,virus optimization algorithm,and two local search strategies,a hybrid algorithm(GA-VOA-BMS)has been designed to solve the model.The GA-VOA-BMS applies a novel Batch First Fit(BFF)heuristic for incompatible job families to improve the quality of the initial population,adopting the batch moving strategy and batch merging strategy to further enhance the quality of the solution and accelerate the convergence of the algorithm.The proposed algorithm was then compared with multi-objective swarm optimization algorithms,namely NSGA-ll,SPEA-l,and PESA-ll,to evaluate its effectiveness.The results of the performance comparison indicate that the proposed algorithm outperforms the others in terms of both qualityand stability.

An Adaptive Shuffled Frog-Leaping Algorithm for Hybrid-Flow Shop Scheduling with No Precedence Between Some Stages

Hybrid flow shop scheduling problem(HFSP)has been extensively considered,however,some reallife conditions are seldom investigated.In this study,HFsP with no precedence between some stages is solved and an adaptive shuffled frog-leaping algorithm(ASFLA)is developed to optimize makespan.A new solution representation and a decoding procedure are presented,an adaptive memeplex search and dynamical population shuffling are implemented together.Many computational experiments are implemented.Computational results prove that the new strategies of ASFLA are effective and ASFLA is very competitive in solving HFSP with no precedence between some stages.

Multi-UAV Cooperative Trajectory Planning Based on Many-Objective Evolutionary Algorithm

The trajectory planning of multiple unmanned aerial vehicles(UAVs)is the core of efficient UAV mission execution.Existing studies have mainly transformed this problem into a single-objective optimization problem using a single metric to evaluate multi-UAV trajectory planning methods.However,multi-UAV trajectory planning evolves into a many-objective optimization problem due to the complexity of the demand and the environment.Therefore,a multi-UAV cooperative trajectory planning model based on many-objective optimization is proposed to optimize trajectory distance,trajectory time,trajectory threat,and trajectory coordination distance costs of UAVs.The NSGA-III algorithm,which overcomes the problems of traditional trajectory planning,is used to solve the model.This paper also designs a segmented crossover strategy and introduces dynamic crossover probability in the crossover operator to improve the solving efficiency of the model and accelerate the convergence speed of the algorithm.Experimental results prove the effectiveness of the multi-UAV cooperative trajectory planning algorithm,thereby addressing different actual needs.

Multicommodity Flow Modeling for the Data Transmission Scheduling Problem in Navigation Satellite Systems

Introducing InterSatellite Links(ISLs)is a major trend in new-generation Global Navigation Satellite Systems(GNSSs).Data transmission scheduling is a crucial problem in the study of ISL management.The existing research on intersatellite data transmission has not considered the capacities of ISL bandwidth.Thus,the current study is the first to describe the intersatellite data transmission scheduling problem with capacity restrictions in GNSSs.A model conversion strategy is designed to model the aforementioned problem as a length-bounded single-path multicommodity flow problem.An integer programming model is constructed to minimize the maximal sum of flows on each intersatellite edge;this minimization is equivalent to minimizing the maximal occupied ISL bandwidth.An iterated tree search algorithm is proposed to resolve the problem,and two ranking rules are designed to guide the search.Experiments based on the BeiDou satellite constellation are designed,and results demonstrate the effectiveness of the proposed model and algorithm.

A Review of Reinforcement Learning Based Intelligent Optimization for Manufacturing Scheduling

As the critical component of manufacturing systems,production scheduling aims to optimize objectives in terms of profit,efficiency,and energy consumption by reasonably determining the main factors including processing path,machine assignment,execute time and so on.Due to the large scale and strongly coupled constraints nature,as well as the real-time solving requirement in certain scenarios,it faces great challenges in solving the manufacturing scheduling problems.With the development of machine learning,Reinforcement Learning(RL)has made breakthroughs in a variety of decision-making problems.For manufacturing scheduling problems,in this paper we summarize the designs of state and action,tease out RL-based algorithm for scheduling,review the applications of RL for different types of scheduling problems,and then discuss the fusion modes of reinforcement learning and meta-heuristics.Finally,we analyze the existing problems in current research,and point out the future research direction and significant contents to promote the research and applications of RL-based scheduling optimization.

Simulation of COVID-19 Outbreak in Nanjing Lukou Airport Based on Complex Dynamical Networks

The Corona Virus Disease 2019(COVID-19)pandemic is still imposing a devastating impact on public health,the economy,and society.Predicting the development of epidemics and exploring the effects of various mitigation strategies have been a research focus in recent years.However,the spread simulation of COVID-19 in the dynamic social system is relatively unexplored.To address this issue,considering the outbreak of COVID-19 at Nanjing Lukou Airport in 2021,we constructed an artificial society of Nanjing Lukou Airport based on the Artificial societies,Computational experiments,and Parallel execution(ACP)approach.Specifically,the artificial society includes an environmental model,population model,contact networks model,disease spread model,and intervention strategy model.To reveal the dynamic variation of individuals in the airport,we first modeled the movement of passengers and designed an algorithm to generate the moving traces.Then,the mobile contact networks were constructed and aggregated with the static networks of staff and passengers.Finally,the complex dynamical network of contacts between individuals was generated.Based on the artificial society,we conducted large-scale computational experiments to study the spread characteristics of COVID-19 in an airport and to investigate the effects of different intervention strategies.Learned from the reproduction of the outbreak,it is found that the increase in cumulative incidence exhibits a linear growth mode,different from that(an exponential growth mode)in a static network.In terms of mitigation measures,promoting unmanned security checks and boarding in an airport is recommended,as to reduce contact behaviors between individuals and staff.

Distributed Model Predictive Contouring Control for Real-Time Multi-Robot Motion Planning

Existing motion planning algorithms for multi-robot systems must be improved to address poor coordination and increase low real-time performance.This paper proposes a new distributed real-time motion planning method for a multi-robot system using Model Predictive Contouring Control(MPCC).MPCC allows separating the tracking accuracy and productivity,to improve productivity better than the traditional Model Predictive Control(MPC)which follows a time-dependent reference.In the proposed distributed MPCC,each robot exchanges the predicted paths of the other robots and generates the collision-free motion in a parallel manner.The proposed distributed MPCC method is tested in industrial operation scenarios in the robot simulation platform Gazebo.The simulation results show that the proposed distributed MPCC method realizes real-time multi-robot motion planning and performs better than three commonly-used planning methods(dynamic window approach,MPC,and prioritized planning).