The reduction of energy consumption is an increasingly important topic of the railway system.Energy-efficient train control(EETC)is one solution,which refers to mathematically computing when to accelerate,which cruisi...The reduction of energy consumption is an increasingly important topic of the railway system.Energy-efficient train control(EETC)is one solution,which refers to mathematically computing when to accelerate,which cruising speed to hold,how long one should coast over a suitable space,and when to brake.Most approaches in literature and industry greatly simplify a lot of nonlinear effects,such that they ignore mostly the losses due to energy conversion in traction components and auxiliaries.To fill this research gap,a series of increasingly detailed nonlinear losses is described and modelled.We categorize an increasing detail in this representation as four levels.We study the impact of those levels of detail on the energy optimal speed trajectory.To do this,a standard approach based on dynamic programming is used,given constraints on total travel time.This evaluation of multiple test cases highlights the influence of the dynamic losses and the power consumption of auxiliary components on railway trajectories,also compared to multiple benchmarks.The results show how the losses can make up 50%of the total energy consumption for an exemplary trip.Ignoring them would though result in consistent but limited errors in the optimal trajectory.Overall,more complex trajectories can result in less energy consumption when including the complexity of nonlinear losses than when a simpler model is considered.Those effects are stronger when the trajectory includes many acceleration and braking phases.展开更多
Energy efficiency stands as an essential factor when implementing deep reinforcement learning(DRL)policies for robotic control systems.Standard algorithms,including Deep Deterministic Policy Gradient(DDPG),primarily o...Energy efficiency stands as an essential factor when implementing deep reinforcement learning(DRL)policies for robotic control systems.Standard algorithms,including Deep Deterministic Policy Gradient(DDPG),primarily optimize task rewards but at the cost of excessively high energy consumption,making them impractical for real-world robotic systems.To address this limitation,we propose Physics-Informed DDPG(PI-DDPG),which integrates physics-based energy penalties to develop energy-efficient yet high-performing control policies.The proposed method introduces adaptive physics-informed constraints through a dynamic weighting factor(λ),enabling policies that balance reward maximization with energy savings.Our motivation is to overcome the impracticality of rewardonly optimization by designing controllers that achieve competitive performance while substantially reducing energy consumption.PI-DDPG was evaluated in nine MuJoCo continuous control environments,where it demonstrated significant improvements in energy efficiency without compromising stability or performance.Experimental results confirm that PI-DDPG substantially reduces energy consumption compared to standard DDPG,while maintaining competitive task performance.For instance,energy costs decreased from 5542.98 to 3119.02 in HalfCheetah-v4 and from1909.13 to 1586.75 in Ant-v4,with stable performance in Hopper-v4(205.95 vs.130.82)and InvertedPendulum-v4(322.97 vs.311.29).Although DDPG sometimes yields higher rewards,such as in HalfCheetah-v4(5695.37 vs.4894.59),it requires significantly greater energy expenditure.These results highlight PI-DDPG as a promising energy-conscious alternative for robotic control.展开更多
The safe driving and operation of trains is a necessary condition for ensuring the safe operation of trains.In particular,heavy-haul trains are characterized by the difficulty in driving and operation.Considering the ...The safe driving and operation of trains is a necessary condition for ensuring the safe operation of trains.In particular,heavy-haul trains are characterized by the difficulty in driving and operation.Considering the uncertainties in train driving and operation,this paper analyzes the relationship between the safety of heavy-haul electric locomotive hauled trains and driving and operation.It studies the auxiliary intelligent driving safety operation control methods.Through K-means to identify the characteristics of drivers'driving manipulation,the hidden Markov model adaptively adjusts the train driving and operation sequence,and conducts auxiliary driving reconstruction for heavy-haul locomotive driving and operation.Based on the train running curve and the locomotive traction/braking characteristics,it smoothly controls the exertion of the traction/braking force of heavy-haul locomotives,thereby optimizing the driving safety control of heavy-haul trains in the vehicle-environment-track system.Finally,the train operation simulation and optimized driving verification are carried out by simulating some track sections.The results show that the proposed method can correct and pre-optimize driving operations,improving the smoothness of heavy-haul trains by approximately 10%.It verifies the effectiveness of the proposed train assisted driving control reconstruction method,facilitating the smooth and safe operation of heavy-haul trains.展开更多
Optimal trajectory planning of high-speed trains(HSTs)aims to obtain such speed curves that guarantee safety,punctuality,comfort and energy-saving of the train.In this paper,a new shrinking horizon model predictive co...Optimal trajectory planning of high-speed trains(HSTs)aims to obtain such speed curves that guarantee safety,punctuality,comfort and energy-saving of the train.In this paper,a new shrinking horizon model predictive control(MPC)algorithm is proposed to plan the optimal trajectories of HSTs using real-time traffic information.The nonlinear longitudinal dynamics of HSTs are used to predict the future behaviors of the train and describe variable slopes and variable speed limitations based on real-time traffic information.Then optimal trajectory planning of HSTs is formulated as the shrinking horizon optimal control problem with the consideration of safety,punctuality,comfort and energy consumption.According to the real-time position and running time of the train,the shrinking horizon is updated to ensure the recursive feasibility of the optimization problem.The optimal speed curve of the train is computed by online solving the optimization problem with the Radau Pseudo-spectral method(RPM).Simulation results demonstrate that the proposed method can satisfy the requirements of energy efficiency and punctuality of the train.展开更多
Purpose–In recent years,the rapid advancement of artificial intelligence(AI)has exerted profound impacts on and provided strong impetus to numerous fields in the industrial sector.Within the railway industry,AI has d...Purpose–In recent years,the rapid advancement of artificial intelligence(AI)has exerted profound impacts on and provided strong impetus to numerous fields in the industrial sector.Within the railway industry,AI has driven continuous upgrading and optimization of intelligent train control technology,thanks to its enhanced computational capabilities derived from advanced algorithms and models,as well as its role in improving safety performance.Integrating AI technology more extensively into train autonomous driving and control has thus become an inevitable trend in the global development of railways.Design/methodology/approach–This paper,therefore,conducts a comprehensive analysis of the development progress and current status of AI technology applications in the field of train driving and control on a global scale.It systematically sorts out and analyzes the advantages of various AI technologies and the positive impacts they bring to the upgrading of train control technology,elucidates the feasibility and future prospects of applying a range of emerging AI technologies from the perspective of technical theory and provides guidance for the intelligent development of this field from a practical perspective.Findings–The application of AI technology in the train driving and control field is still in its infancy.While a large number of AI technologies have been widely adopted,there remains significant room for further optimization and improvement of these technologies.Additionally,a variety of AI technologies that have been applied in other industrial sectors but not yet widely implemented in training autonomous driving and control have demonstrated tremendous development potential.Originality/value–The research findings provide references and guidance for advancing train control technology,promoting the digital transformation of railways,accelerating the overall optimization and upgrading of railway industry technologies,and facilitating the accelerated development of global railways.展开更多
This paper reports a case of cerebral stem infarction with quadriplegia and complete dependence on daily life.The course of the disease lasted more than 7 months.Frenchay's improved articulation Disorder Assessmen...This paper reports a case of cerebral stem infarction with quadriplegia and complete dependence on daily life.The course of the disease lasted more than 7 months.Frenchay's improved articulation Disorder Assessment Form has been assessed as severe articulation disorder.The patient has significantly improved his speech function and quality of life after systematic head control training,respiratory function training,articulation motor training,and articulation training.In the course of treatment,emphasis was placed on head postural control training and respiratory function training,and emphasis was placed on the strength and coordination training of articulatory organs,and the results were remarkable.After the patient was discharged from the hospital,the follow-up of basic daily life communication was not limited.展开更多
With the integration of informatization and intelligence into the Communication-Based Train Control(CBTC)systems,the system is facing an increasing number of information security threats.As an important method of char...With the integration of informatization and intelligence into the Communication-Based Train Control(CBTC)systems,the system is facing an increasing number of information security threats.As an important method of characterizing the system security status,the security situation assessment is used to analyze the system security situation.However,existing situation assessment methods fail to integrate the coupling relationship between the physical layer and the information layer of the CBTC systems,and cannot dynamically characterize the real-time security situation changes under cyber attacks.In this paper,a hierarchical security situation assessment approach is proposed to address the security challenges of CBTC systems,which can perceive cyber attacks,quantify the security situation,and characterize the security situation changes under cyber attacks.Specifically,for the physical layer ofCBTC systems,the impact of cyber attacks is evaluated with the train punctuality rate and train departure interval indicators.For the information layer of CBTC systems,the system vulnerabilities and system threats are selected as static level indicators,and the critical network characteristics are selected as dynamic level indicators to quantify the real-time security situation.Finally,the comprehensive security situation assessment value of the CBTC systems is obtained by integrating the physical and information layer indicators.Simulation results illustrate that the proposed approach can dynamically characterize the real-time security situation of CBTC systems,enhancing the ability to perceive and assess information security risks.展开更多
Background Evidence on the effects of different exercise interventions on cognitive function is insufficient.Aims To evaluate the feasibility and effects of remotely supervised aerobic exercise(AE)and resistance exerc...Background Evidence on the effects of different exercise interventions on cognitive function is insufficient.Aims To evaluate the feasibility and effects of remotely supervised aerobic exercise(AE)and resistance exercise(RE)interventions in older adults with mild cognitive impairment(MCI).Methods This study is a 6-month pilot three-arm randomised controlled trial.Eligible participants(n=108)were recruited and randomised to the AE group,RE group or control(CON)group with a 1:1:1 ratio.Interventions were delivered at home with remote supervision.We evaluated participants’global cognition,memory,executive function,attention,physical activity levels,physical performance and muscle strength of limbs at baseline,3 months(T1)and 6 months(T2)after randomisation.A linear mixed-effects model was adopted for data analyses after controlling for covariates.Tukey’s method was used for adjusting for multiple comparisons.Sensitivity analyses were performed after excluding individuals with low compliance rates.Results 15(13.89%)participants dropped out.The median compliance rates in the AE group and RE group were 67.31%and 93.27%,respectively.After adjusting for covariates,the scores of the Alzheimer’s Disease Assessment Scale-Cognitive subscale in the AE group decreased by 2.04(95%confidence interval(CI)−3.41 to−0.67,t=−2.94,p=0.004)and 1.53(95%CI−2.88 to−0.17,t=−2.22,p=0.028)points more than those in the CON group at T1 and T2,respectively.The effects of AE were still significant at T1(estimate=−1.70,95%CI−3.20 to−0.21,t=−2.69,p=0.021),but lost statistical significance at T2 after adjusting for multiple comparisons.As for executive function,the Stroop time interference in the RE group decreased by 11.76 s(95%CI−21.62 to−1.90,t=−2.81,p=0.015)more than that in the AE group at T2 after Tukey’s adjustment.No other significant effects on cognitive functions were found.Conclusions Both remotely supervised AE and RE programmes are feasible in older adults with MCI.AE has positive effects on global cognition,and RE improves executive function.展开更多
In this paper, the energy-efficient power control problem in cognitive radio （CR） networks is studied not only to provide energy-efficient transmission, but also to guarantee the normal operation of primary users （...In this paper, the energy-efficient power control problem in cognitive radio （CR） networks is studied not only to provide energy-efficient transmission, but also to guarantee the normal operation of primary users （PUs）. Moreover, the static energy-efficient power control （SEPC） algorithm is proposed in static scenario to maximize the capacity of secondary users （SUs） and to reduce the power consumption according to the interference from PU to SU. Furthermore, based on the analysis of PU＇s dynamic feature with Markov chain and SEPC algorithm,the dynamic energy-efficient power control （DEPC） algorithm is proposed taking into account the probability of detection and false alarm caused by sensing errors. Extensive simulation results show that the performance of the proposed algorithms is significantly improved compared with the existing algorithm.展开更多
Proportional, integral and derivative (PID) control strategy has been widely applied in heating systems in decades. To improve the accuracy and the robustness of PID control, self-tuning radial-basis-function neural n...Proportional, integral and derivative (PID) control strategy has been widely applied in heating systems in decades. To improve the accuracy and the robustness of PID control, self-tuning radial-basis-function neural network PID (RBF-PID) is developed and used. Even though being popular, during the control process both of PID and RBF-PID control strategy are inadequate in achieving simultaneous high energy-efficiency and good control accuracy. To address this problem, in this paper we develop and report an enhanced self-tuning radial-basis-function neural network PID (e-RBF-PID) controller. To identify the superiority of e-RBF-PID, following works are conducted and reported in this paper. Firstly, four controllers, i.e., on-off, PID, RBF-PID and e-RBF-PID are designed. Secondly, in order to test the performance of the e-RBF-PID controller, an experimental water heating system is constructed for being controlled. Finally, the energy consumption for the four controllers under the three control scenarios is investigated through experiments. The experimental results indicate that in the three scenarios, the developed e-RBF-PID controller outperforms on-off controller as having higher accuracy. Compared to the PID controller, the e-RBF-PID controller has higher speed in control, and the experimental results show that settling time savings is between 12.6% - 49.0%. Most importantly, less control energy consumption is obtained if using the e-RBF-PID controller. It is found that up to 28.5% energy consumption can be saved. Therefore, it is concluded that the proposed e-RBF-PID is capable of enhancing energy efficiency during control process.展开更多
The important work of Yu,et al.[1]who presented one of the first randomized controlled trials(RCTs)to directly compare robot-assisted and manual percutaneous coronary intervention(PCI),is commendable;offering importan...The important work of Yu,et al.[1]who presented one of the first randomized controlled trials(RCTs)to directly compare robot-assisted and manual percutaneous coronary intervention(PCI),is commendable;offering important insights into the feasibility and outcomes of this emerging technology.While the analysis is timely,several issues warrant further consideration.展开更多
[Objectives]To investigate the clinical effects of implementing structured phased rehabilitation training,in addition to conventional rehabilitation,on shoulder joint function and pain alleviation in patients with rot...[Objectives]To investigate the clinical effects of implementing structured phased rehabilitation training,in addition to conventional rehabilitation,on shoulder joint function and pain alleviation in patients with rotator cuff injuries managed conservatively.[Methods]Eighty patients diagnosed with rotator cuff injury were selected and randomly assigned to either the control group or the experimental group,each comprising 40 individuals.The control group received conventional rehabilitation treatment,whereas the experimental group underwent phased rehabilitation training in addition to the conventional treatment for 6 weeks.Assessments were conducted prior to treatment,6 weeks following treatment,and 8 weeks after the completion of treatment(follow-up period).The visual analogue scale(VAS)was employed to evaluate pain intensity,the Constant-Murley score was utilized to assess shoulder joint function,and the shoulder joint range of motion was measured.[Results]Prior to treatment,no statistically significant differences were observed between the two patient groups across all measured indicators(P>0.05).Following 6 weeks of treatment and throughout the follow-up period,both groups exhibited significant reductions in VAS scores compared to baseline measurements,alongside improvements in Constant-Murley scores and shoulder joint range of motion(P<0.05).Furthermore,the magnitude of improvement in the experimental group was significantly greater than that in the control group(P<0.05).[Conclusions]Phased rehabilitation training can enhance shoulder joint function and alleviate pain in patients with rotator cuff injuries beyond the effects of conventional rehabilitation treatment,demonstrating notable clinical application value.展开更多
Objective To observe the clinical efficacy of acupuncture combined with speech rehabilitation training for post-stroke spasmodic dysphonia and compare the differences in efficacy among the therapy of acupuncture combi...Objective To observe the clinical efficacy of acupuncture combined with speech rehabilitation training for post-stroke spasmodic dysphonia and compare the differences in efficacy among the therapy of acupuncture combined with speech rehabilitation training and the monotherapy.Methods Two hundred and seventy cases of patients with post-stroke spasmodic dysarthria were randomly divided into three groups with the ratio of 1：1：1.Group A：acupuncture combined with speech rehabilitation training group（90 cases）,group B：acupuncture group（90 cases）,group C：speech rehabilitation training group（90 cases）.In the group B,acupuncture treatment was given at Baihui（百会 GV 20）,JTnjin（金津 EX-HN 12） and Yuye（玉液 EX-HN13） as well as tongue-three needles.In the group C,the treatment of speech rehabilitation training was provided.The two treatments mentioned above were combined in the group A.Patients were treated once a day for a month with improved Frenchay dysarthria rating scale as the indices of therapeutic effect evaluation.Results ① Group A：the cured and markedly effective rate was 88.7%,and total effective rate was 94.3%;group B：the cured and markedly effective rate was 44.2%and total effective rate was 81.4%;group C：the cured and markedly effective rate was 23.5%and total effective rate was 61.2%.Both the cured and markedly effective rate and the total effective rate in the group A were significantly higher than those in the group B or group C（all P0.05）;both the cured and markedly effective rate and the total effective rate in the group B were higher than those of group C（both P0.05）;② In comparison of functional recovery of tongue in accordance with the Frenchay dysarthria rating scale,the recovery rate of the tongue-stationary state was 71.74%in the group A,18.87%in the group B and 4.44%in the group C;the recovery rate of tongue lolling out was 66.23%in the group A,27.63%in the group B and 1.59%in the group C;the recovery rate of tongue up and down motion was 44.19%in the group A,4.94%in the group B and 1.35%in the group C;the recovery rate of lateral motion was 40.24%in the group A,7.59%in the group B and 0.00%in the group C;the recovery rate of alternating motion was 29.07%in the group A,7.14%in the group B and 1.23%in the group C;the recovery rate of speech was 29.07%in the group A,5.88%in the group B and 1.22%in the group C.In the three groups,the recovery rates of stationary state and tongue lolling out were superior to those of up and down movement,lateral movement,alternating movement and speech（all P0.05）.Conclusion The clinical efficacy of acupuncture combined with speech rehabilitation training for patients with post-stroke spasmodic dysarthria is significant,and the efficacy of acupuncture is superior to that of speech rehabilitation training;as for functional recovery of tongue like stationary state and tongue out,the therapy of acupuncture combined with speech rehabilitation training is effective.展开更多
This paper proposes cooperative adaptive control schemes for a train platoon to improve efficient utility and guarantee string stability. The control schemes are developed based on a bidirectional strategy, i.e., the ...This paper proposes cooperative adaptive control schemes for a train platoon to improve efficient utility and guarantee string stability. The control schemes are developed based on a bidirectional strategy, i.e., the information of proximal（preceding and following） trains is used in the controller design. Based on available proximal information（prox-info） of location, speed, and acceleration, a direct adaptive control is designed to maintain the tracking interval at the minimum safe distance. Based on available prox-info of location, an observer-based adaptive control is designed to achieve the same target, which alleviates the requirements of equipped sensors to measure prox-info of speed and acceleration. The developed schemes are capable of on-line estimating of the unknown system parameters and stabilizing the closed-loop system, the string stability of train platoon is guaranteed on the basis of Lyapunov stability theorem. Numerical simulation results are presented to verify the effectiveness of the proposed control laws.展开更多
In modern trains wheelset skidding leads to the deterioration of braking behavior,the degradation of comfort,as well as a boost in system hazards.Because of the nonlinearity and unknown characteristics of wheelset adh...In modern trains wheelset skidding leads to the deterioration of braking behavior,the degradation of comfort,as well as a boost in system hazards.Because of the nonlinearity and unknown characteristics of wheelset adhesion,simplifications are widely adopted in the modeling process of conventional antiskid controllers.Therefore,conventional antiskid controllers usually cannot perform satisfactorily.In this paper,systematic computer simulation and field tests for railway antiskid control system are introduced.The operating principal of antiskid control system is explained,which is fundamental to the simulation of antiskid brakes,and the simulation model is introduced,which incorporates both the adhesion creep curve and a pneumatic submodel of antiskid control system.In addition,the characteristics of adhesion curves and the simulation target are also provided.Using DHSplus,the pneumatic submodel is created to analyze the performance of the different control strategies of antiskid valves.Then the system simulation is realized by combining the kinematical characteristics of railway trains and the pneumatic submodel.The simulation is performed iteratively to obtain the optimized design of the antiskid control system.The design result is incorporated in the hardware design of the antiskid control system and is evaluated in the field tests in Shanghai Subway Line 1.Judging by the antiskid efficiency,the antiskid braking performance observed in the field tests shows the superiority of the optimized design.Therefore,the proposed simulation method,especially in view of its ease of application,appears to be a useful one for designing railway antiskid control systems.展开更多
This paper presents an adaptive terminal sliding mode control(ATSMC) method for automatic train operation. The criterion for the design is keeping high-precision tracking with relatively less adjustment of the control...This paper presents an adaptive terminal sliding mode control(ATSMC) method for automatic train operation. The criterion for the design is keeping high-precision tracking with relatively less adjustment of the control input. The ATSMC structure is designed by considering the nonlinear characteristics of the dynamic model and the parametric uncertainties of the train operation in real time. A nonsingular terminal sliding mode control is employed to make the system quickly reach a stable state within a finite time, which makes the control input less adjust to guarantee the riding comfort. An adaptive mechanism is used to estimate controller parameters to get rid of the need of the prior knowledge about the bounds of system uncertainty. Simulations are presented to demonstrate the effectiveness of the proposed controller, which has robust performance to deal with the external disturbance and system parametric uncertainties. Thereby, the system guarantees the train operation to be accurate and comfortable.展开更多
In order to improve the energy efficiency(EE)in cognitive radio(CR),this paper investigates the joint design of cooperative spectrum sensing time and the power control optimization problem for the secondary user syste...In order to improve the energy efficiency(EE)in cognitive radio(CR),this paper investigates the joint design of cooperative spectrum sensing time and the power control optimization problem for the secondary user systems to achieve the maximum energy efficiency in a cognitive network based on hybrid spectrum sharing,meanwhile considering the maximum transmit power,user quality of service(QoS)requirements,interference limitations,and primary user protection.The optimization of energy efficient sensing time and power allocation is formulated as a non-convex optimization problem.The Dinkelbach’s method is adopted to solve this problem and to transform the non-convex optimization problem in fractional form into an equivalent optimization problem in the form of subtraction.Then,an iterative power allocation algorithm is proposed to solve the optimization problem.The simulation results show the effectiveness of the proposed algorithms for energy-efficient resource allocation in the cognitive network.展开更多
This paper focuses on the problem of the adaptive robust control of a lower limbs rehabilitation robot(LLRR) that is a nonlinear system running under passive training mode. In reality, uncertainties including modeling...This paper focuses on the problem of the adaptive robust control of a lower limbs rehabilitation robot(LLRR) that is a nonlinear system running under passive training mode. In reality, uncertainties including modeling error, initial condition deviation, friction force and other unknown external disturbances always exist in a LLRR system. So, it is necessary to consider the uncertainties in the unilateral man-machine dynamical model of the LLRR we described. In the dynamical model, uncertainties are(possibly fast) time-varying and bounded. However, the bounds are unknown. Based on the dynamical model, we design an adaptive robust control with an adaptive law that is leakagetype based and on the framework of Udwadia-Kalaba theory to compensate for the uncertainties and to realize tracking control of the LLRR. Furthermore, the effectiveness of designed control is shown with numerical simulations.展开更多
The risk of failure of the control loop can occur when a high-speed maglev train runs on viaduct.Meanwhile,the failure of the levitation magnets which balances the gravity of the maglev train could cause the train col...The risk of failure of the control loop can occur when a high-speed maglev train runs on viaduct.Meanwhile,the failure of the levitation magnets which balances the gravity of the maglev train could cause the train collision with track.To study the dynamic response of the train and the viaduct when the levitation magnet control loop failure occurs,a high-speed maglev train-viaduct coupling model,which includes a maglev controller fitted by measured force-gap data and considers the actual structure of train and viaduct,is established.Then the accuracy and effectiveness of the established approach are validated by comparing the computed dynamic responses and frequencies with the measurement results.After that,the dynamic responses of maglev train and viaduct are discussed under normal operation and control loop failures,and the most disadvantageous combination of control loop failures is obtained.The results show that when a single control loop fails,it only has a great influence on the failed electromagnet,and the maglev response of adjacent electromagnets has no obvious change and no collision occurs.But there is a risk of rail collisions when the dual control loop fails.展开更多
基金supported by Swiss Federal Office of Transport,the ETH foundation and via the grant RAILPOWER.
文摘The reduction of energy consumption is an increasingly important topic of the railway system.Energy-efficient train control(EETC)is one solution,which refers to mathematically computing when to accelerate,which cruising speed to hold,how long one should coast over a suitable space,and when to brake.Most approaches in literature and industry greatly simplify a lot of nonlinear effects,such that they ignore mostly the losses due to energy conversion in traction components and auxiliaries.To fill this research gap,a series of increasingly detailed nonlinear losses is described and modelled.We categorize an increasing detail in this representation as four levels.We study the impact of those levels of detail on the energy optimal speed trajectory.To do this,a standard approach based on dynamic programming is used,given constraints on total travel time.This evaluation of multiple test cases highlights the influence of the dynamic losses and the power consumption of auxiliary components on railway trajectories,also compared to multiple benchmarks.The results show how the losses can make up 50%of the total energy consumption for an exemplary trip.Ignoring them would though result in consistent but limited errors in the optimal trajectory.Overall,more complex trajectories can result in less energy consumption when including the complexity of nonlinear losses than when a simpler model is considered.Those effects are stronger when the trajectory includes many acceleration and braking phases.
文摘Energy efficiency stands as an essential factor when implementing deep reinforcement learning(DRL)policies for robotic control systems.Standard algorithms,including Deep Deterministic Policy Gradient(DDPG),primarily optimize task rewards but at the cost of excessively high energy consumption,making them impractical for real-world robotic systems.To address this limitation,we propose Physics-Informed DDPG(PI-DDPG),which integrates physics-based energy penalties to develop energy-efficient yet high-performing control policies.The proposed method introduces adaptive physics-informed constraints through a dynamic weighting factor(λ),enabling policies that balance reward maximization with energy savings.Our motivation is to overcome the impracticality of rewardonly optimization by designing controllers that achieve competitive performance while substantially reducing energy consumption.PI-DDPG was evaluated in nine MuJoCo continuous control environments,where it demonstrated significant improvements in energy efficiency without compromising stability or performance.Experimental results confirm that PI-DDPG substantially reduces energy consumption compared to standard DDPG,while maintaining competitive task performance.For instance,energy costs decreased from 5542.98 to 3119.02 in HalfCheetah-v4 and from1909.13 to 1586.75 in Ant-v4,with stable performance in Hopper-v4(205.95 vs.130.82)and InvertedPendulum-v4(322.97 vs.311.29).Although DDPG sometimes yields higher rewards,such as in HalfCheetah-v4(5695.37 vs.4894.59),it requires significantly greater energy expenditure.These results highlight PI-DDPG as a promising energy-conscious alternative for robotic control.
基金Project(U2034211)supported by the National Natural Science Foundation of ChinaProject(20232ACE01013)supported by the Major Scientific and Technological Research and Development Special Project of Jiangxi Province,China。
文摘The safe driving and operation of trains is a necessary condition for ensuring the safe operation of trains.In particular,heavy-haul trains are characterized by the difficulty in driving and operation.Considering the uncertainties in train driving and operation,this paper analyzes the relationship between the safety of heavy-haul electric locomotive hauled trains and driving and operation.It studies the auxiliary intelligent driving safety operation control methods.Through K-means to identify the characteristics of drivers'driving manipulation,the hidden Markov model adaptively adjusts the train driving and operation sequence,and conducts auxiliary driving reconstruction for heavy-haul locomotive driving and operation.Based on the train running curve and the locomotive traction/braking characteristics,it smoothly controls the exertion of the traction/braking force of heavy-haul locomotives,thereby optimizing the driving safety control of heavy-haul trains in the vehicle-environment-track system.Finally,the train operation simulation and optimized driving verification are carried out by simulating some track sections.The results show that the proposed method can correct and pre-optimize driving operations,improving the smoothness of heavy-haul trains by approximately 10%.It verifies the effectiveness of the proposed train assisted driving control reconstruction method,facilitating the smooth and safe operation of heavy-haul trains.
基金supported by the National Natural Science Foundation of China(No.61773345)the Zhejang Provincial Natural Science Foundation(No.LR17F030004).
文摘Optimal trajectory planning of high-speed trains(HSTs)aims to obtain such speed curves that guarantee safety,punctuality,comfort and energy-saving of the train.In this paper,a new shrinking horizon model predictive control(MPC)algorithm is proposed to plan the optimal trajectories of HSTs using real-time traffic information.The nonlinear longitudinal dynamics of HSTs are used to predict the future behaviors of the train and describe variable slopes and variable speed limitations based on real-time traffic information.Then optimal trajectory planning of HSTs is formulated as the shrinking horizon optimal control problem with the consideration of safety,punctuality,comfort and energy consumption.According to the real-time position and running time of the train,the shrinking horizon is updated to ensure the recursive feasibility of the optimization problem.The optimal speed curve of the train is computed by online solving the optimization problem with the Radau Pseudo-spectral method(RPM).Simulation results demonstrate that the proposed method can satisfy the requirements of energy efficiency and punctuality of the train.
文摘Purpose–In recent years,the rapid advancement of artificial intelligence(AI)has exerted profound impacts on and provided strong impetus to numerous fields in the industrial sector.Within the railway industry,AI has driven continuous upgrading and optimization of intelligent train control technology,thanks to its enhanced computational capabilities derived from advanced algorithms and models,as well as its role in improving safety performance.Integrating AI technology more extensively into train autonomous driving and control has thus become an inevitable trend in the global development of railways.Design/methodology/approach–This paper,therefore,conducts a comprehensive analysis of the development progress and current status of AI technology applications in the field of train driving and control on a global scale.It systematically sorts out and analyzes the advantages of various AI technologies and the positive impacts they bring to the upgrading of train control technology,elucidates the feasibility and future prospects of applying a range of emerging AI technologies from the perspective of technical theory and provides guidance for the intelligent development of this field from a practical perspective.Findings–The application of AI technology in the train driving and control field is still in its infancy.While a large number of AI technologies have been widely adopted,there remains significant room for further optimization and improvement of these technologies.Additionally,a variety of AI technologies that have been applied in other industrial sectors but not yet widely implemented in training autonomous driving and control have demonstrated tremendous development potential.Originality/value–The research findings provide references and guidance for advancing train control technology,promoting the digital transformation of railways,accelerating the overall optimization and upgrading of railway industry technologies,and facilitating the accelerated development of global railways.
基金Teaching and Research Project of Anhui Urban Management Vocational College(Project No.:2024kfkc001)。
文摘This paper reports a case of cerebral stem infarction with quadriplegia and complete dependence on daily life.The course of the disease lasted more than 7 months.Frenchay's improved articulation Disorder Assessment Form has been assessed as severe articulation disorder.The patient has significantly improved his speech function and quality of life after systematic head control training,respiratory function training,articulation motor training,and articulation training.In the course of treatment,emphasis was placed on head postural control training and respiratory function training,and emphasis was placed on the strength and coordination training of articulatory organs,and the results were remarkable.After the patient was discharged from the hospital,the follow-up of basic daily life communication was not limited.
基金supported in part by the project of the State Key Laboratory of Advanced Rail Autonomous Operation(RAO2023ZZ004)in part by the Beijing Natural Science Foundation-Fengtai Rail Transit Frontier Research Joint Fund(L211002)+2 种基金in part by the Foundation of China State Railway Group Corporation Limited under Grant L2021G003in part by the Scientific and Technical Research Fund of China Academy of Railway Sciences Corporation Limited under Grant 2021YJ094in part by the Project I23L00200 and Project I24F00010.
文摘With the integration of informatization and intelligence into the Communication-Based Train Control(CBTC)systems,the system is facing an increasing number of information security threats.As an important method of characterizing the system security status,the security situation assessment is used to analyze the system security situation.However,existing situation assessment methods fail to integrate the coupling relationship between the physical layer and the information layer of the CBTC systems,and cannot dynamically characterize the real-time security situation changes under cyber attacks.In this paper,a hierarchical security situation assessment approach is proposed to address the security challenges of CBTC systems,which can perceive cyber attacks,quantify the security situation,and characterize the security situation changes under cyber attacks.Specifically,for the physical layer ofCBTC systems,the impact of cyber attacks is evaluated with the train punctuality rate and train departure interval indicators.For the information layer of CBTC systems,the system vulnerabilities and system threats are selected as static level indicators,and the critical network characteristics are selected as dynamic level indicators to quantify the real-time security situation.Finally,the comprehensive security situation assessment value of the CBTC systems is obtained by integrating the physical and information layer indicators.Simulation results illustrate that the proposed approach can dynamically characterize the real-time security situation of CBTC systems,enhancing the ability to perceive and assess information security risks.
基金funded by the National Natural Science Foundation of China(81871854,72374014)the National Key R&D Program of China(2020YFC2008804)+1 种基金the Shanghai Jiao Tong University Young Talent Cultivation Program in Liberal Arts(2024QN041)the Shanghai Jiao Tong University School of Medicine:Nursing Development Program(SJTUHLXK2024).
文摘Background Evidence on the effects of different exercise interventions on cognitive function is insufficient.Aims To evaluate the feasibility and effects of remotely supervised aerobic exercise(AE)and resistance exercise(RE)interventions in older adults with mild cognitive impairment(MCI).Methods This study is a 6-month pilot three-arm randomised controlled trial.Eligible participants(n=108)were recruited and randomised to the AE group,RE group or control(CON)group with a 1:1:1 ratio.Interventions were delivered at home with remote supervision.We evaluated participants’global cognition,memory,executive function,attention,physical activity levels,physical performance and muscle strength of limbs at baseline,3 months(T1)and 6 months(T2)after randomisation.A linear mixed-effects model was adopted for data analyses after controlling for covariates.Tukey’s method was used for adjusting for multiple comparisons.Sensitivity analyses were performed after excluding individuals with low compliance rates.Results 15(13.89%)participants dropped out.The median compliance rates in the AE group and RE group were 67.31%and 93.27%,respectively.After adjusting for covariates,the scores of the Alzheimer’s Disease Assessment Scale-Cognitive subscale in the AE group decreased by 2.04(95%confidence interval(CI)−3.41 to−0.67,t=−2.94,p=0.004)and 1.53(95%CI−2.88 to−0.17,t=−2.22,p=0.028)points more than those in the CON group at T1 and T2,respectively.The effects of AE were still significant at T1(estimate=−1.70,95%CI−3.20 to−0.21,t=−2.69,p=0.021),but lost statistical significance at T2 after adjusting for multiple comparisons.As for executive function,the Stroop time interference in the RE group decreased by 11.76 s(95%CI−21.62 to−1.90,t=−2.81,p=0.015)more than that in the AE group at T2 after Tukey’s adjustment.No other significant effects on cognitive functions were found.Conclusions Both remotely supervised AE and RE programmes are feasible in older adults with MCI.AE has positive effects on global cognition,and RE improves executive function.
基金the National Natural Science Foundation of China，Beijing Municipal Natural Science Foundation，the Key Project of Ministry of Industry and Information Technology，the National Youth Science Foundation
文摘In this paper, the energy-efficient power control problem in cognitive radio （CR） networks is studied not only to provide energy-efficient transmission, but also to guarantee the normal operation of primary users （PUs）. Moreover, the static energy-efficient power control （SEPC） algorithm is proposed in static scenario to maximize the capacity of secondary users （SUs） and to reduce the power consumption according to the interference from PU to SU. Furthermore, based on the analysis of PU＇s dynamic feature with Markov chain and SEPC algorithm,the dynamic energy-efficient power control （DEPC） algorithm is proposed taking into account the probability of detection and false alarm caused by sensing errors. Extensive simulation results show that the performance of the proposed algorithms is significantly improved compared with the existing algorithm.
文摘Proportional, integral and derivative (PID) control strategy has been widely applied in heating systems in decades. To improve the accuracy and the robustness of PID control, self-tuning radial-basis-function neural network PID (RBF-PID) is developed and used. Even though being popular, during the control process both of PID and RBF-PID control strategy are inadequate in achieving simultaneous high energy-efficiency and good control accuracy. To address this problem, in this paper we develop and report an enhanced self-tuning radial-basis-function neural network PID (e-RBF-PID) controller. To identify the superiority of e-RBF-PID, following works are conducted and reported in this paper. Firstly, four controllers, i.e., on-off, PID, RBF-PID and e-RBF-PID are designed. Secondly, in order to test the performance of the e-RBF-PID controller, an experimental water heating system is constructed for being controlled. Finally, the energy consumption for the four controllers under the three control scenarios is investigated through experiments. The experimental results indicate that in the three scenarios, the developed e-RBF-PID controller outperforms on-off controller as having higher accuracy. Compared to the PID controller, the e-RBF-PID controller has higher speed in control, and the experimental results show that settling time savings is between 12.6% - 49.0%. Most importantly, less control energy consumption is obtained if using the e-RBF-PID controller. It is found that up to 28.5% energy consumption can be saved. Therefore, it is concluded that the proposed e-RBF-PID is capable of enhancing energy efficiency during control process.
文摘The important work of Yu,et al.[1]who presented one of the first randomized controlled trials(RCTs)to directly compare robot-assisted and manual percutaneous coronary intervention(PCI),is commendable;offering important insights into the feasibility and outcomes of this emerging technology.While the analysis is timely,several issues warrant further consideration.
文摘[Objectives]To investigate the clinical effects of implementing structured phased rehabilitation training,in addition to conventional rehabilitation,on shoulder joint function and pain alleviation in patients with rotator cuff injuries managed conservatively.[Methods]Eighty patients diagnosed with rotator cuff injury were selected and randomly assigned to either the control group or the experimental group,each comprising 40 individuals.The control group received conventional rehabilitation treatment,whereas the experimental group underwent phased rehabilitation training in addition to the conventional treatment for 6 weeks.Assessments were conducted prior to treatment,6 weeks following treatment,and 8 weeks after the completion of treatment(follow-up period).The visual analogue scale(VAS)was employed to evaluate pain intensity,the Constant-Murley score was utilized to assess shoulder joint function,and the shoulder joint range of motion was measured.[Results]Prior to treatment,no statistically significant differences were observed between the two patient groups across all measured indicators(P>0.05).Following 6 weeks of treatment and throughout the follow-up period,both groups exhibited significant reductions in VAS scores compared to baseline measurements,alongside improvements in Constant-Murley scores and shoulder joint range of motion(P<0.05).Furthermore,the magnitude of improvement in the experimental group was significantly greater than that in the control group(P<0.05).[Conclusions]Phased rehabilitation training can enhance shoulder joint function and alleviate pain in patients with rotator cuff injuries beyond the effects of conventional rehabilitation treatment,demonstrating notable clinical application value.
文摘Objective To observe the clinical efficacy of acupuncture combined with speech rehabilitation training for post-stroke spasmodic dysphonia and compare the differences in efficacy among the therapy of acupuncture combined with speech rehabilitation training and the monotherapy.Methods Two hundred and seventy cases of patients with post-stroke spasmodic dysarthria were randomly divided into three groups with the ratio of 1：1：1.Group A：acupuncture combined with speech rehabilitation training group（90 cases）,group B：acupuncture group（90 cases）,group C：speech rehabilitation training group（90 cases）.In the group B,acupuncture treatment was given at Baihui（百会 GV 20）,JTnjin（金津 EX-HN 12） and Yuye（玉液 EX-HN13） as well as tongue-three needles.In the group C,the treatment of speech rehabilitation training was provided.The two treatments mentioned above were combined in the group A.Patients were treated once a day for a month with improved Frenchay dysarthria rating scale as the indices of therapeutic effect evaluation.Results ① Group A：the cured and markedly effective rate was 88.7%,and total effective rate was 94.3%;group B：the cured and markedly effective rate was 44.2%and total effective rate was 81.4%;group C：the cured and markedly effective rate was 23.5%and total effective rate was 61.2%.Both the cured and markedly effective rate and the total effective rate in the group A were significantly higher than those in the group B or group C（all P0.05）;both the cured and markedly effective rate and the total effective rate in the group B were higher than those of group C（both P0.05）;② In comparison of functional recovery of tongue in accordance with the Frenchay dysarthria rating scale,the recovery rate of the tongue-stationary state was 71.74%in the group A,18.87%in the group B and 4.44%in the group C;the recovery rate of tongue lolling out was 66.23%in the group A,27.63%in the group B and 1.59%in the group C;the recovery rate of tongue up and down motion was 44.19%in the group A,4.94%in the group B and 1.35%in the group C;the recovery rate of lateral motion was 40.24%in the group A,7.59%in the group B and 0.00%in the group C;the recovery rate of alternating motion was 29.07%in the group A,7.14%in the group B and 1.23%in the group C;the recovery rate of speech was 29.07%in the group A,5.88%in the group B and 1.22%in the group C.In the three groups,the recovery rates of stationary state and tongue lolling out were superior to those of up and down movement,lateral movement,alternating movement and speech（all P0.05）.Conclusion The clinical efficacy of acupuncture combined with speech rehabilitation training for patients with post-stroke spasmodic dysarthria is significant,and the efficacy of acupuncture is superior to that of speech rehabilitation training;as for functional recovery of tongue like stationary state and tongue out,the therapy of acupuncture combined with speech rehabilitation training is effective.
基金Project supported by the Beijing Jiaotong University Research Program,China(Grant No.RCS2014ZT18)the Fundamental Research Funds for Central Universities,China(Grant No.2015JBZ007)the National Natural Science Foundation of China(Grant Nos.61233001,61322307,and 61304196)
文摘This paper proposes cooperative adaptive control schemes for a train platoon to improve efficient utility and guarantee string stability. The control schemes are developed based on a bidirectional strategy, i.e., the information of proximal（preceding and following） trains is used in the controller design. Based on available proximal information（prox-info） of location, speed, and acceleration, a direct adaptive control is designed to maintain the tracking interval at the minimum safe distance. Based on available prox-info of location, an observer-based adaptive control is designed to achieve the same target, which alleviates the requirements of equipped sensors to measure prox-info of speed and acceleration. The developed schemes are capable of on-line estimating of the unknown system parameters and stabilizing the closed-loop system, the string stability of train platoon is guaranteed on the basis of Lyapunov stability theorem. Numerical simulation results are presented to verify the effectiveness of the proposed control laws.
基金supported by National Natural Science Foundation of China (Grant No. 61004077)National Key Technology R&D Program of the 11th Five Year Plan of China (Grant No. 2009BAG11B02)Foundation of Traction Power State Key Laboratory of Southwest Jiaotong University,China (Grant No. TPL1107)
文摘In modern trains wheelset skidding leads to the deterioration of braking behavior,the degradation of comfort,as well as a boost in system hazards.Because of the nonlinearity and unknown characteristics of wheelset adhesion,simplifications are widely adopted in the modeling process of conventional antiskid controllers.Therefore,conventional antiskid controllers usually cannot perform satisfactorily.In this paper,systematic computer simulation and field tests for railway antiskid control system are introduced.The operating principal of antiskid control system is explained,which is fundamental to the simulation of antiskid brakes,and the simulation model is introduced,which incorporates both the adhesion creep curve and a pneumatic submodel of antiskid control system.In addition,the characteristics of adhesion curves and the simulation target are also provided.Using DHSplus,the pneumatic submodel is created to analyze the performance of the different control strategies of antiskid valves.Then the system simulation is realized by combining the kinematical characteristics of railway trains and the pneumatic submodel.The simulation is performed iteratively to obtain the optimized design of the antiskid control system.The design result is incorporated in the hardware design of the antiskid control system and is evaluated in the field tests in Shanghai Subway Line 1.Judging by the antiskid efficiency,the antiskid braking performance observed in the field tests shows the superiority of the optimized design.Therefore,the proposed simulation method,especially in view of its ease of application,appears to be a useful one for designing railway antiskid control systems.
基金supported by National Natural Science Foundation of China and High Speed Railway Union Foundation of China(No.U11344205)
文摘This paper presents an adaptive terminal sliding mode control(ATSMC) method for automatic train operation. The criterion for the design is keeping high-precision tracking with relatively less adjustment of the control input. The ATSMC structure is designed by considering the nonlinear characteristics of the dynamic model and the parametric uncertainties of the train operation in real time. A nonsingular terminal sliding mode control is employed to make the system quickly reach a stable state within a finite time, which makes the control input less adjust to guarantee the riding comfort. An adaptive mechanism is used to estimate controller parameters to get rid of the need of the prior knowledge about the bounds of system uncertainty. Simulations are presented to demonstrate the effectiveness of the proposed controller, which has robust performance to deal with the external disturbance and system parametric uncertainties. Thereby, the system guarantees the train operation to be accurate and comfortable.
基金supported in part by the National Natural Science Foundation of China for Young Scholars under Grant No.61701167Young Elite Backbone Teachers in Blue and Blue Project of Jiangsu Province, China
文摘In order to improve the energy efficiency(EE)in cognitive radio(CR),this paper investigates the joint design of cooperative spectrum sensing time and the power control optimization problem for the secondary user systems to achieve the maximum energy efficiency in a cognitive network based on hybrid spectrum sharing,meanwhile considering the maximum transmit power,user quality of service(QoS)requirements,interference limitations,and primary user protection.The optimization of energy efficient sensing time and power allocation is formulated as a non-convex optimization problem.The Dinkelbach’s method is adopted to solve this problem and to transform the non-convex optimization problem in fractional form into an equivalent optimization problem in the form of subtraction.Then,an iterative power allocation algorithm is proposed to solve the optimization problem.The simulation results show the effectiveness of the proposed algorithms for energy-efficient resource allocation in the cognitive network.
基金supported by the National Natural Science Foundation of China(51505116)the Fundamental Research Funds for the Central Universities(JZ2016HGTB0716)+2 种基金Natural and Science Foundation of Anhui Province(1508085SME221)China Postdoctoral Science Foundation(2016M590563)the Science and Technology Public Relations Project of Anhui Province(1604a0902181)
文摘This paper focuses on the problem of the adaptive robust control of a lower limbs rehabilitation robot(LLRR) that is a nonlinear system running under passive training mode. In reality, uncertainties including modeling error, initial condition deviation, friction force and other unknown external disturbances always exist in a LLRR system. So, it is necessary to consider the uncertainties in the unilateral man-machine dynamical model of the LLRR we described. In the dynamical model, uncertainties are(possibly fast) time-varying and bounded. However, the bounds are unknown. Based on the dynamical model, we design an adaptive robust control with an adaptive law that is leakagetype based and on the framework of Udwadia-Kalaba theory to compensate for the uncertainties and to realize tracking control of the LLRR. Furthermore, the effectiveness of designed control is shown with numerical simulations.
基金Project(2021zzts0775) supported by the Independent Exploration and Innovation Project for Graduate Students of Central South University,ChinaProject(2021JJ30053) supported by the Hunan Natural Science Foundation,China。
文摘The risk of failure of the control loop can occur when a high-speed maglev train runs on viaduct.Meanwhile,the failure of the levitation magnets which balances the gravity of the maglev train could cause the train collision with track.To study the dynamic response of the train and the viaduct when the levitation magnet control loop failure occurs,a high-speed maglev train-viaduct coupling model,which includes a maglev controller fitted by measured force-gap data and considers the actual structure of train and viaduct,is established.Then the accuracy and effectiveness of the established approach are validated by comparing the computed dynamic responses and frequencies with the measurement results.After that,the dynamic responses of maglev train and viaduct are discussed under normal operation and control loop failures,and the most disadvantageous combination of control loop failures is obtained.The results show that when a single control loop fails,it only has a great influence on the failed electromagnet,and the maglev response of adjacent electromagnets has no obvious change and no collision occurs.But there is a risk of rail collisions when the dual control loop fails.
