Path Planning and Tracking Control for Parking via Soft Actor-Critic Under Non-Ideal Scenarios

Parking in a small parking lot within limited space poses a difficult task. It often leads to deviations between the final parking posture and the target posture. These deviations can lead to partial occupancy of adjacent parking lots, which poses a safety threat to vehicles parked in these parking lots. However, previous studies have not addressed this issue. In this paper, we aim to evaluate the impact of parking deviation of existing vehicles next to the target parking lot(PDEVNTPL) on the automatic ego vehicle(AEV) parking, in terms of safety, comfort, accuracy, and efficiency of parking. A segmented parking training framework(SPTF) based on soft actor-critic(SAC) is proposed to improve parking performance. In the proposed method, the SAC algorithm incorporates strategy entropy into the objective function, to enable the AEV to learn parking strategies based on a more comprehensive understanding of the environment. Additionally, the SPTF simplifies complex parking tasks to maintain the high performance of deep reinforcement learning(DRL). The experimental results reveal that the PDEVNTPL has a detrimental influence on the AEV parking in terms of safety, accuracy, and comfort, leading to reductions of more than 27%, 54%, and 26%respectively. However, the SAC-based SPTF effectively mitigates this impact, resulting in a considerable increase in the parking success rate from 71% to 93%. Furthermore, the heading angle deviation is significantly reduced from 2.25 degrees to 0.43degrees.

An Advance Commutation Control Method for Low Torque Ripple of Brushless DC Motors

该文给出一种优化的无刷直流电动机变母线电压六拍控制方法。既解决了传统六拍控制策略中由于绕组电感所造成的电流滞后问题,又改善了由于换相所造成的电流脉动问题。该方法是通过在每两拍之间插入一小段缓冲区来实现的,该缓冲区使下一拍将要切入的电流提前切入,同时使当前拍将要切出的电流延迟切出。通过确定缓冲区的起始位置,即超前换相角的大小,保证每一拍所对应的相电流的中心和反电动势的中心重合。通过选取缓冲区开关器件PWM调制的占空比,降低电机运行过程中的换相转矩脉动。该文方法只需根据负载大小选取超前换相角,一旦选定适用于所有转速。文中给出了该方法的理论推导过程和实验验证波形,从实验结果可以发现,电流滞后被消除,换相电流脉动显著减小,电机的利用率得到提高。

Instability mechanism and control technology of soft rock roadway affected by mining and high confined water

Based on deformation and failure characteristics of the second belt conveyor roadway at level II of Zhuxianzhuang coal mine, laboratory experiments, numerical calculation and field test were adopted to analyze the composition and microstructure of mudstone, the law of mudstone hydration and its strength weakening induced by water, the characteristics of surrounding rock deformation and failure under the action of confined water. Results showed that montmorillonite clay minerals accounted for as much as 76% of mudstone, with a large number of pores existing in the microstructure. Besides, as the molecular structure of montmorillonite changed, mudstone microstructure damage occurred with the macroscopic manifestation of its theological instability. Weakening degree of confined water on residual strength of mudstone was almost 50%. The instability mechanism of soft rock roadway caused by high confined water is that surrounding rock circulates the process of ＂fracture-seepage-mud ding-closed＂ twice, which weakens its strength and leads to roadway instability. A combined support technology, namely the, ＂high-toughness sealing layer ＋ hollow grouting cables ＋ full-length anchoring bolts with deep borehole＂ was proposed. Based on field observation, the soft rock roadway was controlled effectively, which also verified the effectiveness of new control technology for surrounding rock.

Control technology for floor heave of Jurassic soft rock in the Erdos Basin of China: A case study

The deformation of soft rock roadway caused by floor heave is a major challenge for coal mines in China western mining areas. To achieve security and stability of soft rock roadway, this work considered the headgate at panel 11505 of the Yushujing Coal Mine as background. First, based on the limit equilibrium method and slip line field theory,a model of floor heave was established, the mechanism of floor heave control was analyzed, and an optimized support method was proposed. Then, the displacement, stress and failure zones around the surrounding rock with the original and optimized support were studied by FLAC. Finally, the serviceability of the support method was verified by field application. The results showed that the main deformation form of soft rock roadway is floor heave, and 0.5 m is relatively reasonable thicknesses of the inverted arch. The extrusion failure zone and shear failure zone were mainly affected by tensile and shear failure, respectively. The modification of floor and the effective support are key points. The failure zone was consistent between numerical simulation and theoretical calculation. The maximum convergences of floor heave determined by numerical simulation and field measurement were 220 mm and 240 mm, respectively, which were reduced by 55% and 60% compared with the original support, and the convergence between sidewalls decreased considerably. The optimized support method controls the floor heave well.

Mixed-Weights Least-Squares Stable Predictive Control Algorithm with Soft and Hard Constraints

Mixed-weight least-squares (MWLS) predictive control algorithm, compared with quadratic programming (QP) method, has the advantages of reducing the computer burden, quick calculation speed and dealing with the case in which the optimization is infeasible. But it can only deal with soft constraints. In order to deal with hard constraints and guarantee feasibility, an improved algorithm is proposed by recalculating the setpoint according to the hard constraints before calculating the manipulated variable and MWLS algorithm is used to satisfy the requirement of soft constraints for the system with the input constraints and output constraints. The algorithm can not only guarantee stability of the system and zero steady state error, but also satisfy the hard constraints of input and output variables. The simulation results show the improved algorithm is feasible and effective.

Temperature-controlled triaxial compression/creep test device for thermodynamic properties of soft sedimentary rock and corresponding theoretical prediction

In deep geological disposal of high-level nuclear waste,one of the most important subjects is to estimate long-term stability and strength of host rock under high temperature conditions caused by radioactive decay of the waste.In this paper,some experimental researches on the thermo-mechanical characteristics of soft sedimentary rock have been presented.For this reason,a new temperature-controlled triaxial compression and creep test device,operated automatically by a computer-controlled system,whose control software has been developed by the authors,was developed to conduct the thermo-mechanical tests in different thermal loading paths,including an isothermal path.The new device is proved to be able to conduct typical thermo-mechanical element tests for soft rock.The test device and the related testing method were introduced in detail.Finally,some test results have been simulated with a thermo-elasto-viscoplastic model that was also developed by the authors.

Study on strata control by delay grouting in soft rock roadway

The properties of broken rock before and after grouting reinforcement are studied. Testing results show that grouting can raise the residual strength of broken rock, and the broken rockness by grouting can keep the steady supporting capacity within a relatively large deformation range. Revealing of the characteristics of stage deformation and damage process comes to the conclusion that the supporting of soft rock roadway should be analyzed in a dynamic view, and the grouting should be delayed at a proper occasion. Based on the above, the stepwise reinforcement technology characterized by immediate shotcreting, timely bolting and delay grouting is put forward and illustrated with a successful engineering practice.

Modeling and Adaptive Neural Network Control for a Soft Robotic Arm With Prescribed Motion Constraints

This paper presents a dynamic model and performance constraint control of a line-driven soft robotic arm.The dynamics model of the soft robotic arm is established by combining the screw theory and the Cosserat theory.The unmodeled dynamics of the system are considered,and an adaptive neural network controller is designed using the backstepping method and radial basis function neural network.The stability of the closed-loop system and the boundedness of the tracking error are verified using Lyapunov theory.The simulation results show that our approach is a good solution to the motion constraint problem of the line-driven soft robotic arm.

Failure mechanism and control technology of water-immersed roadway in high-stress and soft rock in a deep mine

Aiming at soft rock ground support issues under conditions of high stress and long-term water immersion, the ground failure mechanism is revealed by taking the deep-water sumps of Jiulong Mine as the engineering background and employing field investigation, tests of rock structure, mechanical properties and mineral composition. The main factors leading to the surrounding rock failure include the high and complex stress state of the water sumps, high-clay content and water-weakened rock, and the unreasonable support design. In this paper, the broken and fractured rock mass near roadway opening is considered as ground small-structure, and deep stable rock mass as ground large-structure. A support technology focusing on cutting off the water, strengthening the small structure of the rock and transferring the large structure of the rock is proposed. The proposed support technology of interconnecting the large and small structures, based on high-strength bolts, high-stiffness shotcrete layer plugging water,strengthening the small structure with deep-hole grouting and shallow-hole grouting, highpretensioned cables tensioned twice to make the large and small structures bearing the pressure evenly,channel-steel and high-pretensioned cables are used to control floor heave. The numerical simulation and field test show that this support system can control the rock deformation of the water sumps and provide technical support to similar roadway support designs.

Development of fractures in soft rock surrounding a roadway and their control

As the excavation of roadway, new fractures will be formed and the pre-existing fractures extend with the redistribution of stress in surrounding rocks. Eventually, fracture zone and bed separation are formed in rocks because of the developed fractures. Therefore, mastering the fracture evolution of surrounding rocks is very important to maintain the stability of roadway. The surrounding rocks of main haulage road- way in a certain coal mine is so broken and loose that the supporting is very difficult. Based on compre- hensive anal[ysis of the engineering geological conditions, a sight instrument was used to observe the fractures of internal surrounding rocks, Four indices, i.e., the width of fracture zone W, the number of fractures n, the width of fractures d and rock fracture designation RFD, are put forward to evaluate the fracture dewelopment. According to the evolution rules of the soft rock roadway from this paper, control principles by stages and by regions are presented through the research. At the same time, the best time of grouting reinforcement is determined on the basis of fracture saturation. Field practice shows that the roadway can satisfy normal production during service periods by suitable first support and grouting reinforcement.

Analysis of Different Vibration Control Strategies for Soft Mounted Induction Motors with Sleeve Bearings Using Active Motor Foot Mounts

The paper presents a theoretical analysis of different vibration control strategies of soft mounted induction motors with sleeve bearings, using active motor foot mounts. After the vibration model is presented, different controllers in combination with different feedback strategies are mathematically investigated. The focus is here on the forced vibrations, caused by dynamic rotor eccentricity—rotor mass eccentricity, magnetic eccentricity and bent rotor deflection. After the mathematically coherences are described, a numerical example is shown, where the forced vibrations caused by bent rotor deflection are investigated, for different control strategies, where the mass matrix, the stiffness matrix and the damping matrix are influenced by different control parameters. The aim of the paper is to show the mathematically coherences and the possibility to influence the vibration behaviour, by different control strategies to optimize the vibration behaviour of soft mounted induction motors.

Failure mechanism of Mesozoic soft rock roadway in Shajihai coal mine and its surrounding rock control

In view of the buckling failure caused by large deformation of Mesozoic soft rock roadway in Shajihai mining area, such as serious roof fall, rib spalling, floor heave, etc., based on the detail site investigation,theoretical analysis, mineral composition test, microstructure test, water-physical property test and field experiments were carried out. And we revealed the compound failure mechanism of Mesozoic soft rock roadway in Shajihai mining area, namely the molecule expansion-shear slip of weak structural plane-construction disturbance. On this basis, the coupling support technology whose core is constant resistance with large deformation bolt was proposed. The feature of this supporting technology is that a new type of structural composite material was used, which makes the supporting system not only has the ideal deformation characteristics, but also has high supporting resistance. Thus the fully release of plastic energy within surrounding rock and reasonable control of the thickness of the plastic ring were realized. Then the differential deformation between the surrounding rock and support was eliminated by the secondary coupling support of bolt–mesh–cable, and the bolt with high strength was applied in the base angle to control floor. Eventually the collaborative bearing system of surrounding rock–support was formed. Through field tests the validity and rationality of support was also verified.

Feasibility analysis and online adjustment of constraints in model predictive control integrated with soft sensor

Feasibility analysis of soft constraints for input and output variables is critical for model predictive control(MPC).When encountering the infeasible situation, some way should be found to adjust the constraints to guarantee that the optimal control law exists. For MPC integrated with soft sensor, considering the soft constraints for critical variables additionally makes it more complicated and difficult for feasibility analysis and constraint adjustment. Therefore, the main contributions are that a linear programming approach is proposed for feasibility analysis, and the corresponding constraint adjustment method and procedure are given as well. The feasibility analysis gives considerations to the manipulated, secondary and critical variables, and the increment of manipulated variables as well. The feasibility analysis and the constraint adjustment are conducted in the entire control process and guarantee the existence of optimal control. In final, a simulation case confirms the contributions in this paper.

Commutant Lifting for Optimal Control of Time-varying Systems

This paper uses the commutant lifting theorem for representations of the nest algebra to deal with the optimal control of infinite dimensional linear time- varying systems. We solve the model matching problem and a certain optimal feedback control problem, each of which corresponds with one type of four-block problem. We also obtain a new formula for the optimal performance and prove the existence of an optimal controller.

Model control technologies of dynamic secondary cooling and soft reduction for slab continuous casting

Dynamic model control technologies of secondary cooling and soft reduction of Baosteel are introduced. Model principle and control system architecture are summarized, as well as functions and features. Finally, applications of model technologies are discussed. The self-developed dynamic secondary cooling model and the dynamic soft reduction model have been applied on several casting machines inside and outside Baosteel, desired control effects were achieved with good stability and reliability. Temperature measurement results verified the correctness of model.

Identification and Control of Radish Alternaria Leaf Spot, Black Rot, Soft Rot, Virus Disease and Hollowness

The damage characteristics and occurrence regularity of radish alternaria leaf spot, black rot, soft rot, virus disease and hollowness are introduced in the paper, and the corresponding control method is proposed from two aspects of agricultural control and chemical control.

Controlling the output power of soft switching arc welding inverter by two-stage continuous PWM method

The full bridge zero voltage zero current switching （ FB-ZVZCS ） , which could adjust the output power by keeping the duty ratio of lagging leg constant and changing the duty ratio of leading leg, was a common circuit of soft switching arc welding inverter power source. However, when the duty ratio of leading leg was reduced to zero, the output power stayed the constant value instead of becoming zero. The working status and waveforms of some major parameters were studied in this paper while the duty ratio of leading leg was zero. It was concluded that the minimum output power of soft switching inverter was related to the charging voltage of paraUel capacitors, and the output power also could be reduced by reducing the duty ratio of lagging leg. A novel two-stage continuous PWM control method that could switch working-mode between full bridge and half bridge was put forward in this paper. This kind of control method could further reduce the output power of soft switching inverter in order to meet the requirement of low heat input of sheet metal welding.

Corneal Wavefront Aberrations in Patients Wearing Multifocal Soft Contact Lenses for Myopia Control

Purpose: The purpose of this study was to evaluate the change in corneal wavefront aberrations in young adults who have been fit with multifocal soft contact lenses for myopia progression control. Findings have been analyzed for statistical significance and clinical relevance and compared to reportedly successful Orthokeratology outcomes. Methods: The dominant eye of 40 participants (27 women, 13 men;mean age 27.3 ± 3.2 years;range 23 to 39 years) was fit with Proclear Multifocal center distance lenses (Coopervision, Pleasanton, USA) having a variety of distance powers and reading additions. Refractive errors were limited to a range of –6.00 D up to +1.00 D of sphere, and no greater than –1.00 D of cylinder. Corneal wavefront measurements were performed over 6 mm diameters with a Zeiss Atlas 9000 corneal topographer (Zeiss Meditec, Dublin, USA) prior to, and following lens fitting. Data were converted into rectangular Fourier optics terms M, J0, J45 and RMS values for each reading addition were statistically analyzed. Following evaluation of statistical significance and clinical relevance, results were compared to published data from successful Orthokeratology treatments. Results: Statistically significant changes in higher order aberrations were detected for lenses of all reading additions. Lens groups with higher Add-powers demonstrated stronger changes with increased significance. Final RMS values relating to 2nd, 3rd and 4th Zernike Orders reached clinical significance with a wavefront error of 0.10 μm, the equivalent of 0.25D. Moreover, as Add-powers increased, 3rd and 4th order aberrations likewise showed an increase. Pre-fitting astigmatism values accounted for the highest recorded aberrations and remained predominantly unchanged. Conclusion: Proclear Multifocal center-distance contact lenses were found to increase higher order wavefront aberrations in a manner dependent on their Add-power. In comparison to successful Orthokeratology outcomes, the amounts of resulting aberrations are notably different.

Analysis of factors of top coal caving in fully mechanized sublevel caving face in soft coal and control

According to the analysis of the mechanism of top coal caving, the caving condition was pointed out, and many factors of caving were also determined. Then the relationship between factors and caving was studied. Based on the above research, one effective method by using field monitoring was brought forward to determine the controlling factor. Then some related key technologies were provided, such as keeping the integrality of the top-coal, raising the horizontal resistance of supports and decreasing the real end-face distance etc.. At last one application of this method was presented, and it was proved to be an effective method.

Intelligent Robust Control of Redundant Smart Robotic Arm Pt I: Soft Computing KB Optimizer - Deep Machine Learning IT

Redundant robotic arm models as a control object discussed.Background of computational intelligence IT on soft computing optimizer of knowledge base in smart robotic manipulators introduced.Soft computing optimizer is the sophisticated computational intelligence toolkit of deep machine learning SW platform with optimal fuzzy neural network structure.The methods for development and design technology of control systems based on soft computing introduced in this Part 1 allow one to implement the principle of design an optimal intelligent control systems with a maximum reliability and controllability level of a complex control object under conditions of uncertainty in the source data,and in the presence of stochastic noises of various physical and statistical characters.The knowledge bases formed with the application of soft computing optimizer produce robust control laws for the schedule of time dependent coefficient gains of conventional PID controllers for a wide range of external perturbations and are maximally insensitive to random variations of the structure of control object.The robustness is achieved by application a vector fitness function for genetic algorithm,whose one component describes the physical principle of minimum production of generalized entropy both in the control object and the control system,and the other components describe conventional control objective functionals such as minimum control error,etc.The application of soft computing technologies(Part I)for the development a robust intelligent control system that solving the problem of precision positioning redundant(3DOF and 7 DOF)manipulators considered.Application of quantum soft computing in robust intelligent control of smart manipulators in Part II described.