In gas gathering stations,pointer meters are usually read by workers,which takes high labor costs and has low *** solve these problems and build intelligent gas gathering stations,this paper proposes an automatic read...
详细信息
In gas gathering stations,pointer meters are usually read by workers,which takes high labor costs and has low *** solve these problems and build intelligent gas gathering stations,this paper proposes an automatic reading system for real-time and accurate pointer meter reading.A new dataset is first constructed,which consists of700 pointer meter images with different angles,illumination and *** on the dataset,the deep learning model YOLOv5 is trained for dial and pointer *** the pointer mask output by YOLOv5,image preproces sing is used to separate the pointer from the background and generate the pure *** improved skeleton extraction algorithm and the Hough line detection algorithm are combined to extract the pointer center *** the dial image output by YOLOv5,feature matching and perspective transformation are adopted for position ***,pointer reading is obtained by applying the angle method to the corrected dial and the pointer center *** experiments demonstrate the high accuracy and efficiency of the proposed *** strong robustness to various interference factors in complex environments are also validated.
In order to obtain a forecast model for product design time from a small data set, Gaussian Margin Regression (GMR) is presented on the basis of combining Gaussian Margin Machines and kernel based regression. Gaussian...
详细信息
In the automatic railway anomaly inspection technology based on image processing and deep learning, an effective algorithm used for high-precision detection of the fastening system is very important, especially in tur...
详细信息
This paper investigates the speed regulation control of switched reluctance motor(SRM) *** improve the antidisturbance performance of SRM,a composite non-smooth control strategy is ***,the structure of SRM is analyzed...
This paper investigates the speed regulation control of switched reluctance motor(SRM) *** improve the antidisturbance performance of SRM,a composite non-smooth control strategy is ***,the structure of SRM is analyzed,and a simplified nonlinear model is obtained based on a segmented representation of the varying phase inductance.A virtual control function is introduced to represent the nonlinear part of the torque equation,whose inverse function is cascaded to linearized the nonlinear ***,a generalized proportional integral observer(GPIO) is constructed to estimate the lumped disturbance of the system,which is used for feedforward compensation ***,a composite speed controller is designed based on a combination of finite time proportional feedback and feed-forward compensation based on GPIO(FTP+GPIO).The speed error closed-loop system can be regarded as a first-order finite time control system with bounded *** analysis shows that the proposed scheme can improve the anti-disturbance performance of the closed-loop *** effectiveness of the proposed method is verified by simulation ***,it is compared with proportional feedback combining feed-forward compensation(P+GPIO) method and proportional integral(PI) control method.
In this paper,the finite-time state observer design problem for a pneumatic servo system is *** the case of without velocity sensors,a velocity observer is *** rigorous stability analysis,it is proved that the designe...
详细信息
ISBN:
(纸本)9781479970186
In this paper,the finite-time state observer design problem for a pneumatic servo system is *** the case of without velocity sensors,a velocity observer is *** rigorous stability analysis,it is proved that the designed observer is locally finite-time *** on the proposed observer,an output feedback linearization controller is proposed for position tracking control of the pneumatic servo *** simulations illustrate the effectiveness of the proposed velocity observer.
In this paper, we present the design of the multi-dimensional Taylor network(MTN) optimal controller in the flight control of cruise missile. The MTN optimal control, which combines the classical architecture of feedb...
详细信息
In this paper, we present the design of the multi-dimensional Taylor network(MTN) optimal controller in the flight control of cruise missile. The MTN optimal control, which combines the classical architecture of feedback control system and the new controller structure, it is not only suitable for the analysis of the stability of the closed-loop system, but also for the control of nonlinear systems with mechanism known or unknown models. Firstly, this paper will briefly introduce the theoretical basis of the MTN optimal control. Secondly, the characteristics of the missile mathematical model and the theory of missile control will be explained, accompanied with the design of controller. Finally, the feasibility of the method is validated through numerical simulation of the PID controller, PIDNN controller and the MTN optimal controller. The results show that the MTN optimal controller has the best control effect of them.
The vehicle electronic scroll compressors exhibits significant speed fluctuations during low-speed and heavy-load *** periodic fluctuation of load torque leads to speed *** limited sensitivity gain of traditional dist...
详细信息
ISBN:
(数字)9789887581581
ISBN:
(纸本)9798350366907
The vehicle electronic scroll compressors exhibits significant speed fluctuations during low-speed and heavy-load *** periodic fluctuation of load torque leads to speed *** limited sensitivity gain of traditional disturbance observers results in poor performance in suppressing periodic *** response to this issue,this study adopts an adaptive composite disturbance observer to estimate and compensate for load disturbances,in order to reduce speed fluctuations in the low-speed *** adaptive composite disturbance observer has achieved simultaneous and adaptive observation and estimation of periodic and aperiodic slow varying *** adaptive notch filter(ANF) based on variable step-size quantize least mean square(VSQLMS) algorithm is used to estimate the fundamental frequency of periodic *** simulation experiments,the method proposed has improved the control accuracy and dynamic response performance of the system,and has enhanced its robustness.
The idea of M2M platform proposes a completely new system architecture for positioning and monitoring applications with wider coverage and higher communication efficiency. With the comparison of the original communica...
详细信息
The idea of M2M platform proposes a completely new system architecture for positioning and monitoring applications with wider coverage and higher communication efficiency. With the comparison of the original communication mode to the M2M- based one, the communication interface is changed in the new communication solution for the application side accessing to the platform, which is finally designed into two parts according to the interface specification for M2M platform. The one is the local web service which provides methods for the platform to transmit data from the terminal side, and the other is the communication service software developed based on the SDK package from the M2M platform. This interface has been implemented into an actual application for the construction machinery monitoring, and the communication work between the terminals and the control center through M2M platform performs efficiently and reliably.
In this paper,finite-time consensus problem is investigated for multi-AUV(autonomous underwater vehicle) systems. Based on homogeneous control method,finite-time consensus algorithms are proposed for both leaderless a...
详细信息
ISBN:
(纸本)9781479900305
In this paper,finite-time consensus problem is investigated for multi-AUV(autonomous underwater vehicle) systems. Based on homogeneous control method,finite-time consensus algorithms are proposed for both leaderless and leader-follower multi-AUV ***,in the leader-follower case,a novel distributed finite-time observer is developed for the followers to estimate the leader's *** demonstrate the effectiveness of the proposed control algorithms.
This paper investigates the distributed fixed-time consensus problem of networked agents under the connected interaction topology,featuring an upper bound of the convergence time and being independent of initial *** a...
详细信息
ISBN:
(纸本)9781509009107
This paper investigates the distributed fixed-time consensus problem of networked agents under the connected interaction topology,featuring an upper bound of the convergence time and being independent of initial *** achieve fixed-time consensus,a new class of distributed nonlinear consensus protocols are constructed for first-order dynamic agents with or without external *** studies indicate that under the proposed protocols,all states of the agents will converge to a common value in fixed ***,the effectiveness of the theoretical results is illustrated by simulation results.
暂无评论