Position Soft-Sensing of Direct-Driven Hydraulic System Based on Back Propagation Neural Network (original) (raw)
Related papers
Neural network solution for the forward kinematics problem of a redundant hydraulic shoulder
Industrial Electronics Society, …, 2005
Forward kinematics problem of cable robots is very difficult to solve the same as that of parallel robots and in the contrary to the serial manipulators'. This problem is almost impossible to solve analytically because of the nonlinearity and complexity of the robot's kinematic equations. Numerical methods are the most common solutions for this problem of the parallel and cable robots. But, convergency of these methods is the drawback of using them. In this paper, neural network approach is used to solve the forward kinematics problem of an exemplary 3D cable robot. This problem is solved in the typical workspace of the robot. The neural network used in this paper is of the MLP type and a back propagation procedure is utilized to train the network. A simulation study is performed and the results show the advantages of this method in enhancement of convergency together with very small modeling errors.
Vibration analysis of an experimental double bridge crane system with artificial neural networks
Journal of Vibration and Control, 2020
In crane systems, lifting, carrying and lowering the load from one place have different dynamic effects on the system. One of these dynamic effects is the moving load problem caused by the movement of the load on the crane system. With the increasing technology in recent years, production speeds have increased. For this reason, it has made the requirements for fast-running cranes mandatory for the transportation and loading of products. Therefore, it is important to know the dynamic effects of the moving load in fast working conditions. In this experimental study, the dynamic effects occurring on the crane beams with different loads and different working speeds during the transportation of the load on the crane are analysed. Here, there are multiple cars on the crane, and these cars are designed in different numbers on the crane and can be operated at different speeds. Under these conditions, the dynamic effects that have arisen have been tested. Also, vibration measurements were carried out at different points on the bridges. And then, these parameters obtained were used in two different proposed neural network types to predict the vibrations that occur on the crane system. Simulation results show that two approaches suggested that a radial basis neural network type can be used as an adaptive predictor for such systems in the experimental applications.
Sensorless position estimation of simulated direct driven hydraulic actuators
2017
In this study, sensorless position control of hydraulic cylinders is investigated. Direct driven hydraulics units are utilized as a prime mover. Direct driven hydraulics is a valveless pump controlled hydraulic system that uses an electric motor to drive pumps for a single actuator. This brings energy saving and controllability advantages to traditional valve controlled hydraulics. Advantages and disadvantages of various types of position sensors, which are available on the market were investigated for hydraulic cylinder application. These sensors, while accurate, have been noted to be rather expensive and not suitable for harsh environment applications. Virtual sensors can provide an alternative to physical position sensors. Using only torque and speed data received from electric motor controller it is possible to simulate the position of a cylinder, provided that all relevant parameters are known. Simulation model of direct driven hydraulic system of a mining loader test platform ...
Modelling and simulation of sensors for position control for hydraulic mechatronic systems
Proceedings of the 2011 34th International Spring Seminar on Electronics Technology (ISSE), 2011
Many electro-hydraulic applications like automated manufacturing tools and systems, robotics or seismic test benches for civil engineering require precise control of hydraulic cylinders. This control can be obtained only using reliable and accurate position sensors, usually resistive or inductive. The paper presents design, modelling, simulation and implementation of two types of position sensors for hydraulic mechatronic systems-differential inductive type and integrated accelerometer-based. Both sensors use microcontrollers for data processing and communication. Each type has its advantages-the inductive sensor is more accurate, accelerometer-based one requires simpler mechanical construction. The idea of using of accelerometer-based sensor was to replace standard displacement transducer attached on the cylinder with an accelerometer connected to a microcontroller that reads acceleration data and calculates displacement, thus eliminating mechanical coupling between cylinder rod and cylinder body. Both solutions are analyzed and compared on the same hydraulic test bench.
International Journal of Control, Automation and Systems, 2020
In this paper, a neural network-based robust anti-sway control is proposed for a crane system transporting an underwater object. A dynamic model of the crane system is developed by incorporating hoisting dynamics, hydrodynamic forces, and external disturbances. Considering the various uncertain factors that interfere with accurate payload positioning in water, neural networks are designed to compensate for unknown parameters and unmodeled dynamics in the formulated problem. The neural network-based estimators are embedded in the anti-sway control algorithm, which improves the control performance against uncertainties. A sliding mode control with an exponential reaching law is developed to suppress the sway motions during underwater transportation. The asymptotic stability of the sliding manifold is proved via Lyapunov analysis. The embedded estimator prevents the conservative gain selection of the sliding mode control, thus reducing the chattering phenomena. Simulation results are provided to verify the effectiveness and robustness of the proposed control method.
Application of a flexible structure artificial neural network on a servo-hydraulic rotary actuator
International Journal of Advanced Manufacturing Technology, 2008
In this article the results of the application of a flexible structure artificial neural network for controlling the angular velocity of a servo-hydraulic rotary actuator are discussed. A mathematical model for the system is derived, and a flexible artificial neural network (ANN)-based controller with the feedback error learning method as a learning algorithm is applied to the system. The neural network-based controller has a feed-forward structure and three layers. The flexible bipolar sigmoid function was used as the activation function of the network. The simulation and experimental results show good performance of the developed method in learning the inverse dynamic of the system and controlling the angular velocity of the rotary hydro motor. The advantages of the developed method for servo-hydraulic actuators over other traditional approaches are discussed.
Kinematic Analysis of Cranes Using Neural Networks
Proceedings of the ... ISARC, 1999
Due to load uncertainties of cranes, it is necessary to find exact kinematic parameters of crane mechanisms. prograrruning techniques [41. The objective function for minimization was taken as the weight of the girder. The limitations on the stresses and the deflections induced in the girder in different load conditions were stated in the form of inequality constraints. This research is concerned with application of neural network to the kinematic analysis of a crane mechanism. The type of network investigated is a Radial Basis Neural Network (RBNN). The crane mechanism is considered as a double-rocker four-bar mechanism. Desired kinematic parameteres of the crane is found by a a software deal ing with simulation and analysis of nrecharmisms. The RBNN is employed in four parameters prediction schemes; displacement, velocity, acceleration and force. The results obtained have supported the theory that the proposed RBNN is able to predict different types of crane system.
An Investigation on the Performance of Hydrostatic Pumps Using Artificial Neural Network
JSME International Journal Series C, 2004
In this paper, an analysis of volumetric efficiency of hydrostatic pumps in a variety conditions is investigated by using a proposed neural network. The effects of the parameters, such as the number of revolution, hydraulic oil temperature and exit pressures, which act on performances of hydrostatic pumps like gear pumps, vane pumps, and axial reciprocal pumps with swash plate, on the volumetric efficiency have been examined. The revolution number of the pumps, exit pressure of the system and the hydraulic oil temperatures are greatly affected by the leakage flowrate. The neural network structure is very suitable for this kind of system. The network is capable of predicting the leakage flowrate of the experimental system. The network has a parallel structure and fast learning capacity. As it can be seen from the results for both approaches, neural network could be modeled hydrostatic pump systems in real time applications.
Force Analysis of Bearings on Cranes Using a Proposed Recurrent Hybrid Neural Network
Due to load uncertainties of cranes, it is necessary to find exact kinematic parameters of crane mechanisms. This research is concerned with application of neural network to the force analysis of a crane mechanism. The type of network investigated is a Recurrent Hybrid Neural Network (RHNN). The crane mechanism is considered as a double-rocker four-bar mechanism. Desired kinematic parameteres of the crane is found by a software dealing with simulation and analysis of mechanisms. The RHNN is employed in four parameters prediction schemes: displacement, velocity, acceleration and joints forces. The results obtained have supported the theory that the proposed RHNN is able to predict different types of crane system.
Adaptive control of a hydraulic crane using on-line identification
In this paper we present an approach to adaptive control of hydraulic actuators with exible mechanical loads. The approach is based on recursive identication of low order models of the dynamics from valve input to actuator position and e ective load pressure respectively. The model parameters are used to compute a regulator that gives a well damped system with good servo properties. The identi cation is carried out on-line in closed loop with no other signals than those present in normal operation. Here RLS with variable forgetting factor is used. The method does not, however, need not more parameters to be set a priori than ordinary RLS with x forgetting factor. In this way an easily tuned and robust identi cation algorithm is obtained. Results from experiments carried out on a lorry crane are presented.