Neural Network Based Multisensor Fusion in a Novel Permanent Magnet Multi-dof Actuator Orientation Detection System
نویسنده
چکیده
The methods of multi-DOF actuator orientation detection based on machine vision and magnetic field sensor and neural network based multisensor fusion are presented in this paper. Special grid pattern is printed on the surface of rotor according to the pseudo-random encoder for the camera capturing the image of the rotor. The magnetic field sensors are adopted and properly placed circling the shaft of rotor for detection the orientation information. By analyzing the image of the rotor, the coordinates of characteristic points in the coordinate system fixed on the rotor are derived. Combined with the magnetic sensor scheme to reduce the measurement error and enhance the fault tolerant ability, a multisensor data fusion scheme using BP neural network is developed and validated by experiment. The results show that multisensor data fusion based on NN is superior to single INTERNATIONAL JOURNAL ON SMART SENSING AND INTELLIGENT SYSTEMS, VOL. 5, NO. 4, DECEMBER 2012
منابع مشابه
Optimal Shaping of Non-Conventional Permanent Magnet Geometries for Synchronous Motors via Surrogate Modeling and Multi-Objective Optimization Approach
A methodology is proposed for optimal shaping of permanent magnets with non-conventional and complex geometries, used in synchronous motors. The algorithm includes artificial neural network-based surrogate model and multi-objective search based optimization method that will lead to Pareto front solutions. An interior permanent magnet topology with crescent-shaped magnets is also introduced as t...
متن کاملAn efficient method for cloud detection based on the feature-level fusion of Landsat-8 OLI spectral bands in deep convolutional neural network
Cloud segmentation is a critical pre-processing step for any multi-spectral satellite image application. In particular, disaster-related applications e.g., flood monitoring or rapid damage mapping, which are highly time and data-critical, require methods that produce accurate cloud masks in a short time while being able to adapt to large variations in the target domain (induced by atmospheric c...
متن کاملNovel Unified Control Method of Induction and Permanent Magnet Synchronous Motors
Many control schemes have been proposed for induction motor and permanent magnet synchronous motor control, which are almost highly complex and non-linear. Also, a simple and efficient method for unified control of the electric moto are rarely investigated. In this paper, a novel control method based on rotor flux orientation is proposed. The novelties of proposed method are elimination of q-ax...
متن کاملAn Orientation Measurement Method Based on Hall-effect Sensors for Permanent Magnet Spherical Actuators with 3D Magnet Array
An orientation measurement method based on Hall-effect sensors is proposed for permanent magnet (PM) spherical actuators with three-dimensional (3D) magnet array. As there is no contact between the measurement system and the rotor, this method could effectively avoid friction torque and additional inertial moment existing in conventional approaches. Curved surface fitting method based on expone...
متن کاملDynamic Modeling, Characteristic Analysis and Co-simulation of the Permanent-Magnet Spherical Actuator
As the traditional mathematical modeling may lead to difficulties in solving a complex problem, a novel co-modeling and simulation method for the three-degrees-of-freedom (3-DOF) permanent-magnet spherical actuator (PMSA) is presented. After describing the basic structure and operating principle of PMSA, a geometry model is set up based on the SolidWorks. The dynamic characteristics are then an...
متن کامل