This paper proposes a novel method of training the parameters of adaptive-network-based fuzzy inference system (ANFIS). Different from the previous works which emphasized on gradient descent (GD) method, we present an approach to train the parameters of ANFIS by using an improved version of quantum-behaved particle swarm optimization (QPSO). This novel variant of QPSO employs an adaptive dynamical controlling method for the contraction-expansion (CE) coefficient which is the most influential algorithmic parameter for the performance of the QPSO algorithm. The ANFIS trained by the proposed QPSO with adaptive dynamical CE coefficient (QPSO-ADCEC) is applied to five example systems. The simulation results show that the ANFIS-QPSO-ADCEC method performs much better than the original ANFIS, ANFIS-PSO, and ANFIS-QPSO methods.

No abstract

A new high-speed foreign fiber detection system with machine vision is proposed for removing foreign fibers from raw cotton using optimal hardware components and appropriate algorithms designing. Starting from a specialized lens of 3-charged couple device (CCD) camera, the system applied digital signal processor (DSP) and field-programmable gate array (FPGA) on image acquisition and processing illuminated by ultraviolet light, so as to identify transparent objects such as polyethylene and polypropylene fabric from cotton tuft flow by virtue of the fluorescent effect, until all foreign fibers that have been blown away safely by compressed air quality can be achieved. An image segmentation algorithm based on fast wavelet transform is proposed to identify block-like foreign fibers, and an improved canny detector is also developed to segment wire-like foreign fibers from raw cotton. The procedure naturally provides color image segmentation method with region growing algorithm for better adaptability. Experiments on a variety of images show that the proposed algorithms can effectively segment foreign fibers from test images under various circumstances.

Work class remote operated vehicles (ROVs) are generally equipped with underwater manipulators and are widely used in underwater intervention and maintenance tasks. As the load of underwater operation is relatively heavy, most commercial underwater manipulators are hydraulically actuated and are not equipped with any sensor for joint angles to keep their architectures compact. Therefore, the automatic control methods widely used in industrial robots cannot be simply applied to underwater manipulators. In this paper, an estimation method on joint angles of manipulator is presented, in which several markers are arranged on the arm links and positioned from the corresponding cameras; consequently, the joint angles of the manipulator are estimated. The simulation results show that under typical optical vision positioning error (RMS: 5 mm), the positioning error of the end effector can be estimated as about 10 mm (RMS), which means that the proposed estimation method is feasible for the state estimation for automatic control of underwater manipulators.

No abstract