Jingtao Hu

Selection of spectral data for classification of steels using laser-induced breakdown spectroscopy

Principal component analysis (PCA) combined with artificial neural networks was used to classify the spectra of 27 steel samples acquired using laser-induced breakdown spectroscopy. Three methods of spectral data selection, selecting all the peak lines of the spectra, selecting intensive spectral partitions and the whole spectra, were utilized to compare the influence of different inputs of PCA on the classification of steels. Three intensive partitions were selected based on experience and prior knowledge to compare the classification, as the partitions can obtain the best results compared to all peak lines and the whole spectra. We also used two test data sets, mean spectra after being averaged and raw spectra without any pretreatment, to verify the results of the classification. The results of this comprehensive comparison show that a back propagation network trained using the principal components of appropriate, carefully selected spectral partitions can obtain the best results. A perfect result with 100% classification accuracy can be achieved using the intensive spectral partitions ranging of 357-367 nm.

Broken Rotor Bars Fault Detection in Induction Motors Using Park's Vector Modulus and FWNN Approach

In this paper a new integrated diagnostic method based on the current Parks Vector modulus analysis and fuzzy wavelet neural network classifier is proposed for the diagnosis of rotor cage faults in operating three-phase induction motors. Detection of broken rotor bars has long been an important but difficult job in the detection area of induction motor faults. The characteristic frequency components of a faulted rotor in the stator current spectrum are very close to the power frequency component but by far less in amplitude, which brings about great difficulty for accurate detection. In order to overcome the shortage of broken rotor bars characteristic components being submerged by the fundamental one in the spectrum of the stator line current, Parks Vector modulus(PVM) analysis is used to detect the occurrence of broken rotor bar faults in our work. Simulation and experimental results are presented to show the merits of this novel approach for the detection of cage induction motor broken rotor bars.

Design and realization of EtherCAT master

EtherCAT is widely used in the numerical control, machinery processing field etc. EtherCAT solutions and products are mainly imported. Based on studying EtherCAT standard and EtherCAT network system thoroughly, this article presents a kind of feasible, low cost of design for EtherCAT master, which is called simple EtherCAT master, including hardware and software design, and project a plan to test the designed EtherCAT master.

A method for condition monitoring and fault diagnosis in electromechanical system

Condition monitoring of electrical machines has received considerable attention in recent years. Many monitoring techniques have been proposed for electrical machine fault detection and localization. In this paper, the feasibility of using a nonlinear feature extraction method noted as Kernel independent component analysis (KICA) is studied and it is applied in self-organizing map to classify the faults of induction motor. In nonlinear feature extraction, we employed independent component analysis (ICA) procedure and adopted the kernel trick to nonlinearly map the Gaussian chirplet distributions into a feature space. First, the adaptive Gaussian chirplet distributions are mapped into an implicit feature space by the kernel trick, and then ICA is performed to extract nonlinear independent components of the Gaussian chirplet distributions. A thorough laboratory study shows that the diagnostic methods provide accurate diagnosis, high sensitivity with respect to faults, and good diagnostic resolution.

Fault Monitoring and Diagnosis of Induction Machines Based on Harmonic Wavelet Transform and Wavelet Neural Network

The fault symptoms of stator winding inter-turn short circuit and rotor bar breakage are analyzed completely in this paper. And a new method for fault diagnosis of broken rotor bar and inter-turn short-circuits in induction machines is presented. The method is based on the analysis of the motor current signature analysis of induction machines using Zoom FFT spectrum analysis, generalized harmonic wavelet transform filter and hybrid particle swarm optimization (HPSO) based wavelet neural network. As an on-line current monitoring and non-invasive detection scheme, the presented method yields a high degree of accuracy in fault identification as evidenced by the given experimental results, which demonstrate that the detection scheme is valid and feasible.

Velocity control system with variable universe adaptive fuzzy-PD method for agricultural vehicles

The velocity of agricultural vehicle is an important variable for the navigation system and variable rate applicator in precision agriculture, and the stable velocity in the filed improves the control accuracy of those systems. After analyzed the powertrain system of agricultural vehicles, a simple and general velocity control system was designed regardless of the structure of powertrain. Meanwhile, this system can be adapted without damage the vehicles original mechanical structure, and cooperate with the precision agriculture application via the CAN bus. The variable universe method and incomplete derivation control strategy were introduced in the designed of fuzzy-PD controller to improve the adaptability. The road test was accomplished on LOVOL TA800 tractor and YAMMAR VP6 rice transplanter. The test results show that the mean absolute error is less than 0.045 m/s, and the velocity control system is reliable and effective.

DMC-PD cascade control method of the automatic steering system in the navigation control of agricultural machines

In the navigation control of agricultural machines, in order to improve the precision and response speed of the steering control system, an automatic steering control method based on DMC-PD cascade control was proposed. The model of automatic steering driving mechanism was built through analyzing the mechanism and electric control principle. The model of steering mechanism for agricultural machines was identified in time-domain according to dynamic response data. A steering control model was built by combining both models. Based on this model, adopted cascade control structure, the inner loop designed a DMC controller for steering angular velocity, and the outer loop designed a PD controller for steering angle. A steering angular velocity control simulation was taken by Matlab MPC toolbox, and an automatic steering control experiment was carried out in a YANMAR VP6 rice transplanter. The experimental result indicates, the absolute value of steering angle tracking error is 0.5°, and tracking delay is 0.25s. Therefore, the DMC-PD cascade control method can satisfy the requirement of automatic navigation control for agricultural machines.

Adaptive H 2 /H ∞ filter for integrated navigation system

Conventional H_∞filter is much more conservative, as the filter parameters are set in the initial while Kalman filter requires the statistical properties of noise accurately. For the above limitations, this paper proposed an adaptive H₂/H_∞ filter for multi-sensor integrated navigation systems. The method derives the gain weight coefficient using the theory of matrix inequalities and estimation variance matrix based on the least trace criterion. The method can improve the accuracy and robustness of integrated navigation systems by adjusting gain weight coefficient automatically. Finally, the adaptive H₂/H_∞ filter method is compared with Kalman filter and H_∞ filter on the test platform, Results show that the adaptive H₂/H_∞ filter can provide better performance of integrated navigation systems by combining the advantages of the Kalman filter and H_∞ filter.

Speed and Load Torque Estimation of Induction Motors based on an Adaptive Extended Kalman Filter

When we monitor running state of induction motor in field, the sensorless estimation of load torque and speed of induction motor has important significance, in this paper, a method to estimate load torque and speed of motor using adaptive extended kalman filter(AEKF) is presented, the covariance matrices of noises are estimated while the speed and load torque of induction motor are estimated using EKF in this method; this method solved the problem that the estimate results of EKF are affected greatly by the covariance matrices of noise, Simulation demonstrate that this method can get higher estimated accuracy.

Design and Implementation of Visible Human-Machine Interface for Trajectory Tracking in Agriculture Vehicle Navigation

This paper designs a visible human-machine interface for field computer in an agriculture vehicle navigation control system. Field computer, with the function of system configuration, vehicle configuration, steering configuration, job management, path planning and map views, is the human-machine interface in agriculture vehicle navigation control system. This paper introduces the design of map views including field view and machine view for field computer system based on coordinate conversion. Field View gives a bird’s eye view of the map. The agriculture vehicle moves while the map keeps stationary. Machine view keeps agriculture vehicle in center of screen, while the map moves along the reverse direction of the agriculture vehicle.