Jiande Wu

An attitude control method of unmanned helicopter based on adaptive output feedback

The unmanned helicopter exhibits a complex and nonlinear dynamic behavior and open-loop unstable. This paper describes a attitude control method based on adaptive output feedback for an unmanned helicopter. First, it is assumed that the controlled system satisfies the output feedback linearization conditions. Second, the approximate model of the system is considered as the diffeomorphism of the system. Then, a linear controller and adaptive neural networks are designed to cancel the model errors produced by nonlinear, uncertainty and disturbance. Finally, the boundedness of tracking errors and weight errors are studied with Lyapunov stability theorem. The application results of an unmanned helicopter show that the proposed controller can not only cancel the dynamical error effectively but also improve tracking performance of the attitude control system.

The Rolling Bearing Fault Feature Extraction Based on the LMD and Envelope Demodulation

Since the working process of rolling bearings is a complex and nonstationary dynamic process, the common time and frequency characteristics of vibration signals are submerged in the noise. Thus, it is the key of fault diagnosis to extract the fault feature from vibration signal. Therefore, a fault feature extraction method for the rolling bearing based on the local mean decomposition (LMD) and envelope demodulation is proposed. Firstly, decompose the original vibration signal by LMD to get a series of production functions (PFs). Then dispose the envelope demodulation analysis on PF component. Finally, perform Fourier Transform on the demodulation signals and judge failure condition according to the dominant frequency of the spectrum. The results show that the proposed method can correctly extract the fault characteristics to diagnose faults.

Fault Diagnosis Method of Check Valve Based on Multikernel Cost-Sensitive Extreme Learning Machine

Check valve is one of the most important components and most easily damaged parts in high pressure diaphragm pump, which is a typical representative of reciprocating machinery. In order to ensure the normal operation of the pump, it is necessary to monitor its running state and diagnose fault. However, in the fault diagnosis of check valve, the classification models with single kernel function can not fully interpret the classification decision function, and meanwhile unreasonable assumption of diagnostic cost equalization has a significant impact on classification results. Therefore, the multikernel function and cost-sensitive mechanism are introduced to construct the fault diagnosis model of check valve based on the multikernel cost-sensitive extreme learning machine (MKL-CS-ELM) in this paper. The comparative test results of check valve for high pressure diaphragm pump show that MKL-CS-ELM can obtain fairly or slightly better performance than ELM, CS-ELM, MKL-ELM, and multikernel cost-sensitive support vector learning machine (MKL-CS-SVM). At the same time, the presented method can obtain very high accuracy under imbalance datasets condition and effectively overcome the weakness of diagnostic cost equalization and improve the interpretability and reliability of the decision function of classification model. It, therefore, is more suitable for the practical application.

Fault diagnosis of rolling bearing based on permutation entropy and Extreme Learning Machine

In consideration that bearing faults usually appear in the form of periodical impacts, fault information is easily interfered by noises and it is difficult to extract fault features, a method is proposed for diagnosing faults of roller bearings based on PE (Permutation Entropy) and ELM (Extreme Learning Machine). First of all, signals of original acceleration and vibration are decomposed at several levels for bearings through MRSVD (Multi-resolution Singular Value Decomposition) to extract detailed components including fault features. Subsequently, PE values are extracted from the detailed components as values of fault characteristics, in order to construct feature vectors and input them to the ELM for training and recognition. This method is used for diagnosing local faults of roller bearings in their balls, inners and outers in practices, by analyzing the experimental data, the precision of fault recognition is up to 97.5% and thus proves that this method is highly effective for diagnosing faults of the bearings.

Fault diagnosis for rolling bearing based on lifting wavelet and morphological fractal dimension

The vibration signal of rolling bearing is complex and nonstationary. In this paper, in order to overcome the difficulty of rolling bearing fault diagnosis, lifting wavelet and morphological fractal dimension are combined, puts forward a method based on lifting wavelet and morphological fractal dimension for rolling bearing fault diagnosis. The step of the diagnosis goes as follows: firstly, decompose the vibration signal of rolling bearing into three layers by lifting wavelet transform and restructure it, then analyze energy spectrum of the reconstructed signal to get the energy distribution of signal in time-frequency domain. Secondly, calculate the morphological fractal dimension of energy in time-frequency domain to judge the status of bearing. Finally, the morphological fractal dimension of bearing vibration signal in time domain and time-frequency domain would be compared. The result shows that the status of bearing can be distinguished more accuracy through the propoesd method.

Bearing fault diagnosis method based on singular value decomposition and hidden Markov model

The fault signal feature extraction and fault identification of the bearing has important scientific research significance in the mechanized production. Aiming at this, this paper puts forward bearing fault diagnosis method based on singular value decomposition (SVD) and Hidden Markov Model (HMM). To gain required fault feature information, firstly, it builds Hankel matrix, and conducts decomposition through SVD. SVD method is helpful for gaining effective fault feature information from the complex bearing fault signals, and then apply the achieved characteristic value to build the training model of Markov. The test result proves that the method of this paper has good practicability in the bearing fault identification.

Fault diagnosis method based on wavelet packet-energy entropy and fuzzy kernel extreme learning machine

Aiming at connatural limitations of extreme learning machine in practice, a new fault diagnosis method based on wavelet packet-energy entropy and fuzzy kernel extreme learning machine is proposed. On one hand, the presented method can extract the more efficient features using the wavelet packet-energy entropy method, and on the other hand, the sample fuzzy membership degree matrix U, weight matrix W which is used to describe the sample imbalance, and the kernel function are introduced to construct the fuzzy kernel extreme learning machine model with high accuracy and reliability. The experimental results of rolling bearing and check valve are obtained and analyzed in MATLAB 2010b. The results show that the proposed fuzzy kernel extreme learning machine method can obtain fairly or slightly better classification performance than the traditional extreme learning machine, kernel extreme learning machine, back propagation, support vector machine, and fuzzy support vector machine.

An acoustic emission system for detecting failures of check valves based on STM32 and high-speed USB bulk transfer

As core equipment for transporting solid and liquid slurries through pipelines, reciprocating diaphragm pump is important for analyzing and monitoring failures of check valves on a real-time basis. In this paper, a pipeline of China for transporting iron ore concentrate within a long distance is examined. Besides, an STM32F103ZET6-based high-speed data acquisition and transmission system is designed according to the failures of check valves incurred after long-term operation inside reciprocating diaphragm pumps, such as jamming and leak. This system may upload acquired data to PC through USB Bulk transfer, the highest speed can up to 480Mb/s. Be applicable to hot-plugging, it may accurately transmit data at high speed. The upper computer is designed with C# language, so functions could be selected and the analytical results could be stored on visual interfaces. The experimental results suggest that the system designed could not only rapidly and accurately acquire and transmit data, but can also effectively detect failures of the diaphragm pumps.

Research on moving target detection algorithm based on MRA and wavelet threshold

Aiming at solving the noise problem which had lowered the accuracy in the target detection result from the process of image-collection and image-transmission, the paper proposes a new target detection algorithm based on the improved wavelet threshold. Firstly, these images are filtered by a denoising method, which combines the wavelet threshold method with the correlation of the wavelet coefficients, and its “Zoom” feature can eliminate the negative impact of noise; then a combined algorithm which connects background subtraction and two consecutive inter-frame subtraction is set up in order to combine their advantages and improve the effect of target detection. Compared simulation results of the four models, the results show that the target detection method based on multi-scale wavelet threshold is reasonable and effective, and more suitable for the real-time target detection.

Fault-Tolerant Integrated Navigation Algorithm of the Federal Kalman Filter

As the Federal Kalman filter has some good features such as flexibility, and good fault-tolerance, this paper proposes a federal Kalman filter design method and fault-tolerant structure. The structure uses the residual error between the local filter and reference filter for fault detection. In this paper, a simulation study of the integrated navigation system is done. The study shows that the algorithm is very simple, reliable, not only can quickly detect the fault of the external sensors and reference system, but also has good fault-tolerant. It can quickly detect and isolation fault, and let the integration of the system remain high precision.