Papers by Keyword: ICA

Abstract: In order to further improve monitoring safety of oil and gas pipelines, a leakage detection technology for natural gas pipelines with distributed Fiber Bragg Grating (FBG) is put forward. Optical fiber, set up along pipelines acting as FBG sensors, is used to acquire pressure and vibration signals created by some events such as leakage, mechanical disturbance. Through grating matching and automatic distinguish technique leakage can be detected and located. Moreover, independent component analysis (ICA) technique is studied and used to separate useful signal from noise. Theory analysis and experiments showed this method has good capacity to detect and locate leakage effectively in pipelines.

Abstract: Abstract. This paper discusses about the available transfer capability by using Unified Power Flow Controller-UPFC. Flexible AC Transmission System-FACTS devices helps to reduce power flow on overloaded lines, thereby increasing the loadability of the power system, transient stability, damp out oscillations and also provide security and efficient transmission system. UPFC is one of the most versatile FACTS controllers. It is used for both shunt and series compensation. Newton Raphson method is used to calculate load flow for IEEE 30 bus system. By optimally placing the FACTS device Available Transfer Capability-ATC is improved. The ATC is calculated by using AC Power Transfer Distribution Factor- ACPTDF and this method is based on the sensitivity approach. Imperialistic Competitive Algorithm (ICA) is used to find optimal location of placing UPFC to improve ATC.

Abstract: Strong motion stations have been constructed as a part of earthquake early warning system for high-speed train in China. They are deployed near railways and influenced by train-induced vibration. Then, picking seismic phase, estimating azimuth and extracting predominant frequency become difficult in this scenario. These procedures play a crucial role in locating earthquake, estimating its magnitude and then providing reliable warning to trains. In this paper, instantaneous mixing model was used to describe this problem and show that this influence could be removed by independent component analysis utilizing double sensors.

Abstract: hrough analyzing problems brought on change detection methods of high-resolution remote sensing images, a novel change detection algorithm is proposed. First, feature images of image’s objects extracted using oriented-object method serve as data of input vector to estimate sub-space for Independent Component Analysis(ICA), which can improve effect of noise suppression, simultaneously, a new algorithm using self-adapted weight is proposed in order to extract image’s object, which optimizes processing method on oriented-object deeply；new partitioning scheme using undecimated discrete wavelet transform(UDWT) overcomes effectively prominent problem which shrinking of the size of input vector becomes leads to unprecisely estimation of sub-space for ICA. Compared with typical algorithm, such as ICA and UDWT, simulation results show that new algorithm improves robust and veracity of change detection for high-resolution images greatly.

Abstract: Gearboxes are widely used in various kinds of applications. The normal operation of the gears contributes important roles on the machine performance. Due to harsh environment the rolling bearings are prone to failures. Hence, it is essential to detect the gear faults. However, the vibration signals of the gearbox are often contaminated, leading to deterioration of the fault diagnosis performance. To address this issue, a new approach is proposed based on the kernel independent component analysis (KICA) and BP neural network (BPNN). The KICA was used to extract sensitive signals to eliminate noise signals. Then a BPNN was adopted to detect the gear fault. To improve the fault identification, the Genetic Algorithm (GA) was adopted to optimize the BP parameters. Experiment tests using the gearbox fault simulator have been implemented. The test results show that the noise signals have been eliminated by the KICA and the GA-BPNN can detect the gear fault accurately. Moreover, through comparison with other existing methods, the proposed KICA-GA-BPNN produced the best detection rate of 93.7%.

Abstract: Traditional condition monitoring methods are not suitable for the nonlinear operation parameters and time-variable operation conditions. We propose an independent component analysis method based on sliding window statistics (SSWICA). This method uses statistics in sliding windows of parameters as input samples, then uses a N-step forward sliding window ICA method to modeling. Then we monitor the operating state of the equipments by observing whether the SPE index of real-time parameters exceeds the control limits. SSWICA is applied to condition monitoring of condenser in 600MW unit, comparing with traditional ICA monitoring methods based on sliding window. The results show SSWICA can accurately reflect current operating state and related changes of condensers state parameters, recognize steady, unsteady and fault conditions effectively. It is valuable for engineering practice and suitable for the application to equipments condition monitoring in power plant.

Abstract: Experienced engineers in transformer substation can judge the equipment condition via just listening to the working sounds of electrical equipments. Use audio signal processing applied in engines and other mechanical equipments for reference. A scheme to monitor the working condition of electrical equipments is proposed. Firstly, the basic principles and system structure of this scheme is outlined. It introduces the method of colleting electrical equipments working sounds by Microphone array, because Microphone array form a beam to target the source sound, which can reduce the noise and reverberation. When substation is working, the environmental background interference sounds exist and are independent from electrical working sound. So we can use FastICA algorithm that is based on the largest negentropy to separate the collected sound to several independent source signals. It has the advantage of fast convergence and robust. The simulation result shows this algorithm can effectively separate the multiple independent source signals. The separation accuracy is above 95% for typical sample mixed sounds and the reliability of electrical equipment fault detection system based on audio signal processing is ensured.

Abstract: Recently, automatic face recognition method has become one of the key issues in the field of pattern recognition and artificial intelligence. Typically, the face recognition process can be divided into three parts: the detection and recognition of human face, facial feature extraction and face recognition, and among which the facial feature extraction is the key to face recognition technology. In this paper, an extraction algorithm of face recognition feature, which is based on face recognition feature, is proposed. The experimental results based on the ORL face database demonstrate that this algorithm works well.

Abstract: The Independent Component Analysis (ICA) is a classical algorithm for exploring statistically independent non-Gaussian signals from multi-dimensional data, which has a wide range of applications in engineering, for instance, the blind source separation. The classical ICA measures the Gaussian characteristic by kurtosis, which has the following two disadvantages. Firstly, the kurtosis relies on the value of samples, and is not robust to outliers. Secondly, the algorithm often falls into local optima. To address these drawbacks, we replace the kurtosis by negative entropy, utilize the simulated annealing algorithm for optimization, and finally propose an improved ICA algorithm. Experimental results demonstrate that the proposed algorithm outperforms the classical ICA in its robustness to outliers and convergent rate.

Abstract: For partial discharge of transformer ultrasonic detection method exists positioning accuracy problems, the main reason mostly due to the time delay selected error is analyzed, while the main reason for time delay selected error is due to the transformer PD ultrasonic signal propagation which is extremely complex, the signals received by the ultrasonic sensor are the direct wave, non-direct wave and a mixture of all kinds of noise superimposed, so in order to improve positioning accuracy the correct separation of the direct waves time delay is important, this paper proposes a method of transformer PD direct wave ultrasonic signal separation based on independent component analysis (ICA), by a separate analysis of the direct wave signal, non-direct wave signal and noise characteristics of each principal component, the use of ICA to separate from the mixed signal to extract the direct wave signal and select the time delay, simulation and experimental results demonstrate the feasibility of the method.