The condition monitoring of railway track line is one of the essential tasks to ensure the safety of the railway transportation system. Railway track line is mainly composed of tracks, fasteners, sleepers, and so on. Given the requirements for rapid and accurate inspection, innovative and intelligent methods for multi-target defect identification of the railway track line using image processing and deep learning methods are proposed in this paper. Firstly, the track and fastener positioning method based on variance projection and wavelet transform is introduced. After that, a bag-of-visual-word (BOVW) model combined with spatial pyramid decomposition is proposed for railway track line multi-target defect detection with a detection accuracy of 96.26%. Secondly, an improved YOLOv3 model named TLMDDNet (Track Line Multi-target Defect Detection Network), integrating scale reduction and feature concatenation, is proposed to enhance detection accuracy and efficiency. Finally, to reduce model complexity and further improve the detection speed, with the help of dense connection structure, a lightweight design strategy for the TLMDDNet model named DC-TLMDDNet (Dense Connection Based TLMDDNet) is proposed, in which the DenseNet is applied to optimize feature extraction layers in the backbone network of TLMDDNet. The effectiveness of the proposed methods is demonstrated by the experimental results. INDEX TERMS Railway track line defects, multi-target defect identification, image processing, deep learning, YOLOv3.
This paper aims at the blade root moment sensor fault detection and isolation issue for three-bladed wind turbines with horizontal axis. The underlying problem is crucial to the successful application of the individual pitch control system, which plays a key role for reducing the blade loads of large offshore wind turbines. In this paper, a wind turbine model is built based on the closed loop identification technique, where the wind dynamics is included. The fault detection issue is investigated based on the residuals generated by dual Kalman filters. Both additive faults and multiplicative faults are considered in this paper. For the additive fault case, the mean value change detection of the residuals and the generalized likelihood ratio test are utilized respectively. For multiplicative faults, they are handled via the variance change detection of the residuals. The fault isolation issue is proceeded with the help of dual sensor redundancy. Simulation results show that the proposed approach can be successfully applied to the underlying issue.
Vibration exists everywhere especially in the public railway operation system. The vibration acceleration is the key factor to monitor and evaluate the structure health of the railway equipment. In this paper, a kind of self-powered triboelectric nano vibration accelerometer (TEVA) is presented. A low frequency spring mass vibration model is built to calculate the vibration sensitive performance and the electric output of the TEVA. The prototype of the TEVA is demonstrated and characterized through the railway vibration simulation platform. It has been testified that TEVA can successfully harvest the low frequency vibration energy and convert it to electrical power to achieve the self-powered vibration acceleration monitoring system. The output current and voltage of TEVA are also sensitive to the vibration acceleration from 1.07m/s 2 to 1.25m/s 2 linearly. Hence it can be used as a self-powered nano vibration accelerator for the fault diagnosis. In addition, the generated electricity is used for charging the lithium battery (from 1.5V to 3.1V) which supplies power to the ZigBee module. The experiment shows that the charged battery through TEVA can support the wireless communication between ZigBee modules, with temperature and humidity sensors embedded on it. The temperature and humidity on the train are 22 degree Celsius and 35%RH respectively. Therefore, the vibration energy can be harvested and stored for the power supply of wireless sensor network nodes in the near future. Keyword: Self-powered vibration accelerometer, Spring Mass Model, triboelectric nanogenerator, wireless sensor, state health monitoring 1.Introduction With the development of the high speed railway, the safety operation of railway system has attracted more and more attentions. Key equipment of railway system such as bogies and railway tracks need to be inspected to ensure the safety and reliability during the operation [1]. Information such as using life span and fault classifications derived from the inspection is pretty important for the railway operation safety. Therefore, the state health monitoring (SHM) of key equipment is very necessary. There are a lot of methods for Railway SHM (RSHM), including temperature monitoring, acoustic monitoring and vibration signal monitoring. For example, the wheel brake temperature monitoring will supply feedback to the train driver [2]. And the air temperature and humidity monitoring of the train carriage will prevent the breakdown of traction power system. Vibration signal analysis has many advantages and suitable for almost every kind of railway key equipment. Besides, the collected vibration signal is easily stored and to process. The processing method is various and the fault diagnosis result is accurate [3-6]. The vibration signal analysis method has been used widely, a lot of researches has applied this method for the railway key
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.