Rail corrugation is a common problem in metro lines, and its efficient recognition is always an issue worth studying. To recognize the wavelength and amplitude of rail corrugation, a particle probabilistic neural network (PPNN) algorithm is developed. The PPNN is incorporated with the particle swarm optimization algorithm and the probabilistic neural network. On the basis of the above, the in-vehicle noise characteristics measured in the field are used to recognize normal rail wavelengths of 30 and 50 mm. A stepwise moving window search algorithm suitable for selecting features with a fixed order was developed to select in-vehicle noise features. Sound pressure levels at 400, 500, 630 and 800 Hz of in-vehicle noise are fed into the PPNN, and the average accuracy can reach 96.43%. The bogie acceleration characteristics calculated by the multi-body dynamics simulation model are used to recognize normal rail amplitudes of 0.1 and 0.2 mm. The bogie acceleration is decomposed by the complete ensemble empirical mode decomposition with adaptive noise, and a reconstructional signal is obtained. The energy entropy of the reconstructional signal is fed into the PPNN, and the average accuracy can reach 95.40%. This article is part of the theme issue 'Artificial intelligence in failure analysis of transportation infrastructure and materials'.

No abstract

No abstract

The steel-spring floating slab track (SSFST) is a low-stiffness structure, sensitive to the vehicle loads. Due to the coupling effect of the superposition of adjacent bogies, it is difficult for conventional single-carriage models to meet the simulation requirements. To find a balance between computation efficiency and authenticity of analytical model results, the influence of carriage number on SSFST should be studied. Based on the finite element method and multi-body dynamics, a refined three-dimensional coupled model of multi-carriage-SSFST-tunnel was established. The difference in the dynamic response of the SSFST between single-carriage and multi-carriage models was analyzed and compared with the measured data. The field test results show that structural displacements and accelerations under the two-carriage model are much closer to the measured data. The dynamic model analysis results show that the maximum displacement of the rail and SSFST in the midspan of the slab increase by 0.48 mm and 0.34 mm under the multi-carriage model, and the vibration reduction effectiveness increases by 1.4–2.0 dB. Dynamic responses of the rail and SSFST show minor differences under the two-carriage and three-carriage models. The article is expected to provide a reference for the theoretical research, design, and layout optimization of subway SSFST.

Using a plastic water hose not only affects water resources, but also affects people's daily lives. Due to over bending or twisting during service times, plastic hoses tend to fold, buckle, or crack. The new developed spiral plastic hose can overcome the above problems, however, how to evaluate its properties is still an industry need. By using machine vision technology to analyze the spiral plastic hose quality such as the spring-back property is a good methodology which can facilitate the trust relationship between the industries and consumers. Three-dimensional machine vision technologies were used to examine five different kinds of plastic hoses, i.e. type A-E. At first, a testing platform is designed and the measuring algorithm is proposed to measure the inner radius of the bent plastic hose. By using image processing technology and the developmental program, the radius information of plastic hoses before and after spring-back are obtained for further analysis. According to experimental results based on the proposed inspection system, Type B plastic hoses behave with no-kink and its spring-back ratio is 3.457, which is the best of the plastic hoses. Plastic hose of Type D behaves kink situation and its spring-back ratio is 1.117 which is the worst. By comparing the experimental results to the manufacturers offering information, a good agreement is obtained. Therefore, this study provides an innovative inspection system to determine plastic hose quality.