System and method for monitoring train properties and maintenance quality

Abstract

The present invention discloses a system and a method for monitoring properties of at least one train is disclosed. The system comprises at least one sensor component configured to sample at least one sensor data relevant to the at least one train. The system further comprises at least one processing component configured to process the at least one sensor data. The system comprises at least one storing component configured to store the at least one sensor data, and at least one analyzing component.

1 - 16 . (canceled) 
     
     
         17 . A system for monitoring properties of at least one train/a railway infrastructure, the system comprising:
 at least one sensor component configured to sample at least one sensor data,   at least one processing component configured to process the at least one sensor data,   at least one storing component configured to store the at least one sensor data, and   at least one analyzing component.   
     
     
         18 . The system according to  claim 17  wherein the at least one analyzing component is configured to receive the at least one sensor data from the at least one sensor component further configured to estimate at least one estimation value of the at least one train/railway infrastructure. 
     
     
         19 . The system according to  claim 17  wherein the at least one analyzing component is configured to generate at least one first level model, preferably based on the at least one estimation value. 
     
     
         20 . The system according to  claim 18 , wherein the analyzing component is configured generate at least one first level model based on the at least one estimation value. 
     
     
         21 . The system according to  claim 20  further configured to generate at least one second level model, wherein at least one portion of the at least one second level model is based on at least a first interaction score, wherein the at least one analyzing component is configured to estimate at least two estimation values, and wherein the first interaction score is configured to be calculated by the system between the at least two estimation values. 
     
     
         22 . The system according to  claim 21  wherein the system is further configured to generate at least one third level model, wherein at least one portion of third level model is configured to be based on a second interaction score. 
     
     
         23 . The system according to  claim 22  wherein the analyzing component is configured to label the sensor data based on the first level model and/or second level model and/or the third level model. 
     
     
         24 . The system according to  claim 23  wherein the analyzing component is further configured to monitor and/or forecast at least one railway health status of at least one component of the railway infrastructure, preferably using the labelled sensor data. 
     
     
         25 . The system according to  claim 17  wherein the analyzing component comprises a self-learning module, wherein the self-learning module is configured to analyze at least one property of the at least one train/railway infrastructure. 
     
     
         26 . The system according to  claim 18 , wherein the analyzing component comprises a self-learning module, wherein the self-learning module is configured to analyze the at least one estimation value. 
     
     
         27 . A method for monitoring properties of at least one train/a railway infrastructure wherein the method comprising
 collecting at least one sensor data at least one time via a least one sensor arranged on at least one railway component,   determining at least one property of the at least one train/railway infrastructure based on the at least one sensor data, and   generating at least one determined property finding.   
     
     
         28 . The method according to  claim 27  wherein the method further comprises
 inferring an estimation value of the at least one property of the at least one 
 train/railway infrastructure, and 
 generating at least one estimated value. 
 
     
     
         29 . The method according to  claim 27  wherein the method comprises
 calibrating a physical model of the at least one property, and 
 generating at least one calibrated physical model, wherein the physical model comprises a first level model and/or a second level model and/or a third level model. 
 
     
     
         30 . The method according to  claim 29  wherein the method comprises performing a continuous monitoring, wherein the continuous monitoring comprises providing a series of measurements of the at least one physical property, wherein the method comprises an initial measurement and at least one subsequent measurement, wherein the method comprises comparing the initial measurement and the at least one subsequent measurement to generate at least one evolution status, wherein the at least one evolution status is based on a health status of an asset before and after a corrective measure. 
     
     
         31 . The method according to  claim 28  wherein the method comprises
 estimating a specific physical property of the at least one railway component to generate a first physical property finding, 
 correlating the first physical property finding to a health status of the at least one railway component, and 
 generating at least one final physical property finding comprising the health status of the at least one railway component. 
 
     
     
         32 . The method according to  claim 31 , wherein the estimating of the specific physical property of the at least one railway component is based on the at least one estimated value. 
     
     
         33 . The method according to  claim 27 , wherein the method comprises at least one analytical approach, wherein the analytical approach comprises at least one of: signal filter processing, pattern recognition, probabilistic modeling, Bayesian methods, machine learning, supervised learning, unsupervised learning, reinforcement learning, statistical analytics, statistical models, principle component analysis, independent component analysis (ICA), dynamic time warping, maximum likelihood estimates, modeling, estimating, neural network, convolutional network, deep convolutional network, deep learning, ultra-deep learning, genetic algorithms, particle filters, variations of Kalman filters, Markov models, and/or hidden Markov models. 
     
     
         34 . The method according to  claim 27  comprising building a simulation model based on a track settlement model wherein the simulation model is further based on time series analysis technique assuming that a ballast is uncompressed at an initial time. 
     
     
         35 . The method according to  claim 34  wherein the method comprises calculating a permanent deformation in a ballast geometry based on the track settlement model. 
     
     
         36 . The method according to  claim 27 , wherein the method comprises determining a safety threshold of the at least one train, wherein the safety threshold comprises a specified class of the at least one train, and wherein the specified class data of the at least one train comprises at least one of:
 a speed class data, and   an axle weight class data.