page 1
page 2
page 3
page 4
page 5
page 6
page 7
page 8
page 9
page 10
page 11
page 12
page 13
page 14
page 15
page 16
page 17
page 18
page 19
page 20
page 21
page 22
page 23
page 24
page 25
page 26
page 27
page 28
page 29
page 30
page 31
page 32
page 33
page 34
page 35
page 36
page 37
page 38
page 39
page 40
page 41
page 42
page 43
page 44
page 45
page 46
page 47
page 48
page 49
page 50
page 51
page 52
page 53
page 54
page 55
page 56
page 57
page 58
page 59
page 60
page 61
page 62

30www.SmartRailWorld.comRail and Metro Innovation Guide 2018ROLLING STOCKSECTION 430

Rail and Metro Innovation Guide 2018www.SmartRailWorld.com31SECTION 4: ROLLING STOCKImagine one of the busiest national railway networks in the world. It's a heavy rail network, so intensely used and with such density of track, it actually more closely resembles a country-wide metro system. Now add an increasing number of trains each year plus a privatized market for daily maintenance with performance driven contracts and you will have a picture of the complex 3000km daily reality for Strukton Rail in the Netherlands. Their challenge is a significant one and we are today able to share with you an exclusive insights into their work. The company has had to deal with ever stringent contractual requirements to guarantee better track performance and safer working conditions in less time, and yet continued to make money out of the contract. They have managed to reduce their total maintenance costs by 30% since 2008 and reach a 90% reduction on rail safety related exceedances. Their daily reality is the cradle for many proven, tested and implemented innovations by Strukton Rail, so let's find out more about how they've done this... The latest in Strukton Rail's search for ways to prevent failures from occurring is a combination of POSS (an in-house developed preventative maintenance and breakdown diagnosis system which has been collecting data for over 15 years) with the know-how of the operation of points combined with the big data and artificial intelligence expertise brought in by 'Anchormen' (a Dutch data science expert company). The system itself already automatically issues a warning if a point is consuming too much energy, but this often happens just before the failure occurs. Based on patterns in historical data, a computer model can detect aberrant behaviour before it is actually observable. By learning the behaviour that accompanies a particular type of malfunction, it can identify potential failures at an early stage and issue a warning. Test results show that a substantial number of failures can already be predicted two weeks in advance with a high degree of reliability. Specific maintenance actions can then be taken without obstructing rail traffic, in order to prevent the actual occurrence of the malfunction. This way of working delivers that much needed time to plan maintenance work in a usually very short window of opportunity which in some cases in the Netherlands is just a couple of hours once every four weeks.The POSS system is sold worldwide, but with this added function of predicting potential failures weeks in advance the system truly delivers railroads better and safer track performance in a much shorter possession with a higher level of efficiency."It is possible to train computers in recognizing when maintenance is needed simply with self-learning algorithms. But such systems will always perform better when domain experts are involved. In this case, we were glad that the people from Strukton could guide us and indicate why points can fail and know which data you need to predict specific malfunctions" - Jeffrey Van der Eijk, Anchormen (@anchormenBDS)At home in the Netherlands, the company created a complete control room to keep track of all the track data that comes their way almost every minute. In this data driven environment the POSS monitoring system gives an alarm ideally two weeks in advance. The various systems in the control centre bring up images of the switch in question, made earlier by a video inspection train. The maintenance engineers take a look at the maintenance history of the track combined with satellite images, and plan the necessary maintenance. This planned maintenance action then becomes visible on the clients web portal informing them of when to expect a crew in their track. Based on the principle of the systems and philosophy that they use it doesn't matter whether or not that data comes from a track two streets down the road or from a track on the other side of the world. With the current technology in place it is also possible to monitor a switch and subsequently predict a failure two weeks in advance in Australia or the United States. Strukton Rail can monitor track on another continent by remote control and data analysis while taking on contractual risks as to the performance of that track. This closely resembles a situation which has long been in use in the aviation industry with remote censoring.The rail industry is only just stepping out of a traditional and conservative way of doing things and is just waking up to the potential of new technologies already common elsewhere. Strukton Rail (@StruktonRail) has embraced these new technologies for some time now and has implemented them while continuously improving existing technologies and learning about new ones.Expert view: Identifying problems before they become delays.