Добавил:
Опубликованный материал нарушает ваши авторские права? Сообщите нам.
Вуз: Предмет: Файл:

The topical issues of science and technology. Хрестоматия для студентов-бакалавров направления «Лингвистика»

.pdf
Скачиваний:
0
Добавлен:
11.08.2026
Размер:
649 Кб
Скачать

have room for error. The story is the same for everyone in the global railroad maintenance industry: they can’t man every crossing or regularly inspect every inch of every track, can they?

Gauging the state-of-the-art safety

Most accidents are avoidable, the common causes being derailments, level crossing accidents, collisions, and other hazards such as fire. Great Britain witnessed 517 train accidents in 2018-2019, while the U.S. reported 2,200 incidents in 2018. Before I paint too grim a picture, on the bright side, all these numbers are among the lowest they’ve ever been since the inception of the railroad over two centuries ago. Today, the focus is on enhancing surveillance to improve anomaly detection. The outcome we all desire is better hazard prevention and control. We’re getting there. In fact, the U.S. numbers in 2018 were 92 per cent lower than the 12,000 incidents in 1972.

But maybe we’ve come as far as humanly possible and need a little help as we pull into the last station, the final frontier of efficiency.

Could there possibly be a day where we report zero incidents in lightand heavy-rail transport? It’s a question we often mull over at Ignitarium’s R&D lab, ‘The Crucible’ as it is called. A couple of years ago, we sensed the opportunity to put a higher sense in the sky: aerial analytics. To do what we couldn’t before terrestrially, we would now do aerially – cheaper, faster, better.

61

Imagine being able to spot every fault over the vast expanses of every railroad line. Then building a large enough data set and analysing it to predict the next fault, while enabling this intelligence without disrupting train schedules. And doing it all with limited operator intervention. That’s a tall order. The sheer challenge made it a use case worth exploring. But before we hopped onto this video analytics wagon, which was set to grow at 42 per cent annually by 2022, the question was: we’ll cross the viability barrier, but how do we make it scalable?

Innovation, from the yard to the junction

Iron Man may have Jarvis, but our teams generally have to work with more science than science fiction. Here’s the ‘stark’ reality: hours in the lab are long, and prototype building is an endlessly iterative process of elimination for which one must toil tirelessly. As we tinkered with beta versions in the Ignitarium lab, we tried to ace the first test of any AI solution: running it without human supervision. Aerial analytics obviously meant mounting a camera on a drone or a fixed-wing aircraft, but how would we train it to be highly accurate irrespective of variations in movement?

The first step was to precisely capture the artefacts of interest, compensating for aircraft pitch, roll and yaw. Once that was done, we ensured no operator would be required to control or maneuver the camera system. This was achieved by adding the captain’s wings to Ignitarium’s dynamic camera alignment software. What we needed now was a way to acquire highquality video such that every rail-track-related object of interest

62

would be perfectly ‘centered’ in every single captured frame. Working with our hardware partners, we found a powerful device up for the mission: an AVerMedia Box PC EX731- AAH2-2AC0, with an NVIDIA Jetson TX2 module inside.

Once the aerial vehicle and gimbal were up in the air, the rail track footage was stored in 4K resolution for granular analysis. Complex image processing algorithms were written and rewritten for image registration, detection, and classification, all working in parallel on TYQ-i, Ignitarium’s defect detection

AI platform. At first, the AI was trained to look for obvious faults in the track: cracked or skewed ties and missing spikes or fish plates. Then, as it learned more, it was time to go deeper: see and tag foreign objects and even vegetation of all kinds. After multiple beta builds, it was time to set our AI free and let it fly.

Gathering steam: tunnel vision, sounding the alarm, and more

With our solution put to work for Skycam Aviation, a leading aerial imaging company in the U.S., we felt a sense of pride. And yet, the journey was only beginning. Our team switched tracks to other obstacle detection approaches: more work for us, and more processing for TYQ-i. Think of the combined powers of aerial analytics with cameras mounted on trains, trained to spot disruptions even in the dimmest of conditions: night, rain, snow. Or an AI hammer that analyses sound patterns while testing structural integrity inside tunnels to detect abnormalities. And what if the AI could study the historical

63

footage of the visual landscape around a train’s regular route to identify disparities with the current footage?

It’s not a what-if anymore: it’s as real as it is efficient. The mechanism is to install a depth detection camera in front of the vehicle. We then select a section of the track to be recorded, after which hundreds of frames from point A to point B are geo-tagged and stored as ‘golden reference’ saved feeds. Now we’re ready. When the train is in motion, the saved feed is synchronised with the live feed to detect differences. There are many paths to greater accuracy, and we are exploring them all: from comparing only key points in both frames, to using accelerometer or gyroscope based encoded data, to getting wheel rotation information from the train itself. Whatever the path, the objective is to make detection possible at ultra-high train speeds without missing out on any small objects. Sharpening this also requires the right definition of a region of interest (RoI) window.

Our mission at Ignitarium is to make it possible to implement vision analytics economically, at scale. So, the cost of predictive video analytics isn’t even a consideration when weighing it against human safety. That, I believe, would make my 21-year-old self really proud. As a newly minted electronics engineer from the Bangalore University, setting out on my rail travels at the turn of the millennium, I rolled up the window from my side berth in the coach. Brimming with optimism for the future, I gazed ahead at the tracks as the train snaked along a steep curve bend. Little did I know that a couple of decades

64

later, we would have sent a drone up ahead to gaze at it with me. (7521)

“Global Railway Review”

Flexibility is the key to survival in a rapidly-changing world

David Briginshaw

December 1, 2017

THE quest to reduce the emission of greenhouse and noxious gases from diesel engines appears to have taken on a new sense of urgency judging by the recent flurry of announcements about pilot projects for alternative-fuelled trains and contracts for the supply of trains with innovative traction systems. Such developments are vital if rail is to maintain its environmental competitive edge over other modes.

Renfe in Spain will begin pilot tests this month of a two-car passenger train powered by liquefied natural gas (LNG) in what it says are the first such trials in Europe. A CAF train is being used for the tests, in which one of its two diesel engines has been replaced by an LNG powered engine, with the remaining diesel used as a comparator.

Researchers expect to identify the technical requirements for LNG traction during the trials, which will offer a clearer idea of the environmental implications and the potential use of LNG on non-electrified lines.

65

In Germany, Lower Saxony Transport Authority (LNVG) signed a contract with Alstom and gas supplier Linde Group on November 9 for 14 Coradia iLint hydrogen fuel multiple units - the first order for iLint, following its debut at InnoTrans last year. Linde will install dedicated hydrogen refuelling facilities for the trains, which will have a range of 1000km on a single tank of hydrogen.

Meanwhile, the EcoTrain project led by German Rail (DB) is harnessing lithium-ion battery technology as an alternative to diesel operation, while last year, eight German railway associations called for further development of new traction systems such as batteries, fuel cells and hybrid systems.

In addition, Ballard Power Systems has signed an agreement with Siemens to develop a 200kW fuel cell engine for Siemens’

Mireo multiple unit, with the first main line trials planned for 2021. Siemens Mobility CEO Mrs Sabrina Soussa described the deal as “a decisive step towards replacing diesel-powered rail vehicles with emission-free vehicles.”

Ballard is also working with CRRC Tangshan, China, on a hydrogen-powered LRV and trials began on a 14km light rail line in Tangshan in October.

In the Netherlands, Arriva has signed a contract with Stadler for 18 Wink multiple units, which will initially operate on biodiesel. The trains will have engines designed to use hydrogenated vegetable oil (HVO), with provision for conversion to battery and overhead electric operation.

66

But it is not only rail which is developing new types of traction. A new potential threat to rail comes from Tesla. Mr Elon Musk, its founder and chief executive, unveiled the company’s first electric lorry, the Semi, in Los Angeles on November 17. Musk claims the overall cost of ownership for the Semi will be 12% less per kilometre than for diesel vehicles. The Semi will be able to accelerate from 0-100km/h in 20 seconds with a payload of 36 tonnes compared with around 1 minute for a diesel lorry, and it will climb 5% gradients at 105km/h compared with about 70km/h for a diesel. Tesla says the Semi will be able to regenerate 98% of kinetic energy to the battery. The Semi will have a range of 800km, and Tesla says it plans to introduce rapid dc chargers that will produce a 640km charge in 30 minutes.

The Semi will have an enhanced autopilot as well as automatic emergency braking, automatic lane keeping, lane departure warning, and event recording. But Musk’s most important claim is that several Semis will be able to autonomously follow a lead Semi as a convoy which he says would make it cheaper to send freight by road rather than rail.

While electric trains have better performance than diesel trains, if the Semi becomes a commercial reality and lives up to expectations, it could make life more difficult for rail freight operators wedded to diesel traction such as those in North America.

Nevertheless, one US railway has just made the switch from diesel to LNG. Florida East Coast Railway (FECR) has become

67

the first North American railway to adopt LNG for its entire mainline locomotive fleet following the modification of its fleet of 24 GE locomotives, which operate in pairs with a purposebuilt fuel tender.

LNG has been tested as a locomotive fuel for 25 years in North America and is still under evaluation by several Class 1 railways including BNSF. FECR has switched from diesel to LNG because its mainline locomotive fleet is captive to the Jacksonville - Miami main line, and it has access to a ready source of LNG.

While adopting LNG would enable railways to move away from their polluting diesels, it is not the game changer that electric traction can offer in terms of tractive effort and efficiency. And an electrified railway can be powered by any fuel which makes it ideally placed to withstand future changes in fuel availability. India’s railway minister, Mr Piyush Goyal, made a bold announcement on November 21 that Indian Railways will phase out mainline diesel locomotives within five years in favour of electric traction. While laudable, this appears unrealistic as only around one third of the 62,600km network is electrified and GE won a contract to build 1000 diesel locomotives just a year ago.

Electrification coupled with other innovations such as last-mile diesel-equipped electric locomotives, EMUs with batteries to take them beyond the wires, and dual-mode trains, demonstrate the increasing operational flexibility which is now available and will be one of the keys to success in the future. (5500)

* * *

68

Formal methods for signalling interlockings

Pete Duggan, chief engineer at Siemens Rail Automation September 12, 2017

Back in the day of mechanical signalling, it was comparatively simple to prove that signalling interlockings did what they were supposed to do. There were drawings to study and a finished mechanical system that could be tested. The interlockings themselves were fairly limited in their application, perhaps covering one junction or, at most, a series of junctions such as at a station throat, but it was all fairly comprehensible.

Then along came computer systems. Suddenly, the problem was immeasurably more complex. Every line of code could alter how the system worked and interlockings grew to control larger areas, introducing possibilities of more interactions. So how to check it? With teams of computer experts who were also signalling engineers, or signalling engineers who were also computer programmers, laboriously going through the program line by line?

A sensible and standardised approach was needed. So-called

‘Formal Methods’ are mathematical techniques used to specify, develop and verify computer programs and systems. They seemed like obvious candidates, but would have to be modified to work on safety-critical signalling systems.

69

Railway Industry Association Standard 23, (RIA 23) was developed back in the very early 1990s. ‘Formal Proof of Program’ was one of the selected techniques, labelled R for ‘recommended’ (as opposed to HR – ‘Highly Recommended’), for all (Safety Integrity Level) SIL 3 and SIL 4 systems. It was the forerunner to IEC (International Electrotechnical Commission) standard SC65A, concerned with the functional safety of electrical/electronic/programmable electronic systems (which would encompass safety-related software), and the BS EN 50128 standard – Railway applications, communication, signalling and processing systems, software for railway control and protection systems.

The standard has evolved such that formal methods seen today recommend ‘R’ for SIL 1 and 2, and ‘HR’ for SIL 3 and 4.

Clearly progress has been made with the standards.

However, there are many preconceptions on what ‘formal methods’ means. One of the more common definitions is ‘Using mathematically rigorous techniques and tools for the specification, design and verification of software and hardware systems’. In the early 1990s, few formal methods existed, with

VDM (Vienna Development Method) and the use of Z-notation being two of the options available at the time.

There was good reason for the early standards to only

‘recommend’ formal methods, as they were very much in the early stages of evolution. Not only were they the preserve of academia, but also they were certainly not sufficiently mature

70