Science for Brazil (Reino Unido)

Trains to run on time with “Digital Fat Controller.”

Publicado em 29 novembro 2017

CFlex: Spend five minutes with any railway enthusiast and you’ll discover his (or very occasionally her) real obsession is with scheduling, logistics – and “making the trains run on time.”

Indeed, the runaway global success of the 70 year-old Thomas the Tank Engine children’s book and toy franchise, features stories that hinge on the restoration of an orderly flow to the world’s locomotive traffic – all under the benign influence of the ‘Fat Controller,’ the scheduling mastermind of the stories.

His influence now includes Brazil, where franchise owners Mattel recently created a toy train persona in Raul, a snappy diesel engine badged in the national green-and-yellow flag colours. After long decades during which truck, bus and car travel ruled supreme and Brazil’s rail network was starved of capital, there’s plenty of catching up to be done before Raul’s real-life counterparts can recapture the popular imagination.

No surprise then, that Brazilian scientist-entrepreneurs seeking to aid the rehabilitation of their country’s long-degraded rail cargo network, have focussed on electronic track management and algorithmic solutions to promote orderly flow of goods. The result is the country’s first real time train circulation planning solution provider.

This is the cheapest way to address the multiple and complex disruptions that in real life – just as they do in the Thomas the Tank Engine franchise – play havoc with train schedules. Not just in Brazil, but in more mature markets too.

That’s the logic behind CFlex, a company now devoting its energy to exploiting the commercial potential of the Meta Planning Engine. The company was founded in 1996 as a project spinoff from Softex 2000 from the University of Campinas in São Paulo state to market its first product, CFlex Movement Planner.

CFlex specializes in development of decision support systems, which in turn rely on artificial intelligence and optimization techniques to offer unique and innovative solutions. This piece of software is, its designers claim, far superior to manual planning or the use of traditional mathematical optimization tools.

Meta Planning Engine promises the domestic and international rail transportation markets a new train circulation management solution. The programme will be able to choose the best algorithm among several available algorithms. By contrast, other software tools on the market tend to use just one to calculate train routes across a given network.

“The software will always seek the best possible algorithm among those available to resolve any circulation situation,” explains Plínio Roberto Souza Vilela, a professor at the University of Campinas’ FT-UNICAMP and principal investigator for the Meta Planning Engine project developed by CFlex.

Of course, routing optimisation software is nothing new: established international players in the railroad and air traffic management segment include Optym, Trapeze or Dassault’s Quintiq.

But tiny CFlex is confident there is space for it in the marketplace. CFlex now has a domestic and international presence, using installed computer systems that support decision-making based on a large number of variables.

The firm – which is run by railway engineer Elesbão de Oliveira Neto and civil engineer Carlos Eduardo Carneiro – has already sold its flagship product, CFlex Movement Planner, to large corporate customers in the Brazilian market and abroad. CFlex Movement Planner has been operational for 15 years.

Clients are mostly mining companies that ship ore to coastal ports by rail. Its main customer at present is Anglo-Australian mining and metals giant Rio Tinto. In fact, CFlex Movement Planner has a 90% share of the railway segment in Brazil, in addition to Australia, Argentina and Chile. It covers more than 35,000 kilometres of railway lines using this solution. Its designers claim that regardless of the railway’s profile, size or density, the software will in less than 10 seconds provide a high quality train circulation plan that matches business needs.

Vilela expects even better results from Meta Planning Engine. “We’ll be able to deliver the system with several different algorithms preinstalled, and the tool will choose the best one for use in each situation,” he says.

“For example, suppose we’re in a period of high demand for ore and therefore have many trains circulating in the network. This situation may require the use of an algorithm that’s been specifically designed to operate well in such cases. The tool will automatically detect this algorithm’s capacity to provide better results and choose it. If the demand situation changes, the system will again recognize the change and may choose a different algorithm. So the main advantage is the solution’s enhanced real-time flexibility and adaptability.”

In development, the Meta Planning Engine received support from public funds coordinated by São Paulo state’s research and innovation funding agency FAPESP.

Thanks to FAPESP’s Innovative Research in Small Business Program (PIPE), the firm completed Stage 1 of the project in 2014 and is now developing Stage 2. Meta Planning Engine will offer the domestic and international rail transportation markets a train circulation management solution calculating routes across any given network.

The firm is testing a version of the new software package in the laboratory. According to Vilela, in a few months, tests will be performed on real situations, such as Rio Tinto’s rail network in Australia. It also has a two-year sales plan ready and will again apply to FAPESP for support. “We’re halfway through Stage 2, and the results have been positive, so CFlex is already enrolling for Stage 3,” he says.

You can read a detailed article about CFlex written by Brazilian journalist Suzel Tunes by clicking here.