A reliable system has been created by Southwest Research Institute (SwRI) to autonomously identify compressed air leaks that are very common on trains and communicate their position to maintenance staff. The automated method may decrease the amount of time, money, and manpower required to locate and fix air leaks as well as the overall fuel and get rid of emissions produced by the locomotive industry. Air leaks are responsible for millions of dollars in losses every year. Therefore, finding a way to reduce their occurrence to a minimum is great news for the locomotive industry.
Compressed air is used by trains for several purposes, such as air brakes, shutters, valve actuation, radiators, bells, and horns. Air leaks in trains that happen at various locations cost the rail sector between 2 and 3 percent of its annual vehicle efficiency. Additionally, the operability and safety of trains may suffer as a result of these leaks. Engineers have been striving over the decades to come up with measures that will help minimize air leaks in the industry hence ending up saving a lot of money in the process.
Reducing fuel consumption
Air leaks substantially increase the consumption of fuel and decrease the effectiveness of AESS, which is the automatic engine stop-start system of a locomotive. The system is responsible for causing locomotives to operate more frequently, use more fuel, and shorten the parts’ lifespan like starters, batteries, and air compressors. He further reiterated that the industry may possibly save a lot of fuel while lowering emissions of nitrous oxide, particulate matter, and carbon dioxide.
Currently, identifying air leaks needs railroad workers to do so manually, which is always a lot of work to do. They frequently climb on, underneath, or between train cars to feel or listen for leaks. This procedure is ineffective, consumes a lot of time, and puts mechanical staff members at unnecessary risk. In light of this, allowable train air leaks have been set down by the Federal Railroad Administration and railways.
SwRI has developed a system that autonomously detects, identifies, and reports air leaks, including those on moving trains, using auditory detection technologies, cameras, and machine learning. This way, time and money are preserved and more importantly, the technicians are not put in dangerous situations. Â
Machine learning
The system makes use of a compact SV600 Fluke fixed acoustic imager, which is commercially available. It has a camera for detecting frequencies and an a64 microphone array between 30 and 45 kHz, which are frequencies that are known to stand out for compressed air leaks from the majority of background noise the best. Together, this device and a camera contain a secondary visual spectrum. The group trained and used an algorithm of machine learning to detect air leaks thanks to the sensor outputs. All this happens while disregarding outputs that are non-leak-related to automate the detection procedure.
With a false positive rate of just 0.03%, this prototype system effectively identified a variety of air leaks located in different locations on the trains during testing. On a moving train, the system discovered eleven of every thirteen leaks on average. In the event that an air leak is discovered, the appropriate personnel was sent an alert accompanied by an image that showed the area that required repairs and inspections. As a result, the repairs happen swiftly and imminently.
This particular technology should minimize the workload for mechanical staff as well as boost the effectiveness and efficiency of our compressed air system. If implemented properly, the system could possibly save this industry a lot of dollars in fuel maintenance costs and savings, which are currently draining the industry. However, further field research and testing are still required. By increasing locomotive fuel efficiency, this technology may also significantly lower the emission of greenhouse gases. Planet earth will ultimately benefit from this initiative.
