Optimizing Aircraft maintenance
On 13 February 1955, a Sabena Douglas DC-6 plane crashed while on an approach to Rome, Italy. All 29 passengers and crew aboard were killed. These incidents always attract global horror. What happened? Unfortunately human error remains the largest contributor to aircraft accidents. The second element, however, is maintenance error. Almost 12% of all reported aircraft accidents are due to a maintenance error. These errors impose a significant financial burden on airlines, as they are also a major cause of flight delays and cancellations. Regardless of the class or type of aircraft, surveys consistently indicate that maintenance costs can range from between 10 and 45 percent of total yearly operating expenses. Computer engineer Susana Ferreiro, together with Dr. Basilio Sierra-Araujo (Head of the Department of Robotics and Autonomous Systems of the Computing Faculty in Donostia-San Sebastian), has produced a thesis entitled 'Contributions towards the diagnosis and prognosis of industrial problems by means of Supervised Classification Techniques'. The aim of her research has been to apply artificial intelligence techniques, data mining and machine learning to problems linked to the aeronautics industry and in particular the issue of maintenance. "These are algorithms and classifying models that extract information from large volumes of data and infer knowledge on the basis of these data," explains Ferreiro. The study looked into three specific aspects of aeronautics where maintenance is a major issue. The first issue is the degradation of aircraft brakes, the second is the appearance of burrs created during the drilling process in the manufacture of components while the third is the basicity number (BN) of oil on the basis of spectroscopic data. The BN of oil is used to estimate what condition it is in, and if it needs to be replaced. In terms of aircraft brake wear, the study looked into how to cut the costs of aircraft line maintenance - in other words, maintenance carried out after landing between one flight and the next take off - by deferring it to a more convenient time and place. The study also sought to reduce waiting times between flights to ensure punctuality by eliminating delays caused by corrective maintenance. "A series of components of the aircraft are usually checked between one flight and the next. Sometimes an unanticipated problem arises, so the aim is to have an estimate of the wear of certain components to anticipate all the resources that are going to be necessary," says Ferreiro. "The aim is also to optimise airline routes because sometimes there is an interest in having the maintenance done in a specific country, and what is needed for this is the forward planning of the state of the aircraft." This line of research was also carried out under a European project called TATEM. Drilling burrs occur during the manufacturing process. When the components are manufactured, a check needs to be done to make sure that the burr - the notch that has come away during the drilling - does not exceed 127 microns, as specified by the aeronautics industry. "We have developed a process using the internal signals of the machine which detects in real time when the limit has been exceeded," explains Ferreiro. Normally, after drilling, a process is always applied to eliminate the remaining burr, but thanks to this research, the process would be applied only when the limit is exceeded. This part of the research was started in another EU project called ARKUNE. Oil lubricating properties can deplete over time, which in turn can affect various elements in an airplane. The study looked into prediction of the basicity number (BN) of the oil on the basis of spectroscopic data. "The basicity number (BN) is used to estimate what state it is in i.e. whether it is satisfactory, or whether it needs to be monitored because it has started to degrade, or whether it needs to be replaced," says the author. The aim of the study was to establish a model for detecting the extent of oil degradation without having to run a laboratory test, which can be a very expensive task. The idea developed in this thesis is to replace this method of analysis by near infrared FTIR spectrometry. With this method, "it is possible to develop a sensor and incorporate it into the machine and in what is being monitored without having to run a lab test," explained Ferreiro. The results of the study should help cut maintenance costs and improve airline safety in the long run, making tragic accidents like the Rome crash in February 1955 increasingly a thing of the past.For more information, please visit: Basque Research http://www.basqueresearch.com/berria_irakurri.asp?Berri_Kod=4310&hizk=I#.URtTmWdyJid