Shvartzon, Avraham (Bar Ilan University) | Azaria, Amos (Carnegie Mellon University) | Kraus, Sarit (Bar Ilan University) | Goldman, Claudia V. (General Motors, Herzeliya) | Meyer, Joachim (Tel Aviv University) | Tsimhoni, Omer (General Motors)
Preventive maintenance is essential for the smooth operation of any equipment. Still, people occasionally do not maintain their equipment adequately. Maintenance alert systems attempt to remind people to perform maintenance. However, most of these systems do not provide alerts at the optimal timing, and nor do they take into account the time required for maintenance or compute the optimal timing for a specific user. We model the problem of maintenance performance, assuming maintenance is time consuming. We solve the optimal policy for the user, i.e., the optimal timing for a user to perform maintenance. This optimal strategy depends on the value of user's time, and thus it may vary from user to user and may change over time. %We present a game Based on the solved optimal strategy we present a personalized maintenance agent, which, depending on the value of user's time, provides alerts to the user when she should perform maintenance. In an experiment using a spaceship computer game, we show that receiving alerts from the personalized alert agent significantly improves user performance.
Laura Riley has a 10-year-old son, Louis, and has been chasing child maintenance payments for nine years. She says she is owed more than £9,000, but has been unable to get any money from her son's dad. Across the UK, there is a backlog of more than £3.8bn in uncollected child maintenance payments, with figures showing about 1.2 million people are owed money.
When managing the maintenance practices for a facility it's important to understand the different approaches and the benefits of each. At the core, maintenance styles can be classified into a few different categories. Some of the most common approaches include reactive maintenance and preventative maintenance. You may already be familiar with those or even practicing them yourself, but there are more efficient styles quickly gaining traction. Predictive maintenance (PdM) is defined as maintenance practices designed to help determine the condition of in-service equipment in order to predict when maintenance should be performed rather than on a preset schedule (preventative).
NEW DELHI: Artificial intelligence (AI) that can diagnose the condition of rail tracks will be used by the railways to prepare a repair and replacement calendar and improve punctuality of trains, according to an official. In India, unplanned track maintenance work is often cited as a reason why train operations descend into chaos. Use of AI, the official said, will ensure that at least 90% of trains run on time as routine maintenance work would be planned in advance on the basis of the AI-aided calendar. All large maintenance blocks will be taken up only on Sundays to minimise the impact of train delays, the official said, adding that the national transporter is already procuring automatic track detection machines which, through AI, can predict the life of tracks and track joints. The move is also seen substantially reducing the number of train accidents.
Predictive maintenance is a bit ahead in the hype cycle, having past its peak. Now is the time for it to slowly penetrate business. However most executives are not clear on difference of predictive maintenance from the preventative maintenance they have been conducting for years so it would be great to start off with the definitions. Predictive maintenance: Perform maintenance when you predict that issues will arise. Keeps maintenance costs minimum since maintenance will only be completed when predicted and maintenance will be planned preventing urgent resource allocation inefficiencies.