Marine diesel engines operate in environments in which damage easily occurs from corrosion. Recently, damage to cylinder liners has increased from corrosion wear caused by increased engine power. This damage can cause serious problems in the economy. Thus, many researchers have treated and studied damaged cylinder liners. However, a method is necessary for real-time monitoring of damage to cylinder liners during operation of the engine, before serious damage can occur. This study carries out reciprocating friction and wear tests on a cast iron specimen under various corrosion atmospheres and verifies the variations of friction coefficient and friction surface. Additionally, the friction coefficient and friction status are predicted by using a neural network that learns the vibration and frequency spectrum data from an acceleration sensor. According to our conclusions, amplitude is distributed highly at high frequencies, and values of standard deviation and kurtosis are high when damage to the friction surface is serious. The accuracy rate of the friction coefficient predicted by the neural network is over 80% of the real measured value without NaCl, and application of the neural network is very effective for diagnosing the friction condition and damage to the cylinder liner.