PREDICTION OF STATE VARIABLES FOR AIR FILTERS

Method (100) for predicting a change (2a) of at least one state variable (2), which characterizes the service life and/or performance of at least one air filter (1), comprising the steps: • at least one value of at least one influencing variable (3), on which the change of the state variable (2) per unit time depends, is detected (110); • a time duration (4) for which the influencing variable (3) acts on the air filter (1) with this value is detected (120); • the at least one value of the at least one influencing variable (3) is supplied (130) to at least one model (5), which provides an output variable (6) (140) that is a measure of the contribution to the change of the state variable (2) per unit time caused by the at least one influencing variable (3); • from the output variable (6) and the time duration (4), the change (2a) of the state variable (2) is determined (150). [0002] Method (200) for training a trainable machine learning model (5) for use in method (100) with time derivatives (2c) of an actual time profile (2b) of the state variable (2) and an actual time profile (3a) of an influencing variable (3). [0003] Method (300) for identifying relevant influencing variables (3).