On the validity of the classical aspidal motion formula for tidal distortion

We check the validity of the widely used classical apsidal motion formula as a function of orbital parameters, stellar structure, and stellar rotation rate by comparing dynamical calculations of the periastron advance with the equilibrium tidal formula. We find that the classical formula gives very accurate results when the periods of the low-order quadrupole g, f- and p-modes are smaller than the periastron passage time by a factor of about 10 or more. However, when this condition is not satisfied, the difference between the classical formula and the exact result can be quite large, and even periastron recession can result. The largest difference arises when frequency of one of the low-order modes of the star is nearly resonant with an integer multiple of the orbital frequency minus twice the rotation rate of the star. The resonance of higher order g-modes (number of radial nodes greater than or similar to 4) with the orbit is very unlikely to cause significant deviation from the classical result because of their weak coupling to the tidal force and thus their small contribution to the apsidal motion. Resonances involving rotational modes of the star are also unlikely to make much contribution to the apsidal motion because of their small overlap with the tidal force, even though they have periods comparable to the periastron passage time. We apply our work to two famous binary systems (AS Cam and DI Her) that show abnormally small apsidal motion, and conclude that dynamical effects are unimportant for these systems, i.e., the equilibrium tide assumption is an excellent approximation.