This study focusses on the vibration control of linear large scale engineering structures, modelled as continuous system, with varying system parameters. Because of manufacturing limitations or/and measurement errors, system parameters need to be modelled as random variables. Here, system parameters are modelled as non-Gaussian random variables. Mathematically, continuous system is governed by partial differential equations and solved using approximation methods. High fidelity finite element model is the starting point of the analysis. Since numerical approximation involves large number of degrees-of-freedom, solving the system in real time is computationally expensive and application of control algorithm is cumbersome. In this study, a reduced order model is developed to reduce the state space dimension of the problem and further integrated with the control algorithm. Next, controller gain is obtained using linear quadratic regulator in reduced subspace which is used as a feedback to the actuators to produce the required control force for vibration control. A numerical example of flexible cantilever beam is solved to demonstrate the efficacy of the algorithm and probabilistic characterisation is carried out using Monte Carlo simulation. © 2020 The Society of Instrument and Control Engineers - SICE.