To address the problem of unstable system operation caused by the jump of the target value of system operation parameters in the process of working condition switching

a steady-state optimization method of variable working condition operation parameters is proposed based on association rules. This method improves the original association rule mining strategy. The historical condition is regarded as one of the input conditions of association rule mining under variable working conditions and the steady-state operation parameters were optimized under the constraint of system stability. The quasi-steady-state operation conditions of the system under variable conditions were discussed. A chiller system of a shopping mall was chosen as the study object. Based on the division of typical working conditions

the Apriori algorithm was used to determine the relationship between the main operating parameters and performance indices under the quasi-steady operating conditions of chillers and the parameters were optimized. The simulation results showed that the comprehensive operation stability of the chiller increased by 50.4% and 62.7% in the transition season and summer

respectively. The energy consumption reduced by 14.48% and 16.5%in the transition season and summer

respectively

compared to the original operation mode.